diff --git a/docs/config-catalog.md b/docs/config-catalog.md index f07a12f4a8..1613d39de6 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -638,7 +638,7 @@ export interface Config { thinking?: 'enabled' | 'disabled' /** Default thinking effort (default `high`); `off` disables thinking per request. */ reasoningEffort?: 'off' | 'high' | 'max' - /** Default per-request output cap (default 256,000); explicit request values win. */ + /** Default per-request output cap (default 256,000); a model's own cap and explicit request values win. */ maxTokens?: number /** Positive context capacity used when the selected model has no exact value (default 1,000,000). */ defaultContextWindow?: number @@ -660,6 +660,8 @@ export interface DeepSeekCatalogModel { description?: string /** Known combined request/response context capacity; omitted when deployment metadata is unavailable. */ contextWindow?: number + /** Per-request output cap for this model; omission falls back to the profile's {@link DeepSeekConnectionOptions.maxTokens}. */ + maxTokens?: number } ``` diff --git a/packages/llm/llm-deepseek/README.i18n.yaml b/packages/llm/llm-deepseek/README.i18n.yaml index 45d9cee054..e75778f9f0 100644 --- a/packages/llm/llm-deepseek/README.i18n.yaml +++ b/packages/llm/llm-deepseek/README.i18n.yaml @@ -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: 020aa65073495526be3f32912b7cd06667c52a2e -README.zh.md: 4c655e90ba00340c056f6ac16159621f7a8c1ddb +README.md: 72b04f5982ec7fdef024835ab23e7a9f0005f84c +README.zh.md: 33eb1986a90079a2b8d6768368287b121e2fbd6b diff --git a/packages/llm/llm-deepseek/README.md b/packages/llm/llm-deepseek/README.md index 020aa65073..72b04f5982 100644 --- a/packages/llm/llm-deepseek/README.md +++ b/packages/llm/llm-deepseek/README.md @@ -40,7 +40,7 @@ The plugin registers the single provider route `deepseek-official` together with `contextWindow` is optional per configured model and is not exposed through the advisory catalog. `ctx.llm.resolveModelInfo('deepseek-official', 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-official` 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 adapter does not clamp this request budget against `contextWindow`; deployments with a smaller context or provider output limit must configure a compatible `maxTokens`. +`maxTokens` is the adapter-configured output cap for conversation requests and defaults to 256,000. A catalog entry may carry its own `maxTokens`, which wins for that model; an entry without one, and any unlisted pass-through id, resolve to the profile value, so adding a per-model cap changes one model rather than the route. Exact-model resolution exposes the winner 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 adapter does not clamp this request budget against `contextWindow`; deployments with a smaller context or provider output limit must configure a compatible `maxTokens`. 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. diff --git a/packages/llm/llm-deepseek/README.zh.md b/packages/llm/llm-deepseek/README.zh.md index 4c655e90ba..33eb1986a9 100644 --- a/packages/llm/llm-deepseek/README.zh.md +++ b/packages/llm/llm-deepseek/README.zh.md @@ -40,7 +40,7 @@ harness LLM（大语言模型）seam 的 DeepSeek chat-completions 适配器： `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-official', 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-official` 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`。适配器不会根据 `contextWindow` 自动调低该请求预算；上下文或提供方输出上限较小的部署必须配置与其相容的 `maxTokens`。 +`maxTokens` 是适配器为对话请求配置的输出上限，默认值为 256,000。Catalog 配置项可以自带 `maxTokens`，它对该模型胜出；不含该上限的配置项以及任何未列出原样传递 id 都解析为 profile 值，因此新增按模型的上限只改变一个模型，而非整条路由。确切模型解析会将胜出值公开为 `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`。适配器不会根据 `contextWindow` 自动调低该请求预算；上下文或提供方输出上限较小的部署必须配置与其相容的 `maxTokens`。 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。 