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

Merge remote-tracking branch 'origin/master' into feat/web-diff-card

Browse Source
This commit is contained in:
Chinesezjc
2026-07-30 21:37:01 +08:00
parent 1fd6b5a107 5fc2f4ba04
commit 46e18cf0d3
37 changed files with 710 additions and 169 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
packages/ui/tui/tests/snapshots/surface-after-compaction-narrow.expected.txt
View File

@@ -1,7 +1,7 @@
terminal 44x18 buffer=normal length=18 base=0 viewport=0
terminal 44x18 buffer=normal length=24 base=6 viewport=6
lifecycle started=1 stopped=0 progress=inactive
title "DSH snapshot"
cursor hidden column=7 viewportRow=14 bufferRow=14
cursor hidden column=7 viewportRow=17 bufferRow=23
buffer
0| " DEEPSEEK HARNESS"
style 1-8 fg=bright-magenta bold
@@ -13,25 +13,39 @@ buffer
3| <blank>
4| "Assistant "
style 0-8 fg=bright-magenta bold underline
5| "Model wait 0.0s "
5| <blank>
6| "You "
style 0-2 fg=bright-magenta bold underline
7| "Old prompt with a long line that exercises "
8| "wrapping and stays visible after compaction."
9| <blank>
10| "● Tool / bash / Run the coverage gate"
style 0-36 fg=green
11| "$ pnpm run test:coverage "
style 0-23 dim
12| "/workspace/project "
style 0-17 dim
13| "packages/ui/tui 100% "
style 0-19 dim
14| "… +1 lines (Ctrl+O to expand) "
style 0-28 dim
15| "1 test skipped "
style 0-13 dim
16| "coverage complete "
style 0-16 dim
17| "[exit 0] "
style 0-7 dim
18| "Model wait 0.0s "
style 0-14 dim
6| <blank>
7| "Context · workspace-context"
style 0-26 dim
8| "Additional instructions from: "
style 0-43 dim
9| "nested/AGENTS.md "
style 0-15 dim
10| " "
11| "Render workspace context XML clearly. "
style 0-36 dim
12| <blank>
13| "/workspace/project (tui-staging) deepseek-v"
19| <blank>
20| "… earlier context was compacted … "
style 0-32 dim
21| <blank>
22| "/workspace/project (tui-staging) deepseek-v"
style 0-17 fg=bright-magenta bold
style 18-31 dim
style 34-43 dim
14| " dsh > "
23| " dsh > "
style 1-3 fg=bright-magenta bold
style 5-6 dim
style 7-7 inverse
15-17| <blank>

44
packages/ui/tui/tests/snapshots/surface-after-compaction-wide.expected.txt
View File

@@ -1,7 +1,7 @@
terminal 104x30 buffer=normal length=30 base=0 viewport=0
lifecycle started=1 stopped=0 progress=inactive
title "DSH snapshot"
cursor hidden column=7 viewportRow=13 bufferRow=13
cursor hidden column=7 viewportRow=22 bufferRow=22
buffer
0| " DEEPSEEK HARNESS"
style 1-8 fg=bright-magenta bold
@@ -13,25 +13,41 @@ buffer
3| <blank>
4| "Assistant "
style 0-8 fg=bright-magenta bold underline
5| "Model wait 0.0s "
5| <blank>
6| "You "
style 0-2 fg=bright-magenta bold underline
7| "Old prompt with a long line that exercises wrapping and stays visible after compaction. "
8| <blank>
9| "● Tool / bash / Run the coverage gate"
style 0-36 fg=green
10| "$ pnpm run test:coverage "
style 0-23 dim
11| "/workspace/project "
style 0-17 dim
12| "packages/ui/tui 100% "
style 0-19 dim
13| "… +1 lines (Ctrl+O to expand) "
style 0-28 dim
14| "1 test skipped "
style 0-13 dim
15| "coverage complete "
style 0-16 dim
16| "[exit 0] "
style 0-7 dim
17| "Model wait 0.0s "
style 0-14 dim
6| <blank>
7| "Context · workspace-context"
style 0-26 dim
8| "Additional instructions from: nested/AGENTS.md "
style 0-45 dim
9| " "
10| "Render workspace context XML clearly. "
style 0-36 dim
11| <blank>
12| "/workspace/project (tui-staging) deepseek-v4-flash ↑0 ↓0 0% context"
18| <blank>
19| "… earlier context was compacted … "
style 0-32 dim
20| <blank>
21| "/workspace/project (tui-staging) deepseek-v4-flash ↑0 ↓0 0% context"
style 0-17 fg=bright-magenta bold
style 18-31 dim
style 34-50 dim
style 53-57 dim
style 60-69 dim
13| " dsh > "
22| " dsh > "
style 1-3 fg=bright-magenta bold
style 5-6 dim
style 7-7 inverse
14-29| <blank>
23-29| <blank>

