v0.2.2 - spark-vllm-docker update checks + Apply Update

Backend:
- updates.py: get_update_status() runs git fetch + git rev-list --left-right --count HEAD...origin/main to learn ahead/behind/dirty, plus git log for pending commits
- UpdateManager class with asyncio.Lock; one update at a time
- POST /api/updates/apply triggers "git pull --ff-only && ./build-and-copy.sh -c" over SSH with streamed log + phase detection (Pulling / Building the vLLM container / Copying to peer Sparks)
- GET /api/updates returns {ok, behind, ahead, dirty, current, log[], branch}

Frontend:
- Persistent banner near footer: hidden when up-to-date, blue when N commits behind, warn (orange) when local dirty changes block update
- 'Show details' expands a list of pending commits
- 'Apply update' triggers the long-running build with phase + elapsed timer + collapsible logs
- Confirmation dialog explains the 5–40 min duration

Package: bump 0.2.2:0

image/app/server.py

@@ -16,12 +16,14 @@ from .models import load_catalog
 from .services import docker_state, run_action, services_from_settings
 from .ssh import ssh_run
 from .swap import SwapManager
+from .updates import UpdateManager, get_update_status
 
 
 settings = Settings.from_env()
 catalog = load_catalog(settings.models_yaml)
 swap_manager = SwapManager(settings, catalog)
 download_manager = DownloadManager(settings)
+update_manager = UpdateManager(settings)
 
 app = FastAPI(title="spark-control", version="0.1.0")
 
@@ -307,6 +309,69 @@ async def stream_download(job_id: str):
     return StreamingResponse(gen(), media_type="text/event-stream")
 
 
+@app.get("/api/updates")
+async def get_updates() -> dict:
+    return await get_update_status(settings)
+
+
+class UpdateRequest(BaseModel):
+    mode: Literal["solo", "cluster"] = "cluster"
+
+
+@app.post("/api/updates/apply")
+async def post_update_apply(req: UpdateRequest) -> dict:
+    if not settings.configured:
+        raise HTTPException(503, "spark1 not configured")
+    try:
+        job = await update_manager.trigger(req.mode)
+    except RuntimeError as e:
+        raise HTTPException(409, str(e))
+    return {"job_id": job.id, "mode": job.mode, "state": job.state}
+
+
+@app.get("/api/updates/{job_id}")
+async def get_update_job(job_id: str) -> dict:
+    job = update_manager.get(job_id)
+    if job is None:
+        raise HTTPException(404, "no such job")
+    return {
+        "id": job.id,
+        "mode": job.mode,
+        "state": job.state,
+        "phase": job.phase,
+        "started_at": job.started_at,
+        "finished_at": job.finished_at,
+        "returncode": job.returncode,
+        "lines": job.lines,
+    }
+
+
+@app.get("/api/updates/{job_id}/stream")
+async def stream_update(job_id: str):
+    job = update_manager.get(job_id)
+    if job is None:
+        raise HTTPException(404, "no such job")
+
+    async def gen():
+        sent = 0
+        last_phase = None
+        while True:
+            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.post("/api/test-connection")
 async def test_connection() -> dict:
     """Probe both Sparks with a `hostname` command. Useful for the StartOS setup flow."""