managarten/services
Till JS 8a49e3ffd5 feat(mana-llm): M4 — observability, debug endpoints, SIGHUP reload
- `X-Mana-LLM-Resolved: <provider>/<model>` header on non-streaming
  responses. Streaming clients read the same info from each chunk's
  `model` field (SSE headers go out before the chain is walked).
- Three new Prometheus metrics: `mana_llm_alias_resolved_total{alias,
  target}` (which concrete model an alias resolved to per request),
  `mana_llm_fallback_total{from_model, to_model, reason}` (each
  fallback transition), `mana_llm_provider_healthy{provider}` (gauge,
  mirrors the circuit-breaker).
- New debug endpoints: `GET /v1/aliases` (registry inspection — chain
  + description per alias, useful for confirming SIGHUP reloads),
  `GET /v1/health` (full per-provider liveness snapshot — failure
  counter, last error, unhealthy-until backoff).
- `kill -HUP <pid>` reloads `aliases.yaml`. Parse errors leave the
  previous good state in memory and log the rejection.
- `ProviderHealthCache.add_listener()` for cache→metrics decoupling:
  the gauge is updated via a transition-only listener wired in main.py
  rather than the cache importing prometheus_client itself.
- Request-side metrics now use the requested model string, success-side
  uses the resolved one. So `mana_llm_llm_requests_total{provider="ollama",
  model="gemma3:12b"}` reflects actual upstream load even when callers
  used `mana/long-form` aliases.

16 new observability tests (test_m4_observability.py): listener
fire-on-transition semantics, exception-isolation, multi-listener,
counter increments, gauge writes, end-to-end alias→metric flow,
v1/aliases + v1/health endpoint shape, response.model carries the
resolved target after fallback. Total suite: 115/115 in 1.6s.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-26 20:52:28 +02:00
..
mana-ai feat(shared-ai): route compactor to Haiku-tier model by default (M2.5) 2026-04-23 18:26:50 +02:00
mana-analytics refactor(shared-tailwind): rewrite themes.css to single-layer shadcn convention 2026-04-09 01:13:06 +02:00
mana-api-gateway chore: complete ManaCore → Mana rename (docs, go modules, plists, images) 2026-04-07 12:26:10 +02:00
mana-auth feat(auth): error-classification layer + passkey end-to-end 2026-04-24 01:52:51 +02:00
mana-crawler fix(mana-crawler): default DATABASE_URL to mana_platform in dev 2026-04-15 18:18:19 +02:00
mana-credits feat(credits): add 2-phase debit (reserve/commit/refund) 2026-04-17 14:41:41 +02:00
mana-events fix(events): Eventbrite provider — switch from dead API to web scraping 2026-04-18 16:51:58 +02:00
mana-geocoding test(geocoding): add unit tests + end-to-end smoke test script 2026-04-11 20:21:18 +02:00
mana-image-gen feat(mana-image-gen): replace Mac flux2.c implementation with Windows GPU diffusers 2026-04-08 13:02:42 +02:00
mana-landing-builder fix(tsconfig): unblock shared-types consumers 2026-04-21 18:53:55 +02:00
mana-llm feat(mana-llm): M4 — observability, debug endpoints, SIGHUP reload 2026-04-26 20:52:28 +02:00
mana-mail fix(broadcast): track route paths + shared-branding tsconfig 2026-04-21 18:30:47 +02:00
mana-mcp docs(mana-mcp,mana-ai): CLAUDE.md coverage for M1 agent-loop primitives 2026-04-23 14:25:14 +02:00
mana-media fix(mana-media): HEIC uploads from Chrome — sniff + transcode at the edge 2026-04-25 13:46:13 +02:00
mana-notify fix(mana-auth) + chore: rewrite /api/v1/auth/login JWT mint, remove Matrix stack 2026-04-08 16:32:13 +02:00
mana-persona-runner fix(personas): exact tool_use_id pairing + CI drift audit 2026-04-23 15:34:52 +02:00
mana-research test(mana-research): fixture-based tests for Gemini poll-response parser 2026-04-22 18:44:21 +02:00
mana-search chore(docker): drop obsolete services/mana-search/docker-compose.dev.yml 2026-04-23 15:27:19 +02:00
mana-stt chore(mac-mini): remove all AI service infrastructure (moved to Windows GPU) 2026-04-08 13:06:40 +02:00
mana-subscriptions chore(db): enforce pgSchema isolation with a lint script 2026-04-20 14:45:59 +02:00
mana-sync feat(backup): client-driven v2 snapshot export, drop server-side backup 2026-04-22 18:46:29 +02:00
mana-tts feat(profile): voice interview with pre-rendered TTS audio + Orpheus/Zonos backends 2026-04-17 15:22:52 +02:00
mana-user refactor(shared-tailwind): rewrite themes.css to single-layer shadcn convention 2026-04-09 01:13:06 +02:00
mana-video-gen chore(matrix): final scrub of stale matrix references 2026-04-08 16:47:54 +02:00
mana-voice-bot fix(mana-voice-bot): move default port 3050 → 3024 + Windows GPU deployment notes 2026-04-08 13:14:57 +02:00
news-ingester refactor(shared-rss): extract RSS parsing + Readability into one package 2026-04-15 22:30:44 +02:00