- Include thinking support configuration (type, min, max, levels) in
JSON output for reasoning-capable models
- Add test verifying explicit false booleans are preserved (not omitted)
- Add test verifying thinking config appears for thinking models
Built [OnSteroids](https://onsteroids.ai)
- Add unit tests verifying JSON output structure, field filtering,
and minified format
- Document that --json takes priority over subcommands (refresh/reset)
Built [OnSteroids](https://onsteroids.ai)
- Updated websearch.md to include SearXNG in the configuration guide.
- Implemented SearXNG JSON API integration in websearch-transformer.cjs.
- Enhanced unified-config-loader.ts to support SearXNG settings.
- Defined SearXNG configuration types in unified-config-types.ts.
- Updated hook-env.ts to manage SearXNG environment variables.
- Modified status.ts to include SearXNG in web search provider checks.
- Added SearXNG routes and validation in websearch-routes.ts.
- Implemented SearXNG provider tests in websearch-transformer.test.ts.
- Updated readiness tests to account for SearXNG in status.test.ts.
- Enhanced websearch routes tests to validate SearXNG settings.
- Added SearXNG configuration fields in the UI settings.
- add the huggingface preset and hf alias to the shared preset catalog
- default the preset to Factory Droid because the documented path is generic chat completions
- cover the CLI and dialog behavior with preset metadata and UI tests
- fetch live provider model definitions through /api/cliproxy/catalog
- overlay CCS preset metadata without keeping UI dropdowns as the source of truth
- wire /cliproxy and quick setup to the upstream-backed catalog path
- stop the Codex free-plan compatibility guard from rewriting codex.settings.json
- keep saved dashboard selections intact and rely on runtime fallback when needed
- update reconcile coverage to lock the non-mutating behavior in place
- switch the reviewer workflow from glm-5-turbo to glm-5.1
- increase workflow timeout to 20 minutes and max turns to 45
- lock the workflow test to the full reviewer model configuration
Closes#922
Cache file content in RawTokenCandidate to avoid double-reading token
files (TOCTOU race between metadata extraction and fingerprinting).
Rename stale test description and add fingerprint fields to test
snapshots so they exercise the same comparison path as production.