33
packages/ui/tui/tests/snapshots/surface-before-compaction.expected.txt
View File

@@ -1,7 +1,7 @@
terminal 80x24 buffer=normal length=24 base=0 viewport=0
lifecycle started=1 stopped=0 progress=inactive
title "DSH snapshot"
cursor hidden column=7 viewportRow=20 bufferRow=20
cursor hidden column=7 viewportRow=21 bufferRow=21
buffer
0| " DEEPSEEK HARNESS"
style 1-8 fg=bright-magenta bold
@@ -16,35 +16,36 @@ buffer
5| <blank>
6| "You "
style 0-2 fg=bright-magenta bold underline
7| "Old prompt with a long line that exercises wrapping before compaction. "
8| <blank>
9| "● Tool / bash / Run the coverage gate"
7| "Old prompt with a long line that exercises wrapping and stays visible after "
8| "compaction. "
9| <blank>
10| "● Tool / bash / Run the coverage gate"
style 0-36 fg=green
10| "$ pnpm run test:coverage "
11| "$ pnpm run test:coverage "
style 0-23 dim
11| "/workspace/project "
12| "/workspace/project "
style 0-17 dim
12| "packages/ui/tui 100% "
13| "packages/ui/tui 100% "
style 0-19 dim
13| "… +1 lines (Ctrl+O to expand) "
14| "… +1 lines (Ctrl+O to expand) "
style 0-28 dim
14| "1 test skipped "
15| "1 test skipped "
style 0-13 dim
15| "coverage complete "
16| "coverage complete "
style 0-16 dim
16| "[exit 0] "
17| "[exit 0] "
style 0-7 dim
17| "Model wait 0.0s "
18| "Model wait 0.0s "
style 0-14 dim
18| <blank>
19| "/workspace/project (tui-staging) deepseek-v4-flash ↑0 ↓0 0% context"
19| <blank>
20| "/workspace/project (tui-staging) deepseek-v4-flash ↑0 ↓0 0% context"
style 0-17 fg=bright-magenta bold
style 18-31 dim
style 34-50 dim
style 53-57 dim
style 60-69 dim
20| " dsh > "
21| " dsh > "
style 1-3 fg=bright-magenta bold
style 5-6 dim
style 7-7 inverse
21-23| <blank>
22-23| <blank>

53
packages/ui/tui/tests/snapshots/surface-replayed-compaction.expected.txt Normal file
View File

