- POST /mcp (JSON-RPC 2.0): initialize, ping, tools/list, tools/call; notifications -> 202
- tools: cortiq_route (classify -> routing decision) and cortiq_chat (route -> answer)
- gated by protocols.mcp; admin meta marks it implemented
- docs: README/README.ru protocol tables, highlights and status updated for
streaming, Anthropic, embeddings, semantic cache and MCP
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- cache.rs: cosine-similarity store (threshold, TTL, ring buffer), partitioned by
routing signature; tracks hit rate and model cost saved
- pipeline: embed routing text, look up before the model call (route_source=cache on
hit), insert successful responses; stats record cache hits
- config [cache] + admin settings card; dashboard shows hit-rate and savings
- embedding model resolved from the pool (or first kind="embedding")
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- release.yml: add x86_64-pc-windows-msvc target, OS-aware packaging (.exe + .zip)
- ci.yml: split into lint (fmt/clippy) + test matrix (ubuntu/windows/macos)
- use getrandom for the admin/key token CSPRNG (secure on Windows too)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- bump version to 0.1.0; add crates.io metadata (include list, homepage, rust-version)
- add .github/workflows/release.yml: on tag v* → publish to crates.io + GitHub Release with binaries
- README: absolute links/images and badges so it renders on crates.io; add install section
- CHANGELOG: 0.1.0
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
