feat(llm-deepseek): configure max token defaults
This commit is contained in:
Yichen Jiang
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write packages/llm/llm-deepseek/README.md
|
||||
README.md: 7a2314ea2ca0fb6606310a4961fcbc658240a7b8
|
||||
README.zh.md: d73145f8b8a32d8a515b6b4c0e916f0a11cd4771
|
||||
README.md: 5a22689d0b15ae5de1b82e37cf8c2c283c14af97
|
||||
README.zh.md: 0fa8b16eee72eee741b07d27b1ed61297f5420c2
|
||||
|
||||
@@ -18,6 +18,7 @@ The package root exposes the Cordis plugin contract and `DeepSeekAdapter`; wire
|
||||
baseURL: !!js process.env.DEEPSEEK_BASE_URL # default: https://api.deepseek.com
|
||||
thinking: enabled # optional; provider default is enabled
|
||||
reasoningEffort: high # optional; off | high | max — omitted ⇒ high
|
||||
maxTokens: 256000 # optional positive per-request output cap; this is the default
|
||||
streamIdleTimeoutMs: 300000 # optional; positive finite Node timer delay; five-minute default
|
||||
retryPolicy: # optional; omission uses bounded normal defaults
|
||||
mode: always # normal | always
|
||||
@@ -25,7 +26,7 @@ The package root exposes the Cordis plugin contract and `DeepSeekAdapter`; wire
|
||||
initialDelayMs: 500
|
||||
maxDelayMs: 10000
|
||||
jitterRatio: 0.1
|
||||
defaultContextWindow: 256000 # optional positive-integer fallback for models without an exact value
|
||||
defaultContextWindow: 1000000 # optional positive-integer fallback; this is the default
|
||||
models: # optional; defaults to V4 Flash and V4 Pro
|
||||
- id: deepseek-v4-flash
|
||||
name: DeepSeek-V4-Flash
|
||||
@@ -34,9 +35,11 @@ The package root exposes the Cordis plugin contract and `DeepSeekAdapter`; wire
|
||||
contextWindow: 64000
|
||||
```
|
||||
|
||||
The plugin registers the single provider route `deepseek` together with its resolved `retryPolicy`. A request selects it with `provider: deepseek`; its `model` is passed through as the wire `model` string, so changing DeepSeek models does not require lifecycle-time registration. Omitting `models` advertises `deepseek-v4-flash` as `DeepSeek-V4-Flash` and `deepseek-v4-pro` as `DeepSeek-V4-Pro`, each with a 256,000-token context window; an explicit list replaces those defaults, while `models: []` advertises none. Catalog entries are exposed through `ctx.llm.listModels('deepseek')` for clients such as ACP editors and the Web selector, but remain advisory: unlisted model ids still pass through unchanged. An omitted entry name defaults to its id.
|
||||
The plugin registers the single provider route `deepseek` together with its resolved `retryPolicy`. A request selects it with `provider: deepseek`; its `model` is passed through as the wire `model` string, so changing DeepSeek models does not require lifecycle-time registration. Omitting `models` advertises `deepseek-v4-flash` as `DeepSeek-V4-Flash` and `deepseek-v4-pro` as `DeepSeek-V4-Pro`, each with a 1,000,000-token context window; an explicit list replaces those defaults, while `models: []` advertises none. Catalog entries are exposed through `ctx.llm.listModels('deepseek')` for clients such as ACP editors and the Web selector, but remain advisory: unlisted model ids still pass through unchanged. An omitted entry name defaults to its id.
|
||||
|
||||
`contextWindow` is optional per configured model and is not exposed through the advisory catalog. `ctx.llm.resolveModelInfo('deepseek', model).context` returns an exact model value first, then `defaultContextWindow` for an entry without capacity or an unlisted pass-through id. When neither value exists, `context` is absent without invalidating routing. Pressure-sensitive plugins therefore get deployment-owned capacity without treating the model selector as authoritative. Registering another adapter for `deepseek` throws `LlmError('DUPLICATE_ADAPTER')`.
|
||||
`contextWindow` is optional per configured model and is not exposed through the advisory catalog. `ctx.llm.resolveModelInfo('deepseek', model).context` returns an exact model value first, then `defaultContextWindow` for an entry without capacity or an unlisted pass-through id. The adapter default is 1,000,000; pressure-sensitive plugins therefore get deployment-owned capacity without treating the model selector as authoritative. Registering another adapter for `deepseek` throws `LlmError('DUPLICATE_ADAPTER')`.
|
||||
|
||||
`maxTokens` is the adapter-configured output cap for conversation requests and defaults to 256,000. Exact-model resolution exposes it as `defaultMaxTokens`; `LlmService` materializes that value into `GenerateOptions.maxTokens` before the agent loop writes `request/header`, so the wire request remains reconstructable. An explicit request or `AgentOptions.maxTokens` value wins and is serialized as `max_tokens`.
|
||||
|
||||
The same exact-model result exposes ordered `off`, `high`, and `max` efforts under `reasoning` for every pass-through model when deployment policy permits thinking. `reasoningEffort` selects the deployment default and falls back to `high` when omitted. `agent/request` can replace it on each conversation step; the resolved value is logged in `request/header`. `high` and `max` enable thinking and serialize as the official top-level `reasoning_effort`; adapter-owned `off` instead serializes `thinking.type: disabled` and omits `reasoning_effort`. An unsupported value fails with `UNSUPPORTED_REASONING_EFFORT` before network I/O.