@@ -0,0 +1,53 @@
terminal 104x30 buffer=normal length=30 base=0 viewport=0
lifecycle started=1 stopped=0 progress=inactive
title "DSH snapshot"
cursor hidden column=7 viewportRow=22 bufferRow=22
buffer
0| " DEEPSEEK HARNESS"
style 1-8 fg=bright-magenta bold
style 10-16 bold
1| " Snapshot agent ready."
style 1-21 dim
2| " main-session"
style 1-12 dim
3| <blank>
4| "Assistant "
style 0-8 fg=bright-magenta bold underline
5| <blank>
6| "You "
style 0-2 fg=bright-magenta bold underline
7| "Old prompt with a long line that exercises wrapping and stays visible after compaction. "
8| <blank>
9| "● Tool / bash / Run the coverage gate"
style 0-36 fg=green
10| "$ pnpm run test:coverage "
style 0-23 dim
11| "/workspace/project "
style 0-17 dim
12| "packages/ui/tui 100% "
style 0-19 dim
13| "… +1 lines (Ctrl+O to expand) "
style 0-28 dim
14| "1 test skipped "
style 0-13 dim
15| "coverage complete "
style 0-16 dim
16| "[exit 0] "
style 0-7 dim
17| "Model wait 0.0s "
style 0-14 dim
18| <blank>
19| "… earlier context was compacted … "
style 0-32 dim
20| <blank>
21| "/workspace/project (tui-staging) deepseek-v4-flash ↑0 ↓0 0% context"
style 0-17 fg=bright-magenta bold
style 18-31 dim
style 34-50 dim
style 53-57 dim
style 60-69 dim
22| " dsh > "
style 1-3 fg=bright-magenta bold
style 5-6 dim
style 7-7 inverse
23-29| <blank>

