Taishan-Vision
Enables image recognition for text-only DeepSeek Harness models using Zhipu GLM vision models.
Install
$ dsh plugin --profile web add github:iguanren/taishan-vision#v5.0Plugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Routes image attachments to Zhipu GLM vision models for automated description generation
- Provides native configuration card within DeepSeek Harness plugin settings
- Supports drag-and-drop ordering and toggling of vision models with automatic fallback
- Secure API Key credential storage without plaintext display
- Prompt injection defense with fenced output declarations for visual descriptions
- Built-in diagnostic tool (taishan_diag) for troubleshooting credentials, routes, and wrapping states
Useful For
- Enabling visual understanding and image Q&A when using text-only DeepSeek reasoning models
- Extracting textual information, diagrams, and visual data from uploaded images
- Building multi-model workflows where specialized vision models handle perception and main models perform downstream tasks
Who It Fits
- DeepSeek Harness users relying on text-only reasoning models
- Developers seeking free vision capabilities via Zhipu GLM API
- AI workflow builders requiring visual context preprocessing
Documented Limitations
- Requires a Zhipu AI GLM API key (free tier available from open.bigmodel.cn)
- Image processing latency depends on external Zhipu GLM API availability and network speed
- Configured primarily for the web profile of DeepSeek Harness
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 0 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- iguanren/Taishan-Vision
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- e8a09b2 · 2026-09-25
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 0GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-09-25
- Last release
- 2026-09-25
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Vision routing and pixel-level tools for text-only DeepSeek Harness agents with built-in free fallback.
View plugin →DeepSeek Harness-native vision toolkit enabling image Q&A, OCR, UI restoration, grounding, and pixel diff for text-only models.
View plugin →Automates invoice retrieval from IMAP mailboxes, OCR extraction, categorization, and Excel summary report generation.
View plugin →A DeepSeek Harness vision plugin that turns pasted images into structured OCR, layout, and semantic evidence for supported text-only models.
View plugin →