mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
Merge remote-tracking branch 'origin/master' into feature/subagent-policy-inheritance
# Conflicts: # docs/cordis-catalog/services.md # examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl
This commit is contained in:
kingwl
@@ -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
|
||||
core.md: 781267cccdb5bbda33e5be6a9e807fdbe47dbc83
|
||||
core.zh.md: d0f67983b98b0cf679a8e599a5f8ab3c64490dd0
|
||||
core.md: 86aea325f5401d728a9b4aa147d78db9163a32c1
|
||||
core.zh.md: d09fb48419c14959eefb5a1df1c593b36c188cf5
|
||||
|
||||
@@ -199,7 +199,7 @@ interface LlmModelInfo {
|
||||
}
|
||||
```
|
||||
|
||||
Correctness-sensitive model capacity is queried separately from the advisory catalog and is owned by the adapter serving the exact route.
|
||||
Correctness-sensitive metadata is resolved separately from the advisory catalog and is owned by the adapter serving the exact route. Context capacity and reasoning choices share one exact-model result so consumers do not repeat authoritative model resolution.
|
||||
|
||||
```ts type-equiv
|
||||
/** Provider-owned context capacity for one exact provider/model route. */
|
||||
@@ -209,12 +209,56 @@ interface LlmModelContext {
|
||||
}
|
||||
```
|
||||
|
||||
Reasoning effort is another exact-route capability. The core brands identifiers but does not enumerate their values; each adapter owns the ordered set, display names, and optional deployment default.
|
||||
|
||||
```ts type-equiv
|
||||
/** Adapter-owned identifier for one model's selectable reasoning effort. */
|
||||
type ReasoningEffortId = Branded<'ReasoningEffortId'>
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Display metadata for one adapter-owned reasoning effort. */
|
||||
interface LlmReasoningEffortInfo {
|
||||
/** Opaque stable value accepted by {@link GenerateOptions.reasoningEffort}. */
|
||||
id: ReasoningEffortId
|
||||
/** Human-readable effort name for selectors and diagnostics. */
|
||||
name: string
|
||||
/** Optional user-facing distinction from otherwise similar efforts. */
|
||||
description?: string
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Selectable reasoning efforts for one exact provider/model route. */
|
||||
interface LlmModelReasoningInfo {
|
||||
/** Supported efforts in adapter-preferred display order. */
|
||||
efforts: readonly LlmReasoningEffortInfo[]
|
||||
/**
|
||||
* Adapter-configured default materialized into requests when callers omit
|
||||
* an effort. Absence preserves the provider's own default.
|
||||
*/
|
||||
defaultEffort?: ReasoningEffortId
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Exact-route model metadata resolved by its owning adapter. */
|
||||
interface LlmResolvedModelInfo extends LlmModelInfo {
|
||||
/** Provider-owned context capacity when known. */
|
||||
context?: LlmModelContext
|
||||
/** Adapter-owned selectable reasoning levels when exposed. */
|
||||
reasoning?: LlmModelReasoningInfo
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** A single model request, fully assembled. */
|
||||
interface GenerateOptions {
|
||||
/** Registered provider route selecting the adapter instance. */
|
||||
provider: string
|
||||
model: string
|
||||
/** Adapter-owned reasoning effort selected for this exact model. */
|
||||
reasoningEffort?: ReasoningEffortId
|
||||
/**
|
||||
* Ordered conversation messages, exactly as the provider sees them (after
|
||||
* the `system` slot). A loop-built request assembles them as
|
||||
@@ -291,21 +335,23 @@ The model-facing `ToolSchema` is the wire shape; the registered `ToolDefinition`
|
||||
|
||||
The loop builds each request from logged state. `EpochHeader` records call config, rendered prompt, authoritative returned tool order (configured by `toolOrder`, or lexicographic when unset), and session prefix through full `request/header` snapshots. Together with derived history, this makes the request reconstructable from the session log. See [session.md](session.md#the-request-header-event-requestheader) and the [reconstructability Agent Note](../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md).
|
||||
|
||||
`agent/request` receives a frozen call-config seed and may return a replacement to switch provider, model, or sampling. `agent/session-prefix` composes request-only prefix messages once per loop instance, and the header records the exact result used. Requests reaching `llm/stream` are deep-frozen, so mutation throws, and carry a process-local loop identity so observers do not confuse separately logged frozen auxiliary calls with conversation requests.