diff --git a/packages/llm/llm-deepseek/src/adapter.ts b/packages/llm/llm-deepseek/src/adapter.ts index 85985c41d8..c0d74d3f75 100644 --- a/packages/llm/llm-deepseek/src/adapter.ts +++ b/packages/llm/llm-deepseek/src/adapter.ts @@ -35,6 +35,8 @@ export interface DeepSeekCatalogModel { description?: string /** Known combined request/response context capacity; omitted when deployment metadata is unavailable. */ contextWindow?: number + /** Per-request output cap for this model; omission falls back to the profile's {@link DeepSeekConnectionOptions.maxTokens}. */ + maxTokens?: number } /** @@ -181,7 +183,7 @@ export class DeepSeekAdapter extends LlmAdapter { ? { provider, id: model, name: model } : modelInfo(provider, configured), context: { contextWindow }, - defaultMaxTokens: connection.maxTokens, + defaultMaxTokens: configured?.maxTokens ?? connection.maxTokens, ...connection.defaults.thinking === 'disabled' ? { reasoning: { diff --git a/packages/llm/llm-deepseek/src/index.ts b/packages/llm/llm-deepseek/src/index.ts index 3ecc0bec77..cd2bb9a24e 100644 --- a/packages/llm/llm-deepseek/src/index.ts +++ b/packages/llm/llm-deepseek/src/index.ts @@ -68,7 +68,7 @@ export interface Config { thinking?: 'enabled' | 'disabled' /** Default thinking effort (default `high`); `off` disables thinking per request. */ reasoningEffort?: 'off' | 'high' | 'max' - /** Default per-request output cap (default 256,000); explicit request values win. */ + /** Default per-request output cap (default 256,000); a model's own cap and explicit request values win. */ maxTokens?: number /** Positive context capacity used when the selected model has no exact value (default 1,000,000). */ defaultContextWindow?: number @@ -85,6 +85,7 @@ const catalogModel: z = z.object({ name: z.string(), description: z.string(), contextWindow: z.number().step(1).min(1), + maxTokens: z.number().step(1).min(1), }) export const Config: z = z.object({ @@ -125,6 +126,12 @@ function resolveModels(models: readonly DeepSeekCatalogModel[] | undefined): Dee `llm-deepseek: catalog model "${model.id}" contextWindow must be a positive integer`, ) } + if (model.maxTokens !== undefined + && (!Number.isInteger(model.maxTokens) || model.maxTokens <= 0)) { + throw new Error( + `llm-deepseek: catalog model "${model.id}" maxTokens must be a positive integer`, + ) + } if (seen.has(model.id)) throw new Error(`llm-deepseek: duplicate catalog model "${model.id}"`) seen.add(model.id) return { @@ -132,6 +139,7 @@ function resolveModels(models: readonly DeepSeekCatalogModel[] | undefined): Dee ...model.name === undefined ? {} : { name: model.name }, ...model.description === undefined ? {} : { description: model.description }, ...model.contextWindow === undefined ? {} : { contextWindow: model.contextWindow }, + ...model.maxTokens === undefined ? {} : { maxTokens: model.maxTokens }, } }) } diff --git a/packages/llm/llm-deepseek/tests/adapter.spec.ts b/packages/llm/llm-deepseek/tests/adapter.spec.ts index ec4a271f15..8ee2c81afe 100644 --- a/packages/llm/llm-deepseek/tests/adapter.spec.ts +++ b/packages/llm/llm-deepseek/tests/adapter.spec.ts @@ -793,6 +793,26 @@ describe('plugin registration and config', () => { expect(ctx.llm.listProviders()).toEqual([]) }) + it.each([0, 1.5])('rejects a per-model output cap of %s', (maxTokens) => { + expect(() => resolveAdapterOptions({ models: [{ id: 'bad-cap', maxTokens }] })) + .toThrow(/maxTokens must be a positive integer/) + }) + + it('prefers a model\'s own output cap over the profile default', async () => { + // The profile default stays what an unlisted or uncapped model resolves + // to, so adding a per-model cap changes one model rather than the route. + const adapter = adapterOf({ maxTokens: 4096, models: [ + { id: 'capped', maxTokens: 512 }, + { id: 'uncapped' }, + ] }) + await expect(adapter.resolveModel('deepseek-official', 'capped')) + .resolves.toMatchObject({ defaultMaxTokens: 512 }) + await expect(adapter.resolveModel('deepseek-official', 'uncapped')) + .resolves.toMatchObject({ defaultMaxTokens: 4096 }) + await expect(adapter.resolveModel('deepseek-official', 'not-in-catalog')) + .resolves.toMatchObject({ defaultMaxTokens: 4096 }) + }) + it('rejects invalid context capacity when apply is called directly', async () => { const ctx = new Context() await ctx.plugin(LlmService)