refactor(llm): drop the image content block until a path can honor it

ImageBlock had no production producer and every consumer dropped it:
the deepseek serializer skipped it, the pi-ai converter skipped it as
unrepresentable, the ACP bridge neither advertises image prompt
capability nor forwards image blocks, and compact-basic charged a flat
85-token estimate and rendered an [image] placeholder. A block
constructed today would silently vanish from the wire — the vocabulary
advertised a capability no path honors, the silent-data-loss shape the
defensive patterns warn against. The only constructors were tests
pinning the skip/estimate branches.

Remove ImageBlock and its ContentBlockMap entry (its cache?: CacheHint
field leaves with it; CacheHint itself and the other two cache? fields
are out of scope). compact-basic loses its explicit image estimate and
placeholder arms (the merge-extensible default arms absorb the case);
the deepseek serializer, pi-ai converter, and ACP codec already handled
image in their default arms, so only their image-naming comments
change. The codec's inbound rejection of ACP-protocol image prompt
content stays — that guards wire content a client can send regardless
of our vocabulary.

Tests that constructed harness image blocks to pin the removed branches
are dropped (the 85-token estimate pin) or retargeted onto plugin-added
block types / other non-text blocks, which the surviving default arms
own. Docs, the type-equiv pastes, and the content-block vocabulary
RFC's block list and multimodal-home consequence are updated in the
same change; the RFC moves to implemented/ and the index is
regenerated. A real multimodal feature reintroduces image via
declaration merging together with the adapter mapping, ACP
advertisement, and compaction pricing that honor it.

packages/llm/llm-deepseek/README.md

@@ -34,7 +34,6 @@ A second, independent implementation of the same seam exists in `@deepseek-ai/ds
 ## Limitations (MVP, documented deliberately)
 
 - `prefill` throws `LlmError('UNSUPPORTED')` — DeepSeek's chat-prefix completion is a Beta feature on the `/beta` base URL; future work.
-- `image` blocks are skipped (no vision support on these models).
 - `tool_choice` is not mapped (not part of the core vocabulary).
 
 ## Errors

packages/llm/llm-deepseek/src/serialize.ts

@@ -11,7 +11,6 @@
  *   rule for thinking mode — required there, ignored elsewhere, so we save
  *   the tokens elsewhere); `tool-call` → `tool_calls[]`
  * - `tool-result` → its own `{role: 'tool'}` message (text flattened)
- * - `image` → skipped (MVP limitation, documented in the README)
  *
  * @module dsh-llm-deepseek/serialize
  */

packages/llm/llm-deepseek/tests/serialize.spec.ts

@@ -1,6 +1,6 @@
 import { describe, expect, it } from 'vitest'
 import { CallId, LlmError } from '@deepseek-ai/dsh-llm'
-import type { GenerateOptions, Message } from '@deepseek-ai/dsh-llm'
+import type { ContentBlock, GenerateOptions, Message } from '@deepseek-ai/dsh-llm'
 import { serializeMessages, serializeRequest } from '@deepseek-ai/dsh-llm-deepseek'
 
 function request(overrides: Partial<GenerateOptions> = {}): GenerateOptions {
@@ -110,11 +110,17 @@ describe('serializeMessages', () => {
     ])
   })
 
-  it('skips image blocks (documented MVP limitation)', () => {
+  it('skips plugin-added block types (merge-extensible ContentBlockMap)', () => {
     const wire = serializeMessages([
-      { role: 'user', content: [{ type: 'image', url: 'data:image/png;base64,x' }, { type: 'text', text: 'see image' }] },
+      {
+        role: 'user',
+        content: [
+          { type: 'chart', data: 'x' } as unknown as ContentBlock,
+          { type: 'text', text: 'see chart' },
+        ],
+      },
     ])
-    expect(wire).toEqual([{ role: 'user', content: 'see image' }])
+    expect(wire).toEqual([{ role: 'user', content: 'see chart' }])
   })
 
   it('emits an empty user message rather than dropping block-less messages', () => {

packages/llm/llm-pi-ai/README.md

@@ -31,7 +31,7 @@ pi-ai declares the openai/anthropic/google/mistral/AWS SDKs as install-time depe
 
 ## Limitations
 
-Same MVP contract as llm-deepseek: `prefill` throws `UNSUPPORTED`, images are not representable, `tool_choice` is not mapped.
+Same MVP contract as llm-deepseek: `prefill` throws `UNSUPPORTED`, `tool_choice` is not mapped.
 
