langchain-ai/langchain - CodSpeed

langchain

Blog Docs Changelog

Performance History

Latest Results

fix(openai): add type: message to Responses API input items (#35693)

master

3 hours ago

fix formatting issues from 35851

giulio-leone:fix/responses-api-message-type

3 hours ago

fix: drop zip(strict=True) for Python 3.9 compatibility zip(strict=True) was introduced in Python 3.10, but langchain-core supports Python >=3.9. Remove the strict parameter — the invariant (equal-length lists) is guaranteed by the retry loop logic.

giulio-leone:fix/runnable-retry-batch-corruption-35475-v2

3 hours ago

fix(core): fix nested subgraph rendering for 3+ levels with draw_mermaid (fixes #35492) Root cause: in the "empty subgraphs" section of draw_mermaid, the guard ``if ":" not in prefix`` silently skipped any prefix that contained a colon (e.g. "parent:child"). For 3+ level nesting where no subgraph has internal edges, every prefix is multi-level, so no subgraph boxes were ever emitted — nodes appeared flat with escaped colons ("parent\3achild\3agrandchild"). Fix: replace the flat loop with a recursive helper that expands every prefix into its ancestor levels ("parent" and "parent:child" from "parent:child"), then recurses depth-first to produce properly nested subgraph/end blocks. 2-level nesting (existing behaviour) is unchanged.

shivamtiwari3:fix/nested-subgraph-mermaid-3-plus-levels

4 hours ago

chore: bump orjson from 3.11.5 to 3.11.6 in /libs/partners/nomic (#35859)

master

5 hours ago

fix(core): filter _DirectlyInjectedToolArg params from tool schema to prevent Pydantic validation errors Root cause: `_filter_schema_args` in `structured.py` did not filter `_DirectlyInjectedToolArg` parameters (e.g., `ToolRuntime`) from the auto-generated Pydantic schema. The schema used `extra="forbid"`, so passing a `ToolRuntime` dataclass instance to `model_validate` produced a `ValidationError` (`type=dataclass_type`) because Pydantic could not validate the dataclass. Fix: two-part change so the inferred schema excludes directly-injected params and `_parse_input` strips those values before validation (re-injecting them afterwards via `_injected_args_keys`): 1. `_filter_schema_args`: calls `_is_directly_injected_arg_type` to exclude `_DirectlyInjectedToolArg` annotated params. 2. `_parse_input`: builds `tool_input_for_validation` that omits any value that is a `_DirectlyInjectedToolArg` instance before calling `model_validate`, avoiding the `extra="forbid"` rejection. Fixes langchain-ai/langgraph#6431

shivamtiwari3:fix/filter-directly-injected-tool-args-from-schema

7 hours ago

fix(core): create independent dicts in BaseLLM metadata_list construction Replace [{}] * len(prompts) with [{} for _ in range(len(prompts))] to prevent shared mutable dict references. The old pattern creates N references to the same dict object, so if any downstream code mutates one entry's metadata dict, all entries are silently corrupted. This fix applies to both sync (generate) and async (agenerate) paths. Fixes: langchain-ai/langchain#35900

LincolnBurrows2017:fix/shared-mutable-dict-bug

13 hours ago

fix(core): use list comprehension to avoid shared dict refs in metadata_list `[{}] * len(prompts)` creates N references to the same dict object. If any downstream code mutates one entry, all entries are silently corrupted. Replace with `[{} for _ in range(len(prompts))]` to create independent dicts. Fixes both the sync (`generate`) and async (`agenerate`) paths. Note: the related `[callback_manager] * len(prompts)` pattern in the single-callback else branch is a separate pre-existing issue tracked independently. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

roli-lpci:fix/shared-metadata-dict-refs

15 hours ago

Active Branches

fix(core): prevent output corruption in RunnableRetry.batch when partial retries succeed

last run

3 hours ago

+1%

fix(core): make `self` positional-only in `_run`/`_arun` to allow "self" as tool input key

last run

16 hours ago

+2%

fix(openai): enable bind_tools after with_structured_output

last run

22 hours ago

0%

© 2026 CodSpeed Technology

Home Terms Privacy Docs