Screenshots of stack traces and error dialogs are how bugs actually arrive — pasted into a chat by someone who cannot copy the text. A tool built for reading those, alongside OCR tuned for terminal output, closes a gap most vision tools leave open. The catch is the gate: none of this is purchasable on its own, so it comes with the coding plan or not at all. Note also that the vision server runs locally over stdio while the other three are remote.
Four separate servers Zhipu provides to GLM Coding Plan subscribers, counted together here: web search prime, web reader, a GitHub repository reader, and a vision server that runs locally over stdio.
- webSearchPrime and webReader — search the web, then fetch a page with its title, body, metadata and links
- search_doc, get_repo_structure, read_file — search a GitHub repository's knowledge, walk its tree, read a file in full
- ui_to_artifact, ui_diff_check — turn a UI screenshot into code or a spec, and compare two screenshots for visual drift
- extract_text_from_screenshot, diagnose_error_screenshot — OCR tuned for code and terminal output, and error-dialog diagnosis
- understand_technical_diagram, analyze_data_visualization — structured readings of architecture diagrams and dashboards
- image_analysis and video_analysis — general vision, and MP4/MOV scene analysis up to 8MB locally
A GLM Coding Plan subscription — Lite, Pro or Max. The servers are not sold separately, and the key must be a plan key.
Paste a URL with a key — add the endpoint to your client