|
||||
|
||||
|
||||
@@ -18,6 +18,7 @@ harness LLM（大语言模型）seam 的 DeepSeek chat-completions 适配器：
|
||||
baseURL: !!js process.env.DEEPSEEK_BASE_URL # default: https://api.deepseek.com
|
||||
thinking: enabled # optional; provider default is enabled
|
||||
reasoningEffort: high # optional; off | high | max — omitted ⇒ high
|
||||
maxTokens: 256000 # optional positive per-request output cap; this is the default
|
||||
streamIdleTimeoutMs: 300000 # optional; positive finite Node timer delay; five-minute default
|
||||
retryPolicy: # optional; omission uses bounded normal defaults
|
||||
mode: always # normal | always
|
||||
@@ -25,7 +26,7 @@ harness LLM（大语言模型）seam 的 DeepSeek chat-completions 适配器：
|
||||
initialDelayMs: 500
|
||||
maxDelayMs: 10000
|
||||
jitterRatio: 0.1
|
||||
defaultContextWindow: 256000 # optional positive-integer fallback for models without an exact value
|
||||
defaultContextWindow: 1000000 # optional positive-integer fallback; this is the default
|
||||
models: # optional; defaults to V4 Flash and V4 Pro
|
||||
- id: deepseek-v4-flash
|
||||
name: DeepSeek-V4-Flash
|
||||
@@ -34,9 +35,11 @@ harness LLM（大语言模型）seam 的 DeepSeek chat-completions 适配器：
|
||||
contextWindow: 64000
|
||||
```
|
||||
|
||||
该插件注册唯一提供方路由 `deepseek`，同时注册解析后的 `retryPolicy`。请求使用 `provider: deepseek` 选择该路由；其 `model` 会作为协议 `model` 字符串原样传递，因此更改 DeepSeek 模型不需要生命周期时注册。省略 `models` 会公布 `deepseek-v4-flash`（名称为 `DeepSeek-V4-Flash`）和 `deepseek-v4-pro`（名称为 `DeepSeek-V4-Pro`），两者的上下文窗口均为 256,000 token；显式列表会替换这些默认值，`models: []` 则不公布任何模型。Catalog 配置项通过 `ctx.llm.listModels('deepseek')` 公开给 ACP（Agent Client Protocol）编辑器和 Web 选择器等客户端，但仍只提供建议：未列出模型 id 仍原样传递。省略配置项 name 默认为其 id。
|
||||
该插件注册唯一提供方路由 `deepseek`，同时注册解析后的 `retryPolicy`。请求使用 `provider: deepseek` 选择该路由；其 `model` 会作为协议 `model` 字符串原样传递，因此更改 DeepSeek 模型不需要生命周期时注册。省略 `models` 会公布 `deepseek-v4-flash`（名称为 `DeepSeek-V4-Flash`）和 `deepseek-v4-pro`（名称为 `DeepSeek-V4-Pro`），两者的上下文窗口均为 1,000,000 token；显式列表会替换这些默认值，`models: []` 则不公布任何模型。Catalog 配置项通过 `ctx.llm.listModels('deepseek')` 公开给 ACP（Agent Client Protocol）编辑器和 Web 选择器等客户端，但仍只提供建议：未列出模型 id 仍原样传递。省略配置项 name 默认为其 id。
|
||||
|
||||
`contextWindow` 对每个已配置模型都可选，不会通过建议 catalog 公开。`ctx.llm.resolveModelInfo('deepseek', model).context` 先返回精确模型值，再对不含容量的配置项或未列出原样传递 id 返回 `defaultContextWindow`。两者都不存在时，`context` 字段缺失但不会使路由失效。因此，压力敏感插件可以获得由部署决定的容量，不会将模型 selector 视为权威。为 `deepseek` 注册另一个适配器会抛出 `LlmError('DUPLICATE_ADAPTER')`。
|
||||
`contextWindow` 对每个已配置模型都可选，不会通过建议 catalog 公开。`ctx.llm.resolveModelInfo('deepseek', model).context` 先返回精确模型值，再对不含容量的配置项或未列出原样传递 id 返回 `defaultContextWindow`。适配器默认值为 1,000,000；因此，压力敏感插件可以获得由部署决定的容量，不会将模型 selector 视为权威。为 `deepseek` 注册另一个适配器会抛出 `LlmError('DUPLICATE_ADAPTER')`。
|
||||
|
||||
`maxTokens` 是适配器为对话请求配置的输出上限，默认值为 256,000。确切模型解析会将其公开为 `defaultMaxTokens`；`LlmService` 会在 agent loop（智能体循环）写入 `request/header` 前，将该值填入 `GenerateOptions.maxTokens`，从而仍可根据持久记录重建协议请求。显式的请求值或 `AgentOptions.maxTokens` 值优先，并会序列化为 `max_tokens`。
|
||||
|
||||
同一确切模型结果会在部署策略允许思考时，为每个原样传递模型在 `reasoning` 下公开有序的 `off`、`high` 和 `max` 推理（reasoning）强度。`reasoningEffort` 选择部署默认值，省略时回退为 `high`。`agent/request` 可以在每个会话步骤替换它；解析后的值会记录在 `request/header`。`high` 和 `max` 会启用思考，并序列化为官方顶层 `reasoning_effort`；适配器持有的 `off` 则序列化为 `thinking.type: disabled`，且省略 `reasoning_effort`。不支持的值会在网络 I/O 前以 `UNSUPPORTED_REASONING_EFFORT` 失败。
|
||||
|
||||
|
||||
@@ -42,6 +42,8 @@ export interface DeepSeekAdapterOptions {
|
||||
baseURL: string
|
||||
/** Request defaults applied to every call (thinking mode, effort). */
|
||||
defaults?: RequestDefaults
|
||||
/** Default per-request output cap; explicit request values win. */
|
||||
maxTokens?: number
|
||||
/** Positive context capacity used when the selected model has no exact value. */
|
||||
defaultContextWindow?: number
|
||||
/** Advisory models exposed to discovery consumers; requests remain unrestricted. */
|
||||
@@ -54,6 +56,10 @@ export interface DeepSeekAdapterOptions {
|
||||
|
||||
/** Default maximum idle interval while an adapter stream read is outstanding. */
|
||||
export const DEFAULT_STREAM_IDLE_TIMEOUT_MS = 300_000
|
||||
/** Default combined request/response context capacity. */
|
||||
export const DEFAULT_CONTEXT_WINDOW = 1_000_000
|
||||
/** Default per-request output-token cap. */
|
||||
export const DEFAULT_MAX_TOKENS = 256_000
|
||||
const STREAM_IDLE_TIMEOUT_CODE = 'LLM_STREAM_IDLE_TIMEOUT'
|
||||
const OFF_REASONING_EFFORT = ReasoningEffortId('off')
|
||||
const HIGH_REASONING_EFFORT = ReasoningEffortId('high')
|
||||
@@ -120,6 +126,8 @@ export function httpErrorCode(status: number, error?: WireError['error']): strin
|
||||
export class DeepSeekAdapter extends LlmAdapter {
|
||||
private readonly streamIdleTimeoutMs: number
|
||||
private readonly retryPolicy: ResolvedRetryPolicy
|
||||
private readonly defaultContextWindow: number
|
||||
private readonly maxTokens: number
|
||||
|
||||
constructor(private readonly options: DeepSeekAdapterOptions) {
|
||||
super()
|
||||
@@ -128,10 +136,14 @@ export class DeepSeekAdapter extends LlmAdapter {
|
||||
&& options.defaults.reasoningEffort !== 'off') {
|
||||
throw new Error('llm-deepseek: only reasoningEffort "off" can be configured when thinking is disabled')
|
||||
}
|
||||
if (options.defaultContextWindow !== undefined
|
||||
&& (!Number.isInteger(options.defaultContextWindow) || options.defaultContextWindow <= 0)) {
|
||||
this.defaultContextWindow = options.defaultContextWindow ?? DEFAULT_CONTEXT_WINDOW
|
||||
if (!Number.isInteger(this.defaultContextWindow) || this.defaultContextWindow <= 0) {
|
||||
throw new Error('llm-deepseek: defaultContextWindow must be a positive integer')
|
||||
}
|
||||
this.maxTokens = options.maxTokens ?? DEFAULT_MAX_TOKENS
|
||||
if (!Number.isSafeInteger(this.maxTokens) || this.maxTokens <= 0) {
|
||||
throw new Error('llm-deepseek: maxTokens must be a positive safe integer')
|
||||
}
|
||||
this.streamIdleTimeoutMs = options.streamIdleTimeoutMs ?? DEFAULT_STREAM_IDLE_TIMEOUT_MS
|
||||
if (!Number.isFinite(this.streamIdleTimeoutMs)
|
||||
|| this.streamIdleTimeoutMs <= 0
|
||||
@@ -162,12 +174,13 @@ export class DeepSeekAdapter extends LlmAdapter {
|
||||
): Promise<LlmResolvedModelInfo> {
|
||||
const configured = this.options.models?.find(entry => entry.id === model)
|
||||
const contextWindow = configured?.contextWindow
|
||||
?? this.options.defaultContextWindow
|
||||
?? this.defaultContextWindow
|
||||
return Promise.resolve({
|
||||
...configured === undefined
|
||||
? { provider, id: model, name: model }
|
||||
: modelInfo(provider, configured),
|
||||
...contextWindow === undefined ? {} : { context: { contextWindow } },
|
||||
context: { contextWindow },
|
||||
defaultMaxTokens: this.maxTokens,
|
||||
...this.options.defaults?.thinking === 'disabled'
|
||||
? {
|
||||
reasoning: {
|
||||
@@ -231,7 +244,7 @@ export class DeepSeekAdapter extends LlmAdapter {
|
||||
}
|
||||
|
||||
private async * request(options: GenerateOptions, signal: AbortSignal): AsyncIterable<StreamChunk> {
|
||||
const body = serializeRequest(options, this.options.defaults ?? {})
|
||||
const body = serializeRequest(options, this.options.defaults, this.maxTokens)
|
||||
// Prepared outside the try so the TRANSPORT label below covers exactly the
|
||||
// transport boundary, never a serialization failure.
