AI/ontology_platform/ont_platform/api/deps.py

"""FastAPI dependencies and app lifespan.

Owns the ToolBox singleton, the compiled LangGraph workflow, and the
recursion limit. Construction happens once at app startup; teardown is a
no-op because OntoCast tools don't currently expose a close hook.

Why a module-level holder instead of `app.state`:
    The /process route is async and may be entered concurrently. A simple
    dict on `app.state` works, but pulling the ToolBox through a typed
    dependency function makes the contract explicit and gives every route
    the same view of "what tools and what workflow are available right now".
"""

from __future__ import annotations

import asyncio
import logging
import sys
from dataclasses import dataclass
from pathlib import Path

# Make vendored OntoCast importable. (Same trick as platform/config.py.)
_REPO_ROOT = Path(__file__).resolve().parents[2]
_VENDORED_ONTOCAST = _REPO_ROOT / "vendored" / "ontocast"
if str(_VENDORED_ONTOCAST) not in sys.path:
    sys.path.insert(0, str(_VENDORED_ONTOCAST))

from langchain_core.runnables import RunnableConfig  # noqa: E402
from langgraph.graph.state import CompiledStateGraph  # noqa: E402

from ontocast.cli.serve import calculate_recursion_limit  # noqa: E402
from ontocast.config import ServerConfig  # noqa: E402
from ontocast.stategraph import create_agent_graph  # noqa: E402
from ontocast.toolbox import ToolBox  # noqa: E402

import importlib

platform_config = importlib.import_module("ont_platform.config")

logger = logging.getLogger(__name__)


@dataclass
class AppContext:
    """Immutable holder for objects that live as long as the FastAPI app."""

    settings: "platform_config.PlatformSettings"
    tools: ToolBox
    workflow: CompiledStateGraph
    server_config: ServerConfig
    recursion_limit: int


_context: AppContext | None = None


async def initialize_app_context(
    settings: "platform_config.PlatformSettings | None" = None,
    *,
    head_chunks: int | None = None,
) -> AppContext:
    """Build ToolBox + workflow once. Idempotent on repeat calls."""
    global _context
    if _context is not None:
        return _context

    settings = settings or platform_config.load_settings()
    ontocast_config = platform_config.build_ontocast_config(settings)

    # ToolBox.__init__ 내부에서 LLMTool.create()가 `asyncio.run()`을 호출한다.
    # FastAPI lifespan/테스트가 이미 async 컨텍스트면 이중 loop 충돌이 나므로,
    # 별도 스레드에서 sync 생성자를 실행한다.
    tools = await asyncio.to_thread(ToolBox, ontocast_config)
    # OntoCast's ToolBox.initialize is async; do it here so a request doesn't
    # have to pay the cost.
    await tools.initialize()

    workflow = create_agent_graph(tools)
    server_config = ontocast_config.server
    recursion_limit = calculate_recursion_limit(head_chunks, server_config)

    _context = AppContext(
        settings=settings,
        tools=tools,
        workflow=workflow,
        server_config=server_config,
        recursion_limit=recursion_limit,
    )
    logger.info(
        "App context initialized "
        f"(phase={int(settings.phase)}, backend={settings.storage_backend}, "
        f"working_dir={settings.working_directory})"
    )
    return _context


def get_app_context() -> AppContext:
    """FastAPI dependency. Raises clearly if the lifespan never ran."""
    if _context is None:
        raise RuntimeError(
            "AppContext not initialized — the app lifespan must run "
            "`initialize_app_context()` before serving requests."
        )
    return _context


def reset_app_context_for_testing() -> None:
    """Test-only: drop the cached context so each test can rebuild it."""
    global _context
    _context = None


__all__ = [
    "AppContext",
    "RunnableConfig",
    "get_app_context",
    "initialize_app_context",
    "reset_app_context_for_testing",
]