feat(dsbench): add SDK evaluation composition
This commit is contained in:
@@ -61,6 +61,9 @@ export class DeepSeekAdapter extends LlmAdapter {
|
||||
'content-type': 'application/json',
|
||||
'accept': 'text/event-stream',
|
||||
...attributionHeaders(),
|
||||
...options.sessionId !== undefined
|
||||
? { 'x-deepseek-harness-session-id': String(options.sessionId) }
|
||||
: {},
|
||||
},
|
||||
body: JSON.stringify(body),
|
||||
...options.signal ? { signal: options.signal } : {},
|
||||
|
||||
@@ -3,6 +3,7 @@ import type { IncomingMessage, Server, ServerResponse } from 'node:http'
|
||||
import { afterEach, describe, expect, it, vi } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import LlmService, { LlmError, userAgent } from '@deepseek-ai/dsh-llm'
|
||||
import { SessionId } from '@deepseek-ai/dsh-session'
|
||||
import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
|
||||
import { DeepSeekAdapter, httpErrorCode } from '@deepseek-ai/dsh-llm-deepseek'
|
||||
import { assemble } from './assemble.ts'
|
||||
@@ -131,6 +132,19 @@ describe('DeepSeekAdapter against a mock server', () => {
|
||||
expect(kinds).toEqual(['block-start', 'text-delta', 'block-end', 'usage', 'finish'])
|
||||
})
|
||||
|
||||
it('forwards the harness session id for host-side trajectory routing', 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' }] }],
|
||||
sessionId: SessionId('child-session'),
|
||||
})
|
||||
|
||||
expect(server.headers[0]?.['x-deepseek-harness-session-id']).toBe('child-session')
|
||||
})
|
||||
|
||||
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' })
|
||||
|
||||
Reference in New Issue
Block a user