Commit Graph
1409 Commits
Author SHA1 Message Date
William Fu-Hinthorn e9d62944d3 0.2.61 2025-01-05 14:42:25 -08:00
William FHandGitHub 4798443e31 Import TypedDict from typing_extensions, add ruff rule (#2910)
Within `libs/langgraph`, change all `TypedDict` imports to come from
`typing_extensions` rather than `typing`, as `pydantic` doesn't like the
latter.

Additionally, add a ruff rule to ban these imports too (so this doesn't
regress).

Solves  #2909.
2025-01-04 04:58:43 -08:00
Ramón VargasandGitHub 577f95bd50 Merge branch 'main' into patch-1 2025-01-04 13:26:54 +01:00
Ramón VargasandGitHub 687ee02509 Update client.py
Typo change in function doc
2025-01-03 18:40:15 +01:00
William Fu-Hinthorn 451bc038b6 Support multiple args in @task's 2025-01-03 07:56:27 -08:00
Nuno CamposandGitHub c865e8c070 Update README.md 2025-01-02 10:01:35 +00:00
Nuno CamposandGitHub d74ec2c2de Bubble up stack close task (#2913) 2025-01-02 09:54:43 +00:00
Nuno CamposandGitHub f70bfc6d87 Fix stream_mode=updates for cases where one node returns multiple updates for same key (#2903) 2025-01-02 09:54:06 +00:00
David DuongandGitHub c86f0af107 fix(sdk): Fix SDK Command.update type (#2901)
Align typing with JS:


https://github.com/langchain-ai/langgraphjs/blob/main/libs/langgraph/src/constants.ts#L226
2025-01-01 15:55:58 +01:00
William Fu-Hinthorn c6ee807de5 Bubble up stack close task 2025-01-01 05:41:57 -08:00
Johannes Mario Meissner 7256752f48 Import TypedDict from typing_extensions, add ruff rule 2024-12-31 22:14:16 +09:00
Nuno Campos dac84951aa Fix stream_mode=updates for cases where one node returns multiple updates for same key 2024-12-30 20:10:59 +00:00
Nuno Campos 400d83708a Fix 2024-12-30 20:01:35 +00:00
Nuno Campos 1d9c7ef461 Fix 2024-12-30 19:29:14 +00:00
Nuno Campos 01e5ecedfd Remove assertion of order 2024-12-30 19:26:18 +00:00
Nuno Campos 76199701b0 Add more tests for async cancellation 2024-12-30 18:56:56 +00:00
jacoblee93 2766fccb5b Bump Python version 2024-12-30 10:30:50 -08:00
jacoblee93 6aef3e0117 Update Python types too 2024-12-30 10:29:01 -08:00
jacoblee93 c5023ba147 Modify type 2024-12-30 10:22:06 -08:00
jacoblee93 9a9fe2fdec Update JS SDK command types 2024-12-30 10:14:51 -08:00
Vadym BardaandGitHub a3c5b8fc37 checkpoint-postgres: release 2.0.9 (#2849) 2024-12-20 17:47:20 -05:00
Vadym BardaandGitHub 44ee0199fd checkpoint postgres: add a shallow checkpointer (#2826)
This PR adds a "shallow" version of `PostgresSaver` checkpointer that
ONLY stores the most recent checkpoint and does NOT retain any history.
It is meant to be a light-weight drop-in replacement for the
PostgresSaver that supports most of the LangGraph persistence
functionality with the exception of time travel.
2024-12-20 17:51:20 +00:00
Yassin NouhandGitHub f520a38d30 docs: missing docstring for aupdate_state method (#2435) 2024-12-20 09:06:29 -05:00
Vadym BardaandGitHub 506539ac9d langgraph: actually run test_large_cases_async (#2843) 2024-12-19 22:25:22 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>Vadym Barda
ebb2823be0 build(deps-dev): bump tornado from 6.4.1 to 6.4.2 in /libs/langgraph (#2814)
Bumps [tornado](https://github.com/tornadoweb/tornado) from 6.4.1 to
6.4.2.
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/tornadoweb/tornado/blob/v6.4.2/docs/releases.rst">tornado's
changelog</a>.</em></p>
<blockquote>
<h1>Release notes</h1>
<p>.. toctree::
:maxdepth: 2</p>
<p>releases/v6.4.2
releases/v6.4.1
releases/v6.4.0
releases/v6.3.3
releases/v6.3.2
releases/v6.3.1
releases/v6.3.0
releases/v6.2.0
releases/v6.1.0
releases/v6.0.4
releases/v6.0.3
releases/v6.0.2
releases/v6.0.1
releases/v6.0.0
releases/v5.1.1
releases/v5.1.0
releases/v5.0.2
releases/v5.0.1
releases/v5.0.0
releases/v4.5.3
releases/v4.5.2
releases/v4.5.1
releases/v4.5.0
releases/v4.4.3
releases/v4.4.2
releases/v4.4.1
releases/v4.4.0
releases/v4.3.0
releases/v4.2.1
releases/v4.2.0
releases/v4.1.0
releases/v4.0.2
releases/v4.0.1
releases/v4.0.0
releases/v3.2.2
releases/v3.2.1
releases/v3.2.0
releases/v3.1.1
releases/v3.1.0
releases/v3.0.2
releases/v3.0.1
releases/v3.0.0
releases/v2.4.1
releases/v2.4.0</p>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/tornadoweb/tornado/commit/a5ecfab15e52202a46d34638aad93cddca86d87b"><code>a5ecfab</code></a>
Bump version to 6.4.2</li>
<li><a
href="https://github.com/tornadoweb/tornado/commit/bc7df6bafdec61155e7bf385081feb205463857d"><code>bc7df6b</code></a>
Fix tests with Twisted 24.7.0</li>
<li><a
href="https://github.com/tornadoweb/tornado/commit/d5ba4a1695fbf7c6a3e54313262639b198291533"><code>d5ba4a1</code></a>
httputil: Fix quadratic performance of cookie parsing</li>
<li>See full diff in <a
href="https://github.com/tornadoweb/tornado/compare/v6.4.1...v6.4.2">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=tornado&package-manager=pip&previous-version=6.4.1&new-version=6.4.2)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
You can disable automated security fix PRs for this repo from the
[Security Alerts
page](https://github.com/langchain-ai/langgraph/network/alerts).

