feat(tools): add ReadMediaFile tool for image/video files#661
Merged
Conversation
Signed-off-by: Richard Chien <stdrc@outlook.com>
Signed-off-by: Richard Chien <stdrc@outlook.com>
Signed-off-by: Richard Chien <stdrc@outlook.com>
Contributor
There was a problem hiding this comment.
Pull request overview
This PR adds a dedicated ReadMediaFile tool for reading image and video files, separating media file handling from the ReadFile tool which now focuses exclusively on text files.
Changes:
- Added new
ReadMediaFiletool with 100MB max file size, capability-based availability, and image dimension detection - Updated
ReadFileto reject image/video files and redirect users to use appropriate tools - Added comprehensive test coverage and updated documentation in both English and Chinese
Reviewed changes
Copilot reviewed 25 out of 25 changed files in this pull request and generated 4 comments.
Show a summary per file
| File | Description |
|---|---|
src/kimi_cli/tools/file/read_media.py |
New tool implementation for reading image/video files with capability checks and Kimi-specific video upload support |
src/kimi_cli/tools/file/read_media.md |
Tool description template with dynamic capability-based instructions |
src/kimi_cli/tools/file/read.py |
Removed media handling code, now returns errors for image/video files |
src/kimi_cli/tools/file/read.md |
Updated description to clarify text-only focus |
src/kimi_cli/tools/file/__init__.py |
Added ReadMediaFile to exports |
src/kimi_cli/tools/__init__.py |
Added ReadMediaFile to key argument extraction |
src/kimi_cli/agents/default/agent.yaml |
Added ReadMediaFile to default agent tools |
src/kimi_cli/agents/okabe/agent.yaml |
Added ReadMediaFile to okabe agent tools |
tests/test_read_media_file.py |
Comprehensive tests for the new tool |
tests/test_read_media_file_desc.py |
Tests for capability-based descriptions |
tests/test_read_file.py |
Updated tests to expect errors for media files |
tests/test_read_file_desc.py |
Removed (old capability-based description tests) |
tests/conftest.py |
Added fixture for ReadMediaFile tool |
tests/test_tool_schemas.py |
Added schema test for ReadMediaFile |
tests/test_tool_descriptions.py |
Updated descriptions for both tools |
tests/test_default_agent.py |
Updated default agent test with ReadMediaFile |
tests/test_agent_spec.py |
Added ReadMediaFile to agent specifications |
tests/test_pyinstaller_utils.py |
Added ReadMediaFile to PyInstaller configuration |
docs/zh/customization/agents.md |
Updated Chinese documentation with ReadMediaFile |
docs/en/customization/agents.md |
Updated English documentation with ReadMediaFile |
docs/zh/release-notes/changelog.md |
Added changelog entry in Chinese |
docs/en/release-notes/changelog.md |
Added changelog entry in English |
CHANGELOG.md |
Added changelog entry |
src/kimi_cli/acp/AGENTS.md |
Added note about ReadMediaFile ACP integration |
klips/klip-12-wire-initialize-external-tools.md |
Updated KLIP status to Implemented |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| assert part.image_url.url.startswith("data:image/png;base64,") | ||
| assert result.is_error | ||
| assert result.message == snapshot( | ||
| f"`{image_file}` is a image file. Use other appropriate tools to read image or video files." |
There was a problem hiding this comment.
Grammar error: "is a image" should be "is an image" because "image" starts with a vowel sound.
| assert part.image_url.url.startswith("data:image/png;base64,") | ||
| assert result.is_error | ||
| assert result.message == snapshot( | ||
| f"`{image_file}` is a image file. Use other appropriate tools to read image or video files." |
There was a problem hiding this comment.
Grammar error: "is a image" should be "is an image" because "image" starts with a vowel sound.
| return ToolError( | ||
| message=( | ||
| f"`{path}` is {size} bytes, which exceeds the max " | ||
| f"{MAX_MEDIA_MEGABYTES}MB bytes for media files." |
There was a problem hiding this comment.
Inconsistent error message format. The error message says "{MAX_MEDIA_MEGABYTES}MB bytes" which is redundant. It should be either "{MAX_MEDIA_MEGABYTES}MB" or "{MAX_MEDIA_MEGABYTES << 20} bytes" to match the style in the comparison.
Suggested change
| f"{MAX_MEDIA_MEGABYTES}MB bytes for media files." | |
| f"{MAX_MEDIA_MEGABYTES << 20} bytes for media files." |
|
|
||
| from kaos.path import KaosPath | ||
| from kosong.chat_provider.kimi import Kimi | ||
| from kosong.tooling import CallableTool2, ToolError, ToolOk, ToolReturnValue |
There was a problem hiding this comment.
Import of 'CallableTool2' is not used.
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
Add a dedicated
ReadMediaFiletool for reading image and video files, separating media file handling from theReadFiletool which now focuses exclusively on text files.Changes
New Tool:
ReadMediaFileimage_in/video_incapabilities)Updated Tool:
ReadFileReadMediaFileOther Changes
ReadMediaFileto default and okabe agent configurations