feat: sysops_agent — Docker/git self-management with auto-heal

Adds a new specialist agent that gives the AI system control over its
own infrastructure:

- sysops_tools.py: docker SDK (ps/logs/restart) + git CLI (pull/status/log)
  + Odoo channel notifier for autonomous action broadcasts
- sysops_agent.py: BaseAgent subclass handling on-demand chat requests,
  auto_heal() triggered by health failures, and sweep() for audits
- Background auto-heal loop (main.py): runs every 2 minutes, calls
  _get_failing_systems() and triggers auto_heal() when degraded
- health.py: extracted _get_failing_systems() helper reused by both
  the /health/detailed endpoint and the auto-heal loop
- docker-compose.yml: mount docker socket + /root/odoo workspace +
  SSH keys for git authentication
- Dockerfile: add git to apt-get
- requirements.txt: add docker==7.1.0 Python SDK

Auto-heal behavior:
  - Detects failing containers, restarts them, notifies all bot DM channels
  - Ollama (192.168.2.9) is flagged as external and skipped
  - On-demand via chat: "restart agent", "check logs", "pull latest code"

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

agent_service/routers/health.py

@@ -32,6 +32,41 @@ async def health():
     return HealthResponse(status='ok', uptime_seconds=round(time.time() - _start_time, 1))
 
 
+async def _get_failing_systems() -> list[str]:
+    """Return a list of system names that are not reporting 'ok'."""
+    from ..app_state import get_db_pool, get_master_agent, get_llm_router
+    failing = []
+
+    pool = get_db_pool()
+    if not pool:
+        failing.append('db')
+    else:
+        try:
+            async with pool.acquire(timeout=5) as conn:
+                await conn.fetchval('SELECT 1')
+        except Exception:
+            failing.append('db')
+
+    master = get_master_agent()
+    if master is None:
+        failing.append('master_agent')
+    else:
+        if hasattr(master, '_odoo'):
+            try:
+                await asyncio.wait_for(master._odoo.ping(), timeout=5)
+            except Exception:
+                failing.append('odoo')
+
+    llm_router = get_llm_router()
+    if llm_router and hasattr(llm_router, '_ollama'):
+        try:
+            await asyncio.wait_for(llm_router._ollama.ping(), timeout=5)
+        except Exception:
+            failing.append('ollama')
+
+    return failing
+
+
 @router.get('/detailed', response_model=DetailedHealthResponse)
 async def health_detailed():
     from ..app_state import get_db_pool, get_master_agent, get_llm_router