Update all patch versions

[renovate]

This PR contains the following updates:

Package	Change	Age	Confidence
boto3	==1.43.68 → ==1.43.70
claude-agent-sdk	>=0.2.135 → >=0.2.137
langchain (changelog)	==1.3.14 → ==1.3.15
langchain (changelog)	>=1.3.14 → >=1.3.15
langchain-anthropic (changelog)	==1.5.4 → ==1.5.6
langgraph (source, changelog)	>=1.2.10 → >=1.2.11

---

Warning

Some dependencies could not be looked up. Check the Dependency Dashboard for more information.

---

Release Notes

boto/boto3 (boto3)

v1.43.70

Compare Source

=======

• api-change:dsql: [botocore] Improved validation of Kinesis stream ARN format to ensure only valid ARN characters are accepted
• api-change:glue: [botocore] Documentation updates for materialized views APIs.
• api-change:iam: [botocore] Introduced role manager, an IAM capability that automatically sets up the IAM roles your AWS services need. When you set up a supported service in the console, role manager creates a role for you or reuses an existing one from an AWS-managed template.
• api-change:mediaconnect: [botocore] AWS MediaConnect now supports tuning the internal recovery latency between Router Inputs and Outputs to prioritize stream quality versus end-to-end latency.
• api-change:odb: [botocore] Adds support for Oracle Exadata on Exascale Infrastructure (ExaDB-XS) resources including storage vaults and VM clusters.
• api-change:quicksight: [botocore] Added APIs for DLP with Microsoft Purview (manage configs with label enforcement across Spaces, Chat, Knowledge Bases), Approval Workflows (CRUD for policies on asset sharing for Agents, Knowledge Bases, Spaces), and Limits Management (limit profiles for index storage and agent hours per user).
• api-change:wellarchitected: [botocore] This change releases the Well-Architected Agent, a generative AI service that analyzes a customer's AWS environment and delivers personalized, prioritized recommendations across cost, security, performance, and resilience.

v1.43.69

Compare Source

=======

• api-change:account-access: [botocore] Adds SDK support for AWS IAM account access manager, a feature that enables mapping of IAM roles to the users and groups in AWS IAM Identity Center.
• api-change:bedrock-agentcore: [botocore] Adding online eval arn as input for recommendation API
• api-change:cleanrooms: [botocore] Adds support for exporting redacted query execution logs in AWS Clean Rooms
• api-change:clouddirectory: [botocore] Added an end-of-support notice to Amazon Cloud Directory public CLI reference documentation.
• api-change:connect: [botocore] Seven new APIs for managing custom metrics, including create, describe, update, and delete. Using Custom Metrics, customers of Amazon Connect Customer can tailor analytics dashboards to their needs by applying custom thresholds, filters, and calculations to one or more out of the box measurements.
• api-change:datazone: [botocore] GetSubscriptionGrant now returns materialized asset scope name for mapping Lake Formation data cell filters or Redshift views to subscription grants.
• api-change:eks: [botocore] This feature would give customers the ability to selectively tune certain configurations of Kubernetes control plane components in an Amazon EKS cluster.
• api-change:endpoint-rules: [botocore] Update endpoint-rules client to latest version
• api-change:organizations: [botocore] Documentation update for AWS Organizations that clarifies valid input values for the HandshakePartyType parameter in the InviteAccountToOrganization. API ORGANIZATION is valid in responses only. valid input values are ACCOUNT and EMAIL
• api-change:textract: [botocore] Amazon A2I entered maintenance mode in July 2026 and now rejects StartHumanLoop requests from accounts that it does not recognize as existing customers. This update adds a corresponding note to the HumanLoopConfig parameter documentation so that the API Reference and SDK docs explain this behavior.

anthropics/claude-agent-sdk-python (claude-agent-sdk)

v0.2.137

Compare Source

New Features

• ConversationResetMessage for conversation reset events: The SDK now surfaces the CLI's conversation_reset frame as a ConversationResetMessage dataclass, letting applications detect when a /clear or other transcript-discarding flow resets the conversation mid-session. Includes new_conversation_id, uuid, and session_id fields. This widens the Message union — code that exhaustively matches with assert_never will need updating (#​1196)
• Message origin on UserMessage and ResultMessage: New origin: MessageOrigin | None field on UserMessage and ResultMessage surfaces why a turn was initiated — distinguishing application-submitted prompts ("human") from background-task notifications, scheduled triggers, peer messages, and other session-injected turns. New exported types: MessageOrigin, MessageOriginKind, TaskNotificationOriginSubkind (#​1199)
• resume_session_at / resume_drops_turn options for truncating resume: ClaudeAgentOptions now supports resume_session_at (fork a session at an earlier transcript entry) and resume_drops_turn (validate that only entries from a specific turn are discarded). Enables safe rewind-to-before-last-prompt without silently dropping unobserved messages (#​1198)

