langchain-ai/langchain - CodSpeed

langchain

Blog Docs Changelog

Performance History

Latest Results

fix(core): honor low-detail images before estimating from dimensions

saike148:fix/image-token-resolution

4 hours ago

fix(model-profiles): update stale CI expectations Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>

bot/refresh-model-profiles

11 hours ago

fix(core): avoid mutation in google-genai standard content (#40023) Co-authored-by: Hotragn Pettugani <103170876+Hotragn@users.noreply.github.com>

master

12 hours ago

cc/content-block-mutation

12 hours ago

cc/content-block-mutation

12 hours ago

fix(core): avoid mutation in bedrock converse standard content (#40022) Co-authored-by: Zhewen Tan <127607634+tandede@users.noreply.github.com>

master

13 hours ago

avoid mutation in bedrock converse standard content

cc/bedrock-content-block-mutation

13 hours ago

fix(langchain): include model destination in agent tool routing (#38355) Fixes #38351 This PR fixes `create_agent` conditional edge routing when middleware injects synthetic `ToolMessage` objects for already-satisfied tool calls. Previously, `_make_model_to_tools_edge` could return the model loop entry destination, but that destination was not always included in `model_to_tools_destinations`. This caused LangGraph to raise `KeyError("model")`. Changes: * Include `loop_entry_node` in `model_to_tools_destinations`. * Add a regression test covering synthetic `ToolMessage` injection through `wrap_model_call` middleware using `ExtendedModelResponse` and `Command(update={"messages": ...})`. Test: * `uv run --group test pytest tests/unit_tests/agents/middleware/core/test_framework.py::test_create_agent_synthetic_tool_messages_reroute_to_model` Result: * Passed --------- Co-authored-by: ccurme <26529506+ccurme@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>

master

13 hours ago

Latest Branches

0%

fix(core): count image tokens from image dimensions#39912

9 hours ago

b2079b5

saike148:fix/image-token-resolution

0%

chore(model-profiles): refresh model profile data#40009

11 hours ago

079cf9b

bot/refresh-model-profiles

0%

fix(core): avoid mutation in google-genai standard content#40023

12 hours ago

4e7c85c

cc/content-block-mutation

© 2026 CodSpeed Technology

Home Terms Privacy Docs