From 32a561f3a68bc643f324bb1400e7df32fabd0be1 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 6 Oct 2026 15:47:09 +0800 Subject: [PATCH] refactor(llm): request minimal reasoning without naming a caller purpose `purpose` is a provider-neutral label for replay and transport metadata, so an adapter must not branch on one caller's value. `GenerateOptions` gains `minimizeReasoning`, which any auxiliary caller sets when reasoning would consume the output budget it reserved for a short visible result; both shipped adapters dispatch such a request at the least reasoning the model supports, and `session-title-llm` sets it instead of relying on the adapter recognizing `'session-title'`. The pasted type in the subsystem page and the generated Cordis API catalog follow. Prompted by review: llm-pi-ai must not know about session-title. --- docs/subsystems/llm-streaming.md | 15 +++++++++---- docs/subsystems/llm-streaming.zh.md | 15 +++++++++---- .../extensions/tool-cordis/src/api-catalog.ts | 2 +- packages/llm/llm-deepseek/README.i18n.yaml | 4 ++-- packages/llm/llm-deepseek/README.md | 2 +- packages/llm/llm-deepseek/README.zh.md | 2 +- packages/llm/llm-deepseek/src/serialize.ts | 2 +- .../llm/llm-deepseek/tests/serialize.spec.ts | 4 ++-- packages/llm/llm-pi-ai/README.i18n.yaml | 4 ++-- packages/llm/llm-pi-ai/README.md | 2 +- packages/llm/llm-pi-ai/README.zh.md | 2 +- packages/llm/llm-pi-ai/src/adapter.ts | 22 +++++++++---------- packages/llm/llm-pi-ai/tests/adapter.spec.ts | 10 ++++----- packages/llm/llm/src/types.ts | 15 +++++++++---- .../session-title-llm/README.i18n.yaml | 4 ++-- packages/session/session-title-llm/README.md | 2 +- .../session/session-title-llm/README.zh.md | 2 +- .../session/session-title-llm/src/index.ts | 1 + .../session-title-llm/tests/llm.spec.ts | 1 + 19 files changed, 67 insertions(+), 44 deletions(-) diff --git a/docs/subsystems/llm-streaming.md b/docs/subsystems/llm-streaming.md index 2ccfab41ed..804da814fd 100644 --- a/docs/subsystems/llm-streaming.md +++ b/docs/subsystems/llm-streaming.md @@ -634,12 +634,19 @@ interface GenerateOptions { sessionId?: Branded<'SessionId'> /** * Provider-neutral classification for an auxiliary model call. Adapters may - * map the purpose to model-hidden transport metadata or purpose-specific - * generation policy. A `session-title` call caps output for one short visible - * title, so adapters dispatch it with the least reasoning the model supports. - * Ordinary conversation requests leave it unset. + * map the purpose to model-hidden transport metadata. Ordinary conversation + * requests leave it unset. */ purpose?: 'compaction' | 'session-title' + /** + * Dispatch with the least reasoning the routed model supports: `off` when + * the model offers it, otherwise its lowest declared level. An auxiliary + * caller sets this when reasoning would consume the output budget it + * reserved for a short visible result. The request's own effort and the + * profile default do not apply, and an effort the model does not support is + * not validated for such a request. + */ + minimizeReasoning?: boolean } ``` diff --git a/docs/subsystems/llm-streaming.zh.md b/docs/subsystems/llm-streaming.zh.md index 4d5158d490..6d6ebb6cd8 100644 --- a/docs/subsystems/llm-streaming.zh.md +++ b/docs/subsystems/llm-streaming.zh.md @@ -640,12 +640,19 @@ interface GenerateOptions { sessionId?: Branded<'SessionId'> /** * Provider-neutral classification for an auxiliary model call. Adapters may - * map the purpose to model-hidden transport metadata or purpose-specific - * generation policy. A `session-title` call caps output for one short visible - * title, so adapters dispatch it with the least reasoning the model supports. - * Ordinary conversation requests leave it unset. + * map the purpose to model-hidden transport metadata. Ordinary conversation + * requests leave