feat: add Docker health-state HTTP endpoint for Swarm Health Watchdog

- Python HTTP server on 0.0.0.0:18809
- GET /health -> all monitored containers (JSON)
- GET /health/<name> -> single container
- Monitors: brave-search, kokoro-tts, litellm, litellm-db, n8n-agent, searxng, whisper-server
- Returns status, health, restart count via docker inspect
- systemd user service for auto-start

Task: t_461f71fe
This commit is contained in:
William Valentin
2026-05-13 14:29:25 -07:00
parent aea9042cce
commit 9fdd29f7b7
1272 changed files with 863206 additions and 16973 deletions
@@ -0,0 +1,42 @@
{
"version": 1,
"lastGood": {
"litellm": "litellm:default",
"openai-codex": "openai-codex:william.valentin.info@gmail.com",
"anthropic": "anthropic:manual",
"github-copilot": "github-copilot:github",
"zai": "zai:default"
},
"usageStats": {
"litellm:default": {
"lastUsed": 1774981524176,
"errorCount": 0,
"lastFailureAt": 1774054888659
},
"github-copilot:github": {
"errorCount": 0,
"lastUsed": 1774539324287
},
"anthropic:manual": {
"errorCount": 0,
"lastUsed": 1773951080133
},
"openai-codex:default": {
"lastUsed": 1776297614983,
"errorCount": 0
},
"anthropic:default": {
"errorCount": 0,
"lastFailureAt": 1774583413860
},
"zai:default": {
"errorCount": 0,
"lastUsed": 1774977296466,
"lastFailureAt": 1774982308436
},
"openai-codex:william.valentin.info@gmail.com": {
"errorCount": 0,
"lastUsed": 1776303019964
}
}
}