feat(vision): consult_vision tool + vision settings API

Backend vision update (additive to [email protected] / [email protected],
no version bump).

Contracts mirrored (.dispatch/transport-contract.reference.md):
- VisionSettingsResponse + SetVisionSettingsRequest (GET/PUT /settings/vision).
- Delta note: read_image -> consult_vision; numbered placeholders; compaction.

Tool rendering (ChatView):
- read_image test -> consult_vision (rendering is generic by toolName).
- +2 tests: numbered-placeholder text chunk + [Compacted image] text chunk
  (both regular text chunks, render as-is — no special handling).

New vision feature library (src/features/vision/):
- logic/view-model.ts (32 tests): VisionSettings/VisionSettingsPatch types
  (consumer-defines-port), LoadVisionSettings/SaveVisionSettings ports +
  results, normalizeVisionSettings (network-seam coercion), parseImageLimit/
  imageLimitChanged, compactionModelOptions (vision-capable models via chat's
  public isVisionModel + Auto sentinel), round-trip helpers, imageLimitLabel.
- ui/VisionSettingsView.svelte (9 tests): imageLimit input + Save,
  compactionModel dropdown (Auto + vision-capable models), load-on-mount,
  save-on-change, error/saved feedback.
- index.ts.

Cross-unit seam: isVisionModel added to features/chat public index.ts
(additive); imported through the public surface, not internals.

Store wiring (src/app/store.svelte.ts):
- visionSettings state + refreshVisionSettings (GET /settings/vision,
  normalized at the seam) + setVisionSettings (PUT, partial, returns merged) +
  VisionSettingsResult; seeded on boot; exposed on AppStore. +4 store tests.

Mounted in App.svelte: new "Vision" sidebar view kind + VisionSettingsView
in viewContent (not conversation-scoped); load/save adapters; visionManifest.

Verification: svelte-check 0/0; vitest 948/948 (run twice, +47 since the
prior vision commit); biome clean; vite build OK. See backend-handoff.md §2j.

Not merged or pushed.

1 files changed, 3 insertions, 2 deletions

diff --git a/GLOSSARY.md b/GLOSSARY.md
index 03fd848..3973fe1 100644
--- a/GLOSSARY.md
+++ b/GLOSSARY.md
@@ -27,8 +27,9 @@
 | **computer** | A remote SSH target discovered from the system's `~/.ssh/config` — a read-only VIEW, NOT an editable entity (no CRUD store; to add one the user edits `~/.ssh/config`). Backend-canonical (`[email protected]`, additive). On the wire as `Computer` (`{ alias, hostName, port, user, identityFile, knownHost }`) + `ComputerEntry extends Computer` (adds `usageCount`, for `GET /computers`). `alias` IS the **computerId** — the string persisted per-conversation / per-workspace (the computer analog of `cwd`). Resolution is SERVER-owned (never re-implement): per-conversation `computerId` → `workspace.defaultComputerId` → `null`/local. USER-facing only: a tool-execution target forwarded to tools, NEVER part of the model prompt (does not affect prompt caching); the agent never sees it. HTTP API (`GET /computers`, `GET`/`PUT /conversations/:id/computer`, `PUT /workspaces/:id/default-computer`, `GET /computers/:alias/status`, `POST /computers/:alias/test`) consumed in handoff #2. | ssh host, remote host, server, connection target |
 | **computerId** | The string id of a **computer** — an SSH config `Host` alias users select. Persisted per-conversation and per-workspace (the computer analog of `cwd`/`workspaceId`). `null` means local (no SSH; today's behavior). On `Workspace` as the REQUIRED `defaultComputerId: string \| null` (null = local / no SSH; the computer analog of `defaultCwd`); per-conversation persistence via `GET`/`PUT`/`DELETE /conversations/:id/computer`. `chat.send` need not send it (resolved server-side from the persisted per-conversation value in the MVP). | ssh alias, host id, remote id |
 | **image chunk** | An `ImageChunk` (`{ type: "image", url, mimeType? }`) — a NEW `Chunk` variant for an image attached to a message (a user-pasted screenshot/photo). `url` is a base64 data URL (`data:image/…;base64,…`) OR an `http(s)://` URL. Backend-canonical (`[email protected]`, additive). A user message may be multi-chunk (`[text, image, image, …]` in order). On the wire as `ImageChunk` (persisted) + `ImageInput` (what `ChatRequest.images` carries; the orchestrator converts each into an `ImageChunk`). | picture, photo attachment, screenshot chunk |
-| **vision** (capability) | Whether a model can natively accept image input (multimodal). On the wire as `ModelMetadata.vision?: boolean` (`GET /models` `modelInfo[name].vision`). `true` (e.g. any `kimi/*` model) → image chunks are passed through to the provider natively. Absent/`false` (e.g. `umans/glm-5.2`) → the server's **vision handoff** transcribes each image to a text description before the model sees it. The FE shows a vision badge in the model picker; it does NOT decide handoff (server-owned). | multimodal, image support |
-| **vision handoff** | The server-owned mechanism by which a NON-vision model still reasons about a pasted image: the orchestrator transcribes the image to a text description (via a vision-capable model) and feeds that text instead, so a text-only model never sees the image directly. The persisted user message keeps the original `image` chunk AND a `text` transcription chunk (`[Image analysis (via <model>)]: …`) in the SAME message — the description is reused on every later turn (no re-transcription). The FE renders both; it sends the image and lets the server decide. Distinct from a vision-capable model, which receives the image natively. | image transcription, vision relay |
+| **vision** (capability) | Whether a model can natively accept image input (multimodal). On the wire as `ModelMetadata.vision?: boolean` (`GET /models` `modelInfo[name].vision`). `true` (e.g. any `kimi/*` model) → image chunks are passed through to the provider natively. Absent/`false` (e.g. `umans/glm-5.2`) → the server's **vision handoff** gives the model a numbered placeholder + the `consult_vision` tool. The FE shows a vision badge in the model picker; it does NOT decide handoff (server-owned). | multimodal, image support |
+| **vision handoff** | The server-owned mechanism by which a NON-vision model still reasons about a pasted image. A non-vision model gets a NUMBERED PLACEHOLDER text chunk alongside the persisted `image` chunk, then calls the `consult_vision` tool (which opens a NEW conversation tab with a vision-capable model, attaches the image + question, and returns the vision model's answer). The persisted user message keeps the original `image` chunk (the FE renders it) AND the placeholder text. When a vision-capable model has more than `imageLimit` images in history, image **compaction** transcribes the oldest to `[Compacted image]: <description>` text chunks (the `image` chunk stays for rendering). All these are regular `text` chunks — the FE renders them as-is. Distinct from a vision-capable model, which receives the image natively. | image transcription, vision relay |
+| **consult_vision** | A tool available to all models that defers image analysis to a vision-capable model: it opens a NEW conversation tab (with a vision model, e.g. Kimi), attaches the image (by `imageIds` from a pasted placeholder, or by `path` from disk) + a `question`, and returns the conversation id + the vision model's answer (suggesting the dispatch CLI for follow-ups). Replaces the former `read_image` tool. Rendered generically like any tool call/result (by `toolName`). | read_image (former), vision tool |
 
 ## Frontend-specific
 | Term | Meaning | Aliases to avoid |