feat(consent-tester): Phase C+D — LLM cascade fallback (Qwen → OVH)

New module consent-tester/services/cmp_llm_fallback.py:
- LLMCookieExtractor: single-endpoint adapter (Ollama OR OpenAI-compat)
- LLMCascade: tries Qwen (local Mac Mini Ollama) first; falls through to
  OVH (managed 120B) when Qwen returns no usable strategy
- LLMCascade.from_env(): reads OLLAMA_URL/CMP_LLM_MODEL + OVH_LLM_URL/
  OVH_LLM_KEY/OVH_LLM_MODEL from environment
- LLM returns JSON {strategy: url|selector|text, value: ...}
- Valkey-backed cache per netloc (cmp:hint:<netloc>, 7-day TTL) — next run
  against the same domain skips the LLM entirely

dsi_discovery.py:
- Wired network_log collector (URL/status/content-type/size of every JSON
  response on the page) — passed to LLM prompt as observation
- After Named CMP (Phase B) + Heuristic (Phase A) both fail AND DOM
  < 300 words: invoke LLMCascade.analyze(...)
- _apply_llm_hint executes the LLM's strategy: refetch URL via Playwright
  request context, query DOM selector, or use text directly
- Cache HIT path: apply cached hint, only fall back to LLM if cache is stale

docker-compose.yml:
- consent-tester gets env vars + cmp-data volume (for Phase E)
- All LLM endpoints configurable via env, sensible defaults

consent-tester/requirements.txt:
- redis>=5.0 (asyncio client, Valkey-compatible)
- httpx>=0.27

docker-compose.yml

@@ -12,6 +12,7 @@ networks:
 
 volumes:
   dsms_data:
+  cmp-data:  # consent-tester: CMP discovery log + auto-promoted modules
 
 services:
 
@@ -256,6 +257,18 @@ services:
     depends_on:
       core-health-check:
         condition: service_completed_successfully
+    environment:
+      # LLM fallback for cookie-policy extraction (Phase C+D of cascade)
+      OLLAMA_URL: "${OLLAMA_URL:-http://bp-core-ollama:11434}"
+      CMP_LLM_MODEL: "${CMP_LLM_MODEL:-qwen3:30b-a3b}"
+      OVH_LLM_URL: "${OVH_LLM_URL:-}"
+      OVH_LLM_KEY: "${OVH_LLM_KEY:-}"
+      OVH_LLM_MODEL: "${OVH_LLM_MODEL:-}"
+      VALKEY_URL: "${VALKEY_URL:-redis://bp-core-valkey:6379}"
+      # CMP discovery log (Phase E auto-promote)
+      CMP_DISCOVERY_DB: "/data/cmp_discoveries.db"
+    volumes:
+      - cmp-data:/data
     healthcheck:
       test: ["CMD", "curl", "-f", "http://127.0.0.1:8094/health"]
       interval: 30s