|
||||
const payload = JSON.stringify(body)
|
||||
|
||||
@@ -10,10 +10,20 @@ import z from 'schemastery'
|
||||
import { RetryPolicySchema } from '@deepseek-ai/dsh-llm'
|
||||
import type { RetryPolicyConfig } from '@deepseek-ai/dsh-llm'
|
||||
import { MAX_TIMER_DELAY_MS } from '@deepseek-ai/dsh-timeout'
|
||||
import { DEFAULT_STREAM_IDLE_TIMEOUT_MS, DeepSeekAdapter } from './adapter.ts'
|
||||
import {
|
||||
DEFAULT_CONTEXT_WINDOW,
|
||||
DEFAULT_MAX_TOKENS,
|
||||
DEFAULT_STREAM_IDLE_TIMEOUT_MS,
|
||||
DeepSeekAdapter,
|
||||
} from './adapter.ts'
|
||||
import type { DeepSeekCatalogModel } from './adapter.ts'
|
||||
|
||||
export { DeepSeekAdapter } from './adapter.ts'
|
||||
export {
|
||||
DEFAULT_CONTEXT_WINDOW,
|
||||
DEFAULT_MAX_TOKENS,
|
||||
DEFAULT_STREAM_IDLE_TIMEOUT_MS,
|
||||
DeepSeekAdapter,
|
||||
} from './adapter.ts'
|
||||
export type { DeepSeekAdapterOptions, DeepSeekCatalogModel } from './adapter.ts'
|
||||
export type { RequestDefaults } from './serialize.ts'
|
||||
export type * from './types.ts'
|
||||
@@ -22,8 +32,8 @@ export const name = 'llm-deepseek'
|
||||
export const inject = ['llm']
|
||||
|
||||
const DEFAULT_MODELS: DeepSeekCatalogModel[] = [
|
||||
{ id: 'deepseek-v4-flash', name: 'DeepSeek-V4-Flash', contextWindow: 256_000 },
|
||||
{ id: 'deepseek-v4-pro', name: 'DeepSeek-V4-Pro', contextWindow: 256_000 },
|
||||
{ id: 'deepseek-v4-flash', name: 'DeepSeek-V4-Flash', contextWindow: DEFAULT_CONTEXT_WINDOW },
|
||||
{ id: 'deepseek-v4-pro', name: 'DeepSeek-V4-Pro', contextWindow: DEFAULT_CONTEXT_WINDOW },
|
||||
]
|
||||
|
||||
/**
|
||||
@@ -42,7 +52,9 @@ export interface Config {
|
||||
thinking?: 'enabled' | 'disabled'
|
||||
/** Default thinking effort (default `high`); `off` disables thinking per request. */
|
||||
reasoningEffort?: 'off' | 'high' | 'max'
|
||||
/** Positive context capacity used when the selected model has no exact value. */
|
||||
/** Default per-request output cap (default 256,000); explicit request values win. */
|
||||
maxTokens?: number
|
||||
/** Positive context capacity used when the selected model has no exact value (default 1,000,000). */
|
||||
defaultContextWindow?: number
|
||||
/** Advisory models shown by discovery consumers; defaults to V4 Flash and V4 Pro. */
|
||||
models?: DeepSeekCatalogModel[]
|
||||
@@ -64,7 +76,8 @@ export const Config: z<Config> = z.object({
|
||||
baseURL: z.string(),
|
||||
thinking: z.union(['enabled', 'disabled']),
|
||||
reasoningEffort: z.union(['off', 'high', 'max']),
|
||||
defaultContextWindow: z.number().step(1).min(1),
|
||||
maxTokens: z.number().step(1).min(1).max(Number.MAX_SAFE_INTEGER).default(DEFAULT_MAX_TOKENS),
|
||||
defaultContextWindow: z.number().step(1).min(1).default(DEFAULT_CONTEXT_WINDOW),
|
||||
models: z.array(catalogModel).default(DEFAULT_MODELS),
|
||||
streamIdleTimeoutMs: z.number().min(Number.MIN_VALUE).max(MAX_TIMER_DELAY_MS).default(DEFAULT_STREAM_IDLE_TIMEOUT_MS),
|
||||
retryPolicy: RetryPolicySchema,
|
||||
@@ -116,9 +129,8 @@ export function apply(ctx: Context, config: Config): void {
|
||||
thinking: config.thinking,
|
||||
reasoningEffort: config.reasoningEffort,
|
||||
},
|
||||
...config.defaultContextWindow === undefined
|
||||
? {}
|
||||
: { defaultContextWindow: config.defaultContextWindow },
|
||||
maxTokens: config.maxTokens ?? DEFAULT_MAX_TOKENS,
|
||||
defaultContextWindow: config.defaultContextWindow ?? DEFAULT_CONTEXT_WINDOW,
|
||||
models: resolveModels(config.models),
|
||||
streamIdleTimeoutMs: config.streamIdleTimeoutMs ?? DEFAULT_STREAM_IDLE_TIMEOUT_MS,
|
||||
...config.retryPolicy === undefined ? {} : { retryPolicy: config.retryPolicy },
|
||||
|
||||
@@ -137,9 +137,14 @@ export function serializeMessages(messages: Message[]): WireMessage[] {
|
||||
* provider defaults apply.
