Merge remote app attribution branch

Resolve the RFC and implementation to defer OpenRouter-specific attribution headers and keep mandatory attribution to User-Agent only.

packages/llm/llm-deepseek/README.md

@@ -23,6 +23,10 @@ A second, independent implementation of the same seam exists in `@deepseek-ai/ds
 
 `thinking`/`reasoningEffort` are adapter-level request defaults serialized as the official top-level `thinking: {type}` / `reasoning_effort` wire fields. They live in adapter config (not `GenerateOptions`) to keep the core vocabulary provider-neutral.
 
+## 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.
+
 ## Wire-format notes (verified live + against the official docs)
 
 - Streaming only (`stream_options.include_usage` always on). `usage` may arrive attached to the finish chunk or as a trailing usage-only chunk — the translator defers both to `[DONE]`, so `usage` always precedes `finish` and nothing follows `finish`.

packages/llm/llm-deepseek/package.json

@@ -5,17 +5,19 @@
   "private": true,
   "type": "module",
   "main": "lib/index.js",
-  "types": "lib/index.d.ts",
+  "types": "lib/types/index.d.ts",
   "exports": {
     ".": {
-      "types": "./lib/index.d.ts",
+      "types": "./lib/types/index.d.ts",
       "default": "./lib/index.js"
     },
     "./src/*": "./src/*",
     "./package.json": "./package.json"
   },
   "files": [
-    "lib",
+    "lib/index.js",
+    "lib/types/**/*.d.ts",
+    "lib/types/**/*.d.ts.map",
     "src"
   ],
   "license": "BSD-3-Clause",

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

@@ -5,7 +5,7 @@
  * @module dsh-llm-deepseek/adapter
  */
 
-import { LlmAdapter, LlmError } from '@deepseek-ai/dsh-llm'
+import { attributionHeaders, LlmAdapter, LlmError } from '@deepseek-ai/dsh-llm'
 import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
 import { serializeRequest } from './serialize.ts'
 import type { RequestDefaults } from './serialize.ts'
@@ -21,13 +21,6 @@ export interface DeepSeekAdapterOptions {
   defaults?: RequestDefaults
 }
 
-/**
- * Attribution header sent on every request so the provider can identify the
- * client. Bump in lockstep with this package's version (no build-time version
- * injection is wired in this repo yet).
- */
-const USER_AGENT = 'deepseek-harness/0.0.1'
-
 /** Map an HTTP status to a stable LlmError code. */
 export function httpErrorCode(status: number): string {
   if (status === 401 || status === 403) return 'AUTH'
@@ -67,7 +60,7 @@ export class DeepSeekAdapter extends LlmAdapter {
         'authorization': `Bearer ${this.options.apiKey}`,
         'content-type': 'application/json',
         'accept': 'text/event-stream',
-        'user-agent': USER_AGENT,
+        ...attributionHeaders(),
       },
       body: JSON.stringify(body),
       ...options.signal ? { signal: options.signal } : {},

packages/llm/llm-deepseek/tests/adapter.e2e.ts

@@ -1,9 +1,10 @@
 import { afterEach, describe, expect, it } from 'vitest'
 import { Context } from 'cordis'
 import LlmService, { CallId } from '@deepseek-ai/dsh-llm'
-import type { GenerateResult, Message, ToolSchema } from '@deepseek-ai/dsh-llm'
+import type { Message, ToolSchema } from '@deepseek-ai/dsh-llm'
 import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
 import type { Config } from '@deepseek-ai/dsh-llm-deepseek'
+import { assemble, type AssembledResult } from './assemble.ts'
 
 /**
  * Real-API e2e for the hand-rolled adapter: V4 Flash + V4 Pro across
@@ -31,7 +32,7 @@ function ask(text: string): Message[] {
   return [{ role: 'user', content: [{ type: 'text', text }] }]
 }
 
-function textOf(result: GenerateResult): string {
+function textOf(result: AssembledResult): string {
   return result.message.content
     .filter(block => block.type === 'text')
     .map(block => block.text)
@@ -51,7 +52,7 @@ const weatherTool: ToolSchema = {
 describe.skipIf(!process.env.DEEPSEEK_API_KEY)('llm-deepseek e2e (real API)', () => {
   it('flash + thinking disabled: plain text generation', async () => {
     const ctx = await harness(FLASH, { thinking: 'disabled' })
-    const result = await ctx.llm.generate({
+    const result = await assemble(ctx,{
       model: FLASH,
       messages: ask('Reply with exactly the word: pong'),
       maxTokens: 50,
@@ -65,7 +66,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('llm-deepseek e2e (real API)', ()
 
   it('flash + thinking enabled (effort high): reasoning blocks + reasoning tokens', async () => {
     const ctx = await harness(FLASH, { thinking: 'enabled', reasoningEffort: 'high' })
-    const result = await ctx.llm.generate({
+    const result = await assemble(ctx,{
       model: FLASH,
       messages: ask('Which is larger, 9.11 or 9.8? Answer with just the number.'),
       maxTokens: 2000,
@@ -82,7 +83,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('llm-deepseek e2e (real API)', ()
       const ctx = await harness(PRO, { thinking: 'enabled', reasoningEffort: effort })
 
