enrichment: Haiku flat details + image gallery on expand

apply service
- POST /internal/fetch-listing: headless Playwright fetch of a listing URL,
  returns {html, image_urls[], final_url}. Uses the same browser
  fingerprint/profile as the apply run so bot guards don't kick in

web service
- New enrichment pipeline (web/enrichment.py):
  /internal/flats → upsert → kick() enrichment in a background thread
    1. POST /internal/fetch-listing on apply
    2. llm.extract_flat_details(html, url) — Haiku tool-use call returns
       structured JSON (address, rooms, rent, description, pros/cons, etc.)
    3. Download each image directly to /data/flats/<slug>/NN.<ext>
    4. Persist enrichment_json + image_count + enrichment_status on the flat
- llm.py: minimal Anthropic /v1/messages wrapper, no SDK
- DB migration v5 adds enrichment_json/_status/_updated_at + image_count
- Admin "Altbestand anreichern" button (POST /actions/enrich-all) queues
  backfill for all pending/failed rows; runs in a detached task
- GET /partials/wohnung/<id> renders _wohnung_detail.html
- GET /flat-images/<slug>/<n> serves the downloaded image

UI
- Chevron on each list row toggles an inline detail pane (HTMX fetch on
  first open, hx-preserve keeps it open across the 3–30 s polls)
- CSS .flat-gallery normalises image tiles to a 4/3 aspect with object-fit:
  cover so different source sizes align cleanly
- "analysiert…" / "?" chips on the list reflect enrichment_status

Config
- ANTHROPIC_API_KEY + ANTHROPIC_MODEL wired into docker-compose's web
  service (default model: claude-haiku-4-5-20251001)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

web/templates/base.html

@@ -83,6 +83,29 @@
         body:has(#v_map:checked) .view-map { display: block; }
         #flats-map { height: 520px; border-radius: 10px; }
 
+        /* Flat detail expand */
+        .flat-row { border-top: 1px solid var(--border); }
+        .flat-row:first-child { border-top: 0; }
+        .flat-expand-btn { width: 1.75rem; height: 1.75rem; border-radius: 999px;
+                           display: inline-flex; align-items: center; justify-content: center;
+                           border: 1px solid var(--border); background: var(--surface);
+                           color: var(--muted); cursor: pointer; transition: transform .2s, background .15s; }
+        .flat-expand-btn:hover { background: var(--ghost); color: var(--text); }
+        .flat-expand-btn.open { transform: rotate(180deg); }
+        .flat-detail { background: #fafcfe; border-top: 1px solid var(--border); }
+        .flat-detail:empty { display: none; }
+
+        /* Normalised image gallery — every tile has the same aspect ratio */
+        .flat-gallery { display: grid;
+                        grid-template-columns: repeat(auto-fill, minmax(160px, 1fr));
+                        gap: 8px; }
+        .flat-gallery-tile { aspect-ratio: 4 / 3; overflow: hidden;
+                             border-radius: 8px; border: 1px solid var(--border);
+                             background: #f0f5fa; display: block; }
+        .flat-gallery-tile img { width: 100%; height: 100%; object-fit: cover;
+                                 display: block; transition: transform .3s; }
+        .flat-gallery-tile:hover img { transform: scale(1.04); }
+
         /* Leaflet popup — match site visual */
         .leaflet-popup-content-wrapper { border-radius: 12px; box-shadow: 0 6px 20px rgba(16,37,63,.15); }
         .leaflet-popup-content { margin: 12px 14px; min-width: 220px; color: var(--text); }