Merge pull request 'feat(operations): פאנל בריאות-הסוכנים + הסלמות אחרונות ב-/operations (#218+#222 UI)' (#409) from worktree-ops-agent-health-ui into main

web-ui/src/app/operations/page.tsx

@@ -29,12 +29,15 @@ import {
   useRunLog,
   useCancelRun,
   useResetAgentSession,
+  useAgentHealth,
+  useRecentEscalations,
   type OpsService,
   type OperationsSnapshot,
   type PipelineStats,
   type AgentRun,
   type SubscriptionUsage,
   type UsageWindow,
+  type AgentHealthState,
 } from "@/lib/api/operations";
 import { formatTime, israelParts } from "@/lib/format-date";
 
@@ -802,6 +805,154 @@ function LiveAgentsPanel() {
   );
 }
 
+// ── Agent health taxonomy (#222) + recent escalations (#218) ───────────────
+const HEALTH_LABEL: Record<AgentHealthState, string> = {
+  zombie: "זומבי",
+  stalled: "תקוע",
+  working: "עובד",
+  idle: "רגוע",
+};
+
+function AgentHealthPanel() {
+  const { data, isLoading } = useAgentHealth();
+  const { data: esc } = useRecentEscalations();
+
+  const counts = data?.counts;
+  // Only zombies/stalled are "problems" — the backend already sorts worst-first.
+  // An escalated issue is chair-owned, so it leaves this list; the escalations
+  // card below is the handled-loop history.
+  const problems = (data?.items ?? []).filter(
+    (i) => i.health === "zombie" || i.health === "stalled",
+  );
+  const healthyWorking = counts?.working ?? 0;
+  const healthyIdle = counts?.idle ?? 0;
+
+  return (
+    <div className="space-y-4">
+      <Card className="bg-surface border-rule shadow-sm">
+        <CardContent className="px-6 py-5">
+          {isLoading || !data ? (
+            <Skeleton className="h-24 w-full" />
+          ) : (
+            <>
+              <div className="flex flex-wrap gap-2 mb-4">
+                <StatTile
+                  label="זומבי"
+                  value={counts?.zombie ?? 0}
+                  tone="red"
+                  title="לולאת-recovery — משויך+פעיל-כביכול אך אין ריצה חיה. מוסלם אוטומטית."
+                />
+                <StatTile
+                  label="תקוע"
+                  value={counts?.stalled ?? 0}
+                  tone="amber"
+                  title="ננער חוזר בלי התקדמות"
+                />
+                <StatTile label="עובד" value={counts?.working ?? 0} tone="green" />
+                <StatTile label="רגוע" value={counts?.idle ?? 0} tone="muted" />
+              </div>
+
+              {problems.length === 0 ? (
+                <p className="text-sm text-emerald-600">
+                  אין סוכן תקוע כרגע — כל הסוכנים תקינים.
+                </p>
+              ) : (
+                <div className="grid gap-2">
+                  {problems.map((p) => (
+                    <div
+                      key={p.issue_id}
+                      className={
+                        p.health === "zombie"
+                          ? "flex items-center justify-between gap-3 rounded-md border border-destructive/30 bg-destructive/5 px-3 py-2"
+                          : "flex items-center justify-between gap-3 rounded-md border border-gold/40 bg-gold-wash px-3 py-2"
+                      }
+                    >
+                      <div className="flex items-center gap-2 flex-wrap min-w-0">
+                        <Badge
+                          variant={p.health === "zombie" ? "destructive" : "outline"}
+                          className={
+                            p.health === "stalled"
+                              ? "border-warn/50 text-warn font-normal"
