refactor(vocab): prune producer-less variants — cache hints, agent source, continuation trigger
The vocabulary maps grow by declaration merging, and the admission policy stated on TurnEndReasonMap is that a variant lands with its first emitter. Three declared items had no producer and no consumer: - CacheHint and the cache?: CacheHint fields on TextBlock/ToolResultBlock: nothing constructs a block with cache:, and neither adapter reads .cache — DeepSeek prompt caching is automatic (hints map OUT of responses, never IN). - MessageSourceMap.agent: zero constructors; the subagent backends send the parent prompt with no source (logs as user), and the envelope renderer interpolates source.kind without routing on it. - TurnTriggerMap.continuation: the loop structurally cannot emit it — continuation is further steps within a turn, never a new turn — and its only writer was an llm-replay test fixture that needed any non-message trigger (now an injection trigger). Each variant returns the day it gains a real producer, via the same merge-extensible maps. Docs updated in the same change: the MessageSourceMap paste in core.md, the TurnTriggerMap paste in session.md (manifest untouched — both symbols survive), the content-block vocabulary RFC's cache-hints consequence line, and the RFC moved to implemented/ and amended to shipped reality (the image block's own cache field had already left with the drop-image RFC).
This commit is contained in:
Tianyi Cui
@@ -107,7 +107,6 @@ Where a message came from is itself a merge-extensible sum type:
|
||||
interface MessageSourceMap {
|
||||
user: { kind: 'user' }
|
||||
plugin: { kind: 'plugin'; plugin: string }
|
||||
agent: { kind: 'agent'; agentId: string }
|
||||
}
|
||||
```
|
||||
|
||||
|
||||
@@ -164,7 +164,6 @@ Everything else (`turn/*`, `step/*`) is structural and does not project into a m
|
||||
```ts type-equiv
|
||||
interface TurnTriggerMap {
|
||||
message: { kind: 'message'; source: MessageSource }
|
||||
continuation: { kind: 'continuation' }
|
||||
/**
|
||||
* An out-of-band context injection (`agent.inject()`) made while the agent
|
||||
* was idle. The loop wraps the injected `context/message` in a one-shot turn
|
||||
|
||||
+1
-1
@@ -56,7 +56,6 @@ Do NOT write one for a mechanical or local choice (a variable name, a one-file r
|
||||
| [Drop the unconsumed web observation surface — the `providers-change` event and the status methods](proposed/simplification/2026-07-04-drop-unconsumed-web-observation-surface.md) | 2026-07-04 |
|
||||
| [Fold the stdio UI helper into the stdio app](proposed/simplification/2026-07-04-fold-stdio-ui-helper.md) | 2026-07-04 |
|
||||
| [Prune dead core-spine surface — `SurfaceManager.invalidate()`, the loop-internal exports, `ToolExecutionResult.callId`](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 |
|
||||
| [Prune producer-less vocabulary variants (block cache hints, the `agent` message source, the `continuation` turn trigger)](proposed/simplification/2026-07-04-prune-producerless-vocabulary-variants.md) | 2026-07-04 |
|
||||
| [Prune write-only fields and a dead routing knob from the fs seam](proposed/simplification/2026-07-04-prune-write-only-fs-surface.md) | 2026-07-04 |
|
||||
| [Remove the `agent/steering` mirror emit](proposed/simplification/2026-07-04-remove-agent-steering-mirror.md) | 2026-07-04 |
|
||||
| [Share the app bins' boot glue instead of maintaining twin copies](proposed/simplification/2026-07-04-share-app-bin-boot-glue.md) | 2026-07-04 |
|
||||
@@ -120,6 +119,7 @@ Do NOT write one for a mechanical or local choice (a variable name, a one-file r
|
||||
| [Split the filesystem seam — provider text mutations plus the `dsh-fs-policy` plugin](implemented/simplification/2026-06-26-fsspec-style-fs-seam.md) | 2026-06-26 |
|
||||
| [Stop mirroring the token stream as an agent event](implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md) | 2026-07-02 |
|
||||
| [Drop the `image` content block until a path can honor it](implemented/simplification/2026-07-04-drop-image-content-block.md) | 2026-07-04 |
|
||||
| [Prune producer-less vocabulary variants (block cache hints, the `agent` message source, the `continuation` turn trigger)](implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.md) | 2026-07-04 |
|
||||
|
||||
### Architecture
|
||||
|
||||
|
||||
@@ -16,6 +16,6 @@ In-session context injection (`context/message`, `steering/message`) renders as
|
||||
|
||||
## Consequences
|
||||
|
||||
- Reasoning, prefill, and cache hints have a home without provider contortions. Multimodal content deliberately has NO core block type: the core set is limited to blocks every shipping path honors, and a multimodal feature adds its block type through the merge-extensible map in the same coordinated change that maps it in the adapters, surfaces it in the UI bridges, and prices it in compaction — see [the drop-image RFC](../simplification/2026-07-04-drop-image-content-block.md).
