dsh-vision-patch
模型页面自定义提供商卡片中按模型和按路由设置的图像输入（视觉）复选框，通过 llm-pi-ai 设置命名空间写入。
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:ryasrk/dsh-vision-patch#602e9bf2d796151fd074b9a5c7e9085246e9f819Vision Patch 以 dsh-vision-patch 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。
A plugin with two halves on the llm-pi-ai settings namespace. The client
card on the Models page declares which models accept image input, per model
and per route, and picks a per-route vision fallback model. The host half
uses that fallback to describe images so a turn never dies on an image the
main model cannot read.
The card renders inside every provider card the Models page draws for a
llm-pi-ai route (saved rows, first-run setup rows, add-provider drafts) and
writes through the settings Remote. The host half adds no HTTP route of its
own; it registers a single agent/pre-step interceptor.
input: ['text', 'image'] on the model's stored
entry. Unchecked removes the input key entirely, so the model inherits
the installed catalog's capability (it never writes ['text'], which would
forbid images outright).defaultInput: ['text', 'image'] (set/unset via
path ops) for every model on the route that declares no list of its own.visionFallbackModel.settings/document-updated, so edits made elsewhere on the page converge.A provider with no stored profile (never saved from the Models page) shows guidance text instead of checkboxes.
A provider route in the llm-pi-ai settings namespace may carry a
visionFallbackModel field: { provider?: string; model: string }. The
provider defaults to the route itself; model names a vision-capable model
on it. An absent field turns the feature off for that route. The Models card's
dropdown writes this field; the host reads the same stored profile, so the two
sides always agree.
When the host's agent/pre-step interceptor sees a step whose user message
contains an image content block AND the step's route (from
agent.options.provider) has a configured visionFallbackModel, it:
ctx.llm.stream({ provider, model, messages, signal }) to describe the
image(s);image block in the user message with a text block holding
that description; andIt does not inspect the active main model's modality: it describes whenever a
fallback is configured and an image is present. If the describe fails, times
out, no fallback is configured, or ctx.llm is unavailable, the interceptor
delegates unchanged (next()), so the image falls through to the harness's
default handling and the turn is never blocked.
When the interceptor describes an image it rewrites the user's own message,
replacing each image content block with a text block holding the
description. That rewritten text is not stamped with a plugin source
kind. The whole host seam is validated only against mocks — there is no live
host to confirm a new, non-catalog source kind is accepted — and rewriting an
already-present user message (rather than appending a fresh one) risks
clobbering the harness's own source marker on that message. Durability of the
injected wording is therefore the harness's call; this plugin makes the
injection observable instead, via the host logger:
info when a describe is attempted (an image is present, a fallback model is
configured, and ctx.llm.stream is available);debug when the describe yields no usable text and the interceptor delegates
unchanged (next());debug when a description is actually injected and the turn enters rewritten;debug when a describe is skipped because one is already in flight for the
same agent (the per-agent concurrency guard).All logging is guarded (ctx?.logger?.info?.(...) / debug / warn?.(...)), so
an absent logger is harmless. A silent describe is never silent in the logs: if
the user believes an image was described but no text assembled (for example the
real ctx.llm.stream chunk shape differs from the mock), the debug line names
the agent that fell back to next() unchanged.
dsh plugin --profile web add github:ryasrk/dsh-vision-patch
The profile's dsh.profile.bundles list picks the package up automatically
(its package.json declares dsh.bundle.patch). Restart the web host so the
new bundle layer composes, then reload the Models page.
| Path | Role |
|---|---|
cordis.patch.yml | inserts the dsh-vision-patch loader row |
lib/index.js | host entry — apply(ctx) registers the agent/pre-step interceptor via lib/host.js |
lib/host.js | host helpers: the agent/pre-step handler that describes images and rewrites the turn, plus the settings fallback reader |
client/client.js | browser bundle: the card (image-input checkboxes + vision fallback dropdown), registered on the settings.models.provider-card slot keyed llm-pi-ai |
package.json | dsh.bundle.patch + dsh.client (web platform, inject edges) |
The client bundle requires only react (a platform seed word); it needs no
build step and has no runtime dependencies.
All writes go through ctx.remote.settings against the llm-pi-ai namespace,
carrying the revision the last read observed (settings-conflict on a lost
race):
mutate path ops on ['providers', <route>, 'defaultInput']mutate path ops on ['providers', <route>, 'visionFallbackModel'] (set the { model } choice, unset to clear)update merge restating the whole stored models list (path
ops cannot address array elements), every untouched field merge-preserved.Writes that land return the namespace's post-write view, which folds straight back into the card.
dsh plugin --profile web remove dsh-vision-patch
(Then restart the web host so the bundle layer leaves the composition.)