mirror of
https://github.com/hwchase17/langchain.git
synced 2026-06-09 10:17:00 +00:00
eb1f731aeef415055a5afb4f390ccbaaaf4029bd
16079 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Nick Hollon
|
eb1f731aee |
chore(langchain): bump langgraph to 1.2.4 (#37857)
|
||
Mason Daugherty
|
06e3c2a2af |
chore(langchain): loosen langgraph dep range (#37855)
|
||
dependabot[bot]
|
44545a0ffc |
chore: bump aws-actions/configure-aws-credentials from 6.1.1 to 6.2.0 in the minor-and-patch group (#37846)
Bumps the minor-and-patch group with 1 update: [aws-actions/configure-aws-credentials](https://github.com/aws-actions/configure-aws-credentials). Updates `aws-actions/configure-aws-credentials` from 6.1.1 to 6.2.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/aws-actions/configure-aws-credentials/releases">aws-actions/configure-aws-credentials's releases</a>.</em></p> <blockquote> <h2>v6.2.0</h2> <h2><a href="https://github.com/aws-actions/configure-aws-credentials/compare/v6.1.3...v6.2.0">6.2.0</a> (2026-06-01)</h2> <h3>Features</h3> <ul> <li>add additional session tags by default (<a href="https://redirect.github.com/aws-actions/configure-aws-credentials/issues/1775">#1775</a>) (<a href=" |
||
langchain-model-profile-bot[bot]
|
7a74eeb33c |
chore(model-profiles): refresh model profile data (#37852)
Automated refresh of model profile data for all in-monorepo partner integrations via `langchain-profiles refresh`. 🤖 Generated by the `refresh_model_profiles` workflow. Co-authored-by: mdrxy <61371264+mdrxy@users.noreply.github.com> |
||
|
Nick Hollon
|
dfca7f4424 | feat(langchain): project subagent runs onto typed run.subagents channel (#37739) | ||
Sydney Runkle
|
36be77b0f1 |
feat(langchain): add interrupt_mode and when predicate to HumanInTheLoopMiddleware (#37579)
Adds an optional `when` predicate to `InterruptOnConfig`, allowing
dynamic per-tool-call control over whether a HITL interrupt fires.
---
**`when` predicate in `InterruptOnConfig`**
```python
class InterruptOnConfig(TypedDict):
allowed_decisions: list[DecisionType]
description: NotRequired[str | _DescriptionFactory]
args_schema: NotRequired[dict[str, Any]]
when: NotRequired[Callable[[ToolCallRequest], bool]] # new
```
When provided, `when` is called before adding a tool call to the batch
interrupt. If it returns `False`, the call is auto-approved and
excluded. If it returns `True` (or `when` is absent), existing behaviour
is unchanged.
The predicate receives a `ToolCallRequest` with:
- `tool_call` — the raw tool call dict (name, args, id)
- `tool` — `None` (no `BaseTool` instance is available at the
`after_model` stage)
- `state` — current agent state
- `runtime` — a `ToolRuntime` constructed from the node-level `Runtime`,
with `tool_call_id` populated
Example:
```python
HumanInTheLoopMiddleware(
interrupt_on={
"delete_file": InterruptOnConfig(
allowed_decisions=["approve", "reject"],
when=lambda req: req.tool_call["args"].get("path", "").startswith("/etc"),
)
}
)
```
This change is fully backwards-compatible — `when` is `NotRequired` and
existing configs without it behave identically.
> This PR was developed with AI-agent assistance.
|
||
|
langchain-model-profile-bot[bot]
|
bc5f1517cf |
chore(model-profiles): refresh model profile data (#37802)
Automated refresh of model profile data for all in-monorepo partner integrations via `langchain-profiles refresh`. 🤖 Generated by the `refresh_model_profiles` workflow. Co-authored-by: mdrxy <61371264+mdrxy@users.noreply.github.com> |
||
github-actions[bot]
|
22ebaf95f9 |
chore(deps): bump uv to 0.11.17 (#37824)
Bumps the uv pin in `.github/actions/uv_setup/action.yml` from `0.11.15` to [`0.11.17`](https://github.com/astral-sh/uv/releases/tag/0.11.17). Opened automatically by `bump_uv_pin.yml`. Mirror availability on `releases.astral.sh` was verified before this PR was created, so CI should not race the fallback. Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
langchain-model-profile-bot[bot]
|
a79298a791 |
chore(model-profiles): refresh model profile data (#37791)
Automated refresh of model profile data for all in-monorepo partner integrations via `langchain-profiles refresh`. 🤖 Generated by the `refresh_model_profiles` workflow. Co-authored-by: mdrxy <61371264+mdrxy@users.noreply.github.com> |
||
|
dependabot[bot]
|
4a7476093d |
chore: bump chromadb from 1.5.5 to 1.5.9 in /libs/partners/chroma (#37779)
Bumps [chromadb](https://github.com/chroma-core/chroma) from 1.5.5 to 1.5.9. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/chroma-core/chroma/releases">chromadb's releases</a>.</em></p> <blockquote> <h2>1.5.9</h2> <p>Version: <code>1.5.9</code> Git ref: <code>refs/tags/1.5.9</code> Build Date: <code>2026-05-05T05:55</code> PIP Package: <code>chroma-1.5.9.tar.gz</code> Github Container Registry Image: <code>:1.5.9</code> DockerHub Image: <code>:1.5.9</code></p> <h2>What's Changed</h2> <ul> <li><a href="https://github.com/chroma-core/chroma/blob/HEAD/frontend">ENH</a>: block functions on topology dbs by <a href="https://github.com/rescrv"><code>@rescrv</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6836">chroma-core/chroma#6836</a></li> <li><a href="https://github.com/chroma-core/chroma/blob/HEAD/faults">ENH</a>: Add Tilt fault injection CLI by <a href="https://github.com/rescrv"><code>@rescrv</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6881">chroma-core/chroma#6881</a></li> <li>[CHORE] Debug TimeoutError in test_add.py by <a href="https://github.com/rescrv"><code>@rescrv</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6905">chroma-core/chroma#6905</a></li> <li>[ENH]: Enable rebuilds for sharded collections by <a href="https://github.com/tanujnay112"><code>@tanujnay112</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6916">chroma-core/chroma#6916</a></li> <li>[ENH]: Group by support with sharding by <a href="https://github.com/sanketkedia"><code>@sanketkedia</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6909">chroma-core/chroma#6909</a></li> <li>[CHORE]: Denormalize tenant and database into collection_compaction_cursors table by <a href="https://github.com/tanujnay112"><code>@tanujnay112</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6940">chroma-core/chroma#6940</a></li> <li>[CHORE] Use normalized record sets for test add by <a href="https://github.com/rescrv"><code>@rescrv</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6935">chroma-core/chroma#6935</a></li> <li>[ENH]: Add workflow to build and publish service container images by <a href="https://github.com/jasonvigil"><code>@jasonvigil</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6944">chroma-core/chroma#6944</a></li> <li>[ENH] - Updates language around Chroma Cloud to be more representative. by <a href="https://github.com/tjkrusinskichroma"><code>@tjkrusinskichroma</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6952">chroma-core/chroma#6952</a></li> <li>[ENH]: Add change stream to collection compaction