Commit Graph

15383 Commits

Author SHA1 Message Date
Tanzim Hossain Romel
2d1492a864 fix(core): improve error message for non-JSON-serializable tool schemas (#34376) langchain-core==1.2.15 2026-02-22 17:32:00 -05:00
Balaji Seshadri
d6e46bb4b0 fix(core): improve typing/docs for on_chat_model_start to clarify required positional args (#35324) 2026-02-22 14:46:32 -05:00
dependabot[bot]
875c3c573d chore: bump google-cloud-aiplatform from 1.127.0 to 1.133.0 in /libs/langchain_v1 (#35397) 2026-02-22 13:47:04 -05:00
dependabot[bot]
32725b3d9b chore: bump google-cloud-aiplatform from 1.117.0 to 1.133.0 in /libs/langchain (#35392) 2026-02-22 09:39:06 -05:00
ccurme
2fa460d325 fix(anthropic): update integration tests (#35396) 2026-02-22 09:33:21 -05:00
Mason Daugherty
6199525f50 perf(core): defer specific langsmith imports to reduce import time (#35298)
Defer `langsmith` and tracer imports in `callbacks/manager.py` and
`runnables/config.py` from module-level to function-level.

These imports pull in the full `langsmith` package (~132ms) at import
time but are only used inside `_configure()`, `trace_as_chain_group()`,
`_set_config_context()`, and `set_config_context()` — none of which run
during module initialization.
2026-02-21 00:29:35 -05:00
ccurme
00538ff5fc revert: add ChatAnthropicBedrockWrapper (#35371) 2026-02-20 15:58:35 -05:00
Mason Daugherty
be1c3fcc1d feat(openrouter): default headers (#35369) 2026-02-20 14:44:06 -05:00
ccurme
5f13eb91e0 chore(infra): disable tests on prior published packages on core release (#35368) 2026-02-20 13:58:53 -05:00
ccurme
bcfb87c211 release(core): 1.2.15 (#35367) 2026-02-20 13:44:26 -05:00
Mason Daugherty
ca246ddef2 fix(anthropic): replace retired model IDs in tests and docstrings (#35365)
## Summary

- Replace `claude-3-5-haiku-20241022` and `claude-3-7-sonnet-20250219`
with `claude-haiku-4-5-20251001` and `claude-sonnet-4-5-20250929`
respectively
- Both models were retired by Anthropic on February 19, 2026, causing
all anthropic integration tests to fail
- Updates integration tests, a unit test, and docstring examples in
`langchain-core`

See:
https://platform.claude.com/docs/en/docs/resources/model-deprecations
2026-02-20 13:44:15 -05:00
ccurme
070c234104 fix(langchain): support anthropic-bedrock in init_chat_model (#35366) 2026-02-20 13:38:11 -05:00
NITIN Madan
63f3669e12 feat(anthropic): add ChatAnthropicBedrock wrapper (#35091) 2026-02-20 13:06:12 -05:00
Mohammad Mohtashim
03826061be fix(deepseek): Tool Choice to required for Azure Deployment in case specific function dict is given (#34848) 2026-02-20 12:50:25 -05:00
Mason Daugherty
0081deae96 feat(infra): schedule daily model profile refresh with job summary (#35354)
- Schedules the `refresh_model_profiles` workflow to run daily at 08:00
UTC (manual trigger available).
- Adds a job summary step that reports whether a PR was created/updated
or skipped because profiles were already up to date.
- Each run supersedes any stale PR from a previous run since the action
force-pushes to a fixed branch (`bot/refresh-model-profiles`).
2026-02-20 00:43:09 -05:00
Mason Daugherty
70192690b1 fix(model-profiles): sort generated profiles by model ID for stable diffs (#35344)
- Sort model profiles alphabetically by model ID (the top-level
`_PROFILES` dictionary keys, e.g. `claude-3-5-haiku-20241022`,
`gpt-4o-mini`) before writing `_profiles.py`, so that regenerating
profiles only shows actual data changes in diffs — not random reordering
from the models.dev API response order
- Regenerate all 10 partner profile files with the new sorted ordering
2026-02-19 23:11:22 -05:00
Mason Daugherty
8aa7a3f07a chore: update agent files (#35346) 2026-02-19 23:11:02 -05:00
Mason Daugherty
e95e869d9e chore(infra): add GitHub App token generation step (#35334) 2026-02-19 22:48:51 -05:00
ccurme
5362bf5666 fix(anthropic): set max input tokens based on 1m context beta header (#35341) 2026-02-19 21:01:49 -05:00
Mason Daugherty
135a208919 chore: add model profile info to agent files (#35336) 2026-02-19 14:03:56 -05:00
Mason Daugherty
4af87fd025 fix(infra): fix trailing comma regex in profile generation script (#35333)
The trailing comma regex in the profile generation script consumed the
closing `}` as part of its match, preventing nested closing braces from
getting their own trailing comma. This caused `ruff format` failures on
every generated `_profiles.py` file.

