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

refactor: identify and freeze messages at creation

Browse Source
This commit is contained in:
_Kerman
2026-07-28 13:55:59 +08:00
parent c49c0ba497
commit fbf87e660c
345 changed files with 5220 additions and 2901 deletions
Download Patch File Download Diff File Expand all files Collapse all files

76
docs/core-data-structures/core.md
View File

@@ -116,7 +116,9 @@ interface ContentBlockMap {
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.
A `Message` is a role plus blocks. Loop-derived assistant messages carry their durable provider/model identity and optional adapter-private replay metadata:
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. */
@@ -135,15 +137,16 @@ interface AssistantProvenance {
```
```ts type-equiv
/**
* A single message in a conversation history. Loop-derived assistant messages
* always carry provenance; callers may omit it on hand-built foreign history.
*/
/** One immutable message representation shared by delivery, durable history, and model requests. */
interface Message {
role: 'system' | 'user' | 'assistant'
content: ContentBlock[]
/** Present only on assistant messages produced by a routed adapter. */
provenance?: AssistantProvenance
/** 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
}
```
@@ -157,6 +160,8 @@ Where a message came from is itself a merge-extensible sum type:
interface MessageSourceMap {
user: { kind: 'user' }
plugin: { kind: 'plugin'; plugin: string }
model: ModelMessageSource
tool: ToolMessageSource
}
```
@@ -448,32 +453,7 @@ interface SendOptions {
}
```
The fixed-preset aliases own `target` and `wakeup`; their `UserMessageData` input carries both content and provenance.
`send` returns the accepted message's opaque `AgentMessageId`, stable across that message's `agent/inbox/*` events:
```ts type-equiv
/**
* Opaque id assigned to one accepted {@link Agent.send} message; returned by
* `send` and carried on its `agent/inbox/*` events for correlation.
*/
type AgentMessageId = Branded<'AgentMessageId'>
```
The `agent/inbox/*` live events carry one accepted message; injection bypasses the FIFOs and never appears on them:
```ts type-equiv
/**
* One accepted {@link Agent.send} message, carried by the `agent/inbox/*` live
* events. `id` is the value `send` returned to the caller, stable across this
* message's enqueue, dequeue, and discard events. The agent snapshots and
* freezes the accepted content and source before enqueue observers receive it.
*/
interface AgentMessage extends UserMessageData {
/** The id `send` returned for this message. */
id: AgentMessageId
}
```
The fixed-preset aliases own `target` and `wakeup`; their already identified `UserMessage` carries role, content, and provenance. Its `MessageId` remains stable across that message's `agent/inbox/*` events without being returned by the delivery methods. Injection bypasses the FIFOs and never appears on those events.
```ts type-equiv
/** Options for {@link Agent.cancel}. */
@@ -532,12 +512,11 @@ interface Agent {
* immediately without opening a turn. If admission closes without a turn,
* a context-only boundary appends immediately; context staged beside
* steering remains pending with it.
* The agent snapshots and freezes `input` before publishing or queueing it.
* @param input - model-facing content and its producer provenance.
* The agent snapshots and freezes the identified message before publishing or queueing it.
* @param message - identified model-facing content and its producer provenance.
* @param options - target queue and wakeup decision.
* @returns the accepted message's {@link AgentMessageId}, stable across its `agent/inbox/*` events.
*/
send(input: UserMessageData, options: SendOptions): AgentMessageId
send(message: UserMessage, options: SendOptions): void
/**
* Clear queued and steering work — unless `keepInbox` — and abort the active
@@ -557,10 +536,9 @@ interface Agent {
* Queue an ordinary follow-up turn and wake the driver — the
* `next-turn`/wakeup preset of {@link send}. The item becomes the sole
* ordinary message of its own turn.
* @param input - prompt content and its producer provenance.
* @returns the accepted message's {@link AgentMessageId}.
* @param message - identified prompt content and its producer provenance.
*/
followup(input: UserMessageData): AgentMessageId
followup(message: UserMessage): void
/**
* Submit steering during prompt admission or an open turn — the
@@ -570,10 +548,9 @@ interface Agent {
* or a later prompt takes it. Outside that window steering falls back to a
* woken follow-up turn, while cancellation or disposal may discard pending
* steering.
* @param input - steering content and its producer provenance.
* @returns the accepted message's {@link AgentMessageId}.
* @param message - identified steering content and its producer provenance.
*/
steer(input: UserMessageData): AgentMessageId
steer(message: UserMessage): void
/**
* Append model-facing context without running the model — the
@@ -582,10 +559,9 @@ interface Agent {
* immediately without opening a turn. If admission closes without a turn,
* a context-only boundary appends immediately; context staged beside
* steering remains pending with it.
* @param input - injected context and its producer provenance.
* @returns the accepted message's {@link AgentMessageId}.
* @param message - identified injected context and its producer provenance.
*/
inject(input: UserMessageData): AgentMessageId
inject(message: UserMessage): void
}
```
@@ -601,7 +577,7 @@ The process-local initiator carried by `ctx.agents` is the exact `Agent` above,
## Interception decisions
Prompt and post-tool decisions use the same `UserMessageData` content/source shape as durable user-role input. Each `additionalContexts` entry becomes a separate `user/message`, preserving its provenance. Hook bridges map their native decision fields onto these typed results.
Prompt and post-tool decisions use the same identified `UserMessage` shape as durable user-role input. Each `additionalContexts` entry becomes a separate `user/message`, preserving its identity and provenance. Hook bridges map their native decision fields onto these typed results.
Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types.ts)
@@ -615,7 +591,7 @@ Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types
* `next()` preserves both fields unless it intentionally replaces them.
*/
type PromptDecision =
| { kind: 'allow'; content?: ContentBlock[]; additionalContexts?: UserMessageData[] }
| { kind: 'allow'; content?: ContentBlock[]; additionalContexts?: UserMessage[] }
| { kind: 'block'; reason: string }
```