Experimental/brain-of-reese
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
86 Commits 1 Branch 0 Tags
c73810593218e2770de7ab98d932dc11ee2fabae
Commit Graph
64 Commits
Author SHA1 Message Date
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 fc0d9a2d5c feat(rag): steering notes — tune how Brain answers, stored in Postgres and injected into every system prompt 2026-08-22 16:44:42 -04:00
ducoterra 19df7df99d feat(ui): persist the chat conversation in localStorage — survives refresh and navigation, with a New chat reset 2026-08-22 15:52:53 -04:00
ducoterra 2485b50af0 fix(ui): document viewer back button returns to the page you came from (chat or sources) 2026-08-22 15:26:43 -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 6ec6181c7b feat(ui): clickable document viewer — open any cited document in the browser from chat chips and the sources table 2026-08-22 02:08:49 -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 e5810b0bcf feat(ui): explicit chat state machine — typing indicator, streaming progress, timeout and error recovery 2026-08-21 18:45:27 -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 396e4d47fb feat(rag): stream grounded RAG answers over SSE with source citations 
Phase 03 (Story: Chat RAG Answer — happy path):
- app/rag/retriever.py: top-k cosine search + parent-doc selection with
  per-doc dedupe and BOR_MAX_CONTEXT_CHARS cap ([…truncated…] marker)
- app/rag/prompts.py: locked persona + HIGH/DEFLECT prompt builders
- app/rag/llm.py: LLMError + chat_stream (turbo, temp 0.4, max 700, stream)
- app/api/chat.py: POST /api/chat SSE — delta* then done{deflected,
  sources, suggestions}; query_log row + PLAN §9 per-turn log line;
  structured error event on mid-stream failure, JSON 503 when DB down
- frontend: SSE reader, live bubble streaming, source chips -> /sources.html,
  red role=alert banner, Send button state that always recovers
- fix(scaffold): [hidden] { display: none !important } — .kb-banner's
  display:flex was overriding the hidden attribute (banner always visible)
- tests: unit (retriever/prompts/sse/llm) + integration (real Postgres RAG
  turn, query_log, error + 503 paths, mid-turn failures) + Playwright story
  suite (grounded answer, log row, raw SSE shape); smoke placeholder test
  replaced with the real never-stale-button contract
 2026-08-21 17:17:02 -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 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