M42: calibrate grounded RAGcore fallback

PROJECT_STATE.md

@@ -1,5 +1,23 @@
 # Project state
 
+## M42 — calibrate grounded RAGcore fallback (2026-08-21)
+
+- The first live five-minute acceptance run exposed a real calibration error in M41's
+  new fallback threshold: `/v1/answers` timed out, while `/v1/search` correctly returned
+  `damage-procedure.md` at rank one with fused score `0.0163934426`. RAGcore uses
+  reciprocal-rank fusion (roughly `1 / (60 + rank)`), so the normalized-looking `0.05`
+  threshold could never accept a legitimate result.
+- Set the default minimum to `0.016`: this accepts the first two normal RRF ranks while
+  still rejecting missing scores and the existing low-score `0.01` abuse case. Damage
+  questions continue to require explicit damage evidence and out-of-domain questions
+  continue to return `insufficient`; no generated answer is trusted when retrieval is
+  absent or weak.
+- Added a regression using RAGcore's observed rank-one fused score. Focused knowledge
+  tests **36 passed**; complete isolated PostgreSQL backend suite **270 passed**; Ruff and
+  mypy are clean and `git diff --check` passes.
+- Exact next action: commit and push M42, deploy that exact archive over the healthy M41
+  production deployment, then repeat the live five-minute demo and final health checks.
+
 ## M41 — full review remediation and hardening (2026-08-21)
 
 - Closed all findings from the repository-wide review without expanding the locked PoC:

backend/app/core/config.py

@@ -24,7 +24,9 @@ class Settings(BaseSettings):
     ragcore_space_id: str = ""
     ragcore_http_timeout_seconds: float = 5.0
     # Search fallback is only labelled grounded above this explicit retrieval threshold.
-    ragcore_min_search_score: float = 0.05
+    # RAGcore's fused score is reciprocal-rank based (top ranks are ~1/61), so this
+    # accepts only leading results while still rejecting absent and low-ranked evidence.
+    ragcore_min_search_score: float = 0.016
     n8n_webhook_url: str = "http://n8n:5678/webhook/mobilityops-return"
     n8n_webhook_trigger_token: str = "replace-me-n8n-webhook-trigger-token"
     n8n_callback_token: str = "replace-me-n8n-callback-token"

backend/tests/test_knowledge.py

@@ -711,7 +711,7 @@ def test_ragcore_search_fallback_prefers_damage_procedure(monkeypatch):
     assert any(source.document_id == "damage-procedure" for source in answer.sources)
 
 
-def test_ragcore_search_fallback_accepts_relevant_damage_evidence_above_threshold(monkeypatch):
+def test_ragcore_search_fallback_accepts_top_ranked_ragcore_damage_evidence(monkeypatch):
     provider = RAGcoreKnowledgeProvider()
     monkeypatch.setattr(provider._settings, "ragcore_space_id", "space-1")
     search = _search_body()
@@ -725,7 +725,9 @@ def test_ragcore_search_fallback_accepts_relevant_damage_evidence_above_threshol
                 "excerpt": "Record damage and keep the vehicle blocked.",
             },
             "rank": 1,
-            "scores": {"fused": 0.5},
+            # RAGcore uses reciprocal-rank fusion; a genuine rank-one result is about
+            # 1 / (60 + 1), not a normalized 0..1 relevance score.
+            "scores": {"fused": 0.01639344262295082},
         }
     )
     monkeypatch.setattr(