|
||||
- Reasoning and prefill have a home without provider contortions. Multimodal content deliberately has NO core block type: the core set is limited to blocks every shipping path honors, and a multimodal feature adds its block type through the merge-extensible map in the same coordinated change that maps it in the adapters, surfaces it in the UI bridges, and prices it in compaction — see [the drop-image RFC](../simplification/2026-07-04-drop-image-content-block.md). Block cache hints likewise have no core field: DeepSeek prompt caching is automatic, so no shipping adapter can transmit a hint; a caching feature adds a `cache` field together with the adapter that honors it — see [the producer-less-variants RFC](../simplification/2026-07-04-prune-producerless-vocabulary-variants.md).
|
||||
- Every adapter pays a translation cost; the first real adapters have since validated the streaming protocol, and new adapters should continue proving their provider-specific mapping in adapter-local tests.
|
||||
- IDs that cross package boundaries are branded (`CallId`, `SessionId`, `AgentId`) — nominal typing at zero runtime cost.
|
||||
|
||||
+31
@@ -0,0 +1,31 @@
|
||||
# RFC: Prune producer-less vocabulary variants (block cache hints, the `agent` message source, the `continuation` turn trigger)
|
||||
|
||||
Status: implemented (proposed and accepted 2026-07-04)
|
||||
|
||||
## Problem
|
||||
|
||||
The merge-extensible vocabulary maps are designed to grow by declaration merging, and the codebase already states the admission policy on `TurnEndReasonMap` (`packages/core/session/src/types.ts`): a variant like `refusal` is "deliberately omitted until" an adapter or loop first emits it. Three declared vocabulary items violated that policy — each had no producer and no consumer, and two had not even a test:
|
||||
|
||||
- **`CacheHint` and its `cache?: CacheHint` block fields** on `TextBlock`/`ToolResultBlock` (`packages/llm/llm/src/types.ts`; the image block carried a third such field, which left with it — see [the drop-image RFC](2026-07-04-drop-image-content-block.md)). Nothing constructed a block with `cache:` anywhere — src, tests, and doc pastes all came up empty — and neither adapter read `.cache`: DeepSeek prompt caching is automatic, so the adapters map `prompt_cache_hit_tokens` OUT of responses without ever sending a hint IN. This was Anthropic-style `cache_control` surface with no provider that could honor it.
|
||||
- **`MessageSourceMap.agent`** (`{ kind: 'agent'; agentId: string }`, same file). Zero constructors, tests included. Its intended producer shipped without it: the subagent backends send the parent's prompt to the child with no `source`, so it logs as `{ kind: 'user' }`, and the generic envelope renderer interpolates `source.kind` without ever routing on it.
|
||||
- **`TurnTriggerMap.continuation`** (`packages/core/session/src/types.ts`). The loop structurally cannot emit it — continuation happens *within* a turn as further steps, never as a new turn — and it constructs only `message` and `injection` triggers. The only writer was one hand-built test fixture needing an arbitrary non-message trigger (`packages/support/llm-replay/tests/llm-replay.spec.ts`), which an `injection` trigger serves equally; the only production trigger reader, the ACP bridge, filters on `kind === 'message'`.
|
||||
|
||||
## Decision
|
||||
|
||||
`CacheHint` with both `cache?` fields, the `agent` message-source variant, and the `continuation` turn-trigger variant are deleted. The llm-replay fixture uses an `injection` trigger (any non-`message` trigger serves its purpose). Updated in the same change: the type-equiv pastes in [core.md](../../../core-data-structures/core.md) and [session.md](../../../core-data-structures/session.md) (`scripts/type-equiv.manifest.json` is untouched — both pasted symbols survive, each minus a member), and the [content-block vocabulary RFC](../architecture/2026-06-11-content-block-vocabulary.md)'s consequence line that had named cache hints as having a home, per [implemented/AGENTS.md](../AGENTS.md).
|
||||
|
||||
Each variant returns the day it gains a real producer, exactly as the maps are designed to grow: a caching feature re-adds `cache` together with the adapter that transmits it; subagent attribution re-adds `agent` together with the backend that stamps it and a consumer that routes on it; an auto-continue feature that genuinely starts new turns re-adds `continuation` with the plugin that emits it.
