docs: anchor each subsystem page to its package group; make group READMEs thin tables
core.md read as a type grab-bag: LLM wire vocabulary up front, the agent/loop story buried, and no correspondence to packages/core. It now opens on the packages/core control spine — the package-by-package loop map with a Page column into session/system-prompt/tools/scope — and keeps only what the spine group declares plus the repo-wide patterns: the Agent handle with its delivery/cancellation/interception contracts, the SessionEvent envelope, branded ids, the …Map pattern. The conversation vocabulary (Message/ContentBlock, the model request, adapters — 17 type-equiv blocks) moves to llm-streaming.md, which now declares packages/llm end-to-end; the duplicate ContentBlockMap paste near its seam section folds into the moved section, and the manifest, LINK_MAP, README table rows, website label (Core data structures → Core), and inbound anchors follow. Every packages/<group>/README pair is now a thin front door in one shape: a why-first intro (bash's seam-pattern-first paragraph rewritten as 'shell execution for the agent'), the package table, and a closing pointer to the owning docs/subsystems page — the bash-style table stays the load-bearing middle. Load-bearing trailing paragraphs relocate rather than vanish: the fs no-timeout rationale becomes a filesystem.md section (both languages), session's four sectioned tables merge into one 12-row table, examples' legacy-bin H2 collapses to a pointer at jsonrpc-demo's README, and design rationale that already lives in an Agent Note or subsystem page is now linked instead of restated. All 40 pair records re-recorded.
This commit is contained in:
Tianyi Cui
@@ -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 docs/subsystems/README.md
|
||||
README.md: 59e5a4db09d114e96c19dc0fe29a5ebe8d8c8d32
|
||||
README.zh.md: 6b5fa58bf45654708b08d780aa0e17a8d90b7e17
|
||||
README.md: d225e5f4eeb31d1e6c71cbd8311e28bae1e8b3a5
|
||||
README.zh.md: 9f78ac3e1c79440b053ee4e344dbdba2c11b3dfc
|
||||
|
||||
@@ -6,8 +6,8 @@ One page per subsystem of the DeepSeek Harness: what it is, the data structures
|
||||
|
||||
| Page | Owns |
|
||||
|---|---|
|
||||
| [core.md](core.md) | the spine vocabulary every turn traffics in — `Message`/`ContentBlock`, `StreamChunk`, `SessionEvent`, the `Agent` handle, `ToolDefinition`, branded ids, the `…Map → derived-union` pattern |
|
||||
| [llm-streaming.md](llm-streaming.md) | the `StreamChunk` wire protocol + adapter contract, `BlockAssembler`, the `LlmAdapter` seam |
|
||||
| [core.md](core.md) | the `packages/core` control spine: the package-by-package loop map, the `Agent` handle with its delivery/cancellation/interception contracts, the `SessionEvent` envelope, branded ids, the `…Map → derived-union` pattern |
|
||||
| [llm-streaming.md](llm-streaming.md) | the `packages/llm` conversation vocabulary — `Message`/`ContentBlock`, the assembled model request, the `StreamChunk` wire protocol + adapter contract, `BlockAssembler`, the `LlmAdapter` seam |
|
||||
| [token-meter.md](token-meter.md) | immutable scalar and positional replay measurements with consumed-log revisions |
|
||||
| [scope.md](scope.md) | scoped registration identity, dispatch carriers, and the owned `Scope` context |
|
||||
| [typert.md](typert.md) | Remote invocation descriptors, lookup/Context declarations, TypeRT registries, and the Host Gateway/Client API seams |
|
||||
|
||||
@@ -6,8 +6,8 @@
|
||||
|
||||
| 页面 | 负责内容 |
|
||||
|---|---|
|
||||
| [core.md](core.md) | 每个轮次都在使用的主干词汇——`Message`/`ContentBlock`、`StreamChunk`、`SessionEvent`、`Agent` 句柄、`ToolDefinition`、品牌化 id，以及 `…Map → 派生联合` 模式 |
|
||||
| [llm-streaming.md](llm-streaming.md) | `StreamChunk` 协议格式（wire format）+ 适配器契约（adapter contract）、`BlockAssembler`、`LlmAdapter` seam |
|
||||
| [core.md](core.md) | `packages/core` 控制主干：逐包循环地图、`Agent` 句柄及其投递/取消/拦截契约、`SessionEvent` 信封、品牌化 id，以及 `…Map → 派生联合` 模式 |
|
||||
| [llm-streaming.md](llm-streaming.md) | `packages/llm` 的对话词汇——`Message`/`ContentBlock`、组装完成的模型请求、`StreamChunk` 协议格式（wire format）+ 适配器契约（adapter contract）、`BlockAssembler`、`LlmAdapter` seam |
|
||||
| [token-meter.md](token-meter.md) | 不可变的标量与位置回放度量，附带已消费日志修订号 |
|
||||
| [scope.md](scope.md) | 作用域注册标识、dispatch 载体，以及拥有的 `Scope` 上下文 |
|
||||
| [typert.md](typert.md) | 远程调用描述符、lookup/Context 声明、TypeRT 注册表，以及 Host Gateway/Client API seam |
|
||||
|
||||
@@ -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 docs/subsystems/compaction.md
|
||||
compaction.md: eeea249fa7a9f95e607edb10e6a8c93a24162b64
|
||||
compaction.zh.md: 24c55f062404ff827292f324392347ad59bb7846
|
||||
compaction.md: 5aef839192ea6f67bb409622187fe65fed795e73
|
||||
compaction.zh.md: 63b28518e68f71cc648d2f4e78a82bc5beafb621
|
||||
|
||||
@@ -224,7 +224,7 @@ pruneContent(blocks: readonly ContentBlock[]): ContentBlock[] | null
|
||||
pruneSession(session: Session): PruneResult
|
||||
```
|
||||
|
||||
Types: [ContentBlock](core.md) · [Session](session.md)
|
||||
Types: [ContentBlock](llm-streaming.md) · [Session](session.md)
|
||||
|
||||
Source: [`packages/compact/compact-tool-result-prune/src/index.ts:44`](../../packages/compact/compact-tool-result-prune/src/index.ts)
|
||||
<!-- END GENERATED cordis-surface -->
|
||||
|
||||
@@ -224,7 +224,7 @@ pruneContent(blocks: readonly ContentBlock[]): ContentBlock[] | null
|
||||
pruneSession(session: Session): PruneResult
|
||||
```
|
||||
|
||||
Types: [ContentBlock](core.md) · [Session](session.md)
|
||||
Types: [ContentBlock](llm-streaming.md) · [Session](session.md)
|
||||
|
||||
Source: [`packages/compact/compact-tool-result-prune/src/index.ts:44`](../../packages/compact/compact-tool-result-prune/src/index.ts)
|
||||
<!-- END GENERATED cordis-surface -->
|
||||
|
||||
@@ -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 docs/subsystems/core.md
|
||||
core.md: 8f27727d63e598fbf31b09a87ab53ad686155b4f
|
||||
core.zh.md: fff5bd502cbed6f2167eb23731fb5c3825efb7af
|
||||
core.md: ba9319d377cf250148a145ba3f1fa1baa967c858
|
||||
core.zh.md: 276dc4f99f1f802e66aca050b2fbcdc178931611
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -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 docs/subsystems/filesystem.md
|
||||
filesystem.md: 1999399254fa5d72ab222a42a2fa8f4b890da50a
|
||||
filesystem.zh.md: 044a1c5be91ed8bec5d0442cc6f7edfde6870785
|
||||
filesystem.md: 591f1b4d4b1177ccbe7c2280d2054da5d4be8b99
|
||||
filesystem.zh.md: d599e48c1fba2d564a544f628ca3475b781e5cd5
|
||||
|
||||
@@ -256,6 +256,10 @@ type FsErrorCode =
|
||||
|
||||
`FS_NOT_DIRECTORY`, `FS_PERMISSION_DENIED`, and `FS_IO_ERROR` are used by directory listing to distinguish an existing non-directory target, a denied listing, and an unexpected backend I/O failure. `FS_SANDBOX_DENIED` is a POLICY refusal from a sandbox-enforcing backend (`dsh-fs-sandbox`) — the mode fence denied a write/edit — distinct from `FS_PERMISSION_DENIED` (the host kernel refusing). `FS_NOT_OBSERVED` means the policy plugin has no prior-observation record for this owner (or a `createIfAbsent` hit an existing file). `FS_STALE_VERSION` means the backend version no longer matches the observed one (or an edit hit a missing target). Freshness authorization has no partial/full distinction, so there is no `FS_PARTIAL_OBSERVATION`.
|
||||
|
||||
## No timeouts on file IO
|
||||
|
||||
`read`/`write`/`edit` take **no** `timeoutMs`, and the provider seam arms no deadline — unlike bash and web (which consume [`@deepseek-ai/dsh-timeout`](../../packages/util/timeout/README.md)) and the bash-backed `glob`/`grep` (whose declared `timeoutMs` is enforced by `@deepseek-ai/dsh-timeout-policy`): those are process-backed, where a deadline can really kill the work. A local syscall is best-effort-abortable at most — a timeout could not force an in-progress `fsync`/`rename` to stop, so a deadline here would be a knob that cannot deliver on its promise, and an implicit default in the exact place explicit-over-implicit forbids. Both reference agents (Claude Code, Codex) leave file IO untimed for the same reason; cancellation still propagates through the tool-execution signal for best-effort abort at syscall boundaries.