|
||||
* @param options - the harness request (model, history, system, tools, sampling).
|
||||
* @param defaults - adapter-level thinking defaults; undefined fields put nothing on the wire.
|
||||
* @param defaultMaxTokens - adapter output default used only when the request omits a cap.
|
||||
* @returns the chat-completions request body.
|
||||
*/
|
||||
export function serializeRequest(options: GenerateOptions, defaults: RequestDefaults = {}): WireRequest {
|
||||
export function serializeRequest(
|
||||
options: GenerateOptions,
|
||||
defaults: RequestDefaults = {},
|
||||
defaultMaxTokens?: number,
|
||||
): WireRequest {
|
||||
const messages: WireMessage[] = []
|
||||
if (options.system !== undefined) {
|
||||
messages.push({ role: 'system', content: options.system })
|
||||
@@ -157,6 +162,7 @@ export function serializeRequest(options: GenerateOptions, defaults: RequestDefa
|
||||
// A short title budget must produce visible text; conversation and
|
||||
// compaction calls continue to inherit the adapter's thinking defaults.
|
||||
const resolvedThinking = resolveThinking(options, defaults)
|
||||
const maxTokens = options.maxTokens ?? defaultMaxTokens
|
||||
|
||||
return {
|
||||
model: options.model,
|
||||
@@ -169,7 +175,7 @@ export function serializeRequest(options: GenerateOptions, defaults: RequestDefa
|
||||
: {},
|
||||
...tools !== undefined && tools.length > 0 ? { tools } : {},
|
||||
...options.temperature !== undefined ? { temperature: options.temperature } : {},
|
||||
...options.maxTokens !== undefined ? { max_tokens: options.maxTokens } : {},
|
||||
...maxTokens === undefined ? {} : { max_tokens: maxTokens },
|
||||
...options.stop !== undefined ? { stop: options.stop } : {},
|
||||
}
|
||||
}
|
||||
|
||||
@@ -124,6 +124,7 @@ describe('DeepSeekAdapter against a mock server', () => {
|
||||
// The wire request carried the auth header contents we configured.
|
||||
expect(server.requests[0]).toMatchObject({
|
||||
model: 'deepseek-v4-flash',
|
||||
max_tokens: 256_000,
|
||||
reasoning_effort: 'high',
|
||||
stream: true,
|
||||
stream_options: { include_usage: true },
|
||||
@@ -232,6 +233,20 @@ describe('DeepSeekAdapter against a mock server', () => {
|
||||
})
|
||||
})
|
||||
|
||||
it('uses the configured maxTokens default and preserves an explicit request cap', async () => {
|
||||
const server = await mockServer([
|
||||
{ kind: 'sse', events: textEvents },
|
||||
{ kind: 'sse', events: textEvents },
|
||||
])
|
||||
const ctx = await harness(server.url, { maxTokens: 32_000 })
|
||||
|
||||
await assemble(ctx, { model: 'deepseek-v4-flash', messages: [] })
|
||||
await assemble(ctx, { model: 'deepseek-v4-flash', messages: [], maxTokens: 8_192 })
|
||||
|
||||
expect(server.requests[0]).toMatchObject({ max_tokens: 32_000 })
|
||||
expect(server.requests[1]).toMatchObject({ max_tokens: 8_192 })
|
||||
})
|
||||
|
||||
it('publishes only off and omits the wire effort when thinking is disabled', async () => {
|
||||
const server = await mockServer([{ kind: 'sse', events: textEvents }])
|
||||
const ctx = await harness(server.url, { thinking: 'disabled' })
|
||||
@@ -666,7 +681,8 @@ describe('plugin registration and config', () => {
|
||||
provider: 'deepseek',
|
||||
id: 'deepseek-v4-flash',
|
||||
name: 'DeepSeek-V4-Flash',
|
||||
context: { contextWindow: 256_000 },
|
||||
context: { contextWindow: 1_000_000 },
|
||||
defaultMaxTokens: 256_000,
|
||||
reasoning: {
|
||||
efforts: [
|
||||
{ id: ReasoningEffortId('off'), name: 'Off' },
|
||||
@@ -795,7 +811,10 @@ describe('plugin registration and config', () => {
|
||||
description: 'Higher reasoning budget',
|
||||
})
|
||||
await expect(ctx.llm.resolveModelInfo('deepseek', 'arbitrary-unlisted'))
|
||||
.resolves.not.toHaveProperty('context')
|
||||
.resolves.toMatchObject({
|
||||
context: { contextWindow: 1_000_000 },
|
||||
defaultMaxTokens: 256_000,
|
||||
})
|
||||
})
|
||||
|
||||
it('uses exact model capacity before the adapter-wide default', async () => {
|
||||
@@ -880,6 +899,26 @@ describe('plugin registration and config', () => {
|
||||
},
|
||||
)
|
||||
|
||||
it.each([0, 1.5, Number.MAX_SAFE_INTEGER + 1])(
|
||||
'rejects invalid adapter-wide maxTokens %s',
|
||||
async (maxTokens) => {
|
||||
expect(() => new DeepSeekAdapter({
|
||||
apiKey: 'k',
|
||||
baseURL: 'http://127.0.0.1:1',
|
||||
maxTokens,
|
||||
})).toThrow(/maxTokens must be a positive safe integer/)
|
||||
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await expect(ctx.plugin(LlmDeepSeek, {
|
||||
apiKey: 'k',
|
||||
baseURL: 'http://127.0.0.1:1',
|
||||
maxTokens,
|
||||
})).rejects.toThrow(/maxTokens/)
|
||||
expect(ctx.llm.listProviders()).toEqual([])
|
||||
},
|
||||
)
|
||||
|
||||
it('falls back to DEEPSEEK_API_KEY and DEEPSEEK_BASE_URL env vars', async () => {
|
||||
vi.stubEnv('DEEPSEEK_API_KEY', 'env-key')
|
||||
vi.stubEnv('DEEPSEEK_BASE_URL', 'http://127.0.0.1:1')
|
||||
|
||||
@@ -170,6 +170,13 @@ describe('serializeRequest', () => {
|
||||
expect(wire.stop).toEqual(['END'])
|
||||
})
|
||||
|
||||
it('uses the adapter maxTokens default only when the request omits a cap', () => {
|
||||
expect(serializeRequest(request({ messages: history }), {}, 256_000).max_tokens)
|
||||
.toBe(256_000)
|
||||
expect(serializeRequest(request({ messages: history, maxTokens: 8_192 }), {}, 256_000).max_tokens)
|
||||
.toBe(8_192)
|
||||
})
|
||||
|
||||
it('maps tools to the wire function shape', () => {
|
||||
const wire = serializeRequest(request({
|
||||
messages: history,
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write packages/llm/llm/README.md
|
||||
README.md: d343449d1530bf70a3a8c57f883894e29c42d18f
|
||||
README.zh.md: 4dc4a0ca06378116d05fdb4b9b048738930511fd
|
||||
README.md: 3ffcfb59fa7d3e3077a59d0b0c8ebd9afa590e7e
|
||||
README.zh.md: df44b2bad1d5fa5c03dff86de584bfff63dbf297
|
||||
|
||||
@@ -14,8 +14,8 @@ An adapter registry plus a single streaming call surface, interceptable via a wa
|
||||
- `ctx.llm.listProviders(): LlmProviderInfo[]` Describe registered provider routes in registration order.
