langchain-ai/langchain - CodSpeed

langchain

Blog Docs Changelog

Performance History

Latest Results

fix(core): merge tool_call_chunks without index in streaming Fixes #34654 When using agent.stream() with stream_mode=["messages"], tool_call_chunks with index=None were not merging correctly, creating multiple partial tool_calls with empty names that caused 422 errors from OpenAI API. Modified merge_lists() to handle tool_call_chunks without valid index by: - Merging chunks with same non-empty id when continuation (empty name) - Sequential merging for chunks with empty ids (streaming fragments) - Preserving existing behavior for chunks with valid index Added comprehensive unit tests covering edge cases including multiple tool calls, interleaved chunks, and sequential streaming scenarios. All existing tests pass without regression.

686f6c61:fix/tool-call-chunks-merge-without-index

7 hours ago

why-tracing-runtime

8 hours ago

why-tracing-runtime

8 hours ago

Merge branch 'master' into feat/ollama_log_probs

keenborder786:feat/ollama_log_probs

8 hours ago

Merge branch 'master' into feat/tracing

keenborder786:feat/tracing

8 hours ago

Merge branch 'master' into builtin_middleware

keenborder786:builtin_middleware

8 hours ago

feat(core): add more file extensions to ignore in HTML link extraction (#34552) # feat(core): add more file extensions to ignore in HTML link extraction ## Description This PR enhances the HTML link extraction utility in `libs/core/langchain_core/utils/html.py` by expanding the `SUFFIXES_TO_IGNORE` list to include additional common binary file extensions: - `.webp` - `.pdf` - `.docx` - `.xlsx` - `.pptx` - `.pptm` These file types are non-HTML, non-crawlable resources. Ignoring them prevents `find_all_links` and `extract_sub_links` from mistakenly treating such binary assets as navigable links. This improves link filtering, reduces unnecessary crawling, and aligns behavior with typical web scraping expectations. ## Summary of Changes - **Updated** `libs/core/langchain_core/utils/html.py`: Added `.webp`, `.pdf`, `.docx`, `.xlsx`, `.pptx`, `.pptm` to `SUFFIXES_TO_IGNORE`. ## Related Issues N/A ## Verification - `ruff check libs/core/langchain_core/utils/html.py`: **Passed** - `mypy libs/core/langchain_core/utils/html.py`: **Passed** - `pytest libs/core/tests/unit_tests/utils/test_html.py`: **Passed** (11 tests) --------- Co-authored-by: Mason Daugherty <mason@langchain.dev>

master

10 hours ago

Merge branch 'master' into enhancement/ignore-more-suffixes

Aman071106:enhancement/ignore-more-suffixes

10 hours ago

Active Branches

fix(core): merge tool_call_chunks without index in streaming

last run

7 hours ago

-4%

fix: don't trace injected args only found in signature

last run

8 hours ago

+3%

feat(ollama): logprobs support in Ollama

last run

8 hours ago

0%

© 2026 CodSpeed Technology

Home Terms Privacy Docs