P3.5-P3.7: 2-layer inventory, capability routing, STT/TTS adapters, Dev Contract

NCS:
- _collect_worker_caps() fetches capability flags from node-worker /caps
- _derive_capabilities() merges served model types + worker provider flags
- installed_artifacts replaces inventory_only (disk scan with DISK_SCAN_PATHS env)
- New endpoints: /capabilities/caps, /capabilities/installed

Node Worker:
- STT_PROVIDER, TTS_PROVIDER, OCR_PROVIDER, IMAGE_PROVIDER env flags
- /caps endpoint returns capabilities + providers for NCS aggregation
- STT adapter (providers/stt_mlx_whisper.py) — remote + local mode
- TTS adapter (providers/tts_mlx_kokoro.py) — remote + local mode
- OCR handler via vision_prompted (ollama_vision with OCR prompt)
- NATS subjects: node.{id}.stt/tts/ocr/image.request

Router:
- POST /v1/capability/{stt,tts,ocr,image} — capability-based offload routing
- GET /v1/capabilities — global view with capabilities_by_node
- require_fresh_caps(ttl) preflight guard
- find_nodes_with_capability(cap) + load-based node selection

Ops:
- ops/fabric_snapshot.py — full runtime snapshot collector
- ops/fabric_preflight.sh — quick check + snapshot save + diff
- docs/fabric_contract.md — Dev Contract v0.1 (preflight-first)
- tests/test_fabric_contract.py — CI enforcement (6 tests)

Made-with: Cursor
This commit is contained in:
Apple
2026-02-27 05:24:09 -08:00
parent 194c87f53c
commit 9a36020316
17 changed files with 1352 additions and 21 deletions

View File

@@ -41,6 +41,33 @@ async def prom_metrics():
return {"error": "prometheus_client not installed"}
@app.get("/caps")
async def caps():
"""Capability flags for NCS to aggregate."""
return {
"node_id": config.NODE_ID,
"capabilities": {
"llm": True,
"vision": True,
"stt": config.STT_PROVIDER != "none",
"tts": config.TTS_PROVIDER != "none",
"ocr": config.OCR_PROVIDER != "none",
"image": config.IMAGE_PROVIDER != "none",
},
"providers": {
"stt": config.STT_PROVIDER,
"tts": config.TTS_PROVIDER,
"ocr": config.OCR_PROVIDER,
"image": config.IMAGE_PROVIDER,
},
"defaults": {
"llm": config.DEFAULT_LLM,
"vision": config.DEFAULT_VISION,
},
"concurrency": config.MAX_CONCURRENCY,
}
@app.on_event("startup")
async def startup():
global _nats_client