fix(tui,host): pin replayed compaction and correct projection wording
Review follow-ups on the append-origin transcript projection.
The live/replay equivalence claim was stated unconditionally but does not
cover `tool/call`: only replay re-derives call pairing, because a call
event carries no `surfaceOp` of its own and inherits transcript
membership from the `assistant/message` that advertised it — which the
live listener has necessarily just rendered. Narrow the claim in the TUI
README and Agent Note, and record at `rebuildTranscript` why the filter
is replay-only rather than a missing live branch.
Add `surface-replayed-compaction`: the three existing fixtures all come
from the live path, leaving the resume case the bug report leads with
pinned only by a unit test. The new checkpoint mounts with the
replacement already stored and records byte-identical to
`surface-after-compaction-wide`, so the two fixtures now pin the
equivalence they assert. The shared fixture appends move into
`appendPreCompactionLog` / `appendCompactionCheckpoint`.
`MESSAGE_TYPES` is not "human message event types" — it includes
`assistant/message`. Say what the code distinguishes (append-origin
conversation messages vs. model-only replacement copies) at the const,
the `paginate` and `session.history` JSDoc, the apiproxy README, and the
Agent Note.
Also: spell the replace shape as `Extract<SurfaceOp, { op: 'replace' }>`
for symmetry with the module's two other uses; document why
`isCompactCheckpoint` keeps a replacement check that is redundant at both
call sites; say that Ctrl+R toggles reasoning, which rebuilds the
transcript; and qualify "the sole source of derived history" as derived
*model* history now that the transcript is the other projection.
This commit is contained in:
@@ -51,6 +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',
|
||||
@@ -182,6 +183,64 @@ 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.
|
||||
*/
|
||||
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: 'tool output that stays readable after compaction' }],
|
||||
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']>,
|
||||
@@ -689,57 +748,18 @@ describe('TUI terminal-state snapshots', () => {
|
||||
// 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)
|
||||
// beforeMount runs synchronously inside setupSnapshot, so the range the
|
||||
// checkpoint replaces is assigned before the first await below.
|
||||
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 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: 'tool output that stays readable after compaction' }],
|
||||
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: '<context_checkpoint>\nModel-only summary payload that must never reach the transcript.\n</context_checkpoint>',
|
||||
}],
|
||||
source: COMPACT_CHECKPOINT_SOURCE,
|
||||
}), {
|
||||
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 })
|
||||
@@ -750,6 +770,23 @@ 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, () => {
|
||||
|
||||
Reference in New Issue
Block a user