dsh-plugin-modality-fallback
DeepSeek Harness (dsh) 插件：将单个请求路由到支持相应模态的备用模型，而不是让整个会话固定使用单一模型。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:lilei0311/dsh-plugin-modality-fallback#dc850393fcf290dffab25894dc95e6e2e003cc3cPlugin Modality Fallback 以 dsh-plugin-modality-fallback 发布，当前版本为 0.1.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
English | 中文
A DeepSeek Harness (dsh) plugin. Route one request to a modality-capable fallback model instead of forcing the whole session onto a single model.
A dsh session (Agent) selects one provider/model for its entire lifetime. That single model may not accept every modality that shows up in the session's history — today that means images. Without this plugin:
read_image tool refuses outright when the session's model does not declare image input: "switch to an image-capable model to read images."ApiProxy refuses to send a message, or to switch models, when the session's history already contains an image the target model can't accept.Every one of these paths tells the user to manually switch the whole session to an image-capable model and back — losing the differentiated model choice they made for everything else in that conversation.
It wraps dsh's agent/request waterfall (the extension point dsh-agent-default-model's own README documents as deferred: "per-session selection remains the entry point's responsibility"). Before a request goes out:
agent.session.deriveMessages()).image) and the model resolved by every other listener does not declare that modality (llm.resolveModelInfo(...).inputModalities), it looks up a configured fallback route for that modality.provider/model for that request only. The session's own selection is untouched — the next request (once the image scrolls out of context, or the user switches models) resolves normally again.No core deepseek-harness code is modified. This is an ordinary Cordis plugin, loaded alongside the rest of your dsh composition.
This package declares a dsh.bundle manifest, so dsh plugin installs and wires it into a profile in one step:
dsh plugin --profile web add dsh-plugin-modality-fallback
# or straight from GitHub, no npm publish needed:
dsh plugin --profile web add github:lilei0311/dsh-plugin-modality-fallback
That appends this package to the profile's dsh.profile.bundles and applies cordis.patch.yml, which inserts the plugin row with an empty fallback: {} (no routes configured yet — every request behaves exactly as before). Configure a real route by restating that row's config in your own profile's or $DSH_HOME's cordis.patch.yml (a patch replaces the whole config, so restate the id too):
- id: modality-fallback
config:
fallback:
image: { provider: deepseek-official, model: deepseek-vision }
dsh --profile web --dump-config shows the composed row so you can confirm it landed. See deepseek-harness's plugin-install tutorial for the full bundle/profile mechanics this relies on.
dsh yourself)import ModalityFallback from 'dsh-plugin-modality-fallback'
await ctx.plugin(ModalityFallback, {
fallback: {
image: { provider: 'deepseek-official', model: 'deepseek-vision' },
},
})
Load it after your llm and agent/agent-loop plugins so ctx.llm and the agent/request waterfall already exist.
image is detected today. The modality vocabulary (ModelModality) is open-ended, but this plugin's content check only walks for image blocks. Extending it to another modality means adding a content predicate, not changing the routing mechanism.read_image and ApiProxy's own gates are unaffected. Those refuse before a request is ever built, based only on the session's currently selected model, so they refuse even when this plugin has a working fallback configured for the very modality they're gating. Fixing that requires a change in deepseek-harness core itself (those gates would need to consult this plugin, or an equivalent capability, before refusing) — out of scope for a plugin that doesn't touch core.resolveModelInfo(...).inputModalities is undefined (capability unknown), the plugin does not redirect — matching ApiProxy's existing send/switch-model gates, not the stricter read_image gate (which refuses on unknown capability). A deployment that wants redirection on unknown capability too should have its adapter declare inputModalities explicitly.resolveModelInfo is adapter-owned I/O and can reject (network, an adapter returning invalid metadata, etc.). This plugin only ever helps route around a missing modality, so a probe failure logs a warning (ctx.logger.warn) and leaves the route unchanged rather than failing the whole request — even one whose already-resolved model didn't need a fallback in the first place. The probe itself is also skipped entirely when none of the request's needed modalities have a configured route (the default install, fallback: {}, never calls it at all), so this failure mode only matters once you've actually configured a route.deepseek-harness PRdeepseek-harness is still at an early developer-preview stage and its CONTRIBUTING.md states the project does not accept external pull requests yet. Its own guidance for this situation is to build a plugin and share it — this repository does that, tagged with the dsh-plugin GitHub topic for discoverability.
MIT