dsh-multimodal
DeepSeek Harness multimodal tools for image recognition and image generation through configured external APIs.
Install
$ pnpm dsh plugin --profile web add file:C:/projects/dsh-harness/dsh-multimodalPlugin 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
- Analyzes local images, HTTP(S) URLs, and data URIs with configured vision models.
- Generates text-to-image and image-to-image outputs through configured providers.
- Supports OpenAI-compatible image generation APIs and DashScope native asynchronous image tasks.
- Lists configured vision and image providers with the vision_providers tool.
- Saves generated images to disk and can serve them from a local static server for DSH Web rendering.
- Supports multiple provider configurations and per-call provider selection.
Useful For
- OCR, image description, chart reading, and screenshot analysis.
- Creating images from text prompts in DeepSeek Harness Web.
- Transforming an input image using an image-generation provider.
- Selecting among configured multimodal providers from an agent session.
Who It Fits
- DeepSeek Harness users running the Web profile.
- Developers deploying OpenAI-compatible vision or image-generation endpoints.
- Users of Aliyun DashScope image-generation models.
Documented Limitations
- External apiBase, apiKey, and model settings are required before corresponding tools can succeed.
- Local images for recognition are limited to 25 MiB when inlined as data URIs.
- DashScope native image-to-image requires a public HTTP(S) source image URL.
- Generated-image web serving defaults to localhost port 3081 and can be disabled or affected by port conflicts.
- New DSH sessions are required to see newly installed or upgraded tools.
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, 7 development, 3 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as Apache-2.0.
A root package.json was captured and can be inspected by the registry.
package.json declares a prepare lifecycle script that may run during relevant package installation workflows.
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
- chenkezhen480/dsh-multimodal
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 2f8d16a · 2026-09-11
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
- 3GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-08-17
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Vision routing and pixel-level visual tool suite for DeepSeek Harness agents with built-in free fallbacks.
View plugin →DeepSeek Harness plugin integrating ego-lite Chromium browser with 32 structured automation tools and live interactive screencast panel.
View plugin →DeepSeek Harness-native vision toolkit for image Q&A, OCR, grounding, UI restoration, pixel comparison, and visual artifacts.
View plugin →A bilingual DeepSeek Harness cost-tracking plugin with session and daily costs, budgets, pricing management, balance lookup, and coding-plan quota displays.
View plugin →