max/dev-intel-v2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Commit Graph

  • b8403be96c feat: repo-agnostic refactor (BMad spec-test-build loop) master Jarvis Prime 2026-03-11 14:40:31 +00:00
  • 15fb1a753b Add deep extractors, reference pages, keyword index; eval 53.3% Jarvis Prime 2026-03-10 19:01:21 +00:00
  • 0265ec7a60 feat: confluence benchmark, pattern extractor, agent KB, UX spec Jarvis Prime 2026-03-10 14:20:35 +00:00
  • 049609a358 Phase 9d: Human eval score improvement\n\n- Human readability score increased from 63.9% to 78.6%\n- Structural table additions and quick lookup index resolved navigation bottlenecks\n- NOT_FOUND rate dropped from 17.9% to 3.6% Jarvis Prime 2026-03-10 00:46:37 +00:00
  • ca11b4459a Agent eval hits 93.4% — target exceeded Jarvis Prime 2026-03-10 00:40:38 +00:00
  • 304f0a9e9f Phase 9c: Split eval into Agent (file-browsing) and Human (readability) tracks Jarvis Prime 2026-03-09 23:55:54 +00:00
  • 0cc4abcb0f Phase 9b: structural documentation improvements\n\n- sysdoc.js: Added Summary Statistics, Top Charts, and K8s Resource Types to architecture doc\n- Addresses ratchet failures where system-wide rollups were missing from generated prose\n- Eval v2 shows minor improvement, though RAG context window still limits wide scatter-gather queries Jarvis Prime 2026-03-09 23:40:07 +00:00
  • b99341e8bc Phase 9: Doc Evaluation Harness\n\n- eval-questions.js: Generates ground-truth questions from raw source data\n- eval.js: LLM-as-judge scoring harness (answers from docs, scores against truth)\n- Generated 33 questions covering config, dependencies, resources, and interactions\n- Baseline score: 66.7% (configuration 93%, dependencies 77%, structural 31%) Jarvis Prime 2026-03-09 22:32:41 +00:00
  • d9fa087e22 Phase 6+7: LLM prose generation pass over Foxtrot docs\n\n- Ran Claude Haiku to generate prose for architecture, subsystems, flows, and 124 Helm contracts\n- Fixed describeContract prompt in prose.js to correctly identify and describe Helm contract types without hallucinating\n- 80 files generated with rich architectural summaries Jarvis Prime 2026-03-09 20:15:50 +00:00
  • 4f7c77b3b1 Phase 8b: Helm contract extraction + diagram support Jarvis Prime 2026-03-09 20:05:52 +00:00
  • f49a6c2dd9 Phase 8: Helm chart extraction with Go template support Jarvis Prime 2026-03-09 20:03:04 +00:00
  • d19cee36d7 Phase 6+7D: Sonnet prose generation integration Jarvis Prime 2026-03-09 18:44:19 +00:00
  • 1869fcb5b2 7B: Add parse error tracking (BMad review fix) Jarvis Prime 2026-03-09 18:35:13 +00:00
  • ca02fe131b Phase 7F: Supergraph Multi-Repo Merge Jarvis Prime 2026-03-09 18:19:14 +00:00
  • d9fd7e3284 Phase 7B, 7E, 7D: Contracts, Diagrams, Sysdoc Jarvis Prime 2026-03-09 14:42:15 +00:00
  • 4c212740a2 Phase 7A+7C: Subsystem aggregator + Flow tracer (post-review fixes) Jarvis Prime 2026-03-09 06:51:32 +00:00
  • 4221ab4d76 Phase 6: LLM doc generation + Phase 7 system-docs spec Jarvis Prime 2026-03-09 06:20:54 +00:00
  • 7d5b6cbc32 Add README with benchmarks and V1 vs V2 comparison Jarvis Prime 2026-03-09 05:30:21 +00:00
  • efb12d003b Dev Intel Pipeline v2 — multi-language semantic graph extractor Jarvis Prime 2026-03-09 05:29:29 +00:00