|
||||
`agent/request` receives a frozen call-config seed and may return a replacement to switch provider, model, reasoning effort, or sampling. After the waterfall, the loop prepares the exact model capability under the turn signal, rejects unsupported explicit effort ids without clamping, materializes an adapter-configured default, and logs the effective value. The prepared call keeps one adapter registration through dispatch. `agent/session-prefix` composes request-only prefix messages once per loop instance, and the header records the exact result used. Requests reaching `llm/stream` are deep-frozen, so mutation throws, and carry a process-local loop identity so observers do not confuse separately logged frozen auxiliary calls with conversation requests.
|
||||
|
||||
On the wire, a loop-built request reads in this order: the `system` slot (the rendered prompt assembly) → `messagePrefix` (the frozen session prefix) → the derived history — the boundary snapshot, whose tail is the newest `user/message` on a turn's first step and the previous step's tool results on later steps. The prefix never enters the derived history; its durable record is the header events, and the dev invariant recomputes exactly this equation against every loop-built request.
|
||||
|
||||
FIXME(call-config-shape): revisit the exact definition of this type — which fields are genuinely epoch-level for cache purposes (`model` certainly; the sampling scalars sit here out of caution), and where provider-specific extras (reasoning options, extra body params) belong when an adapter needs them.
|
||||
FIXME(call-config-shape): revisit which remaining fields are genuinely epoch-level for cache purposes (`model` and the model-owned reasoning effort are explicit; the sampling scalars sit here out of caution).
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Provider + model + sampling scalars of one conversation's requests. Every field maps
|
||||
* 1:1 onto the same-named `GenerateOptions` field; the loop builds requests
|
||||
* from the logged header rather than accepting these per call.
|
||||
* Provider, model, reasoning effort, and sampling scalars of one conversation's
|
||||
* requests. Every field maps 1:1 onto the same-named `GenerateOptions` field;
|
||||
* the loop builds requests from the logged header rather than accepting these
|
||||
* per call.
|
||||
*/
|
||||
interface LlmCallConfig {
|
||||
provider: string
|
||||
model: string
|
||||
reasoningEffort?: ReasoningEffortId
|
||||
temperature?: number
|
||||
maxTokens?: number
|
||||
stop?: string[]
|
||||
|
||||
@@ -205,7 +205,7 @@ interface LlmModelInfo {
|
||||
}
|
||||
```
|
||||
|
||||
对正确性敏感的模型容量与参考目录分开查询，并归服务该确切路由的适配器所有。
|
||||
对正确性敏感的元数据与参考目录分开解析，并归服务该确切路由的适配器所有。上下文容量和推理选项共用同一个确切模型结果，消费方因而无需重复执行权威模型解析。
|
||||
|
||||
```ts type-equiv
|
||||
/** Provider-owned context capacity for one exact provider/model route. */
|
||||
@@ -215,12 +215,56 @@ interface LlmModelContext {
|
||||
}
|
||||
```
|
||||
|
||||
推理强度是另一项针对确切路由的能力。核心为标识符添加品牌类型，但不枚举其值；有序集合、展示名称和可选的部署默认值均由各适配器持有。
|
||||
|
||||
```ts type-equiv
|
||||
/** Adapter-owned identifier for one model's selectable reasoning effort. */
|
||||
type ReasoningEffortId = Branded<'ReasoningEffortId'>
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Display metadata for one adapter-owned reasoning effort. */
|
||||
interface LlmReasoningEffortInfo {
|
||||
/** Opaque stable value accepted by {@link GenerateOptions.reasoningEffort}. */
|
||||
id: ReasoningEffortId
|
||||
/** Human-readable effort name for selectors and diagnostics. */
|
||||
name: string
|
||||
/** Optional user-facing distinction from otherwise similar efforts. */
|
||||
description?: string
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Selectable reasoning efforts for one exact provider/model route. */
|
||||
interface LlmModelReasoningInfo {
|
||||
/** Supported efforts in adapter-preferred display order. */
|
||||
efforts: readonly LlmReasoningEffortInfo[]
|
||||
/**
|
||||
* Adapter-configured default materialized into requests when callers omit
|
||||
* an effort. Absence preserves the provider's own default.