|
||||
|
||||
## The service and the plugin
|
||||
|
||||
`FileSystem` (`ctx.fs`, abstract) owns the provider primitives: `resolve`, `processPath`, `fileUrl`, `contains`, `stat`, `lstat`, `readText`, `streamText`, `listDir`, `writeText`, and `editText`. `dsh-fs-policy` registers **no service** — it is a plugin that adds policy through the `fs/*` event gate: it decides the write/edit intent waterfalls (supplying `createIfAbsent`/`replaceIfVersion`/`{ version }` or throwing `FS_NOT_OBSERVED`) and records on `fs/observed`. The executor is `dsh-tool-fs`: it reads/writes/edits through `ctx.fs`, dispatches the waterfalls, and emits the recording event. The generated [`ctx.fs` section](#ctxfs--filesystem-abstract-seam) below shows the exact signatures.
|
||||
|
||||
@@ -256,6 +256,10 @@ type FsErrorCode =
|
||||
|
||||
目录列表使用 `FS_NOT_DIRECTORY`、`FS_PERMISSION_DENIED` 与 `FS_IO_ERROR` 区分已存在但并非目录的目标、被拒绝的列表操作和意外的后端 I/O 失败。`FS_SANDBOX_DENIED` 是强制执行沙箱的后端（`dsh-fs-sandbox`）所作的策略拒绝——模式边界拒绝了写入/编辑——与 `FS_PERMISSION_DENIED`（宿主内核拒绝）不同。`FS_NOT_OBSERVED` 表示策略插件没有此所有者的先前观察记录（或 `createIfAbsent` 遇到了现有文件）。`FS_STALE_VERSION` 表示后端版本不再与观察到的版本匹配（或编辑操作遇到缺失目标）。新鲜度授权没有部分/完整之分，因此不存在 `FS_PARTIAL_OBSERVATION`。
|
||||
|
||||
## 文件 IO 不设超时
|
||||
|
||||
`read`/`write`/`edit` **不**接受 `timeoutMs`，提供方 seam 也不设置截止时间——不同于 bash 与 web（它们消费 [`@deepseek-ai/dsh-timeout`](../../packages/util/timeout/README.md)）以及 bash 支撑的 `glob`/`grep`（其声明的 `timeoutMs` 由 `@deepseek-ai/dsh-timeout-policy` 强制执行）：那些是进程支撑的，截止时间可以真正终止工作。本地系统调用至多是尽力中止——超时无法迫使进行中的 `fsync`/`rename` 停下，因此这里的截止时间会成为无法兑现承诺的旋钮，而且恰好落在"显式优于隐式"禁止隐式默认值的位置。两个参照 agent（Claude Code、Codex）出于同样原因不给文件 IO 计时；取消仍通过工具执行 signal 传播，在系统调用边界尽力中止。
|
||||
|
||||
## 服务与插件
|
||||
|
||||
`FileSystem`（`ctx.fs`，abstract）拥有提供方原语：`resolve`、`processPath`、`fileUrl`、`contains`、`stat`、`lstat`、`readText`、`streamText`、`listDir`、`writeText` 与 `editText`。`dsh-fs-policy` **不注册服务**——它是一个通过 `fs/*` 事件门禁添加策略的插件：对写入/编辑意图 waterfall 作出决策（提供 `createIfAbsent`/`replaceIfVersion`/`{ version }`，或抛出 `FS_NOT_OBSERVED`），并在 `fs/observed` 上记录。执行器是 `dsh-tool-fs`：它通过 `ctx.fs` 读取/写入/编辑，分发 waterfall，并 emit 记录事件。下方生成的 [`ctx.fs` 小节](#ctxfs--filesystem-abstract-seam) 展示确切的 `ctx.fs` 签名。
|
||||
|
||||
@@ -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 docs/subsystems/llm-streaming.md
|
||||
llm-streaming.md: fe4a831660dd81b33a1cd7dc9a9d7026f3831991
|
||||
llm-streaming.zh.md: a10b696ec0887e139785fc7e95d8641e6496de79
|
||||
llm-streaming.md: b3f850f4d07ad9e36d0e0db71dd9e0498e468767
|
||||
llm-streaming.zh.md: bb31c14b9bd0453399d83968b1062f67819caca3
|
||||
|
||||
@@ -2,10 +2,82 @@
|
||||
|
||||
English | [中文](llm-streaming.zh.md)
|
||||
|
||||
The wire-level streaming vocabulary of [dsh-llm](../../packages/llm/llm). [core.md](core.md) introduces `StreamChunk`, `Message`, and `ContentBlock`; this page owns the full chunk protocol, the adapter contract every adapter must obey, and the shared assembler.
|
||||
The conversation and streaming vocabulary of [`packages/llm`](../../packages/llm/README.md): the `Message`/`ContentBlock` shapes every request and durable history share, the fully-assembled model request, the raw `StreamChunk` protocol, the adapter contract every adapter must obey, and the shared assembler. The [core spine](core.md) holds and logs these values on every turn; this page declares them.
|
||||
|
||||
Source: [`packages/llm/llm/src/types.ts`](../../packages/llm/llm/src/types.ts)
|
||||
|
||||
<a id="content-blocks-and-messages"></a>
|
||||
|
||||
## Content blocks and messages
|
||||
|
||||
A conversation is `Message`s; a message is an array of typed **content blocks**. The block union derives from `ContentBlockMap`.
|
||||
|
||||
Source: [`packages/llm/llm/src/types.ts`](../../packages/llm/llm/src/types.ts)
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Merge-extensible content blocks keyed by `type`. New core blocks must land
|
||||
* with adapter, UI, and compaction support.
|
||||
*/
|
||||
interface ContentBlockMap {
|
||||
'text': TextBlock
|
||||
'reasoning': ReasoningBlock
|
||||
'tool-call': ToolCallBlock
|
||||
'tool-result': ToolResultBlock
|
||||
}
|
||||
```
|
||||
|
||||
The block interfaces (full fields in source): `TextBlock` (`text`), `ReasoningBlock` (thinking, distinct from visible text), `ToolCallBlock` (`id: CallId`, `name`, raw-JSON `arguments`), `ToolResultBlock` (`toolCallId`, nested `content: ContentBlock[]`, `isError?`). `ContentBlock = ContentBlockMap[ContentBlockType]`. The core set is limited to blocks every shipping path honors — multimodal content (images, audio, …) has no core block type; a feature that needs one adds it via the merge-extensible map together with the adapter/UI/compaction support that honors it.
|
||||
|
||||
Source: [`packages/llm/llm/src/message.ts`](../../packages/llm/llm/src/message.ts)
|
||||
|
||||
A `Message` is one identified, immutable role/source/content value. Model-produced assistant messages carry provider/model ownership and optional adapter-private replay metadata in their source:
|
||||
|
||||
```ts type-equiv
|
||||
/** Provider ownership and adapter-private replay data for an assistant message. */
|
||||
interface AssistantProvenance {
|
||||
/** Provider route that produced the message. */
|
||||
provider: string
|
||||
/** Provider model id that produced the message. */
|
||||
model: string
|
||||
/**
|
||||
* Lossless-JSON adapter state needed to replay the provider response.
|
||||
* `LlmService` exposes it to a target adapter only when that adapter instance
|
||||
* currently owns both this historical provider and the target provider.
|
||||
*/
|
||||
replayState?: unknown
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** One immutable message representation shared by delivery, durable history, and model requests. */
|
||||
interface Message {
|
||||
/** Stable identity preserved across every representation boundary. */
|
||||
readonly id: MessageId
|
||||
/** Provider-neutral conversation role. */
|
||||
readonly role: 'system' | 'user' | 'assistant'
|
||||
/** Exact model-facing blocks. */
|
||||
readonly content: ContentBlock[]
|
||||
/** Required producer provenance. */
|
||||
readonly source: MessageSource
|
||||
}
|
||||
```
|
||||
|
||||
Where a message came from is itself a merge-extensible sum type:
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Where a message (or injected content) came from.
|
||||
* Merge-extensible sum type — plugins add their own `kind`s.
|
||||
*/
|
||||
interface MessageSourceMap {
|
||||
user: { kind: 'user' }
|
||||
plugin: { kind: 'plugin'; plugin: string }
|
||||
model: ModelMessageSource
|
||||
tool: ToolMessageSource
|
||||
}
|
||||
```
|
||||
|
||||
## `StreamChunk` — the raw protocol
|
||||
|
||||
A streaming response interleaves several typed blocks (text, reasoning, multiple tool calls). `index` ties each delta to its block; `block-end` carries the fully-assembled `ContentBlock` so consumers don't have to re-assemble deltas themselves. It is a **closed** discriminated union — a `switch` over `type` ends with `assertNever`, so adding a variant breaks compilation at every consumer that must handle it.
|
||||
@@ -15,9 +87,8 @@ A streaming response interleaves several typed blocks (text, reasoning, multiple
|
||||
* Raw streaming protocol emitted by adapters.