Switches to a lookahead (`(?=...)`) so the closing bracket is asserted
but not consumed, allowing each nesting level to independently receive
its trailing comma.

Fixes #35332.
2026-02-19 13:27:02 -05:00
Christophe Bornet
6a6ef8caad style: fix some ruff noqa (#35321) 2026-02-19 13:19:30 -05:00
Mason Daugherty
59be7d734f feat(infra): model profile bump tool (#35331) 2026-02-19 13:03:10 -05:00
ccurme
9851838eb8 release(core): 1.2.14 (#35328) langchain-core==1.2.14 2026-02-19 09:18:24 -05:00
Mason Daugherty
18230f625f chore(core): remove langserve from sys info util, add deepagents (#35325)
getting with the times
2026-02-18 23:32:54 -05:00
Théo Deschamps
83f81d65af fix(langchain): allow Gemini 3 models to use ProviderStrategy with tools (#34464) 2026-02-18 21:14:16 -05:00
Mattijs Ugen
5c6f8fe0a6 fix(openai): accept valid responses that are falsy at runtime (#35307) 2026-02-18 21:06:43 -05:00
yaowubarbara
5053436dcf fix(core): fix merge_lists incorrectly merging parallel tool calls (#35281) 2026-02-18 20:33:17 -05:00
Shivangi Sharma
3686bcbd96 fix(core): accept int temperature in _get_ls_params for LangSmith tracing (#35302) 2026-02-18 18:30:02 -05:00
ccurme
9c160e2368 revert: accept integer temperature values in _get_ls_params (#35319) 2026-02-18 18:19:28 -05:00
ccurme
269947b11f release(text-splitters): 1.1.1 (#35318) langchain-text-splitters==1.1.1 2026-02-18 17:59:36 -05:00
Balaji Seshadri
a9f3627229 fix(core): accept integer temperature values in _get_ls_params (#35317) 2026-02-18 17:52:13 -05:00
Maxime Grenu
8951c01fe8 fix(text-splitters): prevent JSFrameworkTextSplitter from mutating self._separators on each split_text() call (#35316) 2026-02-18 17:51:42 -05:00
Eugene Yurtsev
8323f556d9 docs(core): update load note to be precise (#35309)
update load doc-string for precision
2026-02-18 15:22:59 -05:00
Christian Veenhuis
b004103721 docs(perplexity): Fix docstring of output_parsers.strip_think_tags() (#35264) langchain-tests==1.1.5 2026-02-17 21:45:21 -05:00
Mason Daugherty
82ae4fb6fa chore: bump model profiles (#35294) 2026-02-17 20:22:07 -05:00
KarthikRed2000
a565cf85eb fix(core): prevent recursion error when args_schema is dict (#35260) 2026-02-17 17:47:17 -05:00
Mike Lambert
0d13463e7f feat(anthropic): add User-Agent header for Anthropic API calls (#35268) 2026-02-17 15:59:54 -05:00
ccurme
8166e0137d chore(anthropic): add version (#35293) 2026-02-17 15:49:14 -05:00
ccurme
6fe7845cd1 release(openai): 1.1.10 (#35292) langchain-openai==1.1.10 2026-02-17 12:55:21 -05:00
Mason Daugherty
ba3ad67328 fix(core): preserve index and timestamp fields when merging (#34731)
Porting https://github.com/langchain-ai/langchainjs/pull/9781
2026-02-17 11:29:41 -05:00
Mason Daugherty
0a561244f5 docs(core): add security warnings and best practices for deserialization (#35282) 2026-02-17 11:28:39 -05:00
Shivangi Sharma
f7dbdab5ba docs: fix docstring inaccuracies and update outdated LangSmith URLs (#35283)
Fix several docstring inaccuracies in langchain-core and update outdated
LangSmith URLs across three README files.