it unset. */ purpose?: 'compaction' | 'session-title' + /** + * Dispatch with the least reasoning the routed model supports: `off` when + * the model offers it, otherwise its lowest declared level. An auxiliary + * caller sets this when reasoning would consume the output budget it + * reserved for a short visible result. The request's own effort and the + * profile default do not apply, and an effort the model does not support is + * not validated for such a request. + */ + minimizeReasoning?: boolean } ``` diff --git a/packages/extensions/tool-cordis/src/api-catalog.ts b/packages/extensions/tool-cordis/src/api-catalog.ts index 7707d2ffc1..45a5b384fd 100644 --- a/packages/extensions/tool-cordis/src/api-catalog.ts +++ b/packages/extensions/tool-cordis/src/api-catalog.ts @@ -5389,7 +5389,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'GenerateOptions', - declaration: 'export interface GenerateOptions {\n provider: string;\n model: string;\n reasoningEffort?: ReasoningEffortId;\n messages: RequestMessage[];\n system?: string;\n tools?: ToolSchema[];\n toolHistory?: ToolHistory;\n temperature?: number;\n maxTokens?: number;\n stop?: string[];\n signal?: AbortSignal;\n sessionId?: Branded<\'SessionId\'>;\n purpose?: \'compaction\' | \'session-title\';\n}', + declaration: 'export interface GenerateOptions {\n provider: string;\n model: string;\n reasoningEffort?: ReasoningEffortId;\n messages: RequestMessage[];\n system?: string;\n tools?: ToolSchema[];\n toolHistory?: ToolHistory;\n temperature?: number;\n maxTokens?: number;\n stop?: string[];\n signal?: AbortSignal;\n sessionId?: Branded<\'SessionId\'>;\n purpose?: \'compaction\' | \'session-title\';\n minimizeReasoning?: boolean;\n}', }, { name: 'GenericCallView', diff --git a/packages/llm/llm-deepseek/README.i18n.yaml b/packages/llm/llm-deepseek/README.i18n.yaml index 03586f9f68..f2df7f023f 100644 --- a/packages/llm/llm-deepseek/README.i18n.yaml +++ b/packages/llm/llm-deepseek/README.i18n.yaml @@ -30,8 +30,8 @@ en: 3853ba1a1ffbb46c zh: 97203e80ad933e59 /deepseek-ai-dsh-llm-deepseek/use-this-package/streaming-with-thinking-and-images: - en: 9b82549c6ce25261 - zh: 22a3978c5022576b + en: 1d7ba1bedfd11a18 + zh: 9e1a3372f610e9aa /deepseek-ai-dsh-llm-deepseek/use-this-package/dynamic-configuration: en: 49290fc5647136b4 zh: 96fa9ce0f9e83c13 diff --git a/packages/llm/llm-deepseek/README.md b/packages/llm/llm-deepseek/README.md index d778803b69..4b46311293 100644 --- a/packages/llm/llm-deepseek/README.md +++ b/packages/llm/llm-deepseek/README.md @@ -99,7 +99,7 @@ Cached ids are scoped by endpoint and credential, refreshed before expiry, inval Files mode bounds retained request versions by `maxRequestFilesBytes` and `maxImagesPerRequest`; inline fallback has its own base64 budget. Both remove an oldest prefix in configured byte or count quanta. Each omitted image gets its own model-visible placeholder with its display name or attachment id and, when available, normalized dimensions, media type, and current read-only path. The stepped high-watermark policy avoids rewriting an old request prefix after every new image. -`reasoningEffort` selects the advertised default. Exact-model metadata exposes ordered `off`, `low`, `high`, and `max` efforts with selection guidance when deployment policy permits thinking. `low`, `high`, and `max` enable thinking and serialize as `output_config.effort`, while adapter-owned `off` sends `thinking.type: disabled` instead. An unsupported value fails with `UNSUPPORTED_REASONING_EFFORT` before network I/O, and `thinking: disabled` rejects any non-`off` effort at plugin load. Requests with `purpose: 'session-title'` force thinking off to reserve output for visible title text. The adapter forwards an explicit `temperature`; DeepSeek accepts it with thinking enabled but ignores its value in that mode. +`reasoningEffort` selects