8a37710313
Implements webhook support for the crawl job API to eliminate polling requirements. Changes: - Added WebhookConfig and WebhookPayload schemas to schemas.py - Created webhook.py with WebhookDeliveryService class - Integrated webhook notifications in api.py handle_crawl_job - Updated job.py CrawlJobPayload to accept webhook_config - Added webhook configuration section to config.yml - Included comprehensive usage examples in WEBHOOK_EXAMPLES.md Features: - Webhook notifications on job completion (success/failure) - Configurable data inclusion in webhook payload - Custom webhook headers support - Global default webhook URL configuration - Exponential backoff retry logic (5 attempts: 1s, 2s, 4s, 8s, 16s) - 30-second timeout per webhook call Usage: POST /crawl/job with optional webhook_config: - webhook_url: URL to receive notifications - webhook_data_in_payload: include full results (default: false) - webhook_headers: custom headers for authentication Generated with Claude Code https://claude.com/claude-code Co-Authored-By: Claude <noreply@anthropic.com>
109 lines
3.0 KiB
Python
109 lines
3.0 KiB
Python
"""
|
||
Job endpoints (enqueue + poll) for long-running LLM extraction and raw crawl.
|
||
Relies on the existing Redis task helpers in api.py
|
||
"""
|
||
|
||
from typing import Dict, Optional, Callable
|
||
from fastapi import APIRouter, BackgroundTasks, Depends, Request
|
||
from pydantic import BaseModel, HttpUrl
|
||
|
||
from api import (
|
||
handle_llm_request,
|
||
handle_crawl_job,
|
||
handle_task_status,
|
||
)
|
||
from schemas import WebhookConfig
|
||
|
||
# ------------- dependency placeholders -------------
|
||
_redis = None # will be injected from server.py
|
||
_config = None
|
||
_token_dep: Callable = lambda: None # dummy until injected
|
||
|
||
# public router
|
||
router = APIRouter()
|
||
|
||
|
||
# === init hook called by server.py =========================================
|
||
def init_job_router(redis, config, token_dep) -> APIRouter:
|
||
"""Inject shared singletons and return the router for mounting."""
|
||
global _redis, _config, _token_dep
|
||
_redis, _config, _token_dep = redis, config, token_dep
|
||
return router
|
||
|
||
|
||
# ---------- payload models --------------------------------------------------
|
||
class LlmJobPayload(BaseModel):
|
||
url: HttpUrl
|
||
q: str
|
||
schema: Optional[str] = None
|
||
cache: bool = False
|
||
provider: Optional[str] = None
|
||
|
||
|
||
class CrawlJobPayload(BaseModel):
|
||
urls: list[HttpUrl]
|
||
browser_config: Dict = {}
|
||
crawler_config: Dict = {}
|
||
webhook_config: Optional[WebhookConfig] = None
|
||
|
||
|
||
# ---------- LLM job ---------------------------------------------------------
|
||
@router.post("/llm/job", status_code=202)
|
||
async def llm_job_enqueue(
|
||
payload: LlmJobPayload,
|
||
background_tasks: BackgroundTasks,
|
||
request: Request,
|
||
_td: Dict = Depends(lambda: _token_dep()), # late-bound dep
|
||
):
|
||
return await handle_llm_request(
|
||
_redis,
|
||
background_tasks,
|
||
request,
|
||
str(payload.url),
|
||
query=payload.q,
|
||
schema=payload.schema,
|
||
cache=payload.cache,
|
||
config=_config,
|
||
provider=payload.provider,
|
||
)
|
||
|
||
|
||
@router.get("/llm/job/{task_id}")
|
||
async def llm_job_status(
|
||
request: Request,
|
||
task_id: str,
|
||
_td: Dict = Depends(lambda: _token_dep())
|
||
):
|
||
return await handle_task_status(_redis, task_id)
|
||
|
||
|
||
# ---------- CRAWL job -------------------------------------------------------
|
||
@router.post("/crawl/job", status_code=202)
|
||
async def crawl_job_enqueue(
|
||
payload: CrawlJobPayload,
|
||
background_tasks: BackgroundTasks,
|
||
_td: Dict = Depends(lambda: _token_dep()),
|
||
):
|
||
webhook_config = None
|
||
if payload.webhook_config:
|
||
webhook_config = payload.webhook_config.dict()
|
||
|
||
return await handle_crawl_job(
|
||
_redis,
|
||
background_tasks,
|
||
[str(u) for u in payload.urls],
|
||
payload.browser_config,
|
||
payload.crawler_config,
|
||
config=_config,
|
||
webhook_config=webhook_config,
|
||
)
|
||
|
||
|
||
@router.get("/crawl/job/{task_id}")
|
||
async def crawl_job_status(
|
||
request: Request,
|
||
task_id: str,
|
||
_td: Dict = Depends(lambda: _token_dep())
|
||
):
|
||
return await handle_task_status(_redis, task_id, base_url=str(request.base_url))
|