|
||||
*/
|
||||
defaultEffort?: ReasoningEffortId
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Exact-route model metadata resolved by its owning adapter. */
|
||||
interface LlmResolvedModelInfo extends LlmModelInfo {
|
||||
/** Provider-owned context capacity when known. */
|
||||
context?: LlmModelContext
|
||||
/** Adapter-owned selectable reasoning levels when exposed. */
|
||||
reasoning?: LlmModelReasoningInfo
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** A single model request, fully assembled. */
|
||||
interface GenerateOptions {
|
||||
/** Registered provider route selecting the adapter instance. */
|
||||
provider: string
|
||||
model: string
|
||||
/** Adapter-owned reasoning effort selected for this exact model. */
|
||||
reasoningEffort?: ReasoningEffortId
|
||||
/**
|
||||
* Ordered conversation messages, exactly as the provider sees them (after
|
||||
* the `system` slot). A loop-built request assembles them as
|
||||
@@ -297,21 +341,23 @@ interface ToolSchema {
|
||||
|
||||
循环从已记录状态构建每个请求。`EpochHeader` 通过完整的 `request/header` 快照记录调用配置、渲染后的提示词、权威返回工具顺序（由 `toolOrder` 配置；未配置时按字典序）以及会话前缀。结合派生历史，请求便可由会话日志重建。见 [session.md](session.md#the-request-header-event-requestheader) 与[可重建性 Agent Note（agent 决策记录）](../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)。
|
||||
|
||||
`agent/request` 接收冻结的调用配置种子，并可返回替代值以切换提供方、模型或采样参数。`agent/session-prefix` 为每个循环实例组合一次仅用于请求的 prefix 消息，header 记录实际使用的确切结果。到达 `llm/stream` 的请求会被深度冻结，因此变更会抛异常；请求还携带进程本地循环标识，使观察者不会把单独记录的冻结辅助调用误认成对话请求。
|
||||
`agent/request` 接收冻结的调用配置种子，并可返回替代值以切换提供方、模型、推理强度或采样参数。waterfall 结束后，循环会在轮次信号控制下完成确切模型的能力准备，拒绝显式指定但不受支持的推理强度 ID（不自动调整），填入适配器配置的默认值，并记录最终生效值。准备完成的调用直至分派完成始终持有同一项适配器注册。`agent/session-prefix` 为每个循环实例组合一次仅用于请求的 prefix 消息，header 记录实际使用的确切结果。到达 `llm/stream` 的请求会被深度冻结，因此变更会抛异常；请求还携带进程本地循环标识，使观察者不会把单独记录的冻结辅助调用误认成对话请求。
|
||||
|
||||
在协议格式上，循环构建的请求按此顺序读取：`system` 槽位（渲染后的提示词组装）→ `messagePrefix`（冻结的会话前缀）→ 派生历史——边界快照，其尾部在轮次首步是最新的 `user/message`，在后续步骤是上一步的工具结果。前缀从不进入派生历史；它的持久记录是 header 事件，开发不变式针对每个循环构建的请求精确重算此等式。
|
||||
|
||||
FIXME(call-config-shape)：重新审视此类型的精确定义——出于缓存目的，哪些字段确实属于 epoch 层级（`model` 肯定属于；采样标量目前出于谨慎放在这里），以及适配器需要时，提供方特有的额外项（推理选项、额外 body 参数）应归属何处。
|
||||
FIXME(call-config-shape)：重新审视其余哪些字段出于缓存目的确实属于 epoch 层级（`model` 和模型持有的推理强度已明确属于；采样标量目前出于谨慎保留在此）。
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Provider + model + sampling scalars of one conversation's requests. Every field maps
|
||||
* 1:1 onto the same-named `GenerateOptions` field; the loop builds requests
|
||||
* from the logged header rather than accepting these per call.
|
||||
* Provider, model, reasoning effort, and sampling scalars of one conversation's
|
||||
* requests. Every field maps 1:1 onto the same-named `GenerateOptions` field;
|
||||
* the loop builds requests from the logged header rather than accepting these
|
||||
* per call.
