feat(fabric): decommission Swapper from critical path, NCS = source of truth

- Node Worker: replace swapper_vision with ollama_vision (direct Ollama API)
- Node Worker: add NATS subjects for stt/tts/image (stubs ready)
- Node Worker: remove SWAPPER_URL dependency from config
- Router: vision calls go directly to Ollama /api/generate with images
- Router: local LLM calls go directly to Ollama /api/generate
- Router: add OLLAMA_URL and PREFER_NODE_WORKER=true feature flag
- Router: /v1/models now uses NCS global capabilities pool
- NCS: SWAPPER_URL="" -> skip Swapper probing (status=disabled)
- Swapper configs: remove all hardcoded model lists, keep only runtime
  URLs, timeouts, limits
- docker-compose.node1.yml: add OLLAMA_URL, PREFER_NODE_WORKER for router;
  SWAPPER_URL= for NCS; remove swapper-service from node-worker depends_on
- docker-compose.node2-sofiia.yml: same changes for NODA2

Swapper service still runs but is NOT in the critical inference path.
Source of truth for models is now NCS -> Ollama /api/tags.

Made-with: Cursor

services/node-worker/worker.py

@@ -9,7 +9,7 @@ from typing import Any, Dict
 import config
 from models import JobRequest, JobResponse, JobError
 from idempotency import IdempotencyStore
-from providers import ollama, swapper_vision
+from providers import ollama, ollama_vision
 import fabric_metrics as fm
 
 logger = logging.getLogger("node-worker")
@@ -27,9 +27,13 @@ async def start(nats_client):
     global _nats_client
     _nats_client = nats_client
 
+    nid = config.NODE_ID.lower()
     subjects = [
-        f"node.{config.NODE_ID.lower()}.llm.request",
-        f"node.{config.NODE_ID.lower()}.vision.request",
+        f"node.{nid}.llm.request",
+        f"node.{nid}.vision.request",
+        f"node.{nid}.stt.request",
+        f"node.{nid}.tts.request",
+        f"node.{nid}.image.request",
     ]
     for subj in subjects:
         await nats_client.subscribe(subj, cb=_handle_request)
@@ -160,7 +164,7 @@ async def _execute(job: JobRequest, remaining_ms: int) -> JobResponse:
             )
         elif job.required_type == "vision":
             result = await asyncio.wait_for(
-                swapper_vision.infer(
+                ollama_vision.infer(
                     images=payload.get("images"),
                     prompt=payload.get("prompt", ""),
                     model=model,
@@ -171,11 +175,20 @@ async def _execute(job: JobRequest, remaining_ms: int) -> JobResponse:
                 ),
                 timeout=timeout_s,
             )
+        elif job.required_type in ("stt", "tts", "image"):
+            return JobResponse(
+                job_id=job.job_id, trace_id=job.trace_id, node_id=config.NODE_ID,
+                status="error",
+                error=JobError(
+                    code="NOT_YET_IMPLEMENTED",
+                    message=f"{job.required_type} adapter coming soon; use direct runtime API for now",
+                ),
+            )
         else:
             return JobResponse(
                 job_id=job.job_id, trace_id=job.trace_id, node_id=config.NODE_ID,
                 status="error",
-                error=JobError(code="UNSUPPORTED_TYPE", message=f"{job.required_type} not implemented"),
+                error=JobError(code="UNSUPPORTED_TYPE", message=f"{job.required_type} not supported"),
             )
 
         logger.info(