133
packages/ui/tui/tests/tui.snapshot.ts
View File

@@ -5,6 +5,7 @@ import { fileURLToPath } from 'node:url'
import { afterAll, describe, expect, it, vi } from 'vitest'
import type { Context } from 'cordis'
import { agentEvents } from '@deepseek-ai/dsh-agent'
import { COMPACT_CHECKPOINT_SOURCE } from '@deepseek-ai/dsh-compact'
import { createUserMessage, CallId, type ContentBlock , createMessage, createToolResultMessage } from '@deepseek-ai/dsh-llm'
import type {} from '@deepseek-ai/dsh-llm-retry'
import { SessionId, type JsonValue, type Session, type SessionEvent } from '@deepseek-ai/dsh-session'
@@ -50,6 +51,7 @@ const CHECKPOINTS = [
'surface-before-compaction',
'surface-after-compaction-narrow',
'surface-after-compaction-wide',
'surface-replayed-compaction',
'model-selector',
'model-selector-filtered',
'model-switching',
@@ -181,6 +183,67 @@ function appendToolResult(
}, { surfaceOp: 'append' })
}
/** Frozen clock for the compaction fixtures; see the live scenario for why. */
const COMPACTION_FIXTURE_TIME = new Date(2026, 6, 21, 14, 40, 0).getTime()
/** The surface range a compaction checkpoint replaces, with its provenance. */
interface CompactionRange {
start: number
end: number
sources: number[]
}
/**
* Append one prompt / tool-call / tool-result step, the history a compaction
* shadows on the model surface and the transcript must keep showing. The prompt
* text is rendered verbatim; the tool card's body comes from `bash`'s static
* presenter, so the fixtures pin that the shadowed step's card survives rather
* than the result content below.
*/
function appendPreCompactionLog(session: Session): CompactionRange {
const user = session.append('user/message', createUserMessage({
content: [{ type: 'text', text: 'Old prompt with a long line that exercises wrapping and stays visible after compaction.' }],
source: { kind: 'user' },
}), { surfaceOp: 'append' })
const assistant = session.append('assistant/message', {
turn: 1,
step: 1,
message: createMessage({
role: 'assistant',
content: [{ type: 'tool-call', id: CallId('old-tool'), name: 'bash', arguments: '{}' }],
source: {
kind: 'model',
...{ provider: 'mock', model: 'deepseek-v4-flash' },
},
}),
}, { surfaceOp: 'append' })
session.append('tool/call', { turn: 1, step: 1, callId: CallId('old-tool'), name: 'bash', arguments: '{}' })
const result = session.append('tool/result', {
turn: 1,
step: 1,
message: createToolResultMessage({
callId: CallId('old-tool'),
content: [{ type: 'text', text: 'shadowed step tool output' }],
isError: false,
}),
}, { surfaceOp: 'append' })
return { start: user.seq, end: result.seq, sources: [user.seq, assistant.seq, result.seq] }
}
/** Land a compaction: replace the range with the framed model-only checkpoint. */
function appendCompactionCheckpoint(session: Session, range: CompactionRange): void {
session.append('user/message', createUserMessage({
content: [{
type: 'text',
text: '<context_checkpoint>\nModel-only summary payload that must never reach the transcript.\n</context_checkpoint>',
}],
source: COMPACT_CHECKPOINT_SOURCE,
}), {
surfaceOp: { op: 'replace', start: range.start, end: range.end },
sourceEventSeqs: range.sources,
})
}
function visualTool(
name: string,
call: NonNullable<ToolDefinition['presentCall']>,
@@ -684,61 +747,22 @@ describe('TUI terminal-state snapshots', () => {
await disposeSnapshot(harness)
})
it('pins compaction surface replacement and narrow-to-wide reflow', async () => {
it('pins preserved history, the compaction marker, and narrow-to-wide reflow', async () => {
// Freeze the clock: the timing header hides zero-duration buckets, so a
