# vision-control - id: vision-control - version: 0.1.4 - developer: DeepSeek Harness - packageName: vision-control - loaderId: vision-control - sha256: 097cb0b4c5e448440278f0a3147a130f67fdc409b1bdedd3078dab27247cef8a - byteSize: 23861 - publishedAt: 2026-08-25T10:53:52.446Z - updatedAt: 2026-09-21T17:16:41.042Z - releasedAt: 2026-09-21T17:16:41.042Z - html: https://addon.dshdo.com/plugins/vision-control - json: https://addon.dshdo.com/v1/plugins/vision-control - markdown: https://addon.dshdo.com/plugins/vision-control.md - tarball: https://addon.dshdo.com/v1/plugins/vision-control/versions/0.1.4/tarball ## Install ``` curl -fsSL https://addon.dshdo.com/install-plugin-market.sh | sh # then install catalog id vision-control in /plugin-market/ and enable it ``` ## Description 管理 llm-pi-ai 按模型的图片视觉开关；只写自有来源标记的配置，不覆盖用户声明。 ## Changelog (none) ## Versions - 0.1.4 (2026-09-21T17:16:41.042Z) - 0.1.3 (2026-09-08T11:20:12.321Z): 0.1.3: packaging-only release. The 0.1.2 archive unintentionally carried an AppleDouble sidecar (._cordis.patch.yml) from the platform tar tool - 0.1.2 (2026-09-08T09:41:39.736Z): 0.1.2: apply is now a non-constructible arrow so Cordis fiber runner collects and awaits its disposer — unload waits for an in-flight settings.replace and writes nothing after dispose. Real-Cordis/Loader fixture regression test added. - 0.1.1 (2026-09-08T06:04:22.207Z): 0.1.1: ownership/provenance rewrite — write only what this plugin provably owns (marker-gated), verify catalog-route disables against the authoritative llm adapter, async dispose awaiting in-flight reconcile; lost-adapter re-arm + repeated-dispose fixed. - 0.1.0 (2026-08-25T10:53:52.446Z): 首个版本：默认全开 llm-pi-ai 各路由图片输入（defaultInput），支持按 provider/模型手动关闭（disabled），双向收敛与幂等。 ## README # vision-control Out-of-tree Cordis plugin that manages the `llm-pi-ai` image-vision switch per model (no main-program changes, no UI — a pure configuration plane). Version: 0.1.3 ## Purpose Writes to the `llm-pi-ai` user section through `dsh-settings`, doing two things: - **Vision on by default**: when a route declares no `defaultInput` in either the user section or the composition `base` layer, write route-level `defaultInput: [text, image]`. A declared `defaultInput` (even `[text]`) is never overwritten. - **Vision off per model**: for models listed in `disabled`, write `input: [text]` to switch vision off; when a model leaves `disabled`, undo only the entry this plugin wrote itself. ## Ownership and undo rules (since 0.1.1) The plugin writes only fields it "owns", and records every write with a deterministic provenance marker: - Disabling a model on a **hand-declared route** (a route whose config carries a `models` list) writes `input: [text]` only when the model entry declares **no `input`**, together with the provenance marker `_visionControl: { input: true }`. - Disabling a model on a **catalog route** (no `models` list; served from the installed pi-ai catalog) writes `modelOverrides.: { input: [text], _visionControl: { input: true } }` only when the authoritative host model catalog does describe that model on that route. - Writing route-level `defaultInput: [text, image]` also records the marker `_visionControl: { defaultInput: true }` on the route object. - When a disable is lifted or `defaultImage` is set to `false`, **only marker verified writes are removed**. Any unmarked `input` / `defaultInput` — including a user-authored `input: [text]` — is treated as user-owned and is never automatically deleted or rewritten. - If the user later edits a value under a marker (an `input` or a route `defaultInput`), the plugin releases ownership of that entry (removes the marker, keeps the user's value) and will not auto-undo it. - A route that exists only in the resolved layer (never user-declared) is never materialized into the user document. - Idempotent: repeated loads and repeated reconciles have no side effects; config validation failures error at load, never silently skipped. ### Catalog-route disable verification Before disabling a model on a