feat(plan-01): Phase 1 — relocate harness code to packages/casan-harness (symlink facade)

Physically move the pure-code subtrees out of .specify into the package, leaving compat symlinks at the old .specify/<dir> paths so every existing reference (internal CASAN_HARNESS_ROOT + external CI/docker/mjs) keeps resolving. Runtime state stays put. Moved (git mv): scripts/ tests/ security/ templates/ config/ governance/ memory/ .specify/<dir> -> packages/casan-harness/<dir> (+ .specify/<dir> symlink) Stays in .specify (state/governance/domain, handled later): logs/ agentops/ level5/ init-options.json traceability-map.json Python `.resolve()` self-location followed the compat symlink into packages and lost the app root; generate-casan-demo-context.py, generate-agentops-dashboard.py and dashboard-server.py now walk UP for the `.specify` state marker instead of a fixed parent depth (fixes "missing trace files" in run-casan4). Full gate: PASS=64 FAIL=0 SKIP=3 (CASAN_CI_STEP_TIMEOUT_SEC=1200 — track-a ~450s runs close to the 600s default and can tip over under load; this is timing variance, not a regression — it passed cleanly with headroom). Runtime log/audit artifacts kept unstaged. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-08 00:06:00 +09:00
parent 2c765c9a45
commit 664bd1f00c
229 changed files with 268 additions and 3 deletions
@@ -0,0 +1,97 @@
+#!/usr/bin/env python3
+"""CASAN H6 — hosted AgentOps dashboard server (D3).
+
+Serves the generated dashboard over HTTP with a stale-aware /healthz probe so
+an external monitor (uptime check / load-balancer) can page when telemetry
+stops flowing — not just when the process dies.
+
+Routes:
+  GET /            -> dashboard HTML (also /dashboard)
+  GET /healthz     -> 200 {"status":"ok",...} while metrics are fresh,
+                      503 {"status":"stale",...} when metrics are older than
+                      CASAN_DASHBOARD_STALE_S (default 3600s) or missing.
+
+Usage: dashboard-server.py <port>
+"""
+import json
+import os
+import pathlib
+import sys
+import time
+from http.server import BaseHTTPRequestHandler, HTTPServer
+
+def _app_root(start):
+    # Plan-01: `.resolve()` follows the compat symlink into packages/casan-harness;
+    # dashboards + runtime logs live at the app's `.specify`, so walk UP for it.
+    d = pathlib.Path(start).resolve()
+    for p in (d, *d.parents):
+        if (p / ".specify").is_dir():
+            return p
+    return d.parents[3]
+
+
+ROOT = _app_root(__file__)
+PORT = int(sys.argv[1]) if len(sys.argv) > 1 else 8787
+DASH = pathlib.Path(os.environ.get(
+    "CASAN_DASHBOARD_HTML", ROOT / "docs" / "output" / "casan" / "central-agentops-dashboard.html"))
+METRICS = pathlib.Path(os.environ.get(
+    "CASAN_DASHBOARD_METRICS", ROOT / ".specify" / "logs" / "cost" / "metrics.jsonl"))
+ALERTS = pathlib.Path(os.environ.get(
+    "CASAN_DASHBOARD_ALERTS", ROOT / ".specify" / "agentops" / "alerts.log"))
+STALE_S = int(os.environ.get("CASAN_DASHBOARD_STALE_S", "3600"))
+
+
+def count_lines(path: pathlib.Path) -> int:
+    if not path.exists():
+        return 0
+    return sum(1 for line in path.read_text(encoding="utf-8").splitlines() if line.strip())
+
+
+class Handler(BaseHTTPRequestHandler):
+    def _send(self, code: int, ctype: str, body: str) -> None:
+        data = body.encode("utf-8")
+        self.send_response(code)
+        self.send_header("Content-Type", ctype)
+        self.send_header("Content-Length", str(len(data)))
+        self.end_headers()
+        self.wfile.write(data)
+
+    def do_GET(self):  # noqa: N802 (http.server API)
+        if self.path == "/healthz":
+            if METRICS.exists():
+                age = int(time.time() - METRICS.stat().st_mtime)
+                stale = age > STALE_S
+            else:
+                age = -1
+                stale = True
+            body = json.dumps({
+                "status": "stale" if stale else "ok",
+                "metrics_age_s": age,
+                "stale_after_s": STALE_S,
+                "runs": count_lines(METRICS),
+                "alerts": count_lines(ALERTS),
+            })
+            self._send(503 if stale else 200, "application/json", body)
+        elif self.path in ("/", "/dashboard"):
+            if DASH.exists():
+                self._send(200, "text/html; charset=utf-8", DASH.read_text(encoding="utf-8"))
+            else:
+                self._send(404, "text/plain", "dashboard not generated")
+        else:
+            self._send(404, "text/plain", "not found")
+
+    def log_message(self, *args):  # silence per-request stderr noise
+        pass
+
+BIND = os.environ.get("CASAN_DASHBOARD_BIND", "127.0.0.1")
+
+
+if __name__ == "__main__":
+    # SEC-13 (M-09): the dashboard has no auth, so binding to all interfaces exposes
+    # it to the network. In enforced mode refuse a non-loopback bind (fail-closed);
+    # a real deployment must front it with TLS + auth (Plan-07 TIER 2), not 0.0.0.0.
+    _enforced = os.environ.get("CASAN_PROFILE") == "prod" or os.environ.get("CASAN_DASHBOARD_STRICT") == "1"
+    if _enforced and BIND not in ("127.0.0.1", "::1", "localhost"):
+        sys.stderr.write(f"DASHBOARD_BIND_REFUSED bind={BIND} (loopback only in enforced mode)\n")
+        raise SystemExit(1)
+    HTTPServer((BIND, PORT), Handler).serve_forever()