|
||||
- `ctx.llm.providerRetryPolicy(provider: string): ResolvedRetryPolicy` Return the provider-owned retry policy captured during registration, with normal defaults resolved.
|
||||
- `ctx.llm.listModels(provider: string): Promise<LlmModelInfo[]>` Discover the models one registered provider currently advertises.
|
||||
- `ctx.llm.resolveModelInfo(provider: string, model: string, signal?: AbortSignal): Promise<LlmResolvedModelInfo>` Resolve validated exact-model identity plus available context and reasoning metadata from the owning adapter, with optional cancellation for asynchronous adapters.
|
||||
- `ctx.llm.resolveCallConfig(config: LlmCallConfig, signal?: AbortSignal): Promise<LlmCallConfig>` Validate an explicit effort and materialize an adapter-configured default without clamping.
|
||||
- `ctx.llm.resolveModelInfo(provider: string, model: string, signal?: AbortSignal): Promise<LlmResolvedModelInfo>` Resolve validated exact-model identity plus available context, output-default, and reasoning metadata from the owning adapter, with optional cancellation for asynchronous adapters.
|
||||
- `ctx.llm.resolveCallConfig(config: LlmCallConfig, signal?: AbortSignal): Promise<LlmCallConfig>` Validate an explicit effort and materialize adapter-configured call defaults without clamping.
|
||||
- `ctx.llm.prepareCall(config: LlmCallConfig, signal?: AbortSignal): Promise<PreparedLlmCall>` Resolve a config and capture its current adapter registration as one cancellable, one-shot call.
|
||||
- `ctx.llm.stream(options: GenerateOptions): AsyncIterable<StreamChunk>` Stream one model call as raw chunks (token-level deltas). Consumers assemble the chunks into blocks/messages with `BlockAssembler`.
|
||||
|
||||
@@ -23,9 +23,9 @@ An adapter registry plus a single streaming call surface, interceptable via a wa
|
||||
|
||||
Provider and model metadata is a discovery surface, not a routing whitelist. `registerAdapter()` still owns provider exclusivity and captures the adapter's retry policy for each route, while an adapter may accept model ids absent from `listModels()`; consumers must not reject a request because its model is unlisted. Returned selector metadata is detached and invalid or duplicate adapter entries fail with `INVALID_ADAPTER` or `INVALID_CATALOG`.
|
||||
|
||||
Exact-model metadata is a separate correctness query, not a catalog decoration or global LLM setting. `resolveModelInfo()` asks the adapter that owns the exact provider/model route once; an adapter can describe an unlisted dynamic model, and absent `context` or `reasoning` fields mean only that those capabilities are unavailable. Invalid identity, context, or reasoning metadata fails with `INVALID_MODEL_INFO`, `INVALID_MODEL_CONTEXT`, or `INVALID_MODEL_REASONING`.
|
||||
Exact-model metadata is a separate correctness query, not a catalog decoration or global LLM setting. `resolveModelInfo()` asks the adapter that owns the exact provider/model route once; an adapter can describe an unlisted dynamic model, and absent `context`, `defaultMaxTokens`, or `reasoning` fields preserve unknown capacity, provider-owned output defaults, or unavailable reasoning capability. Invalid identity, context, output default, or reasoning metadata fails with `INVALID_MODEL_INFO`, `INVALID_MODEL_CONTEXT`, `INVALID_MODEL_MAX_TOKENS`, or `INVALID_MODEL_REASONING`.
|
||||
|
||||
Reasoning identifiers are opaque adapter-owned strings rather than a core enum. An adapter publishes its ordered selectable list, including an `off` id when that model's capability API exposes one. `resolveCallConfig()` accepts only an exact advertised identifier, materializes `defaultEffort` when present, and otherwise preserves the provider default. Asynchronous model resolvers receive the caller's signal and must settle promptly after cancellation. `prepareCall()` additionally retains the exact adapter registration through header logging and terminal dispatch, so HMR cannot combine one adapter's capability result with another adapter's request; reusing its one-shot handle or changing its call-config fields fails with `INVALID_PREPARED_CALL`. An unsupported explicit or configured effort fails with `UNSUPPORTED_REASONING_EFFORT` before provider I/O.
|
||||
`defaultMaxTokens` is an adapter-configured per-request output cap, not a model hard limit. `resolveCallConfig()` materializes it only when the request omits `maxTokens`; an explicit cap wins. Reasoning identifiers are opaque adapter-owned strings rather than a core enum: the same resolution accepts only an exact advertised identifier, materializes `defaultEffort` when present, and otherwise preserves the provider default. Asynchronous model resolvers receive the caller's signal and must settle promptly after cancellation. `prepareCall()` additionally retains the exact adapter registration through header logging and terminal dispatch, so HMR cannot combine one adapter's capability result with another adapter's request; reusing its one-shot handle or changing its call-config fields fails with `INVALID_PREPARED_CALL`. An unsupported explicit or configured effort fails with `UNSUPPORTED_REASONING_EFFORT` before provider I/O.
|
||||
|
||||
### Events
|
||||
|
||||
@@ -35,7 +35,7 @@ Reasoning identifiers are opaque adapter-owned strings rather than a core enum.
|
||||
|
||||
### Extension points
|
||||
|
||||
- Subclass `LlmAdapter` and call `ctx.llm.registerAdapter(providers, adapter)` to add one or more provider routes. `GenerateOptions.provider` selects the adapter; `GenerateOptions.model` is adapter-owned and may be resolved dynamically. Override `providerRetryPolicy()` to supply provider-owned recovery configuration, `providerInfo()` and asynchronous `listModels()` to expose selector metadata, then implement `resolveModel()` when exact identity, capacity, or selectable reasoning efforts are available; an asynchronous resolver must honor its optional cancellation signal. The defaults use bounded normal retry policy, use the route and model ids as names, advertise no models, and return no capacity or reasoning metadata.
|
||||
- Subclass `LlmAdapter` and call `ctx.llm.registerAdapter(providers, adapter)` to add one or more provider routes. `GenerateOptions.provider` selects the adapter; `GenerateOptions.model` is adapter-owned and may be resolved dynamically. Override `providerRetryPolicy()` to supply provider-owned recovery configuration, `providerInfo()` and asynchronous `listModels()` to expose selector metadata, then implement `resolveModel()` when exact identity, capacity, an output default, or selectable reasoning efforts are available; an asynchronous resolver must honor its optional cancellation signal. The defaults use bounded normal retry policy, use the route and model ids as names, advertise no models, and return no capacity, output default, or reasoning metadata.