       // Turn 1: the model must call the tool (and think before it).
-      const first = await ctx.llm.generate({
+      const first = await assemble(ctx,{
         model: PRO,
         messages: ask('What is the weather in Paris right now? Use the get_weather tool.'),
         tools: [weatherTool],
@@ -96,7 +97,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('llm-deepseek e2e (real API)', ()
 
       // Turn 2: send the tool result back WITH the assistant's reasoning
       // block in history (the official thinking+tools passback rule).
-      const second = await ctx.llm.generate({
+      const second = await assemble(ctx,{
         model: PRO,
         messages: [
           ...ask('What is the weather in Paris right now? Use the get_weather tool.'),
@@ -120,7 +121,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('llm-deepseek e2e (real API)', ()
 
   it('pro + thinking disabled: plain generation without reasoning blocks', async () => {
     const ctx = await harness(PRO, { thinking: 'disabled' })
-    const result = await ctx.llm.generate({
+    const result = await assemble(ctx,{
       model: PRO,
       messages: ask('Reply with exactly the word: pong'),
       maxTokens: 50,

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

@@ -2,9 +2,10 @@ import { createServer } from 'node:http'
 import type { IncomingMessage, Server, ServerResponse } from 'node:http'
 import { afterEach, describe, expect, it, vi } from 'vitest'
 import { Context } from 'cordis'
-import LlmService, { LlmError } from '@deepseek-ai/dsh-llm'
+import LlmService, { LlmError, userAgent } from '@deepseek-ai/dsh-llm'
 import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
 import { DeepSeekAdapter, httpErrorCode } from '@deepseek-ai/dsh-llm-deepseek'
+import { assemble } from './assemble.ts'
 
 /** One scripted behavior for the next request the mock server receives. */
 type Behavior =
@@ -90,11 +91,11 @@ async function harness(baseURL: string, config: object = {}) {
 }
 
 describe('DeepSeekAdapter against a mock server', () => {
-  it('streams a text generation end to end through ctx.llm.generate', async () => {
+  it('streams a text generation end to end through the assembler', async () => {
     const server = await mockServer([{ kind: 'sse', events: textEvents }])
     const ctx = await harness(server.url)
 
-    const result = await ctx.llm.generate({
+    const result = await assemble(ctx, {
       model: 'deepseek-v4-flash',
       messages: [{ role: 'user', content: [{ type: 'text', text: 'hi' }] }],
     })
@@ -108,8 +109,12 @@ describe('DeepSeekAdapter against a mock server', () => {
       stream: true,
       stream_options: { include_usage: true },
     })
-    // Attribution header identifies the harness to the provider.
-    expect(server.headers[0]?.['user-agent']).toMatch(/^deepseek-harness\//)
+    // Attribution reaches the wire: the exact shared User-Agent, and no
+    // provider-specific headers without an explicitly configured target.
+    expect(server.headers[0]?.['user-agent']).toBe(userAgent())
+    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')
   })
 
   it('streams raw chunks through ctx.llm.stream', async () => {
@@ -130,7 +135,7 @@ describe('DeepSeekAdapter against a mock server', () => {
     const server = await mockServer([{ kind: 'sse', events: textEvents }])
     const ctx = await harness(server.url, { thinking: 'disabled', reasoningEffort: 'high' })
 