|
||||
|
||||
## Why not keep them?
|
||||
|
||||
The [content-block vocabulary RFC](../architecture/2026-06-11-content-block-vocabulary.md) listed "cache hints … have a home" as a design consequence, and reserved slots do advertise intent. But an empty slot is contract surface every implementation and consumer must consider (must my adapter honor `cache`? must my renderer route `agent` sources?), and the sibling map's own JSDoc already rejects reservation-without-emitter — `refusal` and `max_turn_requests` are named as variants to add *when something first emits them*, not declared in advance. Holding already-declared dead variants to the same standard makes the vocabulary mean something: if it is in the map, something produces it.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- `rg` for `CacheHint`, the `agent` message-source spelling, and the `continuation` trigger spelling returns only RFC records (this one, and [the drop-image RFC](2026-07-04-drop-image-content-block.md)'s account of the image block's own `cache` field).
|
||||
- The core-data-structures pastes and the type-equiv manifest are in sync (`pnpm run doc-sync` green).
|
||||
- The fixture asserts the same replay behavior with an `injection` trigger; the suite is green.
|
||||
|
||||
## Risks
|
||||
|
||||
None operational — nothing could construct these values. The mirror-event removals (recorded in [the boundary-mirror RFC](2026-06-20-remove-agent-boundary-mirror-events.md) and [the stream-chunk RFC](2026-07-02-remove-stream-chunk-mirror.md)) touch only transient `agent/*` events, never the durable vocabulary, so there is no collision. Elsewhere in the vocabulary the admission policy already holds: `rejected`, `prompt/blocked`, and `hook/invoked`/`hook/result` each have live producers — this RFC extends the same bar to the three variants that lacked one. [The image-block removal](2026-07-04-drop-image-content-block.md) shipped first, taking the image block's `cache?` field with it; this change removed the two that remained.
|
||||
@@ -1,31 +0,0 @@
|
||||
# RFC: Prune producer-less vocabulary variants (block cache hints, the `agent` message source, the `continuation` turn trigger)
|
||||
|
||||
Status: proposed
|
||||
|
||||
## Problem
|
||||
|
||||
The merge-extensible vocabulary maps are designed to grow by declaration merging, and the codebase already states the admission policy on `TurnEndReasonMap` (`packages/core/session/src/types.ts`): a variant like `refusal` is "deliberately omitted until" an adapter or loop first emits it. Three declared vocabulary items violate that policy — each has no producer and no consumer, and two have not even a test:
|
||||
|
||||
- **`CacheHint` and the three `cache?: CacheHint` fields** on `TextBlock`/`ToolResultBlock`/`ImageBlock` (`packages/llm/llm/src/types.ts`). Nothing constructs a block with `cache:` anywhere — src, tests, and doc pastes all come up empty — and neither adapter reads `.cache`: DeepSeek prompt caching is automatic, so the adapters map `prompt_cache_hit_tokens` OUT of responses without ever sending a hint IN. This is Anthropic-style `cache_control` surface with no provider that can honor it.
|
||||
- **`MessageSourceMap.agent`** (`{ kind: 'agent'; agentId: string }`, same file). Zero constructors, tests included. Its intended producer shipped without it: the subagent backends send the parent's prompt to the child with no `source`, so it logs as `{ kind: 'user' }`, and the generic envelope renderer interpolates `source.kind` without ever routing on it. The variant is pasted into [core.md](../../../core-data-structures/core.md).
|
||||
- **`TurnTriggerMap.continuation`** (`packages/core/session/src/types.ts`). The loop structurally cannot emit it — continuation happens *within* a turn as further steps, never as a new turn — and it constructs only `message` and `injection` triggers. The only writer is one hand-built test fixture that needs an arbitrary non-message trigger (`packages/support/llm-replay/tests/llm-replay.spec.ts`); the only production trigger reader, the ACP bridge, filters on `kind === 'message'`. The variant is pasted into [session.md](../../../core-data-structures/session.md).
|
||||
|
||||
## Proposal
|
||||
|
||||
Delete `CacheHint` with its three `cache?` fields, the `agent` message-source variant, and the `continuation` turn-trigger variant. Switch the llm-replay fixture to an `injection` trigger (any non-`message` trigger serves its purpose). Update the type-equiv pastes in [core.md](../../../core-data-structures/core.md) and [session.md](../../../core-data-structures/session.md) (and `scripts/type-equiv.manifest.json` where block identity shifts) in the same change, and amend the [content-block vocabulary RFC](../../implemented/architecture/2026-06-11-content-block-vocabulary.md)'s consequence line naming cache hints as having a home, per [implemented/AGENTS.md](../../implemented/AGENTS.md).
