 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
|
8ca564cd83
|
fix(ui): uniform header bar height on chat, sources, and the document viewer
|
2026-08-22 15:14:31 -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
|
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
|
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
|
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 |
|