|
||||
- Wrap `llm/stream` via `ctx.on()` waterfall listeners for caching, logging, or routing. A wrapper that retries after emitting a chunk has no durable attempt boundary; shipped agent retry policy therefore uses `agent/request-error` instead.
|
||||
|
||||
### Messages (`message.ts`) and content blocks (`types.ts`)
|
||||
@@ -48,7 +48,7 @@ Streaming is a raw chunk protocol (`block-start`, `text-delta`, `reasoning-delta
|
||||
|
||||
### Call configuration (`call-config.ts`)
|
||||
|
||||
`LlmCallConfig` is the provider, model, optional adapter-owned reasoning effort, and sampling scalars of one conversation's requests (`provider`, `model`, `reasoningEffort`, `temperature`, `maxTokens`, `stop` — each mapping 1:1 onto the same-named `GenerateOptions` field). It is per-conversation state recorded in the session log as part of the request header (see the dsh-session `request/header` events), never a silently-adjustable per-call knob: the `agent/request` waterfall proposes a replacement, `prepareCall()` validates and defaults it under the turn signal, and the loop logs the effective value before using the prepared call's registration-bound stream. `callConfigEquals(a, b)` is the field-wise real-change detector; `deepFreeze(value)` is the ownership helper the loop applies to every built request before dispatch (`llm/stream` listeners and adapters read, never rewrite). `markAgentLoopRequest()` gives that exact object process-local loop provenance, and `isAgentLoopRequest()` lets observers distinguish it from independently logged auxiliary calls that may also be frozen and session-associated. `GenerateOptions.purpose` classifies logged auxiliary compaction and session-title calls so adapters can apply purpose-specific transport policy without changing ordinary conversation requests.
|
||||
`LlmCallConfig` is the provider, model, optional adapter-owned reasoning effort, and sampling scalars of one conversation's requests (`provider`, `model`, `reasoningEffort`, `temperature`, `maxTokens`, `stop` — each mapping 1:1 onto the same-named `GenerateOptions` field). It is per-conversation state recorded in the session log as part of the request header (see the dsh-session `request/header` events), never a silently-adjustable per-call knob: the `agent/request` waterfall proposes a replacement, `prepareCall()` validates it and materializes adapter defaults under the turn signal, and the loop logs the effective value before using the prepared call's registration-bound stream. `callConfigEquals(a, b)` is the field-wise real-change detector; `deepFreeze(value)` is the ownership helper the loop applies to every built request before dispatch (`llm/stream` listeners and adapters read, never rewrite). `markAgentLoopRequest()` gives that exact object process-local loop provenance, and `isAgentLoopRequest()` lets observers distinguish it from independently logged auxiliary calls that may also be frozen and session-associated. `GenerateOptions.purpose` classifies logged auxiliary compaction and session-title calls so adapters can apply purpose-specific transport policy without changing ordinary conversation requests.
|
||||
|
||||
### App attribution (`attribution.ts`)
|
||||
|
||||
|
||||
@@ -14,8 +14,8 @@
|
||||
- `ctx.llm.listProviders(): LlmProviderInfo[]` 按注册顺序描述已注册提供方路由。
|
||||
- `ctx.llm.providerRetryPolicy(provider: string): ResolvedRetryPolicy` 返回注册时捕获的提供方重试策略，并解析 normal 默认值。
|
||||
- `ctx.llm.listModels(provider: string): Promise<LlmModelInfo[]>` 发现某个已注册提供方当前公布的模型。
|
||||
- `ctx.llm.resolveModelInfo(provider: string, model: string, signal?: AbortSignal): Promise<LlmResolvedModelInfo>` 从拥有精确路由的适配器解析经校验的确切模型身份、可用上下文和推理（reasoning）元数据；异步适配器可选地支持取消。
|
||||
- `ctx.llm.resolveCallConfig(config: LlmCallConfig, signal?: AbortSignal): Promise<LlmCallConfig>` 校验显式推理强度，并填入适配器配置的默认值，但不自动调整。
|
||||
- `ctx.llm.resolveModelInfo(provider: string, model: string, signal?: AbortSignal): Promise<LlmResolvedModelInfo>` 从拥有精确路由的适配器解析经校验的确切模型身份，以及可用上下文、输出默认值和推理（reasoning）元数据；异步适配器可选地支持取消。
|
||||
- `ctx.llm.resolveCallConfig(config: LlmCallConfig, signal?: AbortSignal): Promise<LlmCallConfig>` 校验显式推理强度，并填入适配器配置的调用默认值，但不自动调整。
|
||||
- `ctx.llm.prepareCall(config: LlmCallConfig, signal?: AbortSignal): Promise<PreparedLlmCall>` 解析配置并将其当前适配器注册捕获为一次可取消、一次性调用。
|
||||
- `ctx.llm.stream(options: GenerateOptions): AsyncIterable<StreamChunk>` 将一次模型调用流式输出为原始分片（token 级增量）。消费方使用 `BlockAssembler` 将分片组装为块／消息。
|
||||
|
||||
@@ -23,9 +23,9 @@
|
||||
|
||||
