Wire legal-writer to chair directions from analysis-and-research.md

Closes the loop so דפנה's positions (written inline in the UI and
saved to analysis-and-research.md) automatically become binding
direction for the legal-writer agent — no manual copy-paste,
no bypass.

Backend:
- research_md.extract_chair_directions(path) returns a compact dict
  with status (missing/empty/partial/complete), filled_count,
  empty_count, and a reduced list of threshold_claims + issues each
  with {id, number, title, direction}. Designed to be directly usable
  as direction_doc by the writer.
- New MCP tool: drafting.get_chair_directions(case_number) wraps the
  helper, resolves the case research file path via config.find_case_dir,
  returns formatted JSON.
- Registered in server.py as mcp__legal-ai__get_chair_directions.

legal-writer agent update:
- Adds get_chair_directions to the tools list.
- New mandatory "שלב 1ב" before any block writing: call
  get_chair_directions, branch on status.
  - missing → halt, report "legal-analyst לא רץ עדיין"
  - empty → halt, instruct Dafna to fill positions via the UI URL
  - partial → halt unless user confirms; write only filled sections
  - complete → proceed
- New "שלב 1ג" constructs an internal direction_doc from the
  received chair rulings before writing block י.
- Block י section expanded with 5 binding rules:
  1. Open each discussion with Dafna's ruling as the thesis
  2. Frame the reasoning in her style (use get_style_guide phrases)
  3. Match her tone (decisive vs nuanced)
  4. Must NOT contradict her position — if she disagreed with your
     own inclination, her position rules
  5. Use legal_questions from the analysis file as the analytical
     structure (principle question first, concrete application second)
- New bullet section for block יא: summarize each chair ruling
  briefly, state final outcome, close with the signed date formula.

Verified all four status paths (missing/empty/partial/complete) via
local test. Now Dafna's workflow is fully end-to-end: she reads the
analyst report in the UI, fills "עמדת ועדת הערר" in each card, hits
blur to auto-save, then triggers legal-writer — which picks up her
positions as direction without any file shuffle.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

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

@@ -353,3 +353,84 @@ def update_chair_position(
         "preview": preview,
         "timestamp": datetime.now().isoformat(),
     }
+
+
+# ── Chair directions extraction (for downstream agents) ─────────
+
+
+def extract_chair_directions(file_path: Path) -> dict[str, Any]:
+    """Extract only the chair positions from analysis-and-research.md.
+
+    Returns a compact dict that the legal-writer agent can use as direction:
+
+    {
+      "case_number": "1033-25",
+      "file_path": "...",
+      "file_exists": True,
+      "total_items": 9,
+      "filled_count": 3,
+      "empty_count": 6,
+      "status": "partial",   # "empty" | "partial" | "complete"
+      "threshold_claims": [
+        {"id": "threshold_1", "number": 1, "title": "...", "direction": "..."},
+        ...
+      ],
+      "issues": [
+        {"id": "issue_1", "number": 1, "title": "...", "direction": "..."},
+        ...
+      ]
+    }
+
+    Used by legal-writer to convert chair positions into direction docs
+    before generating blocks of the decision.
+    """
+    if not file_path.exists():
+        return {
+            "file_exists": False,
+            "status": "missing",
+            "error": "analysis-and-research.md not found",
+            "threshold_claims": [],
+            "issues": [],
+            "total_items": 0,
+            "filled_count": 0,
+            "empty_count": 0,
+        }
+
+    parsed = parse(file_path)
+
+    def reduce_item(item: dict) -> dict:
+        return {
+            "id": item["id"],
+            "number": item["number"],
+            "title": item["title"],
+            "direction": item.get("chair_position", "") or "",
+        }
+
+    threshold = [reduce_item(t) for t in parsed.get("threshold_claims", [])]
+    issues = [reduce_item(i) for i in parsed.get("issues", [])]
+
+    all_items = threshold + issues
+    total = len(all_items)
+    filled = sum(1 for x in all_items if x["direction"].strip())
+    empty = total - filled
+
+    if total == 0:
+        status = "missing"
+    elif filled == 0:
+        status = "empty"
+    elif filled == total:
+        status = "complete"
+    else:
+        status = "partial"
+
+    return {
+        "file_exists": True,
+        "file_path": str(file_path),
+        "case_number": parsed.get("header", {}).get("case_number", ""),
+        "status": status,
+        "total_items": total,
+        "filled_count": filled,
+        "empty_count": empty,
+        "threshold_claims": threshold,
+        "issues": issues,
+    }