feat: integrate Claude Opus vision API for image analysis#17
Draft
Copilot wants to merge 2 commits into
Draft
Conversation
Co-authored-by: leekHotline <117092932+leekHotline@users.noreply.github.com>
Copilot
AI
changed the title
[WIP] Address user acquisition challenges in product launch
feat: integrate Claude Opus vision API for image analysis
Feb 26, 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The image analysis service was a stub returning placeholder text. The constraint requires using Claude Opus as the real vision backend to make the product functional for visually impaired users.
Changes
New dependency
anthropic>=0.40.0added tobackend/pyproject.tomlConfig (
app/core/config.py)ANTHROPIC_API_KEY: str = ""— gates Claude usage; set in.envto enableCLAUDE_MODEL: str = "claude-opus-4-5"— model selection, overridable via envImage analysis service (
modules/image_analysis/service.py)is_clearflagRouter (
modules/image_analysis/router.py)dbsession toservice.describe_image()so the service can resolveimage_file_id→ stored file pathOriginal prompt
💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.