|
||||
* Block indexes correlate interleaved deltas, and `block-end` carries the
|
||||
* assembled block. Adapters emit usage before the terminal finish and nothing
|
||||
* afterward; tool arguments remain raw JSON strings. An adapter implementation
|
||||
* may throw, but `LlmService.stream()` normalizes that failure to a terminal
|
||||
* `error` or `aborted` finish before exposing it to consumers.
|
||||
* afterward; tool arguments remain raw JSON strings. Failures either throw or
|
||||
* end with `error`/`aborted`, and consumers must handle both paths.
|
||||
*/
|
||||
type StreamChunk =
|
||||
| { type: 'block-start'; index: number; blockType: ContentBlockType }
|
||||
@@ -65,10 +136,10 @@ Every adapter MUST obey these, and every consumer may rely on them:
|
||||
- **Provider stalls are bounded at the transport.** Both shipping remote adapters expose positive finite `streamIdleTimeoutMs` with a five-minute default. The watchdog arms only while iterator `next()` is outstanding, uses one stable signal for the whole request, maps its own expiry to `TIMEOUT`, and keeps an earlier caller abort as `ABORTED`.
|
||||
- **Context overflow has one canonical code.** Both DeepSeek adapters classify explicit provider detail through `isContextWindowExceededError()` and surface `CONTEXT_WINDOW_EXCEEDED`, whether the failure arrives as a thrown HTTP `LlmError` or an in-band finish error. Consumers route on the code, never provider text.
|
||||
- **An empty completion is a retryable error, not a silent success.** Both adapters map a terminal `stop` finish that carried no content blocks to `finish {kind:'error'}` with the canonical `EMPTY_RESPONSE` code, and `dsh-llm-retry` retries it by default; see [empty model responses are retryable](../../.agents/notes/implemented/bug-fix/2026-07-24-empty-model-response-is-retryable.md).
|
||||
- **Every provider HTTP request carries the app-attribution header.** Adapters send `attributionHeaders()` (below), the `User-Agent` baseline.
|
||||
- **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. 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.
|
||||
|
||||
Two independent implementations obey this contract: `dsh-llm-deepseek` uses direct fetch with SSE framing through `eventsource-parser`, while `dsh-llm-pi-ai` provides a generic multi-provider adapter through `@earendil-works/pi-ai`. Both carry cancellation and the idle watchdog to the provider 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.
|
||||
|
||||
## `ResolvedRetryPolicy`
|
||||
|
||||
@@ -142,9 +213,8 @@ declare class BlockAssembler {
|
||||
push(chunk: StreamChunk): void;
|
||||
/**
|
||||
* Assemble all blocks seen so far, in stream order.
|
||||
* @returns one block per seen index, except that max-token truncation drops
|
||||
* tool calls that cannot be executed safely; an open block assembles from
|
||||
* its accumulated deltas (an unknown block type never closed by `block-end` throws).
|
||||
* @returns one block per seen index; an open block assembles from its
|
||||
* accumulated deltas (an unknown block type never closed by `block-end` throws).
|
||||
*/
|
||||
blocks(): ContentBlock[];
|
||||
/** Usage from the `usage` chunk; undefined until one arrives. */
|
||||
@@ -162,6 +232,263 @@ declare class BlockAssembler {
|
||||
}
|
||||
```
|
||||
|
||||
<a id="the-model-request-and-result"></a>
|
||||
|
||||
## The model request
|
||||
|
||||
One model call is a fully-assembled `GenerateOptions`. The adapter answers with a raw [`StreamChunk`](#streamchunk--the-raw-protocol) stream; the consumer assembles it with [`BlockAssembler`](#blockassembler).
|
||||
|
||||
Source: [`packages/llm/llm/src/types.ts`](../../packages/llm/llm/src/types.ts)
|
||||
|
||||
Provider and model discovery uses small provider-neutral descriptors. A model catalog is advisory: routing still keys on a registered provider, and an adapter may accept unlisted model ids.
|
||||
|
||||
Registering an adapter returns a handle: the disposer, plus the atomic route replacement a plugin whose route set is user-configurable needs.
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* What {@link LlmService.registerAdapter} returns: the disposer, plus an
|
||||
* atomic route replacement for the same adapter instance.
|
||||
*/
|
||||
interface AdapterRegistrationHandle {
|
||||
/** Release every route this registration currently holds. */
|
||||
(): void
|
||||
/**
|
||||
* Replace this registration's routes with `providers`, keeping the same
|
||||
* adapter instance. The candidate set is validated in full first — a
|
||||
* conflict with another adapter, an invalid name, or bad provider metadata
|
||||
* throws and leaves the current routes untouched — and the swap itself is
|
||||
* one synchronous section, so no request can observe a gap. An empty array
|
||||
* is legal here (a settings section that emptied holds zero routes while
|
||||
* staying registered), unlike an empty initial registration.
|
||||
*
|
||||
* Throws `LlmError` with code `REGISTRATION_DISPOSED` once the registration
|
||||
* has been released: its routes are gone and its disposer has already run,
|
||||
* so anything registered afterwards would have no owner left to release it.
|
||||
* @param providers - the complete next route set for this registration.
|
||||
*/
|
||||
replace(providers: string[]): void
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Display metadata for one registered provider route. */
|
||||
interface LlmProviderInfo {
|
||||
/** Provider route key used by {@link GenerateOptions.provider}. */
|
||||
id: string
|
||||
/** Human-readable provider name for selectors and diagnostics. */
|
||||
name: string
|
||||
}
|
||||
```
|
||||
|
||||
Adapter plugins additionally declare which routes *could* run through `registerConfigurableProviders()`, addressing each one's user-settings section, so configuration surfaces can offer dormant providers before any route registers.
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* One provider route an adapter plugin can activate through configuration,
|
||||
* whether or not the route is currently registered. Configuration surfaces
|
||||
* merge this directory with `listProviders()` to offer every configurable
|
||||
* provider alongside its live/dormant state.
|
||||
*/
|
||||
interface LlmConfigurableProvider {
|
||||
/** Provider route key this entry activates when configured. */
|
||||
provider: string
|
||||
/** Human-readable provider name for configuration surfaces. */
|
||||
displayName: string
|
||||
/** User-settings namespace whose section configures this provider. */
|
||||
settingsNs: string
|
||||
/**
|
||||
* Path from that namespace's section root to this provider's profile
|
||||
* object; empty when the whole section is the profile.
|
||||
*/
|
||||
settingsPath: readonly string[]
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** One adapter-discovered model; catalog membership is advisory, not request validation. */
|
||||
interface LlmModelInfo {
|
||||
/** Provider route that owns this model entry. */
|
||||
provider: string
|
||||
/** Model id passed to {@link GenerateOptions.model}. */
|
||||
id: string
|
||||
/** Human-readable model name for selectors. */
|
||||
name: string
|
||||
/** Optional user-facing distinction from otherwise similar models. */
|
||||
description?: string
|
||||
}
|
||||
```
|
||||
|
||||
Correctness-sensitive metadata is resolved separately from the advisory catalog and is owned by the adapter serving the exact route. Context capacity, adapter call defaults, 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. */
|
||||
interface LlmModelContext {
|
||||
/** Maximum combined request and response context in tokens. */
|
||||
contextWindow: number
|
||||
}
|
||||
```
|
||||
|
||||
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-configured per-request output cap materialized when callers omit one. */
|
||||
defaultMaxTokens?: number
|
||||
/** 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
|
||||
* the derived history (dsh-agent-loop); a hand-built one-shot passes any list.
|
||||
*/
|
||||
messages: Message[]
|
||||
/** System prompt text (adapters map to the provider's system slot). */
|
||||
system?: string
|
||||
/** Tool schemas (adapters map to the provider's `tools` field). */
|
||||
tools?: ToolSchema[]
|
||||
temperature?: number
|
||||
maxTokens?: number
|
||||
/**
|
||||
* Stop sequences: generation halts as soon as the model produces any one of
|
||||
* these strings (adapters map to the provider's stop field, e.g. OpenAI
|
||||
* `stop`). The stop string itself is not included in the output.
|
||||
*/
|
||||
stop?: string[]
|
||||
signal?: AbortSignal
|
||||
/**
|
||||
* Session identity stamped by the loop for listener routing. Adapters ignore
|
||||
* it; replay uses it to keep concurrent parent and child cursors independent.
|
||||
*/
|
||||
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. Ordinary conversation requests leave it unset.
|
||||
*/
|
||||
purpose?: 'compaction' | 'session-title'
|
||||
}
|
||||
```
|
||||
|
||||
Why a model response stopped is a merge-extensible reason. Terminal provider failures carry the streaming contract's [`LlmFailure`](#llmfailure):
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Why a model response stopped.
|
||||
* Merge-extensible so adapters can surface provider-specific reasons.
|
||||
*/
|
||||
interface FinishReasonMap {
|
||||
'stop': { kind: 'stop' }
|
||||
'tool-calls': { kind: 'tool-calls' }
|
||||
'max-tokens': { kind: 'max-tokens' }
|
||||
'aborted': { kind: 'aborted'; failure: LlmFailure }
|
||||
'error': { kind: 'error'; failure: LlmFailure }
|
||||
}
|
||||
```
|
||||
|
||||
`FinishReason = FinishReasonMap[keyof FinishReasonMap]`. `TokenUsage` (per-call accounting with disjoint cache fields) is detailed [below](#tokenusage).
