apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-07-10 22:32:16 +02:00
Code Issues Projects Releases Packages Wiki Activity

chore: bumped version to 0.0.31

Browse source
This commit is contained in:
DESKTOP-RTLN3BA\$punk 2026-07-06 21:43:15 -07:00
parent 8df8565e0a
commit 1c9ab207ef
56 changed files with 520 additions and 190 deletions
Download patch file Download diff file Expand all files Collapse all files

4
surfsense_backend/app/capabilities/web/crawl/executor.py
View file

@ -60,7 +60,9 @@ def build_crawl_executor(engine: WebCrawlerConnector | None = None) -> Executor:
unit="page",
)
items = [_to_item(page, payload.maxLength) for page in pages]
emit_progress("done", f"Crawled {len(items)} page(s)", current=len(items), unit="page")
emit_progress(
"done", f"Crawled {len(items)} page(s)", current=len(items), unit="page"
)
return CrawlOutput(
items=items,
contacts=_aggregate_contacts(items),

3
surfsense_backend/app/capabilities/web/crawl/schemas.py
View file

@ -165,7 +165,8 @@ class CrawlItem(BaseModel):
default=None, description="Crawl provenance (loaded URL, depth, referrer)."
)
markdown: str | None = Field(
default=None, description="Cleaned page content as markdown (null unless success)."
default=None,
description="Cleaned page content as markdown (null unless success).",
)
metadata: dict[str, str] | None = Field(
default=None, description="Page metadata such as title and description."