Repository navigation
fix(media): inspect_document names the image format from its bytes and skips files it cannot read - #344
Merged
Conversation
…d skips files it cannot read Every image/* file was returned as image/jpeg unless it was a PNG or WebP, so a GIF, BMP or HEIC reached the Claude API with the wrong media type and was rejected. Detect the format from the file signature and refuse formats the API cannot take with an explanation. Files that are not an image, PDF or text file were downloaded completely only to be told they are unsupported; classify first and skip the download. Co-Authored-By: Claude Sonnet 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_018Xun6C4mXUAKbVSmiEEh79
chigwell
approved these changes
Oct 21, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Two problems in
inspect_document's image path:smile.jpg, or a HEIC/BMP scan, produced a media type the Claude API rejects with an opaque error.The format is now sniffed from the file signature (
_sniff_image_format: PNG / JPEG / GIF / WebP) and an explicit readable message names the actual format when the bytes are not a viewable image. The format/type/ext triage happens before download, so unsupported formats are refused without transferring the file. Behavior for PDF and text paths is unchanged (same checks, hoisted above the download).Testing
tests/test_inspect_document.pycovers signature sniffing (incl. mismatched extension) and the pre-download refusal.🤖 Generated with Claude Code