133 lines
5.1 KiB
Python
133 lines
5.1 KiB
Python
# backend/src/agent/run.py
|
||
# #region AgentChat.Run [C:3] [TYPE Module] [SEMANTICS agent-chat,entrypoint,startup]
|
||
# @ingroup AgentChat
|
||
# @BRIEF Entrypoint for Gradio agent backend. Fetches LLM config from FastAPI on startup.
|
||
# @PRE FastAPI backend reachable at FASTAPI_URL. Service JWT available for auth.
|
||
# @POST Gradio agent running on configured port.
|
||
# @SIDE_EFFECT Binds to a TCP port via Gradio launch.
|
||
# @RATIONALE Gradio port must match the frontend proxy target. Optional fallback is available only
|
||
# when GRADIO_ALLOW_PORT_FALLBACK=true and an external proxy is updated separately.
|
||
# @REJECTED Hardcoding the port was rejected — it must be configurable for different deployment environments.
|
||
import socket
|
||
|
||
import httpx
|
||
|
||
from src.agent._config import FASTAPI_URL, GRADIO_ALLOW_PORT_FALLBACK, GRADIO_SERVER_NAME, GRADIO_SERVER_PORT, SERVICE_JWT
|
||
from src.core.cot_logger import seed_trace_id
|
||
from src.core.logger import logger
|
||
|
||
|
||
def _find_free_port(start_port: int, max_attempts: int = 100) -> int:
|
||
"""Find a free TCP port starting from start_port, scanning up to max_attempts ports."""
|
||
for port in range(start_port, start_port + max_attempts):
|
||
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
|
||
try:
|
||
s.bind(("", port))
|
||
return port
|
||
except OSError:
|
||
continue
|
||
raise OSError(f"No free port found in range {start_port}-{start_port + max_attempts - 1}")
|
||
|
||
|
||
def _fetch_llm_config() -> dict | None:
|
||
"""Fetch active LLM provider config from FastAPI with retry.
|
||
|
||
Retries up to 30s (6 × 5s) to wait for FastAPI to be ready.
|
||
Falls back to env vars if FastAPI is unreachable or returns no active provider.
|
||
"""
|
||
import time
|
||
service_token = SERVICE_JWT
|
||
headers = {"Authorization": f"Bearer {service_token}"} if service_token else {}
|
||
|
||
for attempt in range(6):
|
||
try:
|
||
resp = httpx.get(f"{FASTAPI_URL}/api/agent/llm-config", headers=headers, timeout=5)
|
||
resp.raise_for_status()
|
||
config = resp.json()
|
||
if config.get("configured"):
|
||
logger.reason(
|
||
"LLM config fetched from FastAPI",
|
||
payload={"provider_type": config.get("provider_type"), "model": config.get("default_model")},
|
||
extra={"src": "AgentChat.Run.FetchLlmConfig"},
|
||
)
|
||
return config
|
||
logger.explore(
|
||
"FastAPI returned no active LLM provider",
|
||
payload={"reason": config.get("reason")},
|
||
error="No configured LLM provider",
|
||
extra={"src": "AgentChat.Run.FetchLlmConfig"},
|
||
)
|
||
except Exception as e:
|
||
if attempt < 5:
|
||
logger.reason(
|
||
f"Waiting for FastAPI (attempt {attempt + 1}/6)",
|
||
payload={"error": str(e)},
|
||
extra={"src": "AgentChat.Run.FetchLlmConfig"},
|
||
)
|
||
time.sleep(5)
|
||
else:
|
||
logger.explore(
|
||
"Failed to fetch LLM config after 6 attempts",
|
||
error=str(e),
|
||
extra={"src": "AgentChat.Run.FetchLlmConfig"},
|
||
)
|
||
logger.explore(
|
||
"Falling back to env vars for LLM config",
|
||
error="FastAPI unreachable",
|
||
extra={"src": "AgentChat.Run.FetchLlmConfig"},
|
||
)
|
||
return None
|
||
|
||
|
||
if __name__ == "__main__":
|
||
import asyncio
|
||
|
||
from src.agent.app import create_chat_interface
|
||
from src.agent.context import set_service_jwt
|
||
from src.agent.langgraph_setup import configure_from_api, init_checkpointer
|
||
|
||
seed_trace_id() # Seed trace for agent startup lifecycle
|
||
|
||
# Propagate SERVICE_JWT to ContextVar for tool calls
|
||
if SERVICE_JWT:
|
||
set_service_jwt(SERVICE_JWT)
|
||
|
||
# Fetch LLM config from FastAPI at startup
|
||
llm_config = _fetch_llm_config()
|
||
if llm_config:
|
||
configure_from_api(llm_config)
|
||
|
||
# Initialize PostgreSQL checkpointer (FR-004/FR-012/FR-027)
|
||
asyncio.run(init_checkpointer())
|
||
|
||
# Bind the configured port. Falling back silently breaks the Vite/nginx proxy target.
|
||
configured_port = GRADIO_SERVER_PORT
|
||
allow_port_fallback = GRADIO_ALLOW_PORT_FALLBACK
|
||
if allow_port_fallback:
|
||
try:
|
||
port = _find_free_port(configured_port)
|
||
if port != configured_port:
|
||
logger.explore(
|
||
"Port in use, falling back",
|
||
payload={"configured_port": configured_port, "actual_port": port},
|
||
error=f"Port {configured_port} is in use",
|
||
extra={"src": "AgentChat.Run.PortBinding"},
|
||
)
|
||
except OSError as e:
|
||
logger.explore(
|
||
"Failed to find a free port",
|
||
error=str(e),
|
||
extra={"src": "AgentChat.Run.PortBinding"},
|
||
)
|
||
raise
|
||
else:
|
||
port = configured_port
|
||
|
||
demo = create_chat_interface()
|
||
|
||
demo.launch(
|
||
server_name=GRADIO_SERVER_NAME,
|
||
server_port=port,
|
||
)
|
||
# #endregion AgentChat.Run
|