|
||||
*/
|
||||
interface LlmCallConfig {
|
||||
provider: string
|
||||
model: string
|
||||
reasoningEffort?: ReasoningEffortId
|
||||
temperature?: number
|
||||
maxTokens?: number
|
||||
stop?: string[]
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# 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
|
||||
llm-streaming.md: fb97e74a9ec01e62ba940295112fb157cc73bd1d
|
||||
llm-streaming.zh.md: fda59a64aeef1c037372d69dbc15ee0de48de222
|
||||
# pnpm run verify-translation-pairing --write docs/core-data-structures/llm-streaming.md
|
||||
llm-streaming.md: 9151ba569af6b640144c1850d616b6f762b68a8b
|
||||
llm-streaming.zh.md: ae4a6843b9bf4f09169b17271c7edea76f8f2051
|
||||
|
||||
@@ -67,7 +67,7 @@ Every adapter MUST obey these, and every consumer may rely on them:
|
||||
- **Every provider HTTP request carries the app-attribution header.** Adapters send `attributionHeaders()` (below) - the `User-Agent` baseline - and prove it with a wire-level test (mock server asserting the received header, or the library's header hook for a library-backed adapter).
|
||||
- **Replay state is adapter-owned.** A successful `finish` may carry lossless-JSON state needed to reconstruct a native provider response. The loop stores it with the assembled assistant message unless an `agent/step-result` listener rewrote the content. On a later request, `LlmService` passes the state only when the historical provider and target provider are currently registered to the exact same adapter instance. That adapter validates the state and owns any cross-model or cross-provider conversion; other adapters receive the provider-neutral content and provenance without the private state.
|
||||
|
||||
This contract is pinned down by two deliberately independent implementations: `dsh-llm-deepseek` (hand-rolled fetch/SSE) and `dsh-llm-pi-ai` (a generic multi-provider adapter through `@earendil-works/pi-ai`). The library-backed adapter exercises the finish-chunk error path, while transport-boundary tests prove each idle watchdog stops its actual request.
|
||||
This contract is pinned down by two deliberately independent implementations: `dsh-llm-deepseek` (direct fetch, SSE framing via `eventsource-parser`) and `dsh-llm-pi-ai` (a generic multi-provider adapter through `@earendil-works/pi-ai`). The library-backed adapter exercises the finish-chunk error path, while transport-boundary tests prove each idle watchdog stops its actual request.
|
||||
|
||||
## `AppIdentity` — app attribution
|
||||
|
||||
@@ -157,14 +157,30 @@ declare class BlockAssembler {
|
||||
|
||||
## The seam
|
||||
|
||||
`LlmAdapter` is the provider seam: subclass, implement `stream()`, and register one adapter instance with `ctx.llm.registerAdapter(providers, adapter)`. `GenerateOptions.provider` selects the registered adapter; `GenerateOptions.model` is passed to that adapter and need not be registered at lifecycle start. Duplicate provider routes fail atomically. Optional `providerInfo()` and asynchronous `listModels()` methods feed `LlmService.listProviders()` / `listModels()` with detached selector metadata. That catalog is advisory rather than a request whitelist: the adapter remains authoritative and may accept unlisted model ids. The separate `resolveModelContext()` query exposes correctness-sensitive capacity for an exact route without making catalog membership authoritative; absence means unknown metadata, not invalid routing. Adapter lookup happens at the terminal continuation of the `llm/stream` waterfall, so a listener may short-circuit the call or route a mutable one-shot request before lookup. The `block-start` / `block-end` `index` correlation and the assembler together mean an adapter only has to emit well-formed chunks — block reassembly is not each adapter's problem. The consumer surface (`ctx.llm.stream()`) and the `llm/stream` waterfall are described in [architecture.md § Content blocks and streaming](../architecture.md#content-blocks-and-streaming-dsh-llm).
|
||||
`LlmAdapter` is the provider seam: subclass, implement `stream()`, and register one adapter instance with `ctx.llm.registerAdapter(providers, adapter)`. `GenerateOptions.provider` selects the registered adapter; `GenerateOptions.model` is passed to that adapter and need not be registered at lifecycle start. Duplicate provider routes fail atomically. Optional `providerInfo()` and asynchronous `listModels()` methods feed `LlmService.listProviders()` / `listModels()` with detached selector metadata. That catalog is advisory rather than a request whitelist: the adapter remains authoritative and may accept unlisted model ids. One asynchronous `resolveModel()` query returns exact model identity plus optional correctness-sensitive context capacity and ordered model-owned reasoning ids with an optional deployment default; absent fields mean unavailable metadata or capability, not invalid catalog membership. The resolver receives optional cancellation and must settle promptly after abort. `LlmService.resolveModelInfo()` validates and detaches the aggregate. The service validates and materializes reasoning through `resolveCallConfig()` at the final adapter boundary, so direct calls cannot bypass unsupported-effort rejection; direct dispatch captures one registration before awaiting that resolution. The agent loop instead uses `prepareCall()` to keep the same registration across model resolution, durable header logging, and dispatch. Adapter lookup happens at the terminal continuation of the `llm/stream` waterfall, so a listener may short-circuit the call or route a mutable one-shot request before lookup. The `block-start` / `block-end` `index` correlation and the assembler together mean an adapter only has to emit well-formed chunks — block reassembly is not each adapter's problem. The consumer surface (`ctx.llm.stream()`) and the `llm/stream` waterfall are described in [architecture.md § Content blocks and streaming](../architecture.md#content-blocks-and-streaming-dsh-llm).
