feat(llm): mark compaction requests with x-deepseek-harness-compact header

packages/llm/llm-deepseek/README.md

@@ -38,7 +38,7 @@ The plugin registers the single provider route `deepseek`. A request selects it
 
 ## App attribution
 
-Every request carries the shared attribution header from dsh-llm's `attributionHeaders()` - the mandatory `User-Agent` baseline identifying the harness (see [dsh-llm § App attribution](../llm/README.md#app-attribution-attributionts)). Direct DeepSeek requests and OpenAI-compatible gateway requests get no provider-specific app-attribution headers under this adapter contract; OpenRouter app attribution is deferred to a future explicit OpenRouter adapter or mode.
+Every request carries the shared attribution header from dsh-llm's `attributionHeaders()` - the mandatory `User-Agent` baseline identifying the harness (see [dsh-llm § App attribution](../llm/README.md#app-attribution-attributionts)). Direct DeepSeek requests and OpenAI-compatible gateway requests get no provider-specific app-attribution headers under this adapter contract; OpenRouter app attribution is deferred to a future explicit OpenRouter adapter or mode. A request with `GenerateOptions.compact` set (dsh-compact-basic's auxiliary summarization call) additionally carries `x-deepseek-harness-compact: 1`, so the host can separate compaction traffic from conversation requests.
 
 ## Wire-format notes (verified live + against the official docs)
 

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

@@ -182,6 +182,9 @@ export class DeepSeekAdapter extends LlmAdapter {
       ...options.sessionId !== undefined
         ? { 'x-deepseek-harness-session-id': String(options.sessionId) }
         : {},
+      ...options.compact === true
+        ? { 'x-deepseek-harness-compact': '1' }
+        : {},
     }
 
     // TODO(http): adopt the Cordis HTTP service when shared transport configuration

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

@@ -129,6 +129,8 @@ describe('DeepSeekAdapter against a mock server', () => {
     expect(server.headers[0]).not.toHaveProperty('http-referer')
     expect(server.headers[0]).not.toHaveProperty('x-openrouter-title')
     expect(server.headers[0]).not.toHaveProperty('x-openrouter-categories')
+    // A conversation request carries no compaction marker.
+    expect(server.headers[0]).not.toHaveProperty('x-deepseek-harness-compact')
   })
 
   it('streams raw chunks through ctx.llm.stream', async () => {
@@ -159,6 +161,19 @@ describe('DeepSeekAdapter against a mock server', () => {
     expect(server.headers[0]?.['x-deepseek-harness-session-id']).toBe('child-session')
   })
 
+  it('marks the auxiliary compaction call on the wire', async () => {
+    const server = await mockServer([{ kind: 'sse', events: textEvents }])
+    const ctx = await harness(server.url)
+
+    await assemble(ctx, {
+      model: 'deepseek-v4-flash',
+      messages: [{ role: 'user', content: [{ type: 'text', text: 'hi' }] }],
+      compact: true,
+    })
+
+    expect(server.headers[0]?.['x-deepseek-harness-compact']).toBe('1')
+  })
+
   it('forwards thinking config onto the wire', async () => {
     const server = await mockServer([{ kind: 'sse', events: textEvents }])
     const ctx = await harness(server.url, { thinking: 'disabled', reasoningEffort: 'high' })

packages/llm/llm/src/types.ts

@@ -226,4 +226,11 @@ export interface GenerateOptions {
    * it; replay uses it to keep concurrent parent and child cursors independent.
    */
   sessionId?: Branded<'SessionId'>
+  /**
+   * Marks the auxiliary compaction (summarization) call. The DeepSeek adapter
+   * forwards it as the `x-deepseek-harness-compact: 1` request header so the
+   * host can separate compaction traffic from conversation requests; it never
+   * enters the model-visible request body. Loop-built requests leave it unset.
+   */
+  compact?: boolean
 }