cursors by <a href="https://github.com/tanujnay112"><code>@tanujnay112</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6955">chroma-core/chroma#6955</a></li> <li>[BUG] Switch to storing DOCKERHUB_USERNAME as var by <a href="https://github.com/jasonvigil"><code>@jasonvigil</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6962">chroma-core/chroma#6962</a></li> <li>[CHORE]: Standardize Tilt CI image build on root docker-bake.hcl by <a href="https://github.com/jasonvigil"><code>@jasonvigil</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6958">chroma-core/chroma#6958</a></li> <li>[BUG]: Rename database on soft delete by <a href="https://github.com/tanujnay112"><code>@tanujnay112</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6943">chroma-core/chroma#6943</a></li> <li>Revert "[CHORE]: Standardize Tilt CI image build on root docker-bake.hcl" by <a href="https://github.com/jasonvigil"><code>@jasonvigil</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6965">chroma-core/chroma#6965</a></li> <li><a href="https://github.com/chroma-core/chroma/blob/HEAD/system">ENH</a>: name and size all worker threads by <a href="https://github.com/rescrv"><code>@rescrv</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6936">chroma-core/chroma#6936</a></li> <li><a href="https://github.com/chroma-core/chroma/blob/HEAD/test">BUG</a>: simplify flaky indexing progress test by <a href="https://github.com/rescrv"><code>@rescrv</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6968">chroma-core/chroma#6968</a></li> <li>[CHORE] stabilize Tilt dev environment configs by <a href="https://github.com/rescrv"><code>@rescrv</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6937">chroma-core/chroma#6937</a></li> <li><a href="https://github.com/chroma-core/chroma/blob/HEAD/garbage_collector">BUG</a>: use correct version file per collection in ancestor walk by <a href="https://github.com/rescrv"><code>@rescrv</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6970">chroma-core/chroma#6970</a></li> <li>[ENH] Add SparsePostingBlock by <a href="https://github.com/HammadB"><code>@HammadB</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6823">chroma-core/chroma#6823</a></li> <li>[ENH] Add basic maxscore writer/reader by <a href="https://github.com/HammadB"><code>@HammadB</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6825">chroma-core/chroma#6825</a></li> <li>[ENH] Add maxscore lazy cursor by <a href="https://github.com/HammadB"><code>@HammadB</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6829">chroma-core/chroma#6829</a></li> <li>[ENH] Add SIMD for maxscore by <a href="https://github.com/Sicheng-Pan"><code>@Sicheng-Pan</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6865">chroma-core/chroma#6865</a></li> <li>[ENH] Benchmark maxscore by <a href="https://github.com/Sicheng-Pan"><code>@Sicheng-Pan</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6866">chroma-core/chroma#6866</a></li> <li>[ENH] Add maxscore option in schema by <a href="https://github.com/Sicheng-Pan"><code>@Sicheng-Pan</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6878">chroma-core/chroma#6878</a></li> <li>[ENH] Add maxscore index to metadata segment by <a href="https://github.com/Sicheng-Pan"><code>@Sicheng-Pan</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6880">chroma-core/chroma#6880</a></li> <li>[ENH] Wire maxscore reader in search by <a href="https://github.com/Sicheng-Pan"><code>@Sicheng-Pan</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6899">chroma-core/chroma#6899</a></li> <li>[PERF] Batch load lazy cursor by <a href="https://github.com/Sicheng-Pan"><code>@Sicheng-Pan</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6974">chroma-core/chroma#6974</a></li> <li><a href="https://github.com/chroma-core/chroma/blob/HEAD/garbage_collector">ENH</a>: add MCMR support for log GC by <a href="https://github.com/rescrv"><code>@rescrv</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6946">chroma-core/chroma#6946</a></li> <li><a href="https://github.com/chroma-core/chroma/blob/HEAD/test">ENH</a>: parameterize multi-region config by <a href="https://github.com/rescrv"><code>@rescrv</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6951">chroma-core/chroma#6951</a></li> <li>[CHORE] fix merge conflict in main by <a href="https://github.com/rescrv"><code>@rescrv</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6986">chroma-core/chroma#6986</a></li> <li>[ENH]: Refactor offset_id to be a mutable AtomicU32 in record by <a href="https://github.com/tanujnay112"><code>@tanujnay112</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6922">chroma-core/chroma#6922</a></li> <li><a href="https://github.com/chroma-core/chroma/blob/HEAD/spanner">ENH</a>: add spanner-cli wrapper binary by <a href="https://github.com/rescrv"><code>@rescrv</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6959">chroma-core/chroma#6959</a></li> <li><a href="https://github.com/chroma-core/chroma/blob/HEAD/sysdb">BUG</a>: preserve legacy hnsw: metadata keys by <a href="https://github.com/rescrv"><code>@rescrv</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6953">chroma-core/chroma#6953</a></li> <li>[TST] refactor repair collection log offset test by <a href="https://github.com/rescrv"><code>@rescrv</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6954">chroma-core/chroma#6954</a></li> <li><a href="https://github.com/chroma-core/chroma/blob/HEAD/garbage_collector">TST</a>: add MCMR hard delete test by <a href="https://github.com/rescrv"><code>@rescrv</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6947">chroma-core/chroma#6947</a></li> <li><a href="https://github.com/chroma-core/chroma/blob/HEAD/log-service">ENH</a>: defer Spanner init to first use by <a href="https://github.com/rescrv"><code>@rescrv</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6915">chroma-core/chroma#6915</a></li> <li>[CHORE]: Denormalize is_deleted in mcmr by <a href="https://github.com/tanujnay112"><code>@tanujnay112</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6989">chroma-core/chroma#6989</a></li> <li>[BUG] Reject NaN/Infinity in base64-encoded embeddings by <a href="https://github.com/philipithomas"><code>@philipithomas</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6664">chroma-core/chroma#6664</a></li> <li>Revert "<a href="https://github.com/chroma-core/chroma/blob/HEAD/garbage_collector">TST</a>: add MCMR hard delete test" by <a href="https://github.com/rescrv"><code>@rescrv</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6992">chroma-core/chroma#6992</a></li> <li>[ENH] Verify file path for compaction by <a href="https://github.com/Sicheng-Pan"><code>@Sicheng-Pan</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6991">chroma-core/chroma#6991</a></li> <li>[DOC]: Document file-upload sync API, AWS credential reuse, and EU region by <a href="https://github.com/philipithomas"><code>@philipithomas</code></a> in <a href="https://redirect.github.com/chroma-core/chroma/pull/6988">chroma-core/chroma#6988</a></li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