|
||||
|
||||
```ts type-equiv
|
||||
/** One model call whose config and adapter registration were resolved together. */
|
||||
interface PreparedLlmCall {
|
||||
/** Detached, deep-frozen config with any adapter-owned default materialized. */
|
||||
readonly config: LlmCallConfig
|
||||
/**
|
||||
* Dispatch this call once through the registration captured during
|
||||
* preparation. The request's call-config fields must match {@link config};
|
||||
* reuse or mismatch fails with `INVALID_PREPARED_CALL`.
|
||||
* @param options - fully assembled request carrying the prepared config.
|
||||
* @returns the chunk stream, including the `llm/stream` waterfall.
|
||||
*/
|
||||
stream(options: GenerateOptions): AsyncIterable<StreamChunk>
|
||||
}
|
||||
```
|
||||
|
||||
```ts public-api
|
||||
/**
|
||||
* Provider-wire adapter for the harness message and stream vocabulary. Register implementations
|
||||
* with `ctx.llm.registerAdapter(providers, adapter)`. Every provider HTTP request must include
|
||||
* `attributionHeaders()`; prove that at the wire or library header-hook boundary. The hand-rolled
|
||||
* DeepSeek and pi-ai adapters intentionally exercise this contract through different internals.
|
||||
* `attributionHeaders()`; prove that at the wire or library header-hook boundary. The direct-fetch
|
||||
* DeepSeek and library-backed pi-ai adapters intentionally exercise this contract through different internals.
|
||||
*/
|
||||
declare abstract class LlmAdapter {
|
||||
/**
|
||||
@@ -182,16 +198,19 @@ declare abstract class LlmAdapter {
|
||||
*/
|
||||
listModels(_provider: string): Promise<readonly LlmModelInfo[]>;
|
||||
/**
|
||||
* Resolve context capacity for one model accepted by this adapter. Absence
|
||||
* means the adapter does not know the capacity, not that routing is invalid.
|
||||
* @param _provider - one provider route owned by this adapter.
|
||||
* @param _model - exact model id passed to {@link GenerateOptions.model}.
|
||||
* @returns provider-owned context metadata, or `undefined` when unavailable.
|
||||
* Resolve all metadata available for one exact model. This query is
|
||||
* independent of the advisory catalog and does not validate request routing.
|
||||
* @param provider - one provider route owned by this adapter.
|
||||
* @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.
|
||||
*/
|
||||
resolveModelContext(
|
||||
_provider: string,
|
||||
_model: string,
|
||||
): Promise<LlmModelContext | undefined>;
|
||||
resolveModel(
|
||||
provider: string,
|
||||
model: string,
|
||||
_signal?: AbortSignal,
|
||||
): Promise<LlmResolvedModelInfo>;
|
||||
/**
|
||||
* Stream one model call as raw chunks. The only required method.
|
||||
* @param options - the fully-assembled request; implementations must honor `options.signal`.
