feat(client): render user skill invocations as dedicated transcript cards

A user/message carrying the skill-invocation source materializes as its
own conversation node (name/args lifted off the source metadata, never
re-parsed from the body) and renders as a right-aligned bubble: the /name
chip plus the user's trailing text, with the injected <skill_content>
collapsed behind a disclosure. A record with an unreadable name degrades
to the injected-context row.
This commit is contained in:
Yichen Jiang
2026-08-08 01:05:08 +08:00
parent 56e9e61749
commit 011e3e4e63
8 changed files with 163 additions and 4 deletions

View File

@@ -49,7 +49,7 @@ export type {
AssistantBlock, AssistantMessageNode, AssistantProvenanceView, AssistantRequestConfig,
AssistantTiming, CodeSubCall, CommandNode, CompactionSummaryNode, ComposerPhase,
ContextMessageNode, ConversationNode, ConversationSnapshot, ModelRetryNode, QueuedMessage,
RunningToolCall,
RunningToolCall, SkillInvocationNode,
SteeringMessageNode, TodoItem, ToolResultNode, TurnErrorNode, UnknownSurfaceNode, UserMessageNode,
} from './sessions/conversation.ts'
export type {

View File

@@ -129,6 +129,25 @@ export interface ContextMessageNode {
form: KnownContextForm | null
}
/**
* A user-explicit skill invocation: the host injected the rendered skill as a
* user message carrying the `skill-invocation` source, so the card presents
* `/name args` from source metadata and collapses the injected body.
*/
export interface SkillInvocationNode {
kind: 'skill-invocation'
seq: number
/** Unix epoch ms from the source session event. */
time: number
/** Invoked skill name read off the message source. */
name: string
/** Trailing user text read off the message source, when recorded. */
args?: string
/** Full injected model-facing content (collapsed by default in the UI). */
content: readonly ContentBlock[]
source: unknown
}
/** Durable notice that a closed failed step is waiting for a model-request retry. */
export type ModelRetryNode = LlmRetryEventData & {
kind: 'model-retry'
@@ -245,6 +264,7 @@ export type ConversationNode =
| AssistantMessageNode
| SteeringMessageNode
| ContextMessageNode
| SkillInvocationNode
| ModelRetryNode
| TurnErrorNode
| ToolResultNode

View File

@@ -57,7 +57,20 @@ function materializeNode(
stepTimings: ReadonlyMap<string, AssistantStepMetadata>,
): ConversationNode {
switch (event.type) {
case 'user/message':
case 'user/message': {
// A user-explicit skill invocation carries its name (and optional args)
// on the source; the dedicated node lets the card render `/name args`
// from metadata instead of re-parsing the injected body. A record whose
// name is unreadable degrades to injected context below.
const source = event.data.source as { kind?: unknown; name?: unknown; args?: unknown }
if (source.kind === 'skill-invocation' && typeof source.name === 'string') {
return {
kind: 'skill-invocation', seq: event.seq, time: event.time,
name: source.name,
...typeof source.args === 'string' ? { args: source.args } : {},
content: event.data.content, source: event.data.source,
}
}
// Injected context (plugin/goal source) folds to a context node, not a
// user message; only a direct human prompt is a user node. A compaction
// checkpoint never reaches here (isCompactCheckpoint routes it away).
@@ -80,6 +93,7 @@ function materializeNode(
kind: 'user', seq: event.seq, time: event.time,
content: event.data.content, source: event.data.source,
}
}
case 'assistant/message':
return {
kind: 'assistant', seq: event.seq, time: event.time,

View File

@@ -164,6 +164,31 @@ describe('TranscriptAdapter', () => {
expect(adapter.nodes().map(node => node.kind)).toEqual(['user', 'user', 'context'])
})
it('materializes a skill-invocation source as its dedicated node', () => {
const adapter = new TranscriptAdapter()
adapter.reset([
at(0, { type: 'user/message', surfaceOp: 'append', data: createUserMessage({
content: [{ type: 'text', text: '<skill_content name="hidden-demo">body</skill_content>\n\ncheck the fixture' }],
source: { kind: 'skill-invocation', name: 'hidden-demo', args: 'check the fixture' } as never,
}) }),
at(1, { type: 'user/message', surfaceOp: 'append', data: createUserMessage({
content: [{ type: 'text', text: '<skill_content name="bare-skill">body</skill_content>' }],
source: { kind: 'skill-invocation', name: 'bare-skill' } as never,
}) }),
])
const nodes = adapter.nodes()
expect(nodes.map(node => node.kind)).toEqual(['skill-invocation', 'skill-invocation'])
expect(nodes[0]).toMatchObject({ name: 'hidden-demo', args: 'check the fixture' })
expect(nodes[1]).toMatchObject({ name: 'bare-skill' })
expect((nodes[1] as { args?: string }).args).toBeUndefined()
// A malformed record (no readable name) degrades to injected context, not a crash.
adapter.append(at(2, { type: 'user/message', surfaceOp: 'append', data: createUserMessage({
content: [{ type: 'text', text: 'odd' }],
source: { kind: 'skill-invocation' } as never,
}) }))
expect(adapter.nodes().at(-1)?.kind).toBe('context')
})
it('skips events core does not call surface-eligible, marker or not', () => {
// The transcript is the append-origin surface, so log-only events (a chunk,
// a turn boundary, a compact/* provenance record) and a future type core

