Merge master into app attribution RFC

This commit is contained in:
Tianyi Cui
2026-07-05 00:45:39 +08:00
197 changed files with 2876 additions and 2047 deletions

View File

@@ -32,13 +32,10 @@ Every request carries the shared attribution header from dsh-llm's `attributionH
- 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`.
- The first thinking-mode chunk carries `reasoning_content: ""` — handled (no spurious reasoning block).
- **Reasoning passback rule**: on assistant turns that carried tool calls, `reasoning_content` is serialized back in history (required by the API in thinking mode); on tool-call-free turns it is dropped (ignored anyway — saves tokens).
- `strict` on tool schemas passes through (officially Beta; the public API wants the `/beta` base URL for it, the internal endpoint accepts it directly).
- Cache accounting: `cacheReadTokens` ← `prompt_cache_hit_tokens` / `prompt_tokens_details.cached_tokens`; DeepSeek reports no cache-write metric.
## 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

View File

@@ -11,12 +11,10 @@
* 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
*/
import { LlmError } from '@deepseek-ai/dsh-llm'
import type { ContentBlock, GenerateOptions, Message } from '@deepseek-ai/dsh-llm'
import type { WireMessage, WireRequest, WireTool } from './types.ts'
@@ -99,19 +97,8 @@ export function serializeMessages(messages: Message[]): WireMessage[] {
return wire
}
/**
* Build the full wire request. Throws `LlmError('UNSUPPORTED')` for
* `prefill` (DeepSeek's chat-prefix completion is a Beta feature on a
* different base URL — see README).
*/
/** Build the full wire request. */
export function serializeRequest(options: GenerateOptions, defaults: RequestDefaults = {}): WireRequest {
if (options.prefill !== undefined) {
throw new LlmError(
'prefill is not supported by the DeepSeek adapter (Beta chat-prefix completion is future work)',
'UNSUPPORTED',
)
}
const messages: WireMessage[] = []
if (options.system !== undefined) {
messages.push({ role: 'system', content: options.system })
@@ -124,8 +111,6 @@ export function serializeRequest(options: GenerateOptions, defaults: RequestDefa
name: tool.name,
description: tool.description,
parameters: tool.parameters,
// strict is officially supported (Beta); pass the tool author's choice.
...tool.strict !== undefined ? { strict: tool.strict } : {},
},
}))

View File

@@ -78,8 +78,6 @@ export interface WireTool {
name: string
description: string
parameters: Record<string, unknown>
/** Beta: strict schema adherence (official: requires the /beta base URL). */
strict?: boolean
}
}

View File

@@ -110,7 +110,7 @@ describe('DeepSeekAdapter against a mock server', () => {
stream_options: { include_usage: true },
})
// Attribution reaches the wire: the exact shared User-Agent, and no
// provider-specific headers without an explicitly configured target.
// provider-specific headers under the User-Agent-only contract.
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')

View File

@@ -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 { CallId } 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', () => {
@@ -149,17 +155,17 @@ describe('serializeRequest', () => {
expect(wire.stop).toEqual(['END'])
})
it('maps tools with strict passthrough', () => {
it('maps tools to the wire function shape', () => {
const wire = serializeRequest(request({
messages: history,
tools: [
{ name: 'a', description: 'A', parameters: { type: 'object', properties: {} } },
{ name: 'b', description: 'B', parameters: { type: 'object', properties: {} }, strict: true },
{ name: 'b', description: 'B', parameters: { type: 'object', properties: { x: { type: 'string' } } } },
],
}))
expect(wire.tools).toEqual([
{ type: 'function', function: { name: 'a', description: 'A', parameters: { type: 'object', properties: {} } } },
{ type: 'function', function: { name: 'b', description: 'B', parameters: { type: 'object', properties: {} }, strict: true } },
{ type: 'function', function: { name: 'b', description: 'B', parameters: { type: 'object', properties: { x: { type: 'string' } } } } },
])
})
@@ -179,17 +185,6 @@ describe('serializeRequest', () => {
expect(wire.thinking).toBeUndefined()
expect(wire.reasoning_effort).toBeUndefined()
})
it('rejects prefill with an UNSUPPORTED LlmError', () => {
expect(() => serializeRequest(request({ prefill: [{ type: 'text', text: 'Sure' }] })))
.toThrow(LlmError)
try {
serializeRequest(request({ prefill: [] }))
expect.unreachable()
} catch (error) {
expect((error as LlmError).code).toBe('UNSUPPORTED')
}
})
})
describe('review fixes: assistant content shapes', () => {