 ## Testing
 

packages/llm/llm-pi-ai/src/convert.ts

@@ -93,7 +93,7 @@ export function toPiContext(options: GenerateOptions): PiContext {
             })
             break
           default:
-            // image / plugin-added block types: not representable here.
+            // plugin-added block types: not representable here.
             break
         }
       }

packages/llm/llm-pi-ai/tests/convert.spec.ts

@@ -1,6 +1,6 @@
 import { describe, expect, it } from 'vitest'
 import { CallId } from '@deepseek-ai/dsh-llm'
-import type { StreamChunk } from '@deepseek-ai/dsh-llm'
+import type { ContentBlock, StreamChunk } from '@deepseek-ai/dsh-llm'
 import type { AssistantMessage, AssistantMessageEvent, Usage } from '@earendil-works/pi-ai'
 import { mapStopReason, mapUsage, toPiContext, toStreamChunks } from '@deepseek-ai/dsh-llm-pi-ai'
 
@@ -171,13 +171,13 @@ describe('toPiContext', () => {
     expect(context.messages.map(message => message.role)).toEqual(['user', 'user', 'toolResult'])
   })
 
-  it('skips image and unknown blocks in assistant content', () => {
+  it('skips plugin-added (unknown) blocks in assistant content', () => {
     const context = toPiContext({
       model: 'm',
       messages: [{
         role: 'assistant',
         content: [
-          { type: 'image', url: 'data:,x' },
+          { type: 'chart', data: 'x' } as unknown as ContentBlock,
           { type: 'text', text: 'visible' },
         ],
       }],

packages/llm/llm/README.md

@@ -25,7 +25,7 @@ An adapter registry plus a single streaming call surface, interceptable via a wa
 
 ### Content-block vocabulary (`types.ts`)
 
-Messages are arrays of typed content blocks: `text`, `reasoning`, `tool-call`, `tool-result`, `image`. The union is derived from the merge-extensible `ContentBlockMap`, so plugins can add block types via declaration merging.
+Messages are arrays of typed content blocks: `text`, `reasoning`, `tool-call`, `tool-result`. The union is derived from the merge-extensible `ContentBlockMap`, so plugins can add block types via declaration merging. The core set is limited to blocks every shipping path honors — multimodal content (images, audio, …) has no core block type; a feature that needs one adds it via the map together with the adapter/UI/compaction support that honors it.
 
 Streaming is a raw chunk protocol (`block-start`, `text-delta`, `reasoning-delta`, `tool-call-delta`, `block-end`, `usage`, `finish`). `BlockAssembler` is the single shared implementation that assembles chunks into blocks/messages.
 

packages/llm/llm/src/types.ts

@@ -57,24 +57,22 @@ export interface ToolResultBlock {
   cache?: CacheHint
 }
 
-/** An image, by URL or data URL. */
-export interface ImageBlock {
-  type: 'image'
-  url: string
-  mimeType?: string
-  cache?: CacheHint
-}
-
 /**
  * All known content block shapes, keyed by their `type` tag.
  * Merge-extensible: plugins add new block types via declaration merging.
+ *
+ * The core set is deliberately limited to blocks every shipping path honors.
+ * Multimodal content (images, audio, …) has no core block type: a feature
+ * that needs one adds it via declaration merging in the same coordinated
+ * change that maps it in the adapters, surfaces it in the UI bridges, and
+ * prices it in compaction — a producer never lands without its consumers
+ * (see docs/rfc/implemented/simplification/2026-07-04-drop-image-content-block.md).
  */
 export interface ContentBlockMap {
   'text': TextBlock
   'reasoning': ReasoningBlock
   'tool-call': ToolCallBlock
   'tool-result': ToolResultBlock
-  'image': ImageBlock
 }
 
 export type ContentBlockType = keyof ContentBlockMap

packages/llm/llm/tests/assembler.spec.ts

@@ -63,12 +63,12 @@ describe('BlockAssembler', () => {
 
   it('throws from assemble() when a partial has an unhandled blockType', () => {
     const assembler = new BlockAssembler()
-    // Directly push a block-end for an image block whose block-start never
-    // called ensure — but the image block-type flows through normally.
-    // What we really need is a partial whose blockType is not text/reasoning/tool-call.
-    // We can achieve this via a block-start for 'image' followed by blocks().
-    assembler.push({ type: 'block-start', index: 0, blockType: 'image' } as unknown as StreamChunk)
-    expect(() => assembler.blocks()).toThrow('cannot assemble incomplete block of type "image"')
+    // A partial whose blockType is not text/reasoning/tool-call cannot be
+    // assembled without its block-end. A plugin-added block type (here
+    // 'video', via the merge-extensible ContentBlockMap) opened by a
+    // block-start with no closing block-end exercises that throw.
+    assembler.push({ type: 'block-start', index: 0, blockType: 'video' } as unknown as StreamChunk)
+    expect(() => assembler.blocks()).toThrow('cannot assemble incomplete block of type "video"')
   })
 
   it('mustGet throws when an index is missing from the partials map (invariant violation)', () => {

packages/llm/llm/tests/properties.spec.ts

@@ -81,7 +81,7 @@ describe('BlockAssembler properties', () => {
     fc.assert(fc.property(streamArb, (chunks) => {
       const blocks = feed(chunks).blocks()
       for (const block of blocks) {
-        expect(['text', 'reasoning', 'tool-call', 'tool-result', 'image']).toContain(block.type)
+        expect(['text', 'reasoning', 'tool-call', 'tool-result']).toContain(block.type)
       }
     }))
   })