chore(deps): bump the uv-minor-and-patch group across 1 directory with 28 updates

[dependabot]

Bumps the uv-minor-and-patch group with 26 updates in the / directory:

Package	From	To
band-client-rest	0.0.27	0.0.32
python-dotenv	1.2.2	1.2.3
filelock	3.28.0	3.32.5
python-json-logger	4.1.0	4.2.0
letta-client	1.10.3	1.12.1
langchain	1.3.14	1.4.0
langchain-openai	1.2.1	1.6.0
langchain-anthropic	1.4.3	1.7.1
claude-agent-sdk	0.2.125	0.2.152
github-copilot-sdk	1.0.5	1.0.11
crewai	1.15.5	1.15.20
starlette	1.3.1	1.6.0
uvicorn	0.51.0	0.52.4
python-multipart	0.0.26	0.0.32
click	8.4.2	8.5.0
agent-client-protocol	0.12.0	0.12.1
slack-sdk	3.42.0	3.44.1
aiohttp	3.13.5	3.14.3
boto3	1.42.91	1.43.88
fastapi	0.140.0	0.141.1
pytest	9.0.3	9.1.1
pytest-rerunfailures	16.4	16.6.1
pydantic-ai-slim	2.18.0	2.39.0
pre-commit	4.5.1	4.6.2
ruff	0.15.11	0.16.6
commitizen	4.13.10	4.18.0

Updates band-client-rest from 0.0.27 to 0.0.32

Commits

• See full diff in compare view

Updates python-dotenv from 1.2.2 to 1.2.3

Release notes

Sourced from python-dotenv's releases.

v1.2.3

Fixed

• Strip a leading UTF-8 BOM from .env file contents so the first variable is no longer silently lost when the file is saved with BOM (e.g. by some JetBrains IDEs on Windows) by [@​h1whelan] in #640
• set_key now escapes backslashes, so values containing them (Windows paths, regular expressions) survive a write/read round-trip. Quoted values ending in an escaped backslash are no longer mis-parsed as an escaped quote, which used to swallow the following lines by [@​dchaudhari7177] in #680
• dotenv run now prints a friendly error instead of a traceback when no command is given by [@​bbc2] in #606
• Cache the parsed result for empty .env files so repeated dotenv_values/load_dotenv calls no longer re-read the file by [@​ReinerBRO] in #638

Changelog

Sourced from python-dotenv's changelog.

[1.2.3] - 2026-08-16

Fixed

• Strip a leading UTF-8 BOM from .env file contents so the first variable is no longer silently lost when the file is saved with BOM (e.g. by some JetBrains IDEs on Windows) by [@​h1whelan] in #640
• set_key now escapes backslashes, so values containing them (Windows paths, regular expressions) survive a write/read round-trip. Quoted values ending in an escaped backslash are no longer mis-parsed as an escaped quote, which used to swallow the following lines by [@​dchaudhari7177] in #680
• dotenv run now prints a friendly error instead of a traceback when no command is given by [@​bbc2] in #606
• Cache the parsed result for empty .env files so repeated dotenv_values/load_dotenv calls no longer re-read the file by [@​ReinerBRO] in #638

Commits

• 49515af Bump version: 1.2.2 → 1.2.3
• 8ac846f chore: add release runbook (RELEASING.md) and make release target
• bb31c94 docs: add 1.2.3 release notes (#606, #638, #680)
• f7b18d9 fix: round-trip backslashes through set_key (#680)
• 751f8c1 ci(deps): bump actions/checkout from 6.0.2 to 6.0.3 in the github-actions gro...
• f1937b6 chore(deps): update mkdocs-include-markdown-plugin requirement from >=6.0.0 t...
• 45b9372 chore(deps): update pytest requirement from >=3.9 to >=9.0.3 (#653)
• 72896e9 docs: fix broken mkdocs link in CONTRIBUTING.md (#636)
• 72754a1 ci(deps): bump peaceiris/actions-gh-pages from 4.0.0 to 4.1.0 in the github-a...
• 078325e ci(security): harden CI/CD supply chain with SHA pinning and least-privilege ...
• Additional commits viewable in compare view

Updates filelock from 3.28.0 to 3.32.5

Release notes

Sourced from filelock's releases.