catalog route, the plugin verifies membership through the runtime `llm` service (`ctx.get('llm')`): the adapter that service materializes for that route is exactly the set of models for which `llm-pi-ai` would accept a `modelOverrides` entry. When membership **cannot be verified** (no `llm` service, no adapter for the route, or a catalog error), the disable is **explicitly refused and logged** — never silently treated as applied, which would leave a model looking vision-off while still on. Adapter registration often trails this plugin's mount or a settings edit, so the plugin listens for `llm/adapters-updated`: a refused catalog disable retries automatically once the adapter is ready instead of staying unapplied. ### 0.1.3 packaging-only release note 0.1.3 is a packaging-only release: identical plugin code and behavior to 0.1.2. The 0.1.2 archive unintentionally carried an AppleDouble sidecar (`._cordis.patch.yml`) created by the platform tar tool from a local extended attribute; 0.1.3 is built with the maintained node-tar writer (`portable`), which never stores macOS filesystem metadata, so the archive contains exactly the intended payload. The 0.1.2 release and its public archive remain immutable history. ### 0.1.2 fix-release note 0.1.2 fixes a real-framework disposal bug: `apply` was a constructible `function`, so Cordis' fiber runner `new`ed it and discarded the async disposer it returns — the "dispose awaits an in-flight `settings.replace`" guarantee silently never registered when the plugin was unloaded by the actual Loader. `apply` is now an arrow function (`export const apply = …`), which Cordis calls directly and whose disposer it collects and awaits. Behavior is otherwise identical to 0.1.1; the 0.1.1 ownership/undo rules and the migration notes below all still apply. The regression is covered by a real-Cordis/Loader fixture test that holds a `settings.replace` in flight and proves the fiber dispose waits for it, with nothing written after disposal. ### 0.1.0 → 0.1.1 migration notes 0.1.0's automatic sync **deleted** user-authored `input: [text]` / `modelOverrides` and wrote its values **without provenance markers** (including route-level `defaultInput`). After upgrading, which values were originally user-authored cannot be recovered: every unmarked existing value is treated as "user-owned" and is never auto-removed by this plugin (setting `defaultImage` to `false` will not undo a route `defaultInput` that 0.1.0 wrote). If 0.1.0 removed an explicit declaration of yours, restore it by hand (for example, rewrite a model's `input` as `['text']`). ## Configuration In the plugin entry's `config` (a manual `cordis.patch.yml` or your config source): ```yaml - insert: - id: vision-control name: vision-control config: defaultImage: true # vision on by default (defaults to true) disabled: # per-model vision off (optional) seawork: [ gpt-5.6-terra ] grok: [ grok-imagine ] ``` - `defaultImage`: boolean, defaults to `true`. When `false`, route-level defaults are not written, and **undoes** route `defaultInput` values this plugin wrote earlier that still carry the marker (the schema's `['text']` floor resumes); user-declared or 0.1.0-era unmarked values are unaffected. - `disabled`: an array of model ids (applies to every route), or a provider-keyed map; `*` matches any route: ```yaml config: disabled: seawork: [ gpt-5.6-terra ] '*': [ shared-model ] ``` ## Behavior boundaries - Writes only the `llm-pi-ai` namespace's user configuration section; does not read or write other namespaces and does not touch the main program. - Disable writes act only on **hand-declared-route model entries** or **catalog-route `modelOverrides`**, never writing `modelOverrides` for a model also listed in a `models` array (`llm-pi-ai` rejects that combination). - `llm-deepseek` runs through its own adapter and is outside this plugin's scope. - This plugin is not a vision-content gate; it only keeps `llm-pi-ai`'s model capability declarations (`input` / `defaultInput`) consistent with your configuration intent.