TypeScript AI agent framework — release highlights, features, and breaking changes.https://docs.reactiveagents.dev/en-ushttps://docs.reactiveagents.dev/guides/whats-new/https://docs.reactiveagents.dev/guides/whats-new/#v0-11-x-production-tooling-full-observability-may-2026/https://docs.reactiveagents.dev/guides/whats-new/#v0-11-x-production-tooling-full-observability-may-2026/The focus: developer tooling that makes agents production-observable and repeatable, plus the first create-reactive-agent scaffolder, cross-runtime support, and three new capabilities (code-action strategy, skill persistence, interactive playground). · ### New packages · - @reactive-agents/observe — Zero-config OpenTelemetry tracing. Set OTELEXPORTEROTLPENDPOINT and every run emits a workflow → LLM → tool span hierarchy, OpenInference-compliant, to any OTLP backend (Jaeger, Grafana Tempo, Langfuse, Arize Phoenix). See OpenTelemetry Tracing. - @reactive-agents/replay — Deterministic trace replaWed, 27 May 2026 23:26:11 GMTv0.11.xhttps://docs.reactiveagents.dev/guides/whats-new/#v0-10-x-local-models-match-frontier-may-2026/https://docs.reactiveagents.dev/guides/whats-new/#v0-10-x-local-models-match-frontier-may-2026/The biggest release since v0.9 — 0.10.0 through 0.10.6, shipped over four weeks. The headline: local Ollama models now hit 91–94% on the same task suite as paid frontier APIs, thanks to a closed-loop healing pipeline and adaptive tool-calling. Read the full v0.10.0 changelog for engineering detail. · ### What you gain · #### Local models that actually work · - Healing Pipeline — 4-stage closed-loop recovery on every tool call (tool-name fuzzy match → parameter-name aliasing → path resolution → type coercion). 86.7% recovery rate, +80pp accuracy, 90% cheaper than LLM reprompt. Ships on by defauWed, 27 May 2026 23:26:11 GMTv0.10.xhttps://docs.reactiveagents.dev/guides/whats-new/#v0-9-x-mcp-production-hardening-pre-v0-10-polish/https://docs.reactiveagents.dev/guides/whats-new/#v0-9-x-mcp-production-hardening-pre-v0-10-polish/- MCP client rewritten on @modelcontextprotocol/sdk — smart auto-detection between stdio and HTTP-only containers, two-phase docker lifecycle — see Orchestration - Composable kernel architecture (initial) — react-kernel.ts reduced from 1,700 to 197 lines via makeKernel({ phases }) factory — see Composable Kernel - Permanently-failed required tools fix — tools that always error no longer cause loop-until-maxIterations — see Harness Control Flow - Cortex MCP CRUD + JSON import — import Cursor/Claude-style MCP configs directly into Cortex — see Cortex - StatusRenderer TUI — live terminal display Wed, 27 May 2026 23:26:11 GMTv0.9.xhttps://docs.reactiveagents.dev/guides/whats-new/#v0-9-0-mcp-production-hardening/https://docs.reactiveagents.dev/guides/whats-new/#v0-9-0-mcp-production-hardening/- MCP client rewritten on @modelcontextprotocol/sdk — smart auto-detection between stdio and HTTP-only containers, two-phase docker lifecycle — see Orchestration - Composable kernel architecture — react-kernel.ts reduced from 1,700 to 197 lines via makeKernel({ phases }) factory; phases are now individually swappable — see Composable Kernel - Permanently-failed required tools fix — tools that always error no longer cause loop-until-maxIterations; framework detects and stops early — see Harness Control Flow - Cortex MCP CRUD + JSON import — import Cursor/Claude-style MCP configs directly into CWed, 27 May 2026 23:26:11 GMTv0.9.0https://docs.reactiveagents.dev/guides/whats-new/#v0-8-5-native-fc-hardening-web-framework-adapters/https://docs.reactiveagents.dev/guides/whats-new/#v0-8-5-native-fc-hardening-web-framework-adapters/- React, Vue, and Svelte adapters — useAgentStream() and useAgent() hooks/composables/stores for all three frameworks, consuming SSE endpoints — see Web Integration and Streaming - 7-hook provider adapter system — taskFraming, toolGuidance, errorRecovery, synthesisPrompt, qualityCheck, continuationHint, systemPromptPatch fully wired — see Reactive Intelligence - Dynamic stopping (3-layer) — novelty signal (Jaccard overlap), budget exhaustion phase transition, and per-tool call cap (maxCallsPerTool) — see Harness Control Flow - Full prompt observability — logModelIO: true logs the complete FC cWed, 27 May 2026 23:26:11 GMTv0.8.5https://docs.reactiveagents.dev/guides/whats-new/#v0-8-0-reactive-intelligence-layer/https://docs.reactiveagents.dev/guides/whats-new/#v0-8-0-reactive-intelligence-layer/- Entropy-aware intelligence pipeline — 5-source composite entropy sensor, trajectory classifier, and reactive controller that takes corrective action automatically — see Reactive Intelligence - Thompson Sampling strategy learner — SQLite-backed bandit learns which reasoning strategy wins per task category across runs — see Reactive Intelligence - Builder hardening — withStrictValidation(), withTimeout(), withRetryPolicy(), withFallbacks(), withHealthCheck(), and withErrorHandler() — see Builder API - Automatic strategy switching — when entropy analysis detects a stuck loop, the agent switchesWed, 27 May 2026 23:26:11 GMTv0.8.0https://docs.reactiveagents.dev/guides/whats-new/#v0-5-0-a2a-protocol-observability-foundation/https://docs.reactiveagents.dev/guides/whats-new/#v0-5-0-a2a-protocol-observability-foundation/- Full A2A (Agent-to-Agent) protocol — JSON-RPC 2.0 server, streaming SSE, client, discovery, and capability matching based on Google's A2A spec — see A2A Protocol - Agent-as-tool pattern — wrap any local or remote A2A agent as a callable tool with createAgentTool() / createRemoteAgentTool() — see Sub-agents - Live observability streaming — withObservability({ live: true, verbosity }) writes structured phase logs to stdout as each step fires — see Observability - rax serve — expose any agent as an A2A-compliant HTTP server with a single CLI command — see CLI - EventBus reasoning events — all 5Wed, 27 May 2026 23:26:11 GMTv0.5.0