busya
1fd5e55db7
The Gradio agent (run.py) crashed with OSError when port 7860 was already occupied by a previous instance. Added _find_free_port() that scans up to 100 ports from the configured GRADIO_SERVER_PORT and picks the first available one, logging a warning on fallback. Contract updates: - AgentChat.Run: [C:3] [TYPE Module] (was C2/Function), added @RATIONALE, @REJECTED, @SIDE_EFFECT for port-finding logic - AgentChat.GradioApp: added @RATIONALE, @REJECTED - AgentChat.LangGraph.Setup: added @REJECTED, deduplicated @RELATION - AgentChat.Tools: added @RATIONALE
93 lines
3.8 KiB
Python
93 lines
3.8 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 (auto-fallback to next free port if busy).
|
||
# @SIDE_EFFECT Binds to a TCP port via Gradio launch.
|
||
# @RATIONALE _find_free_port() prevents port conflicts when a previous agent instance is still running
|
||
# without requiring manual cleanup or port-range environment variables.
|
||
# @REJECTED Failing hard on port-in-use was rejected — multiple restarts during development
|
||
# should not require manual port cleanup.
|
||
import os
|
||
import socket
|
||
import httpx
|
||
import logging
|
||
|
||
logger = logging.getLogger("cot")
|
||
|
||
FASTAPI_URL = os.getenv("FASTAPI_URL", "http://localhost:8000")
|
||
|
||
|
||
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 = os.getenv("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.info("LLM config fetched from FastAPI: %s (%s)", config.get("provider_type"), config.get("default_model"))
|
||
return config
|
||
logger.warning("FastAPI returned no active LLM provider: %s", config.get("reason"))
|
||
except Exception as e:
|
||
if attempt < 5:
|
||
logger.info("Waiting for FastAPI (attempt %d/6): %s", attempt + 1, e)
|
||
time.sleep(5)
|
||
else:
|
||
logger.warning("Failed to fetch LLM config from FastAPI after 6 attempts: %s", e)
|
||
logger.info("Falling back to env vars for LLM config")
|
||
return None
|
||
|
||
|
||
if __name__ == "__main__":
|
||
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
|
||
|
||
# Propagate SERVICE_JWT to ContextVar for tool calls
|
||
service_token = os.getenv("SERVICE_JWT", "")
|
||
if service_token:
|
||
set_service_jwt(service_token)
|
||
|
||
# Fetch LLM config from FastAPI at startup
|
||
llm_config = _fetch_llm_config()
|
||
if llm_config:
|
||
configure_from_api(llm_config)
|
||
|
||
# Find a free port — fallback if the configured port is already in use
|
||
configured_port = int(os.getenv("GRADIO_SERVER_PORT", "7860"))
|
||
try:
|
||
port = _find_free_port(configured_port)
|
||
if port != configured_port:
|
||
logger.warning("Port %d is in use, falling back to port %d", configured_port, port)
|
||
except OSError as e:
|
||
logger.error("Failed to find a free port: %s", e)
|
||
raise
|
||
|
||
demo = create_chat_interface()
|
||
demo.launch(
|
||
server_name=os.getenv("GRADIO_SERVER_NAME", "0.0.0.0"),
|
||
server_port=port,
|
||
)
|
||
# #endregion AgentChat.Run |