the advertised default. Exact-model metadata exposes ordered `off`, `low`, `high`, and `max` efforts with selection guidance when deployment policy permits thinking. `low`, `high`, and `max` enable thinking and serialize as `output_config.effort`, while adapter-owned `off` sends `thinking.type: disabled` instead. An unsupported value fails with `UNSUPPORTED_REASONING_EFFORT` before network I/O, and `thinking: disabled` rejects any non-`off` effort at plugin load. Requests with `GenerateOptions.minimizeReasoning` force thinking off to reserve output for a short visible result. The adapter forwards an explicit `temperature`; DeepSeek accepts it with thinking enabled but ignores its value in that mode. ### Dynamic configuration diff --git a/packages/llm/llm-deepseek/README.zh.md b/packages/llm/llm-deepseek/README.zh.md index 6702984e5d..d1301a9272 100644 --- a/packages/llm/llm-deepseek/README.zh.md +++ b/packages/llm/llm-deepseek/README.zh.md @@ -99,7 +99,7 @@ Messages 和 Files 请求通过 `x-dsh-auth-token` 发送账号 token,不加 B Files 模式通过 `maxRequestFilesBytes` 与 `maxImagesPerRequest` 限制保留请求版本;内联回退有独立 base64 预算。两种模式都按配置的字节或数量量子移除最旧前缀。每张省略图片都有自己的模型可见占位符,包含显示名或附件 id,以及可用时的规范化尺寸、媒体类型与当前只读路径。分阶高水位策略避免每新增一张图片都改写旧请求前缀。 -`reasoningEffort` 选择公布的默认值。当部署策略允许 thinking 时,确切模型元数据会按顺序公开 `off`、`low`、`high` 与 `max` 强度及选择指引。`low`、`high` 与 `max` 启用 thinking,并以 `output_config.effort` 序列化,适配器自有的 `off` 则发送 `thinking.type: disabled`。不支持的取值会在网络 I/O 前以 `UNSUPPORTED_REASONING_EFFORT` 失败;`thinking: disabled` 会在插件加载时拒绝任何非 `off` 强度。`purpose: 'session-title'` 的请求会强制关闭 thinking,把有界输出留给可见标题文本。适配器转发显式 `temperature`;DeepSeek 在启用 thinking 时接受该参数,但忽略其值。 +`reasoningEffort` 选择公布的默认值。当部署策略允许 thinking 时,确切模型元数据会按顺序公开 `off`、`low`、`high` 与 `max` 强度及选择指引。`low`、`high` 与 `max` 启用 thinking,并以 `output_config.effort` 序列化,适配器自有的 `off` 则发送 `thinking.type: disabled`。不支持的取值会在网络 I/O 前以 `UNSUPPORTED_REASONING_EFFORT` 失败;`thinking: disabled` 会在插件加载时拒绝任何非 `off` 强度。携带 `GenerateOptions.minimizeReasoning` 的请求会强制关闭 thinking,把输出留给简短的可见结果。适配器转发显式 `temperature`;DeepSeek 在启用 thinking 时接受该参数,但忽略其值。 ### 动态配置 diff --git a/packages/llm/llm-deepseek/src/serialize.ts b/packages/llm/llm-deepseek/src/serialize.ts index bbfd01d3c3..7fa7d242da 100644 --- a/packages/llm/llm-deepseek/src/serialize.ts +++ b/packages/llm/llm-deepseek/src/serialize.ts @@ -143,7 +143,7 @@ export function serialize( } } if (pending.size > 0) throw new LlmError('DeepSeek Messages history ends with unresolved tools', 'INVALID_REQUEST') - const effort = options.purpose === 'session-title' ? 'off' : options.reasoningEffort ?? (connection.defaults.reasoningEffort ?? (connection.defaults.thinking === 'disabled' ? 'off' : 'high')) + const effort = options.minimizeReasoning === true ? 'off' : options.reasoningEffort ?? (connection.defaults.reasoningEffort ?? (connection.defaults.thinking === 'disabled' ? 'off' : 'high')) if (!['off', 'low', 'high', 'max'].includes(effort) || (connection.defaults.thinking === 'disabled' && effort !== 'off')) { throw new LlmError(`DeepSeek Messages does not support reasoning effort ${effort}`, 'UNSUPPORTED_REASONING_EFFORT') } diff --git a/packages/llm/llm-deepseek/tests/serialize.spec.ts b/packages/llm/llm-deepseek/tests/serialize.spec.ts index e80d487e78..0cf232f7d7 100644 --- a/packages/llm/llm-deepseek/tests/serialize.spec.ts +++ b/packages/llm/llm-deepseek/tests/serialize.spec.ts @@ -285,8 +285,8 @@ describe('Messages request conversion', () => { expect(request.output_config).toEqual(effort === 'off' ? undefined : { effort }) }) - it('disables thinking for titles, passes temperature with thinking and refuses unsupported effort', () => { - expect(body([user()], { purpose: 'session-title', temperature: 0 })).toMatchObject({ thinking: { type: 'disabled' }, temperature: 0 }) + it('disables thinking for a minimized-reasoning request, passes temperature with