Fix YAML parser: HTML-unescape content before parse

Multica's comment REST API returns content with HTML entities escaped
(`"` for `"`, `>` for `>`, etc.). Agent replies are plain UTF-8,
so we unescape before extracting and parsing.

Caught by the first live test against WYL-72: Meta-Judge produced a
perfectly valid YAML evaluation specification with CK-001..CK-010 checklist
items, but my parser reported it as malformed because `"` is not a
valid YAML token. The model was fine; the plumbing was wrong.

- src/coordinator/orchestrator.py: _extract_yaml now calls html.unescape first
- tests/test_orchestrator.py: +2 tests covering entity decoding

Tests: 69 passed.

src/coordinator/orchestrator.py

@@ -43,6 +43,7 @@ Race fix invariant
 """
 from __future__ import annotations
 
+import html
 import logging
 import re
 from datetime import datetime, timezone
@@ -177,14 +178,19 @@ def _find_reply_by_agent(
 def _extract_yaml(content: str) -> str:
     """Pull the YAML block out of a reply.  Prefers fenced code blocks.
 
+    Multica's comment REST API returns content with HTML entities escaped
+    (``"`` for ``"``, ``>`` for ``>``, etc.).  Agent replies are
+    plain UTF-8 to begin with, so we unescape first, then extract.
+
     Returns the YAML text (without fences), or the original content if no fence
     is found.  The caller is responsible for deciding whether the raw content
     is parseable.
     """
-    m = _YAML_FENCE_RE.search(content)
+    unescaped = html.unescape(content)
+    m = _YAML_FENCE_RE.search(unescaped)
     if m:
         return m.group(1).strip()
-    return content.strip()
+    return unescaped.strip()
 
 
 def _parse_rubric(content: str) -> dict[str, Any] | None:

tests/test_orchestrator.py

@@ -192,6 +192,29 @@ def test_extract_yaml_from_unfenced_content():
     assert y == content.strip()
 
 
+def test_extract_yaml_unescapes_html_entities():
+    # Multica REST API returns comment content with `"` as `"`, `>` as `>`, etc.
+    content = "checklist:\n  - id: "CK-001"\n    question: "does it work?""
+    y = _extract_yaml(content)
+    assert '"CK-001"' in y
+    assert """ not in y
+
+
+def test_parse_rubric_accepts_html_encoded_input():
+    encoded = (
+        "rrd_cycle_applied: true\n"
+        "evaluation_specification:\n"
+        "  checklist:\n"
+        "    - id: "CK-001"\n"
+        "      question: "does it work?"\n"
+        "      category: "hard_rule"\n"
+        "      importance: "essential"\n"
+    )
+    spec = _parse_rubric(encoded)
+    assert spec is not None
+    assert "checklist" in spec
+
+
 def test_parse_rubric_valid_flat():
     spec = _parse_rubric(f"```yaml\n{_rubric_yaml_sample()}\n```")
     assert spec is not None