3.32.5

What's Changed

• 🧪 test(fork): report where a stalled fork stops by @​gaborbernat in tox-dev/filelock#715
• 📝 docs: say that mode is read-only in the thread-local section by @​Gares95 in tox-dev/filelock#716
• 🐛 fix(lease): clear token after failed acquire by @​lprnmns in tox-dev/filelock#721

New Contributors

• @​lprnmns made their first contribution in tox-dev/filelock#721

Full Changelog: tox-dev/filelock@3.32.4...3.32.5

3.32.4

What's Changed

• 🐛 fix: retry transient denials on open and claim read by @​gaborbernat in tox-dev/filelock#705
• 🧪 test: deflake six scheduled-run failures by @​gaborbernat in tox-dev/filelock#704
• 🧪 test: cover a reclaimed private record for real by @​gaborbernat in tox-dev/filelock#706
• 🧪 test(fork): fork once the event loop has closed by @​gaborbernat in tox-dev/filelock#714
• 🔧 chore: batch dependency updates weekly on Tuesday by @​gaborbernat in tox-dev/filelock#713
• escape the hostname every marker publishes by @​dxbjavid in tox-dev/filelock#709

Full Changelog: tox-dev/filelock@3.32.3...3.32.4

3.32.3

What's Changed

• 🧪 test(strict): deflake close-fault injections on graalpy by @​gaborbernat in tox-dev/filelock#697
• 📄 docs: publish llms.txt from the docs build by @​gaborbernat in tox-dev/filelock#700
• 🐛 fix(fork): survive audit events during interpreter shutdown by @​gaborbernat in tox-dev/filelock#703

Full Changelog: tox-dev/filelock@3.32.2...3.32.3

3.32.2

What's Changed

• Fix test failures on NetBSD (#689) by @​gaborbernat in tox-dev/filelock#693
• 🧪 test(soft-rw): deflake writer phase-2 peer-marker test by @​gaborbernat in tox-dev/filelock#694
• hand back the claim when a heartbeat thread fails to start by @​dxbjavid in tox-dev/filelock#691
• 🧪 test(unix): deflake sticky-bit concurrent-unlink on graalpy by @​gaborbernat in tox-dev/filelock#695

Full Changelog: tox-dev/filelock@3.32.1...3.32.2

... (truncated)

Changelog

Sourced from filelock's changelog.

########### Changelog ###########

.. towncrier-draft-entries:: Unreleased

.. towncrier release notes start

---

3.32.5 (2026-08-31)

---

• SoftFileLease.token and AsyncSoftFileLease.token now read None after a failed acquisition, so a contender turned away by a live holder no longer reports a token for a claim it never published. :pr:721
• Document that mode has no setter: unlike poll_interval, timeout, blocking and lifetime, it is fixed at construction and lock.mode = ... raises AttributeError. :pr:716

---

3.32.4 (2026-08-23)

---

• StrictSoftFileLock always retries a claim read whose first attempt reports the claim as pending, so a first read that itself outlasts the retry grace no longer fails closed on a claim it could have read. :pr:705
• WindowsFileLock waits out a transient STATUS_ACCESS_DENIED from NtCreateFile for up to half a second before raising PermissionError, since a peer unlinking the lock file as it releases can answer that for a moment; a real denial still fails fast. :pr:705
• Every lock class now escapes the hostname it publishes, so a host whose socket.gethostname() carries a space, a newline or a byte outside UTF-8 no longer writes a marker it reads back as malformed. Such a host used to lose a held SoftReadWriteLock read slot to a peer and could not take a write slot or a StrictSoftFileLock at all. :pr:709

