mirror of
https://github.com/Tencent/BrowserSkill.git
synced 2026-09-10 13:01:23 +08:00
browser_screenshot declared every capture as image/png regardless of the
actual bytes. On Chromium/Edge builds where captureVisibleTab returns JPEG
bytes, the stored attachment reference recorded mediaType "image/png" against
JPEG bytes, so dsh-attachment-local's read-time metadata verification fails
with ATTACHMENT_CORRUPT ("Stored attachment metadata does not match its
reference"), surfacing as code UNKNOWN and triggering endless LLM retries.
- image.ts: sniff the capture's magic bytes (PNG/JPEG/WebP/GIF) and declare
that real media type to attachments.saveImage, instead of always "image/png".
- tools.ts: assemble the tool result from ref.mediaType (the store's verified
type) rather than re-declaring "image/png" as const, and relax the output
schema's const to the accepted media-type enum.
- tests: add a regression case asserting JPEG capture bytes surface as
image/jpeg.
Co-Authored-By: DeepSeek Harness <noreply@deepseek.com>