dependabot[bot]
|
7336690902 |
chore: bump langsmith from 0.8.3 to 0.8.7 in /libs/partners/chroma (#37780)
Bumps [langsmith](https://github.com/langchain-ai/langsmith-sdk) from 0.8.3 to 0.8.7. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langsmith-sdk/releases">langsmith's releases</a>.</em></p> <blockquote> <h2>v0.8.7</h2> <h2>What's Changed</h2> <ul> <li>fix: reconnect sandbox command streams on EOF by <a href="https://github.com/ramon-langchain"><code>@ramon-langchain</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2941">langchain-ai/langsmith-sdk#2941</a></li> <li>feat(sandbox): build snapshots from Dockerfiles by <a href="https://github.com/langchain-infra"><code>@langchain-infra</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2950">langchain-ai/langsmith-sdk#2950</a></li> <li>fix(python): add organization id to context URLs by <a href="https://github.com/vishnu-ssuresh"><code>@vishnu-ssuresh</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2945">langchain-ai/langsmith-sdk#2945</a></li> <li>fix(js): add organization id to context URLs by <a href="https://github.com/vishnu-ssuresh"><code>@vishnu-ssuresh</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2946">langchain-ai/langsmith-sdk#2946</a></li> <li>release(py): 0.8.7 by <a href="https://github.com/ramon-langchain"><code>@ramon-langchain</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2947">langchain-ai/langsmith-sdk#2947</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/langchain-ai/langsmith-sdk/compare/v0.8.6...v0.8.7">https://github.com/langchain-ai/langsmith-sdk/compare/v0.8.6...v0.8.7</a></p> <h2>v0.8.6</h2> <h2>What's Changed</h2> <ul> <li>chore(deps-dev): bump <code>@google/genai</code> from 1.50.1 to 2.0.1 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2875">langchain-ai/langsmith-sdk#2875</a></li> <li>chore(deps): bump mako from 1.3.11 to 1.3.12 in /python by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2880">langchain-ai/langsmith-sdk#2880</a></li> <li>chore(deps): bump authlib from 1.6.11 to 1.6.12 in /python by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2888">langchain-ai/langsmith-sdk#2888</a></li> <li>chore(deps): bump hono from 4.12.15 to 4.12.18 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2894">langchain-ai/langsmith-sdk#2894</a></li> <li>chore(deps): bump fast-uri from 3.1.0 to 3.1.2 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2895">langchain-ai/langsmith-sdk#2895</a></li> <li>chore(deps-dev): bump <code>@anthropic-ai/sdk</code> from 0.94.0 to 0.95.0 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2881">langchain-ai/langsmith-sdk#2881</a></li> <li>chore(deps): bump postcss from 8.5.8 to 8.5.14 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2898">langchain-ai/langsmith-sdk#2898</a></li> <li>chore(deps): bump <code>@protobufjs/utf8</code> from 1.1.0 to 1.1.1 in /js/internal/environment_tests/test-exports-vite in the npm_and_yarn group across 1 directory by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2908">langchain-ai/langsmith-sdk#2908</a></li> <li>chore(deps): bump hono from 4.12.18 to 4.12.19 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2909">langchain-ai/langsmith-sdk#2909</a></li> <li>chore(deps): bump protobufjs from 7.5.7 to 8.0.1 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2896">langchain-ai/langsmith-sdk#2896</a></li> <li>chore(deps): bump idna from 3.11 to 3.15 in /python by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2913">langchain-ai/langsmith-sdk#2913</a></li> <li>chore(deps-dev): bump <code>@anthropic-ai/sdk</code> from 0.95.0 to 0.95.1 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2912">langchain-ai/langsmith-sdk#2912</a></li> <li>AI SDK telemetry and AI SDK v7 support by <a href="https://github.com/dqbd"><code>@dqbd</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2901">langchain-ai/langsmith-sdk#2901</a></li> <li>feat: install websockets by default for sandbox by <a href="https://github.com/open-swe"><code>@open-swe</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2916">langchain-ai/langsmith-sdk#2916</a></li> <li>release(js): 0.7.2 by <a href="https://github.com/dqbd"><code>@dqbd</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2922">langchain-ai/langsmith-sdk#2922</a></li> <li>feat: add list_runs_from_annotation_queue method [closes LSDK-193] by <a href="https://github.com/open-swe"><code>@open-swe</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2892">langchain-ai/langsmith-sdk#2892</a></li> <li>chore(deps-dev): bump <code>@anthropic-ai/sdk</code> from 0.95.1 to 0.95.2 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2917">langchain-ai/langsmith-sdk#2917</a></li> <li>chore(deps-dev): bump types-pyyaml from 6.0.12.20250915 to 6.0.12.20260518 in /python by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2927">langchain-ai/langsmith-sdk#2927</a></li> <li>chore(deps): update pydata-sphinx-theme requirement from >=0.15 to >=0.18.0 in /python by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2928">langchain-ai/langsmith-sdk#2928</a></li> <li>chore: exclude langsmith_api from ruff linter by <a href="https://github.com/KiewanVillatel"><code>@KiewanVillatel</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2933">langchain-ai/langsmith-sdk#2933</a></li> <li>fix(python): retry sandbox connect timeouts by <a href="https://github.com/ramon-langchain"><code>@ramon-langchain</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2940">langchain-ai/langsmith-sdk#2940</a></li> <li>fix(js): [LSDK-202] return context hub URLs for pushed contexts by <a href="https://github.com/vishnu-ssuresh"><code>@vishnu-ssuresh</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2939">langchain-ai/langsmith-sdk#2939</a></li> <li>fix(python): RunTree.create_child appends to self.child_runs LSE-2221 by <a href="https://github.com/catherine-langchain"><code>@catherine-langchain</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2942">langchain-ai/langsmith-sdk#2942</a></li> <li>release(js): 0.7.3 by <a href="https://github.com/vishnu-ssuresh"><code>@vishnu-ssuresh</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2943">langchain-ai/langsmith-sdk#2943</a></li> <li>fix(python): [LSDK-202] return context hub URLs for pushed contexts by <a href="https://github.com/vishnu-ssuresh"><code>@vishnu-ssuresh</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2938">langchain-ai/langsmith-sdk#2938</a></li> <li>release(py): 0.8.6 by <a href="https://github.com/vishnu-ssuresh"><code>@vishnu-ssuresh</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2944">langchain-ai/langsmith-sdk#2944</a></li> </ul> <h2>New Contributors</h2> <ul> <li><a href="https://github.com/KiewanVillatel"><code>@KiewanVillatel</code></a> made their first contribution in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2933">langchain-ai/langsmith-sdk#2933</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/langchain-ai/langsmith-sdk/compare/v0.8.5...v0.8.6">https://github.com/langchain-ai/langsmith-sdk/compare/v0.8.5...v0.8.6</a></p> <h2>v0.8.5</h2> <h2>What's Changed</h2> <ul> <li>release(js): 0.7.0 by <a href="https://github.com/ramon-langchain"><code>@ramon-langchain</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2890">langchain-ai/langsmith-sdk#2890</a></li> <li>fix(js): add alias for <code>experimental/sandbox</code> to appease broad peer dep range within <code>deepagents</code> by <a href="https://github.com/dqbd"><code>@dqbd</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2893">langchain-ai/langsmith-sdk#2893</a></li> <li>feat(js): allow disabling multipart streaming via env variable by <a href="https://github.com/dqbd"><code>@dqbd</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2900">langchain-ai/langsmith-sdk#2900</a></li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