---

3.32.3 (2026-08-13)

---

• The fork-safety audit hook no longer prints Exception ignored in audit hook with a TypeError when an audit event fires during interpreter shutdown, after CPython has already cleared the module globals. :pr:701

---

3.32.2 (2026-07-29)

---

• A SoftReadWriteLock or SoftFileLease acquire whose heartbeat thread fails to start now unlinks its marker and hands the claim back, instead of leaving an unrefreshed marker a peer takes while the caller believes it still holds the lock. :pr:691

---

3.32.1 (2026-07-26)

---

• Canceling an AsyncSoftReadWriteLock acquire now releases the claim instead of leaking a marker whose heartbeat wedges every contender. :pr:686

... (truncated)

Commits

• 1585dfe Release 3.32.5
• 00177c3 🐛 fix(lease): clear token after failed acquire (#721)
• 5aeb9b6 📝 docs: say that mode is read-only in the thread-local section (#716)
• 2634dd1 [pre-commit.ci] pre-commit autoupdate (#720)
• 37dccf0 🧪 test(fork): report where a stalled fork stops (#715)
• cb493d6 Release 3.32.4
• fe07a11 escape the hostname every marker publishes (#709)
• 232732f 🔧 chore: batch dependency updates weekly on Tuesday (#713)
• 2966eb5 🧪 test(fork): fork once the event loop has closed (#714)
• 61511eb build(deps): bump astral-sh/setup-uv from 10.0.0 to 10.0.1 (#712)
• Additional commits viewable in compare view

Updates python-json-logger from 4.1.0 to 4.2.0

Release notes

Sourced from python-json-logger's releases.

4.2.0

4.2.0 - 2026-08-15

Changed

• Logging a dict no longer modifies it. exc_info and stack_info were previously added to the caller's dict. #66
• Move development dependencies from project.optional-dependencies.dev to [dependency-groups].dev (PEP 735). #46

Fixed

• $ style formats now support unbraced $name fields, not just ${name}. #18

Thanks @​gaoflow, @​prateek-dagar, @​Sanjays2402

Changelog

Sourced from python-json-logger's changelog.

4.2.0 - 2026-08-15

Changed

• Logging a dict no longer modifies it. exc_info and stack_info were previously added to the caller's dict. #66
• Move development dependencies from project.optional-dependencies.dev to [dependency-groups].dev (PEP 735). #46

Fixed

• $ style formats now support unbraced $name fields, not just ${name}. #18

Thanks @​gaoflow, @​prateek-dagar, @​Sanjays2402

Commits

• 806dba9 Release 4.2.0
• 010b730 [core] Fixup doc-strings, remove outdated comments
• b865bd3 [core] support unbraced $name fields in $ style formats (#69)
• 23a2c12 test: Add tests for exception notes, exception groups, and exception note gro...
• 355e44f docs: fix spelling typos in docs and core docstrings (#71)
• 0fcfc06 Move development dependencies to dependency-groups (PEP 735) (#70)
• 2557bbc fix: prevent mutation of original dict when record.msg is a dict (#66)
• 3cc30fc Fix tox build failure under PyPy 3.10 by conditionally pinning mypy<2 (#68)
• 01cb83c [docs.security] Fix type on last date
• See full diff in compare view

Updates letta-client from 1.10.3 to 1.12.1

Release notes

Sourced from letta-client's releases.

v1.12.1

SDK 1.12.1.