|
||||
|
||||
`GenerateOptions.tools` carries `ToolSchema` — the JSON-schema description of a tool, as sent to the model. It is declared in dsh-llm (not dsh-tools) precisely because it is part of the request the loop assembles every step:
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* JSON-schema description of a tool, as sent to the model.
|
||||
*
|
||||
* Declared here (not in dsh-tools) because it is part of {@link GenerateOptions};
|
||||
* dsh-tools' ToolDefinition and dsh-system-prompt's PromptAssembly both import
|
||||
* it from this package.
|
||||
*/
|
||||
interface ToolSchema {
|
||||
name: string
|
||||
description: string
|
||||
/** JSON Schema object for the arguments. */
|
||||
parameters: Record<string, unknown>
|
||||
}
|
||||
```
|
||||
|
||||
The model-facing `ToolSchema` is the wire shape; the registered `ToolDefinition` that produces it (schema + `execute`) is on [tools.md](tools.md).
|
||||
|
||||
### The request envelope: `LlmCallConfig` and the logged header
|
||||
|
||||
The loop builds each request from logged state. `EpochHeader` records call config, adapter-default provenance, rendered prompt, and authoritative returned tool order (configured by `toolOrder`, or lexicographic when unset) 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, reasoning effort, or sampling. Before the waterfall, the loop removes values marked as adapter defaults so exact-model preparation materializes the selected route's current values; unmarked explicit settings remain in the proposal. After the waterfall, preparation rejects unsupported explicit effort ids without clamping and logs the effective config plus provenance under the turn signal. The prepared call keeps one adapter registration through dispatch. 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 the `system` slot (the rendered prompt assembly) followed by 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 dev invariant recomputes exactly this equation against every loop-built request.
|
||||
|
||||
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, 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[]
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Effective config fields supplied by exact-model adapter resolution rather
|
||||
* than by the caller's request proposal.
|
||||
*/
|
||||
interface LlmCallConfigAdapterDefaults {
|
||||
reasoningEffort?: true
|
||||
maxTokens?: true
|
||||
}
|
||||
```
|
||||
|
||||
## 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 `providerRetryPolicy()` is captured per route with normal defaults, while `providerInfo()` and asynchronous `listModels()` 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, an adapter-configured `defaultMaxTokens`, and ordered model-owned reasoning ids with an optional deployment default; absent fields mean unavailable metadata or provider-owned behavior, not invalid catalog membership. The resolver receives optional cancellation and must settle promptly after abort. `LlmService.resolveModelInfo()` validates and detaches the aggregate. At the final adapter boundary, `resolveCallConfig()` materializes the output default only when `maxTokens` is absent and validates and materializes reasoning, so direct calls cannot bypass either configured behavior; 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, retain detached context metadata from that exact lookup, and report which config fields the adapter defaulted. 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. AgentLoop observes a request attempt once the outer waterfall returns a stream handle; that limited boundary does not prove a lazy terminal adapter was constructed or began provider I/O. 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).
|
||||
@@ -171,8 +498,6 @@ declare class BlockAssembler {
|
||||
interface PreparedLlmCall {
|
||||
/** Detached, deep-frozen config with any adapter-owned default materialized. */
|
||||
readonly config: LlmCallConfig
|
||||
/** Immutable retry policy captured with the adapter registration. */
|
||||
readonly retryPolicy: ResolvedRetryPolicy
|
||||
/** Detached context metadata resolved with the registration-bound call. */
|
||||
readonly context?: LlmModelContext
|
||||
/** Config fields materialized by the captured adapter rather than proposed by the caller. */
|
||||
@@ -239,22 +564,7 @@ declare abstract class LlmAdapter {
|
||||
}
|
||||
```
|
||||
|
||||
`ContentBlockType` (the key set the `index`-correlated blocks carry) derives from `ContentBlockMap`:
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Merge-extensible content blocks keyed by `type`. New core blocks must land
|
||||
* with adapter, UI, and compaction support.
|
||||
*/
|
||||
interface ContentBlockMap {
|
||||
'text': TextBlock
|
||||
'reasoning': ReasoningBlock
|
||||
'tool-call': ToolCallBlock
|
||||
'tool-result': ToolResultBlock
|
||||
}
|
||||
```
|
||||
|
||||
See [core.md § Content blocks and messages](core.md#content-blocks-and-messages) for the block interfaces.
|
||||
`ContentBlockType` (the key set the `index`-correlated blocks carry) derives from [`ContentBlockMap`](#content-blocks-and-messages) above.
|
||||
|
||||
<!-- BEGIN GENERATED cordis-surface (gen-cordis-catalog.ts) — do not edit between markers -->
|
||||
|
||||
@@ -293,9 +603,9 @@ listProviders(): LlmProviderInfo[]
|
||||
* entry, or a provider already declared by any registration throws
|
||||
* `LlmError` without registering the rest. Disposed with the fiber.
|
||||
* @param entries - every configurable provider this plugin owns.
|
||||
* @returns a handle that withdraws all of them, and can atomically replace them.
|
||||
* @returns the disposer that withdraws all of them.
|
||||
*/
|
||||
registerConfigurableProviders(entries: readonly LlmConfigurableProvider[]): DirectoryRegistrationHandle
|
||||
registerConfigurableProviders(entries: readonly LlmConfigurableProvider[]): () => void
|
||||
|
||||
/**
|
||||
* List every declared configurable provider, registered or dormant.
|
||||
@@ -303,29 +613,6 @@ registerConfigurableProviders(entries: readonly LlmConfigurableProvider[]): Dire
|
||||
*/
|
||||
listConfigurableProviders(): LlmConfigurableProvider[]
|
||||
|
||||
/**
|
||||
* Offer to interrogate provider endpoints on behalf of the settings
|
||||
* namespace this plugin owns. The namespace is the key because that is what
|
||||
* a configuration surface already holds from the configurable-provider
|
||||
* directory, and because a provider being *added* has no route to name yet.
|
||||
* Disposed with the fiber.
|
||||
* @param settingsNs - the namespace whose profiles this discovery serves.
|
||||
* @param discover - interrogates one endpoint; must honor `request.signal`.
|
||||
* @returns the disposer that withdraws the offer.
|
||||
*/
|
||||
registerModelDiscovery( settingsNs: string, discover: (request: LlmModelDiscoveryRequest) => Promise<readonly LlmDiscoveredModel[]>, ): () => void
|
||||
|
||||
/**
|
||||
* Interrogate one provider endpoint for the models it advertises. The
|
||||
* request describes a draft, not a stored route, so nothing here reads or
|
||||
* writes settings or credentials — the caller owns both, and the reply is
|
||||
* candidate metadata a surface may offer for adoption.
|
||||
* @param settingsNs - namespace whose registered discovery serves this draft.
|
||||
* @param request - the endpoint, protocol, and one-shot credential to use.
|
||||
* @returns the advertised models, deduplicated in endpoint order.
|
||||
*/
|
||||
async discoverModels( settingsNs: string, request: LlmModelDiscoveryRequest, ): Promise<LlmDiscoveredModel[]>
|
||||
|
||||
/**
|
||||
* Resolve the retry policy captured when one provider route was registered.
|
||||
* @param provider - registered provider route to inspect.
|
||||
@@ -375,22 +662,22 @@ async resolveCallConfig(config: LlmCallConfig, signal?: AbortSignal): Promise<Ll
|
||||
async prepareCall(config: LlmCallConfig, signal?: AbortSignal): Promise<PreparedLlmCall>
|
||||
|
||||
/**
|
||||
* Stream one model call as raw chunks (token-level deltas). Replay state is
|
||||
* retained only when the same adapter instance owns its historical provider
|
||||
* and the target provider. Final adapter selection remains fixed through
|
||||
* asynchronous exact-model resolution and dispatch. Adapter selection,
|
||||
* dispatch, and iteration failures become terminal `error` or `aborted`
|
||||
* finish chunks; middleware, nested-call, cleanup, and consumer failures
|
||||
* remain thrown.
|
||||
* Stream one model call as raw chunks (token-level deltas). Throws
|
||||
* `LlmError` with code `NO_ADAPTER` if no adapter is registered for
|
||||
* `options.provider`. Replay state is retained only when the same adapter
|
||||
* instance owns its historical provider and the target provider. Final
|
||||
* adapter selection remains fixed through asynchronous exact-model resolution
|
||||
* and dispatch. Selection, dispatch, and iteration failures retain their
|
||||
* original Error identity and are tagged in a call-local scope for narrow
|
||||
* agent-loop request recovery; middleware and nested-call failures remain
|
||||
* untagged for the outer call.
|
||||
* @param options - the full request; `options.provider` selects the adapter.
|
||||
* @returns the chunk stream, possibly wrapped by `llm/stream` listeners.
