homelab-codex-ws/services/kb-query/README.md

# kb-query

FastAPI search API in front of the module-5 KB retrieval engine
(`packages/kb-retrieval/`). Runs on **PIHA**, bound to PIHA's LAN IP only
(`exposure: private`, same class as paperless/nextcloud — no public ingress
yet). This is a **search API, not chat**: no answer synthesis over results,
that's phase 5.

## Endpoints

| Endpoint | Method | Purpose |
|---|---|---|
| `/` | GET | Search UI (Jinja2 shell + `/static/app.js`, no login yet — plan §8 OIDC is a later step) |
| `/static/*` | GET | UI assets (`app.js`, `style.css`) |
| `/healthz` | GET | `{"status": "ok", "sol_status": "up"\|"down"}` — `sol_status` is a live probe of Ollama@SOLARIA, no auth required (monitoring must reach it) |
| `/search?q=<text>&mode=cascade\|flat` | GET | `query_text -> embed -> cascade_query/flat_query -> results`, `mode` defaults to `cascade` |

`/search` response shape (module 5 phase 4 plan §4, `summary`/`summary_tags`
added in Krok 4 for the UI's per-envelope result header — additive, does not
change any field the plan §4 shape already defined):

```json
{
  "query": "...", "mode": "cascade", "sol_status": "up",
  "results": [
    {"envelope_id": "paperless:119", "source": "paperless", "dist": 0.34,
     "chunk_index": 2, "text": "...", "link": "https://paper.kapala.org/documents/119/details",
     "summary": "...", "summary_tags": ["..."]},
    {"envelope_id": "<Message-ID>", "source": "gmail", "dist": 0.44,
     "chunk_index": 0, "text": "...", "subject": "...", "from": "...", "date": "...",
     "link": null, "mail_ui_url": null, "summary": null, "summary_tags": []}
  ]
}
```

`dist` is never filtered server-side — the 0.45/0.55 colour thresholds (below)
are a frontend concern, not an API contract. `summary`/`summary_tags` come
from `document_summary` for `SUMMARY_MODEL`; `null`/`[]` when the envelope
has no summary yet.

## Frontend (Krok 4, plan §7)

One page, served from this same FastAPI process — no separate frontend
container, no node build step (plan §2 decision 4): `app/templates/index.html`
(Jinja2 shell) + `app/static/app.js` (vanilla JS, `fetch()` to `/search`) +
`app/static/style.css`. Wszystko po polsku.

- Pole zapytania + submit (Enter lub przycisk), przełącznik trybu
  kaskada/flat (domyślnie kaskada — checkbox "tryb flat (debug)").
- Wyniki grupowane po `envelope_id` (dokument): nagłówek trafienia to
  streszczenie dokumentu (`summary`, tor haiku) gdy dostępne, w przeciwnym
  razie `envelope_id`; chunki są rozwijanymi fragmentami (`<details>`) pod
  nagłówkiem, posortowane po `dist`.
- Kolorowanie progów (fazy 3, zweryfikowane bramką): `dist < 0.45` zielony,
  `0.45–0.55` żółty (nadal renderowany, z wizualnym ostrzeżeniem), `> 0.55`
  nigdy nie renderowany jako pojedynczy wynik. Jeśli po tym filtrze żadna
  grupa nie zostaje nic do pokazania (wszystkie trafienia > 0.55, albo brak
  trafień w ogóle), całość zastępuje komunikat "Brak odpowiedzi w KB dla
  tego zapytania" z najlepszym (najniższym) zaobserwowanym `dist` w nawiasie.
- Źródło: Paperless → link "Otwórz w Paperless" (`link`); Gmail → metadane
  (`subject`/`from`/`date`) + przycisk "Kopiuj Message-ID" (`envelope_id`
  **jest** Message-ID, plan §2 decyzja 3) — nie ma dokąd linkować, więc
  kopiowalny identyfikator zamiast martwego linku.
- Stopka pokazuje `sol_status` dyskretnie (odświeżane z `/healthz` przy
  starcie strony i po każdym wyszukiwaniu).

## Embed path — active fallback (plan §2 decision 2, §5)

`app/fallback.py` holds one process-global `SolCircuitBreaker`:

1. Cached `sol_status` (30s TTL) is used as-is when fresh — no network call.
2. On expiry, probe `GET {OLLAMA_URL}/api/tags` (500ms timeout); cache the
   result (`up`/`down`) for another 30s.
3. `up` → embed on SOLARIA with a hard 3s timeout.
   - Success → done, `sol_status: "up"`.
   - Timeout/error on the **real** embed call (not just the probe) → flip
     the breaker to `down` immediately and fall through to step 4 **in the
     same request** — the caller never sees an error for this, only the
     first unlucky request in a 30s window pays one extra timeout.
4. `down` → embed locally against `OLLAMA_PIHA_URL` (`ollama-piha`@PIHA,
   `bge-m3`, same model constant as SOLARIA — see the invariant note below).

If **both** legs fail (SOLARIA down and PIHA unreachable/not deployed),
`/search` returns **503**; `/healthz` still answers (`sol_status: "down"`),
same tolerance pattern as `llm-gateway`. `/healthz` shares the same cached
breaker as `/search`, so both report the same view of the world.