• Adds generated SDK support for environment endpoints.
• Includes the latest generated SDK updates promoted from staging.

v1.12.0

What's Changed

• Release SDK updates by @​kianjones9 in letta-ai/letta-python#90

Full Changelog: letta-ai/letta-python@v1.11.0...v1.12.0

v1.11.0

1.11.0 (2026-05-14)

Full Changelog: v1.10.3...v1.11.0

Features

• cap v1 limit query params (b5edad1)
• core: add moonshot and kimi code BYOK providers (0b0940b)
• internal/types: support eagerly validating pydantic iterators (8d289a9)
• support setting headers via env (f0c2ba8)

Bug Fixes

• client: add missing f-string prefix in file type error message (cbf36eb)
• use correct field name format for multipart file arrays (1039e5a)

Performance Improvements

• core: reduce conversation send hot-path reads (8a7b06e)

Chores

• internal: more robust bootstrap script (074fe85)
• internal: reformat pyproject.toml (d9a6109)

Refactors

• hard-deprecate isolated conversation blocks (ed0a3d4)
• stop creating new isolated conversation blocks (aa75f2a)

Commits

• db2d937 Merge pull request #94 from letta-ai/stainless/release
• e01c63a chore(release): bump python SDK to 1.12.1
• a40a98d Merge pull request #93 from letta-ai/stainless/release
• ade51eb fix: reconcile stlc promotion workflow on python staging
• d5583f3 chore(ci): restore stlc promote workflow
• 3398f6a Build SDK
• 52071c7 docs: expose environment endpoints in API reference
• fac4f36 Build SDK
• 708784d Build SDK
• 35554ff Merge pull request #90 from letta-ai/stainless/release
• Additional commits viewable in compare view

Updates langchain from 1.3.14 to 1.4.0

Release notes

Sourced from langchain's releases.

langchain-perplexity==1.4.0

Changes since langchain-perplexity==1.3.2

release(perplexity): 1.4.0 (#37993) feat(perplexity): bind_tools and Responses-API tool round-trip (#37934) hotfix(openai): min core dep (#37990)

langchain-openai==1.4.0

Changes since langchain-openai==1.3.5

release(openai): 1.4.0 (#38983) chore: bump pillow from 12.2.0 to 12.3.0 in /libs/partners/openai (#38999) feat(core): add reasoning_effort as a standard chat model parameter (#38887) chore(model-profiles): refresh model profile data (#38797)

langchain==1.4.0

Changes since langchain==1.3.18

docs(langchain): runnable langchain.mcp examples (#39976) feat(langchain): langchain.mcp namespace, MCPAdapter (#39939) perf(anthropic,langchain): omit middleware trace inputs (#40098) fix(langchain): include model destination in agent tool routing (#38355) chore(langchain): bump vcrpy test dependency minimum to >=8.2.0 (#39942)

langchain==1.4.0a4

Initial release

release(langchain): 1.4.0a4 test(langchain): cover mixed-era ClientGroup and group elicitation Update libs/langchain_v1/langchain/mcp/adapter.py fix(langchain): drive MCP elicitation via member session for fastmcp 4.0.1 fix(sdk): use latest fastmcp and rm reentrant impl cr cr refactor(langchain): inline MCP client arming into __init__ refactor(langchain): stamp an arm marker instead of introspecting the handler closure fix(langchain): gate MCP interrupt routing on the negotiated protocol era refactor(langchain): drop MCP elicitation flag, derive interrupt routing from the client fix(sdk): add _ReentrantClientGroup fix(langchain): narrow MCPAdapter.client union in mcp tests for mypy chore(langchain): format mcp/adapter.py release(langchain): 1.4.0a3 feat(langchain): group MCP tool metadata under an mcp namespace refactor(langchain): stop exporting MCPAdapterTarget from langchain.mcp refactor(langchain): rename convert_mcp_tool_to_langchain_tool to as_langchain_tool refactor(langchain): rename MCPAdapter.get_tools to list_tools feat(langchain): expose cache_mode on MCPAdapter.get_tools chore(langchain): require fastmcp 4.0.0 feat(langchain): accept a ClientGroup as an MCPAdapter target feat(langchain): mark the langchain.mcp namespace as beta

... (truncated)