-    await ctx.llm.generate({
+    await assemble(ctx,{
       model: 'deepseek-v4-flash',
       messages: [{ role: 'user', content: [{ type: 'text', text: 'hi' }] }],
     })
@@ -155,15 +160,15 @@ describe('DeepSeekAdapter against a mock server', () => {
     }
     const server = await mockServer([behavior, behavior, behavior])
     const ctx = await harness(server.url)
-    await expect(ctx.llm.generate({ model: 'deepseek-v4-flash', messages: [] }))
+    await expect(assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }))
       .rejects.toThrow(`failed with ${status}`)
     await expect(
-      ctx.llm.generate({ model: 'deepseek-v4-flash', messages: [] })
+      assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] })
         .catch((error: unknown) => (error as LlmError).code),
     ).resolves.toBe(code)
     // The numeric HTTP status is carried on the error for explicit handling.
     await expect(
-      ctx.llm.generate({ model: 'deepseek-v4-flash', messages: [] })
+      assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] })
         .catch((error: unknown) => (error as LlmError).status),
     ).resolves.toBe(status)
   })
@@ -171,14 +176,14 @@ describe('DeepSeekAdapter against a mock server', () => {
   it('keeps the status-line message for JSON error bodies without a message', async () => {
     const server = await mockServer([{ kind: 'http-error', status: 500, body: '{"error":{"type":"x"}}' }])
     const ctx = await harness(server.url)
-    await expect(ctx.llm.generate({ model: 'deepseek-v4-flash', messages: [] }))
+    await expect(assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }))
       .rejects.toThrow(/HTTP 500/)
   })
 
   it('keeps the status-line message for non-JSON error bodies', async () => {
     const server = await mockServer([{ kind: 'http-error', status: 502, body: 'Bad Gateway', contentType: 'text/plain' }])
     const ctx = await harness(server.url)
-    await expect(ctx.llm.generate({ model: 'deepseek-v4-flash', messages: [] }))
+    await expect(assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }))
       .rejects.toThrow(/HTTP 502/)
   })
 
@@ -207,7 +212,7 @@ describe('DeepSeekAdapter against a mock server', () => {
       events: ['{"choices":[{"delta":{"content":"par"}}]}'],
     }])
     const ctx = await harness(server.url)
-    await expect(ctx.llm.generate({ model: 'deepseek-v4-flash', messages: [] }))
+    await expect(assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }))
       .rejects.toThrow(/terminated|socket|without \[DONE\]/)
   })
 
@@ -278,7 +283,7 @@ describe('plugin registration and config', () => {
     vi.stubEnv('DEEPSEEK_BASE_URL', 'http://env-host:1')
     const server = await mockServer([{ kind: 'sse', events: textEvents }])
     const ctx = await harness(server.url) // harness passes explicit config
-    await ctx.llm.generate({ model: 'deepseek-v4-flash', messages: [] })
+    await assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] })
     expect(server.requests).toHaveLength(1) // hit the explicit URL, not env
   })
 
@@ -288,7 +293,7 @@ describe('plugin registration and config', () => {
     const ctx = new Context()
     await ctx.plugin(LlmService)
     await ctx.plugin(LlmDeepSeek, { apiKey: 'k', models: ['deepseek-v4-flash'] })
-    await ctx.llm.generate({ model: 'deepseek-v4-flash', messages: [] })
+    await assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] })
     expect(server.requests).toHaveLength(1)
   })
 

packages/llm/llm-deepseek/tests/assemble.ts

@@ -0,0 +1,26 @@
+/**
+ * Test helper: drive `ctx.llm.stream()` through a `BlockAssembler` and return
+ * the assembled message + usage + finish reason. This exercises the same
+ * streaming path production uses (the loop), rather than a service-level
+ * one-shot convenience method.
+ */
+
+import { BlockAssembler } from '@deepseek-ai/dsh-llm'
+import type { Context } from 'cordis'
+import type { FinishReason, GenerateOptions, Message, TokenUsage } from '@deepseek-ai/dsh-llm'
+
+export interface AssembledResult {
+  message: Message
+  usage?: TokenUsage
+  finish: FinishReason
+}
+
+export async function assemble(ctx: Context, options: GenerateOptions): Promise<AssembledResult> {
+  const assembler = new BlockAssembler()
+  for await (const chunk of ctx.llm.stream(options)) assembler.push(chunk)
+  return {
+    message: assembler.message(),
+    ...assembler.usage !== undefined ? { usage: assembler.usage } : {},
+    finish: assembler.finish,
+  }
+}

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

@@ -47,7 +47,7 @@ describe('translate: text', () => {
     ))) {
       assembler.push(chunk)
     }
-    const result = assembler.result()
+    const result = { message: assembler.message(), finish: assembler.finish }
     expect(result.message.content).toEqual([{ type: 'text', text: 'hi' }])
     expect(result.finish).toEqual({ kind: 'stop' })
   })

packages/llm/llm-deepseek/tsconfig.json

@@ -2,7 +2,7 @@
   "extends": "../../../tsconfig.base.json",
   "compilerOptions": {
     "rootDir": "src",
-    "outDir": "lib"
+    "outDir": "lib/types"
   },
   "include": [
     "src"