Files
nextcraft/apps/ai-service/ai_service/main.py
T
CIAgent 135ea21a61 merge: hotfix/fresh-box-experience → main (v0.3.5 fresh-box experience)
Fixes the v0.3.4 fresh-box failures: silent CLI under bare-word PATH
invocation (SEA argv detection), bootstrap dying on venv creation without an
actionable hint (poisoned-partial-venv recovery + apt hint + doctor
venv-capability probe + preflight), installer falsely 'verifying' a silent
binary, and localhost-only server binding (network mode: 0.0.0.0 + wildcard
CORS + hostname-derived API URL — remote browsing zero-config).

38 CLI tests, 3 web tests, 409 ai-service tests green; build/typecheck/lint
clean.

---ci---
phase: hotfix
milestone: v0.4
status: complete
type: hotfix
requirements:
  covered: [REQ-4-001, REQ-4-002, REQ-4-003, REQ-4-004, REQ-4-005]
  partial: []
---/ci---
2026-09-13 00:05:37 +00:00

210 lines
9.4 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,
defense_router,
lab_router,
mentor_router,
proctor_router,
sandboxes_router,
telemetry_router,
variants_router,
)
from .config import Settings
from .grading.engine import GradingEngine
from .grading.store import SQLiteGradeStore
from .llm import create_provider
from .sandbox import SandboxManager, UnshareBackend
from .telemetry.ingest import TraceIntegrityMap
from .telemetry.store import SQLiteTraceStore
from .variants.generator import VariantGenerator
from .variants.store import SQLiteVariantStore
from .voice.defense_store import SQLiteDefenseStore
from .voice.factory import voice_provider_from_settings
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
# State-injection override (same pattern as the stores): tests may
# pre-set app.state.provider with a scripted mock; only construct the
# configured provider when none is present.
if getattr(app.state, "provider", None) is None:
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()
# Variant generation (REQ-3-005): VariantStore from the same
# SQLite file as traces/grades (D-027), one VariantGenerator singleton
# wired through app.state — the generator receives store + provider
# via constructor DI and knows nothing of FastAPI (api/ composes it,
# same pattern as GradingEngine). Tests may pre-set
# app.state.variant_store / app.state.variant_generator (the same
# state-injection override); the lifespan adopts a pre-set store but
# NEVER rebuilds a pre-set generator (its provider binding is part
# of the test fixture).
# ORDER NOTE: built BEFORE the grading engine — the engine takes the
# variant store (Phase 4 MH#4: variant anchors ship to the grader
# prompt; variant_seed stamped on graded records).
variant_store = getattr(app.state, "variant_store", None)
if variant_store is None:
settings.db_path.parent.mkdir(parents=True, exist_ok=True)
variant_store = SQLiteVariantStore(db_path=settings.db_path)
app.state.variant_store = variant_store
if getattr(app.state, "variant_generator", None) is None:
app.state.variant_generator = VariantGenerator(
variant_store,
app.state.provider,
model=settings.model,
)
# Oral defense (REQ-3-006): DefenseStore (same SQLite file) + the
# mock-first voice provider (D-030) + the seventh Examiner agent.
# Tests may pre-set app.state.defense_store / voice_provider /
# examiner_agent (state-injection override; never rebuilt if pre-set).
defense_store = getattr(app.state, "defense_store", None)
if defense_store is None:
defense_store = SQLiteDefenseStore(db_path=settings.db_path)
app.state.defense_store = defense_store
if getattr(app.state, "voice_provider", None) is None:
app.state.voice_provider = voice_provider_from_settings(settings)
if getattr(app.state, "examiner_agent", None) is None:
from .agents.examiner import ExaminerAgent
app.state.examiner_agent = ExaminerAgent(app.state.provider, settings)
# Grading persistence + engine (REQ-3-004): GradeStore from the same
# SQLite file as traces (D-027), one GradingEngine singleton wired
# through app.state — the engine receives its stores via constructor
# DI and knows nothing of FastAPI (api/ owns composition). Tests may
# pre-set app.state.grade_store / app.state.grading_engine (the same
# state-injection override as sandbox_manager/trace_store) to swap
# either; the lifespan adopts a pre-set store but NEVER rebuilds a
# pre-set engine (its provider binding is part of the test fixture).
grade_store = getattr(app.state, "grade_store", None)
if grade_store is None:
grade_store = SQLiteGradeStore(db_path=settings.db_path)
app.state.grade_store = grade_store
if getattr(app.state, "grading_engine", None) is None:
app.state.grading_engine = GradingEngine(
trace_store,
grade_store,
app.state.trace_integrity,
app.state.provider,
model=settings.model,
variant_store=variant_store, # MH#4: anchors + seed (D-029)
)
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()
grade_store.close()
variant_store.close()
defense_store.close()
await app.state.http_client.aclose()
app = FastAPI(title="Nextcraft AI Service", version="0.3.0", lifespan=lifespan)
# A-008 + D-038: no-credentials CORS. Default '*' admits remote-browser
# origins in network mode (safe only because allow_credentials stays
# False — never enable credentials with a wildcard). AI_CORS_ORIGINS
# restricts to an explicit list. PUT is CONTRACT, not trivia: the learner
# build surface writes workspace files with PUT (engine-client writeFile)
# — v0.3 initially shipped without it and every cross-origin Save failed
# preflight (caught in P7 review; tests/api/test_cors.py pins the policy).
app.add_middleware(
CORSMiddleware,
allow_origins=settings.cors_origin_list,
allow_methods=["GET", "POST", "PUT", "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)
app.include_router(variants_router)
app.include_router(defense_router)
return app
app = create_app()