thinking and refuses unsupported effort', () => { + expect(body([user()], { minimizeReasoning: true, temperature: 0 })).toMatchObject({ thinking: { type: 'disabled' }, temperature: 0 }) expect(body([user()], { temperature: 0 })).toMatchObject({ thinking: { type: 'enabled' }, temperature: 0 }) expect(() => body([user()], { reasoningEffort: ReasoningEffortId('medium') })).toThrow(/effort/) const disabled = resolveAdapterOptions({ thinking: 'disabled' }) diff --git a/packages/llm/llm-pi-ai/README.i18n.yaml b/packages/llm/llm-pi-ai/README.i18n.yaml index d883753148..42f83ddbba 100644 --- a/packages/llm/llm-pi-ai/README.i18n.yaml +++ b/packages/llm/llm-pi-ai/README.i18n.yaml @@ -30,8 +30,8 @@ en: 376f83206858b601 zh: 38bb6993609c96a6 /deepseek-ai-dsh-llm-pi-ai/use-this-package/run-with-reasoning-and-wire-compatibility: - en: 803f9e75f71fa86e - zh: b17d985dd5267163 + en: 38f5251e412f2445 + zh: f492ef40cdafc20e /deepseek-ai-dsh-llm-pi-ai/use-this-package/change-configuration-at-runtime: en: 92f554e1718614ca zh: f17ed3ad3e5d28e2 diff --git a/packages/llm/llm-pi-ai/README.md b/packages/llm/llm-pi-ai/README.md index 172002ebbd..a73ae58bd2 100644 --- a/packages/llm/llm-pi-ai/README.md +++ b/packages/llm/llm-pi-ai/README.md @@ -102,7 +102,7 @@ A profile's `models` list replaces the route's installed catalog rather than ext `reasoningEfforts` declares a model's selectable thinking levels: each key is a level selectors offer, its value the spelling dispatch sends on the wire, so `max: ultra` renames a level for a gateway with its own vocabulary. Omitting the field keeps the installed catalog entry's capability; `false` declares a non-reasoning model. `compat` switches reshape the request for endpoints pi-ai cannot recognize — which role carries the system prompt, which field caps output, how a thinking level travels — configurable per route and per model. A model neither the entry nor the installed catalog sizes takes the route's `defaultContextWindow` and `defaultMaxTokens` fallbacks. -A request carrying `GenerateOptions.purpose: 'session-title'` dispatches at the lowest level its model supports, whatever effort the request or profile names: `off` when the model offers it, otherwise the lowest declared level. A title is a short delayed one-off, so it does not spend its output ceiling on reasoning. `off` dispatches exactly as a selected `off` does, so a protocol that expresses it by omitting the reasoning field leaves the gateway's default in effect; reasoning tokens at any of these levels count toward the title cap. The requested effort is not validated for this purpose, so a name the model does not support fails the main call rather than the title call. +A request carrying `GenerateOptions.minimizeReasoning` dispatches at the lowest level its model supports, whatever effort the request or profile names: `off` when the model offers it, otherwise the lowest declared level. Such a caller reserves its output budget for a short visible result, so it does not spend that budget on reasoning. `off` dispatches exactly as a selected `off` does, so a protocol that expresses it by omitting the reasoning field leaves the gateway's default in effect; reasoning tokens at any of these levels count toward the request's output cap. The requested effort is not validated for such a request, so a name the model does not support fails an ordinary call rather than this one. For self-hosted Chat Completions endpoints, `thinkingTokenBudgetField` selects the reasoning-budget parameter, and `vllmPriority` sets an integer scheduler priority when the server enables priority scheduling. Template arguments accept `$var: thinking.budget`. `openai-responses` gateways can set `supportsMaxOutputTokens: false` to omit `max_output_tokens`; Azure and Codex transports ignore this shared compatibility field. These controls are opt-in; catalog-owned Anthropic effort and fallback capabilities are not configurable switches. diff --git a/packages/llm/llm-pi-ai/README.zh.md b/packages/llm/llm-pi-ai/README.zh.md index 63ed832a77..6624f0b85d 100644 --- a/packages/llm/llm-pi-ai/README.zh.md +++ b/packages/llm/llm-pi-ai/README.zh.md @@ -102,7 +102,7 @@ profile 的 `models` 列表会替换而非扩展路由的已安装目录;每 `reasoningEfforts` 声明模型可选择的 thinking 等级:每个键都是选择器提供的等级,其值是分派时在协议中发送的拼写,因此 `max: ultra` 可以为拥有自有词汇的网关重命名等级。