Monitoring

Google ADK Python v1.27.0 introduces major enhancements across core agent functionality, LLM model support, and observability. Key additions include A2A request interceptors, pluggable auth integrations, PDF support for Anthropic models, streaming capabilities, and new optimization tools. The release also expands tool ecosystems with Skills support, BigQuery enhancements, and improved human-in-the-loop interactions in the web interface.

The Usage & Cost Admin API cookbook provides a practical guide for programmatically accessing Claude API usage and cost data through Anthropic's Admin API. It enables token-level monitoring across models and workspaces, detailed cost breakdowns by service type, and cache efficiency analysis. The guide includes security best practices, API endpoint documentation, and Python code examples for tracking consumption patterns, attributing expenses, and generating financial reports.

This cookbook demonstrates building an autonomous SRE incident response agent using the Claude Agent SDK with read-write MCP tools for safe infrastructure access. The agent can investigate incidents by querying metrics and logs, diagnose root causes, apply remediations by editing configs and restarting services, and document post-mortems. The pattern uses a subprocess-based MCP server with scoped tool access, clear tool descriptions, and human-in-the-loop workflows to enable autonomous yet controlled incident response.

Microsoft AutoGen python-v0.5.7 release introduces improvements to AzureAISearchTool with unified search methods (full-text, vector, and hybrid), enhanced SelectorGroupChat with model_context parameter for better speaker selection, and improved OTEL tracing with additional metadata. The release also includes various bug fixes and improvements to agent runtime, documentation, and integrations with external services like Anthropic Bedrock and MCP servers.

Microsoft AutoGen python-v0.6.2 introduces streaming tools with `BaseStreamTool` and `StreamWorkbench` support, adds `tool_choice` parameter to `ChatCompletionClient`, and enables `AssistantAgent` with an inner tool calling loop via `max_tool_iterations`. Additional features include OpenTelemetry GenAI traces, Mem0 memory extension, `output_task_messages` flag, GraphFlow improvements, and support for latest models like Gemini 2.5 Flash.

crewAI 1.8.0 introduces production-ready Flows and Crews architecture with native async chain support for agent-to-agent (a2a) communication, including poll/stream/push update mechanisms. The release adds human-in-the-loop (HITL) feedback capabilities for Flows, streaming tool call events, and enhanced event handling through improved EventListener and TraceCollectionListener.

crewAI 1.8.1 release introduces A2A (Agent-to-Agent) task execution utilities with server configuration and additional transports, along with bug fixes for Azure model support, flow execution error handling, and frame inspection depth. The release also includes documentation updates for A2A features and work-in-progress PII redaction documentation.

crewAI 1.10.0a1 introduces a unified memory system, enhanced flow tracking with event correlation, and improved HITL (Human-in-the-Loop) functionality. Key updates include tool spec auto-updates, MCP schema improvements, async support enhancements, and security fixes addressing OpenSSL vulnerabilities.

CrewAI 1.10.0 introduces enhanced MCP tool resolution, improved JSON argument parsing, user input handling in Flows, and migrates the CLI HTTP client from requests to httpx. The release includes 20+ bug fixes addressing tool validation, schema handling, callback execution, and race conditions, plus documentation updates for security guidance and 96 new integration actions.

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 v0.10.2 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.

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 v1.23.0 introduces OpenTelemetry-based tracing for BigQuery, automatic session creation, and enhanced tool support with JSON schema declarations. The release includes 30+ features and bug fixes across core, tools, evals, observability, and integrations, with a breaking change replacing custom ContextVar implementation with OpenTelemetry.

Google ADK Python v1.25.0 release introduces significant enhancements including a simple prompt optimizer demo, new CLI flags for auto session creation, event-delta memory management, and post-invocation token compaction. The release adds support for external access tokens in Google credentials, new tools like MCP resource loading and SkillToolset, plus health/version endpoints to the web server. Multiple bug fixes address async iteration, event loop issues, metadata preservation in streaming responses, and PostgreSQL timestamp handling.

Google ADK Python v1.26.0 release introduces major features including intra-invocation token compaction, Apigee LLM chat completions integration, Agent Skills spec compliance, BigQuery search catalog support, and an Agent Registry system. The release also includes numerous bug fixes for streaming tools, memory services, authentication, and various integrations across core, models, tools, evals, and services components.

OpenClaw v2026.2.23 release adds first-class Kilo Gateway and Moonshot provider support, introduces prompt caching documentation and per-agent parameter overrides, and hardens session maintenance with disk-budget controls and security headers. The release includes numerous fixes for browser SSRF policies, Telegram polling/reactions, context overflow detection, and agent reasoning/compaction behavior.

OpenClaw v2026.2.25-beta.1 release includes improvements to Android chat streaming and startup performance, UI enhancements for mobile compose actions, and a major refactor of heartbeat configuration policy. The release addresses numerous critical fixes across Telegram, Slack, Discord, and LINE channels, including subagent delivery state machine improvements, webhook handling, session threading, media routing, and typing indicator management.

OpenClaw v2026.3.1 release introduces major enhancements across multiple platforms including adaptive thinking defaults for Claude 4.6, Kubernetes health check endpoints, expanded Android device capabilities (camera, notifications, sensors), Discord/Telegram session management improvements, and WebSocket-first OpenAI streaming. The release also adds localization support (German, zh-CN), Feishu document/chat tooling, LanceDB memory customization, and numerous reliability fixes for Android, Windows, LINE, and Slack integrations.

OpenClaw v2026.3.2 introduces major features including expanded SecretRef support across 64 targets, native PDF analysis tools, enhanced outbound adapters with multi-media support, and improved session attachments. The release includes several breaking changes around default tool profiles, ACP dispatch enablement, and plugin SDK HTTP handler registration, along with numerous fixes for Telegram, Discord, Feishu, and other channel integrations.

Wild Moose is an autonomous AI agent designed for production debugging that connects to observability data like logs and metrics from Datadog. Rather than focusing on code generation, it performs root-cause analysis by exploring multiple data sources through conversational interfaces, combining code execution with API invocations to answer debugging questions.