|
||||
*/
|
||||
stream(options: GenerateOptions): AsyncIterable<StreamChunk>
|
||||
```
|
||||
|
||||
Types: [AdapterRegistrationHandle](core.md) · [DirectoryRegistrationHandle](core.md) · [GenerateOptions](core.md) · [LlmCallConfig](core.md) · [LlmConfigurableProvider](core.md) · [LlmDiscoveredModel](core.md) · [LlmModelDiscoveryRequest](core.md) · [LlmModelInfo](core.md) · [LlmProviderInfo](core.md) · [LlmResolvedModelInfo](core.md)
|
||||
|
||||
Source: [`packages/llm/llm/src/index.ts:292`](../../packages/llm/llm/src/index.ts)
|
||||
Source: [`packages/llm/llm/src/index.ts:232`](../../packages/llm/llm/src/index.ts)
|
||||
|
||||
<a id="llm-events"></a>
|
||||
|
||||
@@ -415,7 +702,7 @@ The provider topology changed: an adapter registered or unregistered routes, or
|
||||
'llm/adapters-updated'(): void
|
||||
```
|
||||
|
||||
Source: [`packages/llm/llm/src/index.ts:73`](../../packages/llm/llm/src/index.ts)
|
||||
Source: [`packages/llm/llm/src/index.ts:71`](../../packages/llm/llm/src/index.ts)
|
||||
|
||||
<a id="llmstream--waterfall"></a>
|
||||
|
||||
@@ -439,7 +726,5 @@ Waterfall around every streaming model call (retry, replay, routing). Bound to t
|
||||
'llm/stream'(this: LlmService, options: GenerateOptions, next: () => AsyncIterable<StreamChunk>): AsyncIterable<StreamChunk>
|
||||
```
|
||||
|
||||
Types: [GenerateOptions](core.md)
|
||||
|
||||
Source: [`packages/llm/llm/src/index.ts:62`](../../packages/llm/llm/src/index.ts)
|
||||
Source: [`packages/llm/llm/src/index.ts:60`](../../packages/llm/llm/src/index.ts)
|
||||
<!-- END GENERATED cordis-surface -->
|
||||
|
||||
@@ -2,10 +2,84 @@
|
||||
|
||||
[English](llm-streaming.md) | 中文
|
||||
|
||||
[dsh-llm](../../packages/llm/llm) 的协议格式（wire format）级流式输出词汇。[core.md](core.md) 介绍了 `StreamChunk`、`Message` 与 `ContentBlock`；本页拥有完整的分片协议、每个适配器必须遵守的适配器契约（adapter contract），以及共享的 assembler。
|
||||
[`packages/llm`](../../packages/llm/README.md) 的对话与流式输出词汇：每个请求与持久历史共享的 `Message`/`ContentBlock` 形状、完整组装的模型请求、原始 `StreamChunk` 协议、每个适配器必须遵守的适配器契约（adapter contract），以及共享的 assembler。[核心主干](core.md)在每个轮次持有并记录这些值；本页声明它们。
|
||||
|
||||
源码：[`packages/llm/llm/src/types.ts`](../../packages/llm/llm/src/types.ts)
|
||||
|
||||
<a id="content-blocks-and-messages"></a>
|
||||
|
||||
## 内容块与消息
|
||||
|
||||
一段对话由 `Message` 组成；一条消息是一个类型化**内容块**的数组。块的联合类型从 `ContentBlockMap` 派生。
|
||||
|
||||
源码：[`packages/llm/llm/src/types.ts`](../../packages/llm/llm/src/types.ts)
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Merge-extensible content blocks keyed by `type`. New core blocks must land
|
||||
* with adapter, UI, and compaction support.
|
||||
*/
|
||||
interface ContentBlockMap {
|
||||
'text': TextBlock
|
||||
'reasoning': ReasoningBlock
|
||||
'tool-call': ToolCallBlock
|
||||
'tool-result': ToolResultBlock
|
||||
}
|
||||
```
|
||||
|
||||
各块接口（完整字段见源码）：`TextBlock`（`text`）、`ReasoningBlock`（thinking，区别于可见文本）、`ToolCallBlock`（`id: CallId`、`name`、原始 JSON `arguments`）、`ToolResultBlock`（`toolCallId`、嵌套 `content: ContentBlock[]`、`isError?`）。`ContentBlock = ContentBlockMap[ContentBlockType]`。核心集仅限于每条交付路径都尊重的块——多模态内容（图像、音频等）没有核心块类型；需要的功能通过可合并扩展的 map 添加，同时提供适配器/UI/压缩支持。
|
||||
|
||||
源码：[`packages/llm/llm/src/message.ts`](../../packages/llm/llm/src/message.ts)
|
||||
|
||||
`Message` 是一个带标识且不可变的角色／来源／内容值。模型产生的 assistant 消息会在其来源中携带提供方／模型所有权与可选的适配器私有回放元数据：
|
||||
|
||||
```ts type-equiv
|
||||
/** Provider ownership and adapter-private replay data for an assistant message. */
|
||||
interface AssistantProvenance {
|
||||
/** Provider route that produced the message. */
|
||||
provider: string
|
||||
/** Provider model id that produced the message. */
|
||||
model: string
|
||||
/**
|
||||
* Lossless-JSON adapter state needed to replay the provider response.
|
||||
* `LlmService` exposes it to a target adapter only when that adapter instance
|
||||
* currently owns both this historical provider and the target provider.
|
||||
*/
|
||||
replayState?: unknown
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** One immutable message representation shared by delivery, durable history, and model requests. */
|
||||
interface Message {
|
||||
/** Stable identity preserved across every representation boundary. */
|
||||
readonly id: MessageId
|
||||
/** Provider-neutral conversation role. */
|
||||
readonly role: 'system' | 'user' | 'assistant'
|
||||
/** Exact model-facing blocks. */
|
||||
readonly content: ContentBlock[]
|
||||
/** Required producer provenance. */
|
||||
readonly source: MessageSource
|
||||
}
|
||||
```
|
||||
|
||||
消息来源本身也是一个可合并扩展的和类型：
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Where a message (or injected content) came from.
|
||||
* Merge-extensible sum type — plugins add their own `kind`s.
|
||||
*/
|
||||
interface MessageSourceMap {
|
||||
user: { kind: 'user' }
|
||||
plugin: { kind: 'plugin'; plugin: string }
|
||||
model: ModelMessageSource
|
||||
tool: ToolMessageSource
|
||||
}
|
||||
```
|
||||
|
||||
<a id="streamchunk--the-raw-protocol"></a>
|
||||
|
||||
## `StreamChunk`：原始协议
|
||||
|
||||
一个流式响应交错包含多种类型的块（文本、推理（reasoning）、多个工具调用）。`index` 将每个 delta 关联到其所属块；`block-end` 携带完整组装好的 `ContentBlock`，消费方无需自行重新组装 delta。这是一个**封闭的**可辨识联合类型：对 `type` 的 `switch` 以 `assertNever` 结尾，因此新增变体会在每个必须处理它的消费方处触发编译错误。
|
||||
@@ -15,9 +89,8 @@
|
||||
* Raw streaming protocol emitted by adapters.
|
||||
* Block indexes correlate interleaved deltas, and `block-end` carries the
|
||||
* assembled block. Adapters emit usage before the terminal finish and nothing
|
||||
* afterward; tool arguments remain raw JSON strings. An adapter implementation
|
||||
* may throw, but `LlmService.stream()` normalizes that failure to a terminal
|
||||
* `error` or `aborted` finish before exposing it to consumers.
|
||||
* afterward; tool arguments remain raw JSON strings. Failures either throw or
|
||||
* end with `error`/`aborted`, and consumers must handle both paths.
