WEBDIENSTE/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-08-30 19:59:40 +02:00
Code Issues Packages Projects Releases Wiki Activity
6,621 Commits 322 Branches 572 Tags
90865e2af9d75f709f5ebe814b1dfbbbf8065da9
Commit Graph
6621 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Quanzheng Long 90865e2af9 simplify 2026-03-17 18:24:37 -07:00
Quanzheng Long e13004da77 stream-draft 2026-03-17 16:12:16 -07:00
Quanzheng Long 5a9264d124 v2 2026-03-16 16:53:09 -07:00
Quanzheng Long efa86a6b14 fix 2026-03-16 16:52:05 -07:00
Quanzheng Long f9866186d9 makefile 2026-03-16 16:46:33 -07:00
Quanzheng Long bfdd7deb60 makefile 2026-03-16 16:41:14 -07:00
Quanzheng Long 09c8bb7c1c revert 2026-03-16 16:34:17 -07:00
Quanzheng Long 84d59adcd8 publish 2026-03-16 16:31:02 -07:00
Quanzheng Long 841ebf0c77 publish 2026-03-16 16:18:25 -07:00
Quanzheng Long 4f5b775819 no-finish-node 2026-03-16 15:55:35 -07:00
Quanzheng Long 76bee17ec4 fix 2026-03-14 17:58:28 -07:00
Quanzheng Long d4335683e6 rewrite-state-graph 2026-03-14 17:56:30 -07:00
Quanzheng Long b43107ec99 rewrite-state-graph 2026-03-14 17:50:55 -07:00
Quanzheng Long 3987f9cd63 rewrite-state-graph 2026-03-14 17:47:33 -07:00
Quanzheng Long 2bbc3bb1da more 2026-03-14 11:30:25 -07:00
Quanzheng Long b3474d2db1 more 2026-03-14 10:29:42 -07:00
Quanzheng Long 56e9fe1b10 more 2026-03-13 23:31:52 -07:00
Quanzheng Long 1b3d075dbb tokio-rewrite 2026-03-13 23:16:40 -07:00
Quanzheng Long c2a9661d2a more 2026-03-13 21:54:02 -07:00
Quanzheng Long 9e723642c0 more 2026-03-13 15:46:07 -07:00
Quanzheng Long 7c0a9275f9 more 2026-03-13 15:44:41 -07:00
Quanzheng Long 783b3d3435 more 2026-03-13 15:40:49 -07:00
Quanzheng Long 597b3402e6 optimizeUpdateState 2026-03-13 15:07:41 -07:00
Quanzheng Long 54b723775c more 2026-03-13 14:23:54 -07:00
Quanzheng Long 93c4a0a2d5 more 2026-03-13 14:14:58 -07:00
Quanzheng Long a5b90fbb95 more 2026-03-13 13:52:28 -07:00
Quanzheng Long 85272db354 more 2026-03-13 13:50:52 -07:00
Quanzheng Long d7614999b0 more 2026-03-13 13:44:44 -07:00
Quanzheng Long af5f74f2ad more 2026-03-13 13:27:32 -07:00
Quanzheng Long 708c0dff7f more 2026-03-13 13:21:11 -07:00
Quanzheng Long d50801d871 more 2026-03-13 13:16:11 -07:00
Quanzheng Long 0327a86b80 rename 2026-03-12 22:42:47 -07:00
Quanzheng Long 13847a32c0 refactor-go 2026-03-12 22:41:32 -07:00
Quanzheng Long 03ad7a011c imp 2026-03-12 21:48:32 -07:00
Quanzheng Long 896c1a8054 draft 2026-03-12 18:44:18 -07:00
Quanzheng Long 388d6b3593 done 2026-03-12 16:05:12 -07:00
Quanzheng Long 667b679694 more 2026-03-12 15:58:42 -07:00
Quanzheng Long ccb9f4c41a more 2026-03-12 15:58:21 -07:00
Quanzheng Long 789be99634 ref 2026-03-12 15:44:35 -07:00
Quanzheng Long e33842ff54 mre 2026-03-12 15:39:46 -07:00
Quanzheng Long 89d37a0f9b more 2026-03-12 15:38:22 -07:00
Quanzheng Long 8f717d3874 more 2026-03-12 15:27:25 -07:00
Quanzheng Long 508193272a anyof 2026-03-12 15:15:49 -07:00
Quanzheng Long 788ae6cb72 rm 2026-03-12 15:03:58 -07:00
Quanzheng Long b2dca399e8 1 2026-03-12 13:31:54 -07:00
Quanzheng Long 4b2167dd25 1stpass 2026-03-12 13:13:08 -07:00
Quanzheng Long be46e91180 doc 2026-03-12 12:37:34 -07:00
Quanzheng Long bbb308259b poc 2026-03-12 12:31:46 -07:00
Sydney RunkleandGitHub 14ce607111 chore: remove md notes (#7103) 2026-03-10 08:44:55 -04:00
Sydney RunkleandGitHub 3330ccdea4 release(langgraph): 1.1 (#7102) 
exciting!

