Merge pull request 'feat(learning): מסלול נקי להעלאת החלטה סופית + פאנל-סגנון דו-סוכני (DeepSeek+Gemini)' (#158) from worktree-final-upload-pipeline into main

web/app.py

@@ -3312,6 +3312,128 @@ async def api_mark_final(case_number: str, filename: str):
     }
 
 
+@app.post("/api/cases/{case_number}/final/upload")
+async def api_upload_final_decision(case_number: str, file: UploadFile = File(...)):
+    """Clean path: upload the CHAIR's signed final decision (Dafna's version).
+
+    Distinct from the two pre-existing flows:
+      • exports/upload  → uploads a *revised version of OUR draft* (retrofits bookmarks,
+        becomes active_draft). NOT for the chair's final.
+      • exports/{f}/mark-final → marks one of *our* exports as final.
+
+    This endpoint takes the EXTERNAL signed final, stores it canonically, enrolls it in
+    the style corpus, and opens the draft↔final reconciliation pair (INV-LRN4) so the
+    staged learning step can persist its analysis. It does NOT touch active_draft and
+    does NOT run the LLM pipeline (run-learning / run-halacha do, on the local worker).
+    """
+    case = await db.get_case_by_number(case_number)
+    if not case:
+        raise HTTPException(404, f"תיק {case_number} לא נמצא")
+    if not file.filename:
+        raise HTTPException(400, "לא צוין שם קובץ")
+    if Path(file.filename).suffix.lower() != ".docx":
+        raise HTTPException(400, "רק קבצי DOCX נתמכים")
+    content = await file.read()
+    if len(content) > MAX_FILE_SIZE:
+        raise HTTPException(400, f"קובץ גדול מדי. מקסימום: {MAX_FILE_SIZE // (1024*1024)}MB")
+
+    export_dir = config.find_case_dir(case_number) / "exports"
+    export_dir.mkdir(parents=True, exist_ok=True)
+    final_name = f"סופי-{case_number}.docx"
+    final_path = export_dir / final_name
+    final_path.write_bytes(content)
+
+    # Enroll in the style corpus. Use the FULL case_number as decision_number so a
+    # בל"מ never collides with a same-numbered ערר already in the corpus (e.g. ARAR-25-8126).
+    config.TRAINING_DIR.mkdir(parents=True, exist_ok=True)
+    training_dest = config.TRAINING_DIR / f"החלטה-{case_number}.docx"
+    shutil.copy2(str(final_path), str(training_dest))
+
+    # Extract the final text (word count for the UI; full text snapshotted into the pair).
+    final_text = ""
+    try:
+        final_text, _pages, _ = await extractor.extract_text(str(final_path))
+    except Exception as e:
+        logger.warning("final text extraction failed for %s: %s", case_number, e)
+
+    # Case → final.
+    pool = await db.get_pool()
+    async with pool.acquire() as conn:
+        await conn.execute(
+            "UPDATE cases SET status = 'final', updated_at = now() WHERE id = $1",
+            UUID(case["id"]),
+        )
+
+    # INV-LRN4 — snapshot OUR draft now and open the pair (status=final_received).
+    pair_id: str | None = None
+    draft_words = 0
+    try:
+        decision = await db.get_decision_by_case(UUID(case["id"]))
+        draft_text = ""
+        if decision:
+            async with pool.acquire() as conn:
+                brows = await conn.fetch(
+                    "SELECT content FROM decision_blocks "
+                    "WHERE decision_id = $1 AND word_count > 0 ORDER BY block_index",
+                    UUID(decision["id"]),
+                )
+            draft_text = "\n\n".join(b["content"] for b in brows if b["content"])
+        draft_words = len(draft_text.split())
+        pair_id = await db.create_draft_final_pair(
+            UUID(case["id"]), draft_text, str(final_path),
+        )
+    except Exception as e:
+        logger.warning("draft_final_pair snapshot failed for %s: %s", case_number, e)
+
+    case_dir = config.find_case_dir(case_number)
+    if case_dir.exists():
+        commit_and_push(case_dir, f"החלטה סופית של היו\"ר: {final_name}")
+
+    return {
+        "final_filename": final_name,
+        "training_copy": str(training_dest),
+        "pair_id": pair_id,
+        "draft_words": draft_words,
+        "final_words": len(final_text.split()),
+        "status": "final",
+    }
+
+
+async def _wake_final_task(case_number: str, task: str) -> dict:
+    """Shared trigger for the staged learning / halacha steps — wakes the local curator."""
+    case = await db.get_case_by_number(case_number)
+    if not case:
+        raise HTTPException(404, f"תיק {case_number} לא נמצא")
+    final_name = f"סופי-{case_number}.docx"
+    prefix = case_number[:1]
+    company_id = (
+        PAPERCLIP_COMPANIES["licensing"] if prefix == "1"
+        else PAPERCLIP_COMPANIES["betterment"] if prefix in ("8", "9")
+        else ""
+    )
+    try:
+        return await pc_wake_curator_for_final(
+            case_number, final_name, company_id=company_id, task=task,
+        )
+    except Exception as e:
+        logger.warning("final %s wakeup failed for %s: %s", task, case_number, e)
+        return {"status": "error", "error": str(e)}
+
+
+@app.post("/api/cases/{case_number}/final/run-learning")
+async def api_final_run_learning(case_number: str):
+    """Staged step 1 — voice learning: wake the local worker to run ingest_final_version
+    (Opus distillation) + the 2-judge style panel (DeepSeek+Gemini)."""
+    return await _wake_final_task(case_number, "learning")
+
+
+@app.post("/api/cases/{case_number}/final/run-halacha")
+async def api_final_run_halacha(case_number: str):
+    """Staged step 2 — halacha validation: wake the local worker to extract the cited
+    halachot, build corroboration, and run the 3-judge halacha panel (--apply)."""
+    return await _wake_final_task(case_number, "halacha")
+
+
 @app.post("/api/cases/{case_number}/export-docx")
 async def api_export_docx(case_number: str, background_tasks: BackgroundTasks):
     """Trigger DOCX export for a case.

