Tool Use

langchain-tests version 1.1.5 release includes dependency updates across multiple directories, a ruff version bump to 0.15, langsmith upgrade from 0.4.56 to 0.6.3, and modifications to the test suite for sandbox-only execution. This is a maintenance release focused on dependency management and testing infrastructure improvements.

langchain-core version 1.2.14 was released with bug fixes for merge_lists with parallel tool calls, temperature parameter handling in LangSmith tracing, recursion errors in args_schema, and index/timestamp preservation during merging. The release also includes documentation updates for security best practices, removal of langserve from sys info utilities, and dependency bumps.

langchain-core version 1.2.15 was released with improvements to error messaging for non-JSON-serializable tool schemas, enhanced typing/documentation for chat model callbacks, and performance optimizations through deferred langsmith imports. The release also includes a new ChatAnthropicBedrock wrapper for Anthropic integration and updates to deprecated model IDs in tests.

langchain-anthropic version 1.3.4 release includes bug fixes for OpenAI response block filtering, model ID updates, and integration test improvements. Key features added include ChatAnthropicBedrock wrapper, User-Agent header support for Anthropic API calls, and max input token configuration based on context beta headers.

LangChain Core version 1.2.16 has been released with a bug fix that treats empty tool chunk IDs as missing during merge operations. This patch addresses an issue in the core library's tool handling functionality.

langchain-core version 1.2.17 has been released with a key fix for extracting usage metadata from serialized tracer message outputs. The release also includes dependency updates across multiple directories.

LangChain released langchain-openrouter version 0.1.0 with significant enhancements including streaming token usage support, cost tracking in response metadata, standard model properties, and default headers. The release includes bug fixes for SDK compatibility and model profile improvements.

OpenAI Agents Python SDK v0.9.0 drops Python 3.9 support and introduces configurable timeout handling for function tools with options for timeout_seconds, timeout_behavior, and timeout_error_function. The release also narrows the Agent#as_tool() return type to FunctionTool, adds ToolOutputTrimmer for context management, and includes fixes for tracing and audio buffer handling.

OpenAI Agents Python v0.9.1 release includes critical bug fixes for input history materialization, tracing function spans, import-time fork hazards, and nested agent-tool state persistence. The release also bumps the RunState schema to 1.1 with explicit backward-read policy and includes comprehensive documentation updates.

OpenAI Agents Python v0.9.2 introduces a new `reasoning_item_id_policy: 'omit'` option for RunConfig to prevent 400 errors when using reasoning models with inconsistent item sets. The release includes fixes for reasoning item filtering in nested handoffs and voice trace handling, plus documentation updates.

OpenAI Agents Python v0.9.3 release fixes an issue where total_tokens was incorrectly included in OpenAI tracing usage payloads. This patch update addresses a bug in the tracing functionality to ensure proper payload formatting.

OpenAI Agents Python v0.10.0 introduces WebSocket mode support for the Responses API as an opt-in feature, enabling more efficient real-time communication. The release includes utilities like `responses_websocket_session()` and configuration options to enable WebSocket connections globally or per-agent, along with bug fixes for token usage tracking.

OpenAI Agents Python v0.10.1 release includes a fix for syncing realtime model literals in the realtime config. Documentation updates cover websocket support for responses, and translated document pages have been updated.

OpenAI Agents Python v0.10.2 release includes bug fixes for trace reattachment without duplicates, oversized tracing span payload sanitization, MCP policy approval requirements, and exposure of model request IDs on raw responses. The release also includes documentation structure improvements and updates to translated pages.

OpenAI Agents Python v0.10.3 release includes new features for exposing immutable agent tool invocation metadata on run results and adding RunResult tool_context accessor for agent tools. Performance improvements include using deque for BFS queue and voice task ordering, along with comprehensive documentation updates and test enhancements.

OpenAI Agents Python v0.10.4 release includes a critical fix for isolating parallel function tool failures to prevent cascading errors. The release also improves documentation navigation and entry points, updates translated documentation, and adds stability checks for async teardown operations.

OpenAI Agents Python v0.10.5 release adds explicit MultiProvider prefix modes and improves error handling by returning McpError as structured results instead of crashing agent runs. The release includes extensive documentation improvements for Dapr sessions, realtime transport, agent runtime flows, and fixes Python 3.11+ compatibility issues.

Google ADK Python v1.20.0 introduces multi-provider LLM support (Claude, LiteLLM), streaming function call arguments, and a new APIRegistryToolset for Cloud API integration. The release includes numerous bug fixes for agent validation, response processing, path handling, and LLM compatibility improvements.

Google ADK Python v1.21.0 introduces support for the Gemini Interactions API, enhances tools with header providers and SSL verification, upgrades BigQueryAgentAnalytics to v2.0, and adds Gemma3Ollama model integration. The release includes numerous bug fixes for LiteLLM response formatting, Spanner client initialization, OpenAPI schema generation, and security updates for FastAPI/Starlette vulnerabilities.

Google ADK Python v1.22.0 introduces major features including optional LLM model configuration with fallback, regex support for allowed origins, progressive SSE streaming by default, custom instructions for user simulators, Cloud Pub/Sub tool support, and a new JSON-based database schema for DatabaseSessionService. The release includes 30+ bug fixes addressing event content validation, OAuth token refresh, eval result serialization, MCP tool errors, and deployment configurations.