dev issues 6 - #183
Open
lzsweb wants to merge 4 commits into
Open
Conversation
added 4 commits
August 27, 2026 17:34
The only multimodal entry point was user-input @path expansion, so after scrape_web_screenshot/camera_capture the model could not see the saved image and sometimes echoed the user-facing @path hint verbatim, ending the turn prematurely. view_image routes a local image to a vision-capable model on the active provider (active model if vision- capable, else the provider's declared vision model, else a per- provider fallback), and screenshot/camera hints now point at it.
Synced from agenticCLI ae76b1a: vision backends downscale ultra-tall images until text is illegible, so view_image now detects oversized images, crops overlapping slices with Pillow, runs one vision call per slice, and stitches the results. Pillow optional; slice=auto|never.
README.md stays the English primary doc; README_zh.md mirrors it section by section, and both cross-link at the top.
Fixes CI pylint W0622 (redefined-builtin); local pre-commit hooks all pass now, matching the CI --all-files gate.
lzsweb
changed the title
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
view_imagetool so the agent can analyze local images itself (afterscrape_web_screenshot/camera_captureor any user-saved image), routing them to a vision-capable model on the active providerview_imagecrops overlapping slices with Pillow, runs one vision call per slice, and stitches the results; newslice=auto|neverparameter; Pillow optional with whole-image fallbackREADME_zh.md) mirroring README.md, with language switchers in bothTest plan
tests/unit/test_acli_vision_tool.py: 15 unit tests pass (tool registration, model picking, slicing plan coverage/cap, auto-slice path,slice=never, per-slice error reporting)(Image auto-split into N slices ...)covering the whole table