Merge pull request 'fix(learning): extract precedent metadata inline on final-decision enroll' (#335) from worktree-enroll-inline-metadata into main

mcp-server/src/legal_mcp/services/precedent_library.py

@@ -383,7 +383,10 @@ async def reextract_metadata(
     appeal_subtype, and case_name when it equals the citation). User
     values are preserved.
 
-    **MCP-tool-only path** — same constraint as :func:`reextract_halachot`.
+    **Container-safe** — unlike :func:`reextract_halachot` (claude CLI, host-only),
+    metadata extraction runs on Gemini Flash over REST (GOOGLE_GEMINI_API_KEY), so
+    this path is callable from the FastAPI container too. The final-decision
+    enrollment loop (``_enroll_final_in_library``) calls it inline on upload.
     """
     from legal_mcp.services import precedent_metadata_extractor
 

web/app.py

@@ -3643,9 +3643,11 @@ async def _enroll_final_in_library(
         out["error"] = "no final text extracted"
         return out
 
-    # Deterministic metadata from the case record — the Gemini metadata extractor is
+    # Deterministic seeds from the case record first — proceeding_type / date /
-    # tuned for EXTERNAL rulings and returns no_metadata for internal decisions, so we
+    # citation are identity, not inference, so we set them ourselves (no LLM) and the
-    # populate proceeding_type / date / tags / summary / citation ourselves (no LLM).
+    # later Gemini pass (reextract_metadata, below) is fills-empty-only and won't
+    # touch them. subject_tags/summary seeded here from the case (chair-curated
+    # subject_categories win when present); when empty, Gemini fills them inline.
     district = "ירושלים"
     proceeding_type = (case.get("proceeding_type") or "ערר").strip()
     decision_date = case.get("decision_date") or case.get("hearing_date")
@@ -3685,6 +3687,26 @@ async def _enroll_final_in_library(
     except Exception as e:
         logger.warning("citation build failed for %s: %s", case_number, e)
 
+    # Fill the LLM-derived metadata (subject_tags, summary, headnote, key_quote)
+    # inline via Gemini (REST — container-safe; GOOGLE_GEMINI_API_KEY in Coolify),
+    # reusing the same reextract_metadata path the UI/drain use (G2 — one path, full
+    # status lifecycle). apply_to_record fills ONLY empty fields, so the deterministic
+    # seeds above (proceeding_type / date / citation, plus any chair-curated
+    # subject_categories) are preserved. Without this the row sat at
+    # metadata_extraction_status='pending' with empty tags until a drain happened to
+    # pick it up, so a freshly-enrolled final showed no subject tags in the edit UI.
+    # Best-effort — surfaced in the return value, never silently swallowed.
+    try:
+        from legal_mcp.services import precedent_library as plib_service
+        meta = await plib_service.reextract_metadata(UUID(case_law_id))
+        out["metadata"] = {
+            "status": meta.get("status"),
+            "fields": meta.get("fields") or [],
+        }
+    except Exception as e:
+        logger.warning("inline metadata extraction failed for %s: %s", case_number, e)
+        out["metadata_error"] = str(e)
+
     # The precedents this decision cites → link to the library; flag the ones not found.
     try:
         await cit_tools.extract_internal_citations(case_law_id=case_law_id, limit=0)