Fixes#34517
Supersedes #34557, #34570
Fixes token inflation in `SummarizationMiddleware` that caused context
window overflow during summarization.
**Root cause:** When formatting messages for the summary prompt,
`str(messages)` was implicitly called, which includes all Pydantic
metadata fields (`usage_metadata`, `response_metadata`,
`additional_kwargs`, etc.). This caused the stringified representation
to use ~2.5x more tokens than `count_tokens_approximately` estimates.
**Problem:**
- Summarization triggers at 85% of context window based on
`count_tokens_approximately`
- But `str(messages)` in the prompt uses 2.5x more tokens
- Results in `ContextLengthExceeded`
**Fix:** Use `get_buffer_string()` to format messages, which produces
compact output:
```
Human: What's the weather?
AI: Let me check...[tool_calls]
Tool: 72°F and sunny
```
Instead of verbose Pydantic repr:
```python
[HumanMessage(content='What's the weather?', additional_kwargs={}, response_metadata={}), ...]
```
Fixed typo in ImportError messages where "langchain experiment" should
be "langchain_experimental" for consistency with the actual package
name.
This helps improve clarity for users who encounter these error messages
when trying to use deprecated tools that have moved to the
langchain_experimental package.
Related issues: #13858, #13859
Co-authored-by: Ademola <ademicho@gmail>
**Description:**
*Closes
#[33883](https://github.com/langchain-ai/langchain/issues/33883)*
Chat model cache keys are generated by serializing messages via
`dumps(messages)`. The optional `BaseMessage.id` field (a UUID used
solely for tracing/threading) is included in this serialization, causing
functionally identical messages to produce different cache keys. This
results in repeated API calls, cache bloat, and degraded performance in
production workloads (e.g., agents, RAG chains, long conversations).
This change normalizes messages **only for cache key generation** by
stripping the nonsemantic `id` field using Pydantic V2’s
`model_copy(update={"id": None})`. The normalization is applied in both
synchronous and asynchronous cache paths (`_generate_with_cache` /
`_agenerate_with_cache`) immediately before `dumps()`.
```python
normalized_messages = [
msg.model_copy(update={"id": None})
if getattr(msg, "id", None) is not None
else msg
for msg in messages
]
prompt = dumps(normalized_messages)
---------
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Summary
Fixes an issue where HTMLSemanticPreservingSplitter failed to preserve
elements nested inside non-container tags. With these changes, preserved
elements are now correctly detected and handled at any nesting depth.
Root Cause
`_process_element()` only recursed into a small set of hard-coded
container tags (`html`, `body`, `div`, `main`). For other tags, the
subtree was flattened into text, preventing nested preserved elements
(inside `<p>`, `<section>`, `<article>`, etc.) from being detected.
Fix
- Updated traversal logic in _process_element (html.py) to recursively
process child elements for any tag that contains nested elements
- Avoided duplicate text extraction
- Preserved correct placeholder ordering
- Treated leaf nodes as text only
Tests
Adds regression tests covering preserved elements nested inside
non-container tags, including:
- table inside section
- nested divs
- code inside paragraph
All existing tests pass (make lint, format, test, etc).
Breaking changes
None.
Fixes
Fixes#31569
Disclaimer
GitHub Copilot was used to assist with test case design in
test_text_splitters.py and documentation comments; all code logic was
manually implemented and reviewed.
---------
Co-authored-by: julih <julih@julihs-MacBook-Pro.local>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
This PR updates an outdated GitHub Action version.
- Updated `astral-sh/setup-uv` from `v6` to `v7` in
`.github/actions/uv_setup/action.yml`
Looks like this was missed as part of
https://github.com/langchain-ai/langchain/pull/33457 so hopefully safe
to bring it into alignment.
Addresses a flaky test
When executing `exit 1` as a startup command, the shell process
terminates immediately. The code then tries to write a marker command
(`printf '...'`) to stdin, but the pipe is already broken because the
shell has exited, causing `BrokenPipeError`.
* Support sentence-transformers optional dep on python 3.14
* Bump some dep locks to use pre-built wheels instead of building them
(murmurhash, cymem, preshed, thinc, srsly, blis)
* Still not possible to use spacy: even though there are wheels
available, spacy depends on Pydantic v1 which doesn't work on Python
3.14.
* Speeds up installation and CI.
Co-authored-by: Mason Daugherty <mason@langchain.dev>
Bump lock of MarkupSafe to 3.0.3 which has Python 3.14 pre-built wheels.
Speeds up installation and CI.
Co-authored-by: Mason Daugherty <mason@langchain.dev>
The Code of Conduct link was pointing to a non-existent file path.
Updated to use GitHub's community standards tab URL which correctly
displays the Code of Conduct.
Changed from:
https://github.com/langchain-ai/langchain/blob/master/.github/CODE_OF_CONDUCT.md
To:
https://github.com/langchain-ai/langchain/?tab=coc-ov-file
(Replace this entire block of text)
Read the full contributing guidelines:
https://docs.langchain.com/oss/python/contributing/overview
Thank you for contributing to LangChain! Follow these steps to have your
pull request considered as ready for review.
1. PR title: Should follow the format: TYPE(SCOPE): DESCRIPTION
- Examples:
- fix(anthropic): resolve flag parsing error
- feat(core): add multi-tenant support
- test(openai): update API usage tests
- Allowed TYPE and SCOPE values:
https://github.com/langchain-ai/langchain/blob/master/.github/workflows/pr_lint.yml#L15-L33
2. PR description:
- Write 1-2 sentences summarizing the change.
- If this PR addresses a specific issue, please include "Fixes
#ISSUE_NUMBER" in the description to automatically close the issue when
the PR is merged.
- If there are any breaking changes, please clearly describe them.
- If this PR depends on another PR being merged first, please include
"Depends on #PR_NUMBER" inthe description.
3. Run `make format`, `make lint` and `make test` from the root of the
package(s) you've modified.
- We will not consider a PR unless these three are passing in CI.
Additional guidelines:
- We ask that if you use generative AI for your contribution, you
include a disclaimer.
- PRs should not touch more than one package unless absolutely
necessary.
- Do not update the `uv.lock` files unless or add dependencies to
`pyproject.toml` files (even optional ones) unless you have explicit
permission to do so by a maintainer.