web/paperclip_client.py

@@ -1050,17 +1050,75 @@ async def wake_ceo_agent(issue_id: str, case_number: str, company_id: str = "")
     return result
 
 
+def _curator_task_brief(task: str, case_number: str, final_filename: str) -> tuple[str, str]:
+    """Build the (sub-issue title, description) for a staged final-decision task.
+
+    task='learning' — draft↔final voice distillation + the 2-judge style panel.
+    task='halacha'  — extract the halachot CITED in the final + corroboration + the
+                      3-judge halacha panel.
+    The curator (Hermes) has Bash + MCP tools, so it both calls MCP tools and runs the
+    local panel scripts. Panels write only reversible, CSV-backed proposals (INV-G10).
+    """
+    if task == "halacha":
+        title = f"[ערר {case_number}] אימות-הלכות — פאנל 3-סוכנים"
+        description = (
+            f"אימות ההלכות שצוטטו בהחלטה הסופית של תיק {case_number} "
+            f"(`{final_filename}`).\n\n"
+            f"**שלב 1 — ציטוטים:** הרץ "
+            f"`mcp__legal-ai__extract_internal_citations(chair_name=\"דפנה תמיר\")` "
+            f"כדי למפות לאילו תקדימים ההחלטה מפנה.\n"
+            f"**שלב 2 — חילוץ הלכות:** לכל תקדים מצוטט שקיים בספרייה הרץ "
+            f"`mcp__legal-ai__precedent_extract_halachot(case_law_id=...)` (idempotent). "
+            f"תקדים מצוטט שחסר — `mcp__legal-ai__missing_precedent_create`.\n"
+            f"**שלב 3 — corroboration:** `mcp__legal-ai__corroboration_rebuild` לבניית "
+            f"אות-התיקוף (treatment) ומדיניות.\n"
+            f"**שלב 4 — פאנל-הלכות (אוטו-אישור + אסקלציה):** הרץ "
+            f"`cd ~/legal-ai/mcp-server && .venv/bin/python ../scripts/halacha_panel_approve.py --apply`. "
+            f"הסכמה 2/3+ → approved/rejected (הפיך, מגובה ל-CSV); פיצול → נשאר pending_review "
+            f"ליו\"ר. **אל תקבע סמכות binding/persuasive — היא נגזרת מ-precedent_level (INV-DM7).**\n"
+            f"**שלב 5:** כתוב comment בעברית עם סיכום (כמה אושרו/נדחו/הוסלמו), סגור issue (done)."
+        )
+        return title, description
+
+    # default: learning (voice distillation + style panel)
+    title = f"[ערר {case_number}] סקירת ידע — Knowledge Curator"
+    description = (
+        f"דפנה סימנה את ההחלטה הסופית של תיק {case_number} כסופית.\n"
+        f"קובץ סופי: `{final_filename}`\n\n"
+        f"**שלב 1 — דיסטילציה (חובה, draft↔final):** הרץ "
+        f"`mcp__legal-ai__ingest_final_version(case_number=\"{case_number}\")`. "
+        f"הוא משווה את הטיוטה (snapshot מפנקס-ההתאמה) לסופי, מסווג כל שינוי "
+        f"style_method מול substance (INV-LRN5), ושומר את ההצעה ב-draft_final_pairs "
+        f"(status→analyzed). **אל תקבע לקח לבד — זו הצעה לאישור.**\n"
+        f"**שלב 2 — פאנל-סגנון דו-סוכני (DeepSeek+Gemini, אוטו-אישור + אסקלציה):** הרץ "
+        f"`cd ~/legal-ai/mcp-server && .venv/bin/python ../scripts/style_lesson_panel.py "
+        f"--case {case_number} --apply`. הסכמה 2/2 → נכתב כ-decision_lesson "
+        f"(source=panel:deepseek+gemini); פיצול → מוסלם ליו\"ר. רק לקחי style_method "
+        f"נשקלים (substance מדולג, INV-LRN5).\n"
+        f"**שלב 3 — הצעה:** מתוך לקחי-הסגנון שאושרו בפאנל, בחר 3-5 דפוסים שלא תועדו "
+        f"ב-skills/decision/SKILL.md / docs/legal-decision-lessons.md / "
+        f"daphna-voice-fingerprint.md (אל תציע מה שכבר שם). כתוב comment בעברית, ניטרלי, ממוספר.\n"
+        f"**שלב 4:** עדכן MEMORY.md, סגור issue (status=done). הטמעה ל-SKILL.md/lessons.md "
+        f"נשארת אישור-יו\"ר ידני (INV-G10)."
+    )
+    return title, description
+
+
 async def wake_curator_for_final(
     case_number: str,
     final_filename: str,
     company_id: str = "",
+    task: str = "learning",
 ) -> dict:
-    """Wake the Knowledge Curator (Hermes) when a case is marked final.
+    """Wake the Knowledge Curator (Hermes) for a staged final-decision task.
 