提供方与模型元数据是发现接口，不是路由白名单。`registerAdapter()` 仍拥有提供方排他性，并为每条路由捕获适配器的重试策略；适配器则可以接受 `listModels()` 中不存在的模型 id，消费方禁止因模型未列出而拒绝请求。返回的 selector 元数据与输入脱离，无效或重复适配器配置项会以 `INVALID_ADAPTER` 或 `INVALID_CATALOG` 失败。
|
||||
|
||||
确切模型元数据是独立的正确性查询，不是 catalog 装饰或全局 LLM 设置。`resolveModelInfo()` 会向拥有精确提供方／模型路由的适配器查询一次；适配器可以描述未列出的动态模型，缺少 `context` 或 `reasoning` 字段只表示相应能力不可用。无效的身份、上下文或推理元数据会以 `INVALID_MODEL_INFO`、`INVALID_MODEL_CONTEXT` 或 `INVALID_MODEL_REASONING` 失败。
|
||||
确切模型元数据是独立的正确性查询，不是 catalog 装饰或全局 LLM 设置。`resolveModelInfo()` 会向拥有精确提供方／模型路由的适配器查询一次；适配器可以描述未列出的动态模型，缺少 `context`、`defaultMaxTokens` 或 `reasoning` 字段会分别保留未知容量、提供方持有的输出默认值或不可用的推理能力。无效的身份、上下文、输出默认值或推理元数据会以 `INVALID_MODEL_INFO`、`INVALID_MODEL_CONTEXT`、`INVALID_MODEL_MAX_TOKENS` 或 `INVALID_MODEL_REASONING` 失败。
|
||||
|
||||
推理标识符是由适配器持有的不透明字符串，而非核心枚举。适配器会公布有序可选列表；模型能力 API 提供 `off` id 时，列表也会包含它。`resolveCallConfig()` 只接受与已公布标识符完全一致的值，在存在 `defaultEffort` 时填入它，否则保留提供方默认值。异步模型解析器会接收调用方的 signal，并且必须在取消后迅速结束。`prepareCall()` 还会让精确适配器注册跨越请求头记录和最终分派，因此 HMR（热模块替换）不会将一个适配器的能力结果与另一个适配器的请求混用；复用其一次性句柄或更改调用配置字段会以 `INVALID_PREPARED_CALL` 失败。不支持的显式或配置推理强度会在提供方 I/O 前以 `UNSUPPORTED_REASONING_EFFORT` 失败。
|
||||
`defaultMaxTokens` 是适配器配置的单次请求输出上限，不是模型硬上限。仅当请求省略 `maxTokens` 时，`resolveCallConfig()` 才会填入该值；显式上限优先。推理标识符是由适配器持有的不透明字符串，而非核心枚举：同一次解析只接受与已公布标识符完全一致的值，在存在 `defaultEffort` 时填入它，否则保留提供方默认值。异步模型解析器会接收调用方的 signal，并且必须在取消后迅速结束。`prepareCall()` 还会让精确适配器注册跨越请求头记录和最终分派，因此 HMR（热模块替换）不会将一个适配器的能力结果与另一个适配器的请求混用；复用其一次性句柄或更改调用配置字段会以 `INVALID_PREPARED_CALL` 失败。不支持的显式或配置推理强度会在提供方 I/O 前以 `UNSUPPORTED_REASONING_EFFORT` 失败。
|
||||
|
||||
### 事件
|
||||
|
||||
@@ -35,7 +35,7 @@
|
||||
|
||||
### 扩展点
|
||||
|
||||
- 继承 `LlmAdapter` 并调用 `ctx.llm.registerAdapter(providers, adapter)`，添加一条或多条提供方路由。`GenerateOptions.provider` 选择适配器；`GenerateOptions.model` 属于适配器，可以动态解析。覆盖 `providerRetryPolicy()` 以提供由提供方持有的恢复配置，覆盖 `providerInfo()` 和异步 `listModels()` 以公开 selector 元数据；精确身份、容量或可选推理强度可用时，实现 `resolveModel()`；异步解析器必须响应其可选的取消 signal。默认实现使用有界的 normal 重试策略，将路由和模型 id 用作名称，不公布模型，也不返回容量或推理元数据。
|
||||
- 继承 `LlmAdapter` 并调用 `ctx.llm.registerAdapter(providers, adapter)`，添加一条或多条提供方路由。`GenerateOptions.provider` 选择适配器；`GenerateOptions.model` 属于适配器，可以动态解析。覆盖 `providerRetryPolicy()` 以提供由提供方持有的恢复配置，覆盖 `providerInfo()` 和异步 `listModels()` 以公开 selector 元数据；精确身份、容量、输出默认值或可选推理强度可用时，实现 `resolveModel()`；异步解析器必须响应其可选的取消 signal。默认实现使用有界的 normal 重试策略，将路由和模型 id 用作名称，不公布模型，也不返回容量、输出默认值或推理元数据。
|
||||
- 包装 `llm/stream` 时，通过 `ctx.on()` waterfall listener 实现缓存、日志或路由。发出分片后重试的包装层没有持久尝试边界；因此已发布 agent 重试策略改用 `agent/request-error`。
|
||||
|
||||
### 消息（`message.ts`）与内容块（`types.ts`）
|
||||
@@ -48,7 +48,7 @@
|
||||
|
||||
### 调用配置（`call-config.ts`）
|
||||
|
||||
`LlmCallConfig` 是一个会话中各次请求的提供方、模型、可选的适配器持有推理强度和采样标量（`provider`、`model`、`reasoningEffort`、`temperature`、`maxTokens`、`stop`，每个都与同名 `GenerateOptions` 字段 1:1 映射）。它是作为请求标头一部分记录在会话日志中的每会话状态（见 dsh-session `request/header` 事件），绝不是可静默调整的每次调用旋钮：`agent/request` waterfall 会提议替换，`prepareCall()` 在轮次 signal 控制下校验并填入默认值，loop 随后记录生效值，再使用已准备调用中与注册绑定的流。`callConfigEquals(a, b)` 是逐字段真实变更检测器；`deepFreeze(value)` 是 loop 在 dispatch 前对每个已构建请求应用的所有权 helper（`llm/stream` listener 与适配器只读，绝不改写）。`markAgentLoopRequest()` 为该精确对象添加进程本地 loop 溯源，`isAgentLoopRequest()` 让观测方可以将其与同样可能冻结并关联会话、但独立记录的辅助调用区分。`GenerateOptions.purpose` 对已记录辅助压缩与会话标题调用分类，让适配器可以应用目的特定传输策略，而不改变普通会话请求。
|
||||
`LlmCallConfig` 是一个会话中各次请求的提供方、模型、可选的适配器持有推理强度和采样标量（`provider`、`model`、`reasoningEffort`、`temperature`、`maxTokens`、`stop`，每个都与同名 `GenerateOptions` 字段 1:1 映射）。它是作为请求标头一部分记录在会话日志中的每会话状态（见 dsh-session `request/header` 事件），绝不是可静默调整的每次调用旋钮：`agent/request` waterfall 会提议替换，`prepareCall()` 在轮次 signal 控制下校验它并填入适配器默认值，loop 随后记录生效值，再使用已准备调用中与注册绑定的流。`callConfigEquals(a, b)` 是逐字段真实变更检测器；`deepFreeze(value)` 是 loop 在 dispatch 前对每个已构建请求应用的所有权 helper（`llm/stream` listener 与适配器只读，绝不改写）。`markAgentLoopRequest()` 为该精确对象添加进程本地 loop 溯源，`isAgentLoopRequest()` 让观测方可以将其与同样可能冻结并关联会话、但独立记录的辅助调用区分。`GenerateOptions.purpose` 对已记录辅助压缩与会话标题调用分类，让适配器可以应用目的特定传输策略，而不改变普通会话请求。
|
||||
|
||||
### 应用归因（`attribution.ts`）
|
||||
|
||||
|
||||
@@ -166,7 +166,7 @@ export abstract class LlmAdapter {
|
||||
* @param model - exact model id passed to {@link GenerateOptions.model}.
|
||||
* @param _signal - cancellation for this exact-model lookup; asynchronous
|
||||
* implementations must settle promptly after it aborts.
|
||||
* @returns provider/model identity plus any context and reasoning metadata.
|
||||
* @returns provider/model identity plus any context, call-default, and reasoning metadata.