+                              : "font-normal"
+                          }
+                        >
+                          {HEALTH_LABEL[p.health]}
+                        </Badge>
+                        <span dir="ltr" className="font-mono text-[0.82rem] text-navy font-semibold">
+                          {p.identifier}
+                        </span>
+                        <span className="text-[0.82rem] text-navy font-semibold">
+                          {p.agent_name}
+                        </span>
+                        <span className="text-[0.7rem] text-ink-muted">
+                          {p.recovery_wakeups > 0
+                            ? `${p.recovery_wakeups} יקיצות-שחזור`
+                            : `${p.wakeups} יקיצות`}
+                        </span>
+                      </div>
+                      <span className="text-[0.7rem] text-ink-muted shrink-0">
+                        {p.health === "zombie" ? "יוסלם אוטומטית" : "מנוטר"}
+                      </span>
+                    </div>
+                  ))}
+                </div>
+              )}
+
+              <p className="mt-3 text-[0.78rem] text-ink-muted">
+                <b className="text-navy">{healthyWorking + healthyIdle} סוכנים תקינים</b> —{" "}
+                {healthyWorking} עובדים, {healthyIdle} רגועים. מוצגות רק בעיות.
+              </p>
+            </>
+          )}
+        </CardContent>
+      </Card>
+
+      {/* handled-loop history — the watchdog's escalations, gold-wash like a gate */}
+      <Card className="bg-gold-wash border-gold/40 shadow-sm">
+        <CardContent className="px-5 py-4">
+          <h3 className="text-navy text-sm font-semibold mb-0.5">הסלמות אוטומטיות אחרונות</h3>
+          <p className="text-ink-muted text-[0.72rem] mb-3">
+            כל זומבי מתמשך (לולאת-recovery ≥2 יקיצות-שחזור) משויך אליך אוטומטית עם הערת-מערכת
+            — בלי להעיר סוכן מחדש.
+          </p>
+          {!esc?.items?.length ? (
+            <p className="text-sm text-ink-muted">אין הסלמות אחרונות.</p>
+          ) : (
+            <div className="grid gap-1">
+              {esc.items.map((e) => (
+                <div
+                  key={`${e.issue_id}-${e.created_at ?? ""}`}
+                  className="flex items-start gap-2.5 border-t border-gold/15 first:border-0 pt-2 first:pt-0"
+                >
+                  <Badge
+                    variant={e.severity === "medium" ? "outline" : "destructive"}
+                    className={
+                      e.severity === "medium"
+                        ? "border-gold/50 text-gold-deep font-normal shrink-0"
+                        : "font-normal shrink-0"
+                    }
+                  >
+                    {e.severity}
+                  </Badge>
+                  <div className="min-w-0 flex-1">
+                    <span dir="ltr" className="font-mono text-[0.8rem] text-navy font-semibold">
+                      {e.identifier}
+                    </span>
+                    <div className="text-[0.78rem] text-ink-soft">{e.reason}</div>
+                  </div>
+                  <span className="text-[0.68rem] text-ink-muted shrink-0">
+                    {e.created_at ? ago(Date.parse(e.created_at)) : ""}
+                  </span>
+                </div>
+              ))}
+            </div>
+          )}
+        </CardContent>
+      </Card>
+    </div>
+  );
+}
+
 export default function OperationsPage() {
   const { data, isLoading, error } = useOperations();
 