// real-clock millisecond tick between the fixture appends and the render
// would flip `Tools 0.0s` in and out of the pinned header.
const nowSpy = vi.spyOn(Date, 'now').mockReturnValue(new Date(2026, 6, 21, 14, 40, 0).getTime())
let replacementStart = 0
let replacementEnd = 0
let replacementSources: number[] = []
const nowSpy = vi.spyOn(Date, 'now').mockReturnValue(COMPACTION_FIXTURE_TIME)
// The awaited setup always invokes beforeMount, so the range the checkpoint
// replaces is assigned by the time the appends below need it.
let compacted!: CompactionRange
const harness = await setupSnapshot({
tools: ADVANCED_CARD_TOOLS,
beforeMount(session) {
const user = session.append('user/message', createUserMessage({
content: [{ type: 'text', text: 'Old prompt with a long line that exercises wrapping before compaction.' }],
source: { kind: 'user' },
}), { surfaceOp: 'append' })
const assistant = session.append('assistant/message', {
turn: 1,
step: 1,
message: createMessage({
role: 'assistant',
content: [{ type: 'tool-call', id: CallId('old-tool'), name: 'bash', arguments: '{}' }],
source: {
kind: 'model',
...{ provider: 'mock', model: 'deepseek-v4-flash' },
},
}),
}, { surfaceOp: 'append' })
session.append('tool/call', { turn: 1, step: 1, callId: CallId('old-tool'), name: 'bash', arguments: '{}' })
const result = session.append('tool/result', {
turn: 1,
step: 1,
message: createToolResultMessage({
callId: CallId('old-tool'),
content: [{ type: 'text', text: 'obsolete output that must disappear' }],
isError: false,
}),
}, { surfaceOp: 'append' })
replacementStart = user.seq
replacementEnd = result.seq
replacementSources = [user.seq, assistant.seq, result.seq]
},
beforeMount(session) { compacted = appendPreCompactionLog(session) },
}, { columns: 80, rows: 24 })
await checkpoint('surface-before-compaction', harness.terminal, { includeScrollback: true })
await renderAfter(harness, () => {
harness.session.append('user/message', createUserMessage({
content: [{
type: 'text',
text: '<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nRender workspace context XML clearly.\n</system-reminder>',
}],
source: { kind: 'plugin', plugin: 'workspace-context' },
}), {
surfaceOp: { op: 'replace', start: replacementStart, end: replacementEnd },
sourceEventSeqs: replacementSources,
})
appendCompactionCheckpoint(harness.session, compacted)
harness.terminal.resize(44, 18)
})
await checkpoint('surface-after-compaction-narrow', harness.terminal, { includeScrollback: true })
@@ -749,6 +773,23 @@ describe('TUI terminal-state snapshots', () => {
nowSpy.mockRestore()
})
// The resume path, which is what regressed for real users: the replacement is
// already stored when the terminal mounts, so the transcript comes from replay
// rather than from live appends. Pinned against the same log the live scenario
// ends on, at its wide size, so the two fixtures are directly comparable.
it('pins a stored compaction replayed at mount', async () => {
const nowSpy = vi.spyOn(Date, 'now').mockReturnValue(COMPACTION_FIXTURE_TIME)
const harness = await setupSnapshot({
tools: ADVANCED_CARD_TOOLS,
beforeMount(session) {
appendCompactionCheckpoint(session, appendPreCompactionLog(session))
},
}, { columns: 104, rows: 30 })
await checkpoint('surface-replayed-compaction', harness.terminal, { includeScrollback: true })
await disposeSnapshot(harness)
nowSpy.mockRestore()
})
it('pins wrapped and explicit multiline shell-prompt input', async () => {
const harness = await setupSnapshot({}, { columns: 44, rows: 18 })
await renderAfter(harness, () => {

