v0.21.0:0 - matrix-bridge bot tile (status, update, restart, logs)

image/app/server.py

@@ -3,7 +3,7 @@ import asyncio
 import json
 from pathlib import Path
 
-from fastapi import FastAPI, HTTPException
+from fastapi import FastAPI, HTTPException, Query, Request
 from fastapi.responses import FileResponse, JSONResponse, StreamingResponse
 from fastapi.staticfiles import StaticFiles
 from pydantic import BaseModel
@@ -21,6 +21,7 @@ from .embeddings_proxy import build_router as build_embeddings_router
 from .redaction_gateway import build_router as build_redaction_router, MapStore
 from .hardware import HardwareProbe
 from .health import check_kokoro, check_parakeet, check_vllm, check_embeddings, check_qdrant
+from .matrix_bridge import MatrixBridgeManager
 from .models import load_catalog
 from .nim import SUGGESTED_NIMS, CATALOG_URL, NimManager
 from .overrides import add_custom, delete_custom, extract_knobs_from_args, load_overrides, set_knobs
@@ -43,6 +44,7 @@ hardware_probe = HardwareProbe(settings)
 nim_manager = NimManager(settings)
 deep_health = DeepHealth(settings)
 speech_models = SpeechModelsManager(settings)
+matrix_bridge = MatrixBridgeManager(settings)
 
 app = FastAPI(title="spark-control", version="0.1.0")
 
@@ -474,6 +476,11 @@ async def get_services() -> dict:
             http = await check_embeddings(settings)
         elif name == "qdrant":
             http = await check_qdrant(settings)
+        elif svc.kind == "bot":
+            # No HTTP health endpoint (host networking, no port) — judged purely
+            # by docker state. http_ready stays None so the badge isn't pinned
+            # to a "Starting…" verdict that can never clear.
+            http = {"ok": None, "base_url": None}
         else:
             # Custom services expose a /health endpoint by convention.
             http = await check_kokoro(settings) if svc.kind == "tts" else {"ok": None, "base_url": svc.host and f"http://{svc.host}:{svc.port}"}
@@ -484,7 +491,9 @@ async def get_services() -> dict:
             "container": svc.container,
             "kind": svc.kind,
             "base_url": http.get("base_url"),
-            "http_ready": bool(http.get("ok")),
+            # None (not False) for services with no HTTP surface (the bot), so
+            # the UI judges them by docker state alone instead of "Starting…".
+            "http_ready": None if svc.kind == "bot" else bool(http.get("ok")),
             # Prefer the check fn's own top-level model key (embeddings reports
             # it there); fall back to a model field inside detail for services
             # whose /health embeds it (parakeet).
@@ -500,8 +509,11 @@ async def get_services() -> dict:
     results = await asyncio.gather(*[one(n) for n in services.keys()])
     for name, info in results:
         out[name] = info
-        # Feed http reachability into the connectivity log (transition-only)
-        record_state(name, bool(info.get("http_ready")))
+        # Feed http reachability into the connectivity log (transition-only).
+        # Skip services with no HTTP surface (http_ready is None) — they'd
+        # otherwise register as perpetually "down".
+        if info.get("http_ready") is not None:
+            record_state(name, bool(info.get("http_ready")))
     return out
 
 
@@ -606,7 +618,7 @@ async def stream_nim_install(job_id: str):
 @app.delete("/api/services/{name}")
 async def del_service(name: str) -> dict:
     # Only allow deleting custom services (not the bundled built-in keys)
-    if name in ("parakeet", "kokoro", "embeddings", "qdrant"):
+    if name in ("parakeet", "kokoro", "embeddings", "qdrant", "matrix-bridge"):
         raise HTTPException(400, "built-in service; cannot delete (use Configure Sparks to point at a different host)")
     delete_custom_service(name)
     return {"ok": True, "name": name}
@@ -625,6 +637,81 @@ async def service_action(name: str, action: str) -> dict:
     return {"name": name, "action": action, **result}
 
 
+# ---- matrix-bridge bot: update (git pull + rebuild) + logs ----
+# Status badge + start/stop/restart ride the generic /api/services machinery
+# above (the bot is a registered ServiceDef). Only the long-running Update and
+# the logs view need bespoke endpoints.
+
+def _serialize_mb_update(job) -> dict:
+    return {
+        "id": job.id,
+        "state": job.state,
+        "phase": job.phase,
+        "started_at": job.started_at,
+        "finished_at": job.finished_at,
+        "returncode": job.returncode,
+        "lines": job.lines,
+    }
+
+
+@app.post("/api/matrix-bridge/update")
+async def post_matrix_bridge_update() -> dict:
+    """Pull latest code, rebuild, and recreate the bot container. Long-running
+    (docker build) — returns a job id to stream."""
+    try:
+        job = await matrix_bridge.trigger_update()
+    except RuntimeError as e:
+        raise HTTPException(409 if "in progress" in str(e) else 503, str(e))
+    return {"job_id": job.id, "state": job.state}
+
+
+@app.get("/api/matrix-bridge/update/{job_id}")
+async def get_matrix_bridge_update(job_id: str) -> dict:
+    job = matrix_bridge.get(job_id)
+    if job is None:
+        raise HTTPException(404, "no such job")
+    return _serialize_mb_update(job)
+
+
+@app.get("/api/matrix-bridge/update/{job_id}/stream")
+async def stream_matrix_bridge_update(job_id: str, request: Request):
+    job = matrix_bridge.get(job_id)
+    if job is None:
+        raise HTTPException(404, "no such job")
+
+    async def gen():
+        sent = 0
+        last_phase = None
+        while True:
+            # An update can run for minutes; bail promptly if the client is gone
+            # rather than spinning the poll loop until the job's 25-min ceiling.
+            if await request.is_disconnected():
+                return
+            n = len(job.lines)
+            if n > sent:
+                for line in job.lines[sent:n]:
+                    yield f"data: {json.dumps({'line': line})}\n\n"
+                sent = n
+            if job.phase != last_phase:
+                yield f"event: phase\ndata: {json.dumps({'state': job.state, 'phase': job.phase})}\n\n"
+                last_phase = job.phase
+            if job.returncode is not None and sent >= len(job.lines):
+                yield f"event: done\ndata: {json.dumps({'state': job.state, 'returncode': job.returncode})}\n\n"
+                return
+            await asyncio.sleep(0.5)
+
+    return StreamingResponse(gen(), media_type="text/event-stream")
+
+
+@app.get("/api/matrix-bridge/logs")
+async def get_matrix_bridge_logs(tail: int = Query(100, ge=1, le=1000)) -> dict:
+    """Last N lines of `docker logs` for the bot container (stderr merged)."""
+    result = await matrix_bridge.fetch_logs(tail=tail)
+    if not result.get("ok"):
+        raise HTTPException(502, result.get("output") or result.get("error") or "could not read logs")
+    return result
+
+
 # ---- Speech model patch management ----
 
 @app.get("/api/speech-models")