feat: advance repository records and provenance

Assistant: codex
Assistant-Model: gpt-5.6-sol
Assistant-Session: 01a023c0-a0a3-7c03-b395-5a0d2757214d

src/repo_manager/parse/record.py

@@ -0,0 +1,78 @@
+"""Parse repository-owned intake and decision records from Markdown YAML fences."""
+
+from __future__ import annotations
+
+import re
+from dataclasses import dataclass, field
+from pathlib import Path
+from typing import Any
+
+import yaml
+
+_YAML_FENCE_RE = re.compile(r"```ya?ml\s*\n(.*?)\n```", re.DOTALL | re.IGNORECASE)
+SUPPORTED_RECORD_KINDS = frozenset({"intake", "decision"})
+
+
+@dataclass
+class ParsedRecord:
+    kind: str
+    id: str
+    title: str | None
+    status: str | None
+    uuid: str | None
+    source_path: str
+    raw: dict[str, Any] = field(default_factory=dict)
+    block_start: int = 0
+    block_end: int = 0
+
+
+def parse_record_text(text: str, *, relative_path: str) -> list[ParsedRecord]:
+    """Return intake/decision records embedded in YAML fenced blocks."""
+    records: list[ParsedRecord] = []
+    for match in _YAML_FENCE_RE.finditer(text):
+        try:
+            data = yaml.safe_load(match.group(1)) or {}
+        except yaml.YAMLError:
+            continue
+        if not isinstance(data, dict) or data.get("kind") not in SUPPORTED_RECORD_KINDS:
+            continue
+        record_id = data.get("id")
+        if record_id is None:
+            continue
+        kind = str(data["kind"])
+        uuid_field = "state_hub_intake_id" if kind == "intake" else "state_hub_decision_id"
+        records.append(
+            ParsedRecord(
+                kind=kind,
+                id=str(record_id),
+                title=str(data["title"]) if data.get("title") is not None else None,
+                status=str(data["status"]) if data.get("status") is not None else None,
+                uuid=str(data[uuid_field]) if data.get(uuid_field) is not None else None,
+                source_path=relative_path,
+                raw=data,
+                block_start=match.start(),
+                block_end=match.end(),
+            )
+        )
+    return records
+
+
+def parse_record_file(path: Path, *, repo_root: Path) -> list[ParsedRecord]:
+    return parse_record_text(
+        path.read_text(encoding="utf-8"),
+        relative_path=str(path.relative_to(repo_root)),
+    )
+
+
+def iter_record_files(repo_root: Path) -> list[Path]:
+    """Find only the governed record locations; do not interpret arbitrary docs."""
+    files: set[Path] = set()
+    for relative in ("intakes", "decisions", "docs/intakes", "docs/decisions", "workplans"):
+        root = repo_root / relative
+        if root.is_dir():
+            files.update(path for path in root.rglob("*.md") if not path.name.startswith("."))
+    for name in ("INTAKES.md", "DECISIONS.md"):
+        path = repo_root / name
+        if path.is_file():
+            files.add(path)
+    return sorted(files)