省略该字段时保留已安装目录条目的能力;`false` 声明非推理模型。对于 pi-ai 无法识别的端点,`compat` 开关重塑请求——哪个角色携带系统提示词、哪个字段限制输出、thinking 等级如何传递——可逐路由、逐模型配置。条目与已安装目录都没有尺寸的模型,会采用路由的 `defaultContextWindow` 与 `defaultMaxTokens` 回退值。 -携带 `GenerateOptions.purpose: 'session-title'` 的请求会以其模型支持的最低等级分派,不论请求或 profile 指定何种推理强度:模型提供 `off` 时使用 `off`,否则使用声明的最低等级。标题是延迟敏感的短小一次性请求,不把输出上限花在推理上。`off` 的分派方式与手动选择 `off` 完全相同,因此以省略推理字段表达 `off` 的协议会沿用网关默认行为;这些等级下产生的推理 token 都计入标题上限。该用途不校验所请求的强度,因此模型不支持的名称会让主请求失败,而不是标题请求。 +携带 `GenerateOptions.minimizeReasoning` 的请求会以其模型支持的最低等级分派,不论请求或 profile 指定何种推理强度:模型提供 `off` 时使用 `off`,否则使用声明的最低等级。这类调用方把输出预算留给简短的可见结果,因此不把该预算花在推理上。`off` 的分派方式与手动选择 `off` 完全相同,因此以省略推理字段表达 `off` 的协议会沿用网关默认行为;这些等级下产生的推理 token 都计入该请求的输出上限。该请求不校验所请求的强度,因此模型不支持的名称会让普通调用失败,而不是该请求。 对于自托管 Chat Completions 端点,`thinkingTokenBudgetField` 选择推理预算参数,`vllmPriority` 在服务端启用优先级调度时设置整数调度优先级。模板参数接受 `$var: thinking.budget`。`openai-responses` 网关可设置 `supportsMaxOutputTokens: false` 来省略 `max_output_tokens`;Azure 与 Codex 传输会忽略这个共享兼容字段。这些控制均需显式启用;目录拥有的 Anthropic effort 和回退能力不是可配置开关。 diff --git a/packages/llm/llm-pi-ai/src/adapter.ts b/packages/llm/llm-pi-ai/src/adapter.ts index 1f2d73b810..63b6025b99 100644 --- a/packages/llm/llm-pi-ai/src/adapter.ts +++ b/packages/llm/llm-pi-ai/src/adapter.ts @@ -169,26 +169,26 @@ function resolveReasoningLevel( } /** - * The level one request dispatches with. A `session-title` request takes the - * model's lowest supported level, which is `off` whenever the model can stop - * reasoning, because reasoning a model cannot switch off still counts toward - * the dispatch cap. That request deliberately skips the requested-effort - * check, so a name the model does not support fails the main call rather than - * the auxiliary one. Every other request validates the requested or profile - * effort. + * The level one request dispatches with. A request asking to minimize reasoning + * takes the model's lowest supported level, which is `off` whenever the model + * can stop reasoning, because reasoning a model cannot switch off still counts + * toward the output budget the caller reserved. That request deliberately + * skips the requested-effort check, so a name the model does not support fails + * an ordinary call rather than this one. Every other request validates the + * requested or profile effort. * @param model - the resolved model descriptor. - * @param options - the request's purpose and requested effort. + * @param options - the request's reasoning preference and requested effort. * @param profile - the route profile carrying the default effort. * @returns the level to dispatch, or undefined to send none, which a - * `session-title` request gets only for a model whose metadata leaves it no - * supported level. + * minimized-reasoning request gets only for a model whose metadata leaves it + * no supported level. */ function requestReasoningLevel( model: Model, options: GenerateOptions, profile: ResolvedPiAiProviderProfile, ): ModelThinkingLevel | undefined { - if (options.purpose === 'session-title') return getSupportedThinkingLevels(model)[0] + if (options.minimizeReasoning === true) return getSupportedThinkingLevels(model)[0] return resolveReasoningLevel(model, options.reasoningEffort ?? profile.reasoning) } diff --git a/packages/llm/llm-pi-ai/tests/adapter.spec.ts b/packages/llm/llm-pi-ai/tests/adapter.spec.ts index 18cfbb3cb1..a88ab1f751 100644 --- a/packages/llm/llm-pi-ai/tests/adapter.spec.ts +++ b/packages/llm/llm-pi-ai/tests/adapter.spec.ts @@ -788,7 +788,7 @@ describe('provider profile lifecycle', () => { expect(server.requests[0]).not.toHaveProperty('reasoning_effort') }) - it('dispatches session-title requests at the lowest level each model supports', async () => { + it('dispatches a minimized-reasoning request at the lowest level each model supports', async () => { vi.stubEnv('PI_TEST_KEY', 'test-key') const server = await mockServer([ { events: anthropicTextEvents }, @@ -813,18 +813,18 @@ describe('provider profile lifecycle', () => { }, }, }) - const request = (model: string, purpose?: 'session-title'): Promise => assemble(ctx, { + const request = (model: string, minimizeReasoning?: true): Promise => assemble(ctx, { provider: 'adaptive-gateway', model, reasoningEffort: ReasoningEffortId('max'), maxTokens: 64, messages: [], - ...purpose === undefined ? {} : { purpose }, + ...minimizeReasoning === undefined ? {} : { minimizeReasoning }, }) await request('always-thinks') - await request('always-thinks', 'session-title') - await request('may-think', 'session-title') + await request('always-thinks', true) + await request('may-think', true) expect(server.requests[0]).toMatchObject({ thinking: { type: 'adaptive' }, output_config: { effort: 'max' } }) expect(server.requests[1]).toMatchObject({ diff --git a/packages/llm/llm/src/types.ts b/packages/llm/llm/src/types.ts index ee537b443b..7251493bb9 100644 --- a/packages/llm/llm/src/types.ts +++ b/packages/llm/llm/src/types.ts @@ -546,10 +546,17 @@ export interface GenerateOptions { sessionId?: Branded<'SessionId'> /** * Provider-neutral classification for an auxiliary model call. Adapters may - * map the purpose to model-hidden transport metadata or purpose-specific - * generation policy. A `session-title` call caps output for one short visible - * title, so adapters dispatch it with the least reasoning the model supports. - * Ordinary conversation requests leave it unset. + * map the purpose to model-hidden transport metadata. Ordinary conversation + * requests leave it unset. */ purpose?: 'compaction' | 'session-title' + /** + * Dispatch with the least reasoning the routed model supports: `off` when + * the model offers it, otherwise its lowest declared level. An auxiliary + * caller sets this when reasoning would consume the output budget it + * reserved for a short visible result. The request's own effort and the + * profile default do not apply, and an effort the model does not support is + * not validated for such a request. + */ + minimizeReasoning?: boolean } diff --git a/packages/session/session-title-llm/README.i18n.yaml b/packages/session/session-title-llm/README.i18n.yaml index d3d19f893b..d595206e93 100644 --- a/packages/session/session-title-llm/README.i18n.yaml +++ b/packages/session/session-title-llm/README.i18n.yaml @@ -36,8 +36,8 @@ en: 0fdc928704abdd3a zh: bd4c0a7dd47578cf /deepseek-ai-dsh-session-title-llm/understand-the-implementation/request-flow: - en: 9103f1df0e62575f - zh: fda4aa05f54f5c69 + en: d60754b3baf4e947 + zh: e347c55c9dba1987 /deepseek-ai-dsh-session-title-llm/further-exploration: en: 641f31c35c48916b zh: 8e809fbdfef61b61 diff --git a/packages/session/session-title-llm/README.md b/packages/session/session-title-llm/README.md index d0e750f855..cf670f1dc1 100644 --- a/packages/session/session-title-llm/README.md +++ b/packages/session/session-title-llm/README.md @@ -72,7 +72,7 @@ One shared policy so provider plugins cannot drift: config validation, route res ### Request flow -A generation validates the config once at registration; each revision frames the selected messages as JSON, measures the framed prompt's UTF-8 bytes against `maxInputBytes`, resolves the route (the explicit pair or the logged `request/header`), appends a log-only `session/title-llm-request` event carrying the