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/#v0-16-0-harness-control-memory-reliability-september-2026/https://docs.reactiveagents.dev/guides/whats-new/#v0-16-0-harness-control-memory-reliability-september-2026/<Aside type="note" title="No breaking changes"> v0.16 is additive: a new builder method, new chat/session controls, new tools, and a broad correctness/accuracy sweep. No builder-surface removals, no migration needed. </Aside> · ### Harness Control Surface — .withHarness({...}) · A typed, per-agent config for the harness's internal mechanisms: tool disclosure, tool discovery, tool index, verbose rules, context budgets, and more. Precedence is config over RA env vars over the default, and the resolved config is inherited by sub-agents. ContextProfile.toolDisclosureMode is now wired through to thSun, 06 Sep 2026 18:09:34 GMTv0.16.0https://docs.reactiveagents.dev/guides/whats-new/#v0-15-0-hardening-pass-august-2026/https://docs.reactiveagents.dev/guides/whats-new/#v0-15-0-hardening-pass-august-2026/<Aside type="note" title="No breaking changes"> v0.15 is a bugfix and hardening release: no builder-surface removals, no migration needed. One security-relevant fix: .withApprovalPolicy({ mode: "block" }) now actually enforces. </Aside> · A cluster of fixes found through live-model QA and a pre-release health sweep, plus one security fix and two small additions. · Security fix: .withApprovalPolicy({ mode: "block" }) now enforces. "block" mode (what you get without .withDurableRuns()) was previously an inert switch: no gate read it, so a requiresApproval tool ran unattended. It now decides eachSun, 06 Sep 2026 18:09:34 GMTv0.15.0https://docs.reactiveagents.dev/guides/whats-new/#v0-14-0-the-log-the-process-july-2026/https://docs.reactiveagents.dev/guides/whats-new/#v0-14-0-the-log-the-process-july-2026/<Aside type="note" title="The truthful release"> v0.14 is the release where the declared control surface and the enforced one converge. An internal audit found several builder methods that a caller could set but that the harness silently ignored; rather than ship a promise we don't keep, this release removes the ones that lied and wires the ones worth keeping — every fix landed with a mutation test that goes red if the wiring is cut. It is a breaking release: see Migrating below. </Aside> · The Arc 1 theme: runs are inspectable processes, and every run leaves a signed record. · ### The trust rSun, 06 Sep 2026 18:09:34 GMTv0.14.0https://docs.reactiveagents.dev/guides/whats-new/#v0-13-5-groq-xai-the-agentic-ui-kit-july-2026/https://docs.reactiveagents.dev/guides/whats-new/#v0-13-5-groq-xai-the-agentic-ui-kit-july-2026/<Aside type="tip" title="Released on npm"> Shipped July 2026 — all {metrics.packagesTotal} packages are published. Install or upgrade with bunx create-reactive-agent or pin reactive-agents@0.13.5. </Aside> · Two new providers, a headless UI-controller package that unifies the React, Svelte, and Vue bindings, a durable request-for-input rail in Cortex, and honest error surfacing. · ### Groq and xAI providers · Both wire through a shared makeOpenAICompatProvider factory, so they inherit the full OpenAI-compatible stack — streaming, native function calling, structured output — with no bespoke adaSun, 06 Sep 2026 18:09:34 GMTv0.13.5https://docs.reactiveagents.dev/guides/whats-new/#v0-13-0-receipts-first-touch-july-2026/https://docs.reactiveagents.dev/guides/whats-new/#v0-13-0-receipts-first-touch-july-2026/<Aside type="tip" title="Released on npm"> Shipped July 2026 — all 35 packages are published. Install or upgrade with bunx create-reactive-agent or pin reactive-agents@0.13.0. </Aside> · The v0.13 line is about receipts and first-touch: native reasoning on every provider, cost-aware routing, an overhauled first-ten-minutes developer experience, honest abstention as a first-class terminal, a new efficiency-first Blueprint strategy, two token-waste guards, and a broad correctness sweep across providers and the kernel. · ### Native thinking on every provider · .withThinking(...) turns on native rSun, 06 Sep 2026 18:09:34 GMTv0.13.0https://docs.reactiveagents.dev/guides/whats-new/#v0-12-0-durable-honest-june-2026/https://docs.reactiveagents.dev/guides/whats-new/#v0-12-0-durable-honest-june-2026/<Aside type="tip" title="Released on npm"> Shipped June 2026 — all packages are published. Install or upgrade with bunx create-reactive-agent or pin reactive-agents@0.12.0. </Aside> · The v0.12 line makes runs survive crashes, makes outputs typed and grounded, and makes "which capabilities are on" explicit and honest. Headline capabilities: typed structured output, durable execution, and HarnessProfile composition — plus a developer-experience pass that removes Effect from the common builder surface. · ### Typed Structured Output · Turn any agent into a typed extractor. Attach a schema at builSun, 06 Sep 2026 18:09:34 GMTv0.12.0https://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 replaSun, 06 Sep 2026 18:09:34 GMTv0.11.xhttps://docs.reactiveagents.dev/guides/whats-new/#v0-10-x-local-models-run-the-full-loop-may-2026/https://docs.reactiveagents.dev/guides/whats-new/#v0-10-x-local-models-run-the-full-loop-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 run the same tool-calling agent loop 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). Deterministic repairs instead of an LLM reprompt. Ships on by default — see LLM PrSun, 06 Sep 2026 18:09:34 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 Tools - 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 with colSun, 06 Sep 2026 18:09:34 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 Tools - 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 Cortex — Sun, 06 Sep 2026 18:09:34 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 - Provider adapter hook system — 4 kernel prompt hooks (continuationHint, errorRecovery, synthesisPrompt, qualityCheck) plus parseToolCalls (normalizes malformed native tool calls in every provider complete()/stream()); calibration composes additively with the tier adapter rather than replacing it — see LLM Providers - Dynamic stopping (3-layer) — novelty signal (Jaccard overlap), budget exhaustion phase transition, aSun, 06 Sep 2026 18:09:34 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 switchesSun, 06 Sep 2026 18:09:34 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 sSun, 06 Sep 2026 18:09:34 GMTv0.5.0