Bug Fixes

• Seed settings.json into temp config dir on SessionStore resume: Resuming from a SessionStore now copies settings.json and cowork_settings.json into the temporary config directory, preserving apiKeyHelper auth, user hooks, env vars, and permissions. Previously, hosts authenticating solely via apiKeyHelper would fail with "Not logged in" on resume (#​1197)
• Improved error messages for failed resume: When the CLI rejects a resume (e.g. nonexistent session or resume_drops_turn guard failure), pending control requests like initialize() now receive the actual error text instead of a generic "Command failed with exit code 1" (#​1198)

Internal/Other Changes

• Updated bundled Claude CLI to version 2.1.229

v0.2.136

Compare Source

Internal/Other Changes

• Updated bundled Claude CLI to version 2.1.228

langchain-ai/langgraph (langgraph)

v1.2.11: langgraph==1.2.11

Compare Source

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)

---

Configuration

📅 Schedule: (UTC)

• Branch creation
  • "before 8am every weekday"
• Automerge
  • At any time (no schedule defined)

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

👻 Immortal: This PR will be recreated if closed unmerged. Get config help if that's undesired.

---

• If you want to rebase/retry this PR, check this box

---

This PR was generated by Mend Renovate. View the repository job log.

[Copilot]

Pull request overview

Note

Copilot could not run the full agentic suite for this review because it was automatically requested on a bot-authored pull request. Request a review from Copilot under Reviewers to retry with the full agentic suite. Improved support for bot-authored pull requests is coming soon.

Updates GenAI-related dependency versions across tests, examples, and docs to keep LangChain/LangGraph/Claude Agent SDK integrations current.

Changes:

• Bump langchain from 1.3.14 to 1.3.15 across genai-langchain tests and examples.
• Bump langgraph minimum version from 1.2.10 to 1.2.11 in workflow/tools/agent examples.
• Bump claude-agent-sdk to >=0.2.136 and align related docs/test requirements (plus minor bumps to langchain-anthropic and boto3 in latest test requirements).

Reviewed changes

Copilot reviewed 11 out of 13 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
instrumentation/opentelemetry-instrumentation-genai-langchain/tests/requirements.latest.txt	Updates pinned “latest” test dependencies (LangChain, LangChain Anthropic, boto3).
instrumentation/opentelemetry-instrumentation-genai-langchain/examples/zero-code/requirements.txt	Bumps LangChain pin used by the zero-code example.
instrumentation/opentelemetry-instrumentation-genai-langchain/examples/zero-code/pyproject.toml	Bumps LangChain pin in the example’s Python project metadata.
instrumentation/opentelemetry-instrumentation-genai-langchain/examples/workflow/requirements.txt	Raises minimum LangChain and LangGraph versions for workflow example.
instrumentation/opentelemetry-instrumentation-genai-langchain/examples/tools/requirements.txt	Updates LangChain pin and LangGraph minimum for tools example.
instrumentation/opentelemetry-instrumentation-genai-langchain/examples/manual/requirements.txt	Bumps LangChain pin used by the manual example.
instrumentation/opentelemetry-instrumentation-genai-langchain/examples/manual/pyproject.toml	Bumps LangChain pin in the example’s Python project metadata.
instrumentation/opentelemetry-instrumentation-genai-langchain/examples/agent/requirements.txt	Raises minimum LangChain and LangGraph versions for agent example.
instrumentation/opentelemetry-instrumentation-genai-claude-agent-sdk/examples/zero-code/requirements.txt	Raises minimum Claude Agent SDK version for zero-code example.
instrumentation/opentelemetry-instrumentation-genai-claude-agent-sdk/examples/manual/requirements.txt	Raises minimum Claude Agent SDK version for manual example.
docs-requirements.txt	Aligns docs build requirements with the bumped SDK/LangChain versions.

---

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

[opentelemetry-pr-dashboard]

Pull request dashboard status

Waiting on maintainers · refreshed 2026-08-13 03:31 UTC

Merge when ready.

Status above doesn't look right?

• Just replied or pushed? Anything around or after the refresh time above may not be picked up yet — give it a few minutes.
• Anything look wrong? Report it with what you expected; it helps us improve the dashboard.

[eternalcuriouslearner]

rerunning failed jobs. Checking the reason for failure.

[eternalcuriouslearner]

CI is green again, we can merge this.