Experimental/brain-of-reese
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
182 Commits 1 Branch 0 Tags
2ac3fc89c2f7cfa3cf230b6122ace2a60346984a
Commit Graph
3 Commits
Author SHA1 Message Date
ducoterra 6cf1df9bf2 feat(sync): fail fast with a modal when a model is unavailable 
TODO.md L4: with a dead model endpoint the sync discovered it only
mid-import, after slow clones — and a tooltip on the button is not a
readable error.

- app/rag/llm.py: ModelUnavailableError + check_models(llm) — a tiny
  pre-sync probe (one short embedding + one 1-token-scale completion)
  that fails naming the unavailable model (embed first, then the
  summary model); the sync sanitizer still masks credentials.
- app/api/sync.py: the probe is step 1 of _run_sync — before source
  resolution and before any clone_or_pull; a model failure is just
  another 'failed' state (no new endpoint, A10/A12 untouched).
- frontend/assets/header.js: applySyncFailure now also opens the
  module-owned error modal (every page carrying #sync-btn, zero
  page-markup changes): lazily built backdrop + role=alertdialog
  panel, error text via textContent, close via button / Esc /
  backdrop, focus in-and-out to #sync-btn (with a body→#sync-btn
  fallback — the run's disabled button drops focus to <body>).
- frontend/assets/styles.css: the modal on the phase-08 error palette
  (z-index above the header, .is-open open/close, reduced-motion
  stilling, 44px close target).
- Tests: probe unit tests (both up / embed down / summary down /
  custom model names), sync integration (fail-fast before any clone,
  probe-before-effective_sources ordering, credential masking,
  healthy regression), the phase-41 source pins, and the story E2E
  (two module apps on distinct ports — dead endpoint on a closed
  loopback port vs session mock: ≤10 s fail-fast + modal contract,
  all three dismissal paths with focus out to #sync-btn, button
  title/.is-error + Sources banner untouched, healthy phase-32
  lifecycle regression to 'Synced HH:MM').

E2E (isolation): test_sync_model_down.py 4/4, test_sync_button.py
3/3, test_git_sources_admin.py 6/6, test_local_directory_sources.py
3/3; unit+integration 721 passed, app/ coverage 99%; ruff + pyright
clean.
 2026-08-27 23:44:35 -04:00
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 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