|
||||
|
||||
@@ -67,7 +67,7 @@ interface LlmFailure {
|
||||
- **每个提供方 HTTP 请求都携带应用归属头。** 适配器发送 `attributionHeaders()`（见下文）作为 `User-Agent` 基线，并通过协议级测试加以证明（mock 服务器断言收到的 header，或对基于库的适配器使用库的 header 钩子）。
|
||||
- **回放状态归适配器所有。** 成功的 `finish` 可以携带重建提供方原生响应所需的无损 JSON 状态。除非 `agent/step-result` listener 改写了内容，否则循环会将其与组装后的 assistant 消息一起存储。后续请求中，仅当历史提供方与目标提供方当前注册到完全相同的适配器实例时，`LlmService` 才会传递该状态。该适配器负责校验状态并拥有所有跨模型或跨提供方转换；其他适配器只会收到提供方无关的内容与 provenance，不会收到私有状态。
|
||||
|
||||
该契约由两个有意保持独立的实现锁定：`dsh-llm-deepseek`（手写 fetch/SSE（Server-Sent Events））和 `dsh-llm-pi-ai`（通过 `@earendil-works/pi-ai` 实现的通用多提供方适配器）。基于库的适配器覆盖 finish 分片错误路径，而传输边界测试证明每个空闲 watchdog 都会停止其实际请求。
|
||||
该契约由两个有意保持独立的实现锁定：`dsh-llm-deepseek`（直接 fetch，SSE（Server-Sent Events）分帧经由 `eventsource-parser`）和 `dsh-llm-pi-ai`（通过 `@earendil-works/pi-ai` 实现的通用多提供方适配器）。基于库的适配器覆盖 finish 分片错误路径，而传输边界测试证明每个空闲 watchdog 都会停止其实际请求。
|
||||
|
||||
## `AppIdentity`：应用归属
|
||||
|
||||
@@ -157,14 +157,30 @@ declare class BlockAssembler {
|
||||
|
||||
## seam
|
||||
|
||||
`LlmAdapter` 是提供方 seam：创建子类、实现 `stream()`，再用 `ctx.llm.registerAdapter(providers, adapter)` 注册一个适配器实例。`GenerateOptions.provider` 选择已注册适配器；`GenerateOptions.model` 会传给该适配器，无需在生命周期启动时注册。重复提供方路由会原子失败。可选的 `providerInfo()` 与异步 `listModels()` 方法为 `LlmService.listProviders()` / `listModels()` 提供分离的 selector 元数据。该目录仅供参考，不是请求白名单：适配器仍是权威，并可接受未列出的模型 id。单独的 `resolveModelContext()` 查询会暴露确切路由上对正确性敏感的容量信息，但不会让目录成员关系具有权威性；缺失表示元数据未知，而不是路由无效。适配器查找发生在 `llm/stream` waterfall（瀑布式事件）的终端 continuation，因此 listener 可以在查找前短路调用，或路由一个可变的一次性请求。`block-start` / `block-end` 的 `index` 关联与 assembler 共同意味着适配器只需 emit 格式正确的分片——块重组不是每个适配器各自的问题。消费方 surface（`ctx.llm.stream()`）与 `llm/stream` waterfall 见 [architecture.md § 内容块与流式传输](../architecture.md#content-blocks-and-streaming-dsh-llm)。
|
||||
`LlmAdapter` 是提供方 seam：创建子类、实现 `stream()`，再用 `ctx.llm.registerAdapter(providers, adapter)` 注册一个适配器实例。`GenerateOptions.provider` 选择已注册适配器；`GenerateOptions.model` 会传给该适配器，无需在生命周期启动时注册。重复提供方路由会原子失败。可选的 `providerInfo()` 与异步 `listModels()` 方法为 `LlmService.listProviders()` / `listModels()` 提供分离的 selector 元数据。该目录仅供参考，不是请求白名单：适配器仍是权威，并可接受未列出的模型 id。单次异步 `resolveModel()` 查询返回确切模型身份，以及可选的对正确性敏感的上下文容量、由模型持有的有序推理强度 ID 和部署默认值；字段缺失表示元数据或能力不可用，而不表示目录成员关系无效。解析器会接收可选的取消信号，并且必须在信号中止后迅速完成结算。`LlmService.resolveModelInfo()` 会校验聚合结果并返回分离值。服务通过最终适配器边界的 `resolveCallConfig()` 校验推理强度并填入默认值，因此直接调用也无法绕过对不支持推理强度的拒绝；直接分派会在等待解析前捕获一项适配器注册。agent loop 则使用 `prepareCall()`，使模型解析、请求头持久记录和分派全程使用同一项注册。适配器查找发生在 `llm/stream` waterfall（瀑布式事件）的终端 continuation，因此 listener 可以在查找前短路调用，或路由一个可变的一次性请求。`block-start` / `block-end` 的 `index` 关联与 assembler 共同意味着适配器只需 emit 格式正确的分片——块重组不是每个适配器各自的问题。消费方 surface（`ctx.llm.stream()`）与 `llm/stream` waterfall 见 [architecture.md § 内容块与流式传输](../architecture.md#content-blocks-and-streaming-dsh-llm)。
|
||||
|
||||
```ts type-equiv
|
||||
/** One model call whose config and adapter registration were resolved together. */
|
||||
interface PreparedLlmCall {
|
||||
/** Detached, deep-frozen config with any adapter-owned default materialized. */
|
||||
readonly config: LlmCallConfig
|
||||
/**
|
||||
* Dispatch this call once through the registration captured during
|
||||
* preparation. The request's call-config fields must match {@link config};
|
||||
* reuse or mismatch fails with `INVALID_PREPARED_CALL`.
