State Inject 'Any' types

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -1,72 +1,58 @@
 name: "\U0001F41B Bug Report"
-description: Report a bug in LangGraph. To report a security issue, please instead use the security option (below). For questions, please use the LangChain forum (below).
-labels: ["bug"]
-type: bug
+description: Report a bug in LangGraph. To report a security issue, please instead use the security option below. For questions, please use the GitHub Discussions.
+labels: ["02 Bug Report"]
 body:
   - type: markdown
     attributes:
-      value: |
-        Thank you for taking the time to file a bug report.
-
-        > **All contributions must be in English.** See the [language policy](https://docs.langchain.com/oss/python/contributing/overview#language-policy).
-
-        For usage questions, feature requests and general design questions, please use the [LangChain Forum](https://forum.langchain.com/).
-
-        Check these before submitting to see if your issue has already been reported, fixed or if there's another way to solve your problem:
-
-        * [Documentation](https://docs.langchain.com/oss/python/langgraph/overview),
-        * [API Reference Documentation](https://reference.langchain.com/python/),
-        * [LangChain ChatBot](https://chat.langchain.com/)
-        * [GitHub search](https://github.com/langchain-ai/langgraph),
-        * [LangChain Forum](https://forum.langchain.com/),
+      value: >
+        Thank you for taking the time to file a bug report. 
+        
+        Use this to report bugs in LangChain. 
+        
+        If you're not certain that your issue is due to a bug in LangChain, please use [GitHub Discussions](https://github.com/langchain-ai/langchain/discussions)
+        to ask for help with your issue.
+        
+        Relevant links to check before filing a bug report to see if your issue has already been reported, fixed or
+        if there's another way to solve your problem:
+        
+        [LangGraph documentation](https://langchain-ai.github.io/langgraph/).
+        [LangChain documentation with the integrated search](https://python.langchain.com/docs/get_started/introduction),
+        [GitHub search](https://github.com/langchain-ai/langgraph),
+        [LangChain Github Discussions](https://github.com/langchain-ai/langgraph/discussions),
+        [LangChain Github Issues](https://github.com/langchain-ai/langgraph/issues),
+        [LangChain ChatBot](https://chat.langchain.com/)
   - type: checkboxes
     id: checks
     attributes:
       label: Checked other resources
       description: Please confirm and check all the following options.
       options:
-        - label: This is a bug, not a usage question.
+        - label: I added a very descriptive title to this issue.
           required: true
-        - label: I added a clear and descriptive title that summarizes this issue.
+        - label: I searched the [LangGraph](https://langchain-ai.github.io/langgraph/)/LangChain documentation with the integrated search.
           required: true
         - label: I used the GitHub search to find a similar question and didn't find it.
           required: true
-        - label: I am sure that this is a bug in LangGraph rather than my code.
+        - label: I am sure that this is a bug in LangGraph/LangChain rather than my code.
           required: true
-        - label: The bug is not resolved by updating to the latest stable version of LangGraph (or the specific integration package).
+        - label: I am sure this is better as an issue [rather than a GitHub discussion](https://github.com/langchain-ai/langgraph/discussions/new/choose), since this is a LangGraph bug and not a design question.
           required: true
-        - label: This is not related to the langchain-community package.
-          required: true
-        - label: I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.
-          required: true
-  - type: textarea
-    id: related
-    validations:
-      required: false
-    attributes:
-      label: Related Issues / PRs
-      description: |
-        If this bug is related to any existing issues or pull requests, please link them here.
-      placeholder: |
-        * e.g. #123, #456
   - type: textarea
     id: reproduction
     validations:
       required: true
     attributes:
-      label: Reproduction Steps / Example Code (Python)
+      label: Example Code
       description: |
         Please add a self-contained, [minimal, reproducible, example](https://stackoverflow.com/help/minimal-reproducible-example) with your use case.
-
+        
         If a maintainer can copy it, run it, and see it right away, there's a much higher chance that you'll be able to get help.
+        
+        **Important!** 
+        
+        * Reduce your code to the minimum required to reproduce the issue if possible. This makes it much easier for others to help you.
+        * Avoid screenshots when possible, as they are hard to read and (more importantly) don't allow others to copy-and-paste your code.
 
-        **Important!**
-
-        * Avoid screenshots, as they are hard to read and (more importantly) don't allow others to copy-and-paste your code.
-        * Reduce your code to the minimum required to reproduce the issue if possible.
-
-        (This will be automatically formatted into code, so no need for backticks.)
-      render: python
       placeholder: |
         from langgraph.graph import StateGraph
 
@@ -75,13 +61,17 @@ body:
           
         chain = StateGraph(list)
         chain.invoke('Hello!')
+      render: python
   - type: textarea
+    id: error
+    validations:
+      required: false
     attributes:
       label: Error Message and Stack Trace (if applicable)
       description: |
-        If you are reporting an error, please copy and paste the full error message and
-        stack trace.
-        (This will be automatically formatted into code, so no need for backticks.)
+        If you are reporting an error, please include the full error message and stack trace.
+      placeholder: |
+        Exception + full stack trace
       render: shell
   - type: textarea
     id: description
@@ -102,19 +92,25 @@ body:
     attributes:
       label: System Info
       description: |
-        Please share your system info with us.
-
-        Run the following command in your terminal and paste the output here:
-
-        `python -m langchain_core.sys_info`
-
-        or if you have an existing python interpreter running:
-
-        ```python
-        from langchain_core import sys_info
-        sys_info.print_sys_info()
-        ```
-      placeholder: |
+        Please share your system info with us. 
+        
+        "pip freeze | grep langchain" 
+        platform (windows / linux / mac)
+        python version
+        
+        OR if you're on a recent version of langchain-core you can paste the output of:
+        
         python -m langchain_core.sys_info
+      placeholder: |
+        "pip freeze | grep langgraph"
+        platform
+        python version
+        
+        Alternatively, if you're on a recent version of langchain-core you can paste the output of:
+        
+        python -m langchain_core.sys_info
+        
+        These will only surface LangChain packages, don't forget to include any other relevant
+        packages you're using (if you're not sure what's relevant, you can paste the entire output of `pip freeze`).
     validations:
       required: true

.github/ISSUE_TEMPLATE/config.yml

@@ -1,15 +1,15 @@
 blank_issues_enabled: false
 version: 2.1
 contact_links:
-  - name: 💬 LangChain Forum
-    url: https://forum.langchain.com/
-    about: General community discussions and support
-  - name: 📚 LangGraph Documentation
-    url: https://docs.langchain.com/oss/python/langgraph/overview
-    about: View the official LangGraph documentation
-  - name: 📚 API Reference Documentation
-    url: https://reference.langchain.com/python/langgraph/
-    about: View the official LangGraph API reference documentation
-  - name: 📚 Documentation issue
-    url: https://github.com/langchain-ai/docs/issues/new?template=02-langgraph.yml
-    about: Report an issue related to the LangGraph documentation
+  - name: 🤔 Question or Problem
+    about: Ask a question or ask about a problem in GitHub Discussions.
+    url: https://github.com/langchain-ai/langgraph/discussions/categories/q-a
+  - name: Feature Request
+    url: https://github.com/langchain-ai/langgraph/discussions/categories/ideas
+    about: Suggest a feature or an idea
+  - name: Show and tell
+    about: Show what you built with LangChain
+    url: https://github.com/langchain-ai/langgraph/discussions/categories/show-and-tell
+  - name: Slack
+    url:  https://www.langchain.com/join-community
+    about: General community discussions

.github/ISSUE_TEMPLATE/documentation.yml

@@ -0,0 +1,19 @@
+name: Documentation
+description: Report an issue related to the LangGraph documentation.
+title: "DOC: <Please write a comprehensive title after the 'DOC: ' prefix>"
+labels: [03 - Documentation]
+
+body:
+- type: textarea
+  attributes: 
+    label: "Issue with current documentation:"
+    description: >
+      Please make sure to leave a reference to the document/code you're
+      referring to.
+
+- type: textarea
+  attributes:
+    label: "Idea or request for content:"
+    description: >
+      Please describe as clearly as possible what topics you think are missing
+      from the current documentation.

.github/ISSUE_TEMPLATE/privileged.yml

@@ -1,28 +1,25 @@
-name: "\U0001F512 Privileged"
-description: You are a LangGraph maintainer. If not, check the other options.
+name: 🔒 Privileged
+description: You are a LangChain maintainer, or was asked directly by a maintainer to create an issue here. If not, check the other options.
 body:
   - type: markdown
     attributes:
       value: |
-        > **All contributions must be in English.** See the [language policy](https://docs.langchain.com/oss/python/contributing/overview#language-policy).
-
-        If you are not a LangGraph maintainer, employee, or were not asked directly by a maintainer to create an issue, then please start the conversation on the [LangChain Forum](https://forum.langchain.com/) instead.
-
-        **Note:** Do not begin work on a PR unless explicitly assigned to this issue by a maintainer.
+        Thanks for your interest in LangChain! 🚀
+        
+        If you are not a LangChain maintainer or were not asked directly by a maintainer to create an issue, then please start the conversation in a [Question in GitHub Discussions](https://github.com/langchain-ai/langchain/discussions/categories/q-a) instead.
+        
+        You are a LangChain maintainer if you maintain any of the packages inside of the LangChain repository 
+        or are a regular contributor to LangChain with previous merged merged pull requests.
   - type: checkboxes
     id: privileged
     attributes:
       label: Privileged issue
       description: Confirm that you are allowed to create an issue here.
       options:
-        - label: I am a LangGraph maintainer.
+        - label: I am a LangChain maintainer, or was asked directly by a LangChain maintainer to create an issue here.
           required: true
   - type: textarea
     id: content
     attributes:
       label: Issue Content
       description: Add the content of the issue here.
-  - type: markdown
-    attributes:
-      value: |
-        Please do not begin work on a PR unless explicitly assigned to this issue by a maintainer.

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,40 +0,0 @@
-Fixes #
-
-<!-- Replace everything above this line with a 1-2 sentence description of your change. Keep the "Fixes #xx" keyword and update the issue number. -->
-
-Read the full contributing guidelines: https://docs.langchain.com/oss/python/contributing/overview
-
-> **All contributions must be in English.** See the [language policy](https://docs.langchain.com/oss/python/contributing/overview#language-policy).
-
-If you paste a large clearly AI generated description here your PR may be IGNORED or CLOSED!
-
-Thank you for contributing to LangGraph! Follow these steps to have your pull request considered as ready for review.
-
-1. PR title: Should follow the format: TYPE(SCOPE): DESCRIPTION
-
-    - feat(langgraph): add multi-tenant support
-  - Allowed TYPE and SCOPE values: https://github.com/langchain-ai/langgraph/blob/main/.github/workflows/pr_lint.yml#L19-L43
-
-2. PR description:
-
-  - Write 1-2 sentences summarizing the change.
-  - The `Fixes #xx` line at the top is **required** for external contributions — update the issue number and keep the keyword. This links your PR to the approved issue and auto-closes it on merge.
-  - If there are any breaking changes, please clearly describe them.
-  - If this PR depends on another PR being merged first, please include "Depends on #PR_NUMBER" in the description.
-
-3. Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified.
-
-  - We will not consider a PR unless these three are passing in CI.
-
-4. How did you verify your code works?
-
-Additional guidelines:
-
-  - All external PRs must link to an issue or discussion where a solution has been approved by a maintainer, and you must be assigned to that issue. PRs without prior approval will be closed.
-  - PRs should not touch more than one package unless absolutely necessary.
-  - Do not update the `uv.lock` files or add dependencies to `pyproject.toml` files (even optional ones) unless you have explicit permission to do so by a maintainer.
-
-## Social handles (optional)
-<!-- If you'd like a shoutout on release, add your socials below -->
-Twitter: @
-LinkedIn: https://linkedin.com/in/

.github/THREAT_MODEL.md

@@ -1,479 +0,0 @@
-# Threat Model: LangGraph
-
-> Generated: 2026-03-28 | Commit: 0ba22143 | Scope: Full monorepo (all libs/)
-
-> **Disclaimer:** This threat model is automatically generated to help developers and security researchers understand where trust is placed in this system and where boundaries exist. It is experimental, subject to change, and not an authoritative security reference — findings should be validated before acting on them. The analysis may be incomplete or contain inaccuracies. We welcome suggestions and corrections to improve this document.
-
-For vulnerability reporting, see the [GitHub Security Advisories](https://github.com/langchain-ai/langgraph/security/advisories) page.
-
-## Scope
-
-### In Scope
-
-- `libs/langgraph` — Core graph execution engine (Pregel, StateGraph, channels, functional API with `@entrypoint`/`@task`)
-- `libs/prebuilt` — High-level agent APIs (ToolNode, create_react_agent, ValidationNode, InjectedState/InjectedStore/ToolRuntime injection)
-- `libs/checkpoint` — Checkpoint serialization/deserialization (JsonPlusSerializer, EncryptedSerializer, BaseCache, stores, serde event hooks, SAFE_MSGPACK_TYPES allowlist)
-- `libs/checkpoint-postgres` — PostgreSQL checkpoint saver, key-value store, and vector search
-- `libs/checkpoint-sqlite` — SQLite checkpoint saver, key-value store, and vector search
-- `libs/cli` — CLI for Docker-based deployment (`langgraph up/build/dev/new`), WebhookUrlPolicy
-- `libs/sdk-py` — Python SDK client for LangGraph Server API (HttpClient, Auth system, Encryption handlers)
-
-### Out of Scope
-
-- `libs/sdk-js` — Moved to external `langchain-ai/langgraphjs` repository; no source in this repo
-- `libs/checkpoint-conformance` — Conformance test suite only; not shipped code
-- LangGraph Server / `langgraph-api` — Closed-source server runtime; not in this repo
-- LangChain Core (`langchain-core`) — Upstream dependency; separate threat model
-- User application code — Tools, prompts, model selection, deployment infrastructure
-- LLM provider behavior — Model output content and safety
-- LangSmith platform — Observability/tracing backend
-- Tests, benchmarks, documentation — Not shipped code
-
-### Assumptions
-
-1. The project is used as a library/framework — users control their own application code, model selection, and deployment.
-2. Checkpoint storage backends (databases) are deployed with proper access controls by the user.
-3. LLM providers return well-formed responses per their documented API contracts.
-4. The `langgraph.json` configuration file is developer-controlled and not user-supplied at runtime.
-5. The CLI runs in a developer environment with Docker access.
-6. The SDK connects to trusted LangGraph Server endpoints chosen by the user.
-7. SDK Encryption handlers are developer-authored server-side code with application-level trust.
-
----
-
-## System Overview
-
-LangGraph is an open-source Python framework for building stateful, multi-actor AI agent applications. It provides a graph-based execution model (Bulk Synchronous Parallel via the Pregel engine) where user-defined nodes process shared state through typed channels. The framework supports two authoring APIs: the declarative StateGraph API and the functional API (`@entrypoint`/`@task` decorators). It includes checkpointing (persistence of graph state to databases), tool execution (dispatching LLM-generated tool calls with runtime injection of state/store/context), remote graph composition (calling LangGraph Server APIs), Docker-based deployment via a CLI, and a beta SDK encryption framework for custom at-rest encryption handlers.
-
-### Architecture Diagram
-
-```
-+---------------------------------------------------------------------------+
-|                        User Application                                    |
-|                                                                            |
-|  +-----------------------------------------------+                        |
-|  |  User Application Code                         |                       |
-|  |  (graph nodes, tools; StateGraph builder API   |                       |
-|  |   and functional API @entrypoint/@task both    |                       |
-|  |   compile to the same Pregel execution engine) |                       |
-|  +------------------------+----------------------+                        |
-|                           |                                                |
-|              +------------v-----------+                                   |
-|              |  StateGraph / Pregel    |                                   |
-|              |  (core execution engine)|                                   |
-|              +------+----------+------+                                   |
-|                     |          |                                           |
-|              InjectedState  +--v---------+                                |
-|              InjectedStore  |  ToolNode  |                                |
-|              ToolRuntime    |  (opt-in)  |                                |
-|                             +------------+                                |
-|                       |                                                    |
-| - - - - - - - - - - - | - - - - TB1: User/Framework API - - - - - - - -  |
-|                       |                                                    |
-|                 +-----v------+   +--------------+                         |
-|                 | Checkpoint |   | RemoteGraph   |                         |
-|                 | Serializer |   | (SDK client)  |                         |
-|                 |(jsonplus)  |   +------+--------+                         |
-|                 +-----+------+          |                                  |
-|                       |                 |                                   |
-| - - - - - - - - - - - | - - - - - - - -|- - TB2: Storage/Network - - - -  |
-|                       v                 v                                   |
-|               +--------------+  +--------------+                          |
-|               |  PostgreSQL  |  |  LangGraph   |                          |
-|               |  / SQLite    |  |  Server API  |                          |
-|               +--------------+  +--------------+                          |
-|                                                                            |
-|  +----------+                   +--------------+                          |
-|  |   CLI    |------------------>|   Docker     |                          |
-|  |(langgraph|   TB4: Config    |   Engine     |                          |
-|  | up/build)|                   +--------------+                          |
-|  +----------+                                                             |
-|                                                                            |
-|  +--------------------+                                                   |
-|  | SDK Encryption     |  TB5: Developer-authored handlers                 |
-|  | Handlers (beta)    |  (server-side execution in langgraph-api)         |
-|  +--------------------+                                                   |
-+---------------------------------------------------------------------------+
-```
-
----
-
-## Components
-
-| ID | Component | Description | Trust Level | Default? | Entry Points |
-|----|-----------|-------------|-------------|----------|--------------|
-| C1 | StateGraph / Pregel | Core graph builder and execution engine with v1/v2 output, durability modes (sync/async/exit), interrupt_before/interrupt_after | framework-controlled | Yes | `StateGraph.add_node()`, `StateGraph.compile()`, `Pregel.invoke()`, `Pregel.stream()` |
-| C2 | JsonPlusSerializer | Checkpoint serialization/deserialization with msgpack, JSON, and pickle codecs; 47-entry SAFE_MSGPACK_TYPES allowlist | framework-controlled | Yes | `loads_typed()`, `dumps_typed()`, `_create_msgpack_ext_hook()`, `_reviver()` |
-| C3 | ToolNode | Dispatches LLM-generated tool calls to registered BaseTool instances; supports InjectedState/InjectedStore/ToolRuntime injection into tools | framework-controlled | No (explicit opt-in required) | `ToolNode._func()`, `_run_one()`, `_execute_tool_sync()`, `_validate_tool_call()`, `_inject_tool_args()` |
-| C4 | RemoteGraph | Client for remote LangGraph Server API; implements PregelProtocol | framework-controlled | No (opt-in) | `RemoteGraph.stream()`, `RemoteGraph.invoke()`, `RemoteGraph.get_state()` |
-| C5 | PostgresSaver / PostgresStore | PostgreSQL checkpoint saver, key-value store, and vector search | framework-controlled | No (opt-in) | `from_conn_string()`, `put()`, `get_tuple()`, `search()` |
-| C6 | SqliteSaver / SqliteStore | SQLite checkpoint saver, key-value store with JSON path filtering | framework-controlled | No (opt-in) | `from_conn_string()`, `put()`, `get_tuple()`, `search()` |
-| C7 | EncryptedSerializer | AES-EAX authenticated encryption wrapper for checkpoint data | framework-controlled | No (opt-in) | `from_pycryptodome_aes()`, `loads_typed()`, `dumps_typed()` |
-| C8 | CLI (langgraph_cli) | Docker-based build and deployment tooling; config schema includes WebhookUrlPolicy for SSRF protection | framework-controlled | No (separate install) | `langgraph up`, `langgraph build`, `langgraph dev`, `langgraph new` |
-| C9 | SDK Client (langgraph_sdk) | HTTP client for LangGraph Server API with SSE streaming and reconnection | framework-controlled | Yes | `get_client()`, `get_sync_client()`, `HttpClient.request_reconnect()`, `HttpClient.stream()` |
-| C10 | User-Registered Tools | BaseTool instances provided by users; may use InjectedState/InjectedStore/ToolRuntime annotations | user-controlled | N/A | Tool `invoke()` / `ainvoke()` methods |
-| C11 | User-Registered Nodes | Arbitrary callables added via `add_node()` or `@task`/`@entrypoint` | user-controlled | N/A | Node function signatures |
-| C12 | Checkpoint Storage | PostgreSQL or SQLite databases storing serialized graph state | external | N/A | Database connection interface |
-| C13 | Functional API | `@entrypoint`/`@task` decorators for function-based workflow authoring with retry/cache policies | framework-controlled | Yes | `entrypoint.__call__()`, `task()`, `_TaskFunction.__call__()` (`libs/langgraph/langgraph/func/__init__.py`) |
-| C14 | BaseCache | Cache layer for task results with JsonPlusSerializer (pickle_fallback=False) | framework-controlled | No (opt-in, requires checkpointer) | `get()`, `set()`, `clear()` (`libs/checkpoint/langgraph/cache/base/__init__.py`) |
-| C15 | Serde Event Hooks | Monitoring system for serialization/deserialization events (msgpack_blocked, msgpack_unregistered_allowed, msgpack_method_blocked) | framework-controlled | Yes | `register_serde_event_listener()`, `emit_serde_event()` (`libs/checkpoint/langgraph/checkpoint/serde/event_hooks.py`) |
-| C16 | Auth System (SDK) | Custom authentication/authorization handler framework | framework-controlled | No (opt-in) | `Auth.authenticate()`, `Auth.on()` handler registration (`libs/sdk-py/langgraph_sdk/auth/__init__.py`) |
-| C17 | SDK Encryption Handlers (beta) | Custom at-rest encryption/decryption framework; supports blob and JSON handlers with per-model/field context; server-side execution | framework-controlled | No (opt-in, beta) | `Encryption.encrypt.blob()`, `Encryption.encrypt.json()`, `Encryption.decrypt.blob()`, `Encryption.decrypt.json()`, `Encryption.context()` (`libs/sdk-py/langgraph_sdk/encryption/__init__.py`) |
-
----
-
-## Data Classification
-
-| ID | PII Category | Specific Fields | Sensitivity | Storage Location(s) | Encrypted at Rest | Retention | Regulatory |
-|----|-------------|----------------|-------------|---------------------|-------------------|-----------|------------|
-| DC1 | API credentials | `x-api-key` header, `LANGGRAPH_API_KEY`, `LANGSMITH_API_KEY`, `LANGCHAIN_API_KEY` env vars | Critical | Environment variables, HTTP headers in transit | N/A (in-memory) | Session lifetime | All — breach trigger |
-| DC2 | Encryption keys | `LANGGRAPH_AES_KEY` env var, `key` parameter to `from_pycryptodome_aes()` | Critical | Environment variable, in-memory | N/A | Application lifetime | All — breach trigger |
-| DC3 | Serialized graph state | Checkpoint data in `checkpoints` and `writes` tables (msgpack/JSON/pickle bytes) | High | PostgreSQL (BYTEA), SQLite (BLOB) | Optional via EncryptedSerializer or SDK Encryption Handlers | Unbounded (no default TTL) | GDPR if state contains PII |
-| DC4 | Store key-value data | User-stored items in `store` tables via BaseStore | High | PostgreSQL, SQLite | No (plaintext JSON); optional via SDK Encryption Handlers | Configurable TTL, default unbounded | GDPR if contains PII |
-| DC5 | Checkpoint metadata | `thread_id`, `checkpoint_ns`, `run_id`, `step`, `source` | Medium | PostgreSQL, SQLite (metadata JSONB/JSON column) | No | Same as DC3 | Minimal |
-| DC6 | Agent conversation history | LangChain messages (HumanMessage, AIMessage, ToolMessage) serialized in checkpoint state | High | PostgreSQL, SQLite (within DC3 checkpoint bytes) | Only if DC3 encrypted | Unbounded | GDPR, CCPA if contains user PII |
-| DC7 | Connection strings | PostgreSQL URIs, SQLite file paths passed to `from_conn_string()` | Critical | Application code, environment variables | N/A (in-memory) | Application lifetime | All — may contain credentials |
-| DC8 | Vector embeddings | Document embeddings in `store_vectors` table | Low | PostgreSQL (pgvector), SQLite (vec extension) | No | Same as DC4 | Minimal |
-| DC9 | SDK Encryption context metadata | `EncryptionContext.metadata` dict passed to encryption handlers | Medium | In-memory per request; persisted with encrypted data | N/A (context, not payload) | Request lifetime + persistence alongside encrypted data | Depends on content |
-
-### Data Classification Details
-
-#### DC1: API Credentials
-
-- **Fields**: `x-api-key` HTTP header, `LANGGRAPH_API_KEY`/`LANGSMITH_API_KEY`/`LANGCHAIN_API_KEY` environment variables
-- **Storage**: Environment variables (loaded at runtime), HTTP request headers (in transit)
-- **Access**: SDK client code (`libs/sdk-py/langgraph_sdk/_shared/utilities.py:_get_api_key`), any process with env var access
-- **Encryption**: TLS in transit (if HTTPS); no at-rest encryption for env vars
-- **Retention**: Session/process lifetime
-- **Logging exposure**: API key stripped of quotes but could appear in debug logs if HTTP headers are logged. `RESERVED_HEADERS` prevents user override of `x-api-key` but doesn't prevent logging.
-- **Cross-border**: Travels with every HTTP request to the LangGraph Server
-- **Gaps**: SDK `request_reconnect()` and `stream()` forward `x-api-key` header to server-controlled `Location` redirect URLs without URL validation (see T9)
-
-#### DC2: Encryption Keys
-
-- **Fields**: `LANGGRAPH_AES_KEY` environment variable, `key` bytes parameter
-- **Storage**: Environment variable or direct bytes in application code
-- **Access**: `libs/checkpoint/langgraph/checkpoint/serde/encrypted.py:from_pycryptodome_aes`
-- **Encryption**: N/A — this IS the encryption key
-- **Retention**: Application lifetime
-- **Logging exposure**: Not logged by framework code
-- **Gaps**: Key loaded from env var as UTF-8 string limits entropy to ~6.57 bits/byte (see T7). Cipher name validated with `assert` which is stripped by `python -O` (see T8).
-
-#### DC3: Serialized Graph State
-
-- **Fields**: All channel values serialized via `JsonPlusSerializer.dumps_typed()` — includes complete agent state, conversation history, tool call results, and any user-defined state
-- **Storage**: PostgreSQL `checkpoints.checkpoint` (BYTEA), `writes.blob` (BYTEA); SQLite `checkpoints.checkpoint` (BLOB), `writes.blob` (BLOB)
-- **Access**: Any code with database credentials; `BaseCheckpointSaver.get_tuple()` / `put()`
-- **Encryption**: Optional via `EncryptedSerializer` wrapping (AES-EAX) or SDK Encryption Handlers (beta, server-side). Not encrypted by default.
-- **Retention**: Unbounded by default. Optional TTL via `CheckpointerConfig.ttl` (server-side config)
-- **Logging exposure**: Serde event hooks emit module/class names of deserialized types but not the data itself
-- **Gaps**: Default unbounded retention of potentially PII-containing state. Unencrypted by default. EncryptedSerializer has fallback that accepts unencrypted data (see T10).
-
-#### DC6: Agent Conversation History
-
-- **Fields**: `HumanMessage.content`, `AIMessage.content`, `ToolMessage.content`, `AIMessage.tool_calls` — embedded within DC3 checkpoint bytes
-- **Storage**: Same as DC3 (within serialized checkpoint data)
-- **Access**: Same as DC3
-- **Encryption**: Only if DC3 is encrypted via EncryptedSerializer or SDK Encryption Handlers
-- **Retention**: Same as DC3 (unbounded default)
-- **Gaps**: Conversation content may include user PII, PHI, or sensitive business data. No field-level encryption or redaction. Retention inherits from DC3 with no conversation-specific policy.
-
-#### DC9: SDK Encryption Context Metadata
-
-- **Fields**: `EncryptionContext.model` (str), `EncryptionContext.field` (str), `EncryptionContext.metadata` (dict)
-- **Storage**: In-memory during request processing; persisted alongside encrypted data for later decryption
-- **Access**: Encryption/decryption handlers (developer-authored), ContextHandler (receives authenticated BaseUser)
-- **Encryption**: N/A — this is context for encryption, not encrypted data itself
-- **Retention**: Persisted with encrypted data indefinitely
-- **Logging exposure**: Not logged by SDK code
-- **Gaps**: `metadata` is a mutable dict — whether cross-request isolation is enforced depends on server-side implementation (langgraph-api, out of scope). ContextHandler registration at `libs/sdk-py/langgraph_sdk/encryption/__init__.py:Encryption.context` does not call `_validate_handler` (missing async/param-count validation, unlike all other handler types).
-
----
-
-## Trust Boundaries
-
-| ID | Boundary | Description | Controls (Inside) | Does NOT Control (Outside) |
-|----|----------|-------------|-------------------|---------------------------|
-| TB1 | User/Framework API | Where user-provided code and configuration enters the framework | Graph execution logic, channel semantics, default configs, validation of graph structure, tool injection merge order (system values overwrite LLM values) | User node implementations, tool behavior, model selection, prompt construction, state schema design |
-| TB2 | Checkpoint Storage | Where serialized data enters/leaves the persistence layer | Serialization format, allowlists for deserialization (47 safe types, 1 safe method), encryption (if configured), serde event hooks | Database access controls, who can write to the checkpoint tables, storage infrastructure security |
-| TB3 | Remote API | Where data crosses the network to/from LangGraph Server | Outbound config sanitization (`_sanitize_config`), SDK HTTP transport, API key handling, `RESERVED_HEADERS` | Remote server behavior, response content integrity, network security (TLS), server-provided Location redirect targets |
-| TB4 | CLI Config/Docker | Where developer config drives container image generation | Dockerfile template structure, config schema validation (including WebhookUrlPolicy), list-based subprocess args, build command content validation | `langgraph.json` file content, Docker daemon security, host filesystem |
-| TB5 | SDK Encryption Handlers | Where developer-authored encryption handlers process sensitive data | Handler signature validation (async, 2-param for encrypt/decrypt), duplicate registration prevention, EncryptionContext construction | Handler implementation correctness, key management, actual encrypt/decrypt behavior, server-side execution environment |
-
-### Boundary Details
-
-#### TB1: User/Framework API
-
-- **Inside**: Graph compilation validates structure (`libs/langgraph/langgraph/pregel/_validate.py:validate_graph`). Channel types enforce update semantics (`libs/langgraph/langgraph/channels/base.py:BaseChannel.update`). Functional API validates entrypoint has at least one parameter (`libs/langgraph/langgraph/func/__init__.py:entrypoint`). Sensitive config keys filtered from metadata propagation — keys containing "key", "token", "secret", "password", "auth" are excluded (`libs/langgraph/langgraph/_internal/_config.py:_exclude_as_metadata`). Tool injection merge order ensures system-injected values (InjectedState/InjectedStore/ToolRuntime) overwrite any LLM-supplied collisions (`libs/prebuilt/langgraph/prebuilt/tool_node.py:ToolNode._inject_tool_args` line 1380). Injected parameter names hidden from LLM tool schema via `tool_call_schema` filtering.
-- **Outside**: What user nodes do, what tools return, what LLMs generate, how users handle output.
-- **Crossing mechanism**: Python function calls — `add_node(callable)`, `add_edge()`, `compile(checkpointer=...)`, `@entrypoint`, `@task`.
-
-#### TB2: Checkpoint Storage
-
-- **Inside**: `JsonPlusSerializer` controls serialization format (`libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py:JsonPlusSerializer`). Msgpack type allowlist (`libs/checkpoint/langgraph/checkpoint/serde/_msgpack.py:SAFE_MSGPACK_TYPES` — 47 safe types including stdlib, langchain_core messages, and langgraph types). Msgpack method allowlist (`libs/checkpoint/langgraph/checkpoint/serde/_msgpack.py:SAFE_MSGPACK_METHODS` — 1 safe method: `datetime.datetime.fromisoformat`). JSON module allowlist (`libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py:_check_allowed_json_modules`). Serde event hooks for monitoring (`libs/checkpoint/langgraph/checkpoint/serde/event_hooks.py:emit_serde_event`). Optional `EncryptedSerializer` wrapping (`libs/checkpoint/langgraph/checkpoint/serde/encrypted.py:EncryptedSerializer`). SQLite filter key regex validation (`libs/checkpoint-sqlite/langgraph/checkpoint/sqlite/utils.py:_validate_filter_key`). Parameterized SQL queries in both Postgres and SQLite backends.
-- **Outside**: Database access controls, who can read/write checkpoint tables, storage backend integrity.
-- **Crossing mechanism**: Database read/write operations — serialized bytes stored as BYTEA (Postgres) or BLOB (SQLite).
-
-#### TB3: Remote API
-
-- **Inside**: `_sanitize_config()` strips non-primitive values and drops checkpoint-internal keys from outbound config (`libs/langgraph/langgraph/pregel/remote.py:_sanitize_config`). SDK handles API key from env vars (`libs/sdk-py/langgraph_sdk/_shared/utilities.py:_get_api_key`). `RESERVED_HEADERS` prevents user override of `x-api-key` (`libs/sdk-py/langgraph_sdk/_shared/utilities.py:RESERVED_HEADERS`).
-- **Outside**: Remote server response content, network integrity, whether the server is legitimate, server-provided Location redirect targets.
-- **Crossing mechanism**: HTTPS requests via `httpx` through `langgraph_sdk`.
-
-#### TB4: CLI Config/Docker
-
-- **Inside**: Config file parsed as JSON (`libs/cli/langgraph_cli/config.py:validate_config_file`). Docker subprocess invoked with list-based args via `asyncio.create_subprocess_exec`, not `shell=True` (`libs/cli/langgraph_cli/exec.py:subp_exec`). Template downloads from hardcoded GitHub URLs (`libs/cli/langgraph_cli/templates.py`). Config schema validation covers store, auth, encryption, http, webhooks, checkpointer, and ui sections (`libs/cli/langgraph_cli/schemas.py`). Build command content validation blocks shell metacharacters (`libs/cli/langgraph_cli/config.py:has_disallowed_build_command_content`). WebhookUrlPolicy (`libs/cli/langgraph_cli/schemas.py:WebhookUrlPolicy`) supports `require_https`, `allowed_domains`, `allowed_ports`, `max_url_length`, `disable_loopback` for SSRF protection.
-- **Outside**: Content of `langgraph.json`, Docker daemon behavior, filesystem permissions.
-- **Crossing mechanism**: JSON file read, subprocess execution, ZIP download/extraction.
-
-#### TB5: SDK Encryption Handlers
-
-- **Inside**: Handler signature validation — must be async, must accept exactly 2 positional params (`libs/sdk-py/langgraph_sdk/encryption/__init__.py:_validate_handler`). Duplicate handler registration prevention (`DuplicateHandlerError`). `EncryptionContext` construction with model/field/metadata (`libs/sdk-py/langgraph_sdk/encryption/types.py:EncryptionContext`). JSON key preservation constraint documented (enforced server-side).
-- **Outside**: Handler implementation correctness, key management strategy, actual encryption/decryption logic, server-side execution in langgraph-api.
-- **Crossing mechanism**: Python decorator registration at import time; server-side invocation at runtime.
-
----
-
-## Data Flows
-
-| ID | Source | Destination | Data Type | Classification | Crosses Boundary | Protocol |
-|----|--------|-------------|-----------|----------------|------------------|----------|
-| DF1 | C12 (Checkpoint Storage) | C2 (JsonPlusSerializer) | Serialized checkpoint bytes (msgpack/JSON/pickle) | DC3 | TB2 | Database read |
-| DF2 | C2 (JsonPlusSerializer) | C1 (Pregel) | Deserialized Python objects (channel state) | DC3, DC6 | TB2 | Function call |
-| DF3 | LLM (external) | C3 (ToolNode) | Tool call arguments (JSON strings in AIMessage) | — | TB1 | Function call (via langchain-core) |
-| DF4 | C3 (ToolNode) | C10 (User Tools) | Parsed argument dicts merged with injected state/store/runtime | — | TB1 | `tool.invoke(call_args)` |
-| DF5 | C4 (RemoteGraph) | C1 (Pregel) | Stream chunks (JSON-deserialized dicts) | — | TB3 | HTTPS / SSE |
-| DF6 | `langgraph.json` | C8 (CLI) | Config dict (graphs, env, store, auth, encryption, http, webhooks, checkpointer, ui) | — | TB4 | `json.load()` |
-| DF7 | C8 (CLI) | Docker | Dockerfile content with embedded ENV values | — | TB4 | `asyncio.create_subprocess_exec` |
-| DF8 | C11 (User Nodes) | C1 (Pregel) | State updates (arbitrary Python objects) | — | TB1 | Channel write |
-| DF9 | C9 (SDK Client) | C4 (RemoteGraph) | API responses (JSON) | — | TB3 | HTTPS |
-| DF10 | User config | C7 (EncryptedSerializer) | AES key from LANGGRAPH_AES_KEY env var | DC2 | TB2 | `os.getenv()` |
-| DF11 | C12 (Checkpoint Storage) | C14 (BaseCache) | Cached task results via JsonPlusSerializer | DC3 | TB2 | Database read |
-| DF12 | LangGraph Server | C9 (SDK Client) | HTTP responses with Location header | DC1 | TB3 | HTTP redirect |
-| DF13 | C9 (SDK Client) | Redirect target | Request headers including x-api-key | DC1 | TB3 | HTTPS |
-| DF14 | C1 (Pregel state) | C3 (ToolNode) | InjectedState/InjectedStore/ToolRuntime values for tool injection | DC3, DC4 | TB1 | Function call (dict merge) |
-| DF15 | Developer code | C17 (SDK Encryption Handlers) | Encryption/decryption handler functions and context handler | — | TB5 | Python decorator registration |
-
-### Flow Details
-
-#### DF1: Checkpoint Storage -> JsonPlusSerializer
-
-- **Data**: Serialized graph state as `(type_tag, bytes)` tuples. Type tags include `"msgpack"`, `"json"`, `"pickle"`, `"bytes"`, `"null"`. When encrypted: `"msgpack+aes"`, `"json+aes"`.
-- **Validation**: Type tag dispatches to codec. Msgpack: `_create_msgpack_ext_hook` with allowlist check — `SAFE_MSGPACK_TYPES` (47 entries) always checked first, then `allowed_modules` determines behavior for unregistered types (`libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py:_create_msgpack_ext_hook`). JSON: `_reviver` with `lc:2` module allowlist. Pickle: **no restrictions** (`pickle.loads(data_)` if `pickle_fallback=True`, `libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py:JsonPlusSerializer.loads_typed`). The proposed `secure_pickle.py` with `RestrictedUnpickler` was documented in `SECURITY_FIX_SUMMARY.md` but never merged.
-- **Trust assumption**: Checkpoint storage is access-controlled. An attacker with write access to the database can craft malicious checkpoint data.
-
-#### DF3: LLM -> ToolNode
-
-- **Data**: Tool call name and arguments from LLM-generated `AIMessage.tool_calls`.
-- **Validation**: Tool name checked against registered `tools_by_name` dict — unknown names return error `ToolMessage` (`libs/prebuilt/langgraph/prebuilt/tool_node.py:ToolNode._validate_tool_call`). Argument values validated only by the target tool's Pydantic schema.
-- **Trust assumption**: LLM output is treated as untrusted for tool name routing but argument values pass through to tools without ToolNode-level sanitization.
-
-#### DF4: ToolNode -> User Tools (with Injection)
-
-- **Data**: Parsed argument dicts from LLM, merged with system-injected InjectedState/InjectedStore/ToolRuntime values.
-- **Validation**: Four-layer defense: (1) Injected parameter names hidden from LLM via `tool_call_schema` filtering. (2) Dict merge `{**llm_args, **injected_args}` places system values last — system always wins on collision (`libs/prebuilt/langgraph/prebuilt/tool_node.py:ToolNode._inject_tool_args` line 1380). (3) Pydantic `model_validate` with default `extra="ignore"` drops unknown keys. (4) Output construction only includes declared model fields.
-- **Trust assumption**: LLM-provided arguments cannot override system-injected values due to merge order.
-
-#### DF5: RemoteGraph -> Pregel
-
-- **Data**: Stream event chunks containing dicts for `Interrupt`, `Command`, state snapshots.
-- **Validation**: **None** on inbound data. `Interrupt(**i)` uses dict-splatting with no schema check (`libs/langgraph/langgraph/pregel/remote.py:RemoteGraph.stream`). `Command(**chunk.data)` uses dict-splatting for parent commands.
-- **Trust assumption**: Remote server is trusted. A compromised or malicious server can inject arbitrary field values.
-
-#### DF6: langgraph.json -> CLI
-
-- **Data**: JSON config including `graphs`, `env`, `store`, `auth`, `encryption`, `http`, `webhooks`, `checkpointer`, `ui`, `ui_config` sections.
-- **Validation**: Schema validation in `validate_config_file()` (`libs/cli/langgraph_cli/config.py:validate_config_file`). Config values embedded in Dockerfile via `json.dumps()` in single-quoted `ENV` lines (`libs/cli/langgraph_cli/config.py:python_config_to_docker`). Build command content validation (`libs/cli/langgraph_cli/config.py:has_disallowed_build_command_content`) blocks shell metacharacters.
-- **Trust assumption**: `langgraph.json` is developer-authored. Single quotes in config values could break Dockerfile `ENV` syntax.
-
-#### DF11: Checkpoint Storage -> BaseCache
-
-- **Data**: Cached task results stored via `BaseCache.set()` and retrieved via `BaseCache.get()`.
-- **Validation**: Uses `JsonPlusSerializer(pickle_fallback=False)` by default (`libs/checkpoint/langgraph/cache/base/__init__.py:BaseCache`). Subject to same msgpack deserialization behavior as DF1 (allowed_modules defaults based on `LANGGRAPH_STRICT_MSGPACK`).
-- **Trust assumption**: Cache storage has same access controls as checkpoint storage.
-
-#### DF12-13: Server -> SDK -> Redirect Target (API Key Leak)
-
-- **Data**: Server provides `Location` header in HTTP response. SDK follows the redirect and sends all original request headers (including `x-api-key`) to the target URL.
-- **Validation**: **None** on Location URL. No allowlist, no same-origin check, no header stripping on cross-origin redirect.
-- **Trust assumption**: The LangGraph Server is trusted to not redirect to malicious URLs. Violated if server is compromised.
-
-#### DF14: Pregel State -> ToolNode (Runtime Injection)
-
-- **Data**: Graph state dict (InjectedState), BaseStore instance (InjectedStore), ToolRuntime object (containing state, config, store, context, stream_writer, tool_call_id).
-- **Validation**: Injection targets determined by tool type annotations at compile time. Injected values overwrite any LLM-provided values with matching keys (safe merge order). Pydantic validation on tool input drops extra keys not in the tool's declared schema.
-- **Trust assumption**: System-injected values are trusted; LLM-provided values cannot interfere due to merge order guarantees.
-
-#### DF15: Developer Code -> SDK Encryption Handlers
-
-- **Data**: Async Python callables registered via decorators for blob/JSON encryption/decryption and context derivation.
-- **Validation**: `_validate_handler` checks async-ness and 2-param signature for encrypt/decrypt handlers. `DuplicateHandlerError` prevents double registration. **Gap**: `Encryption.context()` method does NOT call `_validate_handler` — a sync function or wrong param count passes registration and fails only at server-side invocation (`libs/sdk-py/langgraph_sdk/encryption/__init__.py:Encryption.context`).
-- **Trust assumption**: Handler authors are application developers with server-level trust.
-
----
-
-## Threats
-
-| ID | Data Flow | Classification | Threat | Boundary | Severity | Validation | Code Reference |
-|----|-----------|----------------|--------|----------|----------|------------|----------------|
-| T1 | DF1, DF11 | DC3 | Arbitrary code execution via msgpack deserialization when strict mode is OFF (default) | TB2 | High | Verified | `libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py:_create_msgpack_ext_hook` |
-| T2 | DF1 | DC3 | Arbitrary code execution via `pickle.loads` when `pickle_fallback=True` | TB2 | High | Verified | `libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py:JsonPlusSerializer.loads_typed` |
-| T3 | DF1 | DC3 | Arbitrary module import/execution via JSON `lc:2` constructor when `allowed_json_modules=True` | TB2 | High | Verified | `libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py:JsonPlusSerializer._revive_lc2` |
-| T4 | DF5 | — | Unvalidated dict-splatting from remote API into `Interrupt`/`Command` objects | TB3 | Medium | Likely | `libs/langgraph/langgraph/pregel/remote.py:RemoteGraph.stream` |
-| T5 | DF6, DF7 | — | Dockerfile ENV injection via single-quote in `langgraph.json` config values | TB4 | Low | Likely | `libs/cli/langgraph_cli/config.py:python_config_to_docker` |
-| T6 | DF7 | — | ZIP slip in `langgraph new` template extraction | TB4 | Low | Unverified | `libs/cli/langgraph_cli/templates.py:_download_repo_with_requests` |
-| T7 | DF10 | DC2 | AES key entropy limited to printable characters via env var string encoding | TB2 | Info | — | `libs/checkpoint/langgraph/checkpoint/serde/encrypted.py:EncryptedSerializer.from_pycryptodome_aes` |
-| T8 | DF10 | DC2 | EncryptedSerializer cipher name check uses `assert` (stripped with `python -O`) | TB2 | Low | Verified | `libs/checkpoint/langgraph/checkpoint/serde/encrypted.py:PycryptodomeAesCipher.decrypt` |
-| T9 | DF12, DF13 | DC1 | SDK API key leak via server-controlled Location redirect to attacker-controlled URL | TB3 | Medium | Verified | `libs/sdk-py/langgraph_sdk/_async/http.py:HttpClient.request_reconnect`, `libs/sdk-py/langgraph_sdk/_async/http.py:HttpClient.stream` |
-| T10 | DF1 | DC3 | EncryptedSerializer silently accepts unencrypted data — attacker bypasses encryption by writing plain type tags | TB2 | Medium | Verified | `libs/checkpoint/langgraph/checkpoint/serde/encrypted.py:EncryptedSerializer.loads_typed` |
-| T11 | DF1, DF11 | DC3, DC6 | Unbounded retention of checkpoint data containing PII/conversation history | TB2 | Medium | — | `libs/checkpoint/langgraph/checkpoint/base/__init__.py:BaseCheckpointSaver` |
-
-### Threat Details
-
-#### T1: Msgpack Deserialization RCE (Default Config)
-
-- **Flow**: DF1 (Checkpoint Storage -> JsonPlusSerializer), DF11 (Checkpoint Storage -> BaseCache)
-- **Description**: When `LANGGRAPH_STRICT_MSGPACK` is not set (the default), the msgpack `_create_msgpack_ext_hook` allows **any** `(module, class)` pair stored in checkpoint data to be imported via `importlib.import_module` and instantiated with attacker-controlled arguments. The `SAFE_MSGPACK_TYPES` allowlist (47 entries) is checked first, but unregistered types are logged as warnings and allowed through when `allowed_modules=True` (the default when strict mode is off). Seven EXT codes are processed: `EXT_CONSTRUCTOR_SINGLE_ARG` (0), `EXT_CONSTRUCTOR_POS_ARGS` (1), `EXT_CONSTRUCTOR_KW_ARGS` (2), `EXT_METHOD_SINGLE_ARG` (3), `EXT_PYDANTIC_V1` (4), `EXT_PYDANTIC_V2` (5), `EXT_NUMPY_ARRAY` (6). The `BaseCache` component uses `JsonPlusSerializer(pickle_fallback=False)` but inherits the same msgpack `allowed_modules` default behavior. The proposed `RestrictedUnpickler` (`secure_pickle.py`) documented in `SECURITY_FIX_SUMMARY.md` was never merged — pickle remains unrestricted when enabled.
-- **Preconditions**: Attacker must have write access to the checkpoint database (PostgreSQL or SQLite). This requires compromised database credentials or a co-located attacker.
-
-#### T2: Pickle Deserialization RCE
-
-- **Flow**: DF1 (Checkpoint Storage -> JsonPlusSerializer)
-- **Description**: When `pickle_fallback=True` is explicitly passed to `JsonPlusSerializer`, checkpoint data with type tag `"pickle"` is deserialized via `pickle.loads()` with zero restrictions (`libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py:JsonPlusSerializer.loads_typed`).
-- **Preconditions**: (1) Application or checkpointer explicitly enables `pickle_fallback=True`. (2) Attacker writes `("pickle", <payload>)` to checkpoint storage.
-
-#### T3: JSON lc:2 Constructor RCE
-
-- **Flow**: DF1 (Checkpoint Storage -> JsonPlusSerializer)
-- **Description**: The JSON `_reviver` handles `lc:2` type constructors by importing the module path from checkpoint JSON data via `importlib.import_module` (`libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py:JsonPlusSerializer._revive_lc2`). If `allowed_json_modules=True` (explicit opt-in), any module reachable in the Python environment can be imported and instantiated. The method also supports method chaining — a `method` key in the JSON can call arbitrary methods on the imported class.
-- **Preconditions**: (1) `allowed_json_modules` set to `True` (not the default). (2) Attacker writes crafted JSON to checkpoint storage.
-
-#### T4: RemoteGraph Unvalidated Inbound Data
-
-- **Flow**: DF5 (RemoteGraph -> Pregel)
-- **Description**: Stream events from the remote LangGraph Server are deserialized from JSON and dict-splatted into `Interrupt(**i)` and `Command(**chunk.data)` without schema validation (`libs/langgraph/langgraph/pregel/remote.py:RemoteGraph.stream`). A compromised or malicious remote server can inject unexpected fields. `Command.update` can carry arbitrary state modifications; `Command.goto` can alter graph execution flow. `Interrupt` accepts `**deprecated_kwargs` which includes a `ns` parameter that can override interrupt ID generation via `xxh3_128_hexdigest`.
-- **Preconditions**: User connects `RemoteGraph` to a compromised or attacker-controlled server URL.
-
-#### T5: Dockerfile ENV Single-Quote Injection
-
-- **Flow**: DF6, DF7 (langgraph.json -> CLI -> Dockerfile)
-- **Description**: Config values from `langgraph.json` are serialized via `json.dumps()` and embedded in single-quoted `ENV` directives across multiple config sections (store, auth, encryption, http, webhooks, checkpointer, ui, ui_config, graphs). JSON does not escape single quotes, so a config value containing `'` could break the Dockerfile syntax or inject additional Dockerfile instructions. The pattern is duplicated in two Dockerfile generation functions (`libs/cli/langgraph_cli/config.py:python_config_to_docker` and `libs/cli/langgraph_cli/config.py:node_config_to_docker`).
-- **Preconditions**: A `langgraph.json` config value contains a single quote character.
-
-#### T6: ZIP Slip in Template Extraction
-
-- **Flow**: DF7 (CLI template download)
-- **Description**: `langgraph new` downloads a ZIP from GitHub and uses `zip_file.extractall(path)`. If the archive contains path-traversal entries (e.g., `../../etc/cron.d/exploit`), files could be written outside the target directory.
-- **Preconditions**: The GitHub-hosted template archive must contain malicious path entries. This requires compromise of the upstream template repo.
-
-#### T7: AES Key Entropy via Environment Variable
-
-- **Flow**: DF10 (User config -> EncryptedSerializer)
-- **Description**: The AES key is loaded from `LANGGRAPH_AES_KEY` as a UTF-8 string and `.encode()`d to bytes (`libs/checkpoint/langgraph/checkpoint/serde/encrypted.py:EncryptedSerializer.from_pycryptodome_aes`). This limits key entropy to printable characters (~6.57 bits/byte vs. 8 bits/byte for random bytes), reducing effective key strength for AES-128 from 128 bits to ~105 bits.
-- **Preconditions**: User relies on environment variable path for key loading (vs. passing raw bytes directly via `key=` parameter).
-
-#### T8: EncryptedSerializer Assert Bypass
-
-- **Flow**: DF10 (Encrypted checkpoint data)
-- **Description**: The cipher name check in `decrypt()` uses `assert ciphername == "aes"` (`libs/checkpoint/langgraph/checkpoint/serde/encrypted.py:PycryptodomeAesCipher.decrypt`), which is stripped when Python runs with `-O` (optimize) flag. The `ciphername` value comes from the type tag in checkpoint storage (split from the `type+cipher` format).
-- **Preconditions**: Python running with `-O` flag AND attacker can write to checkpoint storage.
-
-#### T9: SDK API Key Leak via Server-Controlled Location Redirect
-
-- **Flow**: DF12 (Server -> SDK), DF13 (SDK -> Redirect target)
-- **Description**: The SDK's `HttpClient.request_reconnect()` (`libs/sdk-py/langgraph_sdk/_async/http.py:HttpClient.request_reconnect`) follows server-provided `Location` headers and forwards the full `request_headers` dict (including the `x-api-key` authentication header) to the redirected URL. The `HttpClient.stream()` method (`libs/sdk-py/langgraph_sdk/_async/http.py:HttpClient.stream`) also follows `Location` headers for SSE reconnection and forwards `reconnect_headers` (which include `x-api-key`) to the server-controlled URL. No URL validation, same-origin check, or sensitive header stripping is performed before following the redirect. The same pattern exists in the sync client (`libs/sdk-py/langgraph_sdk/_sync/http.py`).
-- **Preconditions**: (1) User connects SDK to a LangGraph Server that is compromised or attacker-controlled. (2) The server returns a response with a `Location` header pointing to an attacker-controlled URL.
-
-#### T10: EncryptedSerializer Encryption Bypass via Unencrypted Data Injection
-
-- **Flow**: DF1 (Checkpoint Storage -> EncryptedSerializer)
-- **Description**: `EncryptedSerializer.loads_typed()` (`libs/checkpoint/langgraph/checkpoint/serde/encrypted.py:EncryptedSerializer.loads_typed`) checks if the type tag contains a `+` delimiter. If it does not (e.g., type tag is `"msgpack"` instead of `"msgpack+aes"`), the data is passed directly to the inner serde's `loads_typed()` **without any decryption or MAC verification**. An attacker with write access to checkpoint storage can bypass the encryption layer entirely by writing data with a plain type tag.
-- **Preconditions**: (1) Application uses `EncryptedSerializer` for checkpoint protection. (2) Attacker has write access to checkpoint storage.
-
-#### T11: Unbounded Checkpoint Data Retention
-
-- **Flow**: DF1, DF11 (Checkpoint Storage lifecycle)
-- **Description**: Checkpoint data (DC3, DC6) is retained indefinitely by default. No built-in TTL, pruning, or data lifecycle management in the library-level checkpoint savers. Conversation history containing user PII may accumulate without bounds.
-- **Preconditions**: Application uses checkpointing (the primary use case). No explicit cleanup configured.
-
----
-
-## Input Source Coverage
-
-| Input Source | Data Flows | Threats | Validation Points | Responsibility | Gaps |
-|-------------|-----------|---------|-------------------|----------------|------|
-| User direct input (graph state, config) | DF8 | — | Graph structure validation (`libs/langgraph/langgraph/pregel/_validate.py:validate_graph`), channel type enforcement (`libs/langgraph/langgraph/channels/base.py:BaseChannel`), sensitive key filtering (`libs/langgraph/langgraph/_internal/_config.py:_exclude_as_metadata`) | User | Node implementation safety is user's responsibility |
-| LLM output (tool calls) | DF3, DF4, DF14 | — | Tool name allowlist (`libs/prebuilt/langgraph/prebuilt/tool_node.py:ToolNode._validate_tool_call`), tool Pydantic schemas, injection merge order (`libs/prebuilt/langgraph/prebuilt/tool_node.py:ToolNode._inject_tool_args`), `tool_call_schema` filtering of injected params | Shared (project validates name and injection safety; user validates args via tool schema) | No ToolNode-level argument sanitization beyond injection overwrite |
-| Checkpoint storage data | DF1, DF2, DF11 | T1, T2, T3, T10 | Msgpack allowlist (`libs/checkpoint/langgraph/checkpoint/serde/_msgpack.py:SAFE_MSGPACK_TYPES` — 47 entries), msgpack method allowlist (`libs/checkpoint/langgraph/checkpoint/serde/_msgpack.py:SAFE_MSGPACK_METHODS`), JSON allowlist (`libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py:_check_allowed_json_modules`), pickle gating, serde event hooks, optional encryption | Shared (project owns serializer defaults; user owns DB access controls) | Default msgpack mode allows unregistered types; EncryptedSerializer accepts unencrypted data; proposed secure_pickle.py never merged |
-| Remote API responses | DF5, DF9, DF12, DF13 | T4, T9 | Outbound config sanitization (`libs/langgraph/langgraph/pregel/remote.py:_sanitize_config`); no inbound validation; no redirect URL validation | User (user chooses which server to trust) | No inbound schema validation; API key forwarded on redirects |
-| Configuration (langgraph.json) | DF6, DF7 | T5 | JSON schema validation (`libs/cli/langgraph_cli/config.py:validate_config_file`), build command content validation (`libs/cli/langgraph_cli/config.py:has_disallowed_build_command_content`), list-based subprocess args, WebhookUrlPolicy (`libs/cli/langgraph_cli/schemas.py:WebhookUrlPolicy`) | User (developer-controlled file) | Single-quote not escaped in ENV embedding |
-| Configuration (env vars) | DF10 | T7, T8 | AES key length validation, EAX MAC verification | User (deployer controls env) | Key entropy, assert-based check |
-| Developer encryption handlers | DF15 | — | Handler signature validation (`libs/sdk-py/langgraph_sdk/encryption/__init__.py:_validate_handler`), duplicate prevention | User (developer-authored code) | `context()` handler missing `_validate_handler` call |
-
----
-
-## Out-of-Scope Threats
-
-Threats that appear valid in isolation but fall outside project responsibility because they depend on conditions the project does not control.
-
-| Pattern | Why Out of Scope | Project Responsibility Ends At |
-|---------|-----------------|-------------------------------|
-| Prompt injection leading to arbitrary tool execution | Project does not control LLM model behavior, user prompt construction, or which tools are registered. ToolNode routes by name only to user-registered tools. | Providing tool name allowlist routing (`libs/prebuilt/langgraph/prebuilt/tool_node.py:ToolNode._validate_tool_call`); user owns tool registration and argument handling |
-| State poisoning via malicious node output | User-registered nodes (including `@task`-decorated functions) can write arbitrary values to channels. The framework executes nodes as provided. | Enforcing channel type contracts (`libs/langgraph/langgraph/channels/base.py:BaseChannel.update`); user owns node implementation correctness |
-| Cross-session state access via thread_id guessing | Checkpoint savers index by `thread_id`. Without application-level auth, any caller with a valid thread_id can access that thread's state. | Providing the `Auth` handler system for access control (`libs/sdk-py/langgraph_sdk/auth/__init__.py:Auth`); user must implement auth handlers |
-| Tool shadowing via duplicate registration | If a user registers two tools with the same name, ToolNode uses the last one. This is user misconfiguration. | Documenting tool registration semantics |
-| Indirect prompt injection via tool output | LLM reads tool output and may follow injected instructions. This is a fundamental LLM limitation, not a framework vulnerability. | Not including tool output in system prompts; user owns output handling |
-| Model selecting dangerous tool arguments | An LLM may generate SQL injection, path traversal, or command injection payloads as tool arguments. The risk depends entirely on what the user's tools do with those arguments. | Routing tool calls to registered tools only; user owns tool input validation |
-| RCE via user-provided node code | `add_node()` and `@entrypoint`/`@task` accept arbitrary callables. A malicious node can do anything. This is by design — the user controls their own code. | Executing nodes within the graph runtime; user owns node code safety |
-| SSRF via RemoteGraph URL | User provides the `url` parameter to `RemoteGraph`. Pointing it at an internal service is the user's decision. | Documenting that `url` should be a trusted endpoint; user owns URL selection |
-| Malicious SDK Encryption handler | Encryption handlers are developer-authored server-side code. A malicious handler has full process access, equivalent to any application code. | Validating handler signature (async, param count); handler behavior is the developer's responsibility |
-
-### Rationale
-
-**Prompt injection and tool execution**: LangGraph's `ToolNode` validates tool names against the registered set but does not inspect or sanitize argument values. This is the correct boundary — the framework cannot know what constitutes a "safe" argument for an arbitrary user-defined tool. The tool's own Pydantic schema and implementation must validate inputs. The framework's responsibility is to not execute unregistered tools and to correctly route registered ones. The injection system (InjectedState/InjectedStore/ToolRuntime) is safe because system-injected values always overwrite LLM-supplied collisions via dict merge order, and injected parameter names are hidden from the LLM's tool schema.
-
-**State integrity**: LangGraph channels enforce type contracts (e.g., `LastValue` accepts one value per step, `BinaryOperatorAggregate` applies a reducer). The framework validates graph structure at compile time (`libs/langgraph/langgraph/pregel/_validate.py:validate_graph`). However, the semantic correctness of state updates is the user's responsibility — the framework cannot know what values are "valid" for a user-defined state schema.
-
-**Checkpoint access control**: The framework provides `BaseCheckpointSaver` as an abstract interface and the `Auth` handler system for authorization (`libs/sdk-py/langgraph_sdk/auth/__init__.py:Auth`). It does not enforce authentication by default because it operates as a library, not a server. The `langgraph-api` server layer (out of scope) is responsible for enforcing auth on API endpoints. Users embedding LangGraph directly must implement their own access controls.
-
-**Encryption handler safety**: The SDK Encryption module (`libs/sdk-py/langgraph_sdk/encryption/`) provides a registration framework for developer-authored encryption handlers. These handlers run server-side with full process access, identical to any application code. A buggy or malicious handler could return crafted data, but this is the same trust model as any developer-written code. The SDK validates handler shape (async, 2-param) but not handler behavior — this is the correct boundary for developer-trust-level code.
-
----
-
-## Investigated and Dismissed
-
-| ID | Original Threat | Investigation | Evidence | Conclusion |
-|----|----------------|---------------|----------|------------|
-| D1 | SQL injection via filter keys in PostgreSQL store | Traced filter key handling through `libs/checkpoint-postgres/langgraph/store/postgres/base.py:_get_filter_condition`. All filter operations use parameterized queries with `%s` placeholders. Keys map to `json_extract` path operators with type-safe wrappers. | `libs/checkpoint-postgres/langgraph/store/postgres/base.py:_get_filter_condition` — parameterized `%s` for all value bindings; key names used in `value->%s` path expressions are also parameterized | Disproven: All SQL operations in PostgreSQL store are fully parameterized. No injection vector. |
-| D2 | SQL injection via filter keys in SQLite store (post-fix) | Traced current filter handling through `libs/checkpoint-sqlite/langgraph/store/sqlite/base.py` and `libs/checkpoint-sqlite/langgraph/checkpoint/sqlite/utils.py:_validate_filter_key`. Regex `^[a-zA-Z0-9_.-]+$` applied to all filter keys before use in `json_extract()` expressions. | `libs/checkpoint-sqlite/langgraph/checkpoint/sqlite/utils.py:_validate_filter_key` — regex validation blocks injection characters. Published advisories GHSA-9rwj-6rc7-p77c and GHSA-7p73-8jqx-23r8 confirmed fixed. | Disproven: SQL injection in SQLite store filter keys is remediated by regex validation. |
-| D3 | Command injection via CLI subprocess execution | Traced CLI subprocess invocation path. `libs/cli/langgraph_cli/exec.py:subp_exec` uses `asyncio.create_subprocess_exec` with list-based arguments (not `shell=True`). `has_disallowed_build_command_content` blocks shell metacharacters in user-provided Dockerfile lines. | `libs/cli/langgraph_cli/exec.py:subp_exec` — explicit exec-style invocation; `libs/cli/langgraph_cli/config.py:has_disallowed_build_command_content` — regex blocks `\|`, `;`, `$`, `>`, `<`, backtick, `\`, single `&` | Disproven: CLI uses exec-style subprocess and validates build command content. No shell injection vector. |
-| D4 | Tool argument injection via InjectedState/InjectedStore dict-splatting | Investigated whether LLM-generated tool call arguments could override system-injected values (InjectedState, InjectedStore, ToolRuntime) via key collision in the dict merge at `libs/prebuilt/langgraph/prebuilt/tool_node.py:ToolNode._inject_tool_args` line 1380. Traced four independent defense layers. | (1) `tool_call_schema` at langchain-core `base.py` filters injected params from LLM schema. (2) `{**llm_args, **injected_args}` merge puts system values last — system wins on collision. (3) Pydantic `model_validate` with `extra="ignore"` drops unknown keys. (4) Output construction at `base.py` only includes declared model fields. | Disproven: Four-layer defense prevents LLM arguments from overriding system-injected values. Merge order guarantees system values win. No adversarial collision path exists. |
-
----
-
-## External Context
-
-### Published Security Advisories
-
-| GHSA ID | Severity | Summary | CWEs | Relevance |
-|---------|----------|---------|------|-----------|
-| GHSA-g48c-2wqr-h844 | Medium | Unsafe msgpack deserialization in LangGraph checkpoint loading | — | Directly relates to T1 — patched in 1.0.10, confirms attack path via crafted msgpack payloads |
-| GHSA-mhr3-j7m5-c7c9 | Medium | BaseCache Deserialization RCE | CWE-502 | Directly relates to T1 — msgpack deserialization in cache layer |
-| GHSA-9rwj-6rc7-p77c | High | SQL injection via metadata filter key in SQLite checkpointer | CWE-89 | Fixed via `_validate_filter_key()` regex — see D2 |
-| GHSA-wwqv-p2pp-99h5 | High | RCE in JSON mode of JsonPlusSerializer | CWE-502 | Directly relates to T3 — `lc:2` constructor import |
-| GHSA-7p73-8jqx-23r8 | High | SQLite Filter Key SQL Injection in SqliteStore | CWE-89 | Fixed via `_validate_filter_key()` regex — see D2 |
-
-**Pattern**: 3 of 5 published advisories involve CWE-502 (insecure deserialization) in the checkpoint serialization layer. This confirms the checkpoint storage boundary (TB2) as the highest-risk area. The extensive closed advisory history (~15 deserialization bypass attempts) further validates this assessment. No new published advisories since the prior assessment (2026-03-27).
-
-
----
-
-## Revision History
-
-| Date | Author | Changes |
-|------|--------|---------|
-| 2026-03-04 | Generated | Initial threat model |
-| 2026-03-04 | Updated | Added C13 (Functional API), C14 (BaseCache), DF11. Updated T1 for BaseCache/serde event hooks. Added GHSA-mhr3-j7m5-c7c9 and GHSA-9rwj-6rc7-p77c. Updated CLI config scope. Added External Context section. |
-| 2026-03-27 | Deep refinement | **Mode upgraded to Deep.** Added: Data Classification section (DC1-DC8 with detailed analysis for Critical/High entries). Added: C15 (Serde Event Hooks), C16 (Auth System). Added: Default? column to Components. Added: Classification column to Data Flows. Added: DF12-DF13 (SDK redirect flows). Added: T9 (SDK API key leak via Location redirect), T10 (EncryptedSerializer encryption bypass), T11 (unbounded checkpoint retention). Added: Validation column to Threats with flaw validation for High/Critical. Added: Investigated and Dismissed section (D1-D3: SQL injection and CLI command injection disproven). Added: Input Source Coverage section. Updated external context with GHSA-g48c-2wqr-h844 (new published advisory). Updated all code references to file:SymbolName notation. Expanded trust boundary details. |
-| 2026-03-30 | Diagram and Default? corrections | Fixed architecture diagram: merged "User Code" and "User-Registered Tools" into single "User Application Code" boundary; removed @entrypoint/@task as separate diagram elements (both compile to Pregel — authoring style, not separate component). Fixed Default? column: C3 ToolNode → No (explicit opt-in required); C8 CLI → No (separate install). |
-| 2026-03-28 | Deep update | **Added:** C17 (SDK Encryption Handlers — beta at-rest encryption framework). DC9 (SDK Encryption context metadata). TB5 (SDK Encryption Handler boundary). DF14 (ToolRuntime injection flow), DF15 (Encryption handler registration flow). D4 (Tool argument injection via InjectedState dict-splatting — disproven with 4-layer defense evidence). **Updated:** C1 description (v1/v2 output, durability modes, interrupt_before/after). C2 description (SAFE_MSGPACK_TYPES now 47 entries including langchain_core messages, Document, GetOp). C3 description (InjectedState/InjectedStore/ToolRuntime injection support, _inject_tool_args entry point). C8 description (WebhookUrlPolicy for SSRF protection). TB1 details (tool injection merge order guarantees). TB2 details (47 safe types, updated allowlist composition). TB4 details (WebhookUrlPolicy). DF4 description (injection merge semantics). T1 details (noted secure_pickle.py proposed but never merged). T4 details (Interrupt deprecated_kwargs ns parameter). Input Source Coverage (LLM output row updated with injection validation points, encryption handler row added). Out-of-Scope Threats (malicious encryption handler pattern added). Commit updated to 0ba22143. External context confirmed no new published advisories. |

