kevin/deepseek-harness
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/master' into worktree/web-multimodal-image-input

Browse Source 
# Conflicts:
#	docs/architecture.i18n.yaml
#	docs/architecture.md
#	docs/architecture.zh.md
#	docs/config-catalog.md
#	docs/core-data-structures/core.i18n.yaml
#	docs/core-data-structures/llm-streaming.i18n.yaml
#	docs/module-graph.md
#	examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl
#	packages/README.i18n.yaml
#	packages/client/connection/src/client/fixture.ts
#	packages/client/connection/src/index.ts
#	packages/client/runtime/README.i18n.yaml
#	packages/client/runtime/README.md
#	packages/client/runtime/README.zh.md
#	packages/client/runtime/src/client/sessions/conversation.ts
#	packages/client/ui-conversation/README.i18n.yaml
#	packages/client/ui-conversation/src/client/apply.ts
#	packages/client/ui-conversation/src/client/chat/ChatView.tsx
#	packages/client/ui-conversation/src/client/chat/MessageItem.tsx
#	packages/client/ui-conversation/src/client/contract/slots.ts
#	packages/client/ui-trajectory/tests/views.spec.tsx
#	packages/compact/compact-basic/README.i18n.yaml
#	packages/cordis/tool-cordis/src/api-catalog.ts
#	packages/host/apiproxy/src/api-proxy.ts
#	packages/host/apiproxy/src/api/index.ts
#	packages/host/apiproxy/src/api/sessions.ts
#	packages/host/apiproxy/src/index.ts
#	packages/host/apiproxy/tests/fetch-carrier.spec.ts
#	packages/llm/llm-deepseek/src/adapter.ts
#	packages/llm/llm-deepseek/tests/adapter.spec.ts
#	packages/llm/llm-deepseek/tests/serialize.spec.ts
#	packages/llm/llm-pi-ai/README.i18n.yaml
#	packages/llm/llm-pi-ai/src/adapter.ts
#	packages/llm/llm-pi-ai/src/index.ts
#	packages/llm/llm-pi-ai/tests/adapter.spec.ts
#	packages/llm/llm/src/types.ts
#	packages/ui/tui/README.i18n.yaml
#	packages/ui/tui/src/index.ts
#	packages/ui/tui/tests/tui.spec.ts
This commit is contained in:
Yichen Jiang
2026-07-28 11:41:40 +08:00
parent a1835c3228 2a46685414
commit 004f598917
1499 files changed
+48621 -21956
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/core-data-structures/llm-streaming.md
+45 -16
View File
@@ -59,15 +59,19 @@ Every adapter MUST obey these, and every consumer may rely on them:
- **`usage` before `finish`, nothing after `finish`.** Defer both to the provider's end-of-stream marker so a trailing usage-only chunk can't violate the ordering.
- **Tool-call `arguments` stay raw JSON strings end-to-end.** Partial fragments stream via `argumentsDelta`; a provider that hands back parsed objects re-stringifies at `block-end`.
- **Two sanctioned error paths, one fact shape.** A failure may either THROW from `stream()` (transport/protocol errors) **or** end the stream with `finish {kind:'error'|'aborted', failure}` (provider in-band errors, for adapters that can't throw mid-stream). `LlmError.failure` carries the same `LlmFailure`. The final adapter boundary preserves the exact thrown `Error` object and associates immutable facts with that call; the agent loop closes the failed step and offers the error, facts, and immutable prior-retried facts to `agent/request-error`. Absent recovery the structured failure becomes the turn error, and no normal assistant message or tool side effect is committed for that attempt.
- **One adapter call is one provider attempt.** Adapters disable library retries. Agent-level recovery opens another durable numbered step; direct `ctx.llm.stream()` callers remain single-attempt.
- **Two sanctioned error paths, one fact shape.** A failure may either THROW from `stream()` (transport/protocol errors) **or** end the stream with `finish {kind:'error'|'aborted', failure}` (provider in-band errors, for adapters that can't throw mid-stream). `LlmError.failure` carries the same `LlmFailure`. The final adapter boundary preserves the exact thrown `Error` object and associates immutable facts plus the serving registration's immutable retry policy with that call; the agent loop closes the failed step and offers the error, facts, immutable prior-retried facts, serving policy, and turn signal to `agent/request-error`. A handling listener returns `{ kind: 'retry' }` after its awaited repair; absent recovery the structured failure becomes the turn error, and no normal assistant message or tool side effect is committed for that attempt.
- **One adapter call is one provider attempt.** Adapters disable library retries. Agent-level recovery opens another durable numbered turn; direct `ctx.llm.stream()` callers remain single-attempt.
- **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 - 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.
- **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.
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.
## `ResolvedRetryPolicy`
Provider configuration resolves before route registration into an immutable discriminated union. Normal mode carries `mode: 'normal'`, finite `maxRetries`, `retryableCodes`, and required `initialDelayMs`, `maxDelayMs`, and `jitterRatio`; always mode carries `mode: 'always'` and the same required backoff fields without a finite maximum. `LlmService.providerRetryPolicy(provider)` returns the currently registered value and supplies normal defaults when the adapter omits one; `llmRetryPolicyOf(stream)` returns the exact serving registration's captured value after that call enters its final adapter boundary, so later route disposal or replacement cannot change an in-flight failure's recovery policy. The [generated config catalog](../config-catalog.md) owns the optional input shapes.
## `AppIdentity` — app attribution
@@ -157,14 +161,30 @@ 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 `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 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 {
/**
@@ -173,6 +193,12 @@ declare abstract class LlmAdapter {
* @returns detached display metadata whose id must equal `provider`.
*/
providerInfo(provider: string): LlmProviderInfo;
/**
* Return the provider-owned retry policy captured with this route.
* @param _provider - a route passed to `registerAdapter()` for this instance.
* @returns a resolved policy, or `undefined` to use the normal defaults.
*/
providerRetryPolicy(_provider: string): ResolvedRetryPolicy | undefined;
/**
* List models this adapter can currently advertise for one owned provider.
* The result is advisory: an adapter may accept unlisted model ids, and
@@ -182,16 +208,19 @@ 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`.