|
||||
*/
|
||||
resolveModel(
|
||||
provider: string,
|
||||
@@ -331,12 +331,21 @@ export class LlmService extends Service {
|
||||
'INVALID_MODEL_CONTEXT',
|
||||
)
|
||||
}
|
||||
const defaultMaxTokens = resolved.defaultMaxTokens
|
||||
if (defaultMaxTokens !== undefined
|
||||
&& (!Number.isSafeInteger(defaultMaxTokens) || defaultMaxTokens <= 0)) {
|
||||
throw new LlmError(
|
||||
`adapter returned invalid default maxTokens for provider "${provider}" model "${model}"`,
|
||||
'INVALID_MODEL_MAX_TOKENS',
|
||||
)
|
||||
}
|
||||
const info: LlmResolvedModelInfo = {
|
||||
provider,
|
||||
id: model,
|
||||
name: resolved.name,
|
||||
...resolved.description === undefined ? {} : { description: resolved.description },
|
||||
...context === undefined ? {} : { context: { contextWindow: context.contextWindow } },
|
||||
...defaultMaxTokens === undefined ? {} : { defaultMaxTokens },
|
||||
}
|
||||
const reasoning = resolved.reasoning
|
||||
if (reasoning === undefined) return info
|
||||
@@ -385,7 +394,7 @@ export class LlmService extends Service {
|
||||
|
||||
/**
|
||||
* Validate a conversation call config against its exact model capability and
|
||||
* materialize an adapter-configured default. Unsupported explicit efforts
|
||||
* materialize adapter-configured defaults. Unsupported explicit efforts
|
||||
* reject before provider I/O; no clamping or aliasing is performed. This
|
||||
* standalone query does not bind a later dispatch; use {@link prepareCall}
|
||||
* when logging and streaming must share one adapter registration.
|
||||
@@ -402,8 +411,12 @@ export class LlmService extends Service {
|
||||
config: LlmCallConfig,
|
||||
signal?: AbortSignal,
|
||||
): Promise<LlmCallConfig> {
|
||||
const reasoning = (await this.resolveModelInfoFor(registration, config.model, signal)).reasoning
|
||||
const requested = config.reasoningEffort
|
||||
const info = await this.resolveModelInfoFor(registration, config.model, signal)
|
||||
const defaulted = config.maxTokens === undefined && info.defaultMaxTokens !== undefined
|
||||
? { ...config, maxTokens: info.defaultMaxTokens }
|
||||
: config
|
||||
const reasoning = info.reasoning
|
||||
const requested = defaulted.reasoningEffort
|
||||
if (reasoning === undefined) {
|
||||
if (requested !== undefined) {
|
||||
throw new LlmError(
|
||||
@@ -411,17 +424,17 @@ export class LlmService extends Service {
|
||||
'UNSUPPORTED_REASONING_EFFORT',
|
||||
)
|
||||
}
|
||||
return config
|
||||
return defaulted
|
||||
}
|
||||
const effective = requested ?? reasoning.defaultEffort
|
||||
if (effective === undefined) return config
|
||||
if (effective === undefined) return defaulted
|
||||
if (!reasoning.efforts.some(effort => effort.id === effective)) {
|
||||
throw new LlmError(
|
||||
`provider "${config.provider}" model "${config.model}" does not support reasoning effort "${effective}"`,
|
||||
'UNSUPPORTED_REASONING_EFFORT',
|
||||
)
|
||||
}
|
||||
return requested === effective ? config : { ...config, reasoningEffort: effective }
|
||||
return requested === effective ? defaulted : { ...defaulted, reasoningEffort: effective }
|
||||
}
|
||||
|
||||
/**
|
||||
|
||||
@@ -162,6 +162,8 @@ export interface LlmModelReasoningInfo {
|
||||
export interface LlmResolvedModelInfo extends LlmModelInfo {
|
||||
/** Provider-owned context capacity when known. */
|
||||
context?: LlmModelContext
|
||||
/** Adapter-configured per-request output cap materialized when callers omit one. */
|
||||
defaultMaxTokens?: number
|
||||
/** Adapter-owned selectable reasoning levels when exposed. */
|
||||
reasoning?: LlmModelReasoningInfo
|
||||
}
|
||||
|
||||
@@ -60,6 +60,7 @@ class CatalogAdapter extends ScriptedAdapter {
|
||||
private readonly models: readonly LlmModelInfo[],
|
||||
private readonly contexts: Readonly<Record<string, LlmModelContext>> = {},
|
||||
private readonly reasoning: Readonly<Record<string, LlmModelReasoningInfo>> = {},
|
||||
private readonly defaultMaxTokens: Readonly<Record<string, number>> = {},
|
||||
) {
|
||||
super(SCRIPT)
|
||||
}
|
||||
@@ -82,6 +83,7 @@ class CatalogAdapter extends ScriptedAdapter {
|
||||
name: model,
|
||||
...this.contexts[model] === undefined ? {} : { context: this.contexts[model] },
|
||||
...this.reasoning[model] === undefined ? {} : { reasoning: this.reasoning[model] },
|
||||
...this.defaultMaxTokens[model] === undefined ? {} : { defaultMaxTokens: this.defaultMaxTokens[model] },
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -920,6 +922,46 @@ describe('LlmService', () => {
|
||||
await expect(ctx.llm.resolveCallConfig(explicit)).resolves.toBe(explicit)
|
||||
})
|
||||
|
||||
it('materializes an adapter-owned maxTokens default while preserving an explicit cap', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['route'], new CatalogAdapter(
|
||||
{ id: 'route', name: 'Route' },
|
||||
[],
|
||||
{},
|
||||
{},
|
||||
{ model: 256_000 },
|
||||
))
|
||||
|
||||
await expect(ctx.llm.resolveModelInfo('route', 'model')).resolves.toMatchObject({
|
||||
defaultMaxTokens: 256_000,
|
||||
})
|
||||
await expect(ctx.llm.resolveCallConfig({ provider: 'route', model: 'model' })).resolves.toEqual({
|
||||
provider: 'route',
|
||||
model: 'model',
|
||||
maxTokens: 256_000,
|
||||
})
|
||||
const explicit = { provider: 'route', model: 'model', maxTokens: 8_192 }
|
||||
await expect(ctx.llm.resolveCallConfig(explicit)).resolves.toBe(explicit)
|
||||
})
|
||||
|
||||
it.each([0, 1.5, Number.MAX_SAFE_INTEGER + 1])(
|
||||
'rejects invalid adapter-owned default maxTokens %s',
|
||||
async (defaultMaxTokens) => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
const adapter = new class extends ScriptedAdapter {
|
||||
override resolveModel(provider: string, model: string): Promise<LlmResolvedModelInfo> {
|
||||
return Promise.resolve({ provider, id: model, name: model, defaultMaxTokens })
|
||||
}
|
||||
}(SCRIPT)
|
||||
ctx.llm.registerAdapter(['route'], adapter)
|
||||
|
||||
await expect(ctx.llm.resolveModelInfo('route', 'model'))
|
||||
.rejects.toMatchObject({ code: 'INVALID_MODEL_MAX_TOKENS' })
|
||||
},
|
||||
)
|
||||
|
||||
it.each([
|
||||
[{ efforts: [] }, 'empty effort list'],
|
||||
[{ efforts: [{ id: '', name: 'Empty' }] }, 'empty id'],
|
||||
|
||||
Reference in New Issue
Block a user