.github/actions/poetry_setup/action.yml

@@ -0,0 +1,88 @@
+# An action for setting up poetry install with caching.
+# Using a custom action since the default action does not
+# take poetry install groups into account.
+# Action code from:
+# https://github.com/actions/setup-python/issues/505#issuecomment-1273013236
+name: poetry-install-with-caching
+description: Poetry install with support for caching of dependency groups.
+
+inputs:
+  python-version:
+    description: Python version, supporting MAJOR.MINOR only
+    required: true
+
+  poetry-version:
+    description: Poetry version
+    required: true
+
+  cache-key:
+    description: Cache key to use for manual handling of caching
+    required: true
+
+runs:
+  using: composite
+  steps:
+    - uses: actions/setup-python@v5
+      name: Setup python ${{ inputs.python-version }}
+      id: setup-python
+      with:
+        python-version: ${{ inputs.python-version }}
+
+    - uses: actions/cache@v3
+      id: cache-bin-poetry
+      name: Cache Poetry binary - Python ${{ inputs.python-version }}
+      env:
+        SEGMENT_DOWNLOAD_TIMEOUT_MIN: "1"
+      with:
+        path: |
+          /opt/pipx/venvs/poetry
+        # This step caches the poetry installation, so make sure it's keyed on the poetry version as well.
+        key: bin-poetry-${{ runner.os }}-${{ runner.arch }}-py-${{ inputs.python-version }}-${{ inputs.poetry-version }}
+
+    - name: Refresh shell hashtable and fixup softlinks
+      if: steps.cache-bin-poetry.outputs.cache-hit == 'true'
+      shell: bash
+      env:
+        POETRY_VERSION: ${{ inputs.poetry-version }}
+        PYTHON_VERSION: ${{ inputs.python-version }}
+      run: |
+        set -eux
+
+        # Refresh the shell hashtable, to ensure correct `which` output.
+        hash -r
+
+        # `actions/cache@v3` doesn't always seem able to correctly unpack softlinks.
+        # Delete and recreate the softlinks pipx expects to have.
+        rm /opt/pipx/venvs/poetry/bin/python
+        cd /opt/pipx/venvs/poetry/bin
+        ln -s "$(which "python$PYTHON_VERSION")" python
+        chmod +x python
+        cd /opt/pipx_bin/
+        ln -s /opt/pipx/venvs/poetry/bin/poetry poetry
+        chmod +x poetry
+
+        # Ensure everything got set up correctly.
+        /opt/pipx/venvs/poetry/bin/python --version
+        /opt/pipx_bin/poetry --version
+
+    - name: Install poetry
+      if: steps.cache-bin-poetry.outputs.cache-hit != 'true'
+      shell: bash
+      env:
+        POETRY_VERSION: ${{ inputs.poetry-version }}
+        PYTHON_VERSION: ${{ inputs.python-version }}
+      # Install poetry using the python version installed by setup-python step.
+      run: pipx install "poetry==$POETRY_VERSION" --python '${{ steps.setup-python.outputs.python-path }}' --verbose
+
+    - name: Restore pip and poetry cached dependencies
+      uses: actions/cache@v3
+      env:
+        SEGMENT_DOWNLOAD_TIMEOUT_MIN: "4"
+      with:
+        path: |
+          ~/.cache/pip
+          ~/.cache/pypoetry/virtualenvs
+          ~/.cache/pypoetry/cache
+          ~/.cache/pypoetry/artifacts
+          ./.venv
+        key: py-deps-${{ runner.os }}-${{ runner.arch }}-py-${{ inputs.python-version }}-poetry-${{ inputs.poetry-version }}-${{ inputs.cache-key }}-${{ hashFiles('./poetry.lock') }}

.github/actions/uv_setup/action.yml

@@ -1,35 +0,0 @@
-# Helper to set up Python and uv with caching
-
-name: uv-install
-description: Set up Python and uv with caching
-
-inputs:
-  python-version:
-    description: Python version, supporting MAJOR.MINOR only
-    required: true
-  enable-cache:
-    description: Enable caching for uv dependencies
-    required: false
-    default: "true"
-  cache-suffix:
-    description: Custom cache key suffix for cache invalidation
-    required: false
-    default: ""
-  working-directory:
-    description: Working directory for cache glob scoping
-    required: false
-    default: "**"
-
-runs:
-  using: composite
-  steps:
-    - name: Install uv and set the python version
-      uses: astral-sh/setup-uv@v7
-      with:
-        python-version: ${{ inputs.python-version }}
-        enable-cache: ${{ inputs.enable-cache }}
-        cache-dependency-glob: |
-          ${{ inputs.working-directory }}/pyproject.toml
-          ${{ inputs.working-directory }}/uv.lock
-          ${{ inputs.working-directory }}/requirements*.txt
-        cache-suffix: ${{ inputs.cache-suffix }}

.github/dependabot.yml

@@ -1,188 +0,0 @@
-version: 2
-updates:
-  - package-ecosystem: "github-actions"
-    directory: "/"
-    schedule:
-      interval: "monthly"
-    groups:
-      minor-and-patch:
-        patterns:
-          - "*"
-        update-types:
-          - "minor"
-          - "patch"
-      major:
-        patterns:
-          - "*"
-        update-types:
-          - "major"
-
-  - package-ecosystem: "uv"
-    directory: "/libs/checkpoint"
-    schedule:
-      interval: "monthly"
-    groups:
-      minor-and-patch:
-        patterns:
-          - "*"
-        update-types:
-          - "minor"
-          - "patch"
-      major:
-        patterns:
-          - "*"
-        update-types:
-          - "major"
-
-  - package-ecosystem: "uv"
-    directory: "/libs/checkpoint-conformance"
-    schedule:
-      interval: "monthly"
-    groups:
-      minor-and-patch:
-        patterns:
-          - "*"
-        update-types:
-          - "minor"
-          - "patch"
-      major:
-        patterns:
-          - "*"
-        update-types:
-          - "major"
-
-  - package-ecosystem: "uv"
-    directory: "/libs/checkpoint-postgres"
-    schedule:
-      interval: "monthly"
-    groups:
-      minor-and-patch:
-        patterns:
-          - "*"
-        update-types:
-          - "minor"
-          - "patch"
-      major:
-        patterns:
-          - "*"
-        update-types:
-          - "major"
-
-  - package-ecosystem: "uv"
-    directory: "/libs/checkpoint-sqlite"
-    schedule:
-      interval: "monthly"
-    groups:
-      minor-and-patch:
-        patterns:
-          - "*"
-        update-types:
-          - "minor"
-          - "patch"
-      major:
-        patterns:
-          - "*"
-        update-types:
-          - "major"
-
-  - package-ecosystem: "uv"
-    directory: "/libs/cli"
-    schedule:
-      interval: "monthly"
-    groups:
-      minor-and-patch:
-        patterns:
-          - "*"
-        update-types:
-          - "minor"
-          - "patch"
-      major:
-        patterns:
-          - "*"
-        update-types:
-          - "major"
-
-  - package-ecosystem: "uv"
-    directory: "/libs/langgraph"
-    schedule:
-      interval: "monthly"
-    groups:
-      minor-and-patch:
-        patterns:
-          - "*"
-        update-types:
-          - "minor"
-          - "patch"
-      major:
-        patterns:
-          - "*"
-        update-types:
-          - "major"
-
-  - package-ecosystem: "uv"
-    directory: "/libs/prebuilt"
-    schedule:
-      interval: "monthly"
-    groups:
-      minor-and-patch:
-        patterns:
-          - "*"
-        update-types:
-          - "minor"
-          - "patch"
-      major:
-        patterns:
-          - "*"
-        update-types:
-          - "major"
-
-  - package-ecosystem: "uv"
-    directory: "/libs/sdk-py"
-    schedule:
-      interval: "monthly"
-    groups:
-      minor-and-patch:
-        patterns:
-          - "*"
-        update-types:
-          - "minor"
-          - "patch"
-      major:
-        patterns:
-          - "*"
-        update-types:
-          - "major"
-
-  - package-ecosystem: "npm"
-    directory: "/libs/cli/js-examples"
-    schedule:
-      interval: "monthly"
-    groups:
-      minor-and-patch:
-        patterns:
-          - "*"
-        update-types:
-          - "minor"
-          - "patch"
-      major:
-        patterns:
-          - "*"
-        update-types:
-          - "major"
-
-  - package-ecosystem: "npm"
-    directory: "/libs/cli/js-monorepo-example"
-    schedule:
-      interval: "monthly"
-    groups:
-      minor-and-patch:
-        patterns:
-          - "*"
-        update-types:
-          - "minor"
-          - "patch"
-      major:
-        patterns:
-          - "*"
-        update-types:
-          - "major"

.github/images/logo-dark.svg

@@ -1,5 +0,0 @@
-<svg width="472" height="100" viewBox="0 0 472 100" fill="none" xmlns="http://www.w3.org/2000/svg">
-<rect x="100" y="6.10352e-05" width="100" height="100" rx="20" transform="rotate(90 100 6.10352e-05)" fill="#161F34"/>
-<path d="M32.1494 67.8579H45.2266C45.2246 75.0778 39.3716 80.93 32.1514 80.9302C24.9301 80.9301 19.0756 75.0762 19.0752 67.855C19.0752 60.6341 24.9288 54.78 32.1494 54.7788V67.8579ZM67.8691 54.7788C75.0906 54.779 80.9443 60.6335 80.9443 67.855C80.944 75.0762 75.0904 80.93 67.8691 80.9302C60.6488 80.9301 54.7949 75.0778 54.793 67.8579H67.8594V54.7788C67.8626 54.7788 67.8659 54.7788 67.8691 54.7788ZM67.8691 19.0757C75.0906 19.0759 80.9443 24.9304 80.9443 32.1519C80.944 39.3731 75.0904 45.2269 67.8691 45.2271C67.8659 45.2271 67.8626 45.2261 67.8594 45.2261V32.1479H54.793C54.795 24.9281 60.6489 19.0758 67.8691 19.0757ZM32.1514 19.0757C39.3716 19.0759 45.2246 24.9281 45.2266 32.1479H32.1494V45.2261C24.929 45.2249 19.0755 39.3725 19.0752 32.1519C19.0752 24.9303 24.9299 19.0758 32.1514 19.0757Z" fill="#7FC8FF"/>
-<path d="M142.427 70.248V65.748H153.227V32.748H142.427V28.248H158.147V65.748H168.947V70.248H142.427ZM189.174 70.608C182.454 70.608 177.894 67.248 177.894 61.668C177.894 55.548 182.154 52.128 190.194 52.128H199.194V50.028C199.194 46.068 196.374 43.668 191.574 43.668C187.254 43.668 184.374 45.708 183.774 48.828H178.854C179.574 42.828 184.434 39.288 191.814 39.288C199.614 39.288 204.114 43.188 204.114 50.328V63.708C204.114 65.328 204.714 65.748 206.094 65.748H207.654V70.248H204.954C200.874 70.248 199.494 68.508 199.434 65.508C197.514 68.268 194.454 70.608 189.174 70.608ZM189.534 66.408C195.654 66.408 199.194 62.868 199.194 57.768V56.268H189.714C185.334 56.268 182.874 57.888 182.874 61.368C182.874 64.368 185.454 66.408 189.534 66.408ZM216.601 70.248V39.648H220.861L221.521 43.788C223.321 41.448 226.321 39.288 231.121 39.288C237.601 39.288 243.001 42.948 243.001 52.848V70.248H238.081V53.148C238.081 47.028 235.201 43.788 230.281 43.788C224.941 43.788 221.521 47.928 221.521 53.988V70.248H216.601ZM266.348 82.608C258.548 82.608 253.088 78.948 252.308 72.228H257.348C258.188 76.068 261.608 78.228 266.708 78.228C273.128 78.228 276.608 75.228 276.608 68.568V64.968C274.568 68.448 271.268 70.608 266.108 70.608C257.648 70.608 251.408 64.908 251.408 54.948C251.408 45.588 257.648 39.288 266.108 39.288C271.268 39.288 274.688 41.508 276.608 44.928L277.268 39.648H281.528V68.748C281.528 77.568 276.848 82.608 266.348 82.608ZM266.588 66.228C272.588 66.228 276.668 61.608 276.668 55.068C276.668 48.348 272.588 43.668 266.588 43.668C260.528 43.668 256.448 48.288 256.448 54.948C256.448 61.608 260.528 66.228 266.588 66.228ZM303.555 82.608C295.755 82.608 290.295 78.948 289.515 72.228H294.555C295.395 76.068 298.815 78.228 303.915 78.228C310.335 78.228 313.815 75.228 313.815 68.568V64.968C311.775 68.448 308.475 70.608 303.315 70.608C294.855 70.608 288.615 64.908 288.615 54.948C288.615 45.588 294.855 39.288 303.315 39.288C308.475 39.288 311.895 41.508 313.815 44.928L314.475 39.648H318.735V68.748C318.735 77.568 314.055 82.608 303.555 82.608ZM303.795 66.228C309.795 66.228 313.875 61.608 313.875 55.068C313.875 48.348 309.795 43.668 303.795 43.668C297.735 43.668 293.655 48.288 293.655 54.948C293.655 61.608 297.735 66.228 303.795 66.228ZM327.862 70.248V65.748H335.422V44.148H327.862V39.648H340.222V44.928C341.602 42.588 344.482 39.648 350.482 39.648H355.582V44.448H349.942C342.562 44.448 340.342 49.968 340.342 54.828V65.748H353.902V70.248H327.862ZM375.209 70.608C368.489 70.608 363.929 67.248 363.929 61.668C363.929 55.548 368.189 52.128 376.229 52.128H385.229V50.028C385.229 46.068 382.409 43.668 377.609 43.668C373.289 43.668 370.409 45.708 369.809 48.828H364.889C365.609 42.828 370.469 39.288 377.849 39.288C385.649 39.288 390.149 43.188 390.149 50.328V63.708C390.149 65.328 390.749 65.748 392.129 65.748H393.689V70.248H390.989C386.909 70.248 385.529 68.508 385.469 65.508C383.549 68.268 380.489 70.608 375.209 70.608ZM375.569 66.408C381.689 66.408 385.229 62.868 385.229 57.768V56.268H375.749C371.369 56.268 368.909 57.888 368.909 61.368C368.909 64.368 371.489 66.408 375.569 66.408ZM401.076 82.248V39.648H405.336L405.996 44.568C408.036 41.748 411.336 39.288 416.496 39.288C424.956 39.288 431.196 44.988 431.196 54.948C431.196 64.308 424.956 70.608 416.496 70.608C411.336 70.608 407.856 68.508 405.996 65.568V82.248H401.076ZM416.016 66.228C422.076 66.228 426.156 61.608 426.156 54.948C426.156 48.288 422.076 43.668 416.016 43.668C410.016 43.668 405.936 48.288 405.936 54.828C405.936 61.548 410.016 66.228 416.016 66.228ZM439.663 70.248V28.248H444.583V43.788C446.863 40.968 450.403 39.288 454.363 39.288C462.043 39.288 466.423 44.388 466.423 53.208V70.248H461.503V53.508C461.503 47.268 458.623 43.788 453.523 43.788C448.063 43.788 444.583 48.108 444.583 54.948V70.248H439.663Z" fill="white"/>
-</svg>

.github/images/logo-light.svg

@@ -1,5 +0,0 @@
-<svg width="472" height="100" viewBox="0 0 472 100" fill="none" xmlns="http://www.w3.org/2000/svg">
-<rect x="100" width="100" height="100" rx="20" transform="rotate(90 100 0)" fill="#161F34"/>
-<path d="M32.1494 67.8578H45.2266C45.2246 75.0776 39.3716 80.9299 32.1514 80.9301C24.9301 80.9299 19.0756 75.0761 19.0752 67.8549C19.0752 60.634 24.9288 54.7799 32.1494 54.7787V67.8578ZM67.8691 54.7787C75.0906 54.7789 80.9443 60.6334 80.9443 67.8549C80.944 75.076 75.0904 80.9299 67.8691 80.9301C60.6488 80.9299 54.7949 75.0777 54.793 67.8578H67.8594V54.7787C67.8626 54.7787 67.8659 54.7787 67.8691 54.7787ZM67.8691 19.0756C75.0906 19.0758 80.9443 24.9303 80.9443 32.1517C80.944 39.373 75.0904 45.2267 67.8691 45.2269C67.8659 45.2269 67.8626 45.226 67.8594 45.226V32.1478H54.793C54.795 24.928 60.6489 19.0757 67.8691 19.0756ZM32.1514 19.0756C39.3716 19.0757 45.2246 24.928 45.2266 32.1478H32.1494V45.226C24.929 45.2248 19.0755 39.3724 19.0752 32.1517C19.0752 24.9302 24.9299 19.0757 32.1514 19.0756Z" fill="#7FC8FF"/>
-<path d="M142.427 70.248V65.748H153.227V32.748H142.427V28.248H158.147V65.748H168.947V70.248H142.427ZM189.174 70.608C182.454 70.608 177.894 67.248 177.894 61.668C177.894 55.548 182.154 52.128 190.194 52.128H199.194V50.028C199.194 46.068 196.374 43.668 191.574 43.668C187.254 43.668 184.374 45.708 183.774 48.828H178.854C179.574 42.828 184.434 39.288 191.814 39.288C199.614 39.288 204.114 43.188 204.114 50.328V63.708C204.114 65.328 204.714 65.748 206.094 65.748H207.654V70.248H204.954C200.874 70.248 199.494 68.508 199.434 65.508C197.514 68.268 194.454 70.608 189.174 70.608ZM189.534 66.408C195.654 66.408 199.194 62.868 199.194 57.768V56.268H189.714C185.334 56.268 182.874 57.888 182.874 61.368C182.874 64.368 185.454 66.408 189.534 66.408ZM216.601 70.248V39.648H220.861L221.521 43.788C223.321 41.448 226.321 39.288 231.121 39.288C237.601 39.288 243.001 42.948 243.001 52.848V70.248H238.081V53.148C238.081 47.028 235.201 43.788 230.281 43.788C224.941 43.788 221.521 47.928 221.521 53.988V70.248H216.601ZM266.348 82.608C258.548 82.608 253.088 78.948 252.308 72.228H257.348C258.188 76.068 261.608 78.228 266.708 78.228C273.128 78.228 276.608 75.228 276.608 68.568V64.968C274.568 68.448 271.268 70.608 266.108 70.608C257.648 70.608 251.408 64.908 251.408 54.948C251.408 45.588 257.648 39.288 266.108 39.288C271.268 39.288 274.688 41.508 276.608 44.928L277.268 39.648H281.528V68.748C281.528 77.568 276.848 82.608 266.348 82.608ZM266.588 66.228C272.588 66.228 276.668 61.608 276.668 55.068C276.668 48.348 272.588 43.668 266.588 43.668C260.528 43.668 256.448 48.288 256.448 54.948C256.448 61.608 260.528 66.228 266.588 66.228ZM303.555 82.608C295.755 82.608 290.295 78.948 289.515 72.228H294.555C295.395 76.068 298.815 78.228 303.915 78.228C310.335 78.228 313.815 75.228 313.815 68.568V64.968C311.775 68.448 308.475 70.608 303.315 70.608C294.855 70.608 288.615 64.908 288.615 54.948C288.615 45.588 294.855 39.288 303.315 39.288C308.475 39.288 311.895 41.508 313.815 44.928L314.475 39.648H318.735V68.748C318.735 77.568 314.055 82.608 303.555 82.608ZM303.795 66.228C309.795 66.228 313.875 61.608 313.875 55.068C313.875 48.348 309.795 43.668 303.795 43.668C297.735 43.668 293.655 48.288 293.655 54.948C293.655 61.608 297.735 66.228 303.795 66.228ZM327.862 70.248V65.748H335.422V44.148H327.862V39.648H340.222V44.928C341.602 42.588 344.482 39.648 350.482 39.648H355.582V44.448H349.942C342.562 44.448 340.342 49.968 340.342 54.828V65.748H353.902V70.248H327.862ZM375.209 70.608C368.489 70.608 363.929 67.248 363.929 61.668C363.929 55.548 368.189 52.128 376.229 52.128H385.229V50.028C385.229 46.068 382.409 43.668 377.609 43.668C373.289 43.668 370.409 45.708 369.809 48.828H364.889C365.609 42.828 370.469 39.288 377.849 39.288C385.649 39.288 390.149 43.188 390.149 50.328V63.708C390.149 65.328 390.749 65.748 392.129 65.748H393.689V70.248H390.989C386.909 70.248 385.529 68.508 385.469 65.508C383.549 68.268 380.489 70.608 375.209 70.608ZM375.569 66.408C381.689 66.408 385.229 62.868 385.229 57.768V56.268H375.749C371.369 56.268 368.909 57.888 368.909 61.368C368.909 64.368 371.489 66.408 375.569 66.408ZM401.076 82.248V39.648H405.336L405.996 44.568C408.036 41.748 411.336 39.288 416.496 39.288C424.956 39.288 431.196 44.988 431.196 54.948C431.196 64.308 424.956 70.608 416.496 70.608C411.336 70.608 407.856 68.508 405.996 65.568V82.248H401.076ZM416.016 66.228C422.076 66.228 426.156 61.608 426.156 54.948C426.156 48.288 422.076 43.668 416.016 43.668C410.016 43.668 405.936 48.288 405.936 54.828C405.936 61.548 410.016 66.228 416.016 66.228ZM439.663 70.248V28.248H444.583V43.788C446.863 40.968 450.403 39.288 454.363 39.288C462.043 39.288 466.423 44.388 466.423 53.208V70.248H461.503V53.508C461.503 47.268 458.623 43.788 453.523 43.788C448.063 43.788 444.583 48.108 444.583 54.948V70.248H439.663Z" fill="#161F34"/>
-</svg>

.github/scripts/check_sdk_methods.py

@@ -1,69 +0,0 @@
-import ast
-import os
-from itertools import filterfalse
-from typing import Dict, List, Tuple
-
-ROOT_PATH = os.path.abspath(os.path.join(__file__, "..", "..", ".."))
-CLIENT_PATH = os.path.join(ROOT_PATH, "libs", "sdk-py", "langgraph_sdk", "client.py")
-ASYNC_TO_SYNC_METHOD_MAP: Dict[str, str] = {
-    "aclose": "close",
-    "__aenter__": "__enter__",
-    "__aexit__": "__exit__",
-}
-
-
-def get_class_methods(node: ast.ClassDef) -> List[str]:
-    return [n.name for n in node.body if isinstance(n, (ast.FunctionDef, ast.AsyncFunctionDef))]
-
-
-def find_classes(tree: ast.AST) -> List[Tuple[str, List[str]]]:
-    classes = []
-    for node in ast.walk(tree):
-        if isinstance(node, ast.ClassDef):
-            methods = get_class_methods(node)
-            classes.append((node.name, methods))
-    return classes
-
-
-def compare_sync_async_methods(sync_methods: List[str], async_methods: List[str]) -> List[str]:
-    sync_set = set(sync_methods)
-    async_set = {ASYNC_TO_SYNC_METHOD_MAP.get(async_method, async_method) for async_method in async_methods}
-    missing_in_sync = list(async_set - sync_set)
-    missing_in_async = list(sync_set - async_set)
-    return missing_in_sync + missing_in_async
-
-
-def main():
-    with open(CLIENT_PATH, "r") as file:
-        tree = ast.parse(file.read())
-
-    classes = find_classes(tree)
-
-    def is_sync(class_spec: Tuple[str, List[str]]) -> bool:
-        return class_spec[0].startswith("Sync")
-
-    sync_class_name_to_methods = {class_name: class_methods for class_name, class_methods in filter(is_sync, classes)}
-    async_class_name_to_methods = {class_name: class_methods for class_name, class_methods in filterfalse(is_sync, classes)}
-
-    mismatches = []
-
-    for async_class_name, async_class_methods in async_class_name_to_methods.items():
-        sync_class_name = "Sync" + async_class_name
-        sync_class_methods = sync_class_name_to_methods.get(sync_class_name, [])
-        diff = compare_sync_async_methods(sync_class_methods, async_class_methods)
-        if diff:
-            mismatches.append((sync_class_name, async_class_name, diff))
-
-    if mismatches:
-        error_message = "Mismatches found between sync and async client methods:\n"
-        for sync_class_name, async_class_name, diff in mismatches:
-            error_message += f"{sync_class_name} vs {async_class_name}:\n"
-            for method in diff:
-                error_message += f"  - {method}\n"
-        raise ValueError(error_message)
-
-    print("All sync and async client methods match.")
-
-
-if __name__ == "__main__":
-    main()

.github/scripts/run_langgraph_cli_test.py

@@ -1,177 +0,0 @@
-import logging
-import pathlib
-import sys
-import time
-from urllib import error, request
-
-import langgraph_cli
-import langgraph_cli.config
-import langgraph_cli.docker
-from langgraph_cli.cli import prepare_args_and_stdin
-from langgraph_cli.constants import DEFAULT_PORT
-from langgraph_cli.exec import Runner, subp_exec
-from langgraph_cli.progress import Progress
-
-logger = logging.getLogger(__name__)
-logging.basicConfig(level=logging.INFO)
-
-
-def test(config: pathlib.Path, port: int, tag: str, verbose: bool):
-    """Spin up API with Postgres/Redis via docker compose and wait until ready."""
-    logger.info("Starting test...")
-    with Runner() as runner, Progress(message="Pulling...") as set:
-        # Detect docker/compose capabilities
-        capabilities = langgraph_cli.docker.check_capabilities(runner)
-
-        # Validate config and prepare compose stdin/args using built image
-        config_json = langgraph_cli.config.validate_config_file(config)
-        args, stdin = prepare_args_and_stdin(
-            capabilities=capabilities,
-            config_path=config,
-            config=config_json,
-            docker_compose=None,
-            port=port,
-            watch=False,
-            debugger_port=None,
-            debugger_base_url=f"http://127.0.0.1:{port}",
-            postgres_uri=None,
-            api_version=None,
-            image=tag,
-            base_image=None,
-        )
-
-        # Compose up with wait (implies detach), similar to `langgraph up --wait`
-        args_up = [*args, "up", "--remove-orphans", "--wait"]
-
-        compose_cmd = ["docker", "compose"]
-        if capabilities.compose_type == "standalone":
-            compose_cmd = ["docker-compose"]
-
-        set("Starting...")
-        try:
-            runner.run(
-                subp_exec(
-                    *compose_cmd,
-                    *args_up,
-                    input=stdin,
-                    verbose=verbose,
-                )
-            )
-        except Exception as e:  # noqa: BLE001
-            # On failure, show diagnostics then ensure clean teardown
-            sys.stderr.write(f"docker compose up failed: {e}\n")
-            try:
-                sys.stderr.write("\n== docker compose ps ==\n")
-                runner.run(
-                    subp_exec(*compose_cmd, *args, "ps", input=stdin, verbose=True)
-                )
-            except Exception:
-                pass
-            try:
-                sys.stderr.write("\n== docker compose logs (api) ==\n")
-                runner.run(
-                    subp_exec(
-                        *compose_cmd,
-                        *args,
-                        "logs",
-                        "langgraph-api",
-                        input=stdin,
-                        verbose=True,
-                    )
-                )
-            except Exception:
-                pass
-            finally:
-                try:
-                    runner.run(
-                        subp_exec(
-                            *compose_cmd,
-                            *args,
-                            "down",
-                            "-v",
-                            "--remove-orphans",
-                            input=stdin,
-                            verbose=False,
-                        )
-                    )
-                finally:
-                    raise
-
-        set("")
-        base_url = f"http://localhost:{port}"
-        ok_url = f"{base_url}/ok"
-        logger.info(f"Waiting for {ok_url} to respond with 200...")
-        deadline = time.time() + 30
-        last_err: Exception | None = None
-        while time.time() < deadline:
-            try:
-                with request.urlopen(ok_url, timeout=2) as resp:
-                    if resp.status == 200:
-                        sys.stdout.write(
-                            f"""Ready!\n- API: {base_url}\n- /ok: 200 OK\n"""
-                        )
-                        sys.stdout.flush()
-                        break
-                    else:
-                        last_err = RuntimeError(f"Unexpected status: {resp.status}")
-                        logger.error(f"Unexpected status: {resp.status}")
-            except error.URLError as e:
-                logger.error(f"URLError: {e}")
-                last_err = e
-            except Exception as e:  # noqa: BLE001
-                logger.error(f"Exception: {e}")
-                last_err = e
-            time.sleep(0.5)
-        else:
-            logger.error("Timeout waiting for /ok to return 200")
-            # Bring stack down before raising
-            args_down = [*args, "down", "-v", "--remove-orphans"]
-            try:
-                runner.run(
-                    subp_exec(
-                        *compose_cmd,
-                        *args_down,
-                        input=stdin,
-                        verbose=verbose,
-                    )
-                )
-            finally:
-                raise SystemExit(
-                    f"/ok did not return 202 within timeout. Last error: {last_err}"
-                )
-
-        # Clean up: bring compose stack down to free ports for next test
-        logger.info("Test succeeded. Bringing down compose stack...")
-        try:
-            args_down = [*args, "down", "-v", "--remove-orphans"]
-            runner.run(
-                subp_exec(
-                    *compose_cmd,
-                    *args_down,
-                    input=stdin,
-                    verbose=verbose,
-                )
-            )
-            logger.info("Compose stack down. Finishing...")
-        except Exception:
-            logger.exception("Failed to bring down compose stack")
-            pass
-
-    logger.info("Test finished")
-
-
-if __name__ == "__main__":
-    import argparse
-
-    parser = argparse.ArgumentParser()
-    parser.add_argument("-t", "--tag", type=str)
-    parser.add_argument("-c", "--config", type=str, default="./langgraph.json")
-    parser.add_argument("-p", "--port", type=int, default=DEFAULT_PORT)
-    args = parser.parse_args()
-    try:
-        test(pathlib.Path(args.config), args.port, args.tag, verbose=True)
-    except BaseException:
-        logger.exception("Test failed")
-        raise
-    
-    logger.info("Test execution finished")