dependabot[bot]
|
66ba4b7592 |
chore: bump langsmith from 0.8.0 to 0.8.7 in /libs/partners/fireworks (#37781)
Bumps [langsmith](https://github.com/langchain-ai/langsmith-sdk) from 0.8.0 to 0.8.7. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain-ai/langsmith-sdk/releases">langsmith's releases</a>.</em></p> <blockquote> <h2>v0.8.7</h2> <h2>What's Changed</h2> <ul> <li>fix: reconnect sandbox command streams on EOF by <a href="https://github.com/ramon-langchain"><code>@ramon-langchain</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2941">langchain-ai/langsmith-sdk#2941</a></li> <li>feat(sandbox): build snapshots from Dockerfiles by <a href="https://github.com/langchain-infra"><code>@langchain-infra</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2950">langchain-ai/langsmith-sdk#2950</a></li> <li>fix(python): add organization id to context URLs by <a href="https://github.com/vishnu-ssuresh"><code>@vishnu-ssuresh</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2945">langchain-ai/langsmith-sdk#2945</a></li> <li>fix(js): add organization id to context URLs by <a href="https://github.com/vishnu-ssuresh"><code>@vishnu-ssuresh</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2946">langchain-ai/langsmith-sdk#2946</a></li> <li>release(py): 0.8.7 by <a href="https://github.com/ramon-langchain"><code>@ramon-langchain</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2947">langchain-ai/langsmith-sdk#2947</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/langchain-ai/langsmith-sdk/compare/v0.8.6...v0.8.7">https://github.com/langchain-ai/langsmith-sdk/compare/v0.8.6...v0.8.7</a></p> <h2>v0.8.6</h2> <h2>What's Changed</h2> <ul> <li>chore(deps-dev): bump <code>@google/genai</code> from 1.50.1 to 2.0.1 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2875">langchain-ai/langsmith-sdk#2875</a></li> <li>chore(deps): bump mako from 1.3.11 to 1.3.12 in /python by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2880">langchain-ai/langsmith-sdk#2880</a></li> <li>chore(deps): bump authlib from 1.6.11 to 1.6.12 in /python by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2888">langchain-ai/langsmith-sdk#2888</a></li> <li>chore(deps): bump hono from 4.12.15 to 4.12.18 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2894">langchain-ai/langsmith-sdk#2894</a></li> <li>chore(deps): bump fast-uri from 3.1.0 to 3.1.2 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2895">langchain-ai/langsmith-sdk#2895</a></li> <li>chore(deps-dev): bump <code>@anthropic-ai/sdk</code> from 0.94.0 to 0.95.0 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2881">langchain-ai/langsmith-sdk#2881</a></li> <li>chore(deps): bump postcss from 8.5.8 to 8.5.14 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2898">langchain-ai/langsmith-sdk#2898</a></li> <li>chore(deps): bump <code>@protobufjs/utf8</code> from 1.1.0 to 1.1.1 in /js/internal/environment_tests/test-exports-vite in the npm_and_yarn group across 1 directory by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2908">langchain-ai/langsmith-sdk#2908</a></li> <li>chore(deps): bump hono from 4.12.18 to 4.12.19 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2909">langchain-ai/langsmith-sdk#2909</a></li> <li>chore(deps): bump protobufjs from 7.5.7 to 8.0.1 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2896">langchain-ai/langsmith-sdk#2896</a></li> <li>chore(deps): bump idna from 3.11 to 3.15 in /python by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2913">langchain-ai/langsmith-sdk#2913</a></li> <li>chore(deps-dev): bump <code>@anthropic-ai/sdk</code> from 0.95.0 to 0.95.1 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2912">langchain-ai/langsmith-sdk#2912</a></li> <li>AI SDK telemetry and AI SDK v7 support by <a href="https://github.com/dqbd"><code>@dqbd</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2901">langchain-ai/langsmith-sdk#2901</a></li> <li>feat: install websockets by default for sandbox by <a href="https://github.com/open-swe"><code>@open-swe</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2916">langchain-ai/langsmith-sdk#2916</a></li> <li>release(js): 0.7.2 by <a href="https://github.com/dqbd"><code>@dqbd</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2922">langchain-ai/langsmith-sdk#2922</a></li> <li>feat: add list_runs_from_annotation_queue method [closes LSDK-193] by <a href="https://github.com/open-swe"><code>@open-swe</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2892">langchain-ai/langsmith-sdk#2892</a></li> <li>chore(deps-dev): bump <code>@anthropic-ai/sdk</code> from 0.95.1 to 0.95.2 in /js by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2917">langchain-ai/langsmith-sdk#2917</a></li> <li>chore(deps-dev): bump types-pyyaml from 6.0.12.20250915 to 6.0.12.20260518 in /python by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2927">langchain-ai/langsmith-sdk#2927</a></li> <li>chore(deps): update pydata-sphinx-theme requirement from >=0.15 to >=0.18.0 in /python by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2928">langchain-ai/langsmith-sdk#2928</a></li> <li>chore: exclude langsmith_api from ruff linter by <a href="https://github.com/KiewanVillatel"><code>@KiewanVillatel</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2933">langchain-ai/langsmith-sdk#2933</a></li> <li>fix(python): retry sandbox connect timeouts by <a href="https://github.com/ramon-langchain"><code>@ramon-langchain</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2940">langchain-ai/langsmith-sdk#2940</a></li> <li>fix(js): [LSDK-202] return context hub URLs for pushed contexts by <a href="https://github.com/vishnu-ssuresh"><code>@vishnu-ssuresh</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2939">langchain-ai/langsmith-sdk#2939</a></li> <li>fix(python): RunTree.create_child appends to self.child_runs LSE-2221 by <a