whitelonng/dsh-plugin-describe-image
dsh-plugin-describe-image is a tool for DeepSeek Harness. DeepSeek Harness plugin: describe_image — give a text-only model vision through an OpenAI-compatible VLM endpoint
REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
Solid, well-documented vision bridge for text-only models, but requires a harness checkout to build and test.
README states the package lives as a subtree inside deepseek-harness with workspace:^ deps and that building, type-checking, and testing happen inside a harness checkout, so standalone CI/test evidence is not visible.
README documents redirect refusal, magic-byte media-type gating, maxBytes/maxOutputTokens/timeoutMs bounds, truncated error excerpts, and a three-layer API key resolution that never logs secrets.
It solves a concrete gap by letting a text-only DeepSeek model call a VLM via an OpenAI-compatible endpoint, with only description text entering the session log.
Last updated 2026-08-15, not archived, and the README describes a git subtree sync workflow, but only 6 stars and no visible release cadence.
README covers install command, cordis.yml config example, three input forms, settings card, API key layers, FAQ, and repository layout, though it lacks a usage example of an actual describe_image call.
Generated by AI after reading the project README — a decision aid, not an endorsement. Neutral scores are given when information is limited.
Loading GitHub README...
The GitHub README is temporarily unavailable. Please try again later.
Open repositoryINSTALL REFERENCE
dsh plugin --profile web add github:whitelonng/dsh-plugin-describe-imageThis command passed the install-plan safety checks and can be executed by the DSH host. Validation is not a security audit or official endorsement.
PROJECT TOPICS
VALIDATION LADDER
FAQ
DeepSeek Harness plugin: describe_image — give a text-only model vision through an OpenAI-compatible VLM endpoint
dsh-plugin-describe-image has 6 stars and 1 forks on GitHub, last updated 2026-08-15.
dsh-plugin-describe-image is distributed under the MIT license.
dsh-plugin-describe-image is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:describe-image、image-understanding、multimodal、vision。
liustack
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | The strongest vision add-on plugin for DeepSeek Harness, adding vision capability to text-only models like DeepSeek and GLM, paste an image and get structured JSON evidence (OCR, layout, semantics).
tong-io
TongFlow — Multimodal GenAI Studio
Anionex
[dsh] A more powerful visual toolkit for text-only models: one-line install and use, paste images for direct recognition, multi-image Q&A, screenshot-to-frontend UI restoration, and more｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
DDDMUC
Free web search provider for DeepSeek Harness - DuckDuckGo backend, no API key needed
anysearch-team
AnySearch web search provider and advanced search tools for DeepSeek Harness (DSH)
omdsh-dev
Connect DSH to your database for conversational data analysis and actionable business insights.