.github/workflows/_integration_test.yml

@@ -2,12 +2,9 @@ name: CLI integration test
 
 on:
   workflow_call:
-    secrets:
-      LANGSMITH_API_KEY:
-        required: false
 
-permissions:
-  contents: read
+env:
+  POETRY_VERSION: "1.7.1"
 
 jobs:
   build:
@@ -16,153 +13,48 @@ jobs:
       matrix:
         python-version:
           - "3.10"
-          - "3.14"
-        example:
-          - name: A
-            workdir: libs/cli/examples
-            tag: langgraph-test-a
-          - name: B
-            workdir: libs/cli/examples/graphs
-            tag: langgraph-test-b
-          - name: C
-            workdir: libs/cli/examples/graphs_reqs_a
-            tag: langgraph-test-c
-          - name: D
-            workdir: libs/cli/examples/graphs_reqs_b
-            tag: langgraph-test-d
+          - "3.11"
     name: "CLI integration test"
-    env:
-      HAS_LANGSMITH_API_KEY: ${{ secrets.LANGSMITH_API_KEY != '' }}
     defaults:
       run:
         working-directory: libs/cli
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - name: Get changed files
         id: changed-files
-        if: github.event_name != 'workflow_dispatch'
-        uses: Ana06/get-changed-files@25f79e676e7ea1868813e21465014798211fad8c # v2.3.0
+        uses: Ana06/get-changed-files@v2.2.0
         with:
           filter: "libs/cli/**"
-      - name: Set up Python ${{ matrix.python-version }}
-        if: (steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch')
-        uses: ./.github/actions/uv_setup
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        if: steps.changed-files.outputs.all
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ matrix.python-version }}
-          enable-cache: "false"
-          working-directory: libs/cli
+          poetry-version: ${{ env.POETRY_VERSION }}
+          cache-key: integration-test-cli
+      - name: Setup env
+        if: steps.changed-files.outputs.all
+        working-directory: libs/cli/examples
+        run: cat .env.example > .env
       - name: Install cli globally
-        if: (steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch')
+        if: steps.changed-files.outputs.all
         run: pip install -e .
-      - name: Build service ${{ matrix.example.name }}
-        if: (steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch')
-        working-directory: ${{ matrix.example.workdir }}
+      - name: Start service A
+        if: steps.changed-files.outputs.all
         run: |
-          langgraph build -t ${{ matrix.example.tag }}
-      - name: Test service ${{ matrix.example.name }}
-        if: ${{ (steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch') &&env.HAS_LANGSMITH_API_KEY == 'true' }}
-        working-directory: ${{ matrix.example.workdir }}
-        env:
-          LANGSMITH_API_KEY: ${{ secrets.LANGSMITH_API_KEY }}
+          timeout 60 langgraph test -c examples/langgraph.json --verbose || (exit "$(($? == 124 ? 0 : $?))")
+      - name: Start service B
+        if: steps.changed-files.outputs.all
+        working-directory: libs/cli/examples/graphs
         run: |
-          # Prepare environment file from local or parent example directory
-          if [ -f .env.example ]; then cp .env.example .env; elif [ -f ../.env.example ]; then cp ../.env.example .env && cp ../.env.example ../.env; fi
-          echo "LANGSMITH_API_KEY=${{ secrets.LANGSMITH_API_KEY }}" >> .env
-          if [ -f ../.env ]; then echo "LANGSMITH_API_KEY=${{ secrets.LANGSMITH_API_KEY }}" >> ../.env; fi
-          # Run the integration test using the built tag
-          REPO_ROOT=$(git rev-parse --show-toplevel)
-          timeout 60 python "$REPO_ROOT/.github/scripts/run_langgraph_cli_test.py" -t ${{ matrix.example.tag }}
-
-      - name: Build JS service
-        if: ${{ (steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch') &&matrix.example.name == 'A' }}
-        working-directory: libs/cli/js-examples
+          timeout 60 langgraph test --verbose || (exit "$(($? == 124 ? 0 : $?))")
+      - name: Start service C
+        if: steps.changed-files.outputs.all
+        working-directory: libs/cli/examples/graphs_reqs_a
         run: |
-          langgraph build -t langgraph-test-e
-
-      - name: Build JS monorepo service
-        if: ${{ (steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch') &&matrix.example.name == 'A' }}
-        working-directory: libs/cli/js-monorepo-example
+          timeout 60 langgraph test --verbose || (exit "$(($? == 124 ? 0 : $?))")
+      - name: Start service D
+        if: steps.changed-files.outputs.all
+        working-directory: libs/cli/examples/graphs_reqs_b
         run: |
-          langgraph build -t langgraph-test-f -c apps/agent/langgraph.json --build-command "yarn run turbo build" --install-command "yarn install"
-
-      - name: Build Python monorepo service
-        if: ${{ (steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch') &&matrix.example.name == 'A' }}
-        working-directory: libs/cli/python-monorepo-example
-        run: |
-          langgraph build -t langgraph-test-g -c apps/agent/langgraph.json
-      - name: Test Python monorepo service
-        if: ${{ (steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch') &&matrix.example.name == 'A' && env.HAS_LANGSMITH_API_KEY == 'true' }}
-        working-directory: libs/cli/python-monorepo-example
-        env:
-          LANGSMITH_API_KEY: ${{ secrets.LANGSMITH_API_KEY }}
-        run: |
-          cp apps/agent/.env.example apps/agent/.env
-          echo "LANGSMITH_API_KEY=${{ secrets.LANGSMITH_API_KEY }}" >> apps/agent/.env
-          timeout 60 python ../../../.github/scripts/run_langgraph_cli_test.py -t langgraph-test-g -c apps/agent/langgraph.json
-
-      - name: Build prerelease reqs service
-        if: ${{ (steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch') &&matrix.example.name == 'A' }}
-        working-directory: libs/cli/examples/graph_prerelease_reqs
-        run: |
-          langgraph build -t langgraph-test-h
-      - name: Test prerelease reqs service
-        if: ${{ (steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch') &&matrix.example.name == 'A' && env.HAS_LANGSMITH_API_KEY == 'true' }}
-        working-directory: libs/cli/examples/graph_prerelease_reqs
-        env:
-          LANGSMITH_API_KEY: ${{ secrets.LANGSMITH_API_KEY }}
-        run: |
-          cp ../.env.example .env
-          echo "LANGSMITH_API_KEY=${{ secrets.LANGSMITH_API_KEY }}" >> .env
-          timeout 60 python ../../../../.github/scripts/run_langgraph_cli_test.py -t langgraph-test-h
-          echo "Finished starting up langgraph-test-h"
-          LANGGRAPH_VERSION=$(docker run --rm --entrypoint "" langgraph-test-h python -c "import sys; from importlib.metadata import version; v = version('langgraph'); print(v);")
-          if [ "$LANGGRAPH_VERSION" != "1.1.5" ]; then
-            echo "LANGGRAPH_VERSION != 1.1.5; $LANGGRAPH_VERSION"
-            exit 1
-          fi
-          LANGCHAIN_OPENAI_VERSION=$(docker run --rm --entrypoint "" langgraph-test-h python -c "import sys; from importlib.metadata import version; v = version('langchain-openai'); print(v);")
-          if [ "$LANGCHAIN_OPENAI_VERSION" != "1.1.14" ]; then
-            echo "LANGCHAIN_OPENAI_VERSION != 1.1.14; $LANGCHAIN_OPENAI_VERSION"
-            exit 1
-          fi
-          LANGCHAIN_ANTHROPIC_VERSION=$(docker run --rm --entrypoint "" langgraph-test-h python -c "import sys; from importlib.metadata import version; v = version('langchain-anthropic'); print(v);")
-          if [ "$LANGCHAIN_ANTHROPIC_VERSION" != "1.0.0a5" ]; then
-            echo "LANGCHAIN_ANTHROPIC_VERSION != 1.0.0a5; $LANGCHAIN_ANTHROPIC_VERSION"
-            exit 1
-          fi
-
-      - name: Build and test prerelease reqs fail service
-        if: ${{ (steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch') &&matrix.example.name == 'A' }}
-        working-directory: libs/cli/examples/graph_prerelease_reqs_fail
-        run: |
-          langgraph build -t langgraph-test-i || [ $? -eq 1 ]
-
-      - name: Build uv simple service
-        if: ${{ (steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch') &&matrix.example.name == 'A' }}
-        working-directory: libs/cli/uv-examples/simple
-        run: |
-          langgraph build -t langgraph-test-uv-simple
-      - name: Test uv simple service
-        if: ${{ (steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch') &&matrix.example.name == 'A' && env.HAS_LANGSMITH_API_KEY == 'true' }}
-        working-directory: libs/cli/uv-examples/simple
-        env:
-          LANGSMITH_API_KEY: ${{ secrets.LANGSMITH_API_KEY }}
-        run: |
-          cp .env.example .env
-          echo "LANGSMITH_API_KEY=${{ secrets.LANGSMITH_API_KEY }}" >> .env
-          timeout 60 python ../../../../.github/scripts/run_langgraph_cli_test.py -t langgraph-test-uv-simple
-
-      - name: Build uv monorepo service
-        if: ${{ (steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch') &&matrix.example.name == 'A' }}
-        working-directory: libs/cli/uv-examples/monorepo/apps/agent
-        run: |
-          langgraph build -t langgraph-test-uv-monorepo
-      - name: Test uv monorepo service
-        if: ${{ (steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch') &&matrix.example.name == 'A' && env.HAS_LANGSMITH_API_KEY == 'true' }}
-        working-directory: libs/cli/uv-examples/monorepo/apps/agent
-        env:
-          LANGSMITH_API_KEY: ${{ secrets.LANGSMITH_API_KEY }}
-        run: |
-          cp .env.example .env
-          echo "LANGSMITH_API_KEY=${{ secrets.LANGSMITH_API_KEY }}" >> .env
-          timeout 60 python ../../../../../../.github/scripts/run_langgraph_cli_test.py -t langgraph-test-uv-monorepo
+          timeout 60 langgraph test --verbose || (exit "$(($? == 124 ? 0 : $?))")

.github/workflows/_lint.yml

@@ -8,10 +8,9 @@ on:
         type: string
         description: "From which folder this pipeline executes"
 
-permissions:
-  contents: read
-
 env:
+  POETRY_VERSION: "1.7.1"
+
   # This env var allows us to get inline annotations when ruff has complaints.
   RUFF_OUTPUT_FORMAT: github
 
@@ -28,41 +27,62 @@ jobs:
         # Starting new jobs is also relatively slow,
         # so linting on fewer versions makes CI faster.
         python-version:
-          - "3.12"
+          - "3.9"
+          - "3.11"
     name: "lint #${{ matrix.python-version }}"
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - name: Get changed files
         id: changed-files
-        if: github.event_name != 'workflow_dispatch'
-        uses: Ana06/get-changed-files@25f79e676e7ea1868813e21465014798211fad8c # v2.3.0
+        uses: Ana06/get-changed-files@v2.2.0
         with:
           filter: "${{ inputs.working-directory }}/**"
-      - name: Set up Python ${{ matrix.python-version }}
-        if: steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch'
-        uses: ./.github/actions/uv_setup
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        if: steps.changed-files.outputs.all
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ matrix.python-version }}
-          cache-suffix: lint-${{ inputs.working-directory }}
+          poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
+          cache-key: lint-with-extras
+
+      - name: Check Poetry File
+        if: steps.changed-files.outputs.all
+        shell: bash
+        working-directory: ${{ inputs.working-directory }}
+        run: poetry check
+
+      - name: Check lock file
+        if: steps.changed-files.outputs.all
+        shell: bash
+        working-directory: ${{ inputs.working-directory }}
+        run: poetry lock --check
 
       - name: Install dependencies
-        if: steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch'
+        if: steps.changed-files.outputs.all
+        # Also installs dev/lint/test/typing dependencies, to ensure we have
+        # type hints for as many of our libraries as possible.
+        # This helps catch errors that require dependencies to be spotted, for example:
+        # https://github.com/langchain-ai/langchain/pull/10249/files#diff-935185cd488d015f026dcd9e19616ff62863e8cde8c0bee70318d3ccbca98341
+        #
+        # If you change this configuration, make sure to change the `cache-key`
+        # in the `poetry_setup` action above to stop using the old cache.
+        # It doesn't matter how you change it, any change will cause a cache-bust.
         working-directory: ${{ inputs.working-directory }}
-        run: uv sync --frozen --group lint
+        run: poetry install --with dev
 
       - name: Get .mypy_cache to speed up mypy
-        if: steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch'
-        uses: actions/cache@v5
+        if: steps.changed-files.outputs.all
+        uses: actions/cache@v3
         env:
           SEGMENT_DOWNLOAD_TIMEOUT_MIN: "2"
         with:
           path: |
             ${{ inputs.working-directory }}/.mypy_cache
-          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/uv.lock', inputs.working-directory)) }}
+          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
 
       - name: Analysing package code with our lint
-        if: steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch'
+        if: steps.changed-files.outputs.all
         working-directory: ${{ inputs.working-directory }}
         run: |
           if make lint_package > /dev/null 2>&1; then
@@ -73,22 +93,31 @@ jobs:
           fi
 
       - name: Install test dependencies
-        if: steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch'
+        if: steps.changed-files.outputs.all
+        # Also installs dev/lint/test/typing dependencies, to ensure we have
+        # type hints for as many of our libraries as possible.
+        # This helps catch errors that require dependencies to be spotted, for example:
+        # https://github.com/langchain-ai/langchain/pull/10249/files#diff-935185cd488d015f026dcd9e19616ff62863e8cde8c0bee70318d3ccbca98341
+        #
+        # If you change this configuration, make sure to change the `cache-key`
+        # in the `poetry_setup` action above to stop using the old cache.
+        # It doesn't matter how you change it, any change will cause a cache-bust.
         working-directory: ${{ inputs.working-directory }}
-        run: uv sync --group lint
+        run: |
+          poetry install --with dev
 
       - name: Get .mypy_cache_test to speed up mypy
-        if: steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch'
-        uses: actions/cache@v5
+        if: steps.changed-files.outputs.all
+        uses: actions/cache@v3
         env:
           SEGMENT_DOWNLOAD_TIMEOUT_MIN: "2"
         with:
           path: |
             ${{ inputs.working-directory }}/.mypy_cache_test
-          key: mypy-test-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/uv.lock', inputs.working-directory)) }}
+          key: mypy-test-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
 
       - name: Analysing tests with our lint
-        if: steps.changed-files.outputs.all || github.event_name == 'workflow_dispatch'
+        if: steps.changed-files.outputs.all
         working-directory: ${{ inputs.working-directory }}
         run: |
           if make lint_tests > /dev/null 2>&1; then

.github/workflows/_test.yml

@@ -8,8 +8,8 @@ on:
         type: string
         description: "From which folder this pipeline executes"
 
-permissions:
-  contents: read
+env:
+  POETRY_VERSION: "1.7.1"
 
 jobs:
   build:
@@ -17,39 +17,42 @@ jobs:
     strategy:
       matrix:
         python-version:
+          - "3.9"
           - "3.10"
           - "3.11"
           - "3.12"
-          - "3.13"
-          - "3.14"
-
     name: "test #${{ matrix.python-version }}"
     steps:
-      - uses: actions/checkout@v6
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: ./.github/actions/uv_setup
+      - uses: actions/checkout@v4
+      - name: Get changed files
+        id: changed-files
+        uses: Ana06/get-changed-files@v2.2.0
+        with:
+          filter: "${{ inputs.working-directory }}/**"
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        if: steps.changed-files.outputs.all
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ matrix.python-version }}
-          cache-suffix: test-${{ inputs.working-directory }}
+          poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
-      - name: Login to Docker Hub
-        uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2 # v4
-        if: ${{ !github.event.pull_request.head.repo.fork }}
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_RO_TOKEN }}
+          cache-key: core
 
       - name: Install dependencies
+        if: steps.changed-files.outputs.all
         shell: bash
         working-directory: ${{ inputs.working-directory }}
-        run: uv sync --frozen --group test --no-dev
+        run: poetry install --with dev
 
-      - name: Run tests
+      - name: Run core tests
+        if: steps.changed-files.outputs.all
         shell: bash
         working-directory: ${{ inputs.working-directory }}
-        run: make test
+        run: |
+          make test
 
       - name: Ensure the tests did not create any additional files
+        if: steps.changed-files.outputs.all
         shell: bash
         working-directory: ${{ inputs.working-directory }}
         run: |

.github/workflows/_test_langgraph.yml

@@ -1,65 +0,0 @@
-name: test
-
-on:
-  workflow_call:
-
-permissions:
-  contents: read
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.10"
-          - "3.11"
-          - "3.12"
-          - "3.13"
-          - "3.14"
-
-    defaults:
-      run:
-        working-directory: libs/langgraph
-    name: "test #${{ matrix.python-version }}"
-    steps:
-      - uses: actions/checkout@v6
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: ./.github/actions/uv_setup
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache-suffix: "test-langgraph"
-          working-directory: libs/langgraph
-      - name: Login to Docker Hub
-        uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2 # v4
-        if: ${{ !github.event.pull_request.head.repo.fork }}
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_RO_TOKEN }}
-
-      - name: Install dependencies
-        shell: bash
-        run: uv sync --frozen --group test --no-dev
-
-      - name: Run tests
-        shell: bash
-        run: make test_parallel
-
-      - name: Run strict msgpack pregel tests
-        if: ${{ matrix.python-version == '3.13' }}
-        shell: bash
-        env:
-          LANGGRAPH_STRICT_MSGPACK: "true"
-        run: make test TEST="tests/test_pregel.py tests/test_pregel_async.py"
-
-      - name: Ensure the tests did not create any additional files
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(git status)"
-          echo "$STATUS"
-
-          # grep will exit non-zero if the target message isn't found,
-          # and `set -e` above will cause the step to fail.
-          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/_test_release.yml

@@ -9,13 +9,12 @@ on:
         description: "From which folder this pipeline executes"
 
 env:
+  POETRY_VERSION: "1.7.1"
   PYTHON_VERSION: "3.10"
 
-permissions:
-  contents: read
-
 jobs:
   build:
+    if: github.ref == 'refs/heads/main'
     runs-on: ubuntu-latest
 
     outputs:
@@ -23,14 +22,15 @@ jobs:
       version: ${{ steps.check-version.outputs.version }}
 
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ env.PYTHON_VERSION }}
-        uses: ./.github/actions/uv_setup
+      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ env.PYTHON_VERSION }}
-          cache-suffix: "release"
+          poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
+          cache-key: release
 
       # We want to keep this build stage *separate* from the release stage,
       # so that there's no sharing of permissions between them.
@@ -44,11 +44,11 @@ jobs:
       # > from the publish job.
       # https://github.com/pypa/gh-action-pypi-publish#non-goals
       - name: Build project for distribution
-        run: uv build
+        run: poetry build
         working-directory: ${{ inputs.working-directory }}
 
       - name: Upload build
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v4
         with:
           name: test-dist
           path: ${{ inputs.working-directory }}/dist/
@@ -58,8 +58,8 @@ jobs:
         shell: bash
         working-directory: ${{ inputs.working-directory }}
         run: |
-          echo pkg-name=$(grep -m 1 "^name = " pyproject.toml | cut -d '"' -f 2)
-          echo version=$(grep -m 1 "^version = " pyproject.toml | cut -d '"' -f 2)
+          echo pkg-name="$(poetry version | cut -d ' ' -f 1)" >> $GITHUB_OUTPUT
+          echo version="$(poetry version --short)" >> $GITHUB_OUTPUT
 
   publish:
     needs:
@@ -74,15 +74,15 @@ jobs:
       id-token: write
 
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
 
-      - uses: actions/download-artifact@v8
+      - uses: actions/download-artifact@v4
         with:
           name: test-dist
           path: ${{ inputs.working-directory }}/dist/
 
       - name: Publish to test PyPI
-        uses: pypa/gh-action-pypi-publish@ed0c53931b1dc9bd32cbe73a98c7f6766f8a527e # release/v1
+        uses: pypa/gh-action-pypi-publish@release/v1
         with:
           packages-dir: ${{ inputs.working-directory }}/dist/
           verbose: true
@@ -93,5 +93,3 @@ jobs:
           # This is *only for CI use* and is *extremely dangerous* otherwise!
           # https://github.com/pypa/gh-action-pypi-publish#tolerating-release-package-file-duplicates
           skip-existing: true
-          # Temp workaround since attestations are on by default as of gh-action-pypi-publish v1.11.0
-          attestations: false

.github/workflows/baseline.yml

@@ -1,37 +0,0 @@
-name: baseline
-
-on:
-  workflow_dispatch:
-  push:
-    branches: [main]
-    paths:
-      - "libs/**"
-
-permissions:
-  contents: read
-
-jobs:
-  benchmark:
-    runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: libs/langgraph
-    steps:
-      - uses: actions/checkout@v6
-      - run: SHA=$(git rev-parse HEAD) && echo "SHA=$SHA" >> $GITHUB_ENV
-      - name: Set up Python 3.11
-        uses: ./.github/actions/uv_setup
-        with:
-          python-version: "3.11"
-          cache-suffix: "bench"
-          working-directory: libs/langgraph
-      - name: Install dependencies
-        run: uv sync --group test
-      - name: Run benchmarks
-        run: OUTPUT=out/benchmark-baseline.json make -s benchmark
-      - name: Save outputs
-        uses: actions/cache/save@v5
-        with:
-          key: ${{ runner.os }}-benchmark-baseline-${{ env.SHA }}
-          path: |
-            libs/langgraph/out/benchmark-baseline.json

.github/workflows/bench.yml

@@ -1,71 +0,0 @@
-name: bench
-
-on:
-  pull_request:
-    paths:
-      - "libs/**"
-
-permissions:
-  contents: read
-
-jobs:
-  benchmark:
-    runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: libs/langgraph
-    steps:
-      - uses: actions/checkout@v6
-      - id: files
-        name: Get changed files
-        uses: Ana06/get-changed-files@25f79e676e7ea1868813e21465014798211fad8c # v2.3.0
-        with:
-          format: json
-      - name: Set up Python 3.11
-        uses: ./.github/actions/uv_setup
-        with:
-          python-version: "3.11"
-          cache-suffix: "bench"
-          working-directory: libs/langgraph
-      - name: Install dependencies
-        run: uv sync --group test
-      - name: Download baseline
-        uses: actions/cache/restore@v5
-        with:
-          key: ${{ runner.os }}-benchmark-baseline
-          restore-keys: |
-            ${{ runner.os }}-benchmark-baseline-
-          fail-on-cache-miss: true
-          path: |
-            libs/langgraph/out/benchmark-baseline.json
-      - name: Run benchmarks
-        id: benchmark
-        run: |
-          {
-            echo 'OUTPUT<<EOF'
-            make -s benchmark-fast
-            echo EOF
-          } >> "$GITHUB_OUTPUT"
-      - name: Compare benchmarks
-        id: compare
-        run: |
-          {
-            echo 'OUTPUT<<EOF'
-            mv out/benchmark-baseline.json out/main.json
-            mv out/benchmark.json out/changes.json
-            uv run pyperf compare_to out/main.json out/changes.json --table --group-by-speed
-            echo EOF
-          } >> "$GITHUB_OUTPUT"
-      - name: Annotation
-        uses: actions/github-script@v8
-        with:
-          script: |
-            const file = JSON.parse(`${{ steps.files.outputs.added_modified_renamed }}`)[0]
-            core.notice(`${{ steps.benchmark.outputs.OUTPUT }}`, {
-              title: 'Benchmark results',
-              file,
-            })
-            core.notice(`${{ steps.compare.outputs.OUTPUT }}`, {
-              title: 'Comparison against main',
-              file,
-            })

.github/workflows/ci.yml

@@ -1,183 +1,108 @@
 ---
-name: CI
+    name: CI
 
-on:
-  workflow_dispatch:
-  push:
-    branches:
-      - main
-  pull_request:
-  
+    on:
+      push:
+        branches: [main]
+      pull_request:
 
-permissions:
-  contents: read
+    # If another push to the same PR or branch happens while this workflow is still running,
+    # cancel the earlier run in favor of the next run.
+    #
+    # There's no point in testing an outdated version of the code. GitHub only allows
+    # a limited number of job runners to be active at the same time, so it's better to cancel
+    # pointless jobs early so that more useful jobs can run sooner.
+    concurrency:
+      group: ${{ github.workflow }}-${{ github.ref }}
+      cancel-in-progress: true
 
-# If another push to the same PR or branch happens while this workflow is still running,
-# cancel the earlier run in favor of the next run.
-#
-# There's no point in testing an outdated version of the code. GitHub only allows
-# a limited number of job runners to be active at the same time, so it's better to cancel
-# pointless jobs early so that more useful jobs can run sooner.
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  changes:
-    runs-on: ubuntu-latest
-    outputs:
-      python: ${{ steps.filter.outputs.python || 'true' }}
-      deps: ${{ steps.filter.outputs.deps || 'true' }}
-    steps:
-      - uses: actions/checkout@v6
-      - uses: dorny/paths-filter@fbd0ab8f3e69293af611ebaee6363fc25e6d187d # v4
-        if: github.event_name != 'workflow_dispatch'
-        id: filter
-        with:
-          filters: |
-            python:
-              - 'libs/langgraph/**'
-              - 'libs/sdk-py/**'
-              - 'libs/cli/**'
-              - 'libs/checkpoint/**'
-              - 'libs/checkpoint-sqlite/**'
-              - 'libs/checkpoint-postgres/**'
-              - 'libs/checkpoint-conformance/**'
-              - 'libs/prebuilt/**'
-            deps:
-              - '**/pyproject.toml'
-              - '**/uv.lock'
-
-  lint:
-    needs: changes
-    name: cd ${{ matrix.working-directory }}
-    strategy:
-      matrix:
-        working-directory:
-          [
-            "libs/langgraph",
-            "libs/sdk-py",
-            "libs/cli",
-            "libs/checkpoint",
-            "libs/checkpoint-sqlite",
-            "libs/checkpoint-postgres",
-            "libs/checkpoint-conformance",
-            "libs/prebuilt",
-          ]
-    if: needs.changes.outputs.python == 'true' || needs.changes.outputs.deps == 'true'
-    uses: ./.github/workflows/_lint.yml
-    with:
-      working-directory: ${{ matrix.working-directory }}
-    secrets: inherit
-
-  test:
-    needs: changes
-    name: cd ${{ matrix.working-directory }}
-    strategy:
-      matrix:
-        working-directory:
-          [
-            "libs/cli",
-            "libs/checkpoint",
-            "libs/checkpoint-sqlite",
-            "libs/checkpoint-postgres",
-            "libs/checkpoint-conformance",
-            "libs/prebuilt",
-            "libs/sdk-py",
-          ]
-    if: needs.changes.outputs.python == 'true' || needs.changes.outputs.deps == 'true'
-    uses: ./.github/workflows/_test.yml
-    with:
-      working-directory: ${{ matrix.working-directory }}
-    secrets: inherit
-
-  # NOTE: we're testing langgraph separately because it requires a different matrix
-  test-langgraph:
-    needs: changes
-    if: needs.changes.outputs.python == 'true' || needs.changes.outputs.deps == 'true'
-    name: "cd libs/langgraph"
-    uses: ./.github/workflows/_test_langgraph.yml
-    secrets: inherit
-
-  check-sdk-methods:
-    needs: changes
-    if: needs.changes.outputs.python == 'true'
-    name: "Check SDK methods matching"
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v6
-      - name: Set up Python
-        uses: actions/setup-python@v6
-        with:
-          python-version: "3.11"
-      - name: Run check_sdk_methods script
-        run: python .github/scripts/check_sdk_methods.py
-
-  check-schema:
-    needs: changes
-    if: needs.changes.outputs.python == 'true'
-    name: "Check CLI schema hasn't changed #${{ matrix.python-version }}"
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.13"
-    steps:
-      - uses: actions/checkout@v6
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: ./.github/actions/uv_setup
-        with:
-          python-version: "3.13"
-          cache-suffix: "schema-check-cli"
-          working-directory: libs/cli
-      - name: Install CLI dependencies
-        run: |
-          cd libs/cli
-          uv sync
-      - name: Generate schema and check for changes
-        run: |
-          cd libs/cli
-          # Create a temporary copy of the current schema
-          cp schemas/schema.json schemas/schema.current.json
-          # Generate new schema
-          uv run python generate_schema.py
-          # Compare the new schema with the original
-          if ! diff -q schemas/schema.json schemas/schema.current.json > /dev/null; then
-            echo "Error: Langgraph.json configuration schema has changed. Please run 'uv run python generate_schema.py' in the libs/cli directory and commit the changes."
-            diff schemas/schema.json schemas/schema.current.json
-            exit 1
-          fi
-          echo "Schema check passed - no changes detected"
-
-  integration-test:
-    needs: changes
-    if: needs.changes.outputs.python == 'true' || needs.changes.outputs.deps == 'true'
-    name: CLI integration test
-    uses: ./.github/workflows/_integration_test.yml
-    secrets: inherit
-
-  ci_success:
-    name: "CI Success"
-    needs:
-      [
-        lint,
-        test,
-        test-langgraph,
-        check-sdk-methods,
-        check-schema,
-        integration-test,
-      ]
-    if: |
-      always()
-    runs-on: ubuntu-latest
     env:
-      JOBS_JSON: ${{ toJSON(needs) }}
-      RESULTS_JSON: ${{ toJSON(needs.*.result) }}
-      EXIT_CODE: ${{!contains(needs.*.result, 'failure') && !contains(needs.*.result, 'cancelled') && '0' || '1'}}
-    steps:
-      - name: "CI Success"
-        run: |
-          echo $JOBS_JSON
-          echo $RESULTS_JSON
-          echo "Exiting with $EXIT_CODE"
-          exit $EXIT_CODE
+      POETRY_VERSION: "1.7.1"
+
+    jobs:
+      build:
+        runs-on: ubuntu-latest
+        steps:
+          - uses: actions/checkout@v4
+          - uses: actions/setup-python@v5
+            with:
+              python-version: '3.10'
+
+      lint:
+        name: cd ${{ matrix.working-directory }}
+        needs: [ build ]
+        strategy:
+          matrix:
+            working-directory: [
+                "libs/langgraph",
+                "libs/sdk-py",
+                "libs/cli"
+            ]
+        uses: ./.github/workflows/_lint.yml
+        with:
+          working-directory: ${{ matrix.working-directory }}
+        secrets: inherit
+
+      test:
+        name: cd ${{ matrix.working-directory }}
+        needs: [ build ]
+        strategy:
+          matrix:
+            working-directory: [
+                "libs/langgraph",
+                "libs/cli"
+            ]
+        uses: ./.github/workflows/_test.yml
+        with:
+          working-directory: ${{ matrix.working-directory }}
+        secrets: inherit
+
+      integration-test:
+        name: CLI integration test
+        needs: [ build ]
+        uses: ./.github/workflows/_integration_test.yml
+        secrets: inherit
+
+      lint-js:
+        runs-on: ubuntu-latest
+        needs: [ build ]
+        strategy:
+          matrix:
+            working-directory:
+              - "libs/sdk-js"
+        defaults:
+          run:
+            working-directory: ${{ matrix.working-directory }}
+        steps:
+          - uses: actions/checkout@v3
+          - name: Setup Node.js (LTS)
+            uses: actions/setup-node@v3
+            with:
+              node-version: "20"
+              cache: "yarn"
+              cache-dependency-path: ${{ matrix.working-directory }}/yarn.lock
+          - name: Install dependencies
+            run: yarn install
+          - name: Run lint
+            run: yarn lint
+          - name: Build
+            run: yarn build
+
+      ci_success:
+        name: "CI Success"
+        needs: [build, lint, lint-js, test, integration-test]
+        if: |
+          always()
+        runs-on: ubuntu-latest
+        env:
+          JOBS_JSON: ${{ toJSON(needs) }}
+          RESULTS_JSON: ${{ toJSON(needs.*.result) }}
+          EXIT_CODE: ${{!contains(needs.*.result, 'failure') && !contains(needs.*.result, 'cancelled') && '0' || '1'}}
+        steps:
+          - name: "CI Success"
+            run: |
+              echo $JOBS_JSON
+              echo $RESULTS_JSON
+              echo "Exiting with $EXIT_CODE"
+              exit $EXIT_CODE
+    

.github/workflows/codespell.yml

@@ -0,0 +1,39 @@
+---
+    name: CI / cd . / make spell_check
+    
+    on:
+      push:
+        branches: [main]
+      pull_request:
+        branches: [main]
+    
+    permissions:
+      contents: read
+    
+    jobs:
+      codespell:
+        name: (Check for spelling errors)
+        runs-on: ubuntu-latest
+    
+        steps:
+          - name: Checkout
+            uses: actions/checkout@v4
+    
+          - name: Install Dependencies
+            run: |
+              pip install toml codespell jupytext
+    
+          - name: Extract Ignore Words List
+            run: |
+              # Use a Python script to extract the ignore words list from pyproject.toml
+              python .github/workflows/extract_ignored_words_list.py
+            id: extract_ignore_words
+    
+          - name: Codespell
+            uses: codespell-project/actions-codespell@v2
+            with:
+              skip: '*.ambr,*.lock,*.ipynb'
+              ignore_words_list: ${{ steps.extract_ignore_words.outputs.ignore_words_list }}
+          # We do this to avoid spellchecking cell outputs
+          - name: Codespell Notebooks
+            run: make codespell

.github/workflows/deploy-redirects.yml

@@ -1,49 +0,0 @@
-name: Deploy Redirects to GitHub Pages
-
-on:
-  push:
-    branches:
-      - main
-    paths:
-      - 'docs/**'
-      - '.github/workflows/deploy-redirects.yml'
-  workflow_dispatch:
-
-permissions:
-  contents: read
-  pages: write
-  id-token: write
-
-concurrency:
-  group: "pages"
-  cancel-in-progress: false
-
-jobs:
-  deploy:
-    environment:
-      name: github-pages
-      url: ${{ steps.deployment.outputs.page_url }}
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v6
-
-      - name: Setup Python
-        uses: actions/setup-python@v6
-        with:
-          python-version: '3.11'
-
-      - name: Generate redirect files
-        run: python docs/generate_redirects.py
-
-      - name: Setup Pages
-        uses: actions/configure-pages@v6
-
-      - name: Upload artifact
-        uses: actions/upload-pages-artifact@v4
-        with:
-          path: 'docs/_site'
-
-      - name: Deploy to GitHub Pages
-        id: deployment
-        uses: actions/deploy-pages@v5

.github/workflows/deploy_docs.yml

@@ -0,0 +1,68 @@
+name: Deploy Docs
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+  workflow_dispatch:
+
+env:
+  POETRY_VERSION: "1.7.1"
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+concurrency:
+  group: "pages"
+  cancel-in-progress: false
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: "3.12"
+          poetry-version: ${{ env.POETRY_VERSION }}
+          cache-key: docs
+
+      - name: Install dependencies
+        run: |
+          poetry install --with docs
+
+      - name: Build site
+        run: make build-docs
+        env:
+          MKDOCS_GIT_COMMITTERS_APIKEY: ${{ secrets.MKDOCS_GIT_COMMITTERS_APIKEY }}
+
+      - name: Configure GitHub Pages
+        if: github.ref == 'refs/heads/main'
+        uses: actions/configure-pages@v4
+
+      - name: Upload Pages Artifact
+        if: github.ref == 'refs/heads/main'
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: ./docs/site/
+
+      - name: Deploy to GitHub Pages
+        if: github.ref == 'refs/heads/main'
+        id: deployment
+        uses: actions/deploy-pages@v4
+
+      - name: Deploy Pull Request Preview
+        if: github.event_name == 'pull_request'
+        uses: actions/upload-artifact@v2
+        with:
+          name: pr-preview-${{ github.event.number }}
+          path: ./docs/site/

.github/workflows/extract_ignored_words_list.py

@@ -0,0 +1,10 @@
+import toml
+
+pyproject_toml = toml.load("libs/langgraph/pyproject.toml")
+
+# Extract the ignore words list (adjust the key as per your TOML structure)
+ignore_words_list = (
+    pyproject_toml.get("tool", {}).get("codespell", {}).get("ignore-words-list")
+)
+
+print(f"::set-output name=ignore_words_list::{ignore_words_list}")  # noqa: T201

.github/workflows/link_check.yml

@@ -0,0 +1,87 @@
+name: Check Docs & Links
+
+on:
+  pull_request:
+    branches:
+      - main
+  push:
+    branches:
+      - main
+  schedule:
+    - cron: "0 5 * * *"
+  workflow_dispatch:
+
+env:
+  POETRY_VERSION: "1.7.1"
+
+jobs:
+  markdown-link-check:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Check links in Markdown files
+        uses: gaurav-nelson/github-action-markdown-link-check@v1
+        with:
+          folder-path: "examples/,docs/"
+          check-modified-files-only: ${{ github.event_name != 'schedule' }}
+          file-path: "./README.md"
+          config-file: "./.markdown-link-check.config.json"
+
+  notebook-link-check:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+      - name: Set up Python 3.x + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: "3.11"
+          poetry-version: ${{ env.POETRY_VERSION }}
+          cache-key: core
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          poetry install --with docs
+          poetry run pip install -U pytest pytest-check-links langsmith langchain GitPython
+
+      - name: Check links in notebooks
+        env:
+          LANGCHAIN_API_KEY: test
+        run: |
+          if [ "${{ github.event_name }}" == "schedule" ] || [ "${{ github.event_name }}" == "workflow_dispatch" ] || ([ "${{ github.event_name }}" == "push" ] && [ "${{ github.ref }}" == "refs/heads/main" ]); then
+            echo "Running link check on all notebooks in examples directory..."
+            poetry run pytest -v --check-links-ignore "https://(api|web)\.smith\.langchain\.com/.*" --check-links-ignore "https://x.com/.*" --check-links examples
+          else
+            echo "Fetching changes from origin/main..."
+            git fetch origin main
+            echo "Checking for changed notebook files..."
+            CHANGED_FILES=$(git diff --name-only --diff-filter=d origin/main | grep '\.ipynb$' || true)
+            echo "Changed files: ${CHANGED_FILES}"
+            if [ -n "${CHANGED_FILES}" ]; then
+              echo "Running link check on changed notebook files..."
+              poetry run pytest -v --check-links-ignore "https://(api|web)\.smith\.langchain\.com/.*" --check-links-ignore "https://x.com/.*" --check-links ${CHANGED_FILES} || ([ $? = 5 ] && exit 0 || exit $?)
+            else
+              echo "No notebook files changed."
+            fi
+          fi
+  check-readmes-synced:
+    # This checks that the repo README.md is identical to the libs/langgraph/README.md
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Check README.md is in sync
+        run: |
+            if ! diff -q README.md libs/langgraph/README.md >/dev/null; then
+            echo "README.md is out of sync with libs/langgraph/README.md"
+            diff -C 3 README.md libs/langgraph/README.md
+            exit 1
+            fi

.github/workflows/pr_lint.yml

@@ -1,46 +0,0 @@
-name: PR Title Lint
-
-permissions:
-  pull-requests: read
-
-on:
-  pull_request:
-    types: [opened, edited, synchronize]
-
-jobs:
-  lint-pr-title:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Validate PR Title
-        uses: amannn/action-semantic-pull-request@48f256284bd46cdaab1048c3721360e808335d50 # v6
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          types: |
-            feat
-            fix
-            docs
-            style
-            refactor
-            perf
-            test
-            build
-            ci
-            chore
-            revert
-            release
-          scopes: |
-            checkpoint
-            checkpoint-postgres
-            checkpoint-sqlite
-            cli
-            langgraph
-            prebuilt
-            scheduler-kafka
-            sdk-py
-            docs
-            ci
-            deps
-          requireScope: false
-          ignoreLabels: |
-            ignore-lint-pr-title

.github/workflows/release.yml

@@ -6,16 +6,15 @@ on:
       working-directory:
         required: true
         type: string
-        default: "libs/langgraph"
-
-permissions:
-  contents: read
+        default: 'libs/langgraph'
 
 env:
   PYTHON_VERSION: "3.11"
+  POETRY_VERSION: "1.7.1"
 
 jobs:
   build:
+    if: github.ref == 'refs/heads/main'
     runs-on: ubuntu-latest
 
     outputs:
@@ -25,14 +24,15 @@ jobs:
       tag: ${{ steps.check-version.outputs.tag }}
 
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
 
-      - name: Set up Python
-        uses: ./.github/actions/uv_setup
+      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ env.PYTHON_VERSION }}
-          cache-suffix: "release"
+          poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
+          cache-key: release
 
       # We want to keep this build stage *separate* from the release stage,
       # so that there's no sharing of permissions between them.
@@ -46,11 +46,11 @@ jobs:
       # > from the publish job.
       # https://github.com/pypa/gh-action-pypi-publish#non-goals
       - name: Build project for distribution
-        run: uv build
+        run: poetry build
         working-directory: ${{ inputs.working-directory }}
 
       - name: Upload build
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v4
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
@@ -60,14 +60,8 @@ jobs:
         shell: bash
         working-directory: ${{ inputs.working-directory }}
         run: |
-          PKG_NAME=$(grep -m 1 "^name = " pyproject.toml | cut -d '"' -f 2)
-          if grep -q 'dynamic.*=.*\[.*"version".*\]' pyproject.toml; then
-            # handle dynamic versioning
-            DIR_NAME=$(echo "$PKG_NAME" | tr '-' '_')
-            VERSION=$(grep -m 1 '^__version__' "${DIR_NAME}/__init__.py" | cut -d '"' -f 2)
-          else
-            VERSION=$(grep -m 1 "^version = " pyproject.toml | cut -d '"' -f 2)
-          fi
+          PKG_NAME="$(poetry version | cut -d ' ' -f 1)"
+          VERSION="$(poetry version --short)"
           SHORT_PKG_NAME="$(echo "$PKG_NAME" | sed -e 's/langgraph//g' -e 's/-//g')"
           if [ -z $SHORT_PKG_NAME ]; then
             TAG="$VERSION"
@@ -86,7 +80,7 @@ jobs:
     outputs:
       release-body: ${{ steps.generate-release-body.outputs.release-body }}
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           repository: langchain-ai/langgraph
           path: langgraph
@@ -110,7 +104,7 @@ jobs:
             REGEX="^$SHORT_PKG_NAME==\\d+\\.\\d+\\.\\d+((a|b|rc)\\d+)?\$"
           fi
           echo $REGEX
-          PREV_TAG=$(git tag --sort=-creatordate | grep -P $REGEX | head -1 || echo "")
+          PREV_TAG=$(git tag --sort=-creatordate | grep -P $REGEX | head -1)
           echo $PREV_TAG
           if [ "$TAG" == "$PREV_TAG" ]; then
             echo "No new version to release"
@@ -142,10 +136,9 @@ jobs:
     needs:
       - build
       - release-notes
-    permissions:
-      contents: read
-      id-token: write
-    uses: ./.github/workflows/_test_release.yml
+    permissions: write-all
+    uses:
+      ./.github/workflows/_test_release.yml
     with:
       working-directory: ${{ inputs.working-directory }}
     secrets: inherit
@@ -157,7 +150,7 @@ jobs:
       - test-pypi-publish
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
 
       # We explicitly *don't* set up caching here. This ensures our tests are
       # maximally sensitive to catching breakage.
@@ -172,11 +165,11 @@ jobs:
       # - The package is published, and it breaks on the missing dependency when
       #   used in the real world.
 
