Cogtrix follows semantic versioning. Breaking changes bump the minor version while pre-1.0; the patch version is for fixes and additive changes.
The canonical changelog lives in the Cogtrix repo at CHANGELOG.md. This page summarises the highlights — for the full per-PR detail, follow the link.
0.3.0 — current (2026-06-06)
- Resolver / dispatcher hardening — tighter contracts around message routing.
- ThreadPoolExecutor migration — background work (knowledge extraction, LLM-judge classification, summarisation) moved off ad-hoc threads onto bounded pools with timeouts.
- Agent fleet runner — orchestration entry point for fanning a task across multiple agents.
- Rate-limit productionization — per-chat and per-channel limits now enforced consistently across REST + WebSocket + assistant mode.
0.2.13 (2026-05-31)
Release bundle — see v0.2.13 notes for the per-PR detail.
0.2.12 (2026-05-27)
Bug-fix release; production release-title guard. See v0.2.12 notes.
0.2.11 (2026-05-24)
- REST + WebSocket API: 159 endpoints across 27 route groups.
- WebSocket auth: session WebSocket now accepts JWT via
Sec-WebSocket-Protocol: ["bearer", "<token>"]for browser clients, in addition to the existingAuthorization: Bearerheader for CLI/SDK. - 67 built-in tools.
- Multi-provider: Ollama, OpenAI, Anthropic, Gemini, DeepSeek, xAI; any OpenAI-compatible endpoint.
- MCP support: connect any Model Context Protocol server as a tool source.
- Three memory modes:
conversation,code,reasoning. - Deep Think: Tree-of-Thought reasoning engine via
/think. - Delegation: parallel sub-agent dispatch via
/delegate. - Setup wizard:
--setupgenerates a starter config. - Docker: official image with both CLI and API mode in the same container.
- Assistant mode: headless WhatsApp / Telegram daemon with workflow routing.
Earlier releases
See CHANGELOG.md in the Cogtrix repo for the full release history including 0.1.x and the M-series milestones.