CIAgent
b6850fc036
Task 2-2-01: sandbox-agent.py stdlib-only (D-031) — shell capture (command/file_diff/
run_result/test_result/stdin/stdout), per-task monotonic seq, JSONL fsync spool (at-least-once,
D-026), raw-socket RFC6455 client (no websockets in-namespace), exponential-backoff reconnect,
SIGKILL-safe. Loopback tests: ordered emission, spool-on-disconnect, reconnect flush order,
stdlib-only AST scan.
Task 2-2-02: WS /v1/telemetry/ingest (D-026) — query-param identity (extra=forbid frames),
server-side dedup on (learner,task,seq), gap detection + warnings, ping keepalive. G-3 flood
control: overflow or >50000 events/task -> 1008 close + trace marked INCOMPLETE_FLOODED
(terminal, Proctor signal); no silent drop. GET traces + gaps endpoints. TraceIntegrityMap
(process-local, D-019 precedent) exposes is_incomplete for the Phase 3 grader gate (G-4).
214/214 + ruff clean.
---ci---
phase: 2
milestone: v0.3
status: execute
requirements: {covered: [REQ-3-003], partial: []}
---/ci---
126 lines
4.8 KiB
Python
126 lines
4.8 KiB
Python
"""FastAPI app factory — lifespan, CORS, health, routers."""
|
|
|
|
import asyncio
|
|
import contextlib
|
|
import logging
|
|
from contextlib import asynccontextmanager
|
|
|
|
import httpx
|
|
from fastapi import FastAPI
|
|
from fastapi.middleware.cors import CORSMiddleware
|
|
|
|
from .agents.registry import AgentRegistry, register_builtin_agents
|
|
from .agents.session import InMemorySessionStore
|
|
from .api import (
|
|
assessment_router,
|
|
chat_router,
|
|
lab_router,
|
|
mentor_router,
|
|
proctor_router,
|
|
sandboxes_router,
|
|
telemetry_router,
|
|
)
|
|
from .config import Settings
|
|
from .llm import create_provider
|
|
from .sandbox import SandboxManager, UnshareBackend
|
|
from .telemetry.ingest import TraceIntegrityMap
|
|
from .telemetry.store import SQLiteTraceStore
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
#: Interval between wall-clock/G-2 reaper passes (the manager owns the pass;
|
|
#: the lifespan owns the loop). 60s against a 900s default timeout → ≤6.7% lag.
|
|
REAPER_INTERVAL_S = 60.0
|
|
|
|
|
|
def create_app(settings: Settings | None = None) -> FastAPI:
|
|
settings = settings or Settings()
|
|
|
|
@asynccontextmanager
|
|
async def lifespan(app: FastAPI):
|
|
# Shared HTTP client pool (D-017): 10s connect / 300s read for cloud TTFT
|
|
timeout = httpx.Timeout(connect=10.0, read=300.0, write=30.0, pool=10.0)
|
|
app.state.http_client = httpx.AsyncClient(timeout=timeout)
|
|
app.state.settings = settings
|
|
app.state.provider = create_provider(settings, app.state.http_client)
|
|
app.state.session_store = InMemorySessionStore()
|
|
app.state.agent_registry = AgentRegistry()
|
|
register_builtin_agents(app.state.agent_registry)
|
|
|
|
# v0.3 sandbox fabric (REQ-3-001): singleton manager, DI'd via
|
|
# app.state. Tests may pre-set app.state.sandbox_manager (dependency
|
|
# override by state injection) to swap the backend; the lifespan then
|
|
# adopts it instead of constructing the real UnshareBackend one.
|
|
manager = getattr(app.state, "sandbox_manager", None)
|
|
if manager is None:
|
|
manager = SandboxManager(backend=UnshareBackend(), settings=settings)
|
|
app.state.sandbox_manager = manager
|
|
await manager.start() # a-1: reap on-disk orphans from a previous process
|
|
|
|
# Telemetry persistence (REQ-3-003, D-027): TraceStore wired through
|
|
# app.state. Tests may pre-set app.state.trace_store (state-injection
|
|
# override, same pattern as sandbox_manager) — the lifespan adopts it.
|
|
trace_store = getattr(app.state, "trace_store", None)
|
|
if trace_store is None:
|
|
settings.db_path.parent.mkdir(parents=True, exist_ok=True)
|
|
trace_store = SQLiteTraceStore(db_path=settings.db_path)
|
|
app.state.trace_store = trace_store
|
|
# Trace-integrity flags (G-3 INCOMPLETE_FLOODED): process-local map is
|
|
# intentional (D-019 registry precedent); the lifespan owns it so the
|
|
# grader and the ingest endpoint share one instance.
|
|
if getattr(app.state, "trace_integrity", None) is None:
|
|
app.state.trace_integrity = TraceIntegrityMap()
|
|
|
|
async def _reaper_loop() -> None:
|
|
# Wall-clock timeout + G-2 workdir-size sweep, one pass per tick.
|
|
while True:
|
|
await asyncio.sleep(REAPER_INTERVAL_S)
|
|
try:
|
|
await manager.reap_expired()
|
|
except Exception:
|
|
logger.exception("sandbox reaper pass failed; retrying next tick")
|
|
|
|
reaper = asyncio.create_task(_reaper_loop())
|
|
try:
|
|
yield
|
|
finally:
|
|
reaper.cancel()
|
|
with contextlib.suppress(asyncio.CancelledError):
|
|
await reaper
|
|
# No orphans outlive the process (a-1, shutdown half): destroy
|
|
# everything live; workdirs stay on disk for snapshot restore.
|
|
await manager.destroy_all()
|
|
trace_store.close()
|
|
await app.state.http_client.aclose()
|
|
|
|
app = FastAPI(title="Nextcraft AI Service", version="0.3.0", lifespan=lifespan)
|
|
|
|
# A-008: localhost-only CORS, no credentials
|
|
app.add_middleware(
|
|
CORSMiddleware,
|
|
allow_origins=["http://localhost:3000", "http://127.0.0.1:3000"],
|
|
allow_methods=["GET", "POST", "DELETE", "OPTIONS"],
|
|
allow_headers=["Content-Type"],
|
|
allow_credentials=False,
|
|
)
|
|
|
|
@app.get("/health")
|
|
async def health() -> dict:
|
|
return {
|
|
"status": "ok",
|
|
"provider": settings.provider,
|
|
"model": settings.model,
|
|
}
|
|
|
|
app.include_router(chat_router)
|
|
app.include_router(lab_router)
|
|
app.include_router(assessment_router)
|
|
app.include_router(mentor_router)
|
|
app.include_router(proctor_router)
|
|
app.include_router(sandboxes_router)
|
|
app.include_router(telemetry_router)
|
|
return app
|
|
|
|
|
|
app = create_app()
|