feat(health): טקסונומיית-בריאות לסוכן — zombie/stalled/working/idle (#222)

מוסיף web/agent_health.py — מסווג-טהור classify_issue_health (agent-agnostic,
testable) שממפה כל issue פתוח+משויך-סוכן למצב-בריאות אחד, ו-get_agent_health
ב-paperclip_client שגוזר את הפרימיטיבים מ-heartbeat_runs (run חי=finished_at null
בחלון) + agent_wakeup_requests (total + recovery-markers בחלון). מרכיב על אירועי
#219 (אותם reasons של recovery).

- zombie = פתוח+משויך-סוכן, אין run חי, יש wakeup-recovery → הstranded-child שאובחן
  ידנית (reference_recovery_loop_stranded_child) עולה אוטומטית.
- stalled = ננער חוזר בלי progress; working = run חי; idle = המתנה בנונית.
- Port: pc_get_agent_health (read-only, לא עטוף-טלמטריה לפי הכלל); endpoint
  GET /api/operations/agents/health (worst-first, +counts).
- 7 בדיקות pytest (מסווג-טהור + fetch fake-asyncpg). אומת חי read-only מול
  Paperclip DB: 6 issues→idle נכון, אפס zombie.

Invariants: מקיים G12 (מסווג אגנוסטי; fetch מהמעטפת; המגע מהשער), G2 (מקור-בריאות
יחיד). UI ב-/operations = follow-up מגודר-שער-עיצוב (feedback_claude_design_gate).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

web/tests/test_agent_health.py

@@ -0,0 +1,115 @@
+"""Tests for #222 — agent health taxonomy (pure classifier + Paperclip fetch).
+
+Pure-classifier tests need no deps. The fetch test fakes an asyncpg connection
+(routing the three queries by content) so it never touches the live DB.
+"""
+
+from __future__ import annotations
+
+import asyncio
+import os
+import sys
+from pathlib import Path
+
+import pytest
+
+sys.path.insert(0, str(Path(__file__).resolve().parents[1]))  # web/
+
+from agent_health import (  # noqa: E402
+    STALL_WAKEUP_THRESHOLD,
+    classify_issue_health,
+    is_recovery_reason,
+)
+
+
+# ── pure classifier ────────────────────────────────────────────────────────
+def test_live_run_is_working_regardless_of_wakeups():
+    assert classify_issue_health(has_live_run=True, recovery_wakeups=9, total_wakeups=9) == "working"
+
+
+def test_recovery_wakeup_without_live_run_is_zombie():
+    # the stranded-child signature: assigned+open, nothing running, recovery firing
+    assert classify_issue_health(has_live_run=False, recovery_wakeups=1, total_wakeups=1) == "zombie"
+
+
+def test_repeated_wakeups_no_recovery_is_stalled():
+    assert (
+        classify_issue_health(
+            has_live_run=False, recovery_wakeups=0, total_wakeups=STALL_WAKEUP_THRESHOLD
+        )
+        == "stalled"
+    )
+
+
+def test_quiet_open_issue_is_idle():
+    assert classify_issue_health(has_live_run=False, recovery_wakeups=0, total_wakeups=1) == "idle"
+
+
+def test_is_recovery_reason_markers():
+    assert is_recovery_reason("source_scoped_recovery_action")
+    assert is_recovery_reason("issue_continuation_needed")
+    assert is_recovery_reason("issue_reopened_via_comment")
+    assert not is_recovery_reason("start_workflow_8125-09-24")
+    assert not is_recovery_reason(None)
+
+
+# ── Paperclip fetch (fake DB) ───────────────────────────────────────────────
+os.environ.setdefault("PAPERCLIP_DB_URL", "postgres://x:x@127.0.0.1:54329/paperclip")
+pc = pytest.importorskip("paperclip_client", reason="web deps unavailable")
+
+
+class _FakeConn:
+    def __init__(self, issues, live, wakeups):
+        self._issues, self._live, self._wakeups = issues, live, wakeups
+
+    async def fetch(self, query, *args):
+        if "FROM issues" in query:
+            return self._issues
+        if "heartbeat_runs" in query:
+            return self._live
+        if "agent_wakeup_requests" in query:
+            return self._wakeups
+        raise AssertionError(f"unexpected query: {query[:40]}")
+
+    async def close(self):
+        pass
+
+
+def test_get_agent_health_classifies_and_sorts(monkeypatch):
+    # zombie agent A (recovery wake, no live run); working agent B (live run);
+    # idle agent C (quiet).
+    issues = [
+        {"id": "iA", "identifier": "CMP-1", "status": "blocked", "assignee_agent_id": "agA", "agent_name": "writer"},
+        {"id": "iB", "identifier": "CMP-2", "status": "in_progress", "assignee_agent_id": "agB", "agent_name": "analyst"},
+        {"id": "iC", "identifier": "CMP-3", "status": "todo", "assignee_agent_id": "agC", "agent_name": "qa"},
+    ]
+    live = [{"agent_id": "agB"}]
+    wakeups = [
+        {"agent_id": "agA", "issue_id": "iA", "reason": "source_scoped_recovery_action"},
+        {"agent_id": "agC", "issue_id": "iC", "reason": "start_workflow_x"},
+    ]
+
+    async def _connect(_url):
+        return _FakeConn(issues, live, wakeups)
+
+    monkeypatch.setattr(pc.asyncpg, "connect", _connect)
+
+    result = asyncio.run(pc.get_agent_health())
+    assert result["ok"] is True
+    by_issue = {it["issue_id"]: it["health"] for it in result["items"]}
+    assert by_issue == {"iA": "zombie", "iB": "working", "iC": "idle"}
+    assert result["counts"]["zombie"] == 1
+    assert result["counts"]["working"] == 1
+    assert result["counts"]["idle"] == 1
+    # worst-first: zombie leads
+    assert result["items"][0]["health"] == "zombie"
+    assert result["items"][0]["recovery_wakeups"] == 1
+
+
+def test_get_agent_health_empty(monkeypatch):
+    async def _connect(_url):
+        return _FakeConn([], [], [])
+
+    monkeypatch.setattr(pc.asyncpg, "connect", _connect)
+    result = asyncio.run(pc.get_agent_health())
+    assert result == {"ok": True, "items": [], "counts": {"zombie": 0, "stalled": 0, "working": 0, "idle": 0}}