Commits

• 79cab2d release(anthropic): 1.7.1 (#40181)
• 1e6a4f0 chore(model-profiles): refresh model profile data (#40171)
• 8330dfe docs(langchain): runnable langchain.mcp examples (#39976)
• 280442b feat(langchain): langchain.mcp namespace, MCPAdapter (#39939)
• f5ee2b6 chore(chroma): bump Pygments security constraint (#40162)
• 234255c chore(model-profiles): refresh model profile data (#40009)
• 79e0e4a chore(deps): bump mistune from 3.3.0 to 3.3.3 in /libs/langchain (#40149)
• e90201b chore(deps): bump mistune from 3.3.0 to 3.3.3 in /libs/core (#40150)
• 4240248 chore(deps): bump mistune from 3.3.0 to 3.3.3 in /libs/text-splitters (#40148)
• 530290a chore(deps): bump uv to 0.12.8 (#40092)
• Additional commits viewable in compare view

Updates langchain-core from 1.5.0 to 1.6.2

Release notes

Sourced from langchain-core's releases.

langchain-core==1.6.2

Changes since langchain-core==1.6.1

release(core): 1.6.2 (#40209) feat(openai): support async tools (#40208) chore(deps): bump mistune from 3.3.0 to 3.3.3 in /libs/core (#40150) chore(deps): bump tornado from 6.5.7 to 6.5.8 in /libs/core (#40113) fix(core): avoid mutation in google-genai standard content (#40023) fix(core): avoid mutation in bedrock converse standard content (#40022)

langchain-core==1.6.1

Changes since langchain-core==1.6.0

revert: release(core): 1.6.2 (#39971) release(core): 1.6.2 (#39967) fix(core): shore up indexing in genai v1 streaming content (#39964) fix(core): make StructuredTool JSON-serializable (#39631) chore(deps): bump minor and patch dependencies (#39869) release(core): 1.6.1 (#39832) feat(core): propagate gateway information on error path (#39829)

langchain-core==1.6.0

Changes since langchain-core==1.5.6

release(core): 1.6.0 (#39760) fix(core): resolve postponed annotations in StructuredTool._injected_args_keys (#39602) feat(core): add standard model exception types (#39538) fix(core): allow deserializing RunnablePick (#39753) fix(core): make convert_to_openai_function handle callables and non-dict mappings (#39750) fix(core): make subprocess and temporary file tests portable on Windows (#39664) fix(core): fail fast when tool schemas can't resolve forward refs during serialization (#39570) test(core): avoid version-dependent runnable snapshots (#39705) fix(core): require all nested properties for strict tool schemas (#39306) fix(core): remove stale sync-stream xfail [closes #39720] (#39723) perf(core): Lazily import transformers (#38037) fix(core): accept non-dict Mapping values in mustache templates (#39680) docs(core): clarify Runnable pipe coercion [closes #39075] (#39707) fix(core): finalize chain-group runs on BaseException (#39699)

langchain-core==1.5.6

Changes since langchain-core==1.5.5

chore(core): release 1.5.6 (#39704) feat(core): incorporate gateway metadata to traces (#39703)

langchain-core==1.5.5

Changes since langchain-core==1.5.4

release(core): 1.5.5 (#39655) fix(core): make abatch_iterate consistent with batch_iterate for None and zero size (#39367)

... (truncated)

Commits

• 8215039 release(core): 1.6.2 (#40209)
• 3f212e7 feat(openai): support async tools (#40208)
• 1a3d817 feat(openai): support configuration_update (#40201)
• aac7904 chore(model-profiles): refresh model profile data (#40198)
• 0d50cbd docs: add openwiki (#40183)
• 79cab2d release(anthropic): 1.7.1 (#40181)
• 1e6a4f0 chore(model-profiles): refresh model profile data (#40171)
• 8330dfe docs(langchain): runnable langchain.mcp examples (#39976)
• 280442b feat(langchain): langchain.mcp namespace, MCPAdapter (#39939)
• f5ee2b6 chore(chroma): bump Pygments security constraint (#40162)
• Additional commits viewable in compare view