-      - name: Set up Python
-        uses: ./.github/actions/uv_setup
+      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ env.PYTHON_VERSION }}
-          enable-cache: false
+          poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
 
       - name: Import published package
@@ -195,34 +188,24 @@ jobs:
         # - attempt install again after 5 seconds if it fails because there is
         #   sometimes a delay in availability on test pypi
         run: |
-          uv run pip install \
+          poetry run pip install \
             --extra-index-url https://test.pypi.org/simple/ \
             "$PKG_NAME==$VERSION" || \
           ( \
             sleep 5 && \
-            uv run pip install \
+            poetry run pip install \
               --extra-index-url https://test.pypi.org/simple/ \
               "$PKG_NAME==$VERSION" \
           )
 
-          if [[ "$PKG_NAME" == *prebuilt* ]]; then
-            uv run pip install langgraph
-          fi
+          # Replace all dashes in the package name with underscores,
+          # since that's how Python imports packages with dashes in the name.
+          IMPORT_NAME="$(echo "$PKG_NAME" | sed s/-/_/g)"
 
-          if [[ "$PKG_NAME" == *checkpoint* || "$PKG_NAME" == *prebuilt* ]]; then
-            # since checkpoint packages are namespace packages, import them with . convention
-            # i.e. import langgraph.checkpoint or langgraph.checkpoint.sqlite
-            IMPORT_NAME="$(echo "$PKG_NAME" | sed s/-/./g)"
-          else
-            # Replace all dashes in the package name with underscores,
-            # since that's how Python imports packages with dashes in the name.
-            IMPORT_NAME="$(echo "$PKG_NAME" | sed s/-/_/g)"
-          fi
-
-          uv run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"
+          poetry run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"
 
       - name: Import test dependencies
-        run: uv sync --group test
+        run: poetry install --with dev
         working-directory: ${{ inputs.working-directory }}
 
       # Overwrite the local version of the package with the test PyPI version.
@@ -233,7 +216,7 @@ jobs:
           PKG_NAME: ${{ needs.build.outputs.pkg-name }}
           VERSION: ${{ needs.build.outputs.version }}
         run: |
-          uv run pip install \
+          poetry run pip install \
             --extra-index-url https://test.pypi.org/simple/ \
             "$PKG_NAME==$VERSION"
 
@@ -261,28 +244,27 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
 
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
 
-      - name: Set up Python
-        uses: ./.github/actions/uv_setup
+      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ env.PYTHON_VERSION }}
-          cache-suffix: "release"
+          poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
+          cache-key: release
 
-      - uses: actions/download-artifact@v8
+      - uses: actions/download-artifact@v4
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
 
       - name: Publish package distributions to PyPI
-        uses: pypa/gh-action-pypi-publish@ed0c53931b1dc9bd32cbe73a98c7f6766f8a527e # release/v1
+        uses: pypa/gh-action-pypi-publish@release/v1
         with:
           packages-dir: ${{ inputs.working-directory }}/dist/
           verbose: true
           print-hash: true
-          # Temp workaround since attestations are on by default as of gh-action-pypi-publish v1.11.0
-          attestations: false
 
   mark-release:
     needs:
@@ -302,27 +284,27 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
 
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
 
-      - name: Set up Python
-        uses: ./.github/actions/uv_setup
+      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ env.PYTHON_VERSION }}
-          cache-suffix: "release"
+          poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
+          cache-key: release
 
-      - uses: actions/download-artifact@v8
+      - uses: actions/download-artifact@v4
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
 
       - name: Create Tag
-        uses: ncipollo/release-action@339a81892b84b4eeb0f6e744e4574d79d0d9b8dd # v1
+        uses: ncipollo/release-action@v1
         with:
           artifacts: "dist/*"
           token: ${{ secrets.GITHUB_TOKEN }}
           generateReleaseNotes: false
           tag: ${{needs.build.outputs.tag}}
-          name: ${{ needs.build.outputs.pkg-name }}==${{ needs.build.outputs.version }}
           body: ${{ needs.release-notes.outputs.release-body }}
           commit: ${{ github.sha }}

.github/workflows/release_js.yml

@@ -0,0 +1,38 @@
+name: JS Release
+
+on:
+  workflow_dispatch:
+
+jobs:
+  publish:
+    # Disallow publishing from branches that aren't `main`.
+    if: github.ref == 'refs/heads/main'
+    runs-on: ubuntu-latest
+
+    strategy:
+      matrix:
+        working-directory:
+          - "libs/sdk-js"
+
+    defaults:
+      run:
+        working-directory: ${{ matrix.working-directory }}
+
+    steps:
+      - uses: actions/checkout@v4
+      # JS Build
+      - name: Use Node.js
+        uses: actions/setup-node@v3
+        with:
+          node-version: "20"
+          cache: "yarn"
+          cache-dependency-path: ${{ matrix.working-directory }}/yarn.lock
+
+      - name: Install dependencies
+        run: yarn install
+      - name: Build
+        run: yarn build
+      - name: Publish package to NPM
+        run: |
+          echo "//registry.npmjs.org/:_authToken=${{ secrets.NPM_TOKEN }}" > .npmrc
+          npm publish

.github/workflows/reopen_on_assignment.yml

@@ -1,195 +0,0 @@
-# Reopen PRs that were auto-closed by require_issue_link.yml when the
-# contributor was not assigned to the linked issue. When a maintainer
-# assigns the contributor to the issue, this workflow finds matching
-# closed PRs, verifies the issue link, and reopens them.
-#
-# Uses the default GITHUB_TOKEN (not a PAT or app token) so that the
-# reopen and label-removal events do NOT re-trigger other workflows.
-# GitHub suppresses events created by the default GITHUB_TOKEN within
-# workflow runs to prevent infinite loops.
-
-name: Reopen PR on Issue Assignment
-
-on:
-  issues:
-    types: [assigned]
-
-permissions:
-  contents: read
-
-jobs:
-  reopen-linked-prs:
-    runs-on: ubuntu-latest
-    permissions:
-      actions: write
-      pull-requests: write
-
-    steps:
-      - name: Find and reopen matching PRs
-        uses: actions/github-script@v8
-        with:
-          script: |
-            const { owner, repo } = context.repo;
-            const issueNumber = context.payload.issue.number;
-            const assignee = context.payload.assignee.login;
-
-            console.log(
-              `Issue #${issueNumber} assigned to ${assignee} — searching for closed PRs to reopen`,
-            );
-
-            const q = [
-              `is:pr`,
-              `is:closed`,
-              `author:${assignee}`,
-              `label:missing-issue-link`,
-              `repo:${owner}/${repo}`,
-            ].join(' ');
-
-            let data;
-            try {
-              ({ data } = await github.rest.search.issuesAndPullRequests({
-                q,
-                per_page: 30,
-              }));
-            } catch (e) {
-              throw new Error(
-                `Failed to search for closed PRs to reopen after assigning ${assignee} ` +
-                `to #${issueNumber} (HTTP ${e.status ?? 'unknown'}): ${e.message}`,
-              );
-            }
-
-            if (data.total_count === 0) {
-              console.log('No matching closed PRs found');
-              return;
-            }
-
-            console.log(`Found ${data.total_count} candidate PR(s)`);
-
-            // Must stay in sync with the identical pattern in require_issue_link.yml
-            const pattern = /(?:close[sd]?|fix(?:e[sd])?|resolve[sd]?)\s*#(\d+)/gi;
-
-            for (const item of data.items) {
-              const prNumber = item.number;
-              const body = item.body || '';
-              const matches = [...body.matchAll(pattern)];
-              const referencedIssues = matches.map(m => parseInt(m[1], 10));
-
-              if (!referencedIssues.includes(issueNumber)) {
-                console.log(`PR #${prNumber} does not reference #${issueNumber} — skipping`);
-                continue;
-              }
-
-              // Skip if already bypassed
-              const labels = item.labels.map(l => l.name);
-              if (labels.includes('bypass-issue-check')) {
-                console.log(`PR #${prNumber} already has bypass-issue-check — skipping`);
-                continue;
-              }
-
-              // Reopen first, remove label second — a closed PR that still has
-              // missing-issue-link is recoverable; a closed PR with the label
-              // stripped is invisible to both workflows.
-              try {
-                await github.rest.pulls.update({
-                  owner,
-                  repo,
-                  pull_number: prNumber,
-                  state: 'open',
-                });
-                console.log(`Reopened PR #${prNumber}`);
-              } catch (e) {
-                if (e.status === 422) {
-                  // Head branch deleted — PR is unrecoverable. Notify the
-                  // contributor so they know to open a new PR.
-                  core.warning(`Cannot reopen PR #${prNumber}: head branch was likely deleted`);
-                  try {
-                    await github.rest.issues.createComment({
-                      owner,
-                      repo,
-                      issue_number: prNumber,
-                      body:
-                        `You have been assigned to #${issueNumber}, but this PR could not be ` +
-                        `reopened because the head branch has been deleted. Please open a new ` +
-                        `PR referencing the issue.`,
-                    });
-                  } catch (commentErr) {
-                    core.warning(
-                      `Also failed to post comment on PR #${prNumber}: ${commentErr.message}`,
-                    );
-                  }
-                  continue;
-                }
-                // Transient errors (rate limit, 5xx) should fail the job so
-                // the label is NOT removed and the run can be retried.
-                throw e;
-              }
-
-              // Remove missing-issue-link label only after successful reopen
-              try {
-                await github.rest.issues.removeLabel({
-                  owner,
-                  repo,
-                  issue_number: prNumber,
-                  name: 'missing-issue-link',
-                });
-                console.log(`Removed missing-issue-link from PR #${prNumber}`);
-              } catch (e) {
-                if (e.status !== 404) throw e;
-              }
-
-              // Minimize stale enforcement comment (best-effort;
-              // sync w/ require_issue_link.yml minimize blocks)
-              try {
-                const marker = '<!-- require-issue-link -->';
-                const comments = await github.paginate(
-                  github.rest.issues.listComments,
-                  { owner, repo, issue_number: prNumber, per_page: 100 },
-                );
-                const stale = comments.find(c => c.body && c.body.includes(marker));
-                if (stale) {
-                  await github.graphql(`
-                    mutation($id: ID!) {
-                      minimizeComment(input: {subjectId: $id, classifier: OUTDATED}) {
-                        minimizedComment { isMinimized }
-                      }
-                    }
-                  `, { id: stale.node_id });
-                  console.log(`Minimized stale enforcement comment ${stale.id} as outdated`);
-                }
-              } catch (e) {
-                core.warning(`Could not minimize stale comment on PR #${prNumber}: ${e.message}`);
-              }
-
-              // Re-run the failed require_issue_link check so it picks up the
-              // new assignment.  The re-run uses the original event payload but
-              // fetches live issue data, so the assignment check will pass.
-              //
-              // Limitation: we look up runs by the PR's current head SHA.  If the
-              // contributor pushed new commits while the PR was closed, head.sha
-              // won't match the SHA of the original failed run and the query will
-              // return 0 results.  This is acceptable because any push after reopen
-              // triggers a fresh require_issue_link run against the new SHA.
-              try {
-                const { data: pr } = await github.rest.pulls.get({
-                  owner, repo, pull_number: prNumber,
-                });
-                const { data: runs } = await github.rest.actions.listWorkflowRuns({
-                  owner, repo,
-                  workflow_id: 'require_issue_link.yml',
-                  head_sha: pr.head.sha,
-                  status: 'failure',
-                  per_page: 1,
-                });
-                if (runs.workflow_runs.length > 0) {
-                  await github.rest.actions.reRunWorkflowFailedJobs({
-                    owner, repo,
-                    run_id: runs.workflow_runs[0].id,
-                  });
-                  console.log(`Re-ran failed require_issue_link run ${runs.workflow_runs[0].id} for PR #${prNumber}`);
-                } else {
-                  console.log(`No failed require_issue_link runs found for PR #${prNumber} — skipping re-run`);
-                }
-              } catch (e) {
-                core.warning(`Could not re-run require_issue_link check for PR #${prNumber} (HTTP ${e.status ?? 'unknown'}): ${e.message}`);
-              }
-            }

.github/workflows/require_issue_link.yml

@@ -1,467 +0,0 @@
-# Require external PRs to reference an approved issue (e.g. Fixes #NNN) and
-# the PR author to be assigned to that issue. On failure the PR is
-# labeled "missing-issue-link", commented on, and closed.
-#
-# Maintainer override: an org member can reopen the PR or remove
-# "missing-issue-link" — both add "bypass-issue-check" and reopen.
-#
-# Dependency: tag-external-prs.yml must apply the "external" label
-# first. This workflow does NOT trigger on "opened" (new PRs have no labels
-# yet, so the gate would always skip).
-
-name: Require Issue Link
-
-on:
-  pull_request_target:
-    # NEVER CHECK OUT UNTRUSTED CODE FROM A PR's HEAD IN A pull_request_target JOB.
-    # Doing so would allow attackers to execute arbitrary code in the context of your repository.
-    types: [edited, reopened, labeled, unlabeled]
-
-# ──────────────────────────────────────────────────────────────────────────────
-# Enforcement gate: set to 'true' to activate the issue link requirement.
-# When 'false', the workflow still runs the check logic (useful for dry-run
-# visibility) but will NOT label, comment, close, or fail PRs.
-# ──────────────────────────────────────────────────────────────────────────────
-env:
-  ENFORCE_ISSUE_LINK: "true"
-
-permissions:
-  contents: read
-
-jobs:
-  check-issue-link:
-    # Run when the "external" label is added, on edit/reopen if already labeled,
-    # or when "missing-issue-link" is removed (triggers maintainer override check).
-    # Skip entirely when the PR already carries "trusted-contributor" or
-    # "bypass-issue-check".
-    if: >-
-      !contains(github.event.pull_request.labels.*.name, 'trusted-contributor') &&
-      !contains(github.event.pull_request.labels.*.name, 'bypass-issue-check') &&
-      (
-        (github.event.action == 'labeled' && github.event.label.name == 'external') ||
-        (github.event.action == 'unlabeled' && github.event.label.name == 'missing-issue-link' && contains(github.event.pull_request.labels.*.name, 'external')) ||
-        (github.event.action != 'labeled' && github.event.action != 'unlabeled' && contains(github.event.pull_request.labels.*.name, 'external'))
-      )
-    runs-on: ubuntu-latest
-    permissions:
-      actions: write
-      pull-requests: write
-
-    steps:
-      - name: Check for issue link and assignee
-        id: check-link
-        uses: actions/github-script@v8
-        with:
-          script: |
-            const { owner, repo } = context.repo;
-            const prNumber = context.payload.pull_request.number;
-            const action = context.payload.action;
-
-            // ── Helper: ensure a label exists, then add it to the PR ────────
-            async function ensureAndAddLabel(labelName, color) {
-              try {
-                await github.rest.issues.getLabel({ owner, repo, name: labelName });
-              } catch (e) {
-                if (e.status !== 404) throw e;
-                try {
-                  await github.rest.issues.createLabel({ owner, repo, name: labelName, color });
-                } catch (createErr) {
-                  // 422 = label was created by a concurrent run between our
-                  // GET and POST — safe to ignore.
-                  if (createErr.status !== 422) throw createErr;
-                }
-              }
-              await github.rest.issues.addLabels({
-                owner, repo, issue_number: prNumber, labels: [labelName],
-              });
-            }
-
-            // ── Helper: check if the user who triggered this event (reopened
-            // the PR / removed the label) has write+ access on the repo ───
-            // Uses the repo collaborator permission endpoint instead of the
-            // org membership endpoint. The org endpoint requires the caller
-            // to be an org member, which GITHUB_TOKEN (an app installation
-            // token) never is — so it always returns 403.
-            async function senderIsOrgMember() {
-              const sender = context.payload.sender?.login;
-              if (!sender) {
-                throw new Error('Event has no sender — cannot check permissions');
-              }
-              try {
-                const { data } = await github.rest.repos.getCollaboratorPermissionLevel({
-                  owner, repo, username: sender,
-                });
-                const perm = data.permission;
-                if (['admin', 'maintain', 'write'].includes(perm)) {
-                  console.log(`${sender} has ${perm} permission — treating as maintainer`);
-                  return { isMember: true, login: sender };
-                }
-                console.log(`${sender} has ${perm} permission — not a maintainer`);
-                return { isMember: false, login: sender };
-              } catch (e) {
-                if (e.status === 404) {
-                  console.log(`Cannot check permissions for ${sender} — treating as non-maintainer`);
-                  return { isMember: false, login: sender };
-                }
-                const status = e.status ?? 'unknown';
-                throw new Error(
-                  `Permission check failed for ${sender} (HTTP ${status}): ${e.message}`,
-                );
-              }
-            }
-
-            // ── Helper: apply maintainer bypass (shared by both override paths) ──
-            async function applyMaintainerBypass(reason) {
-              console.log(reason);
-
-              // Remove missing-issue-link if present
-              try {
-                await github.rest.issues.removeLabel({
-                  owner, repo, issue_number: prNumber, name: 'missing-issue-link',
-                });
-              } catch (e) {
-                if (e.status !== 404) throw e;
-              }
-
-              // Reopen before adding bypass label — a failed reopen is more
-              // actionable than a closed PR with a bypass label stuck on it.
-              if (context.payload.pull_request.state === 'closed') {
-                try {
-                  await github.rest.pulls.update({
-                    owner, repo, pull_number: prNumber, state: 'open',
-                  });
-                  console.log(`Reopened PR #${prNumber}`);
-                } catch (e) {
-                  // 422 if head branch deleted; 403 if permissions insufficient.
-                  // Bypass labels still apply — maintainer can reopen manually.
-                  core.warning(
-                    `Could not reopen PR #${prNumber} (HTTP ${e.status ?? 'unknown'}): ${e.message}. ` +
-                    `Bypass labels were applied — a maintainer may need to reopen manually.`,
-                  );
-                }
-              }
-
-              // Add bypass-issue-check so future triggers skip enforcement
-              await ensureAndAddLabel('bypass-issue-check', '0e8a16');
-
-              // Minimize stale enforcement comment (best-effort; must not
-              // abort bypass — sync w/ reopen_on_assignment.yml & step below)
-              try {
-                const marker = '<!-- require-issue-link -->';
-                const comments = await github.paginate(
-                  github.rest.issues.listComments,
-                  { owner, repo, issue_number: prNumber, per_page: 100 },
-                );
-                const stale = comments.find(c => c.body && c.body.includes(marker));
-                if (stale) {
-                  await github.graphql(`
-                    mutation($id: ID!) {
-                      minimizeComment(input: {subjectId: $id, classifier: OUTDATED}) {
-                        minimizedComment { isMinimized }
-                      }
-                    }
-                  `, { id: stale.node_id });
-                  console.log(`Minimized stale enforcement comment ${stale.id} as outdated`);
-                }
-              } catch (e) {
-                core.warning(`Could not minimize stale comment on PR #${prNumber}: ${e.message}`);
-              }
-
-              core.setOutput('has-link', 'true');
-              core.setOutput('is-assigned', 'true');
-            }
-
-            // ── Maintainer override: removed "missing-issue-link" label ─────
-            if (action === 'unlabeled') {
-              const { isMember, login } = await senderIsOrgMember();
-              if (isMember) {
-                await applyMaintainerBypass(
-                  `Maintainer ${login} removed missing-issue-link from PR #${prNumber} — bypassing enforcement`,
-                );
-                return;
-              }
-              // Non-member removed the label — re-add it defensively and
-              // set failure outputs so downstream steps (comment, close) fire.
-              // NOTE: addLabels fires a "labeled" event, but the job-level gate
-              // only matches labeled events for "external", so no re-trigger.
-              console.log(`Non-member ${login} removed missing-issue-link — re-adding`);
-              try {
-                await ensureAndAddLabel('missing-issue-link', 'b76e79');
-              } catch (e) {
-                core.warning(
-                  `Failed to re-add missing-issue-link (HTTP ${e.status ?? 'unknown'}): ${e.message}. ` +
-                  `Downstream step will retry.`,
-                );
-              }
-              core.setOutput('has-link', 'false');
-              core.setOutput('is-assigned', 'false');
-              return;
-            }
-
-            // ── Maintainer override: reopened PR with "missing-issue-link" ──
-            const prLabels = context.payload.pull_request.labels.map(l => l.name);
-            if (action === 'reopened' && prLabels.includes('missing-issue-link')) {
-              const { isMember, login } = await senderIsOrgMember();
-              if (isMember) {
-                await applyMaintainerBypass(
-                  `Maintainer ${login} reopened PR #${prNumber} — bypassing enforcement`,
-                );
-                return;
-              }
-              console.log(`Non-member ${login} reopened PR — proceeding with check`);
-            }
-
-            // ── Fetch live labels (race guard) ──────────────────────────────
-            const { data: liveLabels } = await github.rest.issues.listLabelsOnIssue({
-              owner, repo, issue_number: prNumber,
-            });
-            const liveNames = liveLabels.map(l => l.name);
-            if (liveNames.includes('trusted-contributor') || liveNames.includes('bypass-issue-check')) {
-              console.log('PR has trusted-contributor or bypass-issue-check label — bypassing');
-              core.setOutput('has-link', 'true');
-              core.setOutput('is-assigned', 'true');
-              return;
-            }
-
-            const body = context.payload.pull_request.body || '';
-            const pattern = /(?:close[sd]?|fix(?:e[sd])?|resolve[sd]?)\s*#(\d+)/gi;
-            const matches = [...body.matchAll(pattern)];
-
-            if (matches.length === 0) {
-              console.log('No issue link found in PR body');
-              core.setOutput('has-link', 'false');
-              core.setOutput('is-assigned', 'false');
-              return;
-            }
-
-            const issues = matches.map(m => `#${m[1]}`).join(', ');
-            console.log(`Found issue link(s): ${issues}`);
-            core.setOutput('has-link', 'true');
-
-            // Check whether the PR author is assigned to at least one linked issue
-            const prAuthor = context.payload.pull_request.user.login;
-            const MAX_ISSUES = 5;
-            const allIssueNumbers = [...new Set(matches.map(m => parseInt(m[1], 10)))];
-            const issueNumbers = allIssueNumbers.slice(0, MAX_ISSUES);
-            if (allIssueNumbers.length > MAX_ISSUES) {
-              core.warning(
-                `PR references ${allIssueNumbers.length} issues — only checking the first ${MAX_ISSUES}`,
-              );
-            }
-
-            let assignedToAny = false;
-            for (const num of issueNumbers) {
-              try {
-                const { data: issue } = await github.rest.issues.get({
-                  owner, repo, issue_number: num,
-                });
-                const assignees = issue.assignees.map(a => a.login.toLowerCase());
-                if (assignees.includes(prAuthor.toLowerCase())) {
-                  console.log(`PR author "${prAuthor}" is assigned to #${num}`);
-                  assignedToAny = true;
-                  break;
-                } else {
-                  console.log(`PR author "${prAuthor}" is NOT assigned to #${num} (assignees: ${assignees.join(', ') || 'none'})`);
-                }
-              } catch (error) {
-                if (error.status === 404) {
-                  console.log(`Issue #${num} not found — skipping`);
-                } else {
-                  // Non-404 errors (rate limit, server error) must not be
-                  // silently skipped — they could cause false enforcement
-                  // (closing a legitimate PR whose assignment can't be verified).
-                  throw new Error(
-                    `Cannot verify assignee for issue #${num} (${error.status}): ${error.message}`,
-                  );
-                }
-              }
-            }
-
-            core.setOutput('is-assigned', assignedToAny ? 'true' : 'false');
-
-      - name: Add missing-issue-link label
-        if: >-
-          env.ENFORCE_ISSUE_LINK == 'true' &&
-          (steps.check-link.outputs.has-link != 'true' || steps.check-link.outputs.is-assigned != 'true')
-        uses: actions/github-script@v8
-        with:
-          script: |
-            const { owner, repo } = context.repo;
-            const prNumber = context.payload.pull_request.number;
-            const labelName = 'missing-issue-link';
-
-            // Ensure the label exists (no checkout/shared helper available)
-            try {
-              await github.rest.issues.getLabel({ owner, repo, name: labelName });
-            } catch (e) {
-              if (e.status !== 404) throw e;
-              try {
-                await github.rest.issues.createLabel({
-                  owner, repo, name: labelName, color: 'b76e79',
-                });
-              } catch (createErr) {
-                if (createErr.status !== 422) throw createErr;
-              }
-            }
-
-            await github.rest.issues.addLabels({
-              owner, repo, issue_number: prNumber, labels: [labelName],
-            });
-
-      - name: Remove missing-issue-link label and reopen PR
-        if: >-
-          env.ENFORCE_ISSUE_LINK == 'true' &&
-          steps.check-link.outputs.has-link == 'true' && steps.check-link.outputs.is-assigned == 'true'
-        uses: actions/github-script@v8
-        with:
-          script: |
-            const { owner, repo } = context.repo;
-            const prNumber = context.payload.pull_request.number;
-            try {
-              await github.rest.issues.removeLabel({
-                owner, repo, issue_number: prNumber, name: 'missing-issue-link',
-              });
-            } catch (error) {
-              if (error.status !== 404) throw error;
-            }
-
-            // Reopen if this workflow previously closed the PR. We check the
-            // event payload labels (not live labels) because we already removed
-            // missing-issue-link above; the payload still reflects pre-step state.
-            const labels = context.payload.pull_request.labels.map(l => l.name);
-            if (context.payload.pull_request.state === 'closed' && labels.includes('missing-issue-link')) {
-              await github.rest.pulls.update({
-                owner,
-                repo,
-                pull_number: prNumber,
-                state: 'open',
-              });
-              console.log(`Reopened PR #${prNumber}`);
-            }
-
-            // Minimize stale enforcement comment (best-effort;
-            // sync w/ applyMaintainerBypass above & reopen_on_assignment.yml)
-            try {
-              const marker = '<!-- require-issue-link -->';
-              const comments = await github.paginate(
-                github.rest.issues.listComments,
-                { owner, repo, issue_number: prNumber, per_page: 100 },
-              );
-              const stale = comments.find(c => c.body && c.body.includes(marker));
-              if (stale) {
-                await github.graphql(`
-                  mutation($id: ID!) {
-                    minimizeComment(input: {subjectId: $id, classifier: OUTDATED}) {
-                      minimizedComment { isMinimized }
-                    }
-                  }
-                `, { id: stale.node_id });
-                console.log(`Minimized stale enforcement comment ${stale.id} as outdated`);
-              }
-            } catch (e) {
-              core.warning(`Could not minimize stale comment on PR #${prNumber}: ${e.message}`);
-            }
-
-      - name: Post comment, close PR, and fail
-        if: >-
-          env.ENFORCE_ISSUE_LINK == 'true' &&
-          (steps.check-link.outputs.has-link != 'true' || steps.check-link.outputs.is-assigned != 'true')
-        uses: actions/github-script@v8
-        with:
-          script: |
-            const { owner, repo } = context.repo;
-            const prNumber = context.payload.pull_request.number;
-            const hasLink = '${{ steps.check-link.outputs.has-link }}' === 'true';
-            const isAssigned = '${{ steps.check-link.outputs.is-assigned }}' === 'true';
-            const marker = '<!-- require-issue-link -->';
-
-            let lines;
-            if (!hasLink) {
-              lines = [
-                marker,
-                '**This PR has been automatically closed** because it does not link to an approved issue.',
-                '',
-                'All external contributions must reference an approved issue or discussion. Please:',
-                '1. Find or [open an issue](https://github.com/' + owner + '/' + repo + '/issues/new/choose) describing the change',
-                '2. Wait for a maintainer to approve and assign you',
-                '3. Add `Fixes #<issue_number>`, `Closes #<issue_number>`, or `Resolves #<issue_number>` to your PR description and the PR will be reopened automatically',
-                '',
-                '*Maintainers: reopen this PR or remove the `missing-issue-link` label to bypass this check.*',
-              ];
-            } else {
-              lines = [
-                marker,
-                '**This PR has been automatically closed** because you are not assigned to the linked issue.',
-                '',
-                'External contributors must be assigned to an issue before opening a PR for it. Please:',
-                '1. Comment on the linked issue to request assignment from a maintainer',
-                '2. Once assigned, your PR will be reopened automatically',
-                '',
-                '*Maintainers: reopen this PR or remove the `missing-issue-link` label to bypass this check.*',
-              ];
-            }
-
-            const body = lines.join('\n');
-
-            // Deduplicate: check for existing comment with the marker
-            const comments = await github.paginate(
-              github.rest.issues.listComments,
-              { owner, repo, issue_number: prNumber, per_page: 100 },
-            );
-            const existing = comments.find(c => c.body && c.body.includes(marker));
-
-            if (!existing) {
-              await github.rest.issues.createComment({
-                owner,
-                repo,
-                issue_number: prNumber,
-                body,
-              });
-              console.log('Posted requirement comment');
-            } else if (existing.body !== body) {
-              await github.rest.issues.updateComment({
-                owner,
-                repo,
-                comment_id: existing.id,
-                body,
-              });
-              console.log('Updated existing comment with new message');
-            } else {
-              console.log('Comment already exists — skipping');
-            }
-
-            // Close the PR
-            if (context.payload.pull_request.state === 'open') {
-              await github.rest.pulls.update({
-                owner,
-                repo,
-                pull_number: prNumber,
-                state: 'closed',
-              });
-              console.log(`Closed PR #${prNumber}`);
-            }
-
-            // Cancel all other in-progress and queued workflow runs for this PR
-            const headSha = context.payload.pull_request.head.sha;
-            for (const status of ['in_progress', 'queued']) {
-              const runs = await github.paginate(
-                github.rest.actions.listWorkflowRunsForRepo,
-                { owner, repo, head_sha: headSha, status, per_page: 100 },
-              );
-              for (const run of runs) {
-                if (run.id === context.runId) continue;
-                try {
-                  await github.rest.actions.cancelWorkflowRun({
-                    owner, repo, run_id: run.id,
-                  });
-                  console.log(`Cancelled ${status} run ${run.id} (${run.name})`);
-                } catch (err) {
-                  console.log(`Could not cancel run ${run.id}: ${err.message}`);
-                }
-              }
-            }
-
-            const reason = !hasLink
-              ? 'PR must reference an issue using auto-close keywords (e.g., "Fixes #123").'
-              : 'PR author must be assigned to the linked issue.';
-            core.setFailed(reason);

.github/workflows/size.yml

@@ -0,0 +1,28 @@
+name: Check File Size
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+  workflow_dispatch:
+
+jobs:
+  file-size-check:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Get changed files
+        id: changed-files
+        uses: tj-actions/changed-files@v44
+      - name: Filter by size
+        run: |
+          large_added_files=$(find ${{ steps.changed-files.outputs.added_files }} -maxdepth 0 -size +1M)
+          if [ -n "$large_added_files" ]; then
+            echo "Large files added: $large_added_files"
+            echo "# Large files added:" >> $GITHUB_STEP_SUMMARY
+            echo "$large_added_files" >> $GITHUB_STEP_SUMMARY
+            exit 1
+          fi

.github/workflows/tag-external-issues.yml

@@ -1,402 +0,0 @@
-# Automatically tag issues as "external" or "internal" based on whether
-# the author is a member of the langchain-ai GitHub organization, and
-# apply contributor tier labels to external contributors based on their
-# merged PR history.
-#
-# PR labeling is handled by tag-external-prs.yml.
-# PR + issue backfill lives in the backfill job below (workflow_dispatch).
-#
-# Setup Requirements:
-# 1. Create a GitHub App with permissions:
-#    - Repository: Issues (write), Pull requests (write)
-#    - Organization: Members (read)
-# 2. Install the app on your organization and this repository
-# 3. Add these repository secrets:
-#    - ORG_MEMBERSHIP_APP_ID: Your app's ID
-#    - ORG_MEMBERSHIP_APP_PRIVATE_KEY: Your app's private key
-#
-# The GitHub App token is required to check private organization membership.
-# Without it, the workflow will fail.
-
-name: Tag External Issues
-
-on:
-  issues:
-    types: [opened]
-  workflow_dispatch:
-    inputs:
-      backfill_type:
-        description: "Backfill type (for initial run)"
-        default: "both"
-        type: choice
-        options:
-          - prs
-          - issues
-          - both
-      max_items:
-        description: "Maximum number of items to process"
-        default: "100"
-        type: string
-
-permissions:
-  contents: read
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.issue.number || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  tag-external:
-    if: github.event_name == 'issues'
-    runs-on: ubuntu-latest
-    permissions:
-      issues: write
-
-    steps:
-      - name: Generate GitHub App token
-        id: app-token
-        uses: actions/create-github-app-token@v3
-        with:
-          app-id: ${{ secrets.ORG_MEMBERSHIP_APP_ID }}
-          private-key: ${{ secrets.ORG_MEMBERSHIP_APP_PRIVATE_KEY }}
-
-      - name: Check if contributor is external
-        if: steps.app-token.outcome == 'success'
-        id: check-membership
-        uses: actions/github-script@v8
-        with:
-          github-token: ${{ steps.app-token.outputs.token }}
-          script: |
-            const { owner, repo } = context.repo;
-            const author = context.payload.sender.login;
-            const senderType = context.payload.sender.type;
-
-            if (senderType === 'Bot') {
-              console.log(`${author} is a Bot — treating as internal`);
-              core.setOutput('is-external', 'false');
-              return;
-            }
-
-            try {
-              const membership = await github.rest.orgs.getMembershipForUser({
-                org: 'langchain-ai',
-                username: author,
-              });
-              const isExternal = membership.data.state !== 'active';
-              console.log(
-                isExternal
-                  ? `${author} has pending membership — treating as external`
-                  : `${author} is an active member of langchain-ai`,
-              );
-              core.setOutput('is-external', isExternal ? 'true' : 'false');
-            } catch (e) {
-              if (e.status === 404) {
-                console.log(`${author} is not a member of langchain-ai`);
-                core.setOutput('is-external', 'true');
-              } else {
-                throw new Error(
-                  `Membership check failed for ${author} (${e.status}): ${e.message}`,
-                );
-              }
-            }
-
-      - name: Apply contributor tier label
-        if: steps.check-membership.outputs.is-external == 'true'
-        uses: actions/github-script@v8
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          script: |
-            const { owner, repo } = context.repo;
-            const issue = context.payload.issue;
-            const author = issue.user.login;
-            const issueNumber = issue.number;
-
-            const TRUSTED_THRESHOLD = 5;
-            const LABEL_COLOR = 'b76e79';
-
-            let mergedCount;
-            try {
-              const result = await github.rest.search.issuesAndPullRequests({
-                q: `repo:${owner}/${repo} is:pr is:merged author:"${author}"`,
-                per_page: 1,
-              });
-              mergedCount = result?.data?.total_count;
-            } catch (error) {
-              if (error?.status !== 422) throw error;
-              core.warning(`Search failed for ${author}; skipping tier label.`);
-              return;
-            }
-
-            if (mergedCount == null) {
-              core.warning(`Search response missing total_count for ${author}; skipping tier label.`);
-              return;
-            }
-
-            const tierLabel = mergedCount >= TRUSTED_THRESHOLD ? 'trusted-contributor' : null;
-
-            if (tierLabel) {
-              try {
-                await github.rest.issues.getLabel({ owner, repo, name: tierLabel });
-              } catch (e) {
-                if (e.status !== 404) throw e;
-                try {
-                  await github.rest.issues.createLabel({ owner, repo, name: tierLabel, color: LABEL_COLOR });
-                } catch (createErr) {
-                  if (createErr.status !== 422) throw createErr;
-                }
-              }
-              await github.rest.issues.addLabels({
-                owner, repo, issue_number: issueNumber, labels: [tierLabel],
-              });
-              console.log(`Applied '${tierLabel}' to #${issueNumber} (${mergedCount} merged PRs)`);
-            } else {
-              console.log(`No tier label for ${author} (${mergedCount} merged PRs)`);
-            }
-
-      - name: Add external label
-        if: steps.check-membership.outputs.is-external == 'true'
-        uses: actions/github-script@v8
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          script: |
-            const { owner, repo } = context.repo;
-            const issue_number = context.payload.issue.number;
-            await github.rest.issues.addLabels({
-              owner, repo, issue_number, labels: ['external'],
-            });
-            console.log(`Added 'external' label to issue #${issue_number}`);
-
-      - name: Add internal label
-        if: steps.check-membership.outputs.is-external == 'false'
-        uses: actions/github-script@v8
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          script: |
-            const { owner, repo } = context.repo;
-            const issue_number = context.payload.issue.number;
-            await github.rest.issues.addLabels({
-              owner, repo, issue_number, labels: ['internal'],
-            });
-            console.log(`Added 'internal' label to issue #${issue_number}`);
-
-  backfill:
-    if: github.event_name == 'workflow_dispatch'
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      issues: write
-      pull-requests: write
-
-    steps:
-      - name: Generate GitHub App token
-        id: app-token
-        uses: actions/create-github-app-token@v3
-        with:
-          app-id: ${{ secrets.ORG_MEMBERSHIP_APP_ID }}
-          private-key: ${{ secrets.ORG_MEMBERSHIP_APP_PRIVATE_KEY }}
-
-      - name: Backfill labels
-        uses: actions/github-script@v8
-        with:
-          github-token: ${{ steps.app-token.outputs.token }}
-          script: |
-            const { owner, repo } = context.repo;
-            const rawMax = '${{ inputs.max_items }}';
-            const maxItems = parseInt(rawMax, 10);
-            if (isNaN(maxItems) || maxItems <= 0) {
-              core.setFailed(`Invalid max_items: "${rawMax}" — must be a positive integer`);
-              return;
-            }
-            const backfillType = '${{ inputs.backfill_type }}';
-
-            const TRUSTED_THRESHOLD = 5;
-            const LABEL_COLOR = 'b76e79';
-
-            const tierLabels = ['trusted-contributor'];
-
-            // ── Helpers ─────────────────────────────────────────────────
-
-            async function ensureLabel(name) {
-              try {
-                await github.rest.issues.getLabel({ owner, repo, name });
-              } catch (e) {
-                if (e.status !== 404) throw e;
-                try {
-                  await github.rest.issues.createLabel({ owner, repo, name, color: LABEL_COLOR });
-                } catch (createErr) {
-                  if (createErr.status !== 422) throw createErr;
-                }
-              }
-            }
-
-            async function checkMembership(author, userType) {
-              if (userType === 'Bot') {
-                console.log(`${author} is a Bot — treating as internal`);
-                return { isExternal: false };
-              }
-              try {
-                const membership = await github.rest.orgs.getMembershipForUser({
-                  org: 'langchain-ai',
-                  username: author,
-                });
-                const isExternal = membership.data.state !== 'active';
-                console.log(
-                  isExternal
-                    ? `${author} has pending membership — treating as external`
-                    : `${author} is an active member of langchain-ai`,
-                );
-                return { isExternal };
-              } catch (e) {
-                if (e.status === 404) {
-                  console.log(`${author} is not a member of langchain-ai`);
-                  return { isExternal: true };
-                }
-                throw new Error(
-                  `Membership check failed for ${author} (${e.status}): ${e.message}`,
-                );
-              }
-            }
-
-            async function getContributorInfo(contributorCache, author, userType) {
-              if (contributorCache.has(author)) return contributorCache.get(author);
-
-              const { isExternal } = await checkMembership(author, userType);
-
-              let mergedCount = null;
-              if (isExternal) {
-                try {
-                  const result = await github.rest.search.issuesAndPullRequests({
-                    q: `repo:${owner}/${repo} is:pr is:merged author:"${author}"`,
-                    per_page: 1,
-                  });
-                  mergedCount = result?.data?.total_count ?? null;
-                } catch (e) {
-                  if (e?.status !== 422) throw e;
-                  core.warning(`Search failed for ${author}; skipping tier.`);
-                }
-              }
-
-              const info = { isExternal, mergedCount };
-              contributorCache.set(author, info);
-              return info;
-            }
-
-            // ── Setup ────────────────────────────────────────────────────
-
-            for (const name of tierLabels) {
-              await ensureLabel(name);
-            }
-
-            const contributorCache = new Map();
-
-            let processed = 0;
-            let failures = 0;
-
-            // ── Backfill PRs ─────────────────────────────────────────────
-
-            if (backfillType === 'prs' || backfillType === 'both') {
-              const prs = await github.paginate(github.rest.pulls.list, {
-                owner, repo, state: 'open', per_page: 100,
-              });
-
-              for (const pr of prs) {
-                if (processed >= maxItems) break;
-
-                try {
-                  const author = pr.user.login;
-                  const info = await getContributorInfo(contributorCache, author, pr.user.type);
-
-                  const labels = [info.isExternal ? 'external' : 'internal'];
-                  if (info.isExternal && info.mergedCount != null && info.mergedCount >= TRUSTED_THRESHOLD) {
-                    labels.push('trusted-contributor');
-                  }
-
-                  // Ensure all labels exist before batch add
-                  for (const name of labels) {
-                    await ensureLabel(name);
-                  }
-
-                  // Remove stale tier labels
-                  const currentLabels = (await github.paginate(
-                    github.rest.issues.listLabelsOnIssue,
-                    { owner, repo, issue_number: pr.number, per_page: 100 },
-                  )).map(l => l.name ?? '');
-                  for (const name of currentLabels) {
-                    if (tierLabels.includes(name) && !labels.includes(name)) {
-                      try {
-                        await github.rest.issues.removeLabel({
-                          owner, repo, issue_number: pr.number, name,
-                        });
-                      } catch (e) {
-                        if (e.status !== 404) throw e;
-                      }
-                    }
-                  }
-
-                  await github.rest.issues.addLabels({
-                    owner, repo, issue_number: pr.number, labels,
-                  });
-                  console.log(`PR #${pr.number} (${author}): ${labels.join(', ')}`);
-                  processed++;
-                } catch (e) {
-                  failures++;
-                  core.warning(`Failed to process PR #${pr.number}: ${e.message}`);
-                }
-              }
-            }
-
-            // ── Backfill issues ──────────────────────────────────────────
-
-            if (backfillType === 'issues' || backfillType === 'both') {
-              const issues = await github.paginate(github.rest.issues.listForRepo, {
-                owner, repo, state: 'open', per_page: 100,
-              });
-
-              for (const issue of issues) {
-                if (processed >= maxItems) break;
-                if (issue.pull_request) continue;
-
-                try {
-                  const author = issue.user.login;
-                  const info = await getContributorInfo(contributorCache, author, issue.user.type);
-
-                  const labels = [info.isExternal ? 'external' : 'internal'];
-                  if (info.isExternal && info.mergedCount != null && info.mergedCount >= TRUSTED_THRESHOLD) {
-                    labels.push('trusted-contributor');
-                  }
-
-                  // Ensure all labels exist before batch add
-                  for (const name of labels) {
-                    await ensureLabel(name);
-                  }
-
-                  // Remove stale tier labels
-                  const currentLabels = (await github.paginate(
-                    github.rest.issues.listLabelsOnIssue,
-                    { owner, repo, issue_number: issue.number, per_page: 100 },
-                  )).map(l => l.name ?? '');
-                  for (const name of currentLabels) {
-                    if (tierLabels.includes(name) && !labels.includes(name)) {
-                      try {
-                        await github.rest.issues.removeLabel({
-                          owner, repo, issue_number: issue.number, name,
-                        });
-                      } catch (e) {
-                        if (e.status !== 404) throw e;
-                      }
-                    }
-                  }
-
-                  await github.rest.issues.addLabels({
-                    owner, repo, issue_number: issue.number, labels,
-                  });
-                  console.log(`Issue #${issue.number} (${author}): ${labels.join(', ')}`);
-                  processed++;
-                } catch (e) {
-                  failures++;
-                  core.warning(`Failed to process issue #${issue.number}: ${e.message}`);
-                }
-              }
-            }
-
-            console.log(`\nBackfill complete. Processed ${processed} items, ${failures} failures. ${contributorCache.size} unique authors.`);

.github/workflows/tag-external-prs.yml

@@ -1,173 +0,0 @@
-# Automatically tag pull requests as "external" or "internal" based on
-# whether the author is a member of the langchain-ai GitHub organization,
-# and apply contributor tier labels to external contributors based on
-# their merged PR history.
-#
-# Issue labeling is handled by tag-external-issues.yml.
-# Backfill (workflow_dispatch) also lives in tag-external-issues.yml.
-#
-# Setup Requirements:
-# 1. Create a GitHub App with permissions:
-#    - Repository: Pull requests (write)
-#    - Organization: Members (read)
-# 2. Install the app on your organization and this repository
-# 3. Add these repository secrets:
-#    - ORG_MEMBERSHIP_APP_ID: Your app's ID
-#    - ORG_MEMBERSHIP_APP_PRIVATE_KEY: Your app's private key
-#
-# The GitHub App token is required to check private organization membership.
-# Without it, the workflow will fail.
-
-name: Tag External PRs
-
-on:
-  pull_request_target:
-    types: [opened]
-
-permissions:
-  contents: read
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  tag-external:
-    runs-on: ubuntu-latest
-    permissions:
-      pull-requests: write
-
-    steps:
-      - name: Generate GitHub App token
-        id: app-token
-        uses: actions/create-github-app-token@v3
-        with:
-          app-id: ${{ secrets.ORG_MEMBERSHIP_APP_ID }}
-          private-key: ${{ secrets.ORG_MEMBERSHIP_APP_PRIVATE_KEY }}
-
-      - name: Check if contributor is external
-        if: steps.app-token.outcome == 'success'
-        id: check-membership
-        uses: actions/github-script@v8
-        with:
-          github-token: ${{ steps.app-token.outputs.token }}
-          script: |
-            const { owner, repo } = context.repo;
-            const author = context.payload.sender.login;
-            const senderType = context.payload.sender.type;
-
-            if (senderType === 'Bot') {
-              console.log(`${author} is a Bot — treating as internal`);
-              core.setOutput('is-external', 'false');
-              return;
-            }
-
-            try {
-              const membership = await github.rest.orgs.getMembershipForUser({
-                org: 'langchain-ai',
-                username: author,
-              });
-              const isExternal = membership.data.state !== 'active';
-              console.log(
-                isExternal
-                  ? `${author} has pending membership — treating as external`
-                  : `${author} is an active member of langchain-ai`,
-              );
-              core.setOutput('is-external', isExternal ? 'true' : 'false');
-            } catch (e) {
-              if (e.status === 404) {
-                console.log(`${author} is not a member of langchain-ai`);
-                core.setOutput('is-external', 'true');
-              } else {
-                throw new Error(
-                  `Membership check failed for ${author} (${e.status}): ${e.message}`,
-                );
-              }
-            }
-
-      # Apply tier label BEFORE the external label so that
-      # "trusted-contributor" is already present when the "external" labeled
-      # event fires and triggers require_issue_link.yml.
-      - name: Apply contributor tier label
-        if: steps.check-membership.outputs.is-external == 'true'
-        uses: actions/github-script@v8
-        with:
-          # Use App token so the "labeled" event propagates to downstream
-          # workflows (e.g. require_issue_link.yml).
-          github-token: ${{ steps.app-token.outputs.token }}
-          script: |
-            const { owner, repo } = context.repo;
-            const pr = context.payload.pull_request;
-            const author = pr.user.login;
-            const prNumber = pr.number;
-
-            const TRUSTED_THRESHOLD = 5;
-            const LABEL_COLOR = 'b76e79';
-
-            let mergedCount;
-            try {
-              const result = await github.rest.search.issuesAndPullRequests({
-                q: `repo:${owner}/${repo} is:pr is:merged author:"${author}"`,
-                per_page: 1,
-              });
-              mergedCount = result?.data?.total_count;
-            } catch (error) {
-              if (error?.status !== 422) throw error;
-              core.warning(`Search failed for ${author}; skipping tier label.`);
-              return;
-            }
-
-            if (mergedCount == null) {
-              core.warning(`Search response missing total_count for ${author}; skipping tier label.`);
-              return;
-            }
-
-            const tierLabel = mergedCount >= TRUSTED_THRESHOLD ? 'trusted-contributor' : null;
-
-            if (tierLabel) {
-              try {
-                await github.rest.issues.getLabel({ owner, repo, name: tierLabel });
-              } catch (e) {
-                if (e.status !== 404) throw e;
-                try {
-                  await github.rest.issues.createLabel({ owner, repo, name: tierLabel, color: LABEL_COLOR });
-                } catch (createErr) {
-                  if (createErr.status !== 422) throw createErr;
-                }
-              }
-              await github.rest.issues.addLabels({
-                owner, repo, issue_number: prNumber, labels: [tierLabel],
-              });
-              console.log(`Applied '${tierLabel}' to PR #${prNumber} (${mergedCount} merged PRs)`);
-            } else {
-              console.log(`No tier label for ${author} (${mergedCount} merged PRs)`);
-            }
-
-      - name: Add external label
-        if: steps.check-membership.outputs.is-external == 'true'
-        uses: actions/github-script@v8
-        with:
-          # Use App token so the "labeled" event propagates to downstream
-          # workflows (e.g. require_issue_link.yml). Events created by the
-          # default GITHUB_TOKEN do not trigger additional workflow runs.
-          github-token: ${{ steps.app-token.outputs.token }}
-          script: |
-            const { owner, repo } = context.repo;
-            const issue_number = context.payload.pull_request.number;
-            await github.rest.issues.addLabels({
-              owner, repo, issue_number, labels: ['external'],
-            });
-            console.log(`Added 'external' label to PR #${issue_number}`);
-
-      - name: Add internal label
-        if: steps.check-membership.outputs.is-external == 'false'
-        uses: actions/github-script@v8
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          script: |
-            const { owner, repo } = context.repo;
-            const issue_number = context.payload.pull_request.number;
-            await github.rest.issues.addLabels({
-              owner, repo, issue_number, labels: ['internal'],
-            });
-            console.log(`Added 'internal' label to PR #${issue_number}`);

.github/workflows/uv_lock_ugprade.yml

@@ -1,43 +0,0 @@
-name: UV Lock Upgrade
-
-on:
-  schedule:
-    # run at midnight every Sunday
-    - cron: '0 0 * * 0'
-  # allow manual triggering
-  workflow_dispatch:
-
-permissions:
-  contents: write
-  pull-requests: write
-
-jobs:
-  upgrade-dependencies:
-    runs-on: ubuntu-latest
-    
-    steps:
-      - uses: actions/checkout@v6
-      
-      - name: Set up uv
-        uses: ./.github/actions/uv_setup
-        with:
-          python-version: "3.10"
-          cache-suffix: "uv-lock-upgrade"
-          
-      - name: Run uv lock --upgrade in all Python packages
-        run: make lock-upgrade
-          
-      - name: Create Pull Request
-        uses: peter-evans/create-pull-request@c0f553fe549906ede9cf27b5156039d195d2ece0 # v8
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          commit-message: "chore(deps): upgrade dependencies with `uv lock --upgrade`"
-          title: "chore(deps): upgrade dependencies with `uv lock --upgrade`"
-          body: |
-            This PR updates the dependencies in all Python packages using `uv lock --upgrade`.
-            
-            This is an automated PR created by the UV Lock Upgrade workflow.
-          branch: deps/uv-lock-upgrade
-          delete-branch: true
-          labels: |
-            dependencies

.gitignore

@@ -6,6 +6,9 @@ __pycache__/
 *.py[cod]
 *$py.class
 
+# C extensions
+*.so
+
 # Distribution / packaging
 .Python
 build/
@@ -51,12 +54,27 @@ coverage.xml
 .hypothesis/
 .pytest_cache/
 
+# Translations
+*.mo
+*.pot
+
 # Django stuff:
 *.log
 local_settings.py
 db.sqlite3
 db.sqlite3-journal
 
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+docs/docs/_build/
+
 # PyBuilder
 target/
 
@@ -71,9 +89,23 @@ ipython_config.py
 # pyenv
 .python-version
 
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
 # PEP 582; used by e.g. github.com/David-OConnor/pyflow
 __pypackages__/
 
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
 # Environments
 .env
 .envrc
@@ -85,6 +117,16 @@ ENV/
 env.bak/
 venv.bak/
 
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
 # mypy
 .mypy_cache/
 .dmypy.json
@@ -96,7 +138,42 @@ dmypy.json
 # macOS display setting files
 .DS_Store
 
-.vercel
-.turbo
-.editorconfig
-.scratch
+# Wandb directory
+wandb/
+
+# asdf tool versions
+.tool-versions
+/.ruff_cache/
+
+*.pkl
+*.bin
+
+# integration test artifacts
+data_map*
+\[('_type', 'fake'), ('stop', None)]
+
+# Replit files
+*replit*
+
+node_modules
+docs/.yarn/
+docs/node_modules/
+docs/.docusaurus/
+docs/.cache-loader/
+docs/_dist
+docs/api_reference/api_reference.rst
+docs/api_reference/experimental_api_reference.rst
+docs/api_reference/_build
+docs/api_reference/*/
+!docs/api_reference/_static/
+!docs/api_reference/templates/
+!docs/api_reference/themes/
+docs/docs_skeleton/build
+docs/docs_skeleton/node_modules
+docs/docs_skeleton/yarn.lock
+
+# Any new jupyter notebooks
+# not intended for the repo
+Untitled*.ipynb
+
+Chinook.db

.markdown-link-check.config.json

@@ -0,0 +1,4 @@
+{
+  "aliveStatusCodes": [200, 206, 402],
+  "ignorePatterns": ["*dcbadge.vercel.app*"]
+}

.markdownlint.json

@@ -1,14 +0,0 @@
-{
-  "MD013": false,
-  "MD024": {
-    "siblings_only": true
-  },
-  "MD025": false,
-  "MD033": false,
-  "MD034": false,
-  "MD036": false,
-  "MD041": false,
-  "MD046": {
-    "style": "fenced"
-  }
-}

AGENTS.md

@@ -1,57 +0,0 @@
-# AGENTS Instructions
-
-This repository is a monorepo. Each library lives in a subdirectory under `libs/`.
-
-When you modify code in any library, run the following commands in that library's directory before creating a pull request:
-
-- `make format` – run code formatters
-- `make lint` – run the linter
-- `make test` – execute the test suite
-
-To run a particular test file or to pass additional pytest options you can specify the `TEST` variable:
-
-```txt
-TEST=path/to/test.py make test
-```
-
-Other pytest arguments can also be supplied inside the `TEST` variable.
-
-## Libraries
-
-The repository contains several Python and JavaScript/TypeScript libraries.
-Below is a high-level overview:
-
-- **checkpoint** – base interfaces for LangGraph checkpointers.
-- **checkpoint-postgres** – Postgres implementation of the checkpoint saver.
-- **checkpoint-sqlite** – SQLite implementation of the checkpoint saver.
-- **cli** – official command-line interface for LangGraph.
-- **langgraph** – core framework for building stateful, multi-actor agents.
-- **prebuilt** – high-level APIs for creating and running agents and tools.
-- **sdk-js** – JS/TS SDK for interacting with the LangGraph REST API.
-- **sdk-py** – Python SDK for the LangGraph Server API.
-
-### Dependency map
-
-The diagram below lists downstream libraries for each production dependency as
-declared in that library's `pyproject.toml` (or `package.json`).
-
-```text
-checkpoint
-├── checkpoint-postgres
-├── checkpoint-sqlite
-├── prebuilt
-└── langgraph
-
-prebuilt
-└── langgraph
-
-sdk-py
-├── langgraph
-└── cli
-
-sdk-js (standalone)
-```
-
-Changes to a library may impact all of its dependents shown above.
-
-- Do NOT use Sphinx-style double backtick formatting (` ``code`` `). Use single backticks (`` `code` ``) for inline code references in docstrings and comments.

