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

@@ -41,11 +41,12 @@ logger = logging.getLogger(__name__)
 # human (INV-CF3). Kept low — the .gov site shouldn't be hammered (INV-CF4).
 MAX_AUTONOMOUS_ATTEMPTS = int(os.environ.get("COURT_FETCH_MAX_ATTEMPTS", "2"))
 
-# The host-side Tier-1 browser service (pm2). The MCP server runs on the host,
-# so it reaches the service over loopback directly (the container bridge in
-# web/court_fetch_proxy.py is a separate, optional entry point).
+# The host-side Tier-1 browser service (pm2). It binds the docker0 bridge
+# gateway (10.0.1.1) — same as legal-chat-service — so both the host MCP server
+# and containers can reach it; the host reaches 10.0.1.1 as a local interface.
+# Override with COURT_FETCH_SERVICE_URL.
 COURT_FETCH_SERVICE_URL = os.environ.get(
-    "COURT_FETCH_SERVICE_URL", "http://127.0.0.1:8771"
+    "COURT_FETCH_SERVICE_URL", "http://10.0.1.1:8771"
 )
 _SHARED_SECRET = os.environ.get("COURT_FETCH_SHARED_SECRET", "").strip()
 _TIER1_TIMEOUT_S = float(os.environ.get("COURT_FETCH_TIER1_TIMEOUT_S", "300"))

scripts/SCRIPTS.md

@@ -22,6 +22,8 @@
 | `legal-court-fetch-service.config.cjs` | pm2/js | **שירות-מארח Tier-1 לאחזור פסקי-דין מנט המשפט (X13)** — 2 apps: (א) `legal-court-fetch-xvfb` (Xvfb :99, צג-וירטואלי ל-Camoufox); (ב) `legal-court-fetch-service` (`python -m legal_mcp.court_fetch_service.server`, bound `10.0.1.1:8771`, Bearer `COURT_FETCH_SHARED_SECRET` מ-`~/.legal-court-fetch-service.env`, `DISPLAY=:99`). מריץ Camoufox דרך חבילת-הפייתון (in-process) כי הקונטיינר לא יכול דפדפן. תלות: `pip install -e "mcp-server[court-fetch]" && python -m camoufox fetch`. אחזור = ניווט→צופה→`GetImages`(X-Requested-With)→PDF, ללא CAPTCHA; כשל→`ok:false`→orchestrator מסלים ל-fallback אנושי. **אומת על עת"מ 46111-12-22 (34 עמ').** מראָה לדפוס `legal-chat-service.config.cjs`. ספ: `docs/spec/X13-court-fetch.md`. התקנה: `pm2 start scripts/legal-court-fetch-service.config.cjs && pm2 save`. בריאות: `curl http://10.0.1.1:8771/health`. | pm2 (host-side) |
 | `reap_orphan_procs.py` | python | **reaper לתהליכים-יתומים שמרווים את שרת Nautilus** — הורג `task-master-mcp` (Node, מתנפח ל~3GB) ו-`camoufox-bin` (Firefox מ-X13 fetch שקרס) **רק כשהם יתומים (`ppid=1`)** — תהליך עם הורה-חי לעולם לא נוגעים בו. `/proc` טהור, בלי psutil. `--dry-run` (דיווח), `--loop N` (דמון כל N ש'). ראה זיכרון [[project_taskmaster_mcp_memory_leak]]. | דרך `legal-reaper.config.cjs` (pm2) |
 | `legal-reaper.config.cjs` | pm2/js | **דמון pm2 ל-`reap_orphan_procs.py --loop`** (ברירת-מחדל 180ש', `REAP_INTERVAL_S` לעקיפה). `max_memory_restart 100M` (ה-reaper עצמו לא ידלוף). התקנה: `pm2 start scripts/legal-reaper.config.cjs && pm2 save`. לוגים: `pm2 logs legal-reaper`. | pm2 (host-side) |
+| `drain_court_fetch.py` | python | **ריקון תור-אחזור הפסיקה (X13)** — קורא ל-`court_fetch_orchestrator.drain_pending(limit)` שמוריד+קולט כל job ממתין שהיומונים מילאו, וקושר חזרה ליומון. מקומי בלבד (ingest = claude CLI). no-op מהיר כשהתור ריק. הרצה ידנית: `mcp-server/.venv/bin/python scripts/drain_court_fetch.py [limit]`. | דרך `legal-court-fetch-drain.config.cjs` (pm2 cron) |
+| `legal-court-fetch-drain.config.cjs` | pm2/js | **תזמון שעתי של `drain_court_fetch.py`** (cron `17 * * * *`, `COURT_FETCH_DRAIN_CRON` לעקיפה) — הופך את לולאת יומון→אחזור→קליטה ל-fully-autonomous. `autorestart:false` (one-shot per tick). דורש `legal-court-fetch-service` רץ. התקנה: `pm2 start scripts/legal-court-fetch-drain.config.cjs && pm2 save`. | pm2 cron (host-side) |
 | `auto-sync-cases.sh` | bash | סנכרון תיקי ערר ל-Gitea — רץ כל דקה | `* * * * *` (cron) |
 | `backup-db.sh` | bash | גיבוי PostgreSQL יומי ל-`data/backups/` (gzip) | לתזמן: `0 2 * * *` |
 | `restore-db.sh` | bash | שחזור DB מגיבוי (companion ל-backup-db.sh) | ידני |

