kutcr/dsh-image-transcription-plugin
DeepSeek Harness Cordis plugins for durable image transcription and on-demand historical image recall.
安装Install
dsh plugin --profile web add github:kutcr/dsh-image-transcription-plugin
把 kutcr/dsh-image-transcription-plugin 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
DSH Image Transcription Plugin
中文 · Upstream: DeepSeek Harness · Topic
A source release for the DeepSeek Harness image-transcription feature. It is implemented as two Cordis plugins:
@deepseek-ai/dsh-image-transcriptionconverts image-bearing messages into durable visual transcriptions when the primary model is text-only.@deepseek-ai/dsh-tool-image-recallregistersrecall_image, allowing the primary model to ask the configured vision model to re-read a cited historical image.
Features
- Stable
transcriptionIdreferences bind text transcriptions to their original attachments. - Compaction adds a compact image index; original attachments remain stored in the session log.
recall_imagesends only the cited image batch and the current question to the visual route.- The Web UI shows elapsed transcription status and retains clear failures.
Configure the image-transcription model
This plugin requires an image-transcription model configuration before it can process images.
- Open Settings → Models.
- In Image transcription model, select the visual provider and model to use when the primary model is text-only.
- Expand Configuration and enter the provider API key, endpoint, protocol, and available model ID.
- Save the configuration.

License and attribution
This release contains modifications to DeepSeek Harness, licensed under MIT. Keep the included LICENSE and retain upstream attribution in derivative distributions.
nexu-io/open-design
ruvnet/ruflo
amruthpillai/reactive-resume
volcengine/OpenViking
Molunerfinn/PicGo
titanwings/colleague-skill