Commit Graph
14 Commits
Author SHA1 Message Date
ducoterra fe55be0c35 feat(brand): configurable app name — BOR_APP_NAME drives /api/config + the frontend brand layer
Build and Push Containers / build-and-push (push) Successful in 1m50s
One env var (BOR_APP_NAME, default "Brain of Reese") now drives the app's
display name everywhere (TODO.md L12 — owner ask: "a way to customize the
name for 'Brain of'. Should be an env var."). The existing app_name setting
is the source of truth (phase locked decision — no new variable, no rename);
with the variable unset the app is byte-identical to before.

Endpoint (A10 public/stateless, no secrets):
  GET /api/config → exactly {app_name, version} (app/api/config.py, the
  health.py pattern; registered before the static mount). Integration tests:
  anonymous 200, default values, a Settings override follows, key set is
  exactly two keys — no other setting may leak in later.

Frontend brand layer (A11 — runtime fetch, static templates stay static):
  assets/brand.js — a CLASSIC script, first on all six pages, so its top
  level runs at parse time: window.BOR_BRAND = "Brain of Reese"
  synchronously (the default renders immediately, no blank flash), then a
  no-store fetch of /api/config applies the name — document.title (global
  replace), every .brand-text (a name starting "Brain of " keeps the bold
  split Brain of <strong>rest</strong>, any other name renders plain; the
  operator-controlled name is HTML-escaped before innerHTML), a TreeWalker
  over text nodes (script/style rejected — page source never rewritten),
  and the aria-label/placeholder/meta-content attributes. Fetch failure
  keeps the default + console.warn (the loadHealth house style).
  app.js (status labels, typing label, elapsed-hint aria, tool labels) and
  document.js (viewer titles) read window.BOR_BRAND at CALL time via
  brand() — a label set after the fetch lands carries the configured name.
  Containerfile: esbuild minify line for brand.js (classic, like markdown.js);
  the phase-33 ?v= cache-busting picks the new asset ref up automatically.

E2E (A16 — one story, one file, isolated): test_configurable_brand.py boots
a SECOND app instance (same DB/mock-LLM/admin-auth env block, port APP_PORT+1,
BOR_APP_NAME="Brain of Testy") — the shared conftest server keeps the
default name so every other suite's title/label assertions stay untouched —
and asserts /api/config on both instances, the index title/brand/greeting/
#messages aria-label, the sources + login page titles, and one pre-token
chat turn (think out loud marker) whose #send-status reads "Brain of Testy
is thinking"; the no-op regression pins the shared server's default bytes.

Docs: .env.example App section + README configuration reference — what it
affects (titles, header brand, status labels, aria text), the default, the
bold-split rendering rule.

Gates: 695 unit+integration passed, app/ coverage 99% (>90%), story E2E
green in isolation (two consecutive runs), brand-string suites (smoke,
shared header, header consistency, chat persistence) green, ruff + pyright
clean.
2026-08-27 02:24:16 -04:00
ducoterra 1925bb66a8 feat(sources): admin page to add and remove git sources (TODO.md L4) 2026-08-26 18:42:28 -04:00
ducoterra b2d8696741 feat(ui): one consistent navbar on every page (TODO.md L3) 2026-08-26 15:39:42 -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 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 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 2afc77ee56 feat(ui): shared header — Sign in/Sign out and New Chat on every page; hide the Sources nav link from anonymous users 2026-08-24 12:32:45 -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 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 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 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