`OLLAMA_PIHA_URL` defaults to `http://localhost:11434`, which is inert
inside this container (nothing listens there) until you point it at the
real `ollama-piha`@PIHA address — see `services/ollama-piha/README.md` for
that container's deploy status and the RAM/latency calibration gate that
decides whether it's safe to rely on as a default fallback.

## Startup invariant (hard-fail)

At startup, kb-query queries `document_chunk.model` and
`document_summary.embedding_model` for the set of models behind *active*
embeddings, and refuses to start (crash-loop, visible via container restarts)
if the configured `EMBED_MODEL` (default `bge-m3`) isn't in both sets. This
guards against querying with an embedding space that doesn't match what's
actually indexed — see `app/startup.py` for why the check reads
`document_summary.embedding_model` and not `.model` (the latter is the LLM
that *wrote* the summary, e.g. `claude-haiku-4-5`, not the embedder).

**Covers both fallback legs.** `EMBED_MODEL` is a single constant threaded
through `app/fallback.py`'s `embed_with_fallback` and used identically for
the SOLARIA and PIHA embed calls — there is no per-request or per-leg model
choice, so this one startup check already covers both paths. See
`app/fallback.py`'s module docstring for why a second, redundant per-request
DB check was deliberately not added.

## Configuration

`.env` — **gitignored**, copy from `env.example`. Required: `LAN_BIND_IP`,
`KB_DSN`. Optional: `OLLAMA_URL`, `OLLAMA_PIHA_URL`, `EMBED_MODEL`, `SUMMARY_MODEL`.

## Deploy (PIHA)

1. `git pull` on PIHA (`~/homelab-codex-ws`).
2. `cp services/kb-query/env.example services/kb-query/.env` and fill in the
   real `KB_DSN` password.
3. ```
   docker compose -f services/kb-query/docker-compose.yml \
     -f hosts/piha/runtime/kb-query/docker-compose.override.yml up -d --build
   ```
4. Verify: `services/kb-query/healthcheck.sh`, then from PIHA:
   `curl "http://192.168.31.5:8230/search?q=test"` and open
   `http://192.168.31.5:8230/` in a browser.

## Tests

```
pip install -e packages/kb-retrieval/
cd services/kb-query && pip install -r requirements.txt pytest pytest-asyncio && pytest
```

Unit tests mock the DB connection and Ollama HTTP session (no live DB/Ollama
required) — same style as `packages/kb-retrieval/tests/`. `tests/test_frontend.py`
drives `GET /`/`/static/*` through FastAPI's `TestClient` without entering it
as a context manager, so the DB-requiring `lifespan` never runs.

Frontend JS has its own pure-function tests (query-URL encoding, threshold
colouring, envelope grouping), run without a browser via Node's built-in
test runner: `node --test services/kb-query/tests/frontend/`.

## Ingress (`kb.kapala.org`, plan §8)

Wired up 2026-07-23 (`docs/sessions/2026-07-23-kb-f4-ingress.md`), **no code
change in this service** — pure infra step:

- npm@PIHA proxy host #35: `kb.kapala.org` → `http://192.168.31.5:8230`,
  cert #49 (`*.kapala.org` wildcard, DNS-01 via Cloudflare, expires
  2026-09-28) — same pattern as `paper.`/`vikunja.`/`ha.kapala.org`.
- Pi-hole Local DNS (`/etc/pihole/custom.list` on PIHA, runtime, not in Git):
  `kb.kapala.org` → `192.168.31.5`. **This is the first `kapala.org` entry in
  that file** — every other `kapala.org` vhost (paper/ha/immich/vikunja/forgejo)
  has no LAN override and resolves via the public Cloudflare record
  (Tailscale IP) even from LAN, a hairpin the plan assumed was already avoided
  for those too. Not fixed here (out of this task's scope — no other vhosts
  touched); worth a follow-up if it matters for those services.
- Cloudflare A record `kb.kapala.org` → `100.108.208.3` (Tailscale PIHA, DNS
  only): added manually by the operator (no CF API token available in the
  environment that did the rest of this step), verified against Cloudflare's
  own authoritative NS and 8.8.8.8/1.1.1.1 — resolves everywhere now, both
  LAN (via Pi-hole override) and Tailscale/public (via this record).

**No auth.** OIDC (plan §8: `authlib`, `/login`, `/auth/callback`) is explicitly
**not implemented** — confirmed no forward-auth/reverse-proxy-level auth pattern
exists anywhere in this repo (NPM community edition doesn't support it either);
the three precedents (paperless/nextcloud/vikunja) all do OIDC inside the app.
Building that is real service code (`authlib` dependency, session middleware,
Forgejo OAuth2 app registration) — deliberately deferred to a separate session,
decision confirmed with the operator 2026-07-23. Until then `kb.kapala.org` is
reachable by anyone on the LAN/tailnet with no login, same as before this vhost
existed.

## Out of scope for this step

- OIDC login (see above) — separate session, needs `authlib` + Forgejo OAuth2 app.