CLAUDE.md

@@ -1,57 +0,0 @@
-# AGENTS Instructions
-
-This repository is a monorepo. Each library lives in a subdirectory under `libs/`.
-
-When you modify code in any library, run the following commands in that library's directory before creating a pull request:
-
-- `make format` – run code formatters
-- `make lint` – run the linter
-- `make test` – execute the test suite
-
-To run a particular test file or to pass additional pytest options you can specify the `TEST` variable:
-
-```
-TEST=path/to/test.py make test
-```
-
-Other pytest arguments can also be supplied inside the `TEST` variable.
-
-## Libraries
-
-The repository contains several Python and JavaScript/TypeScript libraries.
-Below is a high-level overview:
-
-- **checkpoint** – base interfaces for LangGraph checkpointers.
-- **checkpoint-postgres** – Postgres implementation of the checkpoint saver.
-- **checkpoint-sqlite** – SQLite implementation of the checkpoint saver.
-- **cli** – official command-line interface for LangGraph.
-- **langgraph** – core framework for building stateful, multi-actor agents.
-- **prebuilt** – high-level APIs for creating and running agents and tools.
-- **sdk-js** – JS/TS SDK for interacting with the LangGraph REST API.
-- **sdk-py** – Python SDK for the LangGraph Server API.
-
-### Dependency map
-
-The diagram below lists downstream libraries for each production dependency as
-declared in that library's `pyproject.toml` (or `package.json`).
-
-```text
-checkpoint
-├── checkpoint-postgres
-├── checkpoint-sqlite
-├── prebuilt
-└── langgraph
-
-prebuilt
-└── langgraph
-
-sdk-py
-├── langgraph
-└── cli
-
-sdk-js (standalone)
-```
-
-Changes to a library may impact all of its dependents shown above.
-
-- Do NOT use Sphinx-style double backtick formatting (` ``code`` `). Use single backticks (`` `code` ``) for inline code references in docstrings and comments.

CONTRIBUTING.md

@@ -0,0 +1,293 @@
+# Contributing to LangGraph
+
+Thank you for being interested in contributing to LangGraph!
+
+## General guidelines
+
+Here are some things to keep in mind for all types of contributions:
+
+- Follow the ["fork and pull request"](https://docs.github.com/en/get-started/exploring-projects-on-github/contributing-to-a-project) workflow.
+- Fill out the checked-in pull request template when opening pull requests. Note related issues and tag relevant maintainers.
+- Ensure your PR passes formatting, linting, and testing checks before requesting a review.
+  - If you would like comments or feedback, please open an issue or discussion and tag a maintainer.
+- Backwards compatibility is key. Your changes must not be breaking, except in case of critical bug and security fixes.
+- Look for duplicate PRs or issues that have already been opened before opening a new one.
+- Keep scope as isolated as possible. As a general rule, your changes should not affect more than one package at a time.
+
+### Bugfixes
+
+For bug fixes, please open up an issue before proposing a fix to ensure the proposal properly addresses the underlying problem. In general, bug fixes should all have an accompanying unit test that fails before the fix.
+
+### New features
+
+For new features, please start a new [discussion](https://github.com/langchain-ai/langgraph/discussions), where the maintainers will help with scoping out the necessary changes.
+
+## Contribute Documentation
+
+Documentation is a vital part of LangGraph. We welcome both new documentation for new features and
+community improvements to our current documentation. Please read the resources below before getting started:
+
+- [Documentation style guide](#documentation-style-guide)
+- [Documentation setup](#setup)
+
+## Documentation Style Guide
+
+As LangGraph continues to grow, the surface area of documentation required to cover it continues to grow too.
+This page provides guidelines for anyone writing documentation for LangGraph, as well as some of our philosophies around organization and structure.
+
+## Philosophy
+
+LangGraph's documentation follows the [Diataxis framework](https://diataxis.fr).
+Under this framework, all documentation falls under one of four categories: [Tutorials](#tutorials),
+[How-to guides](#how-to-guides),
+[References](#references), and [Explanations (aka conceptual guides)](#conceptual-guide).
+
+### Tutorials
+
+Tutorials are lessons that take the reader through a practical activity. Their purpose is to help the user
+gain understanding of concepts and how they interact by showing one way to achieve some goal in a hands-on way.
+
+They should **avoid** giving
+multiple permutations of ways to achieve that goal in-depth. Choice is burdensome. Instead, they should guide a new user through a recommended path to accomplishing a concrete goal. While the end result of a tutorial does not necessarily need to
+be completely production-ready, it should be useful and practically satisfy the the goal that you clearly stated in the tutorial's introduction.
+
+To quote the Diataxis website:
+
+> A tutorial serves the user’s *acquisition* of skills and knowledge - their study. Its purpose is not to help the user get something done, but to help them learn.
+
+In LangGraph, these are often higher level guides that show off end-to-end use cases.
+
+Some examples include:
+
+- [Build a Customer Support Bot](https://langchain-ai.github.io/langgraph/tutorials/customer-support/customer-support/)
+- [Build a SQL Agent](https://langchain-ai.github.io/langgraph/tutorials/sql-agent/)
+
+Here are some high-level tips on writing a good tutorial:
+
+- Focus on guiding the user to get something done, but keep in mind the end-goal is more to impart principles than to create a perfect production system.
+- Be specific, not abstract and follow one path.
+  - No need to go deeply into alternative approaches, but it’s ok to reference them, ideally with a link to an appropriate how-to guide.
+- Get "a point on the board" as soon as possible - something the user can run that outputs something.
+  - You can iterate and expand afterwards.
+  - Try to frequently checkpoint at given steps where the user can run code and see progress.
+- Focus on results, not technical explanation.
+  - Crosslink heavily to appropriate conceptual/reference pages
+- The first time you mention a LangGraph concept, use its full name (e.g. "human-in-the-loop"), and link to its conceptual/other documentation page.
+  - It's also helpful to add a prerequisite callout that links to any pages with necessary background information.
+- End with a recap/next steps section summarizing what the tutorial covered and future reading, such as related how-to guides.
+- Use phrases like "Next we can run X & Y. We will expect Z.". Then afterwards, use language like "Notice Z" that recalls our expectations and directs the reader's attention to the topic we are trying to teach.
+- Do not shy away from repetition.
+
+### How-to guides
+
+A how-to guide, as the name implies, demonstrates how to do something discrete and specific.
+It should assume that the user is already familiar with underlying concepts, and is trying to solve an immediate problem, but
+should still give some background or list the scenarios where the information contained within can be relevant.
+They can and should discuss alternatives if one approach may be better than another in certain cases.
+
+To quote the Diataxis website:
+
+> A how-to guide serves the work of the already-competent user, whom you can assume to know what they want to do, and to be able to follow your instructions correctly.
+
+Some examples include:
+
+- [How to add persistence to your graph](https://langchain-ai.github.io/langgraph/how-tos/persistence/)
+- [How to view and update past graph state](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/time-travel/)
+
+Here are some high-level tips on writing a good how-to guide:
+
+- Clearly explain what you are guiding the user through at the start
+- Assume higher intent than a tutorial and show what the user needs to do to get that task done
+- Assume familiarity of concepts, but explain why suggested actions are helpful
+  - Crosslink heavily to conceptual/reference pages
+- Discuss alternatives and responses to real-world tradeoffs that may arise when solving a problem
+- Use lots of example code, ideally within complete code blocks that the reader can copy and run.
+- End with a recap/next steps section summarizing what the tutorial covered and future reading, such as other related how-to guides
+
+### Conceptual guides
+
+LangGraph's conceptual guides fall under the **Explanation** quadrant of Diataxis. They should cover LangChain terms and concepts
+in a more abstract way than how-to guides or tutorials, and should be geared towards curious users interested in
+gaining a deeper understanding of the framework. Try to avoid excessively large code examples. The goal here is to
+impart perspective to the user rather than to finish a practical project. These guides should cover **why** things work they way they do.
+
+
+To quote the Diataxis website:
+
+> The perspective of explanation is higher and wider than that of the other types. It does not take the user’s eye-level view, as in a how-to guide, or a close-up view of the machinery, like reference material. Its scope in each case is a topic - “an area of knowledge”, that somehow has to be bounded in a reasonable, meaningful way.
+
+Some examples include:
+
+- [What does it mean to be agentic?](https://langchain-ai.github.io/langgraph/concepts/high_level/)
+- [Tool calling](https://langchain-ai.github.io/langgraph/concepts/agentic_concepts/#tool-calling)
+
+Here are some high-level tips on writing a good conceptual guide:
+
+- Explain design decisions. Why does concept X exist and why was it designed this way?
+- Use analogies and reference other concepts and alternatives
+- Avoid blending in too much reference content
+- You can and should reference content covered in other guides, but make sure to link to them
+
+### References
+
+References contain detailed, low-level information that describes exactly what functionality exists and how to use it.
+In LangGraph, this is mainly our API reference pages, which are populated from docstrings within code.
+References pages are generally not read end-to-end, but are consulted as necessary when a user needs to know
+how to use something specific.
+
+To quote the Diataxis website:
+
+> The only purpose of a reference guide is to describe, as succinctly as possible, and in an orderly way. Whereas the content of tutorials and how-to guides are led by needs of the user, reference material is led by the product it describes.
+
+Many of the reference pages in LangChain are automatically generated from code,
+but here are some high-level tips on writing a good docstring:
+
+- Be concise
+- Discuss special cases and deviations from a user's expectations
+- Go into detail on required inputs and outputs
+- Light details on when one might use the feature are fine, but in-depth details belong in other sections.
+
+Each category serves a distinct purpose and requires a specific approach to writing and structuring the content.
+
+## General guidelines
+
+Here are some other guidelines you should think about when writing and organizing documentation.
+
+We generally do not merge new tutorials from outside contributors without an actue need.
+We welcome updates as well as new integration docs, how-tos, and references.
+
+### Avoid duplication
+
+Multiple pages that cover the same material in depth are difficult to maintain and cause confusion. There should
+be only one (very rarely two), canonical pages for a given concept or feature. Instead, you should link to other guides.
+
+### Link to other sections
+
+Because sections of the docs do not exist in a vacuum, it is important to link to other sections as often as possible
+to allow a developer to learn more about an unfamiliar topic inline.
+
+This includes linking to the API references as well as conceptual sections!
+
+### Be concise
+
+In general, take a less-is-more approach. If a section with a good explanation of a concept already exists, you should link to it rather than
+re-explain it, unless the concept you are documenting presents some new wrinkle.
+
+Be concise, including in code samples.
+
+### General style
+
+- Use active voice and present tense whenever possible
+- Use examples and code snippets to illustrate concepts and usage
+- Use appropriate header levels (`#`, `##`, `###`, etc.) to organize the content hierarchically
+- Use fewer cells with more code to make copy/paste easier
+- Use bullet points and numbered lists to break down information into easily digestible chunks
+- Use tables (especially for **Reference** sections) and diagrams often to present information visually
+- Include the table of contents for longer documentation pages to help readers navigate the content, but hide it for shorter pages
+
+## Setup
+
+LangChain documentation consists of two components:
+
+1. Main Documentation: Hosted at [https://langchain-ai.github.io](https://langchain-ai.github.io/langgraph/),
+this comprehensive resource serves as the primary user-facing documentation.
+It covers a wide array of topics, including tutorials, use cases, integrations,
+and more, offering extensive guidance on building with LangGraph.
+The content for this documentation lives in the `/docs` directory of the monorepo.
+2. In-code Documentation: This is documentation of the codebase itself, which is also
+used to generate the externally facing [API Reference](https://langchain-ai.github.io/langgraph/reference/graphs/).
+The content for the API reference is autogenerated by scanning the docstrings in the codebase. For this reason we ask that developers document their code well.
+
+We appreciate all contributions to the documentation, whether it be fixing a typo,
+adding a new tutorial or example and whether it be in the main documentation or the API Reference.
+
+### 📜 Main Documentation
+
+The content for the main documentation is located in the `/docs` directory of the monorepo.
+
+The documentation is written using a combination of ipython notebooks (`.ipynb` files)
+and markdown (`.md` files). The notebooks are converted to markdown
+and then built using [MkDocs](https://www.mkdocs.org/).
+
+Feel free to make contributions to the main documentation! 🥰
+
+After modifying the documentation:
+
+1. Run the linting and formatting commands (see below) to ensure that the documentation is well-formatted and free of errors.
+2. Optionally build the documentation locally to verify that the changes look good.
+3. Make a pull request with the changes.
+
+### ⚒️ Linting and Building Documentation Locally
+
+After writing up the documentation, you may want to lint and build the documentation
+locally to ensure that it looks good and is free of errors.
+
+If you're unable to build it locally that's okay as well, as you will be able to
+see a preview of the documentation on the pull request page.
+
+From the **monorepo root**, run the following command to install the dependencies:
+
+```bash
+poetry install --with docs --no-root
+```
+
+#### Building
+
+The code that builds the documentation is located in the `/docs` directory of the monorepo.
+
+Before building the documentation, it is always a good idea to clean the build directory:
+
+```bash
+make clean-docs
+```
+
+You can build and preview the documentation as outlined below:
+
+```bash
+make serve-docs
+```
+
+#### Linting
+
+The documentation is linted from the **monorepo root**. To lint it, run the following from there:
+
+```bash
+make spellcheck
+```
+
+### ️In-code Documentation
+
+The in-code documentation is autogenerated from docstrings.
+
+For the API reference to be useful, the codebase must be well-documented. This means that all functions, classes, and methods should have a docstring that explains what they do, what the arguments are, and what the return value is. This is a good practice in general, but it is especially important for LangChain because the API reference is the primary resource for developers to understand how to use the codebase.
+
+We generally follow the [Google Python Style Guide](https://google.github.io/styleguide/pyguide.html#38-comments-and-docstrings) for docstrings.
+
+Here is an example of a well-documented function:
+
+```python
+
+def my_function(arg1: int, arg2: str) -> float:
+    """This is a short description of the function. (It should be a single sentence.)
+
+    This is a longer description of the function. It should explain what
+    the function does, what the arguments are, and what the return value is.
+    It should wrap at 88 characters.
+
+    Examples:
+        This is a section for examples of how to use the function.
+
+        .. code-block:: python
+
+            my_function(1, "hello")
+
+    Args:
+        arg1: This is a description of arg1. We do not need to specify the type since
+            it is already specified in the function signature.
+        arg2: This is a description of arg2.
+
+    Returns:
+        This is a description of the return value.
+    """
+    return 3.14
+```

Makefile

@@ -1,68 +1,28 @@
-# Define the directories containing projects
-LIBS_DIRS := $(wildcard libs/*)
+.PHONY: build-docs serve-docs serve-clean-docs clean-docs codespell build-typedoc
 
-# Default target
-.PHONY: all
-all: lint format lock test
+build-typedoc:
+	cd libs/sdk-js && yarn install --include-dev && yarn typedoc
+	cd libs/sdk-js && yarn --silent concat-md --decrease-title-levels --ignore=js_ts_sdk_ref.md --start-title-level-at 2 docs > ../../docs/docs/cloud/reference/sdk/js_ts_sdk_ref.md 2>/dev/null
+	#  Add links to the monorepo
+	sed -e '1,10s|@langchain/langgraph-sdk|[@langchain/langgraph-sdk](https://github.com/langchain-ai/langgraph/tree/main/libs/sdk-js)|g' docs/docs/cloud/reference/sdk/js_ts_sdk_ref.md > temp_file && mv temp_file docs/docs/cloud/reference/sdk/js_ts_sdk_ref.md
 
-# Install dependencies for all projects
-.PHONY: install
-install:
-	@echo "Creating virtual environment..."
-	@uv venv
-	@for dir in $(LIBS_DIRS); do \
-		if [ -f $$dir/pyproject.toml ]; then \
-			echo "Installing dependencies for $$dir"; \
-			uv pip install -e $$dir; \
-		fi; \
-	done
 
-# Lint all projects
-.PHONY: lint
-lint:
-	@for dir in $(LIBS_DIRS); do \
-		if [ -f $$dir/Makefile ]; then \
-			echo "Running lint in $$dir"; \
-			$(MAKE) -C $$dir lint; \
-		fi; \
-	done
 
-# Format all projects
-.PHONY: format
-format:
-	@for dir in $(LIBS_DIRS); do \
-		if [ -f $$dir/Makefile ]; then \
-			echo "Running format in $$dir"; \
-			$(MAKE) -C $$dir format; \
-		fi; \
-	done
+build-docs: build-typedoc
+	poetry run python docs/_scripts/copy_notebooks.py
+	poetry run python -m mkdocs build --clean -f docs/mkdocs.yml --strict
 
-# Lock all projects
-.PHONY: lock
-lock:
-	@for dir in $(LIBS_DIRS); do \
-		if [ -f $$dir/Makefile ]; then \
-			echo "Running lock in $$dir"; \
-			(cd $$dir && uv lock); \
-		fi; \
-	done
+serve-clean-docs: clean-docs
+	poetry run python docs/_scripts/copy_notebooks.py
+	poetry run python -m mkdocs serve -c -f docs/mkdocs.yml --strict -w ./libs/langgraph
 
-# Lock all projects and upgrade dependencies
-.PHONY: lock-upgrade
-lock-upgrade:
-	@for dir in $(LIBS_DIRS); do \
-		if [ -f $$dir/Makefile ]; then \
-			echo "Running lock-upgrade in $$dir"; \
-			(cd $$dir && uv lock --upgrade); \
-		fi; \
-	done
+serve-docs: build-typedoc
+	poetry run python docs/_scripts/copy_notebooks.py
+	poetry run python -m mkdocs serve -f docs/mkdocs.yml -w ./libs/langgraph --dirty
 
-# Test all projects
-.PHONY: test
-test:
-	@for dir in $(LIBS_DIRS); do \
-		if [ -f $$dir/Makefile ]; then \
-			echo "Running test in $$dir"; \
-			$(MAKE) -C $$dir test; \
-		fi; \
-	done
+clean-docs:
+	find ./docs/docs -name "*.ipynb" -type f -delete
+	rm -rf docs/site
+
+codespell:
+	./docs/codespell_notebooks.sh .

README.md

@@ -1,82 +1,234 @@
-<div align="center">
-  <a href="https://www.langchain.com/langgraph">
-    <picture>
-      <source media="(prefers-color-scheme: dark)" srcset=".github/images/logo-dark.svg">
-      <source media="(prefers-color-scheme: light)" srcset=".github/images/logo-light.svg">
-      <img alt="LangGraph Logo" src=".github/images/logo-dark.svg" width="50%">
-    </picture>
-  </a>
-</div>
+# 🦜🕸️LangGraph
 
-<div align="center">
-  <h3>Low-level orchestration framework for building stateful agents.</h3>
-</div>
+![Version](https://img.shields.io/pypi/v/langgraph)
+[![Downloads](https://static.pepy.tech/badge/langgraph/month)](https://pepy.tech/project/langgraph)
+[![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langgraph)](https://github.com/langchain-ai/langgraph/issues)
+[![Docs](https://img.shields.io/badge/docs-latest-blue)](https://langchain-ai.github.io/langgraph/)
 
-<div align="center">
-  <a href="https://opensource.org/licenses/MIT" target="_blank"><img src="https://img.shields.io/pypi/l/langgraph" alt="PyPI - License"></a>
-  <a href="https://pypistats.org/packages/langgraph" target="_blank"><img src="https://img.shields.io/pepy/dt/langgraph" alt="PyPI - Downloads"></a>
-  <a href="https://pypi.org/project/langgraph/" target="_blank"><img src="https://img.shields.io/pypi/v/langgraph.svg?label=%20" alt="Version"></a>
-  <a href="https://x.com/langchain" target="_blank"><img src="https://img.shields.io/twitter/url/https/twitter.com/langchain.svg?style=social&label=Follow%20%40LangChain" alt="Twitter / X"></a>
-</div>
+⚡ Building language agents as graphs ⚡
 
-<br>
+> [!NOTE]
+> Looking for the JS version? Click [here](https://github.com/langchain-ai/langgraphjs) ([JS docs](https://langchain-ai.github.io/langgraphjs/)).
 
-Trusted by companies shaping the future of agents – including Klarna, Replit, Elastic, and more – LangGraph is a low-level orchestration framework for building, managing, and deploying long-running, stateful agents.
+> [!TIP]
+> Looking to deploy your LangGraph application? [Join the waitlist](https://www.langchain.com/langgraph-cloud-beta) for [LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/), our managed service for deploying and hosting LangGraph applications.
 
