tasks: the message API carries images now, the surface still does not

Reconciles the two owning docs with souveraine cfad688. Sub-scope A was
always half-landed: the substrate was multimodal end to end and the HTTP
door was text-only, so the TUI could see and every other surface was
blind. The door opens; nothing walks through it yet.

TASK-72 keeps image intake — picker, chip, base64, rendering — and now
has a server to call.

docs/substrate/tasks/multimodal-and-input-metadata.md

@@ -1,12 +1,37 @@
 ---
 task_id: multimodal-input-001
 title: Multimodal + Input Metadata — richer input than plain text
-status: landed (Sub-scopes A & B)
+status: landed (Sub-scope A incl. HTTP boundary, Sub-scope B); C pending
 assignee:
 priority: medium
 phase: 4.x
 ---
 
+> **2026-08-11 update — the HTTP boundary now carries images (souveraine `cfad688`).**
+> Sub-scope A was implemented for the TUI in May and stopped at the server door:
+> `src/api/models.rs` held `content: String`, so no HTTP surface could send an
+> attachment even though the session, `run_turn`, and the provider client were
+> all already multimodal. `MessageContent` is now an untagged `String |
+> Vec<ContentBlock>` — a bare string is the unchanged legacy wire; an array
+> carries ordered text/image parts in the substrate's own `ContentBlock`
+> vocabulary (the same shape `ContentValue` uses facing the provider).
+> Only `text` and `image` are accepted inbound: `tool_use`, `tool_result` and
+> `reasoning` are engine-written and a surface posting one gets 400
+> `unsupported_content_block` rather than a forged turn in history. The vision
+> gate answers at the door — an image sent to a model without `supports_images`
+> returns 422 `image_not_supported` naming the model, instead of being stripped
+> downstream to `[Image: attached by user]`, which reads to the human as if she
+> looked and said nothing. `run_turn`'s marker degrade stays as the fallback for
+> history that already holds images when a model changes.
+> **Verified:** 9 focused tests in `src/api/models.rs`, full suite 330 passing,
+> `cargo clippy -- -D warnings` clean (checked in a detached worktree on
+> ArchDev, not on the laptop). **Not exercised:** no real image has crossed the
+> wire from a surface — nothing sends one yet.
+> **Still open:** the surface half. `surfaces/quickshell/services/Ai.qml::attachFile()`
+> still refuses attachments and its comment now describes a limitation that no
+> longer exists; image intake in the UI belongs to TASK-72. Sub-scope C
+> (user/system metadata) remains pending.
+>
 > **2026-05-19 update:** Sub-scopes A (image support) and B (paste detection) implemented.
 > **What was built:** ContentBlock::Image variant, ContentPart/ContentValue in Bifrost wire format,
 > clipboard paste via arboard (Ctrl+Shift+V), /attach command, resize pipeline (progressive quality

docs/tasks/72-surfacing-pane-tool-primitives.md

@@ -155,7 +155,14 @@ call the last item complete from a clean QML startup alone.
 - **Paste affordance.** The TUI flagged pasted content and wrapped it for the
   agent. The GUI does not, which is why a handoff document addressed to another
   instance was read as a message to me on 2026-08-10.
-- **Image intake** at the UI end.
+- **Image intake** at the UI end. The server side landed 2026-08-11
+  (souveraine `cfad688`): the message API now accepts `"content"` as an ordered
+  array of `text`/`image` parts, gates on the model's vision capability at the
+  door, and refuses engine-owned block kinds. `Ai.qml::attachFile()` still
+  refuses attachments and its comment now cites a limitation that no longer
+  exists. Owner of the inbound contract is
+  `docs/substrate/tasks/multimodal-and-input-metadata.md`; the picker, the
+  chip, the base64 read and the rendering are this task's.
 - **Resume offer** (patch 0001) has no continue affordance until this lane
   lands; default-fresh works, one-tap-continue does not exist.