Updates langgraph from 1.2.9 to 1.2.11

Release notes

Sourced from langgraph's releases.

langgraph==1.2.11

Changes since 1.2.10

• release(langgraph): 1.2.11 (#8595)
• feat(langgraph): expose trace_policy on add_node (#8523)
• chore(deps): bump the minor-and-patch group across 1 directory with 7 updates (#8533)
• chore(deps): bump the minor-and-patch group across 1 directory with 5 updates (#8532)
• release(checkpoint-postgres): 3.1.2 (#8565)
• release(checkpoint): 4.2.0 (#8563)
• fix(checkpoint): collect writes at plain-value seed in delta channel history (#8526)
• chore: enforce PLC0415 in tests for the remaining packages (#8547)
• test(checkpoint-postgres,checkpoint-sqlite): run the conformance suite (#8537)
• chore: enable RUF100 and clear unused noqa directives (#8546)
• chore(deps-dev): bump types-requests from 2.33.0.20260518 to 2.33.0.20260712 in /libs/langgraph (#8502)
• chore(deps): bump cryptography from 48.0.1 to 50.0.0 in /libs/langgraph (#8528)
• release(checkpoint-sqlite): 3.1.1 (#8481)
• release(checkpoint-postgres): 3.1.1 (#8480)

langgraph==1.2.10

Changes since 1.2.9

• release(langgraph): 1.2.10 (#8462)
• chore(deps): bump jupyterlab from 4.5.9 to 4.5.10 in /libs/langgraph (#8440)
• chore(deps): bump setuptools from 80.9.0 to 83.0.0 in /libs/langgraph (#8435)
• feat(langgraph): type v3 stream_events return and native projections (#8389)
• revert(langgraph): delete TracePolicy (#8403)
• feat(langgraph): drop tags from TracePolicy (#8402)
• feat(langgraph): expose trace_policy on add_node (#8362)
• chore(deps): bump mistune from 3.2.1 to 3.3.0 in /libs/langgraph (#8317)
• chore(deps): bump soupsieve from 2.8.1 to 2.8.4 in /libs/langgraph (#8318)
• chore(cli): allow langgraph-api versions up to 1.0.0 (#8319)

Commits

• 644815f release(langgraph): 1.2.11 (#8595)
• 7d6b579 feat(langgraph): expose trace_policy on add_node (#8523)
• d56666f chore(deps): bump the minor-and-patch group across 1 directory with 7 updates...
• 6a2822d chore(deps): bump the minor-and-patch group across 1 directory with 5 updates...
• fde3068 release(checkpoint-postgres): 3.1.2 (#8565)
• f55e772 release(checkpoint): 4.2.0 (#8563)
• a90ab44 fix(checkpoint): collect writes at plain-value seed in delta channel history ...
• ea5f9cc chore: enforce PLC0415 in tests for the remaining packages (#8547)
• 36a505a test(checkpoint-postgres,checkpoint-sqlite): run the conformance suite (#8537)
• d569e18 fix(checkpoint-postgres): find plain-value seeds when walking delta history (...
• Additional commits viewable in compare view

Updates langchain-openai from 1.2.1 to 1.6.0

Release notes

Sourced from langchain-openai's releases.

langchain-openai==1.6.0

Changes since langchain-openai==1.5.2

release(openai): 1.6.0 (#39762) feat(core): add standard model exception types (#39538) fix(openai): raise clear error on unexpected response type in _create_chat_result (#39731)

langchain-openai==1.5.2

Changes since langchain-openai==1.5.1

release(openai): 1.5.2 (#39719) fix(openai): preserve reasoning item boundaries (#39278) release(openai): 1.5.2a1 (#39709) feat(openai): extract gateway metadata from response headers when available (#39706) chore(openai): update snapshots (#39657) fix(openai): support o-series models in get_num_tokens_from_messages (#38710)