-```bash
+## Overview
+
+[LangGraph](https://langchain-ai.github.io/langgraph/) is a library for building stateful, multi-actor applications with LLMs, used to create agent and multi-agent workflows. Compared to other LLM frameworks, it offers these core benefits: cycles, controllability, and persistence. LangGraph allows you to define flows that involve cycles, essential for most agentic architectures, differentiating it from DAG-based solutions. As a very low-level framework, it provides fine-grained control over both the flow and state of your application, crucial for creating reliable agents. Additionally, LangGraph includes built-in persistence, enabling advanced human-in-the-loop and memory features.
+
+LangGraph is inspired by [Pregel](https://research.google/pubs/pub37252/) and [Apache Beam](https://beam.apache.org/). The public interface draws inspiration from [NetworkX](https://networkx.org/documentation/latest/). LangGraph is built by LangChain Inc, the creators of LangChain, but can be used without LangChain.
+
+### Key Features
+
+- **Cycles and Branching**: Implement loops and conditionals in your apps.
+- **Persistence**: Automatically save state after each step in the graph. Pause and resume the graph execution at any point to support error recovery, human-in-the-loop workflows, time travel and more.
+- **Human-in-the-Loop**: Interrupt graph execution to approve or edit next action planned by the agent.
+- **Streaming Support**: Stream outputs as they are produced by each node (including token streaming).
+- **Integration with LangChain**: LangGraph integrates seamlessly with [LangChain](https://github.com/langchain-ai/langchain/) and [LangSmith](https://docs.smith.langchain.com/) (but does not require them).
+
+
+## Installation
+
+```shell
 pip install -U langgraph
 ```
 
-If you're looking to quickly build agents with LangChain's `create_agent` (built on LangGraph), check out the [LangChain Agents documentation](https://docs.langchain.com/oss/python/langchain/agents).
+## Example
 
-> [!NOTE]
-> Looking for the JS/TS library? Check out [LangGraph.js](https://github.com/langchain-ai/langgraphjs) and the [JS docs](https://docs.langchain.com/oss/javascript/langgraph/overview).
+One of the central concepts of LangGraph is state. Each graph execution creates a state that is passed between nodes in the graph as they execute, and each node updates this internal state with its return value after it executes. The way that the graph updates its internal state is defined by either the type of graph chosen or a custom function.
 
-## Why use LangGraph?
+Let's take a look at a simple example of an agent that can use a search tool.
 
-LangGraph provides low-level supporting infrastructure for *any* long-running, stateful workflow or agent:
+```shell
+pip install langchain-anthropic
+```
 
-- **[Durable execution](https://docs.langchain.com/oss/python/langgraph/durable-execution)** — Build agents that persist through failures and can run for extended periods, automatically resuming from exactly where they left off.
-- **[Human-in-the-loop](https://docs.langchain.com/oss/python/langgraph/interrupts)** — Seamlessly incorporate human oversight by inspecting and modifying agent state at any point during execution.
-- **[Comprehensive memory](https://docs.langchain.com/oss/python/langgraph/memory)** — Create truly stateful agents with both short-term working memory for ongoing reasoning and long-term persistent memory across sessions.
-- **[Debugging with LangSmith](https://www.langchain.com/langsmith)** — Gain deep visibility into complex agent behavior with visualization tools that trace execution paths, capture state transitions, and provide detailed runtime metrics.
-- **[Production-ready deployment](https://docs.langchain.com/langsmith/deployments)** — Deploy sophisticated agent systems confidently with scalable infrastructure designed to handle the unique challenges of stateful, long-running workflows.
+```shell
+export ANTHROPIC_API_KEY=sk-...
+```
 
-> [!TIP]
-> For developing, debugging, and deploying AI agents and LLM applications, see [LangSmith](https://docs.langchain.com/langsmith/home).
+Optionally, we can set up [LangSmith](https://docs.smith.langchain.com/) for best-in-class observability.
 
-## LangGraph ecosystem
+```shell
+export LANGSMITH_TRACING=true
+export LANGSMITH_API_KEY=lsv2_sk_...
+```
 
-While LangGraph can be used standalone, it also integrates seamlessly with any LangChain product, giving developers a full suite of tools for building agents.
+```python
+from typing import Annotated, Literal, TypedDict
 
-To improve your LLM application development, pair LangGraph with:
+from langchain_core.messages import HumanMessage
+from langchain_anthropic import ChatAnthropic
+from langchain_core.tools import tool
+from langgraph.checkpoint import MemorySaver
+from langgraph.graph import END, StateGraph, MessagesState
+from langgraph.prebuilt import ToolNode
 
-- [Deep Agents](https://github.com/langchain-ai/deepagents) *(new!)* – Build agents that can plan, use subagents, and leverage file systems for complex tasks.
-- [LangChain](https://docs.langchain.com/oss/python/langchain/overview) – Provides integrations and composable components to streamline LLM application development.
-- [LangSmith](https://www.langchain.com/langsmith) – Helpful for agent evals and observability. Debug poor-performing LLM app runs, evaluate agent trajectories, gain visibility in production, and improve performance over time.
-- [LangSmith Deployment](https://docs.langchain.com/langsmith/deployments) – Deploy and scale agents effortlessly with a purpose-built deployment platform for long-running, stateful workflows. Discover, reuse, configure, and share agents across teams – and iterate quickly with visual prototyping in [LangSmith Studio](https://docs.langchain.com/langsmith/studio).
 
----
+# Define the tools for the agent to use
+@tool
+def search(query: str):
+    """Call to surf the web."""
+    # This is a placeholder, but don't tell the LLM that...
+    if "sf" in query.lower() or "san francisco" in query.lower():
+        return "It's 60 degrees and foggy."
+    return "It's 90 degrees and sunny."
+
+
+tools = [search]
+
+tool_node = ToolNode(tools)
+
+model = ChatAnthropic(model="claude-3-5-sonnet-20240620", temperature=0).bind_tools(tools)
+
+# Define the function that determines whether to continue or not
+def should_continue(state: MessagesState) -> Literal["tools", END]:
+    messages = state['messages']
+    last_message = messages[-1]
+    # If the LLM makes a tool call, then we route to the "tools" node
+    if last_message.tool_calls:
+        return "tools"
+    # Otherwise, we stop (reply to the user)
+    return END
+
+
+# Define the function that calls the model
+def call_model(state: MessagesState):
+    messages = state['messages']
+    response = model.invoke(messages)
+    # We return a list, because this will get added to the existing list
+    return {"messages": [response]}
+
+
+# Define a new graph
+workflow = StateGraph(MessagesState)
+
+# Define the two nodes we will cycle between
+workflow.add_node("agent", call_model)
+workflow.add_node("tools", tool_node)
+
+# Set the entrypoint as `agent`
+# This means that this node is the first one called
+workflow.set_entry_point("agent")
+
+# We now add a conditional edge
+workflow.add_conditional_edges(
+    # First, we define the start node. We use `agent`.
+    # This means these are the edges taken after the `agent` node is called.
+    "agent",
+    # Next, we pass in the function that will determine which node is called next.
+    should_continue,
+)
+
+# We now add a normal edge from `tools` to `agent`.
+# This means that after `tools` is called, `agent` node is called next.
+workflow.add_edge("tools", 'agent')
+
+# Initialize memory to persist state between graph runs
+checkpointer = MemorySaver()
+
+# Finally, we compile it!
+# This compiles it into a LangChain Runnable,
+# meaning you can use it as you would any other runnable.
+# Note that we're (optionally) passing the memory when compiling the graph
+app = workflow.compile(checkpointer=checkpointer)
+
+# Use the Runnable
+final_state = app.invoke(
+    {"messages": [HumanMessage(content="what is the weather in sf")]},
+    config={"configurable": {"thread_id": 42}}
+)
+final_state["messages"][-1].content
+```
+
+```
+"Based on the search results, I can tell you that the current weather in San Francisco is:\n\nTemperature: 60 degrees Fahrenheit\nConditions: Foggy\n\nSan Francisco is known for its microclimates and frequent fog, especially during the summer months. The temperature of 60°F (about 15.5°C) is quite typical for the city, which tends to have mild temperatures year-round. The fog, often referred to as "Karl the Fog" by locals, is a characteristic feature of San Francisco\'s weather, particularly in the mornings and evenings.\n\nIs there anything else you\'d like to know about the weather in San Francisco or any other location?"
+```
+
+Now when we pass the same `"thread_id"`, the conversation context is retained via the saved state (i.e. stored list of messages)
+
+```python
+final_state = app.invoke(
+    {"messages": [HumanMessage(content="what about ny")]},
+    config={"configurable": {"thread_id": 42}}
+)
+final_state["messages"][-1].content
+```
+
+```
+"Based on the search results, I can tell you that the current weather in New York City is:\n\nTemperature: 90 degrees Fahrenheit (approximately 32.2 degrees Celsius)\nConditions: Sunny\n\nThis weather is quite different from what we just saw in San Francisco. New York is experiencing much warmer temperatures right now. Here are a few points to note:\n\n1. The temperature of 90°F is quite hot, typical of summer weather in New York City.\n2. The sunny conditions suggest clear skies, which is great for outdoor activities but also means it might feel even hotter due to direct sunlight.\n3. This kind of weather in New York often comes with high humidity, which can make it feel even warmer than the actual temperature suggests.\n\nIt's interesting to see the stark contrast between San Francisco's mild, foggy weather and New York's hot, sunny conditions. This difference illustrates how varied weather can be across different parts of the United States, even on the same day.\n\nIs there anything else you'd like to know about the weather in New York or any other location?"
+```
+
+### Step-by-step Breakdown
+
+1. <details>
+    <summary>Initialize the model and tools.</summary>
+
+    - we use `ChatAnthropic` as our LLM. **NOTE:** we need make sure the model knows that it has these tools available to call. We can do this by converting the LangChain tools into the format for OpenAI tool calling using the `.bind_tools()` method.
+    - we define the tools we want to use - a search tool in our case. It is really easy to create your own tools - see documentation here on how to do that [here](https://python.langchain.com/docs/modules/agents/tools/custom_tools).
+   </details>
+
+2. <details>
+    <summary>Initialize graph with state.</summary>
+
+    - we initialize graph (`StateGraph`) by passing state schema (in our case `MessagesState`)
+    - `MessagesState` is a prebuilt state schema that has one attribute -- a list of LangChain `Message` objects, as well as logic for merging the updates from each node into the state
+   </details>
+
+3. <details>
+    <summary>Define graph nodes.</summary>
+
+    There are two main nodes we need:
+
+      - The `agent` node: responsible for deciding what (if any) actions to take.
+      - The `tools` node that invokes tools: if the agent decides to take an action, this node will then execute that action.
+   </details>
+
+4. <details>
+    <summary>Define entry point and graph edges.</summary>
+
+      First, we need to set the entry point for graph execution - `agent` node.
+
+      Then we define one normal and one conditional edge. Conditional edge means that the destination depends on the contents of the graph's state (`MessageState`). In our case, the destination is not known until the agent (LLM) decides.
+
+      - Conditional edge: after the agent is called, we should either:
+        - a. Run tools if the agent said to take an action, OR
+        - b. Finish (respond to the user) if the agent did not ask to run tools
+      - Normal edge: after the tools are invoked, the graph should always return to the agent to decide what to do next
+   </details>
+
+5. <details>
+    <summary>Compile the graph.</summary>
+
+    - When we compile the graph, we turn it into a LangChain [Runnable](https://python.langchain.com/v0.2/docs/concepts/#runnable-interface), which automatically enables calling `.invoke()`, `.stream()` and `.batch()` with your inputs
+    - We can also optionally pass checkpointer object for persisting state between graph runs, and enabling memory, human-in-the-loop workflows, time travel and more. In our case we use `MemorySaver` - a simple in-memory checkpointer
+    </details>
+
+6. <details>
+   <summary>Execute the graph.</summary>
+
+    1. LangGraph adds the input message to the internal state, then passes the state to the entrypoint node, `"agent"`.
+    2. The `"agent"` node executes, invoking the chat model.
+    3. The chat model returns an `AIMessage`. LangGraph adds this to the state.
+    4. Graph cycles the following steps until there are no more `tool_calls` on `AIMessage`:
+
+        - If `AIMessage` has `tool_calls`, `"tools"` node executes
+        - The `"agent"` node executes again and returns `AIMessage`
+
+    5. Execution progresses to the special `END` value and outputs the final state.
+    And as a result, we get a list of all our chat messages as output.
+   </details>
+
 
 ## Documentation
 
-- [docs.langchain.com](https://docs.langchain.com/oss/python/langgraph/overview) – Comprehensive documentation, including conceptual overviews and guides
-- [reference.langchain.com/python/langgraph](https://reference.langchain.com/python/langgraph) – API reference docs for LangGraph packages
-- [LangGraph Quickstart](https://docs.langchain.com/oss/python/langgraph/quickstart) – Get started building with LangGraph
-- [Chat LangChain](https://chat.langchain.com/) – Chat with the LangChain documentation and get answers to your questions
+* [Tutorials](https://langchain-ai.github.io/langgraph/tutorials/): Learn to build with LangGraph through guided examples.
+* [How-to Guides](https://langchain-ai.github.io/langgraph/how-tos/): Accomplish specific things within LangGraph, from streaming, to adding memory & persistence, to common design patterns (branching, subgraphs, etc.), these are the place to go if you want to copy and run a specific code snippet.
+* [Conceptual Guides](https://langchain-ai.github.io/langgraph/concepts/): In-depth explanations of the key concepts and principles behind LangGraph, such as nodes, edges, state and more.
+* [API Reference](https://langchain-ai.github.io/langgraph/reference/graphs/): Review important classes and methods, simple examples of how to use the graph and checkpointing APIs, higher-level prebuilt components and more.
+* [Cloud (beta)](https://langchain-ai.github.io/langgraph/cloud/): With one click, deploy LangGraph applications to LangGraph Cloud.
 
-**Discussions**: Visit the [LangChain Forum](https://forum.langchain.com) to connect with the community and share all of your technical questions, ideas, and feedback.
+## Contributing
 
-## Additional resources
-
-- **[Guides](https://docs.langchain.com/oss/python/learn)** – Quick, actionable code snippets for topics such as streaming, adding memory & persistence, and design patterns (e.g. branching, subgraphs, etc.).
-- **[LangChain Academy](https://academy.langchain.com/courses/intro-to-langgraph)** – Learn the basics of LangGraph in our free, structured course.
-- **[Case studies](https://www.langchain.com/built-with-langgraph)** – Hear how industry leaders use LangGraph to ship AI applications at scale.
-- [Contributing Guide](https://docs.langchain.com/oss/python/contributing/overview) – Learn how to contribute to LangChain projects and find good first issues.
-- [Code of Conduct](https://github.com/langchain-ai/langchain/?tab=coc-ov-file) – Our community guidelines and standards for participation.
-
----
-
-## Acknowledgements
-
-LangGraph is inspired by [Pregel](https://research.google/pubs/pub37252/) and [Apache Beam](https://beam.apache.org/). The public interface draws inspiration from [NetworkX](https://networkx.org/documentation/latest/). LangGraph is built by LangChain Inc, the creators of LangChain, but can be used without LangChain.
+For more information on how to contribute, see [here](https://github.com/langchain-ai/langgraph/blob/main/CONTRIBUTING.md).

docs/.gitignore

@@ -1 +1,4 @@
-_site/
+*.ipynb
+site/
+docs/tutorials/**/*.png
+docs/cloud/reference/sdk/js_ts_sdk_ref.md

docs/_scripts/copy_notebooks.py

@@ -0,0 +1,220 @@
+import json
+import os
+import re
+import shutil
+from pathlib import Path
+
+root_dir = Path(__file__).resolve().parents[2]
+
+examples_dir = root_dir / "examples"
+docs_dir = root_dir / "docs/docs"
+how_tos_dir = docs_dir / "how-tos"
+tutorials_dir = docs_dir / "tutorials"
+cloud_how_tos_dir = docs_dir / "cloud/how-tos"
+cloud_sdk_dir = docs_dir / "cloud"
+
+_MANUAL = {
+    "how-tos": [
+        "state-context-key.ipynb",
+        "async.ipynb",
+        "stream-values.ipynb",
+        "stream-updates.ipynb",
+        "stream-multiple.ipynb",
+        "streaming-tokens.ipynb",
+        "streaming-tokens-without-langchain.ipynb",
+        "streaming-content.ipynb",
+        "streaming-events-from-within-tools.ipynb",
+        "streaming-events-from-within-tools-without-langchain.ipynb",
+        "streaming-from-final-node.ipynb",
+        "persistence.ipynb",
+        "input_output_schema.ipynb",
+        "pass_private_state.ipynb",
+        "memory/manage-conversation-history.ipynb",
+        "memory/delete-messages.ipynb",
+        "memory/add-summary-conversation-history.ipynb",
+        "persistence_postgres.ipynb",
+        "persistence_mongodb.ipynb",
+        "persistence_redis.ipynb",
+        "visualization.ipynb",
+        "state-model.ipynb",
+        "subgraph.ipynb",
+        "force-calling-a-tool-first.ipynb",
+        "pass-run-time-values-to-tools.ipynb",
+        "tool-calling.ipynb",
+        "tool-calling-errors.ipynb",
+        "pass-config-to-tools.ipynb",
+        "dynamic-returning-direct.ipynb",
+        "managing-agent-steps.ipynb",
+        "respond-in-format.ipynb",
+        "branching.ipynb",
+        "dynamically-returning-directly.ipynb",
+        "configuration.ipynb",
+        "map-reduce.ipynb",
+        "create-react-agent.ipynb",
+        "create-react-agent-system-prompt.ipynb",
+        "create-react-agent-memory.ipynb",
+        "create-react-agent-hitl.ipynb",
+        "human_in_the_loop/breakpoints.ipynb",
+        "human_in_the_loop/time-travel.ipynb",
+        "human_in_the_loop/edit-graph-state.ipynb",
+        "human_in_the_loop/wait-user-input.ipynb",
+        "node-retries.ipynb",
+    ],
+    "tutorials": [
+        "introduction.ipynb",
+        "customer-support/customer-support.ipynb",
+        "tutorials/tnt-llm/tnt-llm.ipynb",
+        "tutorials/sql-agent.ipynb",
+    ],
+}
+_MANUAL_INVERSE = {v: docs_dir / k for k, vs in _MANUAL.items() for v in vs}
+_HOW_TOS = {"agent_executor", "chat_agent_executor_with_function_calling", "docs"}
+_HIDE = set(
+    str(examples_dir / f)
+    for f in [
+        "agent_executor/base.ipynb",
+        "agent_executor/force-calling-a-tool-first.ipynb",
+        "agent_executor/high-level.ipynb",
+        "agent_executor/human-in-the-loop.ipynb",
+        "agent_executor/managing-agent-steps.ipynb",
+        "chat_agent_executor_with_function_calling/anthropic.ipynb",
+        "chat_agent_executor_with_function_calling/base.ipynb",
+        "chat_agent_executor_with_function_calling/dynamically-returning-directly.ipynb",
+        "chat_agent_executor_with_function_calling/force-calling-a-tool-first.ipynb",
+        "chat_agent_executor_with_function_calling/high-level-tools.ipynb",
+        "chat_agent_executor_with_function_calling/high-level.ipynb",
+        "chat_agent_executor_with_function_calling/human-in-the-loop.ipynb",
+        "chat_agent_executor_with_function_calling/managing-agent-steps.ipynb",
+        "chat_agent_executor_with_function_calling/prebuilt-tool-node.ipynb",
+        "chat_agent_executor_with_function_calling/respond-in-format.ipynb",
+        "chatbots/customer-support.ipynb",
+        "rag/langgraph_rag_agent_llama3_local.ipynb",
+        "rag/langgraph_self_rag_pinecone_movies.ipynb",
+        "rag/langgraph_adaptive_rag_cohere.ipynb",
+        "dynamically-returning-directly.ipynb",
+        "force-calling-a-tool-first.ipynb",
+        "managing-agent-steps.ipynb",
+        "respond-in-format.ipynb",
+        "quickstart.ipynb",
+        "human-in-the-loop.ipynb",
+        "learning.ipynb",
+        "docs/quickstart.ipynb",
+        "tutorials/rag-agent-testing.ipynb",
+        "tutorials/rag-agent-testing-local.ipynb",
+        "tutorials/tool-calling-agent-local.ipynb",
+        "time-travel.ipynb",
+        "code_assistant/langgraph_code_assistant_mistral.ipynb",
+    ]
+)
+
+
+def clean_notebooks():
+    roots = (how_tos_dir, tutorials_dir)
+    for dir_ in roots:
+        traversed = []
+        for root, dirs, files in os.walk(dir_):
+            for file in files:
+                if file.endswith(".ipynb"):
+                    os.remove(os.path.join(root, file))
+            # Now delete the dir if it is empty now
+            if root not in roots:
+                traversed.append(root)
+
+        for root in reversed(traversed):
+            if not os.listdir(root):
+                os.rmdir(root)
+
+
+def update_notebook_links(notebook_path):
+    with open(notebook_path, "r", encoding="utf-8") as f:
+        notebook = json.load(f)
+
+    for cell in notebook["cells"]:
+        if cell["cell_type"] == "markdown":
+            for i, source in enumerate(cell["source"]):
+                # Update relative notebook links
+                cell["source"][i] = re.sub(
+                    r"\[([^\]]+)\]\(([^:)]+\.ipynb)\)",
+                    lambda m: transform_link(m.group(1), m.group(2)),
+                    source,
+                )
+
+    with open(notebook_path, "w", encoding="utf-8") as f:
+        json.dump(notebook, f, indent=2)
+
+
+def transform_link(text, link):
+    dir_path, filename = os.path.split(link)
+
+    # Remove the .ipynb extension
+    filename_without_ext = os.path.splitext(filename)[0]
+
+    # If it's a local link (starts with ./)
+    if link.startswith("./"):
+        # Change to parent directory and remove ./ prefix
+        new_link = f"../{filename_without_ext}/"
+    elif dir_path:
+        # If there's a directory path, keep it and add one more level up
+        new_link = f"../{dir_path}/{filename_without_ext}/"
+    else:
+        # If it's just a filename, simply go one level up
+        new_link = f"../{filename_without_ext}/"
+
+    return f"[{text}]({new_link})"
+
+
+def copy_notebooks():
+    # Nested ones are mostly tutorials rn
+    for root, dirs, files in os.walk(examples_dir):
+        if any(
+            path.startswith(".") or path.startswith("__") for path in root.split(os.sep)
+        ):
+            continue
+        if any(path in _HOW_TOS for path in root.split(os.sep)):
+            dst_dir = how_tos_dir
+        elif "sdk" in root.split(os.sep):
+            dst_dir = cloud_sdk_dir
+        elif "cloud_examples" in root.split(os.sep):
+            dst_dir = cloud_how_tos_dir
+        else:
+            dst_dir = tutorials_dir
+        for file in files:
+            dst_dir_ = dst_dir
+            if file.endswith((".ipynb", ".png")):
+                src_path = os.path.join(root, file)
+                if src_path in _HIDE:
+                    print("Hiding:", src_path)
+                    continue
+                dst_path = os.path.join(
+                    dst_dir, os.path.relpath(src_path, examples_dir)
+                )
+                for k in _MANUAL_INVERSE:
+                    if src_path.endswith(k):
+                        overridden_dir = _MANUAL_INVERSE[k]
+                        dst_path = os.path.join(
+                            overridden_dir, os.path.relpath(src_path, examples_dir)
+                        )
+                        print(f"Overriding: {src_path} to {dst_path}")
+                        break
+                # Avoid double nesting.
+                dst_path = dst_path.replace("tutorials/tutorials", "tutorials").replace(
+                    "how-tos/how-tos", "how-tos"
+                )
+                os.makedirs(os.path.dirname(dst_path), exist_ok=True)
+                print(f"Copying: {src_path} to {dst_path}")
+                shutil.copy(src_path, dst_path)
+                # Convert all ./img/* to ../img/*
+                if file.endswith(".ipynb"):
+                    with open(dst_path, "r") as f:
+                        content = f.read()
+                    content = content.replace("(./img/", "(../img/")
+                    content = content.replace('src=\\"./img/', 'src=\\"../img/')
+                    with open(dst_path, "w") as f:
+                        f.write(content)
+                    update_notebook_links(dst_path)
+                dst_dir = dst_dir_
+
+
+if __name__ == "__main__":
+    clean_notebooks()
+    copy_notebooks()

docs/codespell_notebooks.sh

@@ -0,0 +1,13 @@
+ERROR_FOUND=0
+for file in $(find $1 -name "*.ipynb"); do
+    OUTPUT=$(cat "$file" | jupytext --from ipynb --to py:percent | codespell -)
+    if [ -n "$OUTPUT" ]; then
+        echo "Errors found in $file"
+        echo "$OUTPUT"
+        ERROR_FOUND=1
+    fi
+done
+
+if [ "$ERROR_FOUND" -ne 0 ]; then
+    exit 1
+fi

docs/docs/cloud/concepts/api.md

@@ -0,0 +1,111 @@
+# API Concepts
+
+This page describes the high-level concepts of the LangGraph Cloud API. The conceptual guide of LangGraph (Python library) is [here](../../concepts/index.md).
+
+## Data Models
+
+The LangGraph Cloud API consists of a few core data models: [Assistants](#assistants), [Threads](#threads), [Runs](#runs), and [Cron Jobs](#cron-jobs).
+
+### Assistants
+
+An assistant is a configured instance of a [`CompiledGraph`][compiledgraph]. It abstracts the cognitive architecture of the graph and contains instance specific configuration and metadata. Multiple assistants can reference the same graph but can contain different configuration and metadata, which may differentiate the behavior of the assistants. An assistant (i.e. the graph) is invoked as part of a run.
+
+The LangGraph Cloud API provides several endpoints for creating and managing assistants. See the <a href="../reference/api/api_ref.html#tag/assistantscreate" target="_blank">API reference</a> for more details.
+
+#### Configuring Assistants
+
+You can save custom assistants from the same graph to set different default prompts, models, and other configurations without changing a line of code in your graph. This allows you the ability to quickly test out different configurations without having to rewrite your graph every time, and also give users the flexibility to select different configurations when using your LangGraph application. See <a href="https://langchain-ai.github.io/langgraph/cloud/how-tos/cloud_examples/configuration_cloud/">this</a> how-to for information on how to configure a deployed graph. 
+
+### Threads
+
+A thread contains the accumulated state of a group of runs. If a run is executed on a thread, then the [state][state] of the underlying graph of the assistant will be persisted to the thread. A thread's current and historical state can be retrieved. To persist state, a thread must be created prior to executing a run.
+
+The state of a thread at a particular point in time is called a checkpoint.
+
+For more on threads and checkpoints, see this section of the [LangGraph conceptual guide](../../concepts/low_level.md#checkpointer).
+
+The LangGraph Cloud API provides several endpoints for creating and managing threads and thread state. See the <a href="../reference/api/api_ref.html#tag/threadscreate" target="_blank">API reference</a> for more details.
+
+### Runs
+
+A run is an invocation of an assistant. Each run may have its own input, configuration, and metadata, which may affect execution and output of the underlying graph. A run can optionally be executed on a thread.
+
+The LangGraph Cloud API provides several endpoints for creating and managing runs. See the <a href="../reference/api/api_ref.html#tag/runscreate" target="_blank">API reference</a> for more details.
+
+### Cron Jobs
+
+It's often useful to run graphs on some schedule. LangGraph Cloud supports cron jobs, which run on a user defined schedule. The user specifies a schedule, an assistant, and some input. After than, on the specified schedule LangGraph cloud will:
+
+- Create a new thread with the specified assistant
+- Send the specified input to that thread
+
+Note that this sends the same input to the thread every time. See the [how-to guide](../how-tos/cloud_examples/cron_jobs.ipynb) for creating cron jobs.
+
+The LangGraph Cloud API provides several endpoints for creating and managing cron jobs. See the <a href="../reference/api/api_ref.html#tag/runscreate/POST/threads/{thread_id}/runs/crons" target="_blank">API reference</a> for more details.
+
+## Features
+
+The LangGraph Cloud API offers several features to support complex agent architectures.
+
+### Streaming
+
+Streaming is critical for making LLM applications feel responsive to end users. When creating a streaming run, the streaming mode determines what data is streamed back to the API client. The LangGraph Cloud API supports five streaming modes.
+
+- `values`: Stream the full state of the graph after each node is executed. See the [how-to guide](../how-tos/stream_values.md) for streaming values.
+- `messages`: Stream complete messages (at the end of node execution) as well as tokens for any messages generated inside a node. This mode is primarily meant for powering chat applications. This is only an option if your graph contains a `messages` key. See the [how-to guide](../how-tos/stream_messages.md) for streaming messages.
+- `updates`: Streams updates to the state of the graph after each node is executed. See the [how-to guide](../how-tos/stream_updates.md) for streaming updates.
+- `events`: Stream all events (including the state of the graph) after each node is executed. See the [how-to guide](../how-tos/stream_events.md) for streaming events. This can be used to do token-by-token streaming for LLMs.
+- `debug`: Stream debug events after each node is executed. See the [how-to guide](../how-tos/stream_debug.md) for streaming debug events.
+
+You can also specify multiple streaming modes at the same time. See the [how-to guide](../how-tos/stream_multiple.md) for configuring multiple streaming modes at the same time.
+
+See the <a href="../reference/api/api_ref.html#tag/runscreate/POST/threads/{thread_id}/runs/stream" target="_blank">API reference</a> for how to create streaming runs.
+
+### Human-in-the-Loop
+
+There are many occasions where the graph cannot run completely autonomously. For instance, the user might need to input some additional arguments to a function call, or select the next edge for the graph to continue on. In these instances, we need to insert some human in the loop interaction, which you can learn about in the [human in the loop how-tos](../how-tos/index.md#human-in-the-loop).
+
+### Double Texting
+
+Many times users might interact with your graph in unintended ways. For instance, a user may send one message and before the graph has finished running send a second message. To solve this issue of "double-texting" (i.e. prompting the graph a second time before the first run has finished), LangGraph has provided four different solutions, all of which are covered in the [Double Texting how-tos](../how-tos/index.md#double-texting). These options are:
+
+- `reject`: This is the simplest option, this just rejects any follow up runs and does not allow double texting. See the [how-to guide](../how-tos/reject_concurrent.md) for configuring the reject double text option.
+- `enqueue`: This is a relatively simple option which continues the first run until it completes the whole run, then sends the new input as a separate run. See the [how-to guide](../how-tos/enqueue_concurrent.md) for configuring the enqueue double text option.
+- `interrupt`: This option interrupts the current execution but saves all the work done up until that point. It then inserts the user input and continues from there. If you enable this option, your graph should be able to handle weird edge cases that may arise. See the [how-to guide](../how-tos/interrupt_concurrent.md) for configuring the interrupt double text option.
+- `rollback`: This option rolls back all work done up until that point. It then sends the user input in, basically as if it just followed the original run input. See the [how-to guide](../how-tos/rollback_concurrent.md) for configuring the rollback double text option.
+
+### Stateless Runs
+
+All runs use the built-in checkpointer to store checkpoints for runs. However, it can often be useful to just kick off a run without worrying about explicitly creating a thread and without wanting to keep those checkpointers around. Stateless runs allow you to do this by exposing an endpoint that:
+
+- Takes in user input
+- Under the hood, creates a thread
+- Runs the agent but skips all checkpointing steps
+- Cleans up the thread afterwards
+
+Stateless runs are still retried as regular retries are per node, while everything still in memory, so doesn't use checkpoints.
+
+The only difference is in stateless background runs, if the task worker dies halfway (not because the run itself failed, for some external reason) then the whole run will be retried like any background run, but
+
+- whereas a stateful background run would retry from the last successful checkpoint
+- a stateless background run would retry from the beginning
+
+See the [how-to guide](../how-tos/cloud_examples/stateless_runs.ipynb) for creating stateless runs.
+
+### Webhooks
+
+For all types of runs, langgraph cloud supports completion webhooks. When you create the run you can pass a webhook URL to be called when the completes (successfully or not). This is especially useful for background runs and cron jobs, as the webhook can give you an indication the run has completed and you can perform further actions for your appilcation.
+
+See this [how-to guide](../how-tos/cloud_examples/webhooks.ipynb) to learn about how to use webhooks with LangGraph Cloud.
+
+## Deployment
+
+The LangGraph Cloud offers several features to support secure and robost deployments.
+
+### Authentication
+
+LangGraph applications deployed to LangGraph Cloud are automatically configured with LangSmith authentication. In order to call the API, a valid <a href="https://docs.smith.langchain.com/how_to_guides/setup/create_account_api_key#api-keys" target="_blank">LangSmith API key</a> is required.
+
+### Local Testing
+
+Before deploying your app in production to LangGraph Cloud, you may wish to test out your graph locally in order to ensure that everything is running as expected. Luckily, LangGraph makes this easy for you through use of the LangGraph CLI. Read more in this [how-to guide](../deployment/test_locally.md) or look at the [CLI reference](../reference/cli.md) to learn more.

docs/docs/cloud/concepts/cloud.md

@@ -0,0 +1,28 @@
+# Cloud Concepts
+
+This page describes the high-level concepts of the LangGraph Cloud deployment.
+
+## Deployment
+
+A deployment is an instance of a LangGraph API. A single deployment can have many [revisions](#revision). When a deployment is created, all of the necessary infrastructure (e.g. database, containers, secrets store) are automatically provisioned. See the [architecture diagram](#architecture) below for more details.
+
+See the [how-to guide](../deployment/cloud.md#create-new-deployment) for creating a new deployment.
+
+## Revision
+
+A revision is an iteration of a [deployment](#deployment). When a new deployment is created, an initial revision is automatically created. To deploy new code changes or update environment variable configurations for a deployment, a new revision must be created. When a revision is created, a new container image is built automatically.
+
+See the [how-to guide](../deployment/cloud.md#create-new-revision) for creating a new revision.
+
+## Asynchronous Deployment
+
+Infrastructure for [deployments](#deployment) and [revisions](#revision) are provisioned and deployed asynchronously. They are not deployed immediately after submission. Currently, deployment can take up to several minutes.
+
+## Architecture
+
+!!! warning "Subject to Change"
+    The LangGraph Cloud deployment architecture may change in the future.
+
+A high-level diagram of a LangGraph Cloud deployment.
+
+![diagram](langgraph_cloud_architecture.png)

docs/docs/cloud/deployment/cloud.md

@@ -0,0 +1,78 @@
+# How to Deploy to LangGraph Cloud
+
+LangGraph Cloud is available within <a href="https://www.langchain.com/langsmith" target="_blank">LangSmith</a>. To deploy a LangGraph Cloud API, navigate to the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>.
+
+## Prerequisites
+
+1. LangGraph Cloud applications are deployed from GitHub repositories. Configure and upload a LangGraph Cloud application to a GitHub repository in order to deploy it to LangGraph Cloud.
+1. [Verify that the LangGraph API runs locally](test_locally.md). If the API does not build and run successfully (i.e. `langgraph up`), deploying to LangGraph Cloud will fail as well.
+
+## Create New Deployment
+
+Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>...
+
+1. In the left-hand navigation panel, select `Deployments`. The `Deployments` view contains a list of existing LangGraph Cloud deployments.
+1. In the top-right corner, select `+ New Deployment` to create a new deployment.
+1. In the `Create New Deployment` panel, fill out the required fields.
+    1. `Deployment details`
+        1. Select `Import from GitHub` and follow the GitHub OAuth workflow to install and authorize LangChain's `hosted-langserve` GitHub app to  access the selected repositories. After installation is complete, return to the `Create New Deployment` panel and select the GitHub repository to deploy from the dropdown menu.
+        1. Specify a name for the deployment.
+        1. Specify the full path to the [LangGraph API config file](../reference/cli.md#configuration-file) including the file name. For example, if the file `langgraph.json` is in the root of the repository, simply specify `langgraph.json`.
+        1. Specify the desired `git` reference (e.g. branch name). For example, different branches of the repository can be deployed.
+    1. Select the desired `Deployment Type`.
+        1. `Development` deployments are meant for non-production use cases and are provisioned with minimal resources.
+        1. `Production` deployments can serve up to 500 requests/second and are provisioned with highly available storage with automatic backups.
+    1. Specify `Environment Variables` and secrets. See the [Environment Variables reference](../reference/env_var.md) to configure additional variables for the deployment.
+        1. Sensitive values such as API keys (e.g. `OPENAI_API_KEY`) should be specified as secrets.
+        1. Additional non-secret environment variables can be specified as well.
+    1. A new LangSmith `Tracing Project` is automatically created with the same name as the deployment.
+1. In the top-right corner, select `Submit`. After a few seconds, the `Deployment` view appears and the new deployment will be queued for provisioning.
+
+## Create New Revision
+
+When [creating a new deployment](#create-new-deployment), a new revision is created by default. Subsequent revisions can be created to deploy new code changes.
+
+Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>...
+
+1. In the left-hand navigation panel, select `Deployments`. The `Deployments` view contains a list of existing LangGraph Cloud deployments.
+1. Select an existing deployment to create a new revision for.
+1. In the `Deployment` view, in the top-right corner, select `+ New Revision`.
+1. In the `New Revision` modal, fill out the required fields.
+    1. Specify the full path to the [LangGraph API config file](../reference/cli.md#configuration-file) including the file name. For example, if the file `langgraph.json` is in the root of the repository, simply specify `langgraph.json`.
+    1. Specify the desired `git` reference (e.g. branch name). For example, different branches of the repository can be deployed.
+    1. Specify `Environment Variables` and secrets. Existing secrets and environment variables are prepopulated. See the [Environment Variables reference](../reference/env_var.md) to configure additional variables for the revision.
+        1. Add new secrets or environment variables.
+        1. Remove existing secrets or environment variables.
+        1. Update the value of existing secrets or environment variables.
+1. Select `Submit`. After a few seconds, the `New Revision` modal will close and the new revision will be queued for deployment.
+
+## View Build and Deployment Logs
+
+Build and deployment logs are available for each revision.
+
+Starting from the `Deployment` view...
+
+1. Select the desired revision from the `Revisions` table. A panel slides open from the right-hand side and the `Build` tab is selected by default, which displays build logs for the revision.
+1. In the panel, select the `Deploy` tab to view deployment logs for the revision.
+1. Within the `Deploy` tab, adjust the date/time range picker as needed. By default, the date/time range picker is set to the `Last 15 minutes`.
+
+## Interrupt Revision
+
+Interrupting a revision will stop deployment of the revision.
+
+!!! warning "Undefined Behavior"
+    Interrupted revisions have undefined behavior. This is only useful if you need to deploy a new revision and you already have a revision "stuck" in progress. In the future, this feature may be removed.
+
+Starting from the `Deployment` view...
+
+1. Select the menu icon (three dots) on the right-hand side of the row for the desired revision from the `Revisions` table.
+1. Select `Interrupt` from the menu.
+1. A modal will appear. Review the confirmation message. Select `Interrupt revision`.
+
+## Delete Deployment
+
+Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>...
+
+1. In the left-hand navigation panel, select `Deployments`. The `Deployments` view contains a list of existing LangGraph Cloud deployments.
+1. Select the menu icon (three dots) on the right-hand side of the row for the desired deployment and select `Delete`.
+1. A `Confirmation` modal will appear. Select `Delete`.

docs/docs/cloud/deployment/graph_rebuild.md

@@ -0,0 +1,146 @@
+# Rebuild Graph at Runtime
+
+You might need to rebuild your graph with a different configuration for a new run. For example, you might need to use a different graph state or graph structure depending on the config. This guide shows how you can do this.
+
+!!! note "Note"
+    In most cases, customizing behavior based on the config should be handled by a single graph where each node can read a config and change its behavior based on it
+
+## Prerequisites
+
+Make sure to check out [this how-to guide](./setup.md) on setting up your app for deployment first.
+
+## Define graphs
+
+Let's say you have an app with a simple graph that calls an LLM and returns the response to the user. The app file directory looks like the following:
+
+```
+my-app/
+|-- requirements.txt
+|-- .env
+|-- openai_agent.py     # code for your graph
+```
+
+where the graph is defined in `openai_agent.py`. 
+
+### No rebuild
+
+In the standard LangGraph API configuration, the server uses the compiled graph instance that's defined at the top level of `openai_agent.py`, which looks like the following:
+
+```python
+from langchain_openai import ChatOpenAI
+from langgraph.graph import END, MessageGraph
+
+model = ChatOpenAI(temperature=0)
+
+graph_workflow = MessageGraph()
+
+graph_workflow.add_node("agent", model)
+graph_workflow.add_edge("agent", END)
+graph_workflow.set_entry_point("agent")
+
+agent = graph_workflow.compile()
+```
+
+To make the server aware of your graph, you need to specify a path to the variable that contains the `CompiledStateGraph` instance in your LangGraph API configuration (`langgraph.json`), e.g.:
+
+```
+{
+    "dependencies": ["."],
+    "graphs": {
+        "openai_agent": "./openai_agent.py:agent",
+    },
+    "env": "./.env"
+}
+```
+
+### Rebuild
+
+To make your graph rebuild on each new run with custom configuration, you need to rewrite `openai_agent.py` to instead provide a _function_ that takes a config and returns a graph (or compiled graph) instance. Let's say we want to return our existing graph for user ID '1', and a tool-calling agent for other users. We can modify `openai_agent.py` as follows:
+
+```python
+from typing import Annotated, TypedDict
+from langchain_openai import ChatOpenAI
+from langgraph.graph import END, MessageGraph
+from langgraph.graph.state import StateGraph
+from langgraph.graph.message import add_messages
+from langgraph.prebuilt import ToolNode
+from langchain_core.tools import tool
+from langchain_core.messages import BaseMessage
+from langchain_core.runnables import RunnableConfig
+
+
+class State(TypedDict):
+    messages: Annotated[list[BaseMessage], add_messages]
+
+
+model = ChatOpenAI(temperature=0)
+
+def make_default_graph():
+    """Make a simple LLM agent"""
+    graph_workflow = StateGraph(State)
+    def call_model(state):
+        return {"messages": [model.invoke(state["messages"])]}
+
+    graph_workflow.add_node("agent", call_model)
+    graph_workflow.add_edge("agent", END)
+    graph_workflow.set_entry_point("agent")
+
+    agent = graph_workflow.compile()
+    return agent
+
+
+def make_alternative_graph():
+    """Make a tool-calling agent"""
+
+    @tool
+    def add(a: float, b: float):
+        """Adds two numbers."""
+        return a + b
+
+    tool_node = ToolNode([add])
+    model_with_tools = model.bind_tools([add])
+    def call_model(state):
+        return {"messages": [model_with_tools.invoke(state["messages"])]}
+
+    def should_continue(state: State):
+        if state["messages"][-1].tool_calls:
+            return "tools"
+        else:
+            return END
+
+    graph_workflow = StateGraph(State)
+
+    graph_workflow.add_node("agent", call_model)
+    graph_workflow.add_node("tools", tool_node)
+    graph_workflow.add_edge("tools", "agent")
+    graph_workflow.set_entry_point("agent")
+    graph_workflow.add_conditional_edges("agent", should_continue)
+
+    agent = graph_workflow.compile()
+    return agent
+
+
+# this is the graph making function that will decide which graph to
+# build based on the provided config
+def make_graph(config: RunnableConfig):
+    user_id = config.get("configurable", {}).get("user_id")
+    # route to different graph state / structure based on the user ID
+    if user_id == "1":
+        return make_default_graph()
+    else:
+        return make_alternative_graph()
+```
+
+Finally, you need to specify the path to your graph-making function (`make_graph`) in `langgraph.json`:
+
+```
+{
+    "dependencies": ["."],
+    "graphs": {
+        "openai_agent": "./openai_agent.py:make_graph",
+    },
+    "env": "./.env"
+}
+```
+
+See more info on LangGraph API configuration file [here](../reference/cli.md#configuration-file)

docs/docs/cloud/deployment/self_hosted.md

@@ -0,0 +1,35 @@
+# How to Self-Host LangGraph Cloud API
+
+!!! warning "Enterprise License Required"
+    Self-hosting LangGraph Cloud API requires a license key. Please contact sales@langchain.dev for more details.
+
+LangGraph Cloud APIs can be self-hosted with a valid LangGraph Cloud license key. Self-hosted deployments are built with Docker and deployed with Helm (on Kubernetes) or with Docker Compose. Ensure that the [Docker CLI](https://docs.docker.com/engine/reference/commandline/cli/) is installed.
+
+LangGraph Cloud license key should be passed to the service as an environment variable named LANGGRAPH_CLOUD_LICENSE_KEY.
+
+## Build Docker Image
+
+1. Follow the [How-to Guide](setup.md) for setting up a LangGraph application for deployment. Your LangGraph application will vary from the example in the How-to Guide. However, ensure that the [LangGraph API configuration file](../reference/cli.md#configuration-file) is created.
+1. Install the [LangGraph CLI](../reference/cli.md#installation).
+1. Run the following LangGraph CLI `build` command to build a Docker image. Specify the image tag (`-t`) and other desired [options](../reference/cli.md#build).
+
+        langgraph build -t tag_name
+
+!!! info "Build Platform"
+    When building the Docker image, ensure that the image is built for the platform of the target Kubernetes cluster: `langgraph build -t tag_name --platform linux/amd64,linux/arm64`
+
+## Self-Host on Kubernetes
+
+This section is for self-hosting LangGraph Cloud API on Kubernetes via Helm. A Kubernetes cluster must be provisioned before proceeding with these steps. The public Helm chart for LangGraph Cloud is available [here](https://github.com/langchain-ai/helm/tree/main/charts/langgraph-cloud).
+
+1. Publish the built Docker image to a repository that can be accessed by the target Kubernetes cluster.
+1. Ensure that the [Helm client](https://github.com/helm/helm?tab=readme-ov-file#install) is installed.
+1. Make note of all environment variables that are needed for the application. These values will need to be set in the Helm `values` YAML configuration.
+1. Follow [these instructions](https://github.com/langchain-ai/helm/tree/main/charts/langgraph-cloud#readme) to configure the Helm chart and deploy to Kubernetes.
+
+## Self-Host with Docker
+
+!!! warning "Under Construction"
+    This section of the documentation is in progress.
+
+Docker Compose can be used to deploy LangGraph Cloud to the compute infrastructure of your choice (e.g. VM).

docs/docs/cloud/deployment/setup.md

@@ -0,0 +1,142 @@
+# How to Set Up a LangGraph Application for Deployment
+
+A LangGraph application must be configured with a [LangGraph API configuration file](../reference/cli.md#configuration-file) in order to be deployed to LangGraph Cloud (or to be self-hosted). This how-to guide discusses the basic steps to setup a LangGraph application for deployment using `requirements.txt` to specify project dependencies. If you prefer using poetry for dependency management, check out [this how-to guide](./setup_pyproject.md) on using `pyproject.toml` for LangGraph Cloud.
+
+The final repo structure will look something like this:
+
+```bash
+my-app/
+|-- requirements.txt    # package dependencies
+|-- .env                # environment variables
+|-- openai_agent.py     # code for an agent
+|-- anthropic_agent.py  # code for another agent
+|-- langgraph.json      # configuration file for LangGraph
+```
+
+After each step, an example file directory is provided to demonstrate how code can be organized.
+
+## Specify Dependencies
+
+Dependencies can optionally be specified in one of the following files: `pyproject.toml`, `setup.py`, or `requirements.txt`. If none of these files is created, then dependencies can be specified later in the [LangGraph API configuration file](#create-langgraph-api-config).
+
+The dependencies below will be included in the image, you can also use them in your code, as long as with a compatible version range:
+```
+langgraph>=0.1.7
+langchain-core>=0.2.7
+orjson>=3.10.1
+langsmith>=0.1.50
+httpx>=0.27.0
+langchain-core>=0.2.8
+langsmith>=0.1.63
+tenacity>=8.3.0
+uvicorn>=0.29.0
+sse-starlette>=2.1.0
+uvloop>=0.19.0
+httptools>=0.6.1
+jsonschema-rs>=0.18.0
+croniter>=1.0.1
+```
+
+Example `requirements.txt` file:
+```
+langgraph
+langchain_openai
+```
+
+Example file directory:
+```
+my-app/
+|-- requirements.txt    # Python packages required for your graph
+```
+
+## Specify Environment Variables
+
+Environment variables can optionally be specified in a file (e.g. `.env`). See the [Environment Variables reference](../reference/env_var.md) to configure additional variables for a deployment.
+
+Example `.env` file:
+```
+MY_ENV_VAR_1=foo
+MY_ENV_VAR_2=bar
+OPENAI_API_KEY=key
+```
+
+Example file directory:
+```
+my-app/
+|-- requirements.txt
+|-- .env                # file with environment variables
+```
+
+## Define Graphs
+
+Implement your graphs! Graphs can be defined in a single file or multiple files. Make note of the variable names of each [CompiledGraph][compiledgraph] to be included in the LangGraph application. The variable names will be used later when creating the [LangGraph API configuration file](../reference/cli.md#configuration-file).
+
+Example `openai_agent.py` file:
+```python
+from langchain_openai import ChatOpenAI
+from langgraph.graph import END, MessageGraph
+
+model = ChatOpenAI(temperature=0)
+
+graph_workflow = MessageGraph()
+
+graph_workflow.add_node("agent", model)
+graph_workflow.add_edge("agent", END)
+graph_workflow.set_entry_point("agent")
+
+agent = graph_workflow.compile()
+```
+
+!!! warning "Assign `CompiledGraph` to Variable"
+    The build process for LangGraph Cloud requires that the `CompiledGraph` object be assigned to a variable at the top-level of a Python module (alternatively, you can provide [a function that creates a graph](./graph_rebuild.md)).
+
+Example file directory:
+```
+my-app/
+|-- requirements.txt
+|-- .env
+|-- openai_agent.py     # code for your graph
+|-- anthropic_agent.py  # code for your graph
+```
+
+## Create LangGraph API Config
+
+Create a [LangGraph API configuration file](../reference/cli.md#configuration-file) called `langgraph.json`. See the [LangGraph CLI reference](../reference/cli.md#configuration-file) for detailed explanations of each key in the JSON object of the configuration file.
+
+Example `langgraph.json` file:
+```json
+{
+    "dependencies": [
+        "."
+    ],
+    "graphs": {
+        "openai_agent": "./openai_agent.py:agent",
+        "anthropic_agent": "./anthropic_agent.py:agent"
+    },
+    "env": "./.env"
+}
+```
+
+Note that the variable name of the `CompiledGraph` appears at the end of the value of each subkey in the top-level `graphs` key (i.e. `:<variable_name>`).
+
+!!! warning "Configuration Location"
+    The LangGraph API configuration file must be placed in a directory that is at the same level or higher than the Python files that contain compiled graphs and associated dependencies.
+
+Example file directory:
+
+```bash
+my-app/
+|-- requirements.txt
+|-- .env
+|-- openai_agent.py
+|-- anthropic_agent.py
+|-- langgraph.json      # configuration file for LangGraph
+```
+
+## Upload to GitHub
+
+To deploy the LangGraph application to LangGraph Cloud, the code must be uploaded to a GitHub repository.
+
+## Next
+
+After you setup your repo, it's time to [deploy your app](./cloud.md).

docs/docs/cloud/deployment/setup_pyproject.md

@@ -0,0 +1,175 @@
+# How to Set Up a LangGraph Application for Deployment
+
+A LangGraph application must be configured with a [LangGraph API configuration file](../reference/cli.md#configuration-file) in order to be deployed to LangGraph Cloud (or to be self-hosted). This how-to guide discusses the basic steps to setup a LangGraph application for deployment using `pyproject.toml` to define your package's dependencies. If you prefer using `requirements.txt` for dependency management, check out [this how-to guide](./setup.md).
+
+The final repo structure will look something like this:
+
+```bash
+my-app/
+├── my_agent # all project code lies within here
+│   ├── __init__.py
+│   └── agent.py # code for your graph
+│-- .env # environment variables
+│-- langgraph.json  # configuration file for LangGraph
+└── pyproject.toml # dependencies for your project
+```
+
+After each step, an example file directory is provided to demonstrate how code can be organized.
+
+## Specify Dependencies
+
+Dependencies can optionally be specified in one of the following files: `pyproject.toml`, `setup.py`, or `requirements.txt`. If none of these files is created, then dependencies can be specified later in the [LangGraph API configuration file](#create-langgraph-api-config).
+
+The dependencies below will be included in the image, you can also use them in your code, as long as with a compatible version range:
+```
+langgraph>=0.1.7
+langchain-core>=0.2.7
+orjson>=3.10.1
+langsmith>=0.1.50
+httpx>=0.27.0
+langchain-core>=0.2.8
+langsmith>=0.1.63
+tenacity>=8.3.0
+uvicorn>=0.29.0
+sse-starlette>=2.1.0
+uvloop>=0.19.0
+httptools>=0.6.1
+jsonschema-rs>=0.18.0
+croniter>=1.0.1
+```
+
+Example `pyproject.toml` file:
+
+```toml
+[tool.poetry]
+name = "my-agent"
+version = "0.0.1"
+description = "An excellent agent build for LangGraph cloud."
+authors = ["Polly the parrot <1223+polly@users.noreply.github.com>"]
+license = "MIT"
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = ">=3.9.0,<3.13"
+langgraph = "^0.1.7"
+langchain-fireworks = "^0.1.3"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+```
+
+Example file directory:
+
+```bash
+my-app/
+├── my_agent
+│   ├── __init__.py
+│   └── agent.py
+└── pyproject.toml   # Python packages required for your graph
+```
+
+## Specify Environment Variables
+
+Environment variables can optionally be specified in a file (e.g. `.env`). See the [Environment Variables reference](../reference/env_var.md) to configure additional variables for a deployment.
+
+Example `.env` file:
+
+```
+MY_ENV_VAR_1=foo
+MY_ENV_VAR_2=bar
+FIREWORKS_API_KEY=key
+```
+
+Example file directory:
+
+```bash
+my-app/
+├── my_agent
+│   ├── __init__.py
+│   └── agent.py
+|-- .env             # file with environment variables
+└── pyproject.toml
+```
+
+## Define Graphs
+
+Implement your graphs! Graphs can be defined in a single file or multiple files. Make note of the variable names of each [CompiledGraph][compiledgraph] to be included in the LangGraph application. The variable names will be used later when creating the [LangGraph API configuration file](../reference/cli.md#configuration-file).
+
+Example `agent.py` file:
+
+```python
+# my_agent/agent.py
+from langchain_fireworks import ChatFireworks
+from langgraph.graph import END, StateGraph, add_messages
+from typing_extensions import TypedDict, Annotated
+
+model = ChatFireworks(model="accounts/fireworks/models/firefunction-v2", temperature=0)
+
+class State(TypedDict):
+    messages: Annotated[list, add_messages]
+
+graph_workflow = StateGraph(State)
+
+graph_workflow.add_node("agent", model)
+graph_workflow.add_edge("agent", END)
+graph_workflow.set_entry_point("agent")
+
+agent = graph_workflow.compile()
+```
+
+!!! warning "Assign `CompiledGraph` to Variable"
+    The build process for LangGraph Cloud requires that the `CompiledGraph` object be assigned to a variable at the top-level of a Python module.
+
+Example file directory:
+
+```bash
+my-app/
+├── my_agent
+│   ├── __init__.py
+│   └── agent.py # code for your graph
+|-- .env
+└── pyproject.toml
+```
+
+## Create LangGraph API Config
+
+Create a [LangGraph API configuration file](../reference/cli.md#configuration-file) called `langgraph.json`. See the [LangGraph CLI reference](../reference/cli.md#configuration-file) for detailed explanations of each key in the JSON object of the configuration file.
+
+Example `langgraph.json` file:
+
+```json
+{
+  "dependencies": ["."],
+  "graphs": {
+    "my_fantastic_agent": "./my_agent/agent.py:agent"
+  },
+  "env": "./.env"
+}
+```
+
+Note that the variable name of the `CompiledGraph` appears at the end of the value of each subkey in the top-level `graphs` key (i.e. `:<variable_name>`).
+
+!!! warning "Configuration Location"
+    The LangGraph API configuration file must be placed in a directory that is at the same level or higher than the Python files that contain compiled graphs and associated dependencies.
+
+Example file directory:
+
+```bash
+my-app/
+├── my_agent
+│   ├── __init__.py
+│   └── agent.py # code for your graph
+│-- .env
+│-- langgraph.json      # configuration file for LangGraph
+└── pyproject.toml
+```
+
+## Upload to GitHub
+
+To deploy the LangGraph application to LangGraph Cloud, the code must be uploaded to a GitHub repository.
+
+## Next
+
+After you setup your repo, it's time to [deploy your app](./cloud.md).

docs/docs/cloud/deployment/test_locally.md

@@ -0,0 +1,99 @@
+# How to test a LangGraph app locally
+
+This guide assumes you have a LangGraph app correctly set up with a proper configuration file and a corresponding compiled graph, and that you have a proper LangChain API key.
+
+Testing locally ensures that there are no errors or conflicts with Python dependencies and confirms that the configuration file is specified correctly.
+
+## Setup
+
+Install the proper packages:
+
+```shell
+pip install langgraph-cli
+```
+
+Ensure you have an API key, which you can create from the LangSmith UI (Settings > API Keys). This is required to authenticate that you have LangGraph Cloud access. After you have saved the key to a safe place, place the following line in your `.env` file:
+
+```python
+LANGCHAIN_API_KEY = *********
+```
+
+## Start the API server
+
+Once you have downloaded the CLI, you can run the following command to start the API server for local testing:
+
+```shell
+langgraph up
+```
+
+This will start up the LangGraph API server locally. If this runs successfully, you should see something like:
+
+```shell
+Ready!
+- API: http://localhost:8123
+2024-06-26 19:20:41,056:INFO:uvicorn.access 127.0.0.1:44138 - "GET /ok HTTP/1.1" 200
+```
+
+### Interact with the server
+
+We can now interact with the API server using the LangGraph SDK. First, we need to start our client, select our assistant (in this case a graph we called "agent", make sure to select the proper assistant you wish to test).
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    # only pass the url argument to get_client() if you changed the default port when calling langgraph up
+    client = get_client()
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    // only set the apiUrl if you changed the default port when calling langgraph up
+    const client = new Client();
+    const assistantId = "agent"
+    const thread = await client.threads.create();
+    ```
+
+Now we can invoke our graph to ensure it is working. Make sure to change the input to match the proper schema for your graph. 
+
+=== "Python"
+
+    ```python
+    input = {"messages": [{"role": "human", "content": "what's the weather in sf"}]}
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id,
+        input=input,
+        stream_mode="updates",
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+=== "Javascript"
+
+    ```js
+    const input = { "messages": [{ "role": "human", "content": "what's the weather in sf"}] }
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: input,
+        streamMode: "updates",
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(`Receiving new event of type: ${chunk.event}...`);
+      console.log(chunk.data);
+      console.log("\n\n");
+    }
+    ```
+
+If your graph works correctly, you should see your graph output displayed in the console. Of course, there are many more ways you might need to test your graph, for a full list of commands you can send with the SDK, see the [Python](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/) and [JS/TS](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/) references.

docs/docs/cloud/how-tos/enqueue_concurrent.md

@@ -0,0 +1,183 @@
+## Enqueue
+
+This guide assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide](../concepts/api.md#double-texting).
+
+The guide covers the `enqueue` option for double texting, which adds the interruptions to a queue and executes them in the order they are received by the client. Below is a quick example of using the `enqueue` option.
+
+
+First, we will define a quick helper function for printing out JS model outputs (you can skip this if using Python):
+
+```js
+function prettyPrint(m) {
+  const padded = " " + m['type'] + " ";
+  const sepLen = Math.floor((80 - padded.length) / 2);
+  const sep = "=".repeat(sepLen);
+  const secondSep = sep + (padded.length % 2 ? "=" : "");
+  
+  console.log(`${sep}${padded}${secondSep}`);
+  console.log("\n\n");
+  console.log(m.content);
+}
+```
+
+Then, let's import our required packages and instantiate our client, assistant, and thread.
+
+=== "Python"
+
+    ```python
+    import asyncio
+
+    import httpx
+    from langchain_core.messages import convert_to_messages
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+    
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+Now let's start two runs, with the second interrupting the first one with a multitask strategy of "enqueue":
+
+=== "Python"
+
+    ```python
+    first_run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in sf?"}]},
+    )
+    second_run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in nyc?"}]},
+        multitask_strategy="enqueue",
+    )
+    ```
+
+=== "Javascript"
+
+    ```js
+    const firstRun = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      input={"messages": [{"role": "human", "content": "what's the weather in sf?"}]},
+    )
+
+    const secondRun = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      input={"messages": [{"role": "human", "content": "what's the weather in nyc?"}]},
+      multitask_strategy="enqueue",
+    )
+    ```
+
+Verify that the thread has data from both runs:
+
+=== "Python"
+
+    ```python
+    # wait until the second run completes
+    await client.runs.join(thread["thread_id"], second_run["run_id"])
+
+    state = await client.threads.get_state(thread["thread_id"])
+
+    for m in convert_to_messages(state["values"]["messages"]):
+        m.pretty_print()
+    ```
+
+=== "Javascript"
+
+    ```js
+    await client.runs.join(thread["thread_id"], secondRun["run_id"]);
+
+    const state = await client.threads.getState(thread["thread_id"]);
+
+    for (const m of state["values"]["messages"]) {
+      prettyPrint(m);
+    }
+    ```
+
+Output:
+
+    ================================ Human Message =================================
+    
+    what's the weather in sf?
+    ================================== Ai Message ==================================
+    
+    [{'id': 'toolu_01Dez1sJre4oA2Y7NsKJV6VT', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01Dez1sJre4oA2Y7NsKJV6VT)
+     Call ID: toolu_01Dez1sJre4oA2Y7NsKJV6VT
+      Args:
+        query: weather in san francisco
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.accuweather.com/en/us/san-francisco/94103/weather-forecast/347629", "content": "Get the current and future weather conditions for San Francisco, CA, including temperature, precipitation, wind, air quality and more. See the hourly and 10-day outlook, radar maps, alerts and allergy information."}]
+    ================================== Ai Message ==================================
+    
+    According to AccuWeather, the current weather conditions in San Francisco are:
+    
+    Temperature: 57°F (14°C)
+    Conditions: Mostly Sunny
+    Wind: WSW 10 mph
+    Humidity: 72%
+    
+    The forecast for the next few days shows partly sunny skies with highs in the upper 50s to mid 60s F (14-18°C) and lows in the upper 40s to low 50s F (9-11°C). Typical mild, dry weather for San Francisco this time of year.
+    
+    Some key details from the AccuWeather forecast:
+    
+    Today: Mostly sunny, high of 62°F (17°C)
+    Tonight: Partly cloudy, low of 49°F (9°C) 
+    Tomorrow: Partly sunny, high of 59°F (15°C)
+    Saturday: Mostly sunny, high of 64°F (18°C)
+    Sunday: Partly sunny, high of 61°F (16°C)
+    
+    So in summary, expect seasonable spring weather in San Francisco over the next several days, with a mix of sun and clouds and temperatures ranging from the upper 40s at night to the low 60s during the days. Typical dry conditions with no rain in the forecast.
+    ================================ Human Message =================================
+    
+    what's the weather in nyc?
+    ================================== Ai Message ==================================
+    
+    [{'text': 'Here are the current weather conditions and forecast for New York City:', 'type': 'text'}, {'id': 'toolu_01FFft5Sx9oS6AdVJuRWWcGp', 'input': {'query': 'weather in new york city'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01FFft5Sx9oS6AdVJuRWWcGp)
+     Call ID: toolu_01FFft5Sx9oS6AdVJuRWWcGp
+      Args:
+        query: weather in new york city
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.weatherapi.com/", "content": "{'location': {'name': 'New York', 'region': 'New York', 'country': 'United States of America', 'lat': 40.71, 'lon': -74.01, 'tz_id': 'America/New_York', 'localtime_epoch': 1718734479, 'localtime': '2024-06-18 14:14'}, 'current': {'last_updated_epoch': 1718733600, 'last_updated': '2024-06-18 14:00', 'temp_c': 29.4, 'temp_f': 84.9, 'is_day': 1, 'condition': {'text': 'Sunny', 'icon': '//cdn.weatherapi.com/weather/64x64/day/113.png', 'code': 1000}, 'wind_mph': 2.2, 'wind_kph': 3.6, 'wind_degree': 158, 'wind_dir': 'SSE', 'pressure_mb': 1025.0, 'pressure_in': 30.26, 'precip_mm': 0.0, 'precip_in': 0.0, 'humidity': 63, 'cloud': 0, 'feelslike_c': 31.3, 'feelslike_f': 88.3, 'windchill_c': 28.3, 'windchill_f': 82.9, 'heatindex_c': 29.6, 'heatindex_f': 85.3, 'dewpoint_c': 18.4, 'dewpoint_f': 65.2, 'vis_km': 16.0, 'vis_miles': 9.0, 'uv': 7.0, 'gust_mph': 16.5, 'gust_kph': 26.5}}"}]
+    ================================== Ai Message ==================================
+    
+    According to the weather data from WeatherAPI:
+    
+    Current Conditions in New York City (as of 2:00 PM local time):
+    - Temperature: 85°F (29°C)
+    - Conditions: Sunny
+    - Wind: 2 mph (4 km/h) from the SSE
+    - Humidity: 63%
+    - Heat Index: 85°F (30°C)
+    
+    The forecast shows sunny and warm conditions persisting over the next few days:
+    
+    Today: Sunny, high of 85°F (29°C)
+    Tonight: Clear, low of 68°F (20°C)
+    Tomorrow: Sunny, high of 88°F (31°C) 
+    Thursday: Mostly sunny, high of 90°F (32°C)
+    Friday: Partly cloudy, high of 87°F (31°C)
+    
+    So New York City is experiencing beautiful sunny weather with seasonably warm temperatures in the mid-to-upper 80s Fahrenheit (around 30°C). Humidity is moderate in the 60% range. Overall, ideal late spring/early summer conditions for being outdoors in the city over the next several days.
+

docs/docs/cloud/how-tos/human_in_the_loop_breakpoint.md

@@ -0,0 +1,103 @@
+# How to Add Breakpoints
+
+When creating LangGraph agents, it is often nice to add a human-in-the-loop component.
+This can be helpful when giving them access to tools.
+Often in these situations you may want to manually approve an action before taking.
+
+This can be in several ways, but the primary supported way is to add an "interrupt" before a node is executed.
+This interrupts execution at that node.
+You can then resume from that spot to continue.  
+
+## Setup
+
+### Code for your graph
+
+In this how-to we use a simple ReAct style hosted graph (you can see the full code for defining it [here](../../how-tos/human_in_the_loop/breakpoints.ipynb)). The important thing is that there are two nodes (one named `agent` that calls the LLM, and one named `action` that calls the tool), and a routing function from `agent` that determines whether to call `action` next or just end the graph run (the `action` node always calls the `agent` node after execution).
+
+### SDK Initialization
+
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent"
+    const thread = await client.threads.create();
+    ```
+
+## Adding a breakpoint
+
+We now want to add a breakpoint in our graph run, which we will do before a tool is called.
+We can do this by adding `interrupt_before=["action"]`, which tells us to interrupt before calling the action node.
+We can do this either when compiling the graph or when kicking off a run.
+Here we will do it when kicking of a run, if you would like to to do it at compile time you need to edit the python file where your graph is defined and add the `interrupt_before` parameter when you call `.compile`.
+
+First let's access our hosted LangGraph instance through the SDK:
+
+And, now let's compile it with a breakpoint before the tool node:
+
+=== "Python"
+
+    ```python
+    input = {"messages": [{"role": "human", "content": "what's the weather in sf"}]}
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id,
+        input=input,
+        stream_mode="updates",
+        interrupt_before=["action"],
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+=== "Javascript"
+
+    ```js
+    const input = { "messages": [{ "role": "human", "content": "what's the weather in sf"}] }
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: input,
+        streamMode: "updates",
+        interruptBefore: ["action"],
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(`Receiving new event of type: ${chunk.event}...`);
+      console.log(chunk.data);
+      console.log("\n\n");
+    }
+    ```
+
+Output:
+
+    Receiving new event of type: metadata...
+    {'run_id': '3b77ef83-687a-4840-8858-0371f91a92c3'}
+    
+    
+    
+    Receiving new event of type: data...
+    {'agent': {'messages': [{'content': [{'id': 'toolu_01HwZqM1ptX6E15A5LAmyZTB', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-e5d17791-4d37-4ad2-815f-a0c4cba62585', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in san francisco'}, 'id': 'toolu_01HwZqM1ptX6E15A5LAmyZTB'}], 'invalid_tool_calls': []}]}}
+    
+    
+    
+    Receiving new event of type: end...
+    None
+    
+    
+    
+

