feat(classification-spine): implement STATE-WP-0065 repo-anchored model

Replace the ad-hoc coordination-domain spine with the Repo Classification
Standard: 14 market domains, classification columns on managed_repos, and
workplans anchored by repo_id (topic_id optional).

- Add Alembic migration d8e9f0a1b2c3 with data backfill and workstream→workplan rename
- Add api/classification.py validation and register-from-classification tooling
- Expose workplan-first REST/MCP surface with legacy workstream aliases
- Add C-24 consistency rule and legacy domain frontmatter mapping
- Update dashboard repos page with category/capability/stake filters
- Update orientation docs; mark STATE-WP-0065 finished

scripts/consistency_check.py

@@ -26,6 +26,7 @@ Checks:
   C-20  workstream-dependency-missing WARN Yes Workplan dependency frontmatter missing from DB graph
   C-22  task-description-drift  WARN  Yes  Task description/content differs between file and DB
   C-23  workstream-active-task-planning-status WARN Yes Workstream/workplan is planning while a task is progress or wait
+  C-24  repo-classification-missing WARN  No   Registered repo lacks a valid .repo-classification.yaml on disk
 
 Usage:
     python scripts/consistency_check.py --repo SLUG [--fix] [--no-writeback] [--json] [--api-base URL]
@@ -42,7 +43,7 @@ Exit codes (--remote --all scheduled sweep):
     1 — automation error: API unreachable, repo list fetch failed, C-00 on
         any repo, or other infrastructure fault that prevented a full run
 
-Assessment failures (C-01..C-23 except C-00) are repo hygiene gaps recorded
+Assessment failures (C-01..C-24 except C-00) are repo hygiene gaps recorded
 in the sweep report for later improvement. They do not fail the scheduler.
 
 Agent/operator Make wrappers normalize exit code 2 to shell success while
@@ -78,6 +79,11 @@ from api.workplan_status import (  # noqa: E402
     normalize_workstream_status as _normalize_workstream_status,
     ready_review_status,
 )
+from api.classification import (  # noqa: E402
+    CLASSIFICATION_FILENAME,
+    load_classification_file,
+    resolve_topic_domain_slug,
+)
 from api.services.lifecycle import should_activate_parent_for_active_tasks  # noqa: E402
 from api.task_status import (  # noqa: E402
     CANONICAL_TASK_STATUSES,
@@ -713,6 +719,31 @@ def check_repo(api_base: str, repo_slug: str, repo_path_override: str | None = N
 
     repo_dir = Path(repo_path)
     workplans_dir = repo_dir / "workplans"
+    repo_market_domain = str(repo.get("domain_slug") or "").strip()
+
+    # C-24: repo classification file missing or invalid (always WARN — migration rows too)
+    class_data, class_errors, class_warnings = load_classification_file(repo_dir)
+    if class_data is None:
+        classified_by = str(repo.get("classified_by") or "").strip()
+        if class_errors:
+            detail = "; ".join(class_errors)
+        else:
+            detail = f"{CLASSIFICATION_FILENAME} missing on disk"
+        if classified_by == "migration":
+            detail = f"{detail} (DB row is migration-derived — commit a human-reviewed file when ready)"
+        report.add(
+            severity="WARN",
+            check_id="C-24",
+            message=f"Repo classification gap: {detail}",
+            fixable=False,
+        )
+    for warning in class_warnings:
+        report.add(
+            severity="WARN",
+            check_id="C-24",
+            message=f"Repo classification advisory: {warning}",
+            fixable=False,
+        )
 
     # C-01: workplans/ directory missing
     if not workplans_dir.is_dir():
@@ -804,6 +835,7 @@ def check_repo(api_base: str, repo_slug: str, repo_path_override: str | None = N
                     "body": body,
                     "repo_id": repo_id,
                     "domain": file_domain,
+                    "repo_market_domain": repo_market_domain,
                 },
             )
             continue
@@ -1708,6 +1740,7 @@ def fix_repo(
                 wp_file = Path(ctx["wp_file"])
                 meta = ctx["meta"]
                 domain = ctx["domain"]
+                repo_market_domain = str(ctx.get("repo_market_domain") or "").strip()
                 repo_id_val = ctx["repo_id"]
                 body = ctx.get("body", "")
                 wp_id = str(meta.get("id", "")).strip()
@@ -1717,17 +1750,23 @@ def fix_repo(
                 if status not in VALID_WP_STATUSES:
                     status = "active"
 
-                # Find topic_id for this domain
+                # Find topic_id — workplan frontmatter may still use legacy
+                # coordination slugs (e.g. custodian); map to market domain first.
+                topic_domain = resolve_topic_domain_slug(
+                    domain,
+                    repo_market_domain=repo_market_domain or None,
+                )
                 topics = _api_get(api_base, "/topics")
                 topic_id = None
                 if isinstance(topics, list):
                     for t in topics:
-                        if t.get("domain_slug") == domain:
+                        if t.get("domain_slug") == topic_domain:
                             topic_id = t["id"]
                             break
                 if topic_id is None:
                     report.fixes_applied.append(
-                        f"C-06 SKIP {wp_id}: no topic found for domain '{domain}'"
+                        f"C-06 SKIP {wp_id}: no topic found for domain "
+                        f"'{topic_domain}' (workplan domain={domain!r})"
                     )
                     continue