@@ -840,6 +991,9 @@ export default function OperationsPage() {
             <SectionHeader>סוכנים פעילים</SectionHeader>
             <LiveAgentsPanel />
 
+            <SectionHeader>בריאות-הסוכנים</SectionHeader>
+            <AgentHealthPanel />
+
             <SectionHeader>מתאמי-סוכנים</SectionHeader>
             <AgentAdaptersPanel />
 

web-ui/src/lib/api/operations.ts

@@ -190,6 +190,61 @@ export function useAgentRuns() {
   });
 }
 
+// ── Agent health taxonomy (#222) + recent escalations (#218) ───────────────
+export type AgentHealthState = "zombie" | "stalled" | "working" | "idle";
+
+export type AgentHealthItem = {
+  issue_id: string;
+  identifier: string;
+  status: string;
+  agent_id: string;
+  agent_name: string;
+  health: AgentHealthState;
+  wakeups: number;
+  recovery_wakeups: number;
+};
+
+export type AgentHealthResponse = {
+  ok: boolean;
+  items: AgentHealthItem[]; // worst-first (zombie → stalled → working → idle)
+  counts: Record<AgentHealthState, number>;
+};
+
+/** Per-issue agent health — surfaces recovery-loop zombies automatically. */
+export function useAgentHealth() {
+  return useQuery({
+    queryKey: ["operations", "agents", "health"],
+    queryFn: ({ signal }) =>
+      apiRequest<AgentHealthResponse>("/api/operations/agents/health", { signal }),
+    refetchInterval: 5000, // live alongside the running-agents view
+    staleTime: 3000,
+  });
+}
+
+export type EscalationItem = {
+  issue_id: string;
+  identifier: string;
+  severity: "critical" | "high" | "medium";
+  reason: string;
+  created_at: string | null;
+};
+
+export type RecentEscalationsResponse = {
+  ok: boolean;
+  items: EscalationItem[]; // newest-first
+};
+
+/** Recent chair escalations (watchdog + manual) — the handled-loop history. */
+export function useRecentEscalations() {
+  return useQuery({
+    queryKey: ["operations", "agents", "escalations"],
+    queryFn: ({ signal }) =>
+      apiRequest<RecentEscalationsResponse>("/api/operations/agents/escalations", { signal }),
+    refetchInterval: 15000, // escalations change slowly (watchdog runs every 15m)
+    staleTime: 10000,
+  });
+}
+
 /** Full output log of one run — fetched on demand (drawer open). */
 export function useRunLog(runId: string | null) {
   return useQuery({

web/agent_platform_port.py

@@ -41,6 +41,7 @@ from web.paperclip_client import (
     create_project as pc_create_project,
     create_workflow_issue as pc_create_workflow_issue,
     get_agent_health as pc_get_agent_health,
+    get_recent_escalations as pc_get_recent_escalations,
     get_predecessor_context as pc_get_predecessor_context,
     get_agents_for_case as pc_get_agents_for_case,
     get_agents_for_company as pc_get_agents,
@@ -180,6 +181,7 @@ __all__ = [
     "pc_escalate_issue",
     # agent-run observability + control (live view + smart management)
     "pc_get_agent_health",
+    "pc_get_recent_escalations",
     "pc_get_predecessor_context",
     "pc_list_live_runs",
     "pc_get_run_log",

web/app.py

@@ -63,6 +63,7 @@ from web.agent_platform_port import (
     pc_create_workflow_issue,
     pc_escalate_issue,
     pc_get_agent_health,
+    pc_get_recent_escalations,
     pc_get_predecessor_context,
     pc_get_agents,
     pc_get_agents_for_case,
@@ -7593,6 +7594,15 @@ async def operations_agent_health():
     return await pc_get_agent_health()
 
 
+@app.get("/api/operations/agents/escalations")
+async def operations_agent_escalations(limit: int = 10, hours: int = 24):
+    """Recent chair escalations — watchdog + manual (#218/#222).
+
+    Read-only history of what was handed to the chair, for the ops health panel.
+    """
+    return await pc_get_recent_escalations(limit, hours)
+
+
 @app.get("/api/operations/issues/{issue_id}/predecessor")
 async def operations_issue_predecessor(issue_id: str, limit: int = 3):
     """Recent finished runs on an issue for session continuation (#220, "seance").

web/paperclip_client.py

@@ -9,6 +9,7 @@ from __future__ import annotations
 import json
 import logging
 import os
+import re
 import uuid
 
 import asyncpg
@@ -1132,6 +1133,57 @@ async def get_agent_health() -> dict:
     return {"ok": True, "items": items, "counts": counts}
 
