Agents & Agentic AI

Findings [1] 2026-09-28 v2.1.284 What's changed Added Claude Sonnet 5.5 (claude-sonnet-5-5), now the default Sonnet model on the Anthropic API — 1M context, $2/$10 per Mtok with $0.20/Mtok cache reads Added a "Yes, but ask again next time" answer to auto mode's prompt before a read… not repeating text typed very fast (for example…

Findings [1] 2026-09-25 v2.51.0 (2026-09-25) What's Changed ⚠️ Compatibility Notes Match dated gemini-3.8-live ids, reject google_affective_dialog on Gemini 3.1 Flash Live and 3.8 Live at connect, and raise RealtimeError for Gemini Live close codes by @DouweM in #8761 Raise a UserError for a realtime tool_choice that forces a tool call on OpenAI, Azure OpenAI,…

Findings [1] 2026-09-25 v2.50.0 (2026-09-24) What's Changed ⚠️ Compatibility Notes Ask a DecisionModel which route to take by name, with one label per route by @DouweM in #8733 Make ModelSelectionContext.messages end with the request being routed, and add ModelSelectionContext.prompt by @DouweM in #8737 Replace the decision model's tool-call lean with an opt-in decision_route_threshold by…

Findings [1] 2026-09-24 v2.1.282 What's changed Added a maxProseWidth setting that caps the width of Claude's prose in wide terminals while tables and code blocks keep the full width Added a startup notice, and /status and claude doctor entries, listing telemetry variables in a project's settings… deleting a prompt line while a shell command…

Findings [1] 2026-09-23 v2.1.281 What's changed Added Claude apps gateway support for newer Claude Desktop keys in desktop policy blocks, including blockReadsOutsideWorkingDirectories and disableBypassPermissionsMode Added assume_role on Claude apps gateway Bedrock upstreams: the gateway calls Bedrock as an IAM role it assumes through STS, in another… ODE_TMPDIR is set Fixed claude --bg starting a…

Findings [1] 2026-09-22 v2.1.280 What's changed Added Claude Opus 5.5 (claude-opus-5-5), now the default Opus model — 1M context, $4/$20 per Mtok with $0.20/Mtok cache reads Added mouse support to more lists in fullscreen mode: the wheel scrolls the /skills list, and a skill's state options… grep with no matches) as failures Fixed background…

Findings [1] 2026-09-21 v0.14.25 Release Notes [2026-09-21] llama-index-agent-agentmesh [0.3.0] fix: resolve a ton of security alerts (#22855) llama-index-agent-azure [0.4.0] fix: resolve a ton of security alerts (#22855) llama-index-callbacks-argilla [0.6.0] fix: resolve a ton of security alerts (#22855) llama-index-callbacks-arize-phoenix [0.8.0] fix: resolve a ton of… llama-index-llms-contextual [0.3.1] chore: raise llama-index-llms-openai-like pin to 0.8.x in 26…

What Happened Agent frameworks and SDKs (examples include LangChain, LangGraph, LlamaIndex, AutoGen, CrewAI, PydanticAI, DSPy, Semantic Kernel, OpenAI Agents SDK and Claude Code) are converging on the same architectural patterns: a planner/executor split, a tool registry, persistent memory or retrieval layers, adapter-based model abstraction, and integrated observability and governance. These components let teams compose tool-using…

What Happened Two representative updates illustrate current agent-framework trends: Claude Code’s v2.1.277 and a LangChain minor release v2.45.0. Both emphasize robustness for multi-tool agents, improved telemetry/cost attribution, and safety/sandboxing fixes. Claude Code v2.1.277: major reliability and UX fixes across headless/SDK sessions, plugin/marketplace integrity, better resume behavior and preserved session cost accounting, gateway/proxy controls…

What Happened Two representative agent-framework releases illustrate current patterns in agentic tooling: LangChain's maintenance and hardening release and a functionality-focused CrewAI update. LangChain v2.44.0 patched four security vulnerabilities impacting the web_fetch_tool and OpenTelemetry instrumentation (IPv6 zone-id bypass, event-loop processing stall, domain-spelling bypass, telemetry content leakage) and made behavioral/compatibility fixes:…

What Happened Recent Claude Code releases introduced a bundle of operational, security and agent-management improvements that illustrate the priorities for production-grade agent platforms: richer session controls, improved permission handling, better observability, and hardening of long-running/background agent behavior. Key changes include: Session and agent lifecycle: session forking to run remote-control sessions in background, MCP-server…

What Happened Recent agent-framework engineering trends and a notable prerelease illustrate converging patterns developers must plan for. DSPy 3.4.0b1 moves LM execution to a shared engine interface, provides a persistent local CPython interpreter for trusted code, adds async ReActV2 execution and custom code-proposal hooks, and changes caching, streaming and multi-answer semantics that affect latency, billing…