scripts/drain_court_fetch.py

@@ -0,0 +1,43 @@
+"""Drain the X13 court-verdict fetch queue (jobs the digest trigger fills).
+
+When a digest points at a court ruling not yet in the corpus, the digest
+trigger enqueues a ``court_fetch_jobs`` row (status=pending). This script
+drains those: for each pending/failed job it runs the full Tier-0/Tier-1 fetch
+(via the host browser service) + the canonical ingest, then links the verdict
+back to its source digest. Serial with a cooldown (INV-CF4); failures are
+recorded and retried until they escalate to ``manual`` (INV-CF3).
+
+Host-only: ingest drives halacha extraction via the local ``claude`` CLI (same
+constraint as ``drain_halacha_queue.py``). A no-op (fast) when the queue is
+empty. Scheduled hourly by ``legal-court-fetch-drain`` (pm2 cron); also runnable
+by hand:
+
+    mcp-server/.venv/bin/python scripts/drain_court_fetch.py [limit]
+"""
+
+import asyncio
+import os
+import sys
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "mcp-server", "src"))
+
+from legal_mcp.services import court_fetch_orchestrator as orch
+
+
+async def main() -> int:
+    limit = int(sys.argv[1]) if len(sys.argv) > 1 else 5
+    res = await orch.drain_pending(limit=limit)
+    print(f"===court-fetch drain=== processed={res.get('processed', 0)} "
+          f"ingested={res.get('done', 0)}", flush=True)
+    for r in res.get("results", []):
+        line = f"    [{r.get('status')}] {r.get('citation', '')}"
+        if r.get("error"):
+            line += f" — {r['error'][:120]}"
+        if r.get("case_law_id"):
+            line += f" → case_law {r['case_law_id']}"
+        print(line, flush=True)
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(asyncio.run(main()))

scripts/legal-court-fetch-drain.config.cjs

@@ -0,0 +1,40 @@
+/**
+ * pm2 ecosystem entry for legal-court-fetch-drain — a scheduled (hourly) one-shot
+ * that drains the X13 court-verdict fetch queue the digest trigger fills, making
+ * the digest → fetch → ingest loop fully autonomous (no manual court_fetch_drain).
+ *
+ * Pattern: cron_restart fires the script on schedule; autorestart:false means it
+ * runs once and exits (pm2 shows it "stopped" between ticks — expected for a cron
+ * job). A no-op (fast) when the queue is empty, so hourly is cheap.
+ *
+ * Requires (already deployed): legal-court-fetch-service (+xvfb) running for the
+ * browser fetch, and the host env (~/.env: POSTGRES_URL, VOYAGE_API_KEY,
+ * COURT_FETCH_SHARED_SECRET) the venv loads via legal_mcp.config. Ingest uses the
+ * local claude CLI for halacha extraction (halachot land pending_review — the
+ * chair's approval gate is untouched).
+ *
+ * Install (once):
+ *     pm2 start /home/chaim/legal-ai/scripts/legal-court-fetch-drain.config.cjs
+ *     pm2 save
+ * Logs:  pm2 logs legal-court-fetch-drain --lines 50
+ * Run now (manual): mcp-server/.venv/bin/python scripts/drain_court_fetch.py
+ *
+ * Schedule override: COURT_FETCH_DRAIN_CRON (default hourly at :17 to avoid the
+ * top-of-hour stampede with other jobs).
+ */
+const cron = process.env.COURT_FETCH_DRAIN_CRON || "17 * * * *";
+
+module.exports = {
+  apps: [
+    {
+      name: "legal-court-fetch-drain",
+      cwd: "/home/chaim/legal-ai",
+      script: "/home/chaim/legal-ai/mcp-server/.venv/bin/python",
+      args: "scripts/drain_court_fetch.py 5",
+      env: { HOME: "/home/chaim", PYTHONUNBUFFERED: "1" },
+      autorestart: false, // one-shot per cron tick
+      cron_restart: cron,
+      max_memory_restart: "800M",
+    },
+  ],
+};