docs/docs/cloud/how-tos/human_in_the_loop_edit_state.md

@@ -0,0 +1,182 @@
+# How to Edit State of a Deployed Graph
+
+When creating LangGraph agents, it is often nice to add a human-in-the-loop component. This can be helpful when giving them access to tools. Often in these situations you may want to edit the graph state before continuing (for example, to edit what tool is being called, or how it is being called).
+
+This can be in several ways, but the primary supported way is to add an "interrupt" before a node is executed. This interrupts execution at that node. You can then use update_state to update the state, and then resume from that spot to continue.
+
+## Setup
+
+We are not going to show the full code for the graph we are hosting, but you can see it [here](../../how-tos/human_in_the_loop/edit-graph-state.ipynb#build-the-agent) if you want to. Once this graph is hosted, we are ready to invoke it and wait for user input. 
+
+### SDK initialization
+
+First, we need to setup our client so that we can communicate with our hosted graph:
+
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+## Editing state
+
+### Initial invocation
+
+Now let's invoke our graph, making sure to interrupt before the `action` node.
+
+=== "Python"
+
+    ```python
+    input = { 'messages':[{ "role":"user", "content":"search for weather in SF" }] }
+
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id,
+        input=input,
+        stream_mode="updates",
+        interrupt_before=["action"],
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const input = {"messages": [{ "role": "human", "content": "search for weather in SF"}] }
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: input,
+        streamMode: "updates",
+        interruptBefore: ["action"],
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+
+Output:
+
+    {'agent': {'messages': [{'content': [{'text': "Certainly! I'll search for the current weather in San Francisco for you using the search function. Here's how I'll do that:", 'type': 'text'}, {'id': 'toolu_01KEJMBFozSiZoS4mAcPZeqQ', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-6dbb0167-f8f6-4e2a-ab68-229b2d1fbb64', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in San Francisco'}, 'id': 'toolu_01KEJMBFozSiZoS4mAcPZeqQ'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+
+### Edit the state
+
+Now, let's assume we actually meant to search for the weather in Sidi Frej (another city with the initials SF). We can edit the state to properly reflect that:
+
+
+=== "Python"
+
+    ```python
+    # First, lets get the current state
+    current_state = await client.threads.get_state(thread['thread_id'])
+
+    # Let's now get the last message in the state
+    # This is the one with the tool calls that we want to update
+    last_message = current_state['values']['messages'][-1]
+
+    # Let's now update the args for that tool call
+    last_message['tool_calls'][0]['args'] = {'query': 'current weather in Sidi Frej'}
+
+    # Let's now call `update_state` to pass in this message in the `messages` key
+    # This will get treated as any other update to the state
+    # It will get passed to the reducer function for the `messages` key
+    # That reducer function will use the ID of the message to update it
+    # It's important that it has the right ID! Otherwise it would get appended
+    # as a new message
+    await client.threads.update_state(thread['thread_id'], {"messages": last_message})
+    ```
+
+=== "Javascript"
+
+    ```js
+    // First, lets get the current state
+    const currentState = await client.threads.getState(thread['thread_id']);
+
+    // Let's now get the last message in the state
+    // This is the one with the tool calls that we want to update
+    let lastMessage = currentState['values']['messages'][-1];
+
+    // Let's now update the args for that tool call
+    lastMessage['tool_calls'][0]['args'] = {'query': 'current weather in Sidi Frej'};
+
+    // Let's now call `update_state` to pass in this message in the `messages` key
+    // This will get treated as any other update to the state
+    // It will get passed to the reducer function for the `messages` key
+    // That reducer function will use the ID of the message to update it
+    // It's important that it has the right ID! Otherwise it would get appended
+    // as a new message
+    await client.threads.updateState(thread['thread_id'], {values:{"messages": lastMessage}});
+    ```
+
+Output:
+
+    {'configurable': {'thread_id': '88d58d3f-4151-47a9-a8e0-e42fdd3527b8',
+      'thread_ts': '1ef3274b-a809-6913-8002-91536ce6554d'}}
+
+
+
+### Resume invocation
+
+Now we can resume our graph run but with the updated state:
+
+
+=== "Python"
+
+    ```python
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id,
+        input=None,
+        stream_mode="updates",
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+=== "Javascript"
+
+    ```js
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: null,
+        streamMode: "updates",
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+
+Output:
+
+    {'action': {'messages': [{'content': '["I looked up: current weather in Sidi Frej. Result: It\'s sunny in San Francisco, but you better look out if you\'re a Gemini 😈."]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '1161b8d1-bee4-4188-9be8-698aecb69f10', 'tool_call_id': 'toolu_01KEJMBFozSiZoS4mAcPZeqQ'}]}}
+    {'agent': {'messages': [{'content': [{'text': 'I apologize for the confusion in my search query. It seems the search function interpreted "SF" as "Sidi Frej" instead of "San Francisco" as we intended. Let me search again with the full city name to get the correct information:', 'type': 'text'}, {'id': 'toolu_0111rrwgfAcmurHZn55qjqTR', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-b8c25779-cfb4-46fc-a421-48553551242f', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in San Francisco'}, 'id': 'toolu_0111rrwgfAcmurHZn55qjqTR'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+    {'action': {'messages': [{'content': '["I looked up: current weather in San Francisco. Result: It\'s sunny in San Francisco, but you better look out if you\'re a Gemini 😈."]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '6bc632ae-5ee6-4d01-9532-79c524a2d443', 'tool_call_id': 'toolu_0111rrwgfAcmurHZn55qjqTR'}]}}
+    {'agent': {'messages': [{'content': "Now, based on the search results, I can provide you with information about the current weather in San Francisco:\n\nThe weather in San Francisco is currently sunny. \n\nIt's worth noting that the search result included an unusual comment about Gemini, which doesn't seem directly related to the weather. This might be due to the search engine including some astrological information or a joke in its results. However, for the purpose of weather information, we can focus on the fact that it's sunny in San Francisco right now.\n\nIs there anything else you'd like to know about the weather in San Francisco or any other location?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-227a042b-dd97-476e-af32-76a3703af5d8', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+
+As you can see it now looks up the current weather in Sidi Frej (although our dummy search node still returns results for SF because we don't actually do a search in this example, we just return the same "It's sunny in San Francisco ..." result every time).

docs/docs/cloud/how-tos/human_in_the_loop_time_travel.md

@@ -0,0 +1,226 @@
+# How to Replay and Branch from Prior States
+
+With LangGraph Cloud you have the ability to return to any of your prior states and either re-run the graph to reproduce issues noticed during testing, or branch out in a different way from what was originally done in the prior states. In this guide we will show a quick example of how to rerun past states and how to branch off from previous states as well.
+
+## Setup
+
+We are not going to show the full code for the graph we are hosting, but you can see it [here](../../how-tos/human_in_the_loop/time-travel.ipynb#build-the-agent) if you want to. Once this graph is hosted, we are ready to invoke it and wait for user input. 
+
+### SDK initialization
+
+First, we need to setup our client so that we can communicate with our hosted graph:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = agent;
+    const thread = await client.threads.create();
+    ```
+
+## Replay a state
+
+### Initial invocation
+
+Before replaying a state - we need to create states to replay from! In order to do this, let's invoke our graph with a simple message:
+
+=== "Python"
+
+    ```python
+    input = { 'messages':[{ "role":"user", "content":"Please search the weather in SF" }] }
+
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id, # graph_id
+        input=input,
+        stream_mode="updates",
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const input = {"messages": [{ "role": "human", "content": "Please search the weather in SF"}] }
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: input,
+        streamMode: "updates",
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+    
+Output:
+
+    {'agent': {'messages': [{'content': [{'text': "Certainly! I'll use the search function to look up the current weather in San Francisco for you. Let me do that now.", 'type': 'text'}, {'id': 'toolu_011vroKUtWU7SBdrngpgpFMn', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ee639877-d97d-40f8-96dc-d0d1ae22d203', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in San Francisco'}, 'id': 'toolu_011vroKUtWU7SBdrngpgpFMn'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+    {'action': {'messages': [{'content': '["I looked up: current weather in San Francisco. Result: It\'s sunny in San Francisco, but you better look out if you\'re a Gemini 😈."]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '7bad0e72-5ebe-4b08-9b8a-b99b0fe22fb7', 'tool_call_id': 'toolu_011vroKUtWU7SBdrngpgpFMn'}]}}
+    {'agent': {'messages': [{'content': "Based on the search results, I can provide you with information about the current weather in San Francisco:\n\nThe weather in San Francisco is currently sunny. This is great news for outdoor activities and enjoying the city's beautiful sights.\n\nIt's worth noting that the search result included an unusual comment about Geminis, which isn't typically part of a weather report. This might be due to the search engine including some astrological information or a joke in its results. However, for the purpose of answering your question about the weather, we can focus on the fact that it's sunny in San Francisco.\n\nIf you need any more specific information about the weather in San Francisco, such as temperature, wind speed, or forecast for the coming days, please let me know, and I'd be happy to search for that information for you.", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-dbac539a-33c8-4f0c-9e20-91f318371e7c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+
+Now let's get our list of states, and invoke from the third state (right before the tool get called):
+
+
+=== "Python"
+
+    ```python
+    states = await client.threads.get_history(thread['thread_id'])
+
+    # We can confirm that this state is correct by checking the 'next' attribute and seeing that it is the tool call node
+    state_to_replay = states[2]
+    print(state_to_replay['next'])
+    ```
+
+=== "Javascript"
+
+    ```js
+    const states = await client.threads.getHistory(thread['thread_id']);
+
+    // We can confirm that this state is correct by checking the 'next' attribute and seeing that it is the tool call node
+    const stateToReplay = states[2];
+    console.log(stateToReplay['next']);
+    ```
+
+Output:
+
+    ['action']
+
+
+
+To rerun from a state, we need to pass in the `checkpoint_id` into the config of the run like follows:
+
+=== "Python"
+
+    ```python
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id, # graph_id
+        input=None,
+        stream_mode="updates",
+        config={"configurable": {"thread_ts": state_to_replay['checkpoint_id']}}
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: null,
+        streamMode: "updates",
+        config: {"configurable": {"thread_ts": stateToReplay['checkpoint_id']}},
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+
+Output:
+
+    {'action': {'messages': [{'content': '["I looked up: current weather in San Francisco. Result: It\'s sunny in San Francisco, but you better look out if you\'re a Gemini 😈."]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': 'eba650e5-400e-4938-8508-f878dcbcc532', 'tool_call_id': 'toolu_011vroKUtWU7SBdrngpgpFMn'}]}}
+    {'agent': {'messages': [{'content': "Based on the search results, I can provide you with information about the current weather in San Francisco:\n\nThe weather in San Francisco is currently sunny. This is great news if you're planning any outdoor activities or simply want to enjoy a pleasant day in the city.\n\nIt's worth noting that the search result included an unusual comment about Geminis, which doesn't seem directly related to the weather. This appears to be a playful or humorous addition to the weather report, possibly from the source where this information was obtained.\n\nIs there anything else you'd like to know about the weather in San Francisco or any other information you need?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-bc6dca3f-a1e2-4f59-a69b-fe0515a348bb', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+
+As we can see, the graph restarted from the tool node with the same input as our original graph run.
+
+## Branch off from previous state
+
+Using LangGraph's checkpointing, you can do more than just replay past states. You can branch off previous locations to let the agent explore alternate trajectories or to let a user "version control" changes in a workflow.
+
+Let's show how to do this to edit the state at a particular point in time. Let's update the state to change the input to the tool
+
+=== "Python"
+
+    ```python
+    # Let's now get the last message in the state
+    # This is the one with the tool calls that we want to update
+    last_message = state_to_replay['values']['messages'][-1]
+
+    # Let's now update the args for that tool call
+    last_message['tool_calls'][0]['args'] = {'query': 'current weather in SF'}
+
+    new_state = await client.threads.update_state(thread['thread_id'],{"messages":[last_message]},checkpoint_id=state_to_replay['checkpoint_id'])
+    ```
+
+=== "Javascript"
+
+    ```js
+    // Let's now get the last message in the state
+    // This is the one with the tool calls that we want to update
+    let lastMessage = stateToReplay['values']['messages'][-1];
+
+    // Let's now update the args for that tool call
+    lastMessage['tool_calls'][0]['args'] = {'query': 'current weather in SF'};
+
+    const newState = await client.threads.updateState(thread['thread_id'],{values:{"messages":[lastMessage]},checkpointId:stateToReplay['checkpoint_id']});
+    ```
+
+Now we can rerun our graph with this new config, starting from the `new_state`, which is a branch of our `state_to_replay`:
+
+=== "Python"
+
+    ```python
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant["assistant_id"], # graph_id
+        input=None,
+        stream_mode="updates",
+        config={"configurable": {"thread_ts": new_state['configurable']['thread_ts']}}
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistant["assistant_id"],
+      {
+        input: null,
+        streamMode: "updates",
+        config: {"configurable": {"thread_ts": newState['configurable']['thread_ts']}},
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+
+Output:
+
+
+    {'action': {'messages': [{'content': '["I looked up: current weather in SF. Result: It\'s sunny in San Francisco, but you better look out if you\'re a Gemini 😈."]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '2baf9941-4fda-4081-9f87-d76795d289f1', 'tool_call_id': 'toolu_011vroKUtWU7SBdrngpgpFMn'}]}}
+    {'agent': {'messages': [{'content': "Based on the search results, I can provide you with information about the current weather in San Francisco (SF):\n\nThe weather in San Francisco is currently sunny. This means it's a clear day with plenty of sunshine. \n\nIt's worth noting that the specific temperature wasn't provided in the search result, but sunny weather in San Francisco typically means comfortable temperatures. San Francisco is known for its mild climate, so even on sunny days, it's often not too hot.\n\nThe search result also included a playful reference to astrological signs, mentioning Gemini. However, this is likely just a joke or part of the search engine's presentation and not related to the actual weather conditions.\n\nIs there any specific information about the weather in San Francisco you'd like to know more about? I'd be happy to perform another search if you need details on temperature, wind conditions, or the forecast for the coming days.", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-a83de52d-ed18-4402-9384-75c462485743', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+
+As we can see, the search query changed from San Francisco to SF, just as we had hoped!

docs/docs/cloud/how-tos/human_in_the_loop_user_input.md

@@ -0,0 +1,166 @@
+# How to Wait for User Input
+
+One of the main human-in-the-loop interaction patterns is waiting for human input. A key use case involves asking the user clarifying questions. One way to accomplish this is simply go to the `END` node and exit the graph. Then, any user response comes back in as fresh invocation of the graph. This is basically just creating a chatbot architecture.
+
+The issue with this is it is tough to resume back in a particular point in the graph. Often times the agent is halfway through some process, and just needs a bit of a user input. Although it is possible to design your graph in such a way where you have a `conditional_entry_point` to route user messages back to the right place, that is not super scalable (as it essentially involves having a routing function that can end up almost anywhere).
+
+A separate way to do this is to have a node explicitly for getting user input. This is easy to implement in a notebook setting - you just put an `input()` call in the node. But that isn't exactly production ready.
+
+Luckily, LangGraph makes it possible to do similar things in a production way. The basic idea is:
+
+- Set up a node that represents human input. This can have specific incoming/outgoing edges (as you desire). There shouldn't actually be any logic inside this node.
+- Add a breakpoint before the node. This will stop the graph before this node executes (which is good, because there's no real logic in it anyways)
+- Use `.update_state` to update the state of the graph. Pass in whatever human response you get. The key here is to use the `as_node` parameter to apply this update **as if you were that node**. This will have the effect of making it so that when you resume execution next it resumes as if that node just acted, and not from the beginning.
+
+## Setup
+
+We are not going to show the full code for the graph we are hosting, but you can see it [here](../../how-tos/human_in_the_loop/wait-user-input.ipynb#build-the-agent) if you want to. Once this graph is hosted, we are ready to invoke it and wait for user input. 
+
+### SDK initialization
+
+First, we need to setup our client so that we can communicate with our hosted graph:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+## Waiting for user input
+
+### Initial invocation
+
+Now, let's invoke our graph by interrupting before `ask_human` node:
+
+=== "Python"
+
+    ```python
+    input = { 'messages':[{ "role":"user", "content":"Use the search tool to ask the user where they are, then look up the weather there" }] }
+
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id,
+        input=input,
+        stream_mode="updates",
+        interrupt_before=["ask_human"],
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+=== "Javascript"
+
+    ```js
+    const input = { "messages":[{ "role":"human", "content": "Use the search tool to ask the user where they are, then look up the weather there"}] }
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: input,
+        streamMode: "updates",
+        interruptBefore: ["ask_human"],
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+    
+Output:
+
+    {'agent': {'messages': [{'content': [{'text': "Certainly! I'll use the AskHuman function to ask the user about their location, and then I'll use the search function to look up the weather for that location. Let's start by asking the user where they are.", 'type': 'text'}, {'id': 'toolu_01RFahzYPvnPWTb2USk2RdKR', 'input': {'question': 'Where are you currently located?'}, 'name': 'AskHuman', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-a8422215-71d3-4093-afb4-9db141c94ddb', 'example': False, 'tool_calls': [{'name': 'AskHuman', 'args': {'question': 'Where are you currently located?'}, 'id': 'toolu_01RFahzYPvnPWTb2USk2RdKR'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+
+### Adding user input to state
+
+We now want to update this thread with a response from the user. We then can kick off another run.
+
+Because we are treating this as a tool call, we will need to update the state as if it is a response from a tool call. In order to do this, we will need to check the state to get the ID of the tool call.
+
+
+=== "Python"
+
+    ```python
+    state = await client.threads.get_state(thread['thread_id'])
+    tool_call_id = state['values']['messages'][-1]['tool_calls'][0]['id']
+
+    # We now create the tool call with the id and the response we want
+    tool_message = [{"tool_call_id": tool_call_id, "type": "tool", "content": "san francisco"}]
+
+    await client.threads.update_state(thread['thread_id'], {"messages": tool_message}, as_node="ask_human")
+    ```
+
+=== "Javascript"
+
+    ```js
+    const state = await client.threads.getState(thread['thread_id']);
+    const toolCallId = state['values']['messages'][-1]['tool_calls'][0]['id'];
+
+    # We now create the tool call with the id and the response we want
+    const toolMessage = [{"tool_call_id": toolCallId, "type": "tool", "content": "san francisco"}];
+
+    await client.threads.updateState(thread['thread_id'], {values: {"messages": toolMessage}, asNode:"ask_human"})
+    ```
+
+Output:
+
+    {'configurable': {'thread_id': '10d0ee61-db47-48fc-a58c-109a1e68cd73',
+      'thread_ts': '1ef32729-3cc3-6647-8002-14dcb621b46e'}}
+
+
+
+### Invoking after receiving human input
+
+We can now tell the agent to continue. We can just pass in None as the input to the graph, since no additional input is needed:
+
+=== "Python"
+
+    ```python
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id, # graph_id
+        input=None,
+        stream_mode="updates",
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+=== "Javascript"
+
+    ```js
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: null,
+        streamMode: "updates",
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+
+Output:
+
+    {'agent': {'messages': [{'content': [{'text': "Thank you for letting me know that you're in San Francisco. Now, I'll use the search function to look up the weather in San Francisco.", 'type': 'text'}, {'id': 'toolu_01K57ofmgG2wyJ8tYJjbq5k7', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-241baed7-db5e-44ce-ac3c-56431705c22b', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in San Francisco'}, 'id': 'toolu_01K57ofmgG2wyJ8tYJjbq5k7'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+    {'action': {'messages': [{'content': '["I looked up: current weather in San Francisco. Result: It\'s sunny in San Francisco, but you better look out if you\'re a Gemini 😈."]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '8b699b95-8546-4557-8e66-14ea71a15ed8', 'tool_call_id': 'toolu_01K57ofmgG2wyJ8tYJjbq5k7'}]}}
+    {'agent': {'messages': [{'content': "Based on the search results, I can provide you with information about the current weather in San Francisco:\n\nThe weather in San Francisco is currently sunny. It's a beautiful day in the city! \n\nHowever, I should note that the search result included an unusual comment about Gemini zodiac signs. This appears to be either a joke or potentially irrelevant information added by the search engine. For accurate and detailed weather information, you might want to check a reliable weather service or app for San Francisco.\n\nIs there anything else you'd like to know about the weather or San Francisco?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-b4d7309f-f849-46aa-b6ef-475bcabd2be9', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+

docs/docs/cloud/how-tos/index.md

@@ -0,0 +1,74 @@
+---
+hide:
+  - toc
+---
+
+# How-to Guides
+
+Welcome to the LangGraph Cloud how-to guides! These guides provide practical, step-by-step instructions for accomplishing key tasks in LangGraph Cloud.
+
+## Deployment
+
+LangGraph Cloud gives you best in class observability, testing, and hosting services. Read more about them in these how to guides:
+
+- [How to set up app for deployment (requirements.txt)](../deployment/setup.md)
+- [How to set up app for deployment (pyproject.toml)](../deployment/setup_pyproject.md)
+- [How to test locally](../deployment/test_locally.md)
+- [How to deploy to LangGraph cloud](../deployment/cloud.md)
+- [How to self-host](../deployment/self_hosted.md)
+
+
+## Streaming
+
+Streaming the results of your LLM application is vital for ensuring a good user experience, especially when your graph may call multiple models and take a long time to fully complete a run. Read about how to stream values from your graph in these how to guides:
+
+- [How to stream values](./stream_values.md)
+- [How to stream updates](./stream_updates.md)
+- [How to stream messages](./stream_messages.md)
+- [How to stream events](./stream_events.md)
+- [How to stream in debug mode](./stream_debug.md)
+- [How to stream multiple modes](./stream_multiple.md)
+
+## Double-texting
+
+Graph execution can take a while, and sometimes users may change their mind about the input they wanted to send before their original input has finished running. For example, a user might notice a typo in their original request and will edit the prompt and resend it. Deciding what to do in these cases is important for ensuring a smooth user experience and preventing your graphs from behaving in unexpected ways. The following how-to guides provide information on the various options LangGraph Cloud gives you for dealing with double-texting:
+
+- [How to use the interrupt option](./interrupt_concurrent.md)
+- [How to use the rollback option](./rollback_concurrent.md)
+- [How to use the reject option](./reject_concurrent.md)
+- [How to use the enqueue option](./enqueue_concurrent.md)
+
+## Human-in-the-loop
+
+When creating complex graphs, leaving every decision up to the LLM can be dangerous, especially when the decisions involve invoking certain tools or accessing specific documents. To remedy this, LangGraph allows you to insert human-in-the-loop behavior to ensure your graph does not have undesired outcomes. Read more about the different ways you can add human-in-the-loop capabilities to your LangGraph Cloud projects in these how-to guides:
+
+- [How to add a breakpoint](./human_in_the_loop_breakpoint.md)
+- [How to wait for user input](./human_in_the_loop_user_input.md)
+- [How to edit graph state](./human_in_the_loop_edit_state.md)
+- [How to replay and branch from prior states](./human_in_the_loop_time_travel.md)
+
+## LangGraph Studio
+
+LangGraph Studio is a built-in UI for visualizing, testing, and debugging your agents.
+
+- [How to enter LangGraph Studio](./test_deployment.md)
+- [How to enter LangGraph Studio for local deployment](./test_local_deployment.md)
+- [How to test your graph in LangGraph Studio](./invoke_studio.md)
+- [Interact with threads in LangGraph Studio](./threads_studio.md)
+
+## Different Types of Runs:
+
+LangGraph Cloud supports multiple types of runs besides streaming runs.
+
+- [How to run an agent in the background](cloud_examples/background_run.ipynb)
+- [How to run multiple agents in the same thread](cloud_examples/same-thread.ipynb)
+- [How to create cron jobs](cloud_examples/cron_jobs.ipynb)
+- [How to create stateless runs](cloud_examples/stateless_runs.ipynb)
+
+## Other 
+
+Other guides that may prove helpful!
+
+- [How to configure agents](cloud_examples/configuration_cloud.ipynb)
+- [How to convert LangGraph calls to LangGraph cloud calls](cloud_examples/langgraph_to_langgraph_cloud.ipynb)
+- [How to integrate webhooks](cloud_examples/webhooks.ipynb)

docs/docs/cloud/how-tos/interrupt_concurrent.md

@@ -0,0 +1,176 @@
+## Interrupt
+
+This guide assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide](../concepts/api.md#double-texting).
+
+The guide covers the `interrupt` option for double texting, which interrupts the prior run of the graph and starts a new one with the double-text. This option does not delete the first run, but rather keeps it in the database but sets its status to `interrupted`. Below is a quick example of using the `interrupt` option.
+
+First, we will define a quick helper function for printing out JS model outputs (you can skip this if using Python):
+
+```js
+function prettyPrint(m) {
+  const padded = " " + m['type'] + " ";
+  const sepLen = Math.floor((80 - padded.length) / 2);
+  const sep = "=".repeat(sepLen);
+  const secondSep = sep + (padded.length % 2 ? "=" : "");
+  
+  console.log(`${sep}${padded}${secondSep}`);
+  console.log("\n\n");
+  console.log(m.content);
+}
+```
+
+Now, let's import our required packages and instantiate our client, assistant, and thread.
+
+=== "Python"
+
+    ```python
+    import asyncio
+
+    from langchain_core.messages import convert_to_messages
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+Now we can start our two runs and join the second on euntil it has completed:
+
+=== "Python"
+
+    ```python
+    # the first run will be interrupted
+    interrupted_run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in sf?"}]},
+    )
+    await asyncio.sleep(2)
+    run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in nyc?"}]},
+        multitask_strategychrom="interrupt",
+    )
+    # wait until the second run completes
+    await client.runs.join(thread["thread_id"], run["run_id"])
+    ```
+
+=== "Javascript"
+
+    ```js
+    // the first run will be interrupted
+    let interruptedRun = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      { input: { messages: [{ role: "human", content: "what's the weather in sf?" }] } }
+    );
+    await new Promise(resolve => setTimeout(resolve, 2000)); 
+
+    let run = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      { 
+        input: { messages: [{ role: "human", content: "what's the weather in nyc?" }] },
+        multitaskStrategy: "interrupt" 
+      }
+    );
+
+    // wait until the second run completes
+    await client.runs.join(thread["thread_id"], run["run_id"]);
+    ```
+
+We can see that the thread has partial data from the first run + data from the second run
+
+
+=== "Python"
+
+    ```python
+    state = await client.threads.get_state(thread["thread_id"])
+
+    for m in convert_to_messages(state["values"]["messages"]):
+        m.pretty_print()
+    ```
+
+=== "Javascript"
+
+    ```js
+    const state = await client.threads.getState(thread["thread_id"]);
+
+    for (const m of state['values']['messages']) {
+      prettyPrint(m);
+    }
+    ```
+
+Output:
+
+    ================================ Human Message =================================
+    
+    what's the weather in sf?
+    ================================== Ai Message ==================================
+    
+    [{'id': 'toolu_01MjNtVJwEcpujRGrf3x6Pih', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01MjNtVJwEcpujRGrf3x6Pih)
+     Call ID: toolu_01MjNtVJwEcpujRGrf3x6Pih
+      Args:
+        query: weather in san francisco
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.wunderground.com/hourly/us/ca/san-francisco/KCASANFR2002/date/2024-6-18", "content": "High 64F. Winds W at 10 to 20 mph. A few clouds from time to time. Low 49F. Winds W at 10 to 20 mph. Temp. San Francisco Weather Forecasts. Weather Underground provides local & long-range weather ..."}]
+    ================================ Human Message =================================
+    
+    what's the weather in nyc?
+    ================================== Ai Message ==================================
+    
+    [{'id': 'toolu_01KtE1m1ifPLQAx4fQLyZL9Q', 'input': {'query': 'weather in new york city'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01KtE1m1ifPLQAx4fQLyZL9Q)
+     Call ID: toolu_01KtE1m1ifPLQAx4fQLyZL9Q
+      Args:
+        query: weather in new york city
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.accuweather.com/en/us/new-york/10021/june-weather/349727", "content": "Get the monthly weather forecast for New York, NY, including daily high/low, historical averages, to help you plan ahead."}]
+    ================================== Ai Message ==================================
+    
+    The search results provide weather forecasts and information for New York City. Based on the top result from AccuWeather, here are some key details about the weather in NYC:
+    
+    - This is a monthly weather forecast for New York City for the month of June.
+    - It includes daily high and low temperatures to help plan ahead.
+    - Historical averages for June in NYC are also provided as a reference point.
+    - More detailed daily or hourly forecasts with precipitation chances, humidity, wind, etc. can be found by visiting the AccuWeather page.
+    
+    So in summary, the search provides a convenient overview of the expected weather conditions in New York City over the next month to give you an idea of what to prepare for if traveling or making plans there. Let me know if you need any other details!
+
+
+Verify that the original, interrupted run was interrupted
+
+=== "Python"
+
+    ```python
+    print((await client.runs.get(thread["thread_id"], interrupted_run["run_id"]))["status"])
+    ```
+
+=== "Javascript"
+
+    ```js
+    console.log((await client.runs.get(thread['thread_id'], interruptedRun["run_id"]))["status"])
+    ```
+
+Output:
+
+    'interrupted'
+

docs/docs/cloud/how-tos/invoke_studio.md

@@ -0,0 +1,15 @@
+# Invoke Assistant
+
+The LangGraph Studio lets you test different configurations and inputs to your graph. The UI allows you to see exactly how your 
+
+1. The LangGraph Studio UI displays a visualization of the selected assistant.
+    1. In the top-right dropdown menu of the left-hand pane, select an assistant.
+    1. In the bottom of the left-hand pane, edit the `Input` and `Configure` the assistant.
+    1. Select `Submit` to invoke the selected assistant.
+1. View output of the invocation in the right-hand pane.
+
+The following video shows these exact steps being carried out:
+
+<video controls allowfullscreen="true" poster="../img/studio_input_poster.png">
+    <source src="../img/studio_input.mp4" type="video/mp4">
+</video>

docs/docs/cloud/how-tos/reject_concurrent.md

@@ -0,0 +1,155 @@
+## Reject
+
+This guide assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide][double-texting].
+
+The guide covers the `reject` option for double texting, which rejects the new run of the graph by throwing an error and continues with the original run until completion. Below is a quick example of using the `reject` option.
+
+First, we will define a quick helper function for printing out JS model outputs (you can skip this if using Python):
+
+```js
+function prettyPrint(m) {
+  const padded = " " + m['type'] + " ";
+  const sepLen = Math.floor((80 - padded.length) / 2);
+  const sep = "=".repeat(sepLen);
+  const secondSep = sep + (padded.length % 2 ? "=" : "");
+  
+  console.log(`${sep}${padded}${secondSep}`);
+  console.log("\n\n");
+  console.log(m.content);
+}
+```
+
+Now, let's import our required packages and instantiate our client, assistant, and thread.
+
+=== "Python"
+
+    ```python
+    import httpx
+    from langchain_core.messages import convert_to_messages
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+Now we can run a thread and try to run a second one with the "reject" option, which should fail since we have already started a run:
+
+
+=== "Python"
+
+    ```python
+    run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in sf?"}]},
+    )
+    try:
+        await client.runs.create(
+            thread["thread_id"],
+            assistant_id,
+            input={
+                "messages": [{"role": "human", "content": "what's the weather in nyc?"}]
+            },
+            multitask_strategy="reject",
+        )
+    except httpx.HTTPStatusError as e:
+        print("Failed to start concurrent run", e)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const run = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      input={"messages": [{"role": "human", "content": "what's the weather in sf?"}]},
+    );
+    
+    try {
+      await client.runs.create(
+        thread["thread_id"],
+        assistantId,
+        { 
+          input: {"messages": [{"role": "human", "content": "what's the weather in nyc?"}]},
+          multitask_strategy:"reject"
+        },
+      );
+    } catch (e) {
+      console.error("Failed to start concurrent run", e);
+    }
+    ```
+
+    Failed to start concurrent run Client error '409 Conflict' for url 'http://localhost:8123/threads/f9e7088b-8028-4e5c-88d2-9cc9a2870e50/runs'
+    For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/409
+
+
+We can verify that the original thread finished executing:
+
+=== "Python"
+
+    ```python
+    # wait until the original run completes
+    await client.runs.join(thread["thread_id"], run["run_id"])
+
+    state = await client.threads.get_state(thread["thread_id"])
+
+    for m in convert_to_messages(state["values"]["messages"]):
+        m.pretty_print()
+    ```
+
+=== "Javascript"
+
+    ```js
+    await client.runs.join(thread["thread_id"], run["run_id"]);
+
+    const state = await client.threads.getState(thread["thread_id"]);
+
+    for (const m of state["values"]["messages"]) {
+      prettyPrint(m);
+    }
+    ```
+
+Output:
+
+    ================================ Human Message =================================
+    
+    what's the weather in sf?
+    ================================== Ai Message ==================================
+    
+    [{'id': 'toolu_01CyewEifV2Kmi7EFKHbMDr1', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01CyewEifV2Kmi7EFKHbMDr1)
+     Call ID: toolu_01CyewEifV2Kmi7EFKHbMDr1
+      Args:
+        query: weather in san francisco
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.accuweather.com/en/us/san-francisco/94103/june-weather/347629", "content": "Get the monthly weather forecast for San Francisco, CA, including daily high/low, historical averages, to help you plan ahead."}]
+    ================================== Ai Message ==================================
+    
+    According to the search results from Tavily, the current weather in San Francisco is:
+    
+    The average high temperature in San Francisco in June is around 65°F (18°C), with average lows around 54°F (12°C). June tends to be one of the cooler and foggier months in San Francisco due to the marine layer of fog that often blankets the city during the summer months.
+    
+    Some key points about the typical June weather in San Francisco:
+    
+    - Mild temperatures with highs in the 60s F and lows in the 50s F
+    - Foggy mornings that often burn off to sunny afternoons
+    - Little to no rainfall, as June falls in the dry season
+    - Breezy conditions, with winds off the Pacific Ocean
+    - Layers are recommended for changing weather conditions
+    
+    So in summary, you can expect mild, foggy mornings giving way to sunny but cool afternoons in San Francisco this time of year. The marine layer keeps temperatures moderate compared to other parts of California in June.
+

docs/docs/cloud/how-tos/rollback_concurrent.md

@@ -0,0 +1,161 @@
+## Rollback
+
+This guide assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide][double-texting].
+
+The guide covers the `rollback` option for double texting, which interrupts the prior run of the graph and starts a new one with the double-text. This option is very similar to the `interrupt` option, but in this case the first run is completely deleted from the database and cannot be restarted. Below is a quick example of using the `rollback` option.
+
+First, we will define a quick helper function for printing out JS model outputs (you can skip this if using Python):
+
+```js
+function prettyPrint(m) {
+  const padded = " " + m['type'] + " ";
+  const sepLen = Math.floor((80 - padded.length) / 2);
+  const sep = "=".repeat(sepLen);
+  const secondSep = sep + (padded.length % 2 ? "=" : "");
+  
+  console.log(`${sep}${padded}${secondSep}`);
+  console.log("\n\n");
+  console.log(m.content);
+}
+```
+
+Now, let's import our required packages and instantiate our client, assistant, and thread.
+
+=== "Python"
+
+    ```python
+    import asyncio
+
+    import httpx
+    from langchain_core.messages import convert_to_messages
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+Now let's run a thread with the multitask parameter set to "rollback":
+
+=== "Python"
+
+    ```python
+    # the first run will be rolled back
+    rolled_back_run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in sf?"}]},
+    )
+    await asyncio.sleep(2)
+    run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in nyc?"}]},
+        multitask_strategy="rollback",
+    )
+    # wait until the second run completes
+    await client.runs.join(thread["thread_id"], run["run_id"])
+    ```
+
+=== "Javascript"
+
+    ```js
+    // the first run will be interrupted
+    let rolledBackRun = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      { input: { messages: [{ role: "human", content: "what's the weather in sf?" }] } }
+    );
+    await new Promise(resolve => setTimeout(resolve, 2000)); 
+
+    let run = await client.runs.create(
+      thread["thread_id"],
+      assistant_id,
+      { 
+        input: { messages: [{ role: "human", content: "what's the weather in nyc?" }] },
+        multitaskStrategy: "rollback" 
+      }
+    );
+
+    // wait until the second run completes
+    await client.runs.join(thread["thread_id"], run["run_id"]);
+    ```
+
+We can see that the thread has data only from the second run
+
+=== "Python"
+
+    ```python
+    state = await client.threads.get_state(thread["thread_id"])
+
+    for m in convert_to_messages(state["values"]["messages"]):
+        m.pretty_print()
+    ```
+
+=== "Javascript"
+
+    ```js
+    const state = await client.threads.getState(thread["thread_id"]);
+
+    for (const m of state['values']['messages']) {
+      prettyPrint(m);
+    }
+    ```
+
+Output:
+
+    ================================ Human Message =================================
+    
+    what's the weather in nyc?
+    ================================== Ai Message ==================================
+    
+    [{'id': 'toolu_01JzPqefao1gxwajHQ3Yh3JD', 'input': {'query': 'weather in nyc'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01JzPqefao1gxwajHQ3Yh3JD)
+     Call ID: toolu_01JzPqefao1gxwajHQ3Yh3JD
+      Args:
+        query: weather in nyc
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.weatherapi.com/", "content": "{'location': {'name': 'New York', 'region': 'New York', 'country': 'United States of America', 'lat': 40.71, 'lon': -74.01, 'tz_id': 'America/New_York', 'localtime_epoch': 1718734479, 'localtime': '2024-06-18 14:14'}, 'current': {'last_updated_epoch': 1718733600, 'last_updated': '2024-06-18 14:00', 'temp_c': 29.4, 'temp_f': 84.9, 'is_day': 1, 'condition': {'text': 'Sunny', 'icon': '//cdn.weatherapi.com/weather/64x64/day/113.png', 'code': 1000}, 'wind_mph': 2.2, 'wind_kph': 3.6, 'wind_degree': 158, 'wind_dir': 'SSE', 'pressure_mb': 1025.0, 'pressure_in': 30.26, 'precip_mm': 0.0, 'precip_in': 0.0, 'humidity': 63, 'cloud': 0, 'feelslike_c': 31.3, 'feelslike_f': 88.3, 'windchill_c': 28.3, 'windchill_f': 82.9, 'heatindex_c': 29.6, 'heatindex_f': 85.3, 'dewpoint_c': 18.4, 'dewpoint_f': 65.2, 'vis_km': 16.0, 'vis_miles': 9.0, 'uv': 7.0, 'gust_mph': 16.5, 'gust_kph': 26.5}}"}]
+    ================================== Ai Message ==================================
+    
+    The weather API results show that the current weather in New York City is sunny with a temperature of around 85°F (29°C). The wind is light at around 2-3 mph from the south-southeast. Overall it looks like a nice sunny summer day in NYC.
+
+
+Verify that the original, rolled back run was deleted
+
+=== "Python"
+
+    ```python
+    try:
+        await client.runs.get(thread["thread_id"], rolled_back_run["run_id"])
+    except httpx.HTTPStatusError as _:
+        print("Original run was correctly deleted")
+    ```
+
+=== "Javascript"
+
+    ```js
+    try {
+      await client.runs.get(thread["thread_id"], rolledBackRun["run_id"]);
+    } catch (e) {
+      console.log("Original run was correctly deleted");
+    }
+    ```
+
+Output:
+
+    Original run was correctly deleted
+

docs/docs/cloud/how-tos/stream_debug.md

@@ -0,0 +1,161 @@
+# How to stream debug events
+
+This guide covers how to stream debug events from your graph (`stream_mode="debug"`).
+
+First let's set up our client and thread:
+
+=== "Python"
+    
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    # create thread
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    // create thread
+    const thread = await client.threads.create();
+    console.log(thread)
+    ```
+
+
+Output:
+
+    {'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3',
+     'created_at': '2024-06-21T22:10:27.696862+00:00',
+     'updated_at': '2024-06-21T22:10:27.696862+00:00',
+     'metadata': {}}
+
+Streaming debug events produces responses containing `type` and `timestamp` keys. Debug events correspond to different steps in the graph's execution (e.g. `task`, `task_result`, `checkpoint`).
+
+
+=== "Python"
+
+    ```python
+    # create input
+    input = {
+        "messages": [
+            {
+                "role": "human",
+                "content": "What's the weather in SF?",
+            }
+        ]
+    }
+
+    # stream debug
+    async for chunk in client.runs.stream(
+        thread_id=thread["thread_id"],
+        assistant_id="agent",
+        input=input,
+        stream_mode="debug",
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+
+=== "Javascript"
+
+    ```js
+    // create input
+    const input = {
+        "messages": [
+            {
+                "role": "human",
+                "content": "What's the weather in SF?",
+            }
+        ]
+    }
+
+    // stream debug
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: "debug"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(f"Receiving new event of type: {chunk.event}...")
+      console.log(chunk.data)
+      console.log("\n\n")
+    }
+    ```
+
+Output:
+
+    Receiving new event of type: metadata...
+    {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.256850+00:00', 'step': -1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a2e-6bb6-bfff-8423bcf47561', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'messages': []}, 'metadata': {'source': 'input', 'step': -1, 'writes': {'messages': [{'role': 'human', 'content': "What's the weather in SF?"}]}}}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.259723+00:00', 'step': 0, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a35-6c86-8000-f4a85315dbeb', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}]}, 'metadata': {'source': 'loop', 'step': 0, 'writes': None}}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task', 'timestamp': '2024-06-21T22:11:09.260021+00:00', 'step': 1, 'payload': {'id': '12ab1026-a551-5f96-9ad3-43424f094774', 'name': 'agent', 'input': {'some_bytes': None, 'some_byte_array': None, 'dict_with_bytes': None, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}], 'sleep': None}, 'triggers': ['start:agent']}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task_result', 'timestamp': '2024-06-21T22:11:09.267632+00:00', 'step': 1, 'payload': {'id': '12ab1026-a551-5f96-9ad3-43424f094774', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.268469+00:00', 'step': 1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a4b-60ae-8001-dd378f965bf7', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 1, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task', 'timestamp': '2024-06-21T22:11:09.268659+00:00', 'step': 2, 'payload': {'id': '494ad427-fe8d-5654-91e6-50495a2699f5', 'name': 'tool', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}, 'triggers': ['branch:agent:should_continue:tool']}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task_result', 'timestamp': '2024-06-21T22:11:09.272916+00:00', 'step': 2, 'payload': {'id': '494ad427-fe8d-5654-91e6-50495a2699f5', 'name': 'tool', 'result': [['messages', [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}]]]}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.273113+00:00', 'step': 2, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a56-6832-8002-8ab17e662980', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}]}, 'metadata': {'source': 'loop', 'step': 2, 'writes': {'tool': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}]}}}}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task', 'timestamp': '2024-06-21T22:11:09.273192+00:00', 'step': 3, 'payload': {'id': '677de327-99b7-5d97-9bbd-0092abb62d46', 'name': 'agent', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}], 'sleep': None}, 'triggers': ['tool']}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task_result', 'timestamp': '2024-06-21T22:11:09.277262+00:00', 'step': 3, 'payload': {'id': '677de327-99b7-5d97-9bbd-0092abb62d46', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-006e1758-b1ca-4c90-9ff3-d2e75b9ca9a7', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.277519+00:00', 'step': 3, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a61-6462-8003-1316d9875b7f', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-006e1758-b1ca-4c90-9ff3-d2e75b9ca9a7', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 3, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-006e1758-b1ca-4c90-9ff3-d2e75b9ca9a7', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}
+    
+    
+    
+    Receiving new event of type: end...
+    None
+    
+    
+    
+

docs/docs/cloud/how-tos/stream_events.md

@@ -0,0 +1,298 @@
+# How to stream events
+This guide covers how to stream events from your graph (`stream_mode="events"`). Depending on the use case and user experience of your LangGraph application, your application may process event types differently.
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    # create thread
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    // create thread
+    const thread = await client.threads.create();
+    console.log(thread)
+    ```
+
+
+Output:
+
+
+    {'thread_id': '3f4c64e0-f792-4a5e-aa07-a4404e06e0bd',
+     'created_at': '2024-06-24T22:16:29.301522+00:00',
+     'updated_at': '2024-06-24T22:16:29.301522+00:00',
+     'metadata': {}}
+
+
+
+Streaming events produces responses containing an `event` key (in addition to other keys such as `data`). See the LangChain [`Runnable.astream_events()` reference](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.astream_events) for all event types.
+
+
+=== "Python"
+
+    ```python
+    # create input
+    input = {
+        "messages": [
+            {
+                "role": "human",
+                "content": "What's the weather in SF?",
+            }
+        ]
+    }
+
+    # stream events
+    async for chunk in client.runs.stream(
+        thread_id=thread["thread_id"],
+        assistant_id="agent",
+        input=input,
+        stream_mode="events",
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+
+=== "Javascript"
+
+    ```js
+    // create input
+    const input = {
+        "messages": [
+            {
+                "role": "human",
+                "content": "What's the weather in SF?",
+            }
+        ]
+    }
+
+    // stream events
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: "events"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(f"Receiving new event of type: {chunk.event}...")
+      console.log(chunk.data)
+      console.log("\n\n")
+    }
+    ```
+
+Output:
+
+    Receiving new event of type: metadata...
+    {'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8'}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {'input': {'messages': [{'role': 'human', 'content': "What's the weather in SF?"}]}}, 'name': 'LangGraph', 'tags': [], 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {}, 'name': 'agent', 'tags': ['graph:step:6'], 'run_id': '7bb08493-d507-4e28-b9e6-4a5eda9d04f0', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_start', 'data': {'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}]]}}, 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'b', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'g', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'i', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'n', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_end', 'data': {'output': {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, 'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}]]}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'name': 'should_continue', 'tags': ['seq:step:3'], 'run_id': 'c7fe4d2d-3fb8-4e53-946d-03de13527853', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': 'tool', 'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'run_id': 'c7fe4d2d-3fb8-4e53-946d-03de13527853', 'name': 'should_continue', 'tags': ['seq:step:3'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '7bb08493-d507-4e28-b9e6-4a5eda9d04f0', 'name': 'agent', 'tags': ['graph:step:6'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}], 'sleep': None}}, 'run_id': '7bb08493-d507-4e28-b9e6-4a5eda9d04f0', 'name': 'agent', 'tags': ['graph:step:6'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {}, 'name': 'tool', 'tags': ['graph:step:7'], 'run_id': 'f044fd3d-7271-488f-b8aa-e01572ff9112', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 7, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': 'f044fd3d-7271-488f-b8aa-e01572ff9112', 'name': 'tool', 'tags': ['graph:step:7'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 7, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': None, 'tool_call_id': 'tool_call_id'}]}}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}]}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}}, 'run_id': 'f044fd3d-7271-488f-b8aa-e01572ff9112', 'name': 'tool', 'tags': ['graph:step:7'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 7, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {}, 'name': 'agent', 'tags': ['graph:step:8'], 'run_id': '1f4f95d0-0ce1-4061-85d4-946446bbd3e5', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_start', 'data': {'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}]]}}, 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'n', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'd', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_end', 'data': {'output': {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, 'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}]]}}, 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'name': 'should_continue', 'tags': ['seq:step:3'], 'run_id': 'f2b2dfaf-475d-422b-8bf5-02a31bcc7d1a', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': '__end__', 'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'run_id': 'f2b2dfaf-475d-422b-8bf5-02a31bcc7d1a', 'name': 'should_continue', 'tags': ['seq:step:3'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1f4f95d0-0ce1-4061-85d4-946446bbd3e5', 'name': 'agent', 'tags': ['graph:step:8'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}], 'sleep': None}}, 'run_id': '1f4f95d0-0ce1-4061-85d4-946446bbd3e5', 'name': 'agent', 'tags': ['graph:step:8'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}, 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'name': 'LangGraph', 'tags': [], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: end...
+    None
+    
+    
+    
+
+
+## Token-by-Token Streaming
+
+Token-by-token streaming can be implemented with the `events` streaming mode. The `on_chat_model_stream` event type should be processed to stream LLM responses token-by-token.
+
+=== "Python"
+
+    ```python
+    llm_response = ""
+
+    # stream token-by-token
+    async for chunk in client.runs.stream(
+        thread_id=thread["thread_id"],
+        assistant_id="agent",
+        input=input,
+        stream_mode="events",
+    ):
+        if (
+            chunk.event == "events" and
+            chunk.data["event"] == "on_chat_model_stream"
+        ):
+            llm_response += chunk.data["data"]["chunk"]["content"]
+            print(llm_response)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const llmResponse = "";
+    // stream events
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: "events"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.event === "events" && chunk.data.event === "on_chat_model_stream") {
+        llmResponse += chunk.data.data.chunk.content;
+        console.log(llmResponse);
+      }
+    }
+    ```
+
+Output:
+
+    b
+    be
+    beg
+    begi
+    begin
+    begine
+    beginen
+    beginend
+