120
packages/ui/tui/tests/tui.spec.ts
View File

@@ -19,6 +19,7 @@ import { createUserMessage,
} from '@deepseek-ai/dsh-llm'
import { GOAL_CHANGE_VERSION, GoalId, renderGoalChange, type GoalSnapshotChangeMeta } from '@deepseek-ai/dsh-goal'
import CommandService, { type CommandInvocation } from '@deepseek-ai/dsh-commands'
import { COMPACT_CHECKPOINT_SOURCE } from '@deepseek-ai/dsh-compact'
import SessionStore, { SessionId, type JsonValue, type SessionEvent, type SessionHeader, type TurnEndReason } from '@deepseek-ai/dsh-session'
import type { SessionRecord } from '@deepseek-ai/dsh-session-query'
import SkillService, { type SkillCatalogSnapshot, type SkillDefinition, type SkillProvider, type SkillSummary } from '@deepseek-ai/dsh-skill'
@@ -4699,10 +4700,10 @@ describe('tool cards and surface replay', () => {
await dispose(result)
})
it('rebuilds after a surface replacement and hides shadowed tool calls', async () => {
it('keeps append-origin history and marks a landed compaction, live and on rebuild', async () => {
const result = await setup({ tools })
appendUser(result.session, 'old prompt')
const assistant = result.session.append('assistant/message', {
result.session.append('assistant/message', {
turn: 1,
step: 1,
message: createMessage({
@@ -4725,21 +4726,116 @@ describe('tool cards and surface replay', () => {
isError: false,
}),
}, { surfaceOp: 'append' })
const start = result.session.surface.nodes[0] as number
result.session.append('user/message', createUserMessage({
content: [{ type: 'text', text: 'summary replacement' }],
source: { kind: 'plugin', plugin: 'compact' },
}), {
surfaceOp: { op: 'replace', start, end: toolResult.seq },
sourceEventSeqs: [start, assistant.seq, toolResult.seq],
// Result pruning rewrites one node's content in place: model-only, and no
// boundary in the conversation, so the terminal keeps the full output.
const originalResult = toolResult.data.message.content[0]
result.session.append('tool/result', {
...toolResult.data,
message: freezeMessage({
...toolResult.data.message,
content: [{ ...originalResult, content: [{ type: 'text', text: 'pruned result copy' }] }] as [typeof originalResult],
}),
}, {
surfaceOp: { op: 'replace', start: toolResult.seq, end: toolResult.seq },
sourceEventSeqs: [toolResult.seq],
})
const nodes = [...result.session.surface.nodes]
const checkpoint = result.session.append('user/message', createUserMessage({
content: [{ type: 'text', text: '<context_checkpoint>model-only summary payload</context_checkpoint>' }],
source: COMPACT_CHECKPOINT_SOURCE,
}), {
surfaceOp: { op: 'replace', start: nodes[0] as number, end: nodes.at(-1) as number },
sourceEventSeqs: nodes,
})
// A regenerated assistant message replaces one node without summarizing
// anything, so it marks no boundary either.
const generic = result.session.append('assistant/message', {
turn: 1,
step: 1,
message: createMessage({
role: 'assistant',
content: [{ type: 'text', text: 'generic replacement copy' }],
source: {
kind: 'model',
...{ provider: 'mock', model: 'deepseek-v4-flash' },
},
}),
}, { surfaceOp: { op: 'replace', start: checkpoint.seq, end: checkpoint.seq }, sourceEventSeqs: [checkpoint.seq] })
// Only a checkpoint carrying the compaction seam's source marks a boundary:
// another plugin replacing a node is model-only.
result.session.append('user/message', createUserMessage({
content: [{ type: 'text', text: 'foreign plugin replacement copy' }],
source: { kind: 'plugin', plugin: 'other' },
}), { surfaceOp: { op: 'replace', start: generic.seq, end: generic.seq }, sourceEventSeqs: [generic.seq] })
await tick()
result.terminal.resize(89)
await tick()
const lastFullRender = result.terminal.output.slice(result.terminal.output.lastIndexOf('\x1b[2J'))
expect(lastFullRender).toContain('summary replacement')
expect(lastFullRender).not.toContain('old output')
const liveRender = result.terminal.output.slice(result.terminal.output.lastIndexOf('\x1b[2J'))
expect(liveRender).toContain('old prompt')
// The shadowed step keeps its card: one call row, one full result, no
// second card from the pruned copy.
expect(liveRender.split('$ printf hello')).toHaveLength(2)
expect(liveRender).toContain('third')
expect(liveRender.split('[exit 0]')).toHaveLength(2)
expect(liveRender.split('… earlier context was compacted …')).toHaveLength(2)
expect(liveRender).not.toContain('model-only summary payload')
expect(liveRender).not.toContain('generic replacement copy')
expect(liveRender).not.toContain('foreign plugin replacement copy')
// Ctrl+R toggles reasoning, which rebuilds the transcript from the log; the
// replayed projection matches what the live appends produced, including the
// shadowed assistant message's tool card.
result.terminal.send('\x12')
await tick()
result.terminal.resize(90)
await tick()
const replayRender = result.terminal.output.slice(result.terminal.output.lastIndexOf('\x1b[2J'))
expect(replayRender).toContain('old prompt')
expect(replayRender.split('$ printf hello')).toHaveLength(2)
expect(replayRender).toContain('third')
expect(replayRender.split('[exit 0]')).toHaveLength(2)
expect(replayRender.split('… earlier context was compacted …')).toHaveLength(2)
expect(replayRender).not.toContain('model-only summary payload')
expect(replayRender).not.toContain('generic replacement copy')
expect(replayRender).not.toContain('foreign plugin replacement copy')
await dispose(result)
})
it('replays a stored compaction as preserved history plus its marker', async () => {
const result = await setup({
beforeMount(session) {
appendUser(session, 'prompt before compaction')
session.append('assistant/message', {
turn: 1,
step: 1,
message: createMessage({
role: 'assistant',
content: [{ type: 'text', text: 'reply before compaction' }],
source: {
kind: 'model',
...{ provider: 'mock', model: 'deepseek-v4-flash' },
},
}),
}, { surfaceOp: 'append' })
const nodes = [...session.surface.nodes]
session.append('user/message', createUserMessage({
content: [{ type: 'text', text: '<context_checkpoint>stored model-only payload</context_checkpoint>' }],
source: COMPACT_CHECKPOINT_SOURCE,
}), {
surfaceOp: { op: 'replace', start: nodes[0] as number, end: nodes.at(-1) as number },
sourceEventSeqs: nodes,
})
},
})
result.terminal.resize(89)
await tick()
const mounted = result.terminal.output.slice(result.terminal.output.lastIndexOf('\x1b[2J'))
expect(mounted).toContain('prompt before compaction')
expect(mounted).toContain('reply before compaction')
expect(mounted.split('… earlier context was compacted …')).toHaveLength(2)
expect(mounted).not.toContain('stored model-only payload')
await dispose(result)
})
})