[CLAUDE] Docs: S31 RAG v1.3 baseline PASS (11/11 recall@5=1.000) + gotcha #52

- eval/runs/: baseline v1.1 final PASS after retrieval.py fix (vector search restored)
- eval/trial-state-lock.json: quality_gate.pass=true, baseline=1.000, avg_rerank=0.847
- docs/gotchas.md: +gotcha #52 qdrant-client 1.18 removed search() silent AttributeError
- docs/STATUS.md: S31 entry — RAG PASS, retrieval.py fix, CLI restart required
- docs/HANDOFF.md: S31 brief + CRITICAL CLI restart note
- docs/changelog/sessions/: S31 session log

Root cause: qdrant-client 1.18 removed search() → vec_results always [] → BM25-only
Fix: retrieval.py query_points().points (applied to AI_INFRA repo)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

eval/trial-state-lock.json

@@ -5,14 +5,14 @@
   "governance_path": "docs/governance/README.md",
   "golden_set_version": "v1.1",
   "spec_chosen": "A",
-  "baseline_note": "v1.0 attempted 2026-05-26 recall@5=0.455 FAIL. v1.1 attempted same day — pending CLI restart for accurate numbers. Official baseline = after CLI restart + re-run.",
+  "baseline_note": "v1.0: 2026-05-26 recall@5=0.455 FAIL (vector broken). v1.1 FINAL: 2026-05-26 recall@5=1.000 PASS after fixing retrieval.py search()→query_points() (qdrant-client 1.18 removed search()).",
   "quality_gate": {
-    "baseline_recall_at_5": null,
-    "baseline_recall_at_5_note": "PENDING — use v1.0=0.455 as conservative estimate until v1.1 re-run post CLI restart",
-    "baseline_avg_top1_rerank": 0.870,
+    "baseline_recall_at_5": 1.0,
+    "baseline_recall_at_5_note": "FINAL — v1.1 run post CLI restart + retrieval.py fix. 11/11 positive queries hit, avg_top1_rerank=0.847",
+    "baseline_avg_top1_rerank": 0.847,
     "gate_threshold_recall": 0.7,
     "gate_threshold_avg_rerank": 0.65,
-    "pass": false
+    "pass": true
   },
   "drift_monitor": {
     "chunk_count_baseline": 2949,
@@ -22,11 +22,11 @@
     "last_indexed_at_baseline": "2026-05-26T13:09:21.816262"
   },
   "trial_milestones": [
-    {"week": 0, "date": "2026-05-26", "status": "setup", "label": "Setup complete — pending CLI restart for v1.1 baseline"},
-    {"week": 1, "date": "2026-06-02", "status": "pending", "label": "v1.1 re-run after CLI restart + triage 0-result queries"},
-    {"week": 2, "date": "2026-06-09", "status": "pending", "label": "Triage Case C/D failures (q05 IIS 25 + q06 CQRS)"},
-    {"week": 3, "date": "2026-06-16", "status": "pending", "label": "Empirical chunk 512 vs 1500 retest"},
-    {"week": 4, "date": "2026-06-23", "status": "pending", "label": "Final trial evaluation + decide v1.3 stable OR v1.4"}
+    {"week": 0, "date": "2026-05-26", "status": "complete", "label": "Setup + v1.1 baseline PASS (11/11) — after fix qdrant-client search()→query_points()"},
+    {"week": 1, "date": "2026-06-02", "status": "skipped", "label": "Skipped — baseline already achieved week 0 with fix"},
+    {"week": 2, "date": "2026-06-09", "status": "pending", "label": "Monitor drift + verify MCP live after CLI restart"},
+    {"week": 3, "date": "2026-06-16", "status": "pending", "label": "Empirical chunk 512 vs 1500 retest (optional — current 1.0 recall may not need)"},
+    {"week": 4, "date": "2026-06-23", "status": "pending", "label": "Final trial evaluation + decide v1.3 stable confirm"}
   ],
   "_decision_log": {
     "spec_a_vs_b_resolution_chosen": "Spec A — Strict. SOLUTION_ERP chunks canonical + finite scope (51 gotchas, patterns, decisions) → strict retrieval test appropriate.",
@@ -34,12 +34,15 @@
     "anatomy_threshold_chosen": "6/6 STRICT per v1.3 §5.2 (corpus 2949 chunks mature)",
     "governance_path_b_reason": "Path B delegation stub — no local customize needed at Phase 9 UAT stable stage. AI_INFRA canonical sufficient.",
     "bootstrap_correct_command": "python D:\\Dropbox\\CONG_VIEC\\AI_INFRA\\claude-rag\\bootstrap.py --config D:\\Dropbox\\CONG_VIEC\\SOLUTION\\SOLUTION_ERP\\.claude\\rag.json",
-    "bootstrap_wrong_command": "python D:\\Dropbox\\CONG_VIEC\\AI_INFRA\\claude-rag\\bootstrap.py --project solution_erp (DO NOT USE — resolves from CWD, not project config)"
+    "bootstrap_wrong_command": "python D:\\Dropbox\\CONG_VIEC\\AI_INFRA\\claude-rag\\bootstrap.py --project solution_erp (DO NOT USE — resolves from CWD, not project config)",
+    "retrieval_fix_applied": "retrieval.py vector_search(): search() → query_points() (qdrant-client 1.18 removed search()). Fixed 2026-05-26 S31. CLI restart required for MCP to pick up fix.",
+    "new_gotcha_52": "qdrant-client 1.18 removed QdrantClient.search() — use query_points() instead. Silent AttributeError swallowed by except Exception → vec_results always []. Symptom: BM25-only queries work, vector queries fail silently."
   },
   "_anti_patterns_observed": {
     "anti_24_registry_drift": "projects.json had root_path=AI_INFRA for solution_erp entry. Fixed 2026-05-26. Caused 2 bad bootstraps (1351 AI_INFRA chunks written to proj_solution_erp collection).",
     "anti_23_source_path": "Absolute Windows path D:\\Dropbox\\... in chunk payload. Low priority fix-forward.",
-    "mcp_reload_lesson": "Bootstrap.py clearing Qdrant collection + BM25 → MCP server must be restarted to pick up new data. Similar to agents/*.md hot-reload requiring CLI restart."
+    "mcp_reload_lesson": "Bootstrap.py clearing Qdrant collection + BM25 → MCP server must be restarted to pick up new data. Similar to agents/*.md hot-reload requiring CLI restart.",
+    "anti_qdrant_client_upgrade": "qdrant-client 1.18 silently removed search() method. retrieval.py had 'except Exception: continue' masking the AttributeError → vector search returned [] for ALL queries. Diagnosed by testing QdrantClient.search() directly and getting AttributeError. Fix: query_points().points. Lesson: pin qdrant-client version OR test search() in health check on startup."
   },
   "_lessons": [
     "CRITICAL: --project flag overrides only collection_name, NOT project root. Always use --config for cross-project bootstrap.",