relnotes preview:

# LangGraph 1.1.0 Release Notes

## Type-Safe Streaming & Invoke

LangGraph 1.1 introduces `version="v2"` — a new opt-in streaming format
that brings full type safety to `stream()`, `astream()`, `invoke()`, and
`ainvoke()`.

### What's changing

**v1 (default, unchanged):** `stream()` yields bare tuples like
`(stream_mode, data)` or just `data`. `invoke()` returns a plain `dict`.
Interrupts are mixed into the output dict under `"__interrupt__"`.

**v2 (opt-in):** `stream()` yields strongly-typed `StreamPart` dicts
with `type`, `ns`, `data`, and (for values) `interrupts` fields.
`invoke()` returns a `GraphOutput` object with `.value` and
`.interrupts` attributes. When your state schema is a Pydantic model or
dataclass, outputs are automatically coerced to the correct type.

### `invoke()` / `ainvoke()` with `version="v2"`

```python
from langgraph.types import GraphOutput

result = graph.invoke({"input": "hello"}, version="v2")

# result is a GraphOutput, not a dict
assert isinstance(result, GraphOutput)
result.value       # your output — dict, Pydantic model, or dataclass
result.interrupts  # tuple[Interrupt, ...], empty if none occurred
```

With a non-`"values"` stream mode, `invoke(..., stream_mode="updates",
version="v2")` returns `list[StreamPart]` instead of `list[tuple]`.

### `stream()` / `astream()` with `version="v2"`

```python
for part in graph.stream({"input": "hello"}, version="v2"):
    if part["type"] == "values":
        part["data"]        # OutputT — full state
        part["interrupts"]  # tuple[Interrupt, ...]
    elif part["type"] == "updates":
        part["data"]        # dict[str, Any]
    elif part["type"] == "messages":
        part["data"]        # tuple[BaseMessage, dict]
    elif part["type"] == "custom":
        part["data"]        # Any
    elif part["type"] == "tasks":
        part["data"]        # TaskPayload | TaskResultPayload
    elif part["type"] == "debug":
        part["data"]        # DebugPayload
```

Each stream mode has its own `TypedDict` — `ValuesStreamPart`,
`UpdatesStreamPart`, `MessagesStreamPart`, `CustomStreamPart`,
`CheckpointStreamPart`, `TasksStreamPart`, `DebugStreamPart` — all
importable from `langgraph.types`. The union type `StreamPart` is a
discriminated union on `part["type"]`, enabling full type narrowing in
editors and type checkers.

### Pydantic & dataclass output coercion

When your graph's state schema is a Pydantic model or dataclass,
`version="v2"` automatically coerces outputs to the declared type:

```python
from pydantic import BaseModel

class MyState(BaseModel):
    answer: str
    count: int

graph = StateGraph(MyState)
# ... build graph ...
compiled = graph.compile()

result = compiled.invoke({"answer": "", "count": 0}, version="v2")
assert isinstance(result.value, MyState)  # not a dict!
```

### Backward compatibility

- **Default is still `version="v1"`** — existing code works without
changes.
- To make migration easier, `GraphOutput` supports old-style best-effort
access to graph values and interrupts. Dict-style access
(`result["key"]`, `"key" in result`, `result["__interrupt__"]`) still
works and delegates to `result.value` / `result.interrupts` under the
hood. However, this is **deprecated** and emits a
`LangGraphDeprecatedSinceV11` warning. It will be removed in v3.0 —
migrate to `result.value` and `result.interrupts` at your convenience.

```python
result = graph.invoke({"input": "hello"}, version="v2")

# Old style — still works, but deprecated
result["input"]          # delegates to result.value["input"]
result["__interrupt__"]  # delegates to result.interrupts
"input" in result        # delegates to "input" in result.value

# New style — preferred
result.value["input"]
result.interrupts
```

## Migration Guide

1. **No action required** — `version="v1"` remains the default. All
existing code continues to work.
2. **Adopt v2 incrementally** — Add `version="v2"` to individual
`invoke()`/`stream()` calls to get typed outputs.
3. **Use typed imports** — Import `GraphOutput`, `StreamPart`, and
individual part types from `langgraph.types` for type-safe code.
1.1.0 		2026-03-10 12:41:30 +00:00