|
||||
* @param options - fully assembled request carrying the prepared config.
|
||||
* @returns the chunk stream, including the `llm/stream` waterfall.
|
||||
*/
|
||||
stream(options: GenerateOptions): AsyncIterable<StreamChunk>
|
||||
}
|
||||
```
|
||||
|
||||
```ts public-api
|
||||
/**
|
||||
* Provider-wire adapter for the harness message and stream vocabulary. Register implementations
|
||||
* with `ctx.llm.registerAdapter(providers, adapter)`. Every provider HTTP request must include
|
||||
* `attributionHeaders()`; prove that at the wire or library header-hook boundary. The hand-rolled
|
||||
* DeepSeek and pi-ai adapters intentionally exercise this contract through different internals.
|
||||
* `attributionHeaders()`; prove that at the wire or library header-hook boundary. The direct-fetch
|
||||
* DeepSeek and library-backed pi-ai adapters intentionally exercise this contract through different internals.
|
||||
*/
|
||||
declare abstract class LlmAdapter {
|
||||
/**
|
||||
@@ -182,16 +198,19 @@ declare abstract class LlmAdapter {
|
||||
*/
|
||||
listModels(_provider: string): Promise<readonly LlmModelInfo[]>;
|
||||
/**
|
||||
* Resolve context capacity for one model accepted by this adapter. Absence
|
||||
* means the adapter does not know the capacity, not that routing is invalid.
|
||||
* @param _provider - one provider route owned by this adapter.
|
||||
* @param _model - exact model id passed to {@link GenerateOptions.model}.
|
||||
* @returns provider-owned context metadata, or `undefined` when unavailable.
|
||||
* Resolve all metadata available for one exact model. This query is
|
||||
* independent of the advisory catalog and does not validate request routing.
|
||||
* @param provider - one provider route owned by this adapter.
|
||||
* @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.
|
||||
*/
|
||||
resolveModelContext(
|
||||
_provider: string,
|
||||
_model: string,
|
||||
): Promise<LlmModelContext | undefined>;
|
||||
resolveModel(
|
||||
provider: string,
|
||||
model: string,
|
||||
_signal?: AbortSignal,
|
||||
): Promise<LlmResolvedModelInfo>;
|
||||
/**
|
||||
* Stream one model call as raw chunks. The only required method.
|
||||
* @param options - the fully-assembled request; implementations must honor `options.signal`.
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# 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
|
||||
session.md: 2cbbac8042d04522fea0b1ed7a66c503e4b63f4e
|
||||
session.zh.md: e932c8f99f684f1b8985b006ab4ddb145db966bd
|
||||
# pnpm run verify-translation-pairing --write docs/core-data-structures/session.md
|
||||
session.md: 59bcf027c3ec728c5583478c7d17bd6eef2dc2fa
|
||||
session.zh.md: 01b6f080b5fcf7b83ca46b99a8d80113a6ebe8bf
|
||||
|
||||
@@ -175,7 +175,7 @@ The request envelope — the `EpochHeader` (call config + rendered system prompt
|
||||
* canonical empty optional fields are absent.
|
||||
*/
|
||||
interface EpochHeader {
|
||||
/** The conversation's call configuration (provider, model, and sampling scalars). */
|
||||
/** The conversation's call configuration (provider, model, reasoning effort, and sampling scalars). */
|
||||
config: LlmCallConfig
|
||||
/** Rendered system prompt text; absent for a system-less request. */
|
||||
system?: string
|
||||
|
||||
@@ -177,7 +177,7 @@ interface TodoItem {
|
||||
* canonical empty optional fields are absent.
|
||||
*/
|
||||
interface EpochHeader {
|
||||
/** The conversation's call configuration (provider, model, and sampling scalars). */
|
||||
/** The conversation's call configuration (provider, model, reasoning effort, and sampling scalars). */
|
||||
config: LlmCallConfig
|
||||
/** Rendered system prompt text; absent for a system-less request. */
|
||||
system?: string
|
||||
|
||||
Reference in New Issue
Block a user