View File

@@ -256,3 +256,30 @@
white-space: nowrap;
vertical-align: baseline;
}
/* User-explicit skill invocation: the injected body collapses behind a
disclosure inside the user bubble. */
.skillInvocationDetails {
margin-top: 6px;
}
.skillInvocationSummary {
cursor: pointer;
font-size: 0.8em;
color: var(--dsw-alias-label-secondary);
user-select: none;
}
.skillInvocationBody {
margin: 6px 0 0;
padding: 8px;
max-height: 320px;
overflow: auto;
border-radius: 6px;
background: var(--dsw-alias-bg-secondary, rgba(0, 0, 0, 0.06));
font-family: var(--dsw-font-mono, monospace);
font-size: 0.78em;
line-height: 1.5;
white-space: pre-wrap;
word-break: break-word;
}

View File

@@ -7,8 +7,8 @@
import { memo, useEffect, useMemo, useState } from 'react'
import type { ReactNode } from 'react'
import type {
CompactionSummaryNode, ContextMessageNode, ModelRetryNode, SteeringMessageNode,
TurnErrorNode, UnknownSurfaceNode, UserMessageNode,
CompactionSummaryNode, ContextMessageNode, ModelRetryNode, SkillInvocationNode,
SteeringMessageNode, TurnErrorNode, UnknownSurfaceNode, UserMessageNode,
} from '@deepseek-ai/dsh-client-runtime/client'
import { JsonBlock, MessageText, StateDot } from '@deepseek-ai/dsh-client-ui-primitives'
import type { ChatViewSlotProps } from '../contract/slots.ts'
@@ -22,6 +22,7 @@ export interface MessageItemProps {
| UserMessageNode
| SteeringMessageNode
| ContextMessageNode
| SkillInvocationNode
| CompactionSummaryNode
| ModelRetryNode
| TurnErrorNode
@@ -193,6 +194,38 @@ function UserStyleBubble({
)
}
/**
* A user-explicit skill invocation: the right-aligned bubble presents the
* `/name args` gesture from source metadata (never re-parsed from the body),
* and the injected `<skill_content>` collapses behind a disclosure — the
* durable content is model-facing bulk, not conversation prose.
*/
function SkillInvocationRow({ node, t }: {
node: SkillInvocationNode
t: ChatViewSlotProps['t']
}): ReactNode {
const { text } = contentText(node.content)
return (
<div className={css.userRow} data-skill-invocation data-time-hover-root>
<div className={css.bubble}>
<span className={css.refChip} data-ref-chip="skill">{`/${node.name}`}</span>
{node.args !== undefined && <MessageText text={` ${node.args}`} />}
<details className={css.skillInvocationDetails}>
<summary className={css.skillInvocationSummary}>{t('message.skillInvocation.expand')}</summary>
<pre className={css.skillInvocationBody}>{text}</pre>
</details>
</div>
<MessageIconActions
text={text}
time={node.time}
clock="start"
className={css.actions}
t={t}
/>
</div>
)
}
/**
* Render one Host-authoritative pending steering item with the same visual
* language as its eventual durable transcript node.
@@ -254,6 +287,8 @@ export const MessageItem = memo(function MessageItem({
t={t}
/>
)
case 'skill-invocation':
return <SkillInvocationRow node={node} t={t} />
case 'compaction':
return <CompactionItem node={node} t={t} />
case 'model-retry':

View File

@@ -79,6 +79,7 @@ export const zh = {
'message.context.recall.counts': '保留 {retained} 条 · 省略 {omitted} 条',
'message.context.recall.truncated': '已截断',
'message.steering': '插话',
'message.skillInvocation.expand': '查看注入的 skill 内容',
'message.compaction': '上下文已压缩',
'message.compaction.expand': '点击查看压缩摘要',
'message.compaction.unavailable': '压缩摘要不可用',
@@ -219,6 +220,7 @@ export const en = {
'message.context.recall.counts': '{retained} kept · {omitted} omitted',
'message.context.recall.truncated': 'truncated',
'message.steering': 'Interjection',
'message.skillInvocation.expand': 'View injected skill content',
'message.compaction': 'Context compacted',
'message.compaction.expand': 'View compaction summary',
'message.compaction.unavailable': 'Compaction summary unavailable',

View File

@@ -864,6 +864,42 @@ describe('MessageItem arms', () => {
view.rerender(<MessageItem t={t} node={node} retryActive />)
expect(view.getByRole('status').textContent).toBe('正在重试模型请求1/2 · 1s')
})
it('skill-invocation renders the /name chip, args, and a collapsed injected body', () => {
const body = '<skill_content name="hidden-demo">instructions</skill_content>\n\ncheck the fixture'
const view = render(
<MessageItem t={t} node={{
kind: 'skill-invocation', seq: 4, time: 1_000,
name: 'hidden-demo', args: 'check the fixture',
content: [{ type: 'text', text: body }] as never,
source: null,
}}
/>,
)
const chip = view.container.querySelector('[data-ref-chip="skill"]')
expect(chip?.textContent).toBe('/hidden-demo')
const details = view.container.querySelector('details')
expect(details).toBeTruthy()
expect(details?.open).toBe(false)
expect(view.getByText('查看注入的 skill 内容')).toBeTruthy()
expect(view.container.querySelector('pre')?.textContent).toBe(body)
expect(view.container.querySelector('[data-skill-invocation]')).toBeTruthy()
})
it('skill-invocation without args renders only the chip line', () => {
const view = render(
<MessageItem t={t} node={{
kind: 'skill-invocation', seq: 5, time: 1_000,
name: 'bare-skill',
content: [{ type: 'text', text: '<skill_content name="bare-skill">x</skill_content>' }] as never,
source: null,
}}
/>,
)
const bubble = view.container.querySelector('[data-skill-invocation]')
expect(bubble?.textContent).toContain('/bare-skill')
expect(bubble?.textContent).not.toContain('undefined')
})
})
describe('formatMessageClock', () => {