     Creates a child issue under the main case issue, assigns it to the
     curator, and triggers wakeup. Best-effort — silently skips if no
     curator is configured for the company or no main issue is found.
 
+    ``task`` selects the brief: 'learning' (voice distillation + style panel) or
+    'halacha' (cited-halacha extraction + corroboration + halacha panel).
+
     Returns ``{"status": "ok"|"skipped", ...}``.
     """
     if not PAPERCLIP_BOARD_API_KEY:
@@ -1080,25 +1138,12 @@ async def wake_curator_for_final(
     main_issue = next((i for i in issues if i.get("status") == "in_progress"), None) or issues[0]
     main_issue_id = main_issue["id"]
 
-    description = (
-        f"דפנה סימנה את ההחלטה הסופית של תיק {case_number} כסופית.\n"
-        f"קובץ סופי: `{final_filename}`\n\n"
-        f"**שלב 1 — דיסטילציה (חובה, draft↔final):** הרץ "
-        f"`mcp__legal-ai__ingest_final_version(case_number=\"{case_number}\")`. "
-        f"הוא משווה את הטיוטה (snapshot מפנקס-ההתאמה) לסופי, מסווג כל שינוי "
-        f"style_method מול substance (INV-LRN5), ושומר את ההצעה ב-draft_final_pairs "
-        f"(status→analyzed). **אל תקבע לקח לבד — זו הצעה לאישור.**\n"
-        f"**שלב 2 — הצעה:** מתוך השינויים מסוג style_method בלבד, בחר 3-5 דפוסי "
-        f"סגנון/שיטה שלא תועדו ב-skills/decision/SKILL.md / docs/legal-decision-lessons.md / "
-        f"daphna-voice-fingerprint.md (אל תציע מה שכבר שם). כתוב comment בעברית, ניטרלי, ממוספר.\n"
-        f"**שלב 3:** עדכן MEMORY.md, סגור issue (status=done). substance (הלכות/עובדות) — "
-        f"לא נכנס לקול; אם זוהתה הלכה חדשה הפנה למסלול precedent."
-    )
+    title, description = _curator_task_brief(task, case_number, final_filename)
     child_resp = await pc_request(
         "POST",
         f"/api/issues/{main_issue_id}/children",
         json={
-            "title": f"[ערר {case_number}] סקירת ידע — Knowledge Curator",
+            "title": title,
             "description": description,
             "status": "in_progress",
             "priority": "low",
@@ -1126,7 +1171,7 @@ async def wake_curator_for_final(
         json={
             "source": "on_demand",
             "triggerDetail": "manual",
-            "reason": f"final_marked_{case_number}",
+            "reason": f"final_{task}_{case_number}",
             "payload": {
                 "issueId": sub_issue_id,
                 "mutation": "assignment",