docs/docs/cloud/how-tos/stream_messages.md

@@ -0,0 +1,390 @@
+# How to stream messages from your graph
+
+LangGraph Cloud supports multiple streaming modes. The main ones are:
+
+- `values`: This streaming mode streams back values of the graph. This is the **full state of the graph** after each node is called.
+- `updates`: This streaming mode streams back updates to the graph. This is the **update to the state of the graph** after each node is called.
+- `messages`: This streaming mode streams back messages - both complete messages (at the end of a node) as well as **tokens** for any messages generated inside a node. This mode is primarily meant for powering chat applications.
+
+
+This guide covers `stream_mode="messages"`.
+
+In order to use this mode, the state of the graph you are interacting with MUST have a `messages` key that is a list of messages.
+E.g., the state should look something like:
+
+=== "Python"
+
+    ```python
+    from typing import TypedDict, Annotated
+    from langgraph.graph import add_messages
+    from langchain_core.messages import AnyMessage
+
+    class State(TypedDict):
+        messages: Annotated[list[AnyMessage], add_messages]
+    ```
+
+
+Alternatively, you can use an instance or subclass of `from langgraph.graph import MessagesState` (`MessagesState` is equivalent to the implementation above).
+
+> [!NOTE]
+> LangGraph Cloud only supports hosting graphs written in Python at the moment.
+
+With `stream_mode="messages"` two things will be streamed back:
+
+- It outputs messages produced by any chat model called inside (unless tagged in a special way)
+- It outputs messages returned from nodes (to allow for nodes to return `ToolMessages` and the like
+
+First let's set up our client and thread:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    # create thread
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    // create thread
+    const thread = await client.threads.create();
+    console.log(thread)
+    ```
+
+Output:
+
+    {'thread_id': 'e1431c95-e241-4d1d-a252-27eceb1e5c86',
+     'created_at': '2024-06-21T15:48:59.808924+00:00',
+     'updated_at': '2024-06-21T15:48:59.808924+00:00',
+     'metadata': {}}
+
+Let's also define a helper function for better formatting of the tool calls in messages
+
+=== "Python"
+
+    ```python
+    def format_tool_calls(tool_calls):
+        if tool_calls:
+            formatted_calls = []
+            for call in tool_calls:
+                formatted_calls.append(
+                    f"Tool Call ID: {call['id']}, Function: {call['name']}, Arguments: {call['args']}"
+                )
+            return "\n".join(formatted_calls)
+        return "No tool calls"
+    ```
+
+=== "Javascript"
+
+    ```js
+    function formatToolCalls(toolCalls) {
+      if (toolCalls && toolCalls.length > 0) {
+        const formattedCalls = toolCalls.map(call => {
+          return `Tool Call ID: ${call.id}, Function: ${call.name}, Arguments: ${call.args}`;
+        });
+        return formattedCalls.join("\n");
+      }
+      return "No tool calls";
+    }
+    ```
+
+Now we can stream by messages, which will return complete messages (at the end of node execution) as well as tokens for any messages generated inside a node:
+
+=== "Python"
+
+    ```python
+    input = {"messages": [{"role": "user", "content": "what's the weather in sf"}]}
+    config = {"configurable": {"model_name": "openai"}}
+
+    async for event in client.runs.stream(
+        thread["thread_id"],
+        assistant_id="agent",
+        input=input,
+        config=config,
+        stream_mode="messages",
+    ):
+        if event.event == "metadata":
+            print(f"Metadata: Run ID - {event.data['run_id']}")
+            print("-" * 50)
+        elif event.event == "messages/partial":
+            for data_item in event.data:
+                if "role" in data_item and data_item["role"] == "user":
+                    print(f"Human: {data_item['content']}")
+                else:
+                    tool_calls = data_item.get("tool_calls", [])
+                    invalid_tool_calls = data_item.get("invalid_tool_calls", [])
+                    content = data_item.get("content", "")
+                    response_metadata = data_item.get("response_metadata", {})
+
+                    if content:
+                        print(f"AI: {content}")
+
+                    if tool_calls:
+                        print("Tool Calls:")
+                        print(format_tool_calls(tool_calls))
+
+                    if invalid_tool_calls:
+                        print("Invalid Tool Calls:")
+                        print(format_tool_calls(invalid_tool_calls))
+
+                    if response_metadata:
+                        finish_reason = response_metadata.get("finish_reason", "N/A")
+                        print(f"Response Metadata: Finish Reason - {finish_reason}")
+            print("-" * 50)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const input = {
+      "messages": [
+        {
+          "role": "human",
+          "content": "What's the weather in sf",
+        }
+      ]
+    }
+    const config = {"configurable": {"model_name": "openai"}}
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        config,
+        streamMode: "messages"
+      }
+    );
+    for await (const event of streamResponse) {
+      if (event.event === "metadata") {
+        console.log(`Metadata: Run ID - ${event.data.run_id}`);
+        console.log("-".repeat(50));
+      } else if (event.event === "messages/partial") {
+        event.data.forEach(dataItem => {
+          if (dataItem.role && dataItem.role === "user") {
+            console.log(`Human: ${dataItem.content}`);
+          } else {
+            const toolCalls = dataItem.tool_calls || [];
+            const invalidToolCalls = dataItem.invalid_tool_calls || [];
+            const content = dataItem.content || "";
+            const responseMetadata = dataItem.response_metadata || {};
+
+            if (content) {
+              console.log(`AI: ${content}`);
+            }
+
+            if (toolCalls.length > 0) {
+              console.log("Tool Calls:");
+              console.log(formatToolCalls(toolCalls));
+            }
+
+            if (invalidToolCalls.length > 0) {
+              console.log("Invalid Tool Calls:");
+              console.log(formatToolCalls(invalidToolCalls));
+            }
+
+            if (responseMetadata) {
+              const finishReason = responseMetadata.finish_reason || "N/A";
+              console.log(`Response Metadata: Finish Reason - ${finishReason}`);
+            }
+          }
+        });
+        console.log("-".repeat(50));
+      }
+    }
+    ```
+
+Output:
+
+    Metadata: Run ID - 1ef2fe5c-6a1d-6575-bc09-d7832711c17e
+    --------------------------------------------------
+    Invalid Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: 
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': ''}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current'}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather'}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in'}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in San'}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in San Francisco'}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in San Francisco'}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in San Francisco'}
+    Response Metadata: Finish Reason - tool_calls
+    --------------------------------------------------
+    --------------------------------------------------
+    AI: The
+    --------------------------------------------------
+    AI: The current
+    --------------------------------------------------
+    AI: The current weather
+    --------------------------------------------------
+    AI: The current weather in
+    --------------------------------------------------
+    AI: The current weather in San
+    --------------------------------------------------
+    AI: The current weather in San Francisco
+    --------------------------------------------------
+    AI: The current weather in San Francisco is
+    --------------------------------------------------
+    AI: The current weather in San Francisco is over
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F).
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-s
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-south
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 k
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph).
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%,
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles).
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is 
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is 3
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is 3.
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is 3.
+    Response Metadata: Finish Reason - stop
+    --------------------------------------------------
+

docs/docs/cloud/how-tos/stream_multiple.md

@@ -0,0 +1,440 @@
+# How to configure multiple streaming modes at the same time
+
+This guide covers how to configure multiple streaming modes at the same time.
+
+First let's set up our client and thread:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    # create thread
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    // create thread
+    const thread = await client.threads.create();
+    console.log(thread)
+    ```
+
+
+Output:
+
+    {'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4',
+     'created_at': '2024-06-24T21:30:07.980789+00:00',
+     'updated_at': '2024-06-24T21:30:07.980789+00:00',
+     'metadata': {}}
+
+When configuring multiple streaming modes for a run, responses for each respective mode will be produced. In the following example, note that a `list` of modes (`messages`, `events`, `debug`) is passed to the `stream_mode` parameter and the response contains `events`, `debug`, `messages/complete`, `messages/metadata`, and `messages/partial` event types.
+
+=== "Python"
+
+    ```python
+    # create input
+    input = {
+        "messages": [
+            {
+                "role": "human",
+                "content": "What's the weather in SF?",
+            }
+        ]
+    }
+
+    # stream events with multiple streaming modes
+    async for chunk in client.runs.stream(
+        thread_id=thread["thread_id"],
+        assistant_id="agent",
+        input=input,
+        stream_mode=["messages", "events", "debug"],
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+
+=== "Javascript"
+
+    ```js
+    // create input
+    const input = {
+      "messages": [
+        {
+          "role": "human",
+          "content": "What's the weather in SF?",
+        }
+      ]
+    }
+
+    // stream events with multiple streaming modes
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: ["messages", "events", "debug"]
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(f"Receiving new event of type: {chunk.event}...")
+      console.log(chunk.data)
+      console.log("\n\n")
+    }
+    ```
+
+Output:
+
+    Receiving new event of type: metadata...
+    {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {'input': {'messages': [{'role': 'human', 'content': "What's the weather in SF?"}]}}, 'name': 'LangGraph', 'tags': [], 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.116009+00:00', 'step': -1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc7c-6daa-bfff-6b9027c1a50e', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'messages': []}, 'metadata': {'source': 'input', 'step': -1, 'writes': {'messages': [{'role': 'human', 'content': "What's the weather in SF?"}]}}}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.116009+00:00', 'step': -1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc7c-6daa-bfff-6b9027c1a50e', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'messages': []}, 'metadata': {'source': 'input', 'step': -1, 'writes': {'messages': [{'role': 'human', 'content': "What's the weather in SF?"}]}}}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['values', {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: messages/complete...
+    [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.117924+00:00', 'step': 0, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc81-68c8-8000-4e18ae7d67a5', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]}, 'metadata': {'source': 'loop', 'step': 0, 'writes': None}}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.117924+00:00', 'step': 0, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc81-68c8-8000-4e18ae7d67a5', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]}, 'metadata': {'source': 'loop', 'step': 0, 'writes': None}}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task', 'timestamp': '2024-06-24T21:34:06.118042+00:00', 'step': 1, 'payload': {'id': '212ed9c2-a454-50c5-a202-12066bbbe7b8', 'name': 'agent', 'input': {'some_bytes': None, 'some_byte_array': None, 'dict_with_bytes': None, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}], 'sleep': None}, 'triggers': ['start:agent']}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task', 'timestamp': '2024-06-24T21:34:06.118042+00:00', 'step': 1, 'payload': {'id': '212ed9c2-a454-50c5-a202-12066bbbe7b8', 'name': 'agent', 'input': {'some_bytes': None, 'some_byte_array': None, 'dict_with_bytes': None, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}], 'sleep': None}, 'triggers': ['start:agent']}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {}, 'name': 'agent', 'tags': ['graph:step:1'], 'run_id': '72b74d24-5792-48da-a887-102100d6e2c0', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_start', 'data': {'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]]}}, 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'b', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: messages/metadata...
+    {'run-2424dd6d-5cf5-4244-8d98-357640ce6e12': {'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}}}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'b', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'be', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'g', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'beg', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'i', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'begi', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'n', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_end', 'data': {'output': {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, 'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]]}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'name': 'should_continue', 'tags': ['seq:step:3'], 'run_id': '227afb0f-f909-4d54-a042-556ca6d98a69', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': 'tool', 'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'run_id': '227afb0f-f909-4d54-a042-556ca6d98a69', 'name': 'should_continue', 'tags': ['seq:step:3'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '72b74d24-5792-48da-a887-102100d6e2c0', 'name': 'agent', 'tags': ['graph:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}, 'input': {'some_bytes': None, 'some_byte_array': None, 'dict_with_bytes': None, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}], 'sleep': None}}, 'run_id': '72b74d24-5792-48da-a887-102100d6e2c0', 'name': 'agent', 'tags': ['graph:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.124350+00:00', 'step': 1, 'payload': {'id': '212ed9c2-a454-50c5-a202-12066bbbe7b8', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.124350+00:00', 'step': 1, 'payload': {'id': '212ed9c2-a454-50c5-a202-12066bbbe7b8', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['values', {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: messages/complete...
+    [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.124510+00:00', 'step': 1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc91-6a34-8001-26353c117c25', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 1, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.124510+00:00', 'step': 1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc91-6a34-8001-26353c117c25', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 1, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task', 'timestamp': '2024-06-24T21:34:06.124572+00:00', 'step': 2, 'payload': {'id': '44139125-a1be-57c2-9cb2-19eb62bbaf2f', 'name': 'tool', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}, 'triggers': ['branch:agent:should_continue:tool']}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task', 'timestamp': '2024-06-24T21:34:06.124572+00:00', 'step': 2, 'payload': {'id': '44139125-a1be-57c2-9cb2-19eb62bbaf2f', 'name': 'tool', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}, 'triggers': ['branch:agent:should_continue:tool']}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {}, 'name': 'tool', 'tags': ['graph:step:2'], 'run_id': '91575720-886e-485e-ae2d-d6817e5346bf', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 2, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '91575720-886e-485e-ae2d-d6817e5346bf', 'name': 'tool', 'tags': ['graph:step:2'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 2, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': None, 'tool_call_id': 'tool_call_id'}]}}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}}, 'run_id': '91575720-886e-485e-ae2d-d6817e5346bf', 'name': 'tool', 'tags': ['graph:step:2'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 2, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.126828+00:00', 'step': 2, 'payload': {'id': '44139125-a1be-57c2-9cb2-19eb62bbaf2f', 'name': 'tool', 'result': [['messages', [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]]]}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.126828+00:00', 'step': 2, 'payload': {'id': '44139125-a1be-57c2-9cb2-19eb62bbaf2f', 'name': 'tool', 'result': [['messages', [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]]]}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['values', {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: messages/complete...
+    [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.126966+00:00', 'step': 2, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc97-6a06-8002-8e9ffc1ea75a', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}, 'metadata': {'source': 'loop', 'step': 2, 'writes': {'tool': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}}}}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.126966+00:00', 'step': 2, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc97-6a06-8002-8e9ffc1ea75a', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}, 'metadata': {'source': 'loop', 'step': 2, 'writes': {'tool': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}}}}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task', 'timestamp': '2024-06-24T21:34:06.127034+00:00', 'step': 3, 'payload': {'id': 'f1ccf371-63b3-5268-a837-7f360a93c4ec', 'name': 'agent', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}], 'sleep': None}, 'triggers': ['tool']}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task', 'timestamp': '2024-06-24T21:34:06.127034+00:00', 'step': 3, 'payload': {'id': 'f1ccf371-63b3-5268-a837-7f360a93c4ec', 'name': 'agent', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}], 'sleep': None}, 'triggers': ['tool']}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {}, 'name': 'agent', 'tags': ['graph:step:3'], 'run_id': 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_start', 'data': {'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]]}}, 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: messages/metadata...
+    {'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575': {'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}}}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'n', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'en', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'd', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_end', 'data': {'output': {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, 'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]]}}, 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'name': 'should_continue', 'tags': ['seq:step:3'], 'run_id': '8af814e9-8136-4aab-acbc-dffc5bcafdfd', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': '__end__', 'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'run_id': '8af814e9-8136-4aab-acbc-dffc5bcafdfd', 'name': 'should_continue', 'tags': ['seq:step:3'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e', 'name': 'agent', 'tags': ['graph:step:3'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}], 'sleep': None}}, 'run_id': 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e', 'name': 'agent', 'tags': ['graph:step:3'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.133991+00:00', 'step': 3, 'payload': {'id': 'f1ccf371-63b3-5268-a837-7f360a93c4ec', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.133991+00:00', 'step': 3, 'payload': {'id': 'f1ccf371-63b3-5268-a837-7f360a93c4ec', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['values', {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: messages/complete...
+    [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.134190+00:00', 'step': 3, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bca9-6418-8003-8d0d0b06845c', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 3, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.134190+00:00', 'step': 3, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bca9-6418-8003-8d0d0b06845c', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 3, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: end...
+    None
+    
+    
+    
+

docs/docs/cloud/how-tos/stream_updates.md

@@ -0,0 +1,119 @@
+# How to stream state updates of your graph
+
+LangGraph Cloud supports multiple streaming modes. The main ones are:
+
+- `values`: This streaming mode streams back values of the graph. This is the **full state of the graph** after each node is called.
+- `updates`: This streaming mode streams back updates to the graph. This is the **update to the state of the graph** after each node is called.
+- `messages`: This streaming mode streams back messages - both complete messages (at the end of a node) as well as **tokens** for any messages generated inside a node. This mode is primarily meant for powering chat applications.
+
+
+This guide covers `stream_mode="updates"`.
+
+First let's set up our client and thread:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    # create thread
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    // create thread
+    const thread = await client.threads.create();
+    console.log(thread)
+    ```
+
+
+Output:
+
+    {'thread_id': '979e3c89-a702-4882-87c2-7a59a250ce16',
+     'created_at': '2024-06-21T15:22:07.453100+00:00',
+     'updated_at': '2024-06-21T15:22:07.453100+00:00',
+     'metadata': {}}
+
+Now we can stream by updates, which outputs updates made to the state by each node after it has executed:
+
+
+=== "Python"
+
+    ```python
+    input = {
+        "messages": [
+            {
+                "role": "human",
+                "content": "what's the weather in la"
+            }
+        ]
+    }
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        "agent",
+        input=input,
+        stream_mode="updates",
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+
+=== "Javascript"
+
+    ```js
+    const input = {
+      "messages": [
+        {
+          "role": "human",
+          "content": "What's the weather in la",
+        }
+      ]
+    }
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: "updates"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(f"Receiving new event of type: {chunk.event}...")
+      console.log(chunk.data)
+      console.log("\n\n")
+    }
+    ```
+
+Output:
+
+    Receiving new event of type: metadata...
+    {'run_id': 'cfc96c16-ed9a-44bd-b5bb-c30e3c0725f0'}
+    
+    
+    
+    Receiving new event of type: data...
+    {'agent': {'messages': [{'content': [{'id': 'toolu_0148tMmDK51iLQfG1yaNwRHM', 'input': {'query': 'weather in los angeles'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-1a9d32b0-7007-4a36-abde-8df812a0ed94', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in los angeles'}, 'id': 'toolu_0148tMmDK51iLQfG1yaNwRHM'}], 'invalid_tool_calls': []}]}}
+    
+    
+    
+    Receiving new event of type: data...
+    {'action': {'messages': [{'content': '[{"url": "https://www.weatherapi.com/", "content": "{\'location\': {\'name\': \'Los Angeles\', \'region\': \'California\', \'country\': \'United States of America\', \'lat\': 34.05, \'lon\': -118.24, \'tz_id\': \'America/Los_Angeles\', \'localtime_epoch\': 1716062239, \'localtime\': \'2024-05-18 12:57\'}, \'current\': {\'last_updated_epoch\': 1716061500, \'last_updated\': \'2024-05-18 12:45\', \'temp_c\': 18.9, \'temp_f\': 66.0, \'is_day\': 1, \'condition\': {\'text\': \'Overcast\', \'icon\': \'//cdn.weatherapi.com/weather/64x64/day/122.png\', \'code\': 1009}, \'wind_mph\': 2.2, \'wind_kph\': 3.6, \'wind_degree\': 10, \'wind_dir\': \'N\', \'pressure_mb\': 1017.0, \'pressure_in\': 30.02, \'precip_mm\': 0.0, \'precip_in\': 0.0, \'humidity\': 65, \'cloud\': 100, \'feelslike_c\': 18.9, \'feelslike_f\': 66.0, \'vis_km\': 16.0, \'vis_miles\': 9.0, \'uv\': 6.0, \'gust_mph\': 7.5, \'gust_kph\': 12.0}}"}]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'tavily_search_results_json', 'id': 'a36e8cd1-0e96-4417-9c15-f10a945d2b42', 'tool_call_id': 'toolu_0148tMmDK51iLQfG1yaNwRHM'}]}}
+    
+    
+    
+    Receiving new event of type: data...
+    {'agent': {'messages': [{'content': 'The weather in Los Angeles is currently overcast with a temperature of around 66°F (18.9°C). There are light winds from the north at around 2-3 mph. The humidity is 65% and visibility is good at 9 miles. Overall, mild spring weather conditions in LA.', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-d5c1c2f0-b12d-41ce-990b-f36570e7483d', 'example': False, 'tool_calls': [], 'invalid_tool_calls': []}]}}
+    
+    
+    
+    Receiving new event of type: end...
+    None

docs/docs/cloud/how-tos/stream_values.md

@@ -0,0 +1,190 @@
+# How to stream full state of your graph
+
+LangGraph Cloud supports multiple streaming modes. The main ones are:
+
+- `values`: This streaming mode streams back values of the graph. This is the **full state of the graph** after each node is called.
+- `updates`: This streaming mode streams back updates to the graph. This is the **update to the state of the graph** after each node is called.
+- `messages`: This streaming mode streams back messages - both complete messages (at the end of a node) as well as **tokens** for any messages generated inside a node. This mode is primarily meant for powering chat applications.
+
+
+This guide covers `stream_mode="values"`.
+
+First let's set up our client and thread:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    # create thread
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl: "whatever-your-deployment-url-is" });
+    // create thread
+    const thread = await client.threads.create();
+    console.log(thread)
+    ```
+
+Output:
+
+    {'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4',
+     'created_at': '2024-06-24T21:30:07.980789+00:00',
+     'updated_at': '2024-06-24T21:30:07.980789+00:00',
+     'metadata': {}}
+
+Now we can stream by values, which streams the full state of the graph after each node has finished executing:
+
+=== "Python"
+
+    ```python
+    input = {"messages": [{"role": "human", "content": "what's the weather in la"}]}
+
+    # stream values
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        "agent", 
+        input=input,
+        stream_mode="values"
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+
+=== "Javascript"
+    
+
+    ```js
+    const input = {"messages": [{"role": "human", "content": "what's the weather in la"}]}
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: "values"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(f"Receiving new event of type: {chunk.event}...")
+      console.log(chunk.data)
+      console.log("\n\n")
+    }
+    ```
+
+
+Output:
+
+    Receiving new event of type: metadata...
+    {'run_id': 'f08791ce-0a3d-44e0-836c-ff62cd2e2786'}
+    
+    
+    
+    Receiving new event of type: values...
+    {'messages': [{'role': 'human', 'content': 'what's the weather in la'}]}
+    
+    
+    
+    Receiving new event of type: values...
+    {'messages': [{'content': 'what's the weather in la', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'faa15565-8823-4aa1-87af-e21b40526fae', 'example': False}, {'content': [{'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g', 'input': {'query': 'weather in los angeles'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-3fe1db7a-6b8d-4d83-ba07-8657190ad811', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in los angeles'}, 'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}], 'invalid_tool_calls': []}]}
+    
+    
+    
+    Receiving new event of type: values...
+    {'messages': [{'content': 'what's the weather in la', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'faa15565-8823-4aa1-87af-e21b40526fae', 'example': False}, {'content': [{'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g', 'input': {'query': 'weather in los angeles'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-3fe1db7a-6b8d-4d83-ba07-8657190ad811', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in los angeles'}, 'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}], 'invalid_tool_calls': []}, {'content': '[{"url": "https://www.weatherapi.com/", "content": "{\'location\': {\'name\': \'Los Angeles\', \'region\': \'California\', \'country\': \'United States of America\', \'lat\': 34.05, \'lon\': -118.24, \'tz_id\': \'America/Los_Angeles\', \'localtime_epoch\': 1716310320, \'localtime\': \'2024-05-21 9:52\'}, \'current\': {\'last_updated_epoch\': 1716309900, \'last_updated\': \'2024-05-21 09:45\', \'temp_c\': 16.7, \'temp_f\': 62.1, \'is_day\': 1, \'condition\': {\'text\': \'Overcast\', \'icon\': \'//cdn.weatherapi.com/weather/64x64/day/122.png\', \'code\': 1009}, \'wind_mph\': 8.1, \'wind_kph\': 13.0, \'wind_degree\': 250, \'wind_dir\': \'WSW\', \'pressure_mb\': 1015.0, \'pressure_in\': 29.97, \'precip_mm\': 0.0, \'precip_in\': 0.0, \'humidity\': 65, \'cloud\': 100, \'feelslike_c\': 16.7, \'feelslike_f\': 62.1, \'vis_km\': 16.0, \'vis_miles\': 9.0, \'uv\': 5.0, \'gust_mph\': 12.5, \'gust_kph\': 20.2}}"}]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'tavily_search_results_json', 'id': '0d5dab31-5ff8-4ae2-a560-bc4bcba7c9d7', 'tool_call_id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}]}
+    
+    
+    
+    Receiving new event of type: values...
+    {'messages': [{'content': 'what's the weather in la', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'faa15565-8823-4aa1-87af-e21b40526fae', 'example': False}, {'content': [{'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g', 'input': {'query': 'weather in los angeles'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-3fe1db7a-6b8d-4d83-ba07-8657190ad811', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in los angeles'}, 'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}], 'invalid_tool_calls': []}, {'content': '[{"url": "https://www.weatherapi.com/", "content": "{\'location\': {\'name\': \'Los Angeles\', \'region\': \'California\', \'country\': \'United States of America\', \'lat\': 34.05, \'lon\': -118.24, \'tz_id\': \'America/Los_Angeles\', \'localtime_epoch\': 1716310320, \'localtime\': \'2024-05-21 9:52\'}, \'current\': {\'last_updated_epoch\': 1716309900, \'last_updated\': \'2024-05-21 09:45\', \'temp_c\': 16.7, \'temp_f\': 62.1, \'is_day\': 1, \'condition\': {\'text\': \'Overcast\', \'icon\': \'//cdn.weatherapi.com/weather/64x64/day/122.png\', \'code\': 1009}, \'wind_mph\': 8.1, \'wind_kph\': 13.0, \'wind_degree\': 250, \'wind_dir\': \'WSW\', \'pressure_mb\': 1015.0, \'pressure_in\': 29.97, \'precip_mm\': 0.0, \'precip_in\': 0.0, \'humidity\': 65, \'cloud\': 100, \'feelslike_c\': 16.7, \'feelslike_f\': 62.1, \'vis_km\': 16.0, \'vis_miles\': 9.0, \'uv\': 5.0, \'gust_mph\': 12.5, \'gust_kph\': 20.2}}"}]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'tavily_search_results_json', 'id': '0d5dab31-5ff8-4ae2-a560-bc4bcba7c9d7', 'tool_call_id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}, {'content': 'Based on the weather API results, the current weather in Los Angeles is overcast with a temperature of around 62°F (17°C). There are light winds from the west-southwest around 8-13 mph. The humidity is 65% and visibility is good at 9 miles. Overall, mild spring weather conditions in LA.', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-4d6d4c23-5aad-4042-b0d9-19407a9e08e3', 'example': False, 'tool_calls': [], 'invalid_tool_calls': []}]}
+    
+    
+    
+    Receiving new event of type: end...
+    None
+    
+    
+    
+
+
+If we want to just get the final result, we can use this endpoint and just keep track of the last value we received
+
+
+=== "Python"
+
+    ```python
+    final_answer = None
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        "agent",
+        input=input,
+        stream_mode="values"
+    ):
+        if chunk.event == "values":
+            final_answer = chunk.data
+    ```
+
+=== "Javascript"
+
+    ```js
+    let finalAnswer;
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: "values"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      finalAnswer = chunk.data;
+    }
+    ```
+
+Output:
+
+    {'messages': [{'content': 'what's the weather in la',
+       'additional_kwargs': {},
+       'response_metadata': {},
+       'type': 'human',
+       'name': None,
+       'id': 'e78c2f94-d810-42fc-a399-11f6bb1b1092',
+       'example': False},
+      {'content': [{'id': 'toolu_01SBMoAGr4U9x3ibztm2UUom',
+         'input': {'query': 'weather in los angeles'},
+         'name': 'tavily_search_results_json',
+         'type': 'tool_use'}],
+       'additional_kwargs': {},
+       'response_metadata': {},
+       'type': 'ai',
+       'name': None,
+       'id': 'run-80767ab8-09fc-40ec-9e45-657ddef5e0b1',
+       'example': False,
+       'tool_calls': [{'name': 'tavily_search_results_json',
+         'args': {'query': 'weather in los angeles'},
+         'id': 'toolu_01SBMoAGr4U9x3ibztm2UUom'}],
+       'invalid_tool_calls': []},
+      {'content': '[{"url": "https://www.weatherapi.com/", "content": "{\'location\': {\'name\': \'Los Angeles\', \'region\': \'California\', \'country\': \'United States of America\', \'lat\': 34.05, \'lon\': -118.24, \'tz_id\': \'America/Los_Angeles\', \'localtime_epoch\': 1716310320, \'localtime\': \'2024-05-21 9:52\'}, \'current\': {\'last_updated_epoch\': 1716309900, \'last_updated\': \'2024-05-21 09:45\', \'temp_c\': 16.7, \'temp_f\': 62.1, \'is_day\': 1, \'condition\': {\'text\': \'Overcast\', \'icon\': \'//cdn.weatherapi.com/weather/64x64/day/122.png\', \'code\': 1009}, \'wind_mph\': 8.1, \'wind_kph\': 13.0, \'wind_degree\': 250, \'wind_dir\': \'WSW\', \'pressure_mb\': 1015.0, \'pressure_in\': 29.97, \'precip_mm\': 0.0, \'precip_in\': 0.0, \'humidity\': 65, \'cloud\': 100, \'feelslike_c\': 16.7, \'feelslike_f\': 62.1, \'vis_km\': 16.0, \'vis_miles\': 9.0, \'uv\': 5.0, \'gust_mph\': 12.5, \'gust_kph\': 20.2}}"}]',
+       'additional_kwargs': {},
+       'response_metadata': {},
+       'type': 'tool',
+       'name': 'tavily_search_results_json',
+       'id': 'af25e94a-c119-48c3-bbd3-096e42f472ac',
+       'tool_call_id': 'toolu_01SBMoAGr4U9x3ibztm2UUom'},
+      {'content': 'Based on the weather API results, the current weather in Los Angeles is overcast with a temperature of around 62°F (17°C). There are light winds from the west-southwest around 8-13 mph. The humidity is 65% and visibility is good at 9 miles. Overall, mild spring weather conditions in LA.',
+       'additional_kwargs': {},
+       'response_metadata': {},
+       'type': 'ai',
+       'name': None,
+       'id': 'run-b90f0037-e56a-4f3b-ad92-00d10d079a9e',
+       'example': False,
+       'tool_calls': [],
+       'invalid_tool_calls': []}]}

docs/docs/cloud/how-tos/test_deployment.md

@@ -0,0 +1,16 @@
+# Test Cloud Deployment
+
+The LangGraph Studio UI connects directly to LangGraph Cloud deployments.
+
+Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>...
+
+1. In the left-hand navigation panel, select `Deployments`. The `Deployments` view contains a list of existing LangGraph Cloud deployments.
+1. Select an existing deployment to test with LangGraph Studio.
+1. In the top-right corner, select `Open LangGraph Studio`.
+1. [Invoke an assistant](./invoke_studio.md) or [view an existing thread](./threads_studio.md).
+
+The following video shows these exact steps being carried out:
+
+<video controls allowfullscreen="true" poster="../img/studio_usage_poster.png">
+    <source src="../img/studio_usage.mp4" type="video/mp4">
+</video>

docs/docs/cloud/how-tos/test_local_deployment.md

@@ -0,0 +1,28 @@
+# LangGraph Studio With Local Deployment
+
+!!! warning "Browser Compatibility"
+    Viewing the studio page of a local LangGraph deployment does not work in Safari. Use Chrome instead.
+
+## Setup
+
+Make sure you have setup your app correctly, by creating a compiled graph, a `.env` file with any environment variables, and a `langgraph.json` config file that points to your environment file and compiled graph. See [here](https://langchain-ai.github.io/langgraph/cloud/deployment/setup/) for more detailed instructions.
+
+After you have your app setup, head into the directory with your `langgraph.json` file and call `langgraph up -c langgraph.json --watch` to start the API server in watch mode which means it will restart on code changes, which is ideal for local testing. If the API server start correctly you should see logs that look something like this:
+
+    Ready!
+    - API: http://localhost:8123
+    2024-06-26 19:20:41,056:INFO:uvicorn.access 127.0.0.1:44138 - "GET /ok HTTP/1.1" 200
+
+Read this [reference](https://langchain-ai.github.io/langgraph/cloud/reference/cli/#up) to learn about all the options for starting the API server.
+
+## Access Studio
+
+Once you have successfully started the API server, you can access the studio by going to the following URL: `https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:8123` (see warning above if using Safari).
+
+If everything is working correctly you should see the studio show up looking something like this (with your graph diagram on the left hand side):
+
+![LangGraph Studio](./img/studio_screenshot.png)
+
+## Use the Studio for Testing
+
+To learn about how to use the studio for testing, read the [LangGraph Studio how-tos](https://langchain-ai.github.io/langgraph/cloud/how-tos/#langgraph-studio).

docs/docs/cloud/how-tos/threads_studio.md

@@ -0,0 +1,23 @@
+# Interacting with Threads in Studio
+
+## View Thread
+
+1. In the top of the right-hand pane, select the `New Thread` dropdown menu to view existing threads.
+1. View the state of the thread (i.e. the output) in the right-hand pane.
+1. To create a new thread, select `+ New Thread`.
+
+The following video shows these exact steps being carried out:
+
+<video controls="true" allowfullscreen="true" poster="../img/studio_threads_poster.png">
+    <source src="../img/studio_threads.mp4" type="video/mp4">
+</video>
+
+## Edit Thread State
+
+The LangGraph Studio UI contains features for editing thread state. Explore these features in the right-hand pane. Select the `Edit` icon, modify the desired state, and then select `Fork` to invoke the assistant with the updated state.
+
+The following video shows how to edit a thread in the studio:
+
+<video controls allowfullscreen="true" poster="../img/studio_forks_poster.png">
+    <source src="../img/studio_forks.mp4" type="video/mp4">
+</video>

docs/docs/cloud/index.md

@@ -0,0 +1,45 @@
+# LangGraph Cloud (beta)
+
+!!! tip
+    - LangGraph is an MIT-licensed open-source library, which we are committed to maintaining and growing for the community.
+    - LangGraph Cloud is an optional managed hosting service for LangGraph, which provides additional features geared towards production deployments.
+    - We are actively contributing improvements back to LangGraph informed by our work on LangGraph Cloud.
+    - You can always deploy LangGraph applications on your own infrastructure using the open-source LangGraph project.
+
+!!! danger "Important"
+    LangGraph Cloud is a closed source, paid product in an invite-only stage. We are currently focused on providing high bandwidth support to make our select early customers successful. If you are interested in applying for access, please fill out [this form](https://www.langchain.com/langgraph-cloud-beta).
+
+!!! warning "Under Construction"
+    LangGraph Cloud documentation is under construction. Contents may change until general availability.
+
+
+<video controls preload="auto" allowfullscreen="true" poster="how-tos/img/studio_forks_poster.png">
+    <source src="how-tos/img/studio_forks.mp4" type="video/mp4">
+</video>
+
+
+## Overview
+
+LangGraph Cloud is a managed service for deploying and hosting LangGraph applications. Deploying applications with LangGraph Cloud shortens the time-to-market for developers. With one click, deploy a production-ready API with built-in persistence for your LangGraph application. LangGraph Cloud APIs are horizontally scalable and deployed with durable storage.
+
+The LangGraph Cloud API exposes functionality of your LangGraph application through [Assistants](./concepts/api.md#assistants). An assistant abstracts the cognitive architecture of your graph. Invoke an assistant by calling the pre-built [API endpoints](./reference/api/api_ref.md).
+
+LangGraph Cloud is seamlessly integrated with [LangSmith](https://www.langchain.com/langsmith) and is accessible from within the LangSmith UI.
+
+## Key Features
+
+The LangGraph Cloud API supports key LangGraph features in addition to new functionality for enabling complex, agentic workflows.
+
+- **Assistants and Threads**: Assistants abstract the cognitive architecture of graphs and threads track the state/history of graphs.
+- **Streaming**: API support for [LangGraph streaming modes](../concepts/low_level.md#streaming) including setting multiple streaming modes at the same time.
+- **Human-in-the-Loop**: API support for [LangGraph human-in-the-loop features](../concepts/agentic_concepts.md#human-in-the-loop).
+- **Double Texting**: Configure how assistants respond when new input is received while processing a previous input. Interrupt, rollback, reject, or enqueue.
+- **Background Runs/Cron Jobs**: A built-in task queue enables background runs and scheduled cron jobs.
+- **Stateless Runs**: For simpler use cases, invoke an assistant without needing to create a thread.
+
+## Documentation
+
+- [Tutorials](./quick_start.md): Learn to build and deploy applications for LangGraph Cloud.
+- [How-to Guides](./how-tos/index.md): Learn how to set up a LangGraph application for deployment and implement features of the LangGraph Cloud API such as streaming tokens, configuring double texting, and creating cron jobs. Go here if you want to copy and run a specific code snippet.
+- [Conceptual Guides](./concepts/api.md): In-depth explanations of the core data models (e.g. assistants), key features of the LangGraph Cloud API (e.g. double texting), and the architecture of a LangGraph Cloud deployment.
+- [Reference](./reference/api/api_ref.md): References for the LangGraph Cloud API, the corresponding Python and JS/TS SDKs, the LangGraph CLI, and deployment environment variables.

docs/docs/cloud/quick_start.md

@@ -0,0 +1,252 @@
+# Quick Start
+
+This quick start guide will cover how to build a simple agent that can look up things on the internet. We will then deploy it to LangGraph Cloud, use the LangGraph Studio to visualize and test it out, and use the LangGraph SDK to interact with it.
+
+## Set up requirements
+
+This tutorial will use:
+
+- Anthropic for the LLM - sign up and get an API key [here](https://console.anthropic.com/)
+- Tavily for the search engine - sign up and get an API key [here](https://app.tavily.com/)
+- LangSmith for hosting - sign up and get an API key [here](https://smith.langchain.com/)
+
+## Set up local files
+
+1.  Create a new application with the following directory and files:
+
+        <my-app>/
+        |-- agent.py            # code for your LangGraph agent
+        |-- requirements.txt    # Python packages required for your graph
+        |-- langgraph.json      # configuration file for LangGraph
+        |-- .env                # environment files with API keys
+
+2.  The `agent.py` file should contain Python code for defining your graph. The following code is a simple example, the important thing is that at some point in your file you compile your graph and assign the compiled graph to a variable (in this case the `graph` variable). This example code uses `create_react_agent`, a prebuilt agent, read more about it [here](..//concepts/agentic_concepts.md#react-agent).
+
+    ```python
+    from langchain_anthropic import ChatAnthropic
+    from langchain_community.tools.tavily_search import TavilySearchResults
+    from langgraph.prebuilt import create_react_agent
+
+    model = ChatAnthropic(model="claude-3-5-sonnet-20240620")
+
+    tools = [TavilySearchResults(max_results=2)]
+
+    graph = create_react_agent(model, tools)
+    ```
+
+3.  The `requirements.txt` file should contain any dependencies for your graph(s). In this case we only require four packages for our graph to run:
+
+        langgraph
+        langchain_anthropic
+        tavily-python
+        langchain_community
+
+4.  The [`langgraph.json`][langgraph.json] file is a configuration file that describes what graph(s) you are going to host. In this case we only have one graph to host: the compiled `graph` object from `agent.py`.
+
+    ```json
+    {
+      "dependencies": ["."],
+      "graphs": {
+        "agent": "./agent.py:graph"
+      },
+      "env": ".env"
+    }
+    ```
+
+    Learn more about the LangGraph CLI configuration file [here](./reference/cli.md#configuration-file).
+
+5.  The `.env` file should have any environment variables needed to run your graph. This will only be used for local testing, so if you are not testing locally you can skip this step. NOTE: if you do add this, you should NOT check this into git. For this graph, we need two environment variables:
+
+    ```shell
+    ANTHROPIC_API_KEY=...
+    TAVILY_API_KEY=...
+    ```
+
+Now that we have set everything up on our local file system, we are ready to host our graph.
+
+## Test the graph build locally
+
+Before deploying to the cloud, we probably want to test the building of our graph locally. This is useful to make sure we have configured our [CLI configuration file][langgraph.json] correctly and our graph runs.
+
+In order to do this we can first install the LangGraph CLI
+
+```shell
+pip install langgraph-cli
+```
+
+We can then test our API server locally. This requires access to LangGraph closed beta. In order to run the server locally, you will need to add your `LANGSMITH_API_KEY` to the .env file so we can validate you have access to LangGraph closed beta.
+
+```shell
+langgraph up
+```
+
+This will start up the LangGraph API server locally. If this runs successfully, you should see something like:
+
+```shell
+Ready!
+- API: http://localhost:8123
+2024-06-26 19:20:41,056:INFO:uvicorn.access 127.0.0.1:44138 - "GET /ok HTTP/1.1" 200
+```
+
+You can now test this out! **Note: this local server is intended SOLELY for local testing purposes and is not performant enough for production applications, so please do not use it as such.** To test it out, you can go to another terminal window and run:
+
+```shell
+curl --request POST \
+    --url http://localhost:8123/runs/stream \
+    --header 'Content-Type: application/json' \
+    --data '{
+    "assistant_id": "agent",
+    "input": {
+        "messages": [
+            {
+                "role": "user",
+                "content": "How are you?"
+            }
+        ]
+    },
+    "metadata": {},
+    "config": {
+        "configurable": {}
+    },
+    "multitask_strategy": "reject",
+    "stream_mode": [
+        "values"
+    ]
+}'
+```
+
+If you get back a valid response, then all is functioning properly!
+
+## Deploy to Cloud
+
+### Push your code to GitHub
+
+Turn the `<my-app>` directory into a GitHub repo. You can use the GitHub CLI if you like, or just create a repo manually (if unfamiliar, instructions [here](https://docs.github.com/en/migrations/importing-source-code/using-the-command-line-to-import-source-code/adding-locally-hosted-code-to-github)).
+
+### Deploy from GitHub with LangGraph Cloud
+
+Once you have created your github repository with a Python file containing your compiled graph as well as a `langgraph.json` file containing the configuration for hosting your graph, you can head over to LangSmith and click on the 🚀 icon on the left navbar to create a new deployment. Then click the `+ New Deployment` button.
+
+![Langsmith Workflow](./img/cloud_deployment.png)
+
+**_If you have not deployed to LangGraph Cloud before:_** there will be a button that shows up saying Import from GitHub. You’ll need to follow that flow to connect LangGraph Cloud to GitHub.
+
+**_Once you have set up your GitHub connection:_** the new deployment page will look as follows:
+
+![Deployment before being filled out](./deployment/img/deployment_page.png)
+
+To deploy your application, you should do the following:
+
+1. Select your GitHub username or organization from the selector
+2. Search for your repo to deploy in the search bar and select it
+3. Choose any name
+4. In the `LangGraph API config file` field, enter the path to your `langgraph.json` file (which in this case is just `langgraph.json`)
+5. For Git Reference, you can select either the git branch for the code you want to deploy, or the exact commit SHA.
+6. If your chain relies on environment variables, add those in. They will be propagated to the underlying server so your code can access them. In this case, we need `ANTHROPIC_API_KEY` and `TAVILY_API_KEY`.
+
+Putting this all together, you should have something as follows for your deployment details:
+
+![Deployment filled out](./deployment/img/deploy_filled_out.png)
+
+Hit `Submit` and your application will start deploying!
+
+## Inspect Traces + Monitor Service
+
+### Deployments View
+
+After your deployment is complete, your deployments page should look as follows:
+
+![Deployed page](./deployment/img/deployed_page.png)
+
+You can see that by default, you get access to the `Trace Count` monitoring chart and `Recent Traces` run view. These are powered by LangSmith.
+
+You can click on `All Charts` to view all monitoring info for your server, or click on `See tracing project` to get more information on an individual trace.
+
+### Access the Docs
+
+You can access the docs by clicking on the API docs link, which should send you to a page that looks like this:
+
+![API Docs page](./deployment/img/api_page.png)
+
+You won’t actually be able to test any of the API endpoints without authorizing first. To do so, grab your Langsmith API key and add it at the top where it says `API KEY (X-API-KEY)`. You should now be able to select any of the API endpoints, click `Test Request`, enter the parameters you would like to pass, and then click `Send` to view the results of the API call.
+
+## Interact with your deployment via LangGraph Studio
+
+If you click on your deployment you should see a blue button in the top right that says `LangGraph Studio`. Clicking on this button will take you to a page that looks like this:
+
+![Studio UI before being run](./deployment/img/graph_visualization.png)
+
+On this page you can test out your graph by passing in starting states and clicking `Start Run` (this should behave identically to calling `.invoke`). You will then be able to look into the execution thread for each run and explore the steps your graph is taking to produce its output.
+
+![Studio UI once being run](./deployment/img/graph_run.png)
+
+## Use with the SDK
+
+Once you have tested that your hosted graph works as expected using LangGraph Studio, you can start using your hosted graph all over your organization by using the LangGraph SDK. Let's see how we can access our hosted graph and execute our run from a python file.
+
+First, make sure you have the SDK installed by calling `pip install langgraph_sdk`.
+
+Before using, you need to get the URL of your LangGraph deployment. You can find this in the `Deployment` view. Click the URL to copy it to the clipboard.
+
+You also need to make sure you have set up your API key properly so you can authenticate with LangGraph Cloud.
+
+```shell
+export LANGSMITH_API_KEY=...
+```
+
+The first thing to do when using the SDK is to setup our client, access our assistant, and create a thread to execute a run on:
+
+```python
+from langgraph_sdk import get_client
+
+# Replace this with the URL of your own deployed graph
+URL = "https://chatbot-23a570f3210f52a7b167f09f6158e3b3-ffoprvkqsa-uc.a.run.app"
+client = get_client(url=URL)
+
+# Search all hosted graphs
+assistants = await client.assistants.search()
+# In this example we select the first assistant since we are only hosting a single graph
+assistant = assistants[0]
+
+# We create a thread for tracking the state of our run
+thread = await client.threads.create()
+```
+
+We can then execute a run on the thread:
+
+```python
+input = {"messages":[{"role": "user", "content": "Hello! My name is Bagatur and I am 26 years old."}]}
+
+async for chunk in client.runs.stream(
+        thread['thread_id'],
+        assistant["assistant_id"],
+        input=input,
+        stream_mode="updates",
+    ):
+    if chunk.data and chunk.event != "metadata":
+        print(chunk.data)
+```
+
+    {'agent': {'messages': [{'content': "Hi Bagatur! It's nice to meet you. How can I assist you today?", 'additional_kwargs': {}, 'response_metadata': {'finish_reason': 'stop', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_9cb5d38cf7'}, 'type': 'ai', 'name': None, 'id': 'run-c89118b7-1b1e-42b9-a85d-c43fe99881cd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+## What's Next
+
+Congratulations! If you've worked your way through this tutorial you are well on your way to becoming a LangGraph Cloud expert. Here are some other resources to check out to help you out on the path to expertise:
+
+### LangGraph Cloud How-tos
+
+If you want to learn more about streaming from hosted graphs, check out the Streaming [how-to guides](how-tos/index.md#streaming).
+
+To learn more about double-texting and all the ways you can handle it in your application, read up on these [how-to guides](how-tos/index.md#double-texting).
+
+To learn about how to include different human-in-the-loop behavior in your graph, take a look at [these how-tos](how-tos/index.md#human-in-the-loop).
+
+### LangGraph Tutorials
+
+Before hosting, you have to write a graph to host. Here are some tutorials to get you more comfortable with writing LangGraph graphs and give you inspiration for the types of graphs you want to host.
+
+[This tutorial](../tutorials/customer-support/customer-support.ipynb) walks you through how to write a customer support bot using LangGraph.
+
+If you are interested in writing a SQL agent, check out [this tutorial](../tutorials/sql-agent.ipynb).
+
+Check out the [LangGraph tutorials](../tutorials/index.md) page to read about more exciting use cases.

docs/docs/cloud/reference/api/api_ref.html

@@ -0,0 +1,19 @@
+<!doctype html>
+<html>
+  <head>
+    <title>LangGraph Cloud API Reference</title>
+    <meta charset="utf-8" />
+    <meta
+      name="viewport"
+      content="width=device-width, initial-scale=1" />
+  </head>
+  <body>
+    <script id="api-reference" data-url="./openapi.json"></script>
+    <script>
+      var configuration = {}
+      document.getElementById('api-reference').dataset.configuration =
+        JSON.stringify(configuration)
+    </script>
+    <script src="https://cdn.jsdelivr.net/npm/@scalar/api-reference"></script>
+  </body>
+</html>

docs/docs/cloud/reference/api/api_ref.md

@@ -0,0 +1,5 @@
+# API Reference
+
+The LangGraph Cloud API reference is available with each deployment at the `/docs` URL path (e.g. `http://localhost:8124/docs`).
+
+Click <a href="/langgraph/cloud/reference/api/api_ref.html" target="_blank">here</a> to view the API reference.

docs/docs/cloud/reference/cli.md

@@ -0,0 +1,127 @@
+# LangGraph CLI
+The LangGraph CLI includes commands to build and run a LangGraph Cloud API server locally in [Docker](https://www.docker.com/). For development and testing, use the CLI to deploy a local API server.
+
+## Installation
+1. Ensure that Docker is installed (e.g. `docker --version`).
+2. Install the `langgraph-cli` Python package (e.g. `pip install langgraph-cli`).
+3. Run the command `langgraph --help` to confirm that the CLI is installed.
+
+[](){#langgraph.json}
+## Configuration File
+The LangGraph CLI requires a JSON configuration file with the following keys:
+
+| Key | Description |
+| --- | ----------- |
+| `dependencies` | **Required**. Array of dependencies for LangGraph Cloud API server. Dependencies can be one of the following: (1) `"."`, which will look for local Python packages, (2) `pyproject.toml`, `setup.py` or `requirements.txt` in the app directory `"./local_package"`, or (3) a package name. |
+| `graphs` | **Required**. Mapping from graph ID to path where the compiled graph or a function that makes a graph is defined. Example: <ul><li>`./your_package/your_file.py:variable`, where `variable` is an instance of `langgraph.graph.state.CompiledStateGraph`</li><li>`./your_package/your_file.py:make_graph`, where `make_graph` is a function that takes a config dictionary (`langchain_core.runnables.RunnableConfig`) and creates an instance of `langgraph.graph.state.StateGraph` / `langgraph.graph.state.CompiledStateGraph`.</li></ul> |
+| `env` | Path to `.env` file or a mapping from environment variable to its value. |
+| `python_version` | `3.11` or `3.12`. Defaults to `3.11`. |
+| `pip_config_file`| Path to `pip` config file. |
+| `dockerfile_lines` | Array of additional lines to add to Dockerfile following the import from parent image. |
+
+<div class="admonition tip">
+    <p class="admonition-title">Note</p>
+    <p>
+        The LangGraph CLI defaults to using the configuration file <strong>langgraph.json</strong> in the current directory.
+    </p>
+</div>
+
+Example:
+```json
+{
+    "dependencies": [
+        "langchain_openai",
+        "./your_package"
+    ],
+    "graphs": {
+        "my_graph_id": "./your_package/your_file.py:variable"
+    },
+    "env": "./.env"
+}
+```
+
+Example:
+```json
+{
+    "python_version": "3.11",
+    "dependencies": [
+        "langchain_openai",
+        "."
+    ],
+    "graphs": {
+        "my_graph_id": "./your_package/your_file.py:make_graph"
+    },
+    "env": {
+        "OPENAI_API_KEY": "secret-key"
+    }
+}
+```
+
+## Commands
+The base command for the LangGraph CLI is `langgraph`.
+
+**Usage**
+```
+langgraph [OPTIONS] COMMAND [ARGS]
+```
+
+### `build`
+Build LangGraph Cloud API server Docker image.
+
+**Usage**
+```
+langgraph build [OPTIONS]
+```
+
+**Options**
+
+| Option | Default | Description |
+| ------ | ------- | ----------- |
+| `--platform TEXT` | | Target platform(s) to build the Docker image for. Example: `langgraph build --platform linux/amd64,linux/arm64` |
+| `-t, --tag TEXT` | | **Required**. Tag for the Docker image. Example: `langgraph build -t my-image` |
+| `--pull / --no-pull` | `--pull` | Build with latest remote Docker image. Use `--no-pull` for running the LangGraph Cloud API server with locally built images. |
+| `-c, --config FILE` | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables. |
+| `--help` | | Display command documentation. |
+
+### `up`
+Start langgraph API server. For local testing, requires a LangSmith API key with access to LangGraph Cloud closed beta. Requires a license key for production use.
+
+**Usage**
+```
+langgraph up [OPTIONS]
+```
+
+**Options**
+
+| Option | Default | Description |
+| ------ | ------- | ----------- |
+| `--wait` | | Wait for services to start before returning. Implies --detach |
+| `--postgres-uri TEXT` | Local database | Postgres URI to use for the database. |
+| `--watch` | | Restart on file changes |
+| `--debugger-base-url TEXT` | `http://127.0.0.1:[PORT]` | URL used by the debugger to access LangGraph API. |
+| `--debugger-port INTEGER` | | Pull the debugger image locally and serve the UI on specified port |
+| `--verbose` | | Show more output from the server logs. |
+| `-c, --config FILE` | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables. |
+| `-d, --docker-compose FILE` | | Path to docker-compose.yml file with additional services to launch. |
+| `-p, --port INTEGER` | `8123` | Port to expose. Example: `langgraph test --port 8000` |
+| `--pull / --no-pull` | `pull` | Pull latest images. Use --no-pull for running the server with locally-built images. Example: `langgraph up --no-pull` |
+| `--recreate / --no-recreate` | `no-recreate` | Recreate containers even if their configuration and image haven't changed |
+| `--help` | | Display command documentation. | 
+
+### `test`
+Test your LangGraph in the cloud. The only function you can call from the SDK after testing your graph is `client.runs.stream(thread_id=None, ...)`
+
+**Usage**
+```
+langgraph test [OPTIONS]
+```
+
+**Options**
+
+| Option | Default | Description |
+| ------ | ------- | ----------- |
+| `--verbose` | | Show more output from the server logs. |
+| `-c, --config FILE` | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables. |
+| `-p, --port INTEGER` | `8123` | Port to expose. Example: `langgraph test --port 8000` |
+| `--pull / --no-pull` | `pull` | Pull latest images. Use --no-pull for running the server with locally-built images. Example: `langgraph up --no-pull` |
+| `--help` | | Display command documentation. |

docs/docs/cloud/reference/env_var.md

@@ -0,0 +1,13 @@
+# Environment Variables
+
+The LangGraph Cloud API supports specific environment variables for configuring a deployment.
+
+## `LANGGRAPH_AUTH_TYPE`
+
+Type of authentication for the LangGraph Cloud API deployment. Valid values: `langsmith`, `noop`.
+
+For deployments to LangGraph Cloud, this environment variable is set automatically. For local development or deployments where authentication is handled externally (e.g. self-hosted), set this environment variable to `noop`.
+
+## `N_JOBS_PER_WORKER`
+
+Number of jobs per worker for the LangGraph Cloud task queue. Defaults to `10`.

docs/docs/cloud/reference/sdk/python_sdk_ref.md

@@ -0,0 +1,79 @@
+# Python SDK Reference
+
+The Python SDK provides four underlying clients (`AssistantsClient`, `ThreadsClient`, `RunsClient`, `CronClient`) that correspond to each of the core API models and one top-level client (`LangGraphClient`) to access them.
+
+## get_client()
+
+The `get_client()` function returns the top-level `LangGraphClient` client.
+
+```python
+from langgraph_sdk import get_client
+
+# get top-level LangGraphClient
+client = get_client(url="http://localhost:8123")
+
+# example usage: client.<model>.<method_name>()
+assistants = await client.assistants.get(assistant_id="some_uuid")
+```
+
+::: langgraph_sdk.client.get_client
+    handler: python
+
+## LangGraphClient
+
+`LangGraphClient` is the top-level client for accessing `AssistantsClient`, `ThreadsClient`, `RunsClient`, and `CronClient`.
+
+::: langgraph_sdk.client.LangGraphClient
+    handler: python
+
+## AssistantsClient
+
+Access the `AssistantsClient` via the `LangGraphClient.assistants` attribute.
+```python
+from langgraph_sdk import get_client
+
+client = get_client(url="http://localhost:8123")
+await client.assistants.<method_name>()
+```
+
+::: langgraph_sdk.client.AssistantsClient
+    handler: python
+
+## ThreadsClient
+
+Access the `ThreadsClient` via the `LangGraphClient.threads` attribute.
+```python
+from langgraph_sdk import get_client
+
+client = get_client(url="http://localhost:8123")
+await client.threads.<method_name>()
+```
+
+::: langgraph_sdk.client.ThreadsClient
+    handler: python
+
+## RunsClient
+
+Access the `RunsClient` via the `LangGraphClient.runs` attribute.
+```python
+from langgraph_sdk import get_client
+
+client = get_client(url="http://localhost:8123")
+await client.runs.<method_name>()
+```
+
+::: langgraph_sdk.client.RunsClient
+    handler: python
+
+## CronClient
+
+Access the `CronClient` via the `LangGraphClient.crons` attribute.
+```python
+from langgraph_sdk import get_client
+
+client = get_client(url="http://localhost:8123")
+await client.crons.<method_name>()
+```
+
+::: langgraph_sdk.client.CronClient
+    handler: python