exact dispatchable request, then streams through `ctx.llm` under a composed timeout and cancellation deadline. The dispatched envelope carries `purpose: 'session-title'` and deliberately lacks the agent loop's process-local request identity; adapters dispatch that purpose with the least reasoning the model supports, so a title request does not spend its output ceiling on reasoning: the DeepSeek adapter disables thinking, and the pi-ai adapter selects the model's lowest supported level. Output assembles into text blocks only; tool calls, malformed or empty output, and non-stop finish reasons reject, and a later model failure leaves the request record intact. +A generation validates the config once at registration; each revision frames the selected messages as JSON, measures the framed prompt's UTF-8 bytes against `maxInputBytes`, resolves the route (the explicit pair or the logged `request/header`), appends a log-only `session/title-llm-request` event carrying the exact dispatchable request, then streams through `ctx.llm` under a composed timeout and cancellation deadline. The dispatched envelope carries `purpose: 'session-title'` for replay labeling and `minimizeReasoning`, and deliberately lacks the agent loop's process-local request identity; adapters dispatch a minimized-reasoning request with the least reasoning the model supports, so a title request does not spend its output ceiling on reasoning: the DeepSeek adapter disables thinking, and the pi-ai adapter selects the model's lowest supported level. Output assembles into text blocks only; tool calls, malformed or empty output, and non-stop finish reasons reject, and a later model failure leaves the request record intact. diff --git a/packages/session/session-title-llm/README.zh.md b/packages/session/session-title-llm/README.zh.md index f9a9d85ffa..36733cb025 100644 --- a/packages/session/session-title-llm/README.zh.md +++ b/packages/session/session-title-llm/README.zh.md @@ -72,7 +72,7 @@ kind: "package-library" ### 请求流程 -生成在注册时校验一次配置;每次修订把选中的消息封装为 JSON,依据 `maxInputBytes` 检查封装提示词的 UTF-8 字节数,解析路由(显式对或已记录 `request/header`),追加一条携带确切可分发请求的仅日志 `session/title-llm-request` 事件,然后在组合的超时与取消截止时间内通过 `ctx.llm` 流式生成。分发的封套携带 `purpose: 'session-title'`,且有意不包含 agent loop 的进程本地请求身份;适配器以模型支持的最少推理分发该用途,使标题请求不把输出上限花在推理上:DeepSeek 适配器禁用思考,pi-ai 适配器选择模型支持的最低等级。输出只组装为文本块;工具调用、格式错误或空输出与非 stop 结束原因都会拒绝,后续模型失败会保留请求记录。 +生成在注册时校验一次配置;每次修订把选中的消息封装为 JSON,依据 `maxInputBytes` 检查封装提示词的 UTF-8 字节数,解析路由(显式对或已记录 `request/header`),追加一条携带确切可分发请求的仅日志 `session/title-llm-request` 事件,然后在组合的超时与取消截止时间内通过 `ctx.llm` 流式生成。分发的封套携带用于重放标注的 `purpose: 'session-title'` 与 `minimizeReasoning`,且有意不包含 agent loop 的进程本地请求身份;适配器以模型支持的最少推理分发最小化推理请求,使标题请求不把输出上限花在推理上:DeepSeek 适配器禁用思考,pi-ai 适配器选择模型支持的最低等级。输出只组装为文本块;工具调用、格式错误或空输出与非 stop 结束原因都会拒绝,后续模型失败会保留请求记录。 diff --git a/packages/session/session-title-llm/src/index.ts b/packages/session/session-title-llm/src/index.ts index 0e42718818..f7017eee6b 100644 --- a/packages/session/session-title-llm/src/index.ts +++ b/packages/session/session-title-llm/src/index.ts @@ -304,6 +304,7 @@ export async function generateSessionTitleWithLlm( maxTokens, sessionId: request.session.id, purpose: 'session-title', + minimizeReasoning: true, signal: callDeadline.signal, }) request.session.append('session/title-llm-request', { diff --git a/packages/session/session-title-llm/tests/llm.spec.ts b/packages/session/session-title-llm/tests/llm.spec.ts index 3a13641b2a..d925a1bb76 100644 --- a/packages/session/session-title-llm/tests/llm.spec.ts +++ b/packages/session/session-title-llm/tests/llm.spec.ts @@ -166,6 +166,7 @@ describe('generateSessionTitleWithLlm', () => { maxTokens: 32, sessionId: providerRequest.session.id, purpose: 'session-title', + minimizeReasoning: true, }) expect(options.system).toContain('5 words') expect(options.system).toContain('10 CJK characters')