**Docstring fixes (libs/core):**
- `tap_output_iter`: docstring says "async iterator" but method accepts
sync `Iterator`
- `agenerate_from_stream`: docstring says "Iterator" but method accepts
`AsyncIterator`
- `BaseLLM.OutputType`: docstring says "input type" but property returns
output type
- Grammar: "or deprecated" → "or be deprecated", "relies" → "rely",
"whose the" → "whose"

**URL fixes (libs/core, libs/langchain, libs/langchain_v1):**
- Updated `smith.langchain.com` → `www.langchain.com/langsmith` (root
README already uses the correct URL)

Verified with `make lint` and `make format` in libs/core — no new issues
introduced. Changes are docs-only with no code logic impact.

*This PR was created with assistance from an AI coding tool.*
2026-02-17 11:22:18 -05:00
ccurme
8f1bc0d3ae feat(openai): support automatic server-side compaction (#35212) 2026-02-17 10:48:52 -05:00
ccurme
32c6ab3033 fix(openai): add model property (#35284) 2026-02-17 10:46:49 -05:00
ccurme
4150bb513f fix(mistralai): update test (#35270) 2026-02-17 09:08:14 -05:00
dependabot[bot]
dba5266fa9 chore: bump langchainhub from 0.1.18 to 0.1.21 in /libs/langchain in the langchain-deps group across 1 directory (#35280)
Bumps the langchain-deps group with 1 update in the /libs/langchain
directory: langchainhub.

Updates `langchainhub` from 0.1.18 to 0.1.21


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=langchainhub&package-manager=uv&previous-version=0.1.18&new-version=0.1.21)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore <dependency name> major version` will close this
group update PR and stop Dependabot creating any more for the specific
dependency's major version (unless you unignore this specific
dependency's major version or upgrade to it yourself)
- `@dependabot ignore <dependency name> minor version` will close this
group update PR and stop Dependabot creating any more for the specific
dependency's minor version (unless you unignore this specific
dependency's minor version or upgrade to it yourself)
- `@dependabot ignore <dependency name>` will close this group update PR
and stop Dependabot creating any more for the specific dependency
(unless you unignore this specific dependency or upgrade to it yourself)
- `@dependabot unignore <dependency name>` will remove all of the ignore
conditions of the specified dependency
- `@dependabot unignore <dependency name> <ignore condition>` will
remove the ignore condition of the specified dependency and ignore
conditions


</details>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-02-17 00:44:53 -08:00
dependabot[bot]
338fd021fe chore: bump transformers from 5.1.0 to 5.2.0 in /libs/text-splitters in the other-deps group across 1 directory (#35279)
Bumps the other-deps group with 1 update in the /libs/text-splitters
directory: [transformers](https://github.com/huggingface/transformers).