</details>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Vadym Barda <vadym@langchain.dev>
2024-12-18 19:36:20 -05:00
William FHandGitHub 2855caa3eb Fix config cli type from Path -> str (#2771)
Config parameter in `dev` was typed as pathlib.Path, but it is actually
a string. We need to manually create a Path from the string when parsing
the config.

FIxes #2647
2024-12-18 15:25:15 -08:00
William Fu-Hinthorn 1709cd3fb5 concept 2024-12-18 15:08:19 -08:00
William Fu-Hinthorn 06e1e4ed12 Update cross-linking 2024-12-18 14:52:02 -08:00
William FHandGitHub f89fe49f99 Merge branch 'main' into wfh/docs/auth 2024-12-18 14:26:39 -08:00
William Fu-Hinthorn 7f0bfdc139 Feedback 2024-12-18 14:15:54 -08:00
William FHandGitHub d79b1a61e8 Merge branch 'main' into fix-cli-path 2024-12-18 12:34:39 -08:00
William Fu-Hinthorn e227f6ce83 Bump version 2024-12-18 12:30:06 -08:00
William Fu-Hinthorn 8a1a11fde5 [CLI] Update min bound for langgraph-api 2024-12-18 12:29:17 -08:00
6b45a281c1 fix example in docs of state_schema in create_react_agent (#2109)
because in
```python
    def call_model(
        state: AgentState,
        config: RunnableConfig,
    )
...
        if (
            (
                "remaining_steps" not in state
                and state["is_last_step"]
                and has_tool_calls
            )
```

https://github.com/langchain-ai/langgraph/blob/c0b56bf60d84ed435609c35b0691cd0305ceae78/libs/langgraph/langgraph/prebuilt/chat_agent_executor.py#L543
the AgentState requires is_last_step to have a default value, like
`False`, and `IsLastStep` can satisfy it.

---------

Co-authored-by: Vadym Barda <vadym@langchain.dev>
2024-12-18 11:41:52 -08:00
BagaturandWilliam Fu-Hinthorn 532bc71c11 langgraph[patch]: format messages in state (#2199)
Add `format` flag to `add_messages` which allows you to specify if the
contents of messages in state should be formatted in a particular way.
PR only adds support for OpenAI style contents. Helpful if you're using
different models at different nodes and want a unified messages format
to interact with when you manually update messages.
2024-12-18 11:41:52 -08:00
Nuno CamposandWilliam Fu-Hinthorn ef88b805a7 0.2.60 2024-12-18 11:41:52 -08:00
Nuno CamposandWilliam Fu-Hinthorn 7e8a68f0f0 Fix 2024-12-18 11:41:52 -08:00
Nuno CamposandWilliam Fu-Hinthorn e20bd15580 lib: Fix incorrect default for Command.update
- this should not default to empty tuple, it should default to None
2024-12-18 11:41:52 -08:00
William Fu-Hinthorn 51c57cc819 [SDK] Add studio user object 2024-12-18 11:41:52 -08:00
William FHandGitHub 77fba7a571 Merge branch 'main' into wfh/sdk/studio_user 2024-12-18 11:28:21 -08:00
William Fu-Hinthorn 60232eadc4 [SDK] Add studio user object 2024-12-18 11:21:13 -08:00
1a6c3114f3 fix example in docs of state_schema in create_react_agent (#2109)
because in
```python
    def call_model(
        state: AgentState,
        config: RunnableConfig,
    )
...
        if (
            (
                "remaining_steps" not in state
                and state["is_last_step"]
                and has_tool_calls
            )
```

https://github.com/langchain-ai/langgraph/blob/c0b56bf60d84ed435609c35b0691cd0305ceae78/libs/langgraph/langgraph/prebuilt/chat_agent_executor.py#L543
the AgentState requires is_last_step to have a default value, like
`False`, and `IsLastStep` can satisfy it.

---------

Co-authored-by: Vadym Barda <vadym@langchain.dev>
2024-12-18 12:46:33 -05:00
BagaturandGitHub 4f1bf4fa7a langgraph[patch]: format messages in state (#2199)
Add `format` flag to `add_messages` which allows you to specify if the
contents of messages in state should be formatted in a particular way.
PR only adds support for OpenAI style contents. Helpful if you're using
different models at different nodes and want a unified messages format
to interact with when you manually update messages.
2024-12-18 17:19:04 +00:00
Nuno Campos 3d85f2296c 0.2.60 2024-12-18 13:45:32 +00:00
Nuno Campos 39281c866d Fix 2024-12-18 13:28:22 +00:00
Nuno Campos 4c3a38d324 lib: Fix incorrect default for Command.update
- this should not default to empty tuple, it should default to None
2024-12-18 13:15:38 +00:00
William FHandGitHub 36fa8e0097 Update ref docs (#2802) 2024-12-17 11:54:32 -08:00
William Fu-Hinthorn bcb11640a5 Update AuthContext 2024-12-17 11:46:30 -08:00
William Fu-Hinthorn b6c3a0d0fd Update wording 2024-12-17 11:37:25 -08:00
William Fu-Hinthorn 8c63cc1778 Add excption docs 2024-12-17 11:22:54 -08:00