langchain-openai==1.5.2a1

Initial release

release(openai): 1.5.2a1 (#39709) feat(openai): extract gateway metadata from response headers when available (#39706) chore(openai): update snapshots (#39657) fix(openai): support o-series models in get_num_tokens_from_messages (#38710) release(openai): 1.5.1 (#39653) fix(openai): preserve streamed encrypted reasoning (#39635) chore(infra): support langsmith gateway in CI (#39651) release(openai): 1.5.0 (#39629) feat(openai): support openai 3.0 SDK (#39613) chore(partners): bump langgraph floor in openai and huggingface lockfiles (#39617) release(openai): 1.4.3 (#39485) fix(openai): filter invalid tool calls from content (#39366) chore(openai): update guidance for responses API for OpenAI-compatible providers (#39327) chore(openai): update docstring for include_response_headers (#39326) release(openai): 1.4.2 (#39322) fix(openai): handle ContextWindowExceededError (#39300) chore: bump the minor-and-patch group across 3 directories with 7 updates (#39187) fix(openai): filter langchain-generated content block IDs (#39209) fix(openai): preserve Responses text options (#39204) fix(openai): redact MCP authorization (#39155) chore(model-profiles): refresh model profile data (#39050) release(openai): 1.4.1 (#39045) feat(anthropic,fireworks,openai): support langsmith gateway through env var (#38742) fix(openai): correct gpt-5.3-chat-latest profile (#39009) release(openai): 1.4.0 (#38983) chore: bump pillow from 12.2.0 to 12.3.0 in /libs/partners/openai (#38999) feat(core): add reasoning_effort as a standard chat model parameter (#38887) chore(model-profiles): refresh model profile data (#38797) release(openai): 1.3.5 (#38785) feat(openai): support explicit prompt caching (#38762)

... (truncated)

Commits

• 3478c28 release(anthropic): 1.6.0 (#39763)
• 420dfc9 release(openai): 1.6.0 (#39762)
• 85602c3 release(core): 1.6.0 (#39760)
• 5c3538e fix(core): resolve postponed annotations in `StructuredTool._injected_args_ke...
• 9984a87 feat(core): add standard model exception types (#39538)
• b3e9eef chore(model-profiles): refresh model profile data (#39751)
• ded2a1f fix(core): allow deserializing RunnablePick (#39753)
• 04ae744 fix(core): make convert_to_openai_function handle callables and non-dict ma...
• 37f2662 feat(langchain): support custom token_counter in ContextEditingMiddleware (#3...
• 2019bf5 fix(openai): raise clear error on unexpected response type in `_create_chat_r...
• Additional commits viewable in compare view

Updates langchain-anthropic from 1.4.3 to 1.7.1

Release notes

Sourced from langchain-anthropic's releases.

langchain-anthropic==1.7.1

Changes since langchain-anthropic==1.7.0

release(anthropic): 1.7.1 (#40181) perf(anthropic,langchain): omit middleware trace inputs (#40098) feat(anthropic): add Claude Fable 5.1 support (#40106)

langchain-anthropic==1.7.0

Changes since langchain-anthropic==1.6.1

release(anthropic): 1.7.0 (#39963) feat(anthropic): support top-level param for skills via container; updates thinking display mode (#39962) feat(anthropic): support 1.0 sdk (#39938) fix(anthropic): auto-append advisor-tool-2026-03-01 beta header for advisor_20260301 tool (#39917) feat(anthropic): surface gateway response metadata (#39809)

langchain-anthropic==1.6.1

Changes since langchain-anthropic==1.6.0

release(anthropic): 1.6.1 (#39804) fix(anthropic): filter invalid tool calls from v1 content (#39803)

langchain-anthropic==1.6.0

Changes since langchain-anthropic==1.5.6

release(anthropic): 1.6.0 (#39763) feat(core): add standard model exception types (#39538) fix(anthropic): exclude sibling directories from grep search scope (#39681) chore(infra): support langsmith gateway in CI (#39651)