href="https://github.com/catherine-langchain"><code>@catherine-langchain</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2942">langchain-ai/langsmith-sdk#2942</a></li> <li>release(js): 0.7.3 by <a href="https://github.com/vishnu-ssuresh"><code>@vishnu-ssuresh</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2943">langchain-ai/langsmith-sdk#2943</a></li> <li>fix(python): [LSDK-202] return context hub URLs for pushed contexts by <a href="https://github.com/vishnu-ssuresh"><code>@vishnu-ssuresh</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2938">langchain-ai/langsmith-sdk#2938</a></li> <li>release(py): 0.8.6 by <a href="https://github.com/vishnu-ssuresh"><code>@vishnu-ssuresh</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2944">langchain-ai/langsmith-sdk#2944</a></li> </ul> <h2>New Contributors</h2> <ul> <li><a href="https://github.com/KiewanVillatel"><code>@KiewanVillatel</code></a> made their first contribution in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2933">langchain-ai/langsmith-sdk#2933</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/langchain-ai/langsmith-sdk/compare/v0.8.5...v0.8.6">https://github.com/langchain-ai/langsmith-sdk/compare/v0.8.5...v0.8.6</a></p> <h2>v0.8.5</h2> <h2>What's Changed</h2> <ul> <li>release(js): 0.7.0 by <a href="https://github.com/ramon-langchain"><code>@ramon-langchain</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2890">langchain-ai/langsmith-sdk#2890</a></li> <li>fix(js): add alias for <code>experimental/sandbox</code> to appease broad peer dep range within <code>deepagents</code> by <a href="https://github.com/dqbd"><code>@dqbd</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2893">langchain-ai/langsmith-sdk#2893</a></li> <li>feat(js): allow disabling multipart streaming via env variable by <a href="https://github.com/dqbd"><code>@dqbd</code></a> in <a href="https://redirect.github.com/langchain-ai/langsmith-sdk/pull/2900">langchain-ai/langsmith-sdk#2900</a></li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
dependabot[bot]
|
7d6a78a036 |
chore: bump requests from 2.34.0 to 2.34.2 in /libs/partners/fireworks (#37782)
Bumps [requests](https://github.com/psf/requests) from 2.34.0 to 2.34.2. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/psf/requests/releases">requests's releases</a>.</em></p> <blockquote> <h2>v2.34.2</h2> <h2>2.34.2 (2026-05-14)</h2> <ul> <li>Moved <code>headers</code> input type back to <code>Mapping</code> to avoid invariance issues with <code>MutableMapping</code> and inferred dict types. Users calling <code>Request.headers.update()</code> may need to narrow typing in their code. (<a href="https://redirect.github.com/psf/requests/issues/7441">#7441</a>)</li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/psf/requests/blob/main/HISTORY.md#2342-2026-05-14">https://github.com/psf/requests/blob/main/HISTORY.md#2342-2026-05-14</a></p> <h2>v2.34.1</h2> <h2>2.34.1 (2026-05-13)</h2> <p><strong>Bugfixes</strong></p> <ul> <li>Widened <code>json</code> input type from <code>dict</code> and <code>list</code> to <code>Mapping</code> and <code>Sequence</code>. (<a href="https://redirect.github.com/psf/requests/issues/7436">#7436</a>)</li> <li>Changed <code>headers</code> input type to MutableMapping and removed <code>None</code> from <code>Request.headers</code> typing to improve handling for users. (<a href="https://redirect.github.com/psf/requests/issues/7431">#7431</a>)</li> <li><code>Response.reason</code> moved from <code>str | None</code> to <code>str</code> to improve handling for users. (<a href="https://redirect.github.com/psf/requests/issues/7437">#7437</a>)</li> <li>Fixed a bug where some bodies with custom <code>__getattr__</code> implementations weren't being properly detected as Iterables. (<a href="https://redirect.github.com/psf/requests/issues/7433">#7433</a>)</li> </ul> <h2>New Contributors</h2> <ul> <li><a href="https://github.com/k223kim"><code>@k223kim</code></a> made their first contribution in <a href="https://redirect.github.com/psf/requests/pull/7433">psf/requests#7433</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/psf/requests/blob/main/HISTORY.md#2341-2026-05-13">https://github.com/psf/requests/blob/main/HISTORY.md#2341-2026-05-13</a></p> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/psf/requests/blob/main/HISTORY.md">requests's changelog</a>.</em></p> <blockquote> <h2>2.34.2 (2026-05-14)</h2> <ul> <li>Moved <code>headers</code> input type back to <code>Mapping</code> to avoid invariance issues with <code>MutableMapping</code> and inferred dict types. Users calling <code>Request.headers.update()</code> may need to narrow typing in their code. (<a href="https://redirect.github.com/psf/requests/issues/7441">#7441</a>)</li> </ul> <h2>2.34.1 (2026-05-13)</h2> <p><strong>Bugfixes</strong></p> <ul> <li>Widened <code>json</code> input type from <code>dict</code> and <code>list</code> to <code>Mapping</code> and <code>Sequence</code>. (<a href="https://redirect.github.com/psf/requests/issues/7436">#7436</a>)</li> <li>Changed <code>headers</code> input type to MutableMapping and removed <code>None</code> from <code>Request.headers</code> typing to improve handling for users. (<a href="https://redirect.github.com/psf/requests/issues/7431">#7431</a>)</li> <li><code>Response.reason</code> moved from <code>str | None</code> to <code>str</code> to improve handling for users. (<a href="https://redirect.github.com/psf/requests/issues/7437">#7437</a>)</li> <li>Fixed a bug where some bodies with custom <code>__getattr__</code> implementations weren't being properly detected as Iterables. (<a href="https://redirect.github.com/psf/requests/issues/7433">#7433</a>)</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
Mason Daugherty
|
b8c02e4389 |
chore(infra): note branch conventions in AGENTS.md (#37776)
|
||
|
langchain-model-profile-bot[bot]
|
3893b9e344 |
chore(model-profiles): refresh model profile data (#37771)
Automated refresh of model profile data for all in-monorepo partner integrations via `langchain-profiles refresh`. 🤖 Generated by the `refresh_model_profiles` workflow. Co-authored-by: mdrxy <61371264+mdrxy@users.noreply.github.com> |
||
|
Mason Daugherty
|
4493b2cce1 |
ci(anthropic): check version consistency in pre-commit (#37758)
Local pre-commit already verified `pyproject.toml`/version-file sync for `core` and `langchain_v1`, but not `anthropic` — even though the `check_core_versions.yml` CI workflow already gates all three. This wires the existing `anthropic` check into pre-commit so the mismatch gets caught before commit rather than only in CI. |
||
|
Mason Daugherty
|
133887180e | release(anthropic): 1.4.4 (#37757) langchain-anthropic==1.4.4 | ||
|
Mason Daugherty
|
1a5403d848 |
fix(anthropic): normalize cross-provider tool-call IDs (#37756)
