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

simplify(llm): drop unconsumed adapter-change event and assembled call surfaces

Browse Source 
The LLM service exposed three call surfaces (stream/streamBlocks/generate) but
the only production consumer — the agent loop — uses stream() exclusively,
feeding raw chunks through its own BlockAssembler for replay fidelity. Drop the
speculative convenience surfaces and the registry-change event that no listener
consumed, leaving stream() as the single model-call contract for both
production and tests.

- Remove LlmService.streamBlocks() and generate(), the llm/generate waterfall,
  and GenerateResult.
- Remove the llm/adapter-change event (declaration + emits) and the
  listener-throw rollback ordering that existed only to protect it; keep the
  HMR rollback disposer.
- Remove BlockAssembler.flushReady()/flushRemaining()/result() and the flushed
  cursor — the streaming-flush slice existed only for streamBlocks().
- Adapter tests drive a stream()+BlockAssembler helper (tests/assemble.ts)
  instead of generate(), exercising the same path production uses.
- Land the AGENTS.md "RFCs are proposals, not golden truth" principle and move
  both RFCs proposed -> implemented.

Implements:
- docs/rfc/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md
- docs/rfc/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.md
This commit is contained in:
Tianyi Cui
2026-06-21 01:27:41 +08:00
parent 18f1c010ca
commit 30cd67b8a1
26 changed files with 164 additions and 428 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
packages/llm/llm/README.md
View File

@@ -4,28 +4,24 @@ Provider-neutral LLM vocabulary and abstract service. This package defines the c
## Service: `LlmService` (ctx key: `llm`)
An adapter registry plus streaming / non-streaming call surfaces. Both call surfaces are interceptable via waterfall events.
An adapter registry plus a single streaming call surface, interceptable via a waterfall event.
### Public API
- `ctx.llm.registerAdapter(models: string[], adapter: LlmAdapter): () => void` Register an adapter for the given model names. Disposed with the calling fiber.
- `ctx.llm.models(): string[]` — model names with a registered adapter.
- `ctx.llm.stream(options: GenerateOptions): AsyncIterable<StreamChunk>` Stream one model call as raw chunks (token-level deltas).
- `ctx.llm.streamBlocks(options: GenerateOptions): AsyncIterable<ContentBlock>` Stream as completed content blocks (convenience view).
- `ctx.llm.generate(options: GenerateOptions): Promise<GenerateResult>` One model call, fully assembled.
- `ctx.llm.stream(options: GenerateOptions): AsyncIterable<StreamChunk>` Stream one model call as raw chunks (token-level deltas). Consumers assemble the chunks into blocks/messages with `BlockAssembler`.
### Events
| Event | Mode | Purpose |
|---|---|---|
| `llm/stream` | waterfall | Intercept/wrap every streaming model call (retry, caching, routing) |
| `llm/generate` | waterfall | Intercept/wrap every non-streaming model call |
| `llm/adapter-change` | emit | An adapter was registered or unregistered |
### Extension points
- Subclass `LlmAdapter` and call `ctx.llm.registerAdapter(models, adapter)` to add a new model provider.
- Wrap `llm/stream` or `llm/generate` via `ctx.on()` waterfall listeners for caching, retry, logging, rate-limiting, etc.
- Wrap `llm/stream` via `ctx.on()` waterfall listeners for caching, retry, logging, rate-limiting, etc.
### Content-block vocabulary (`types.ts`)
@@ -36,8 +32,7 @@ Streaming is a raw chunk protocol (`block-start`, `text-delta`, `reasoning-delta
### Classes
- `LlmAdapter` — abstract base class for provider adapters. The only required method is `stream()`.
- `BlockAssembler` — incrementally assembles raw chunks into complete content blocks and an assistant message. Used by the agent loop (raw chunks for replay
+ assembled for history) and by `streamBlocks()`/`generate()`.
- `BlockAssembler` — incrementally assembles raw chunks into complete content blocks and an assistant message. The agent loop feeds it raw chunks (logging them for replay) while reading the assembled blocks/message for history.
- `HarnessError` — base class for the harness error taxonomy: a stable `code` string (distinct from the human `message`) plus `cause` chaining. Lives here, in the leaf package every other imports, so a single base is shared without a new dependency edge. Per-package errors (`LlmError`, `ToolArgsError`, `InvariantError`, …) extend it. `isHarnessError(value)` narrows at seams.
- `LlmError` — extends `HarnessError`; `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) plus an optional numeric `status` when the failure came from a non-2xx provider response.