|
||||
*/
|
||||
type StreamChunk =
|
||||
| { type: 'block-start'; index: number; blockType: ContentBlockType }
|
||||
@@ -34,6 +107,8 @@ type StreamChunk =
|
||||
}
|
||||
```
|
||||
|
||||
<a id="llmfailure"></a>
|
||||
|
||||
## `LlmFailure`
|
||||
|
||||
每个抛出的失败或最终适配器的带内失败都会规范化为一种可序列化、提供方无关的 payload。`providerRetryAfterMs` 是经校验、由提供方请求的正数延迟，而不是重试决策；`ProviderRequestId` 是用于诊断的不透明品牌字符串。
|
||||
@@ -65,10 +140,10 @@ interface LlmFailure {
|
||||
- **提供方停顿在传输层受到时限约束。** 两个已交付的远程适配器都暴露正数且有限的 `streamIdleTimeoutMs`，默认五分钟。watchdog 只在 iterator `next()` 尚未完成时启动，整个请求使用同一个稳定 signal，把自身到期映射为 `TIMEOUT`，并把更早发生的调用方中止保留为 `ABORTED`。
|
||||
- **上下文溢出只有一个规范 code。** 两个 DeepSeek 适配器都通过 `isContextWindowExceededError()` 对提供方的显式细节分类并暴露 `CONTEXT_WINDOW_EXCEEDED`，无论失败以抛出的 HTTP `LlmError` 还是带内 finish error 到达。消费方按 code 路由，绝不依赖提供方文本。
|
||||
- **空 completion 是可重试错误，而不是静默的成功结果。** 两个适配器都把没有携带任何内容块的终止性 `stop` 结束映射为携带规范 `EMPTY_RESPONSE` code 的 `finish {kind:'error'}`，`dsh-llm-retry` 默认会重试它；详见[空模型响应可重试](../../.agents/notes/implemented/bug-fix/2026-07-24-empty-model-response-is-retryable.md)。
|
||||
- **每个提供方 HTTP 请求都携带应用归属头。** 适配器发送下文的 `attributionHeaders()`，即 `User-Agent` 基线。
|
||||
- **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。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。
|
||||
|
||||
两个彼此独立的实现遵循该契约：`dsh-llm-deepseek` 使用直接 fetch，并通过 `eventsource-parser` 进行 SSE（Server-Sent Events）分帧；`dsh-llm-pi-ai` 则通过 `@earendil-works/pi-ai` 提供通用多提供方适配器。两者都会把取消与空闲 watchdog 传递至提供方请求。
|
||||
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。
|
||||
|
||||
## `ResolvedRetryPolicy`
|
||||
|
||||
@@ -76,7 +151,7 @@ interface LlmFailure {
|
||||
|
||||
## `AppIdentity`：应用归属
|
||||
|
||||
每个适配器都会向提供方发送的静态公开应用标识（[`packages/llm/llm/src/attribution.ts`](../../packages/llm/llm/src/attribution.ts)）。`attributionHeaders(identity?)` 只把它映射到标准 `User-Agent` header；该契约有意不支持 OpenRouter 特有的应用归属 header。默认 `APP_IDENTITY` 从包 manifest（元数据清单）获取版本；每个字段都是公开产品事实——不含 secret、路径、会话 id 或逐用户标识，且任何逐请求信息都不得影响这些值。设计理由见[强制 `User-Agent` 归属](../../.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md)。
|
||||
每个适配器都会向提供方发送的静态公开应用标识（[`packages/llm/llm/src/attribution.ts`](../../packages/llm/llm/src/attribution.ts)）。`attributionHeaders(identity?)` 只把它映射到标准 `User-Agent` header；该契约有意不支持 OpenRouter 特有的应用归属 header。默认 `APP_IDENTITY` 从包（package） manifest（元数据清单）获取版本；每个字段都是公开产品事实——不含 secret、路径、会话 id 或逐用户标识，且任何逐请求信息都不得影响这些值。设计理由见[强制 `User-Agent` 归属](../../.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md)。
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
@@ -96,6 +171,8 @@ interface AppIdentity {
|
||||
}
|
||||
```
|
||||
|
||||
<a id="tokenusage"></a>
|
||||
|
||||
## `TokenUsage`
|
||||
|
||||
逐调用 token 记账。各计数**互不重叠**：`inputTokens` 只包含未缓存输入；缓存输入单独报告，计费输入是三者之和。若提供方把缓存命中折入单一提示词总数（如 DeepSeek 的 `prompt_tokens`），适配器会再将其扣除。`reasoningTokens` 存在时只是信息性细节，已经包含在 `outputTokens` 中；汇总时不得重复相加。
|
||||
@@ -118,6 +195,8 @@ interface TokenUsage {
|
||||
}
|
||||
```
|
||||
|
||||
<a id="blockassembler"></a>
|
||||
|
||||
## `BlockAssembler`
|
||||
|
||||
`BlockAssembler`（[`packages/llm/llm/src/assembler.ts`](../../packages/llm/llm/src/assembler.ts)）是唯一的共享实现，负责把 `StreamChunk` 流折叠回 `ContentBlock`、usage、结束原因与回放状态。循环在记录原始分片的同时，把同一批分片送入 assembler，再将组装后的 assistant 内容连同其提供方/模型 provenance 一起存储。需要组装结果、又不想重新实现 fold 的消费方使用它。
|
||||
@@ -142,9 +221,8 @@ declare class BlockAssembler {
|
||||
push(chunk: StreamChunk): void;
|
||||
/**
|
||||
* Assemble all blocks seen so far, in stream order.
|
||||
* @returns one block per seen index, except that max-token truncation drops
|
||||
* tool calls that cannot be executed safely; an open block assembles from
|
||||
* its accumulated deltas (an unknown block type never closed by `block-end` throws).
|
||||
* @returns one block per seen index; an open block assembles from its
|
||||
* accumulated deltas (an unknown block type never closed by `block-end` throws).
|
||||
*/
|
||||
blocks(): ContentBlock[];
|
||||
/** Usage from the `usage` chunk; undefined until one arrives. */
|
||||
@@ -162,6 +240,263 @@ declare class BlockAssembler {
|
||||
}
|
||||
```
|
||||
|
||||
<a id="the-model-request-and-result"></a>
|
||||
|
||||
## 模型请求
|
||||
|
||||
一次模型调用是一个完全组装好的 `GenerateOptions`。适配器以原始 [`StreamChunk`](#streamchunk--the-raw-protocol) 流作答；消费方用 [`BlockAssembler`](#blockassembler) 组装它。
|
||||
|
||||
源码：[`packages/llm/llm/src/types.ts`](../../packages/llm/llm/src/types.ts)
|
||||
|
||||
提供方与模型发现使用小型、提供方无关的描述符。模型目录仅供参考：路由仍以已注册提供方为键，适配器也可以接受未列出的模型 id。
|
||||
|
||||
注册适配器会返回一个句柄：既是释放器，也带有原子的路由替换——路由集合由用户配置决定的插件正需要它。
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* What {@link LlmService.registerAdapter} returns: the disposer, plus an
|
||||
* atomic route replacement for the same adapter instance.
|
||||
*/
|
||||
interface AdapterRegistrationHandle {
|
||||
/** Release every route this registration currently holds. */
|
||||
(): void
|
||||
/**
|
||||
* Replace this registration's routes with `providers`, keeping the same
|
||||
* adapter instance. The candidate set is validated in full first — a
|
||||
* conflict with another adapter, an invalid name, or bad provider metadata
|
||||
* throws and leaves the current routes untouched — and the swap itself is
|
||||
* one synchronous section, so no request can observe a gap. An empty array
|
||||
* is legal here (a settings section that emptied holds zero routes while
|
||||
* staying registered), unlike an empty initial registration.
|
||||
*
|
||||
* Throws `LlmError` with code `REGISTRATION_DISPOSED` once the registration
|
||||
* has been released: its routes are gone and its disposer has already run,
|
||||
* so anything registered afterwards would have no owner left to release it.
|
||||
* @param providers - the complete next route set for this registration.
|
||||
*/
|
||||
replace(providers: string[]): void
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Display metadata for one registered provider route. */
|
||||
interface LlmProviderInfo {
|
||||
/** Provider route key used by {@link GenerateOptions.provider}. */
|
||||
id: string
|
||||
/** Human-readable provider name for selectors and diagnostics. */
|
||||
name: string
|
||||
}
|
||||
```
|
||||
|
||||
适配器插件还会通过 `registerConfigurableProviders()` 声明哪些路由*可以*运行，并指明每条路由的用户设置分节，使配置界面能在任何路由注册之前就呈现休眠的提供方。
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* One provider route an adapter plugin can activate through configuration,
|
||||
* whether or not the route is currently registered. Configuration surfaces
|
||||
* merge this directory with `listProviders()` to offer every configurable
|
||||
* provider alongside its live/dormant state.
|
||||
*/
|
||||
interface LlmConfigurableProvider {
|
||||
/** Provider route key this entry activates when configured. */
|
||||
provider: string
|
||||
/** Human-readable provider name for configuration surfaces. */
|
||||
displayName: string
|
||||
/** User-settings namespace whose section configures this provider. */
|
||||
settingsNs: string
|
||||
/**
|
||||
* Path from that namespace's section root to this provider's profile
|
||||
* object; empty when the whole section is the profile.
|
||||
*/
|
||||
settingsPath: readonly string[]
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** One adapter-discovered model; catalog membership is advisory, not request validation. */
|
||||
interface LlmModelInfo {
|
||||
/** Provider route that owns this model entry. */
|
||||
provider: string
|
||||
/** Model id passed to {@link GenerateOptions.model}. */
|
||||
id: string
|
||||
/** Human-readable model name for selectors. */
|
||||
name: string
|
||||
/** Optional user-facing distinction from otherwise similar models. */
|
||||
description?: string
|
||||
}
|
||||
```
|
||||
|
||||
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、适配器调用默认值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. */
|
||||
interface LlmModelContext {
|
||||
/** Maximum combined request and response context in tokens. */
|
||||
contextWindow: number
|
||||
}
|
||||
```
|
||||
|
||||
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-configured per-request output cap materialized when callers omit one. */
|
||||
defaultMaxTokens?: number
|
||||
/** 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
|
||||
* the derived history (dsh-agent-loop); a hand-built one-shot passes any list.
|
||||
*/
|
||||
messages: Message[]
|
||||
/** System prompt text (adapters map to the provider's system slot). */
|
||||
system?: string
|
||||
/** Tool schemas (adapters map to the provider's `tools` field). */
|
||||
tools?: ToolSchema[]
|
||||
temperature?: number
|
||||
maxTokens?: number
|
||||
/**
|
||||
* Stop sequences: generation halts as soon as the model produces any one of
|
||||
* these strings (adapters map to the provider's stop field, e.g. OpenAI
|
||||
* `stop`). The stop string itself is not included in the output.
|
||||
*/
|
||||
stop?: string[]
|
||||
signal?: AbortSignal
|
||||
/**
|
||||
* Session identity stamped by the loop for listener routing. Adapters ignore
|
||||
* it; replay uses it to keep concurrent parent and child cursors independent.
|
||||
*/
|
||||
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. Ordinary conversation requests leave it unset.
|
||||
*/
|
||||
purpose?: 'compaction' | 'session-title'
|
||||
}
|
||||
```
|
||||
|
||||
模型响应为何停止由可合并扩展的原因表示。提供方终态失败携带流式契约的 [`LlmFailure`](#llmfailure)：
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Why a model response stopped.
|
||||
* Merge-extensible so adapters can surface provider-specific reasons.
|
||||
*/
|
||||
interface FinishReasonMap {
|
||||
'stop': { kind: 'stop' }
|
||||
'tool-calls': { kind: 'tool-calls' }
|
||||
'max-tokens': { kind: 'max-tokens' }
|
||||
'aborted': { kind: 'aborted'; failure: LlmFailure }
|
||||
'error': { kind: 'error'; failure: LlmFailure }
|
||||
}
|
||||
```
|
||||
|
||||
`FinishReason = FinishReasonMap[keyof FinishReasonMap]`。`TokenUsage`（逐调用计量，含不相交的缓存字段）详见[下文](#tokenusage)。
|
||||
|
||||
`GenerateOptions.tools` 携带 `ToolSchema`——工具的 JSON Schema 描述，发送给模型。它声明在 dsh-llm（而非 dsh-tools）中，正是因为它是循环每一步组装请求的一部分：
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* JSON-schema description of a tool, as sent to the model.
|
||||
*
|
||||
* Declared here (not in dsh-tools) because it is part of {@link GenerateOptions};
|
||||
* dsh-tools' ToolDefinition and dsh-system-prompt's PromptAssembly both import
|
||||
* it from this package.
|
||||
*/
|
||||
interface ToolSchema {
|
||||
name: string
|
||||
description: string
|
||||
/** JSON Schema object for the arguments. */
|
||||
parameters: Record<string, unknown>
|
||||
}
|
||||
```
|
||||
|
||||
面向模型的 `ToolSchema` 是协议格式；产出它的已注册 `ToolDefinition`（schema + `execute`）在 [tools.md](tools.md) 中。
|
||||
|
||||
### 请求信封：`LlmCallConfig` 与记录的 header
|
||||
|
||||
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、适配器默认值来源、渲染后的提示词以及权威返回工具顺序（由 `toolOrder` 配置；未配置时按字典序）。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、推理强度或采样参数。waterfall 开始前，循环会移除标记为适配器默认值的值，使确切模型准备过程填入所选路由的当前值；未带标记的显式设置仍保留在提议中。waterfall 结束后，准备过程会在轮次信号控制下拒绝显式指定但不受支持的推理强度 ID（不自动调整），并记录生效配置及其来源。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。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，循环构建的请求先读取 `system` 槽位（渲染后的提示词组装），再读取派生历史——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。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, 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[]
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Effective config fields supplied by exact-model adapter resolution rather
|
||||
* than by the caller's request proposal.
|
||||
*/
|
||||
interface LlmCallConfigAdapterDefaults {
|
||||
reasoningEffort?: true
|
||||
maxTokens?: true
|
||||
}
|
||||
```
|
||||
|
||||
## 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 `providerRetryPolicy()` 会按路由捕获并填入 normal 默认值，`providerInfo()` 与异步 `listModels()` 方法则为 `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、适配器配置的 `defaultMaxTokens`、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不可用或保留提供方持有的行为，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。在最终适配器边界，`resolveCallConfig()` 仅在 `maxTokens` 缺失时填入输出默认值，并校验和填入推理强度，因此直接调用也无法绕过任何一项已配置行为；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，保留来自同一次查询的分离上下文元数据，并报告适配器填入的配置字段。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。AgentLoop 在外层 waterfall 返回流句柄时观察到一次请求尝试；这个有限边界不能证明惰性终端适配器已构造完成或开始提供方 I/O。`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)。
|
||||
@@ -171,8 +506,6 @@ declare class BlockAssembler {
|
||||
interface PreparedLlmCall {
|
||||
/** Detached, deep-frozen config with any adapter-owned default materialized. */
|
||||
readonly config: LlmCallConfig
|
||||
/** Immutable retry policy captured with the adapter registration. */
|
||||
readonly retryPolicy: ResolvedRetryPolicy
|
||||
/** Detached context metadata resolved with the registration-bound call. */
|
||||
readonly context?: LlmModelContext
|
||||
/** Config fields materialized by the captured adapter rather than proposed by the caller. */
|
||||
@@ -239,22 +572,7 @@ declare abstract class LlmAdapter {
|
||||
}
|
||||
```
|
||||
|
||||
`ContentBlockType`（`index` 关联块所携带的键集合）派生自 `ContentBlockMap`：
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Merge-extensible content blocks keyed by `type`. New core blocks must land
|
||||
* with adapter, UI, and compaction support.
|
||||
*/
|
||||
interface ContentBlockMap {
|
||||
'text': TextBlock
|
||||
'reasoning': ReasoningBlock
|
||||
'tool-call': ToolCallBlock
|
||||
'tool-result': ToolResultBlock
|
||||
}
|
||||
```
|
||||
|
||||
块接口详见 [core.md § Content blocks and messages](core.md#content-blocks-and-messages)。
|
||||
`ContentBlockType`（带 `index` 关联的块所携带的键集合）从上文的 [`ContentBlockMap`](#content-blocks-and-messages) 派生。
|
||||
|
||||
<!-- BEGIN GENERATED cordis-surface (gen-cordis-catalog.ts) — do not edit between markers -->
|
||||
|
||||
@@ -293,9 +611,9 @@ listProviders(): LlmProviderInfo[]
|
||||
* entry, or a provider already declared by any registration throws
|
||||
* `LlmError` without registering the rest. Disposed with the fiber.
|
||||
* @param entries - every configurable provider this plugin owns.
|
||||
* @returns a handle that withdraws all of them, and can atomically replace them.
|
||||
* @returns the disposer that withdraws all of them.
|
||||
*/
|
||||
registerConfigurableProviders(entries: readonly LlmConfigurableProvider[]): DirectoryRegistrationHandle
|
||||
registerConfigurableProviders(entries: readonly LlmConfigurableProvider[]): () => void
|
||||
|
||||
/**
|
||||
* List every declared configurable provider, registered or dormant.
|
||||
@@ -303,29 +621,6 @@ registerConfigurableProviders(entries: readonly LlmConfigurableProvider[]): Dire
|
||||
*/
|
||||
listConfigurableProviders(): LlmConfigurableProvider[]
|
||||
|
||||
/**
|
||||
* Offer to interrogate provider endpoints on behalf of the settings
|
||||
* namespace this plugin owns. The namespace is the key because that is what
|
||||
* a configuration surface already holds from the configurable-provider
|
||||
* directory, and because a provider being *added* has no route to name yet.
|
||||
* Disposed with the fiber.
|
||||
* @param settingsNs - the namespace whose profiles this discovery serves.
|
||||
* @param discover - interrogates one endpoint; must honor `request.signal`.
|
||||
* @returns the disposer that withdraws the offer.
|
||||
*/
|
||||
registerModelDiscovery( settingsNs: string, discover: (request: LlmModelDiscoveryRequest) => Promise<readonly LlmDiscoveredModel[]>, ): () => void
|
||||
|
||||
/**
|
||||
* Interrogate one provider endpoint for the models it advertises. The
|
||||
* request describes a draft, not a stored route, so nothing here reads or
|
||||
* writes settings or credentials — the caller owns both, and the reply is
|
||||
* candidate metadata a surface may offer for adoption.
|
||||
* @param settingsNs - namespace whose registered discovery serves this draft.
|
||||
* @param request - the endpoint, protocol, and one-shot credential to use.
|
||||
* @returns the advertised models, deduplicated in endpoint order.
|
||||
*/
|
||||
async discoverModels( settingsNs: string, request: LlmModelDiscoveryRequest, ): Promise<LlmDiscoveredModel[]>
|
||||
|
||||
/**
|
||||
* Resolve the retry policy captured when one provider route was registered.
|
||||
* @param provider - registered provider route to inspect.
|
||||
@@ -375,22 +670,22 @@ async resolveCallConfig(config: LlmCallConfig, signal?: AbortSignal): Promise<Ll
|
||||
async prepareCall(config: LlmCallConfig, signal?: AbortSignal): Promise<PreparedLlmCall>
|
||||
|
||||
/**
|
||||
* Stream one model call as raw chunks (token-level deltas). Replay state is
|
||||
* retained only when the same adapter instance owns its historical provider
|
||||
* and the target provider. Final adapter selection remains fixed through
|
||||
* asynchronous exact-model resolution and dispatch. Adapter selection,
|
||||
* dispatch, and iteration failures become terminal `error` or `aborted`
|
||||
* finish chunks; middleware, nested-call, cleanup, and consumer failures
|
||||
* remain thrown.
|
||||
* Stream one model call as raw chunks (token-level deltas). Throws
|
||||
* `LlmError` with code `NO_ADAPTER` if no adapter is registered for
|
||||
* `options.provider`. Replay state is retained only when the same adapter
|
||||
* instance owns its historical provider and the target provider. Final
|
||||
* adapter selection remains fixed through asynchronous exact-model resolution
|
||||
* and dispatch. Selection, dispatch, and iteration failures retain their
|
||||
* original Error identity and are tagged in a call-local scope for narrow
|
||||
* agent-loop request recovery; middleware and nested-call failures remain
|
||||
* untagged for the outer call.
|
||||
* @param options - the full request; `options.provider` selects the adapter.
