apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-07-08 22:22:17 +02:00
Code Issues Projects Releases Packages Wiki Activity

feat(capabilities): bound web.scrape batch and expose worst-case units

Browse source
This commit is contained in:
CREDO23 2026-07-01 17:53:42 +02:00
parent 8fbfa5a6e1
commit c696829568
1 changed files with 10 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

12
surfsense_backend/app/capabilities/web/scrape/schemas.py
View file

@ -4,13 +4,21 @@ from __future__ import annotations
from typing import Literal
from pydantic import BaseModel
from pydantic import BaseModel, Field
MAX_SCRAPE_URLS = 20
"""Per-call batch cap: bounds a synchronous request's crawl fan-out (05)."""
class ScrapeInput(BaseModel):
urls: list[str]
urls: list[str] = Field(min_length=1, max_length=MAX_SCRAPE_URLS)
max_length: int = 50_000
@property
def estimated_units(self) -> int:
"""Worst-case billable crawls for pre-flight: one per requested URL."""
return len(self.urls)
class ScrapeRow(BaseModel):
url: str