Anthropic's API rejects `tool_use`/`tool_result` IDs that don't match `^[a-zA-Z0-9_-]+$` with a 400. When a conversation thread is replayed across providers — e.g. a user switches a running thread from Kimi (via Fireworks) to Claude — the prior turns carry tool-call IDs minted by the other provider (Kimi emits `functions.write_todos:0`, whose `.` and `:` are invalid), and the request fails. Tool-call IDs are now normalized to an Anthropic-compatible form during request formatting, with the original `tool_use.id` and its paired `tool_use_id` mapped identically so they stay linked. |
||
|
langchain-model-profile-bot[bot]
|
80ca60014f |
chore(model-profiles): refresh model profile data (#37726)
Automated refresh of model profile data for all in-monorepo partner integrations via `langchain-profiles refresh`. 🤖 Generated by the `refresh_model_profiles` workflow. Co-authored-by: mdrxy <61371264+mdrxy@users.noreply.github.com> |
||
|
Mason Daugherty
|
84e3c795ec | release(perplexity): 1.3.1 (#37720) langchain-perplexity==1.3.1 | ||
open-swe[bot]
|
8951e5666f |
chore(perplexity): bump perplexityai to 0.34.1 (#37710)
## Description Bumps `langchain-perplexity` to require the Perplexity SDK release with fixed Responses streaming and removes the temporary SSE shim workaround. ## Release Note `langchain-perplexity` now requires `perplexityai>=0.34.1` for Responses API streaming. ## Test Plan - [x] `NO_COLOR=1 uv run --group test pytest tests/unit_tests/test_chat_models_responses.py --disable-socket --allow-unix-socket` _Opened collaboratively by Mason Daugherty and open-swe._ --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Mason Daugherty <61371264+mdrxy@users.noreply.github.com> Co-authored-by: Mason Daugherty <github@mdrxy.com> |
||
|
Mason Daugherty
|
b26b0ff23b |
ci: remove unnecessary permission and improve logging in waiting-on-author workflow (#37717)
Tightens the `remove_waiting_on_author` workflow by dropping an unneeded permission and improving debuggability when the target label is missing. |
||
|
Mason Daugherty
|
dc215f8af2 |
ci(infra): auto-remove waiting-on-author label on author reply (#37716)
Ports langchain-ai/deepagents#3626. Adds a workflow that clears the `waiting-on-author` label from an issue or PR as soon as the original author posts a follow-up comment, closing the manual loop where maintainers had to remember to strip the label after a reply landed. |
||
|
Mason Daugherty
|
44d9f86bad | release(fireworks): 1.4.2 (#37715) langchain-fireworks==1.4.2 | ||
|
Mason Daugherty
|
e3ce6e557c |
fix(fireworks): strip non-wire keys from all content parts before serialization (#37714)
`_sanitize_chat_completions_content` now filters every content-part dict against an allowlist derived at import time from the `fireworks-ai` SDK's `ContentUnionMember1` TypedDict, and runs on every message role — not just `ToolMessage`. Fixes 400s of the form `Extra inputs are not permitted, field: 'messages[N].content.list[ChatMessageContent][i].<key>'` when cross-provider history (e.g. an Anthropic-shaped `AIMessage` carrying the v1 streaming-reassembly `index` marker) is forwarded to a Fireworks-hosted model. |
||
|
langchain-model-profile-bot[bot]
|
800f02148b |
chore(model-profiles): refresh model profile data (#37712)
Automated refresh of model profile data for all in-monorepo partner integrations via `langchain-profiles refresh`. 🤖 Generated by the `refresh_model_profiles` workflow. Co-authored-by: mdrxy <61371264+mdrxy@users.noreply.github.com> |
||
|
Mason Daugherty
|
b6a4138318 | release(perplexity): 1.3.0 (#37707) langchain-perplexity==1.3.0 | ||
James Liounis
|
f9be3cc328 |
feat(perplexity): use_responses_api flag on ChatPerplexity (#37359)
Closes #37360 Adds a `use_responses_api` flag to `ChatPerplexity` so requests can be routed through Perplexity's Agent API (the Perplexity-flavored Responses API) in addition to the existing Chat Completions endpoint. This mirrors the `use_responses_api` flag on `ChatOpenAI`. ## Motivation Perplexity exposes two HTTP surfaces from the same SDK client object: `client.chat.completions.create()` (Chat Completions) and `client.responses.create()` (Agent API, OpenAI-compatible Responses shape). The Agent API supports built-in tools (`web_search`, `fetch_url`, `finance_search`, `people_search`), `instructions`, `input`, `previous_response_id`, and `include` — none of which exist on Chat Completions. Today `ChatPerplexity` only calls Chat Completions, so users who want the Agent API have to drop down to the raw SDK. ## What this changes - New field `use_responses_api: bool | None = None` on `ChatPerplexity`. - New module-level helper `_use_responses_api(payload)` that returns `True` when the payload contains a built-in tool (any `tools[*]` whose `type` is not `"function"`) or any of the Responses-only fields `previous_response_id`, `instructions`, `input`, `include`. - New instance method `ChatPerplexity._use_responses_api(payload)` that honors `self.use_responses_api` when it is a `bool`, otherwise delegates to the module helper. - New converters `_convert_responses_to_chat_result(response)` and `_convert_responses_stream_event_to_chunk(event)` that translate Agent API objects/events into `AIMessage` and `AIMessageChunk` (preserving `usage_metadata`, `response_metadata`, citations, images, related questions, search results, and `function_call` tool calls). - A surgical `_to_responses_payload(...)` helper that renames `messages` → `input` and `max_tokens` → `max_output_tokens`, passes through Responses-supported fields, and parks anything Perplexity-specific under `extra_body`. - Each of the four API call sites (`_stream`, `_astream`, `_generate`, `_agenerate`) now branches on `self._use_responses_api(payload)`. The Chat Completions path is untouched. ## Auto-detection rules When `use_responses_api` is unset (the default), routing is decided per call from the outgoing payload: - Has a built-in tool? → Responses - Has `previous_response_id`, `instructions`, `input`, or `include`? → Responses - Otherwise → Chat Completions Explicit `use_responses_api=True` or `=False` always overrides auto-detection. ## Backwards compatibility Existing usage is unchanged. `ChatPerplexity(model="sonar").invoke("hi")` still calls `client.chat.completions.create()`. No public field was renamed or removed; the new field is purely additive. ## Tests Adds `tests/unit_tests/test_chat_models_responses.py` covering the helper, auto-detect routing, explicit overrides in both directions, response-to-`AIMessage` conversion (content, `usage_metadata`, `response_metadata.id`), `function_call` → `tool_calls` conversion, and sync + async streaming of `response.output_text.delta` and `response.completed` events. All mocks use `MagicMock`/`AsyncMock`; no network calls. ## Notes for reviewers This was implemented with help from an AI agent. The shape mirrors `langchain-openai`'s `use_responses_api` — same field name, same helper name, same docstring style — so the diff should be familiar. Closes nothing — net new feature. --------- Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com> Co-authored-by: Mason Daugherty <github@mdrxy.com> |
||
|
Sydney Runkle