|
||||
|
||||
Each variant returns the day it gains a real producer, exactly as the maps are designed to grow: a caching feature re-adds `cache` together with the adapter that transmits it; subagent attribution re-adds `agent` together with the backend that stamps it and a consumer that routes on it; an auto-continue feature that genuinely starts new turns re-adds `continuation` with the plugin that emits it.
|
||||
|
||||
## Why not keep them?
|
||||
|
||||
The [content-block vocabulary RFC](../../implemented/architecture/2026-06-11-content-block-vocabulary.md) lists "cache hints … have a home" as a design consequence, and reserved slots do advertise intent. But an empty slot is contract surface every implementation and consumer must consider (must my adapter honor `cache`? must my renderer route `agent` sources?), and the sibling map's own JSDoc already rejects reservation-without-emitter — `refusal` and `max_turn_requests` are named as variants to add *when something first emits them*, not declared in advance. Holding already-declared dead variants to the same standard makes the vocabulary mean something: if it is in the map, something produces it.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- `rg` for `CacheHint`, the `agent` message-source spelling, and the `continuation` trigger spelling returns only this RFC.
|
||||
- The core-data-structures pastes and the type-equiv manifest are in sync (`pnpm run doc-sync` green).
|
||||
- The fixture asserts the same replay behavior with an `injection` trigger; the suite is green.
|
||||
|
||||
## Risks
|
||||
|
||||
None operational — nothing can construct these values today. The mirror-event removals (recorded in [the boundary-mirror RFC](../../implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md) and [the stream-chunk RFC](../../implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md)) touch only transient `agent/*` events, never the durable vocabulary, so there is no collision. Elsewhere in the vocabulary the admission policy already holds: `rejected`, `prompt/blocked`, and `hook/invoked`/`hook/result` each have live producers — this RFC extends the same bar to the three variants that lack one. If the [image-block RFC](../../implemented/simplification/2026-07-04-drop-image-content-block.md) ships first, one of the three `cache?` fields leaves with it; the two proposals are independent and compose in either order.
|
||||
@@ -91,7 +91,6 @@ export interface CreateSessionOptions {
|
||||
*/
|
||||
export interface TurnTriggerMap {
|
||||
message: { kind: 'message'; source: MessageSource }
|
||||
continuation: { kind: 'continuation' }
|
||||
/**
|
||||
* An out-of-band context injection (`agent.inject()`) made while the agent
|
||||
* was idle. The loop wraps the injected `context/message` in a one-shot turn
|
||||
|
||||
@@ -22,14 +22,10 @@
|
||||
import type { Branded } from '@deepseek-ai/dsh-brand'
|
||||
import type { CallId } from './brand.ts'
|
||||
|
||||
/** Cache hint attached to a content block (provider-interpreted). */
|
||||
export type CacheHint = 'ephemeral'
|
||||
|
||||
/** Plain text visible to the end user. */
|
||||
export interface TextBlock {
|
||||
type: 'text'
|
||||
text: string
|
||||
cache?: CacheHint
|
||||
}
|
||||
|
||||
/** Reasoning / thinking content, distinct from visible text. */
|
||||
@@ -54,7 +50,6 @@ export interface ToolResultBlock {
|
||||
toolCallId: CallId
|
||||
content: ContentBlock[]
|
||||
isError?: boolean
|
||||
cache?: CacheHint
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -91,7 +86,6 @@ export interface Message {
|
||||
export interface MessageSourceMap {
|
||||
user: { kind: 'user' }
|
||||
plugin: { kind: 'plugin'; plugin: string }
|
||||
agent: { kind: 'agent'; agentId: string }
|
||||
}
|
||||
|
||||
export type MessageSource = MessageSourceMap[keyof MessageSourceMap]
|
||||
|
||||
@@ -118,7 +118,7 @@ describe('deriveReplayScript', () => {
|
||||
it('ignores non-assistant/chunk events', () => {
|
||||
let seq = 1
|
||||
const events: SessionEvent[] = [
|
||||
{ type: 'turn/start', seq: seq++, time: 0, data: { turn: 1, trigger: { kind: 'continuation' } } },
|
||||
{ type: 'turn/start', seq: seq++, time: 0, data: { turn: 1, trigger: { kind: 'injection', source: { kind: 'user' } } } },
|
||||
...TEXT_CHUNKS.map(c => chunkEvent(seq++, 1, 1, c)),
|
||||
{ type: 'turn/end', seq: seq++, time: 0, data: { turn: 1, reason: { kind: 'completed' } } },
|
||||
]
|
||||
|
||||
Reference in New Issue
Block a user