Natalie 0120acef26 docs(prospector): add model eval & selection pipeline (Claude-advisor/OSS-worker) ... Bake-off harness in src/eval/ with Claude as offline labeler/judge/advisor (never in the serving loop). Per-role scoring (classifier F1, generator refusal+voice+policy+85% gate, orchestrator tool-call), replay harness to fix Executor cycle-1's no-batch-replay blocker, researched candidate roster (de-refused instruct base + Quinn-voice LoRA over heavy RP fine-tunes). Reuses outcomes.jsonl/gold-turnpairs/RUNNER-POLICY. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>		2026-06-29 23:42:10 -04:00
..
ai-first-v4.md	docs(prospector): split AI roles into orchestrator vs pipeline	2026-06-29 16:20:21 -04:00
deploy.md	feat(ui+ mcp+docs): complete UI fusion (Triage sidebar+toolbar+bi matching designs/main+reports 4 fused with bi+Queue tabs+sim+log+Pastebin sync+Control PWA install); extend MCP with draft/send/thread/list/pastebin/reports/mr/markets for full legacy cockpit parity; update deploy.md with migration 0006 + notes. Per MIGRATION-PLAN Phases 1+3+5. Builds/tsc green.	2026-06-29 09:31:13 -04:00
draft-engine.md	docs: correct deploy target (black dead -> DO droplet) + on-demand GPU lifecycle	2026-06-29 07:22:29 -04:00
gpu-cost-control.md	docs(prospector): split AI roles into orchestrator vs pipeline	2026-06-29 16:20:21 -04:00
mcp.md	docs: README + package.json reflect the implemented web/ operator PWA	2026-06-29 07:58:45 -04:00
model-eval-pipeline.md	docs(prospector): add model eval & selection pipeline (Claude-advisor/OSS-worker)	2026-06-29 23:42:10 -04:00
training-loop.md	docs(prospector): add training-loop (CoT-labeled corpus -> LoRA -> eval gate)	2026-06-29 18:00:01 -04:00