langchain-ai/langchain

langchain

Performance History

Latest Results

fix(core): forward `feedback_config` to `create_feedback` in `EvaluatorCallbackHandler` Closes #31802 Co-authored-by: Cursor <cursoragent@cursor.com>

OkiriGabriel:mdrxy/core/forward-feedback-config-to-create-feedback

3 hours ago

fix(core): avoid `dict` shadowing in language models (#38480) Fixes #37835 --- When Pydantic collects fields for a `BaseLanguageModel` subclass that defines a `dict()` method, inherited annotations can resolve `dict` against the subclass namespace instead of the builtin. With Pydantic 2.14.0a1 this caused `BaseLanguageModel.metadata: dict[str, Any] | None` to fail during rebuild/import with `'function' object is not subscriptable`. This qualifies the inherited `metadata` field annotation as `builtins.dict[...]`, matching the existing pattern in chat models, and documents why the runtime import cannot move behind `TYPE_CHECKING`. It also adds a regression test that rebuilds a `BaseLanguageModel` subclass with a `dict()` method so core catches this failure before partner packages hit it at import time. Related to #37924, which hardens `_create_subset_model_v2`; this PR fixes the `BaseLanguageModel` class-construction failure directly.

master

3 hours ago

fix(core): avoid `dict` shadowing in language models

mdrxy/core/pydantic-dict-shadowing

3 hours ago

stop overriding caller's ls_integration in ls trace

hariharish/ls_integration

2 days ago

fix(langchain): avoid orphan ToolMessages in summarization cutoff Co-authored-by: Cursor <cursoragent@cursor.com>

Chessing234:Chessing234/langchain/summarization-orphan-tool-cutoff

2 days ago

test(core): remove stale xfail markers from passing tests These tests now pass reliably; remove outdated expected-failure markers. Closes #38266 Co-authored-by: Cursor <cursoragent@cursor.com>

Chessing234:Chessing234/core/fix-multimodal-token-counting

2 days ago

fix(core): `_parse_google_docstring` mishandling continuation lines with colons (#35680) ## Description `_parse_google_docstring` incorrectly parses multi-line argument descriptions when a continuation line contains a colon. The continuation line is treated as a new argument definition instead of being appended to the current argument's description. ### Example ```python def search(query: str, top_k: int = 5) -> str: """Search the knowledge base. Args: query: The search query to use for finding things: important ones top_k: Number of results to return """ ``` **Before (broken):** The parser creates 3 args: `query`, `for finding things`, `top_k` **After (fixed):** The parser correctly creates 2 args: `query` (with full description including "for finding things: important ones"), `top_k` ### Root Cause The parser used `if ":" in line` to detect new argument lines without considering indentation. In Google-style docstrings, continuation lines have deeper indentation than argument definition lines. ### Fix Detect the base indentation level from the first argument line and treat any line with deeper indentation as a continuation of the current argument's description, regardless of whether it contains a colon. ## Issue Fixes #35679 ## Dependencies None. ## Testing Added 4 unit tests in `test_function_calling.py::TestParseGoogleDocstring`: - `test_continuation_line_with_colon` — the core bug scenario - `test_simple_args_still_work` — regression check for basic args - `test_continuation_line_without_colon` — multi-line descriptions without colons - `test_multiple_continuation_lines_with_colons` — multiple continuation lines each containing colons All tests pass locally with Python 3.12. --------- Co-authored-by: gambletan <ethanchang32@gmail.com> Co-authored-by: Mason Daugherty <github@mdrxy.com>

master

3 days ago

chore(langchain): add types in agent middleware tests (#38188) Co-authored-by: Mason Daugherty <github@mdrxy.com> Co-authored-by: Mason Daugherty <mason@langchain.dev>

master

3 days ago

Latest Branches

fix(core): forward `feedback_config` to `create_feedback` in `EvaluatorCallbackHandler`#38481

3 hours ago

57ad89d

OkiriGabriel:mdrxy/core/forward-feedback-config-to-create-feedback

-1%

fix(core): avoid `dict` shadowing in language models#38480

3 hours ago

be13680

mdrxy/core/pydantic-dict-shadowing

fix(core): don't override a caller-supplied `ls_integration`#38438

2 days ago

d7bca50

hariharish/ls_integration

Home Terms Privacy Docs