Experimental/brain-of-reese
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
39 Commits 1 Branch 0 Tags
572a4190a62f7fbad32d6fdd3d7e5f68b2b4a775
Commit Graph
29 Commits
Author SHA1 Message Date
ducoterra 572a4190a6 feat(rag): lite-model document summaries — non-markdown docs summarized at import, summary chunk retrieves and resolves to the full source doc 2026-08-25 17:48:37 -04:00
ducoterra 9809482a4b chore(agent): phase roadmap from TODO.md — 4 phases (lite document summaries, KB overview in prompt, admin sync button, cache busting) 2026-08-25 15:43:44 -04:00
ducoterra 3841bd5a30 feat(ui): expose Global Tuning from Chat + Sources headers (admin-only Tuning nav link) 2026-08-25 14:51:16 -04:00
ducoterra 3d044f33a1 feat(rag): git-based import sources — BOR_GIT_SOURCES repos cloned (first run, --depth 1) or pulled (--ff-only) into BOR_SOURCES_DIR/<repo>/ then indexed; --source still wins; a failed sync aborts before importing anything 2026-08-25 14:23:02 -04:00
ducoterra 589e26dbe9 feat(rag): global tuning manager — /tuning.html + PUT /api/steering/{id}: create, edit, list, delete steering notes without a chat 2026-08-25 13:46:32 -04:00
ducoterra fcde1fd37b feat(ui): documents open in an almost-fullscreen modal instead of a new page — same-page overlay on chat + Sources, /document.html kept as the no-JS/direct-link fallback 2026-08-25 13:45:57 -04:00
ducoterra 476aa0e066 chore(agent): phase roadmap from TODO.md — 3 phases (document modal, global tuning, git-based sources) 2026-08-25 10:15:42 -04:00
ducoterra 025f57beb5 fix(ui): background no longer moves — static grid, three glow spots fading in and out on their own slow cycles (owner 2026-08-25) 2026-08-25 09:43:19 -04:00
ducoterra 1e6ae360e0 feat(rag): feed whole matched documents to the LLM — no context truncation (A7 revised) 2026-08-24 23:37:44 -04:00
ducoterra d7a4064616 fix(build): Containerfile builds again — relative module imports, all four pages and shared assets in the image 2026-08-24 22:54:30 -04:00
ducoterra 0adc9b5801 fix(ui): animated background actually animates — grid drift and glow breathe per the phase-08 design 2026-08-24 22:16:41 -04:00
ducoterra 22a6121411 fix(ui): thinking window no longer scrolls — live 320px view pinned to the stream tail 2026-08-24 20:28:12 -04:00
ducoterra 986e704eb1 chore(agent): add phase 24 from TODO.md — whole-document context (no truncation, A7 revised); clear TODO.md 2026-08-24 18:53:24 -04:00
ducoterra 04a7f4c05d fix(ui): thinking window no longer scrolls — live 320px view pinned to the stream tail 2026-08-24 18:24:57 -04:00
ducoterra 76c6a01199 fix(chat): keep the in-flight answer when navigating away mid-turn — partial answer restored on return 2026-08-24 15:53:07 -04:00
ducoterra 824914ca3d chore(agent): add phases 20-23 from TODO.md — four owner-confirmed bug fixes; clear TODO.md 2026-08-24 15:23:49 -04:00
ducoterra 076358db94 uncommit .agent 2026-08-24 10:59:45 -04:00
ducoterra bc0158f858 feat(ui): chat auto-scrolls only while pinned to the bottom — submitting reveals your message, scrolling up holds the viewport 2026-08-24 10:53:04 -04:00
ducoterra b16deb2b1d feat(chat): stream model thinking over SSE and show it in a collapsible block 2026-08-24 09:52:27 -04:00
ducoterra cbc263a4b2 feat(auth): single-admin password login (signed cookie) — gate tuning + Sources catalog, keep chat and document viewer public 2026-08-23 19:58:39 -04:00
ducoterra 0da5275eeb fix(rag): lift chat output cap to 32768 tokens — long answers no longer cut off 2026-08-22 11:30:19 -04:00
