Merge pull request 'feat(digests): Sonnet for digest metadata extraction (X12)' (#116) from worktree-digest-sonnet into main

mcp-server/src/legal_mcp/config.py

@@ -54,6 +54,10 @@ REDIS_URL = os.environ.get("REDIS_URL", "redis://127.0.0.1:6380/0")
 # pinned.
 HALACHA_EXTRACT_MODEL = os.environ.get("HALACHA_EXTRACT_MODEL", "claude-opus-4-8")
 HALACHA_EXTRACT_EFFORT = os.environ.get("HALACHA_EXTRACT_EFFORT", "xhigh")
+# Digest (X12) metadata extraction is a simpler, high-volume task (concept tag,
+# headline, underlying citation, tags from a one-page summary) — Sonnet is the
+# speed/cost sweet-spot here, unlike halacha extraction which pins Opus. Tune via env.
+DIGEST_EXTRACT_MODEL = os.environ.get("DIGEST_EXTRACT_MODEL", "claude-sonnet-4-6")
 # Effort for BULK queue-drain extraction (process_pending over many precedents).
 # xhigh is the quality sweet-spot for a single precedent but very slow at scale
 # (a 64-chunk case ≈ 20 min). Bulk drains use a lighter effort to cut wall-clock;

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

@@ -19,6 +19,7 @@ from __future__ import annotations
 import logging
 from datetime import date as date_type
 
+from legal_mcp import config
 from legal_mcp.config import parse_llm_json
 from legal_mcp.services import claude_session
 
@@ -79,13 +80,17 @@ def _norm_date(result: dict, key: str) -> date_type | None:
         return None
 
 
-async def extract(raw_text: str) -> dict:
+async def extract(raw_text: str, model: str | None = None) -> dict:
     """Extract digest metadata from raw text. Returns a dict (never raises).
 
     Keys: yomon_number, digest_date (date|None), concept_tag, headline_holding,
     summary, underlying_citation, underlying_court, underlying_date (date|None),
     underlying_judge, practice_area, appeal_subtype, subject_tags (list[str]).
     Missing/invalid fields are omitted so the caller's merge keeps user values.
+
+    Model: defaults to ``config.DIGEST_EXTRACT_MODEL`` (Sonnet — this is a
+    high-volume, simple extraction; no need for Opus). Override per-call via
+    ``model``.
     """
     text = (raw_text or "").strip()
     if not text:
@@ -95,6 +100,7 @@ async def extract(raw_text: str) -> dict:
     try:
         result = await claude_session.query_json(
             user_msg, system=DIGEST_EXTRACTION_PROMPT,
+            model=(model or config.DIGEST_EXTRACT_MODEL or None),
         )
     except Exception as e:  # surfaced as warning, not swallowed silently (§6)
         logger.warning("digest_metadata_extractor: query failed: %s", e)