 
+# The escalation note escalate_issue() writes as an author_type='system' comment.
+# One prefix + a [severity] tag — parsed back here for the ops panel (#218/#222 UI).
+_ESCALATION_BODY_PREFIX = "🚨 הסלמה"
+_ESCALATION_SEVERITY_RE = re.compile(r"\[(critical|high|medium)\]")
+
+
+async def get_recent_escalations(limit: int = 10, hours: int = 24) -> dict:
+    """Recent chair escalations (watchdog + manual), newest-first (#218/#222 UI).
+
+    Read-only. Reconstructs escalations from the ``author_type='system'`` notes
+    escalate_issue() leaves (``🚨 הסלמה [severity] לחיים\\n\\n<reason>``) — severity
+    parsed from the tag, reason from the body, identifier joined from the issue.
+    Scoped to the two legal-ai companies; ``limit`` clamped 1..50, ``hours`` 1..168.
+    """
+    limit = max(1, min(int(limit), 50))
+    hours = max(1, min(int(hours), 168))
+    company_ids = list(COMPANIES.values())
+    conn = await asyncpg.connect(PAPERCLIP_DB_URL)
+    try:
+        rows = await conn.fetch(
+            f"""SELECT ic.issue_id, ic.body, ic.created_at, i.identifier
+                  FROM issue_comments ic
+                  JOIN issues i ON i.id = ic.issue_id
+                 WHERE ic.author_type = 'system'
+                   AND ic.company_id = ANY($1::uuid[])
+                   AND ic.body LIKE $2
+                   AND ic.deleted_at IS NULL
+                   AND ic.created_at > now() - interval '{hours} hours'
+              ORDER BY ic.created_at DESC
+                 LIMIT $3""",
+            company_ids, f"{_ESCALATION_BODY_PREFIX}%", limit,
+        )
+    finally:
+        await conn.close()
+
+    items = []
+    for r in rows:
+        body = r["body"] or ""
+        m = _ESCALATION_SEVERITY_RE.search(body)
+        severity = m.group(1) if m else "medium"
+        reason = body.split("\n\n", 1)[1].strip() if "\n\n" in body else body
+        items.append({
+            "issue_id": str(r["issue_id"]),
+            "identifier": r["identifier"],
+            "severity": severity,
+            "reason": reason,
+            "created_at": r["created_at"].isoformat() if r["created_at"] else None,
+        })
+    return {"ok": True, "items": items}
+
+
 async def get_predecessor_context(issue_id: str, limit: int = 3) -> dict:
     """Recent finished runs on an issue, newest-first, for session continuation (#220).
 

web/tests/test_agent_health.py

@@ -143,3 +143,58 @@ def test_get_agent_health_empty(monkeypatch):
     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}}
+
+
+# ── recent escalations (fake DB) — parses severity + reason from system notes ──
+class _FetchConn:
+    def __init__(self, rows):
+        self._rows = rows
+
+    async def fetch(self, query, *args):
+        return self._rows
+
+    async def close(self):
+        pass
+
+
+def test_get_recent_escalations_parses_severity_and_reason(monkeypatch):
+    from datetime import datetime
+
+    rows = [
+        {
+            "issue_id": "iss-1",
+            "identifier": "CMP-141",
+            "body": "🚨 הסלמה [high] לחיים\n\nזוהתה לולאת-recovery — 4 יקיצות-שחזור; נמסר לחיים.",
+            "created_at": datetime(2026, 7, 7, 3, 30, 0),
+        },
+        {
+            "issue_id": "iss-2",
+            "identifier": "CMPA-112",
+            "body": "🚨 הסלמה [medium] לחיים\n\nזוהתה לולאת-recovery — 2 יקיצות.",
+            "created_at": datetime(2026, 7, 7, 2, 49, 0),
+        },
+    ]
+
+    async def _connect(_url):
+        return _FetchConn(rows)
+
+    monkeypatch.setattr(pc.asyncpg, "connect", _connect)
+    result = asyncio.run(pc.get_recent_escalations())
+    assert result["ok"] is True
+    a, b = result["items"]
+    assert a["identifier"] == "CMP-141" and a["severity"] == "high"
+    assert "4 יקיצות" in a["reason"] and "🚨" not in a["reason"]
+    assert a["created_at"] == "2026-07-07T03:30:00"
+    assert b["severity"] == "medium"
+
+
+def test_get_recent_escalations_defaults_severity_when_untagged(monkeypatch):
+    rows = [{"issue_id": "x", "identifier": "CMP-9", "body": "🚨 הסלמה לחיים", "created_at": None}]
+
+    async def _connect(_url):
+        return _FetchConn(rows)
+
+    monkeypatch.setattr(pc.asyncpg, "connect", _connect)
+    (item,) = asyncio.run(pc.get_recent_escalations())["items"]
+    assert item["severity"] == "medium"  # fallback
+    assert item["created_at"] is None