v0.5.0 — Hardening

What's New

Engine reliability hardening — no new tools, but the four existing tools are now significantly more robust.

Engine Reliability

• Readiness gate (#4) — tool calls now block until Stockfish WASM is fully initialized. No more meaningless accuracy scores or zero critical moments on cold start.
• SQLite eval cache (#5) — evaluated positions survive server restarts. Analysis of repeated positions is instant.
• MCP progress notifications (#8) — analyze_game streams live progress ("Evaluating position 34/80…") instead of a silent 30–50s wait.

Performance

• Cloud eval concurrency (#6) — Lichess cloud eval now runs 10 requests in parallel (was 4), with automatic 429 backoff retry.
• Adaptive depth tuning (#7) — quiet positions use depth 10, critical positions use depth 16 (previously 12/18). ~20% faster game analysis with no accuracy loss on critical moments.

Deferred

• Worker Thread spike (#9) — mitigated by improved cloud eval concurrency; deferred.
• Pawn structure / theme expansion (#10, #11) — moved to v0.6.
• Redis cache (#12) — moved to v1.0.

Upgrading

Rebuild the server after pulling:
```bash
cd mcp-server && npm run build
```

What's Changed

• fix: update tests to use axios mocks instead of global.fetch by @rutvij26 in #34
• chore: GitHub repo hygiene — PR template, Dependabot, stale bot, release workflow by @rutvij26 in #32
• chore(deps-dev): bump typescript from 5.9.3 to 6.0.2 in /mcp-server by @dependabot[bot] in #38
• chore(deps): bump zod from 3.25.76 to 4.3.6 in /mcp-server by @dependabot[bot] in #36
• chore(deps-dev): bump @types/node from 22.19.15 to 25.5.0 in /mcp-server by @dependabot[bot] in #37
• chore(deps): bump stockfish from 16.0.0 to 18.0.5 in /mcp-server by @dependabot[bot] in #35
• feat: engine readiness gate for analyze_game by @rutvij26 in #39
• feat: Stockfish Worker Thread pool — parallel position analysis by @rutvij26 in #40
• feat: analyze_game — chess.com URL support, username last-game fallback, integration tests by @rutvij26 in #43
• fix: analyze_game — chess.com URLs, last-game fallback, Stockfish 18, integration tests by @rutvij26 in #44
• ci: integrate Codecov for test coverage reporting by @rutvij26 in #54
• feat: Docker-native Stockfish engine with HTTP router by @rutvij26 in #56
• feat: MCP progress notifications for analyze_game by @rutvij26 in #57
• feat: SQLite-backed eval cache (closes #5) by @rutvij26 in #58
• feat: engine readiness gate for analyze_position (closes #4) by @rutvij26 in #59
• feat: tune adaptive depth — quiet=10, critical=16 by @rutvij26 in #61
• feat: Lichess cloud eval concurrency=10 + 429 backoff retry by @rutvij26 in #62
• docs: set up GitHub Pages with Docsify and CI deploy pipeline by @rutvij26 in #63
• docs: document internal logic of the intelligence layer by @rutvij26 in #64
• docs: add real output examples and complete type schema by @rutvij26 in #68
• docs: clarify what the system does vs what Claude does by @rutvij26 in #66
• docs: document layer boundaries and extensibility guide by @rutvij26 in #65
• docs: document design decisions, observability, and validation by @rutvij26 in #69

New Contributors

• @dependabot[bot] made their first contribution in #38

Full Changelog: https://github.com/rutvij26/chess-context/commits/v0.5.0