Add global Windows training agent queue

crypto_spot_bot/dashboard.py

@@ -4,7 +4,7 @@ import json
 from contextlib import asynccontextmanager
 from typing import Any
 
-from fastapi import FastAPI, Response
+from fastapi import FastAPI, HTTPException, Response
 from fastapi.responses import JSONResponse, PlainTextResponse
 
 from crypto_spot_bot.analytics import analytics_snapshot
@@ -19,6 +19,7 @@ from crypto_spot_bot.reconciliation import reconciliation_snapshot
 from crypto_spot_bot.storage import Storage
 from crypto_spot_bot.strategy import SpotStrategy
 from crypto_spot_bot.time_series import TimeSeriesForecaster
+from crypto_spot_bot.training_coordination import TrainingCoordinator
 
 
 WEB_UI_REMOVED_MESSAGE = "Web UI removed. Use the Android TradeBot AI app and /api/* endpoints."
@@ -42,6 +43,7 @@ def create_app(settings: Settings | None = None) -> FastAPI:
     learner = TradeLearner(settings, storage)
     forecaster = TimeSeriesForecaster(settings)
     bot = CryptoSpotBot(settings, storage, market, broker, strategy, pattern_analyzer, learner, forecaster)
+    training = TrainingCoordinator(settings.time_series_lstm_model_path.parent)
 
     @asynccontextmanager
     async def lifespan(_: FastAPI):
@@ -56,6 +58,7 @@ def create_app(settings: Settings | None = None) -> FastAPI:
     app.state.storage = storage
     app.state.bot = bot
     app.state.market = market
+    app.state.training = training
 
     @app.get("/", response_class=PlainTextResponse, status_code=410)
     async def index() -> str:
@@ -114,7 +117,39 @@ def create_app(settings: Settings | None = None) -> FastAPI:
 
     @app.get("/api/retrain")
     async def retrain() -> dict[str, Any]:
-        return _runtime_json(settings, "torch_retrain_guard.json")
+        data = _runtime_json(settings, "torch_retrain_guard.json")
+        data["coordination"] = training.status()
+        return data
+
+    @app.get("/api/training/status")
+    async def training_status() -> dict[str, Any]:
+        return training.status()
+
+    @app.post("/api/training/retrain")
+    async def training_retrain(payload: dict[str, Any] | None = None) -> dict[str, Any]:
+        return training.request_retrain(payload)
+
+    @app.post("/api/training/heartbeat")
+    async def training_heartbeat(payload: dict[str, Any] | None = None) -> dict[str, Any]:
+        return training.heartbeat(payload)
+
+    @app.post("/api/training/claim")
+    async def training_claim(payload: dict[str, Any] | None = None) -> dict[str, Any]:
+        return training.claim(payload)
+
+    @app.post("/api/training/jobs/{job_id}/artifacts/chunk")
+    async def training_artifact_chunk(job_id: str, payload: dict[str, Any]) -> dict[str, Any]:
+        try:
+            return training.save_artifact_chunk(job_id, payload)
+        except ValueError as exc:
+            raise HTTPException(status_code=400, detail=str(exc)) from exc
+
+    @app.post("/api/training/jobs/{job_id}/complete")
+    async def training_complete(job_id: str, payload: dict[str, Any] | None = None) -> dict[str, Any]:
+        try:
+            return training.complete(job_id, payload)
+        except ValueError as exc:
+            raise HTTPException(status_code=404, detail=str(exc)) from exc
 
     @app.get("/api/config")
     async def config() -> dict[str, Any]: