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

# Conflicts: # apps/cli/README.md # apps/cli/src/web.ts # apps/web/tests/smoke-fixture.e2e.ts # docs/architecture.i18n.yaml # docs/module-graph.md # examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl # packages/client/connection/src/client/api.ts # packages/client/connection/src/client/fixture.ts # packages/client/runtime/README.md # packages/client/runtime/src/client/index.ts # packages/client/runtime/src/client/sessions/conversation.ts # packages/client/runtime/src/client/sessions/service.ts # packages/client/runtime/src/client/sessions/session.ts # packages/client/ui-conversation/src/client/apply.ts # packages/client/ui-conversation/src/client/contract/slots.ts # packages/client/ui-conversation/src/client/index.ts # packages/client/ui-conversation/src/client/service.ts # packages/client/ui-conversation/src/client/skeleton/ConversationRoot.tsx # packages/client/ui-conversation/src/client/skeleton/EmptyState.tsx # packages/client/ui-conversation/src/client/skeleton/InputBar.tsx # packages/client/ui-conversation/src/client/stores.ts # packages/client/ui-conversation/tests/apply-inject.spec.tsx # packages/client/ui-conversation/tests/service-orchestration.spec.ts # packages/client/ui-conversation/tests/skeleton-branches.spec.tsx # packages/client/ui-conversation/tests/skeleton.spec.tsx # packages/cordis/tool-cordis/src/api-catalog.ts # packages/host/apiproxy/package.json # packages/host/apiproxy/src/api-proxy.ts # packages/host/apiproxy/src/api/sessions.schema.ts # packages/host/runtime/package.json # packages/host/runtime/src/boot.ts # packages/host/runtime/tests/host-runtime.spec.ts # packages/host/runtime/tsconfig.json # packages/host/webserver/README.md # packages/host/webserver/src/index.ts # packages/host/webserver/tests/webserver.spec.ts # packages/llm/llm-pi-ai/tests/convert.spec.ts # packages/ui/acp/src/codec.ts # packages/ui/acp/tests/codec.spec.ts # pnpm-lock.yaml
2026-07-25 22:35:22 +08:00
parent dbd93fed02 84be7cc622
commit c981f18921
1264 changed files with 37694 additions and 29428 deletions
@@ -1,5 +1,7 @@
 # LLM Streaming

+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.

 Source: [`packages/llm/llm/src/types.ts`](../../packages/llm/llm/src/types.ts)
@@ -61,6 +63,7 @@ Every adapter MUST obey these, and every consumer may rely on them:
 - **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.
 - **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.