|
||||
* @returns the chunk stream, possibly wrapped by `llm/stream` listeners.
|
||||
*/
|
||||
stream(options: GenerateOptions): AsyncIterable<StreamChunk>
|
||||
```
|
||||
|
||||
Types: [AdapterRegistrationHandle](core.md) · [DirectoryRegistrationHandle](core.md) · [GenerateOptions](core.md) · [LlmCallConfig](core.md) · [LlmConfigurableProvider](core.md) · [LlmDiscoveredModel](core.md) · [LlmModelDiscoveryRequest](core.md) · [LlmModelInfo](core.md) · [LlmProviderInfo](core.md) · [LlmResolvedModelInfo](core.md)
|
||||
|
||||
Source: [`packages/llm/llm/src/index.ts:292`](../../packages/llm/llm/src/index.ts)
|
||||
Source: [`packages/llm/llm/src/index.ts:232`](../../packages/llm/llm/src/index.ts)
|
||||
|
||||
<a id="llm-events"></a>
|
||||
|
||||
@@ -415,7 +710,7 @@ The provider topology changed: an adapter registered or unregistered routes, or
|
||||
'llm/adapters-updated'(): void
|
||||
```
|
||||
|
||||
Source: [`packages/llm/llm/src/index.ts:73`](../../packages/llm/llm/src/index.ts)
|
||||
Source: [`packages/llm/llm/src/index.ts:71`](../../packages/llm/llm/src/index.ts)
|
||||
|
||||
<a id="llmstream--waterfall"></a>
|
||||
|
||||
@@ -439,7 +734,5 @@ Waterfall around every streaming model call (retry, replay, routing). Bound to t
|
||||
'llm/stream'(this: LlmService, options: GenerateOptions, next: () => AsyncIterable<StreamChunk>): AsyncIterable<StreamChunk>
|
||||
```
|
||||
|
||||
Types: [GenerateOptions](core.md)
|
||||
|
||||
Source: [`packages/llm/llm/src/index.ts:62`](../../packages/llm/llm/src/index.ts)
|
||||
Source: [`packages/llm/llm/src/index.ts:60`](../../packages/llm/llm/src/index.ts)
|
||||
<!-- END GENERATED cordis-surface -->
|
||||
|
||||
@@ -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 docs/subsystems/session-reference.md
|
||||
session-reference.md: 60e29c56ea372e100009b94caedea5327308432a
|
||||
session-reference.zh.md: 3ae9264abc15848646e5397dfcbeff764c038918
|
||||
session-reference.md: f539a59b8d26182aff9746b6d6a39a86ba15cb45
|
||||
session-reference.zh.md: 82b6a6c5ec5c91372fc6a43b73ad1572fccf5b3a
|
||||
|
||||
@@ -102,7 +102,7 @@ async listCandidates( agent: Agent, query: string = '', limit: number = this.con
|
||||
async prepare( agent: Agent, content: ContentBlock[], references: SessionReferenceInput[], signal?: AbortSignal, ): Promise<PreparedReferencedMessage>
|
||||
```
|
||||
|
||||
Types: [Agent](core.md) · [ContentBlock](core.md)
|
||||
Types: [Agent](core.md) · [ContentBlock](llm-streaming.md)
|
||||
|
||||
Source: [`packages/context/session-reference/src/index.ts:70`](../../packages/context/session-reference/src/index.ts)
|
||||
<!-- END GENERATED cordis-surface -->
|
||||
|
||||
@@ -102,7 +102,7 @@ async listCandidates( agent: Agent, query: string = '', limit: number = this.con
|
||||
async prepare( agent: Agent, content: ContentBlock[], references: SessionReferenceInput[], signal?: AbortSignal, ): Promise<PreparedReferencedMessage>
|
||||
```
|
||||
|
||||
Types: [Agent](core.md) · [ContentBlock](core.md)
|
||||
Types: [Agent](core.md) · [ContentBlock](llm-streaming.md)
|
||||
|
||||
Source: [`packages/context/session-reference/src/index.ts:70`](../../packages/context/session-reference/src/index.ts)
|
||||
<!-- END GENERATED cordis-surface -->
|
||||
|
||||
@@ -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 docs/subsystems/subagent.md
|
||||
subagent.md: cbf9043b36a5cb2ab37bb99c6dbbf5a18d1e0288
|
||||
subagent.zh.md: ffd8fefd8b9d128c21e1b91ee0ba1fb706638fa9
|
||||
subagent.md: c132c073459642b133e0d7e662ee98a8c9dfb694
|
||||
subagent.zh.md: e46f9aa98389842918ae37dda1477ef1b565e774
|
||||
|
||||
@@ -611,7 +611,7 @@ list(): string[]
|
||||
async start(name: string, request: SubagentStartRequest): Promise<SubagentRun>
|
||||
```
|
||||
|
||||
Types: [Agent](core.md) · [ContentBlock](core.md) · [MessageId](core.md) · [SessionId](core.md)
|
||||
Types: [Agent](core.md) · [ContentBlock](llm-streaming.md) · [MessageId](llm-streaming.md) · [SessionId](core.md)
|
||||
|
||||
Source: [`packages/subagent/subagent/src/index.ts:167`](../../packages/subagent/subagent/src/index.ts)
|
||||
|
||||
|
||||
@@ -613,7 +613,7 @@ list(): string[]
|
||||
async start(name: string, request: SubagentStartRequest): Promise<SubagentRun>
|
||||
```
|
||||
|
||||
Types: [Agent](core.md) · [ContentBlock](core.md) · [MessageId](core.md) · [SessionId](core.md)
|
||||
Types: [Agent](core.md) · [ContentBlock](llm-streaming.md) · [MessageId](llm-streaming.md) · [SessionId](core.md)
|
||||
|
||||
Source: [`packages/subagent/subagent/src/index.ts:167`](../../packages/subagent/subagent/src/index.ts)
|
||||
|
||||
|
||||
@@ -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 docs/subsystems/token-meter.md
|
||||
token-meter.md: 0f53955b3e6afce84520314f4de453edaa897158
|
||||
token-meter.zh.md: 3ba22c54d599982d3f7bdbcb9160b6ffc3255e07
|
||||
token-meter.md: 8a01980191bf29b1fbc0f8b1d0b33d1fb149319c
|
||||
token-meter.zh.md: 7411ce26cb75697607a706469d7923d46ff3f421
|
||||
|
||||
@@ -84,7 +84,7 @@ measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement
|
||||
estimateMessage(message: Message): number
|
||||
```
|
||||
|
||||
Types: [EpochHeader](session.md) · [Message](core.md) · [Session](session.md)
|
||||
Types: [EpochHeader](session.md) · [Message](llm-streaming.md) · [Session](session.md)
|
||||
|
||||
Source: [`packages/llm/token-meter/src/index.ts:74`](../../packages/llm/token-meter/src/index.ts)
|
||||
<!-- END GENERATED cordis-surface -->
|
||||
|
||||
@@ -84,7 +84,7 @@ measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement
|
||||
estimateMessage(message: Message): number
|
||||
```
|
||||
|
||||
Types: [EpochHeader](session.md) · [Message](core.md) · [Session](session.md)
|
||||
Types: [EpochHeader](session.md) · [Message](llm-streaming.md) · [Session](session.md)
|
||||
|
||||
Source: [`packages/llm/token-meter/src/index.ts:74`](../../packages/llm/token-meter/src/index.ts)
|
||||
<!-- END GENERATED cordis-surface -->
|
||||
|
||||
@@ -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 docs/subsystems/tools.md
|
||||
tools.md: 5d72bd54f0dc5995218087030f24c467c8ccbb38
|
||||
tools.zh.md: 2340d4c2d92c51aa9cc89f4694b626c76d05140b
|
||||
tools.md: b63014d1c2058c8fc7e96817d4bca858a1954482
|
||||
tools.zh.md: 2dc5802efce25a732a60c660191cd584ede623bb
|
||||
|
||||
@@ -596,7 +596,7 @@ Shape the DURABLE LOG COPY of one `run_code` sub-dispatch outcome before the bri
|
||||
'tools/code-dispatch-log'(this: Scoped<ToolRegistry>, dispatch: CodeDispatchLog, next: () => Promise<ContentBlock[]>): Promise<ContentBlock[]>
|
||||
```
|
||||
|
||||
Types: [ContentBlock](core.md) · [Scoped](scope.md)
|
||||
Types: [ContentBlock](llm-streaming.md) · [Scoped](scope.md)
|
||||
|
||||
Source: [`packages/core/tools/src/index.ts:173`](../../packages/core/tools/src/index.ts)
|
||||
|
||||
|
||||
@@ -596,7 +596,7 @@ Shape the DURABLE LOG COPY of one `run_code` sub-dispatch outcome before the bri
|
||||
'tools/code-dispatch-log'(this: Scoped<ToolRegistry>, dispatch: CodeDispatchLog, next: () => Promise<ContentBlock[]>): Promise<ContentBlock[]>
|
||||
```
|
||||
|
||||
Types: [ContentBlock](core.md) · [Scoped](scope.md)
|
||||
Types: [ContentBlock](llm-streaming.md) · [Scoped](scope.md)
|
||||
|
||||
Source: [`packages/core/tools/src/index.ts:173`](../../packages/core/tools/src/index.ts)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user