ducoterra 7e8d14702e feat(rag): hybrid FTS+vector retrieval and multi-format ingestion — name-your-tool questions find the right document 2026-08-22 01:27:02 -04:00
ducoterra 2f738a7f19 feat(ui): dark tech theme — emoji-free chrome, subtle animated CSS background, WCAG AA dark palette 2026-08-21 23:34:36 -04:00
ducoterra 1b29b1cf9d feat(ui): responsive + WCAG AA polish pass across chat and sources — v1 feature complete 2026-08-21 19:44:46 -04:00
ducoterra 2364e1ee7d feat(ui): onboarding suggestion chips with one-tap submit, keyboard access, and mobile scroll row 2026-08-21 18:18:47 -04:00
ducoterra cbf8e39e63 feat(rag): honest deflection gate with amber UI state and alternative-question chips 2026-08-21 17:50:33 -04:00
ducoterra 99c48cbe06 feat(rag): index markdown KB — chunker, embed client, delta importer, Sources page 
Phase 02 (story: import documents):

- fence-aware markdown chunker (heading sections, 200-char overlap,
  heading anchor on every chunk, 1200-char hard cap, fence blocks
  kept atomic and split under the cap)
- LLMClient over aipi (LiteLLM) reusing the openai client's httpx
  transport to send a clean {model, input} payload — the openai SDK
  injects encoding_format, which aipi's openai_like group rejects;
  token-budget batching + halving retry for the endpoint's
  ~1024-token per-request input cap
- two-phase per-file upsert importer: sha256 delta (unchanged skip),
  atomic commit, A9 exclusion walk, per-source prune, per-file error
  tolerance (rollback + log + continue, non-zero CLI exit), adaptive
  re-chunk at half target for URL-dense files the endpoint rejects
- scripts/import_docs CLI (repeatable --source, --prune, --limit,
  defaults ~/Homelab + ~/Deployments)
- GET /api/docs with per-doc chunk counts; Sources page wired to the
  real endpoint (stat cards, full-width a11y table, designed empty
  state, DOM-built rows — no innerHTML)
- tests: 63 passed (chunker/llm/importer units, docs API + importer
  integration), story E2E 3/3 (real endpoints, in-thread import);
  app/ coverage 98%
- real KB imported: 672 docs / 8969 chunks in ~3m, idempotent
  re-run (672 unchanged, 0 batches)
- harness: .agent/validate.sh now gates through uv (pytest +
  coverage >90% + ruff + pyright) instead of system python3
 2026-08-21 16:24:45 -04:00
ducoterra dce6d0d6f1 docs(phases): record phase 01 completion — all gates passed, moved to complete/ 2026-08-21 13:42:51 -04:00
ducoterra 022da8e2bc feat: scaffold Brain of Reese — FastAPI RAG chat over Postgres 17 + pgvector 
Foundation (phase 01, verified):
- FastAPI app: /api/health, /api/suggestions, /api/chat (placeholder),
  static frontend served locally (no CDN)
- Postgres 17 + pgvector via db/Containerfile + compose.yaml
  (podman compose up -d db), Alembic initial migration (documents,
  chunks with vector(768), query_log)
- LLM client targeting https://aipi.reeseapps.com/v1 (turbo/embed);
  scripts/llm_probe.py verified models + 768-dim embeddings live
- Conditional debugpy: imported only when DEBUGPY=1 (attach on demand,
  :5678); logging config for clean single-line logs
- Frontend shell: mobile-first chat + Sources pages, tokens, a11y baselines
- Tests: 24 unit+integration (99% coverage on app/), ruff + pyright clean,
  Playwright smoke E2E (3 tests) against a deterministic mock LLM
- Planning: .agent/PLAN.md (architecture + LOCKED decisions), AGENTS.md,
  6 user stories, 7 phase files (one story / one phase / one Playwright
  suite each)
 2026-08-21 13:42:21 -04:00