langchain-anthropic==1.5.6

Changes since langchain-anthropic==1.5.5

release(anthropic): 1.5.6 (#39622) fix(anthropic): normalize tool_search_tool_result blocks (#39621) fix(anthropic): correct model profile data for Fable 5, Sonnet 5, Opus 4.1 (#39604)

langchain-anthropic==1.5.5

Changes since langchain-anthropic==1.5.4

release(anthropic): 1.5.5 (#39597) fix(anthropic): report reasoning tokens in usage metadata (#39590) fix(anthropic): fix KeyError on rename in Claude file-tool middleware (#39293) chore(model-profiles): refresh model profile data (#39299) fix(anthropic): clearer error when no credentials are configured (#39285)

langchain-anthropic==1.5.4

Changes since langchain-anthropic==1.5.3

release(anthropic): 1.5.4 (#39277)

... (truncated)

Commits

• 79cab2d release(anthropic): 1.7.1 (#40181)
• 1e6a4f0 chore(model-profiles): refresh model profile data (#40171)
• 8330dfe docs(langchain): runnable langchain.mcp examples (#39976)
• 280442b feat(langchain): langchain.mcp namespace, MCPAdapter (#39939)
• f5ee2b6 chore(chroma): bump Pygments security constraint (#40162)
• 234255c chore(model-profiles): refresh model profile data (#40009)

[amit-gazal-band]

🔍 Reviewed by the dependabot-triage skill — not approved as-is, left open.

This PR's own CI is RED, and batch-testing confirmed why: it bundles 26 packages via Dependabot's uv-minor-and-patch group, and 2 of them break real things when applied together with the rest of this repo's dependency graph:

• ruff (0.15.11 → 0.16.6): with this repo's unchanged [tool.ruff.lint] config (extend-select = ["PLC0415"] on ruff's default E4/E7/E9/F), the newer ruff reports 1459 new findings across the repo that the current version reports zero of — a real behavior regression against pinned config, not a real code-quality backlog.
• pydantic-ai-slim (2.18.0 → 2.38.0): now depends on an internal httpx2 client. Constructing a live PydanticAIAdapter against an OpenAI model raises TypeError: Invalid http_client argument; Expected httpx.AsyncClient but got httpx2.AsyncClient inside openai's own client init — pydantic-ai's infer_provider hands openai a client type it explicitly rejects. This breaks every real OpenAI-backed pydantic_ai turn, confirmed via tests/test_capability_gating_e2e.py::test_pydantic_ai_adapter_renders_memory_section_when_enabled.

The other 24 packages in this group (band-client-rest, langchain/langchain-openai/langchain-anthropic, claude-agent-sdk, github-copilot-sdk, crewai, starlette, uvicorn, python-multipart, click, agent-client-protocol, slack-sdk, aiohttp, boto3, fastapi, pytest, pytest-rerunfailures, pre-commit, commitizen, python-dotenv, filelock, python-json-logger, letta-client) all validated cleanly in the same consolidated batch (full suite, crewai in dev-crewai, integration, core e2e baseline lane) — see the root-uv batch's commits for the applied versions. Two of those (band-client-rest, crewai) needed small fixes for real API-surface changes (band-client-rest now types ChatMessage.metadata as a ChatMessageMetadata model instead of a plain dict — several call sites assumed the dict shape and needed normalizing).

Since Dependabot groups can't be partially merged, this PR can't be approved as a whole. Options for a maintainer: (a) manually apply the 24 safe bumps (already done on a local batch branch) and close this PR once Dependabot stops re-proposing the safe set, or (b) wait on ruff/pydantic-ai-slim fixes and let this PR re-resolve once they're excluded/fixed upstream.

Filed follow-ups for both blocking packages: see the linked Linear issue. Leaving this PR open (not closed, no ignore entry).