mirror of
https://github.com/tiennm99/ccs.git
synced 2026-07-16 14:16:43 +00:00
kaitranntt
d5f2acaa6e
Intercept Read tool calls for image/PDF files and route through CLIProxy with gemini-2.5-flash for vision analysis. Returns text descriptions instead of blocking, enabling Claude to "see" images via proxy. Key changes: - Add image-analyzer-transformer.cjs hook script - Add ImageAnalysisConfig type and loader - Add hook installer and profile injector - Add prompt templates for analysis customization - Add e2e test suite (excluded from normal CI runs) - Configure test:e2e script for manual testing Environment variables: - CCS_IMAGE_ANALYSIS_ENABLED: Enable/disable (default: 1) - CCS_IMAGE_ANALYSIS_MODEL: Vision model (default: gemini-2.5-flash) - CCS_IMAGE_ANALYSIS_TIMEOUT: Timeout in seconds (default: 60) - CCS_CLIPROXY_API_KEY: API key for CLIProxy auth - CCS_CLIPROXY_PORT: CLIProxy port (default: 8317) Closes #426
14 lines
482 B
Plaintext
14 lines
482 B
Plaintext
Analyze this screenshot in detail for a developer who cannot see it.
|
|
|
|
Focus on:
|
|
1. Application/website type and state
|
|
2. UI elements visible (buttons, inputs, menus, modals)
|
|
3. All text content - transcribe exactly
|
|
4. Error messages or notifications (quote exactly)
|
|
5. Layout and component hierarchy
|
|
6. Interactive elements and their states
|
|
7. Console output or logs if visible
|
|
8. Any code snippets shown
|
|
|
|
Be precise - this enables the assistant to help debug or understand the UI.
|