|
7bb4130c7d |
chore(langchain): bump to 1.3.2, require langgraph>=1.2.2 (#37703)
- Bumps `langchain` to **1.3.2** (patch) - Raises minimum `langgraph` requirement from `>=1.2.1` to `>=1.2.2` langgraph 1.2.2 fixes a race condition where DeltaChannel checkpoint writes could serialize `BaseMessage` objects with `id=None` before `apply_writes()` ran the reducer, causing the same message to appear with a different ID on every `get_state()` call and across resumed invocations (langchain-ai/langgraph#7913). The lockfile will be updated once langgraph 1.2.2 is published to PyPI (langchain-ai/langgraph#7914).langchain==1.3.2 |
||
|
Nick Hollon
|
d9b8dd5183 |
fix(langchain): land final answer in last AIMessage for TodoListMiddleware (#37643)
|
||
|
Mason Daugherty
|
95c6a8aa76 |
chore(core): bump uuid-utils to 0.16.0 (#37699)
Refresh `langchain-core`'s lockfile so the dev/CI environment resolves `uuid-utils` to a release that ships free-threading wheels (`cp313t`, `cp314t`). Unblocks `pip install` on Python 3.14 free-threaded builds — previously the lock pinned `0.14.1`, which had no FT wheel and forced an sdist build. Related to #34870. |
||
|
Mason Daugherty
|
c7858c46d8 |
test(anthropic): retry integration tests on transient failures (#37697)
Enable `pytest-retry` on the `integration_tests` Make target so live API flakes (e.g. `test_batch` timing out against `api.anthropic.com`) no longer fail the job on first miss. Matches the existing convention in `libs/partners/groq`. |
||
|
langchain-model-profile-bot[bot]
|
53a5ac3352 |
chore(model-profiles): refresh model profile data (#37694)
Automated refresh of model profile data for all in-monorepo partner integrations via `langchain-profiles refresh`. 🤖 Generated by the `refresh_model_profiles` workflow. Co-authored-by: mdrxy <61371264+mdrxy@users.noreply.github.com> |
||
|
langchain-model-profile-bot[bot]
|
69d9e95ef4 |
chore(model-profiles): refresh model profile data (#37650)
Automated refresh of model profile data for all in-monorepo partner integrations via `langchain-profiles refresh`. 🤖 Generated by the `refresh_model_profiles` workflow. Co-authored-by: mdrxy <61371264+mdrxy@users.noreply.github.com> |
||
|
Mason Daugherty
|
33875fde2a |
ci(infra): serialize integration test shards across runs (#37648)
Add job-level `concurrency` to the scheduled integration tests so per-package shards from overlapping workflow dispatches don't hit the same live API credentials at once — e.g. a manually triggered `anthropic` run colliding with the daily `all libs` run. |
||
|
Mason Daugherty
|
2638f75e13 |
feat(standard-tests): forward LangSmith CI env vars to traces (#37645)
Scheduled integration runs set `LANGSMITH_TAGS` and `LANGSMITH_METADATA` in `$GITHUB_ENV` (per #37615), but the LangSmith SDK does not read those env vars natively, so the tags/metadata were silently dropped. A new pytest plugin in `langchain-tests` bridges that gap by entering `langsmith.run_helpers.tracing_context` for the duration of each session. |
||
|
Mason Daugherty
|
bdd7f71a1b |
ci(infra): trace scheduled integration tests (#37615)
Wire LangSmith tracing into the scheduled integration test workflow so partner test runs emit traces to a shared project with GitHub Actions metadata attached. Makes failures traceable back to the originating workflow run, sha, and matrix shard without hunting through CI logs. ## Usage - Filter the `oss-python-integration-tests` project by the `github-actions` tag to see only CI runs; add a `sha-<sha>` or `working_directory=<partner>` filter to narrow to a specific commit or partner shard. - From a failing trace, open the `github_run_url` metadata field to jump directly to the originating workflow run; `github_run_attempt` disambiguates reruns. - Tags are flat strings (good for facets); structured fields like `python_version` and `working_directory` live in metadata for richer querying. |
||
|
Nick Hollon
|
11cdce91dc |
ci(infra): add middleware evals workflow for workflow_dispatch discovery (#37644)
Fast-track companion to #37643. GitHub's `workflow_dispatch` event is only discoverable when the workflow file exists on the default branch — even though the workflow code that runs comes from the `ref` passed to the dispatch. This PR lands the `Middleware Evals` workflow file on master so that #37643 (which adds `libs/langchain_v1/tests/evals/`) can be dispatched against the feature branch via: ```bash gh workflow run middleware_evals.yml \ --ref nh/todo-middleware-loop-contract \ --field models='claude-sonnet-4-6,...' ``` without first merging the full eval framework. ## Caveats - The workflow's pytest invocation depends on `libs/langchain_v1/tests/evals/` and the partner SDK list, neither of which exists on master yet. Dispatching with `--ref master` before #37643 lands will fail at pytest collection. That's the intended behavior — the workflow's purpose is to dispatch against branches that ship the eval suite. - Once #37643 merges to master, this workflow file already matches what #37643 adds. The merge will be a no-op for `middleware_evals.yml` itself. |
||
|
Nick Hollon
|
d08245f70d |
feat(langchain): redact streamed PII in flight on PIIMiddleware (#37616)
`PIIMiddleware` previously scrubbed detected PII only at the state level via its `after_model` / `before_model` hooks. Consumers reading the live stream — `astream_events(version="v3")` or `run.messages` / `run.tool_calls` / `run.values` — saw the raw model text, the raw tool-call args, the raw tool outputs, and the raw state snapshots until the run finished and the canonical conversation history was written. This change registers a stream transformer ahead of `MessagesTransformer` that redacts every wire surface of an agent run. The transformer holds a sliding lookback buffer (default 128 characters) per `(run_id, content-block index)` so PII patterns that straddle delta boundaries are caught before the safe prefix is released downstream. Anything older than the lookback is run through the configured detector and emitted; the trailing tail stays buffered until a later delta extends it past the cap or the block finishes. `_finalize_block` always re-runs detection over the full block snapshot so the finalized content lands fully redacted even when the in-flight buffer never released a tail (short responses, or PII arriving in the final delta). The `block` strategy is now supported on the streaming path via a buffering mode that withholds every delta until the block resolves — clean blocks release the full text at finalize, PII-bearing blocks zero the wire and let `after_model` / `apply_to_tool_results` raise `PIIDetectionError` on the original state message. Activation is gated on `apply_to_output=True`, matching the existing post-hoc semantics. The middleware's transformer factory is cloned by `StreamMux._make_child` into every subgraph scope, so attaching `PIIMiddleware` at the outer agent also redacts streamed deltas from sub-agents