Updates `transformers` from 5.1.0 to 5.2.0
<details>
<summary>Commits</summary>
<ul>
<li><a
href="7d9754a051"><code>7d9754a</code></a>
Fix unprotected torch import (<a
href="https://redirect.github.com/huggingface/transformers/issues/44055">#44055</a>)</li>
<li><a
href="a0a3d294b6"><code>a0a3d29</code></a>
Fix peft conversion typo (<a
href="https://redirect.github.com/huggingface/transformers/issues/44053">#44053</a>)</li>
<li><a
href="2096db0aa1"><code>2096db0</code></a>
v5.2.0</li>
<li><a
href="73ecc5e314"><code>73ecc5e</code></a>
[fix][wip] GlmMoeDsa: try implement DSA (<a
href="https://redirect.github.com/huggingface/transformers/issues/43912">#43912</a>)</li>
<li><a
href="349e00c1a3"><code>349e00c</code></a>
Fix early image processor return not raising error (<a
href="https://redirect.github.com/huggingface/transformers/issues/43981">#43981</a>)</li>
<li><a
href="2bd902dbc4"><code>2bd902d</code></a>
Update assignee for generate in bug report template (<a
href="https://redirect.github.com/huggingface/transformers/issues/44042">#44042</a>)</li>
<li><a
href="2546978b80"><code>2546978</code></a>
Add a dim check mechanism in Transpose and fix qwen3_vl_moe weight
mapping (#...</li>
<li><a
href="08c4ad95d4"><code>08c4ad9</code></a>
fix(models): Unpack BitNet packed weights to fix CI failure (<a
href="https://redirect.github.com/huggingface/transformers/issues/43721">#43721</a>)</li>
<li><a
href="53f8a08290"><code>53f8a08</code></a>
SINQ quantization strategy integration (adapted for Transformers V5) (<a
href="https://redirect.github.com/huggingface/transformers/issues/43112">#43112</a>)</li>
<li><a
href="9a9231632e"><code>9a92316</code></a>
split out accelerator args builder method (<a
href="https://redirect.github.com/huggingface/transformers/issues/43987">#43987</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/huggingface/transformers/compare/v5.1.0...v5.2.0">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=transformers&package-manager=uv&previous-version=5.1.0&new-version=5.2.0)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore <dependency name> major version` will close this
group update PR and stop Dependabot creating any more for the specific
dependency's major version (unless you unignore this specific
dependency's major version or upgrade to it yourself)
- `@dependabot ignore <dependency name> minor version` will close this
group update PR and stop Dependabot creating any more for the specific
dependency's minor version (unless you unignore this specific
dependency's minor version or upgrade to it yourself)
- `@dependabot ignore <dependency name>` will close this group update PR
and stop Dependabot creating any more for the specific dependency
(unless you unignore this specific dependency or upgrade to it yourself)
- `@dependabot unignore <dependency name>` will remove all of the ignore
conditions of the specified dependency
- `@dependabot unignore <dependency name> <ignore condition>` will
remove the ignore condition of the specified dependency and ignore
conditions


</details>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-02-17 00:44:21 -08:00
Mason Daugherty
c997955bf3 chore(infra): updates for openrouter/ollama (#35278) 2026-02-16 23:53:51 -05:00
Tune
68a14844b5 fix(nomic,openai,perplexity): update pillow version to >= 12.1.1, <13.0.0 (#35254)
Updates the minimum Pillow version to address CVE-2026-25990 (HIGH
severity out-of-bounds write vulnerability affecting versions 10.3.0
through 12.1.0).

Changes:
langchain-nomic: pillow>=10.3.0,<13.0.0 → pillow>=12.1.1,<13.0.0
langchain-openai: pillow>=10.3.0,<13.0.0 → pillow>=12.1.1,<13.0.0
langchain-perplexity: pillow>=10.3.0,<13.0.0 → pillow>=12.1.1,<13.0.0
Safety: This is a minimum version bump within the existing constraint
range (<13.0.0), so no breaking changes are introduced.

CVE Details:
CVE-2026-25990: An out-of-bounds write may be triggered when loading a
specially crafted PSD image
Affected versions: 10.3.0 to <12.1.1
Fixed in: 12.1.1
Reference: https://nvd.nist.gov/vuln/detail/CVE-2026-25990

** Claude Helped me write this nice message **
The original findings was thanks to a Trivy scan

---------

Co-authored-by: Mason Daugherty <mason@langchain.dev>
2026-02-16 23:17:32 -05:00