From a5e254c73b49b8e608af7d46a1146d6bb9114752 Mon Sep 17 00:00:00 2001 From: emma Date: Thu, 26 Mar 2026 18:21:07 -0400 Subject: [PATCH] add optional rawTextMatch and csrClues fields to page qa model adds new optional fields to capture additional match data for raw text and CSR clues collections. these fields will be used to store enhanced matching information for crawled page analysis. to make use of these new fields, set `crawler_extra_args: "--qaDetectClientSideRendering"` and `to-warc-from-raw` to `crawler_extract_full_text`. --- backend/btrixcloud/models.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/backend/btrixcloud/models.py b/backend/btrixcloud/models.py index 3d20201c25..03cb16d6a1 100644 --- a/backend/btrixcloud/models.py +++ b/backend/btrixcloud/models.py @@ -1480,7 +1480,9 @@ class PageQACompare(BaseModel): screenshotMatch: Optional[float] = None textMatch: Optional[float] = None + rawTextMatch: float | None = None resourceCounts: Optional[Dict[str, int]] = None + csrClues: dict[str, dict[str, int]] | None = None # ============================================================================