invoked inside tools. ## Tool-call and tools-channel coverage The transformer covers every wire surface of an agent run, not just AI message text: - **Streamed AI text deltas** (`content-block-delta` of type `text-delta`) — lookback machinery, redacted in place. - **Streamed tool-call args** (`content-block-delta` with `tool_call_chunk` / `server_tool_call_chunk` fields) — each delta carries the full cumulative args string; detection runs on the field directly and redacts in place. Verified empirically against `_compat_bridge.py` and the consumer-side `_merge_block_delta_into_store` snapshot-replace semantics. - **Finalized tool-call blocks** (`content-block-finish` with `tool_call` / `server_tool_call` / `invalid_tool_call`) — `args` dict walked recursively and each string leaf redacted. - **Tool execution events on the `tools` channel** — `tool-started.input`, `tool-output-delta`, `tool-finished.output`, `tool-error.message` all run through detection. String deltas use the same lookback machinery as text-deltas keyed by `tool_call_id`; structured payloads walk recursively. - **State snapshots on the `values` channel** — message lists are walked and each message's `.content` is redacted on a fresh copy. Graph state itself stays intact for the state-level enforcer (`apply_to_tool_results` via `before_model`) to act on independently. - **Legacy `(BaseMessage, metadata)` payloads** on the `messages` channel (Python 3.10 path, where `langgraph`'s `ASYNCIO_ACCEPTS_CONTEXT = sys.version_info >= (3, 11)` falls back to a code path that doesn't propagate the streaming callback into the chat model) — `.content` and `AIMessage.tool_calls[*].args` are scrubbed. For `block`, the event's `data` tuple is replaced with an empty-content copy so the original message stays in state for `after_model` to raise on. ## Worth a careful look - `_PIIStreamTransformer._mutate_text_delta` — lookback partition. Anything older than `lookback` characters is released after redaction; the tail stays buffered. Bulletproof against whitespace-permissive detectors (notably `credit_card`, whose regex matches across spaces). - `_PIIStreamTransformer._mutate_tool_call_chunk_delta` — direct in-place redaction of the cumulative args string. No buffer; the wire shape is cumulative-snapshot, the consumer-side merge is replace-not-append. - `_PIIStreamTransformer._mutate_legacy_payload` — the dual path: mutate-in-place for non-`block` (idempotent with `after_model`), replace-with-empty-copy for `block` (keeps original in graph state for `after_model` to raise on). - `_PIIStreamTransformer._redact_value` — the recursive walker. `BaseMessage` branch returns a fresh `.content`-redacted copy via `model_copy(update=...)` — never mutates in place — so tool-output payloads that wrap a `ToolMessage` and message lists in state snapshots flow through cleanly. - The new `transformers` attribute on `PIIMiddleware`: this is what makes `create_agent` pick the factory up. Multiple `PIIMiddleware` instances each register one transformer; ordering is preserved within the `before_builtins` lane. ## Compatibility Bumps `langgraph` to `>=1.2.1` for the `before_builtins` opt-in on `StreamTransformer`. |
||
|
langchain-model-profile-bot[bot]
|
06e65072af |
chore(model-profiles): refresh model profile data (#37626)
Automated refresh of model profile data for all in-monorepo partner integrations via `langchain-profiles refresh`. 🤖 Generated by the `refresh_model_profiles` workflow. Co-authored-by: mdrxy <61371264+mdrxy@users.noreply.github.com> |
||
ccurme
|
a1e2daf098 | release(openai): 1.2.2 (#37617) langchain-openai==1.2.2 | ||
|
open-swe[bot]
|
9e21348d73 | fix(openai): guard httpx finalizers against uninitialized instances (#37568) | ||
|
Mason Daugherty
|
74cecb4774 |
ci(infra): expand integration tests dispatch dropdown to external partners (#37614)
Adds `aws`, `google-genai`, and `google-vertexai` to the manual-run
`working-directory` dropdown on the `⏰ Integration Tests` workflow.
These partners live in external repos (`langchain-ai/langchain-google`,
`langchain-ai/langchain-aws`) and were previously only reachable via the
free-form `working-directory-override` input despite the job already
checking them out into `libs/partners/`.
|
||
|
Mason Daugherty
|
269d628d9c |
fix(standard-tests): recognize parametrize-nested xfails in override check (#37613)
`test_no_overrides_DO_NOT_OVERRIDE` only treated an override as valid when the method itself carried an `@pytest.mark.xfail(reason=...)`. Overrides that re-parametrize a standard test and xfail only a subset of cases via `pytest.param(..., marks=pytest.mark.xfail(...))` were rejected. |
||
|
Mason Daugherty
|
23d369e2f4 |
test(xai): tolerate extra block types in web search and xfail v1 streaming tool calls (#37612)
Loosen the xAI integration tests to handle two recent provider behaviors: `web_search` responses may now include block types beyond the core trio, and streaming aggregation under `output_version="v1"` does not produce a `tool_call` content block (tool calls are only available on `.tool_calls`). |
||
|
Mason Daugherty
|
aef86c476d |
chore(infra): bump langchain-tests floor to 1.1.9 (#37610)
Bumps the `langchain-tests` minimum across the monorepo from `1.0.0` to `1.1.9` and adds a partner-level `Makefile` so partner lockfiles can be regenerated in one command, matching the existing convention under `libs/`. |
||
|
Mason Daugherty
|
ebc1880444 | release(standard-tests): 1.1.9 (#37609) langchain-tests==1.1.9 | ||
|
Mason Daugherty
|
22575adba4 |
test(standard-tests): allow extra content blocks in streaming assertions (#37592)
Reasoning-emitting chat models return `[reasoning, text]` content blocks where vanilla models return `[text]`. The shared streaming integration tests asserted exactly one block, which fails when reasoning blocks are returned when streaming is otherwise correct. Relaxed to assert text presence without touching the lifecycle, `chunk_position`, or `output_version` checks. |
||
|
Nick Hollon
|
1aa4496fb4 |
feat(langchain): register stream transformers on middleware (#37591)
Adds a `transformers` attribute to `AgentMiddleware` so middleware can
declare scope-aware `StreamTransformer` factories alongside their
`tools` and lifecycle hooks. `create_agent` merges middleware-registered
factories with any caller-supplied ones at compile time.
## API
```python
class MyMiddleware(AgentMiddleware):
transformers = (MyTransformer,) # factory: (scope,) -> StreamTransformer
```
When the agent compiles, the final transformer order on the run mux is:
1. Built-in ``ToolCallTransformer``
2. Middleware-registered factories, in middleware order
3. Caller-supplied ``transformers=`` from ``create_agent``
This ordering keeps the built-in tool-call projection in front of any
consumer transformers and gives caller-supplied entries the final word.
|
||
|
Mason Daugherty
|
d2931d878f | release(fireworks): 1.4.1 (#37603) langchain-fireworks==1.4.1 |