Merge branch 'worktree-session-modes-rfc' (master: sandbox stack #169, skills #109, prompt snapshots #254)
The stack rebases onto a moved master through its base branch. Beyond mechanical unions (both branches' demo scripts, example rows, service roles, tool lists, acp deps, doc budgets — each side fit alone, the union needs the higher ceilings), three semantic reconciliations: - The ACP bridge now carries BOTH per-session surfaces: the sandbox stack's config options + approval answerer and this branch's session modes; session/new and session/load advertise modes AND configOptions side by side. - The feature matrix supersedes the sandbox stance per the RFC's second-lander rule: session/set_mode and current_mode_update flip to shipped-by-dsh-mode, config-option rows stay as #169 wrote them, and §6 records both landed features under the picker-to-modes / knobs-to-config-options division. - The snapshot pin grammar (#254: one header snapshot + declared deltas + a Markdown prompt golden) gains a symmetric declaration for what a delta cannot express: expectedHeaderSnapshots — a plan-mode flip resorts the canonical tool list, so its widening lands as a second full snapshot, now its own Markdown section. The pin-less-class and model-turn-only-pin amendments carry over; new fixtures cover the extended writer paths, and the plan-acp-agent scenarios re-recorded under the merged composition (the app now bundles the skill tool) with the suite's refresh mode wired through.
This commit is contained in:
@@ -62,6 +62,13 @@ interface Behavior {
|
||||
strayBucketFile?: boolean
|
||||
/** Delete the sessions root entirely (harvest must yield no logs). */
|
||||
deleteSessionsRoot?: boolean
|
||||
/**
|
||||
* Vocabulary for `session/set_config_option`: allowed values per config id.
|
||||
* A set naming an unknown id or an out-of-vocabulary value rejects (the
|
||||
* real bridge's rule); a valid set answers with the complete refreshed
|
||||
* option state, `currentValue` updated. Absent: every set rejects.
|
||||
*/
|
||||
configOptions?: Record<string, string[]>
|
||||
}
|
||||
|
||||
const sessionsRoot = process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? ''
|
||||
@@ -85,6 +92,8 @@ let sessionCwd = ''
|
||||
let parkedPromptId: number | string | null = null
|
||||
/** Resolvers for outbound probe responses (permission/elicitation), keyed by request id. */
|
||||
const pendingOutbound = new Map<number, (result: unknown) => void>()
|
||||
/** Per-run `session/set_config_option` state: config id → current value (first vocabulary entry until set). */
|
||||
const currentConfig: Record<string, string> = {}
|
||||
|
||||
function send(frame: Record<string, unknown>): void {
|
||||
process.stdout.write(`${JSON.stringify({ jsonrpc: '2.0', ...frame })}\n`)
|
||||
@@ -224,6 +233,32 @@ function handleFrame(frame: Record<string, unknown>): void {
|
||||
chunk(`setMode:${String(params.modeId)}`)
|
||||
respond(id as number | string, {})
|
||||
return
|
||||
case 'session/set_config_option': {
|
||||
const vocabulary = behavior.configOptions
|
||||
const configId = params.configId as string
|
||||
const value = params.value as string
|
||||
const values = vocabulary?.[configId]
|
||||
if (values === undefined) {
|
||||
respondError(id as number | string, `unknown config option ${configId}`)
|
||||
return
|
||||
}
|
||||
if (!values.includes(value)) {
|
||||
respondError(id as number | string, `unknown ${configId} value ${value}`)
|
||||
return
|
||||
}
|
||||
currentConfig[configId] = value
|
||||
// The real bridge's contract: every set answers with the COMPLETE
|
||||
// refreshed option state, not just the changed entry.
|
||||
respond(id as number | string, {
|
||||
configOptions: Object.entries(vocabulary as Record<string, string[]>).map(([cid, vs]) => ({
|
||||
id: cid,
|
||||
type: 'select',
|
||||
currentValue: currentConfig[cid] ?? vs[0],
|
||||
options: vs.map(v => ({ value: v, name: v })),
|
||||
})),
|
||||
})
|
||||
return
|
||||
}
|
||||
case 'session/cancel':
|
||||
if (parkedPromptId !== null) {
|
||||
const parked = parkedPromptId
|
||||
|
||||
@@ -1,10 +1,74 @@
|
||||
{
|
||||
"prompt": "respond",
|
||||
"logs": [{
|
||||
"file": "b/main.jsonl",
|
||||
"lines": [
|
||||
{ "type": "session", "id": "{{SID}}", "createdAt": 600, "cwd": "{{CWD}}" },
|
||||
{ "type": "request/header", "seq": 0, "time": 4, "data": { "header": { "config": { "model": "fake" }, "system": "SYS PROMPT", "tools": [{ "name": "t1", "description": "D1", "parameters": { "type": "object" } }] }, "reason": "initial" } }
|
||||
]
|
||||
}]
|
||||
"logs": [
|
||||
{
|
||||
"file": "b/main.jsonl",
|
||||
"lines": [
|
||||
{
|
||||
"type": "session",
|
||||
"id": "{{SID}}",
|
||||
"createdAt": 600,
|
||||
"cwd": "{{CWD}}"
|
||||
},
|
||||
{
|
||||
"type": "request/header",
|
||||
"seq": 0,
|
||||
"time": 4,
|
||||
"data": {
|
||||
"header": {
|
||||
"config": {
|
||||
"model": "fake"
|
||||
},
|
||||
"system": "SYS PROMPT",
|
||||
"tools": [
|
||||
{
|
||||
"name": "t1",
|
||||
"description": "D1",
|
||||
"parameters": {
|
||||
"type": "object"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
"reason": "initial"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"file": "b/pin-child.jsonl",
|
||||
"lines": [
|
||||
{
|
||||
"type": "session",
|
||||
"id": "cdcdcdcd-abab-4efe-8ada-badabadabada",
|
||||
"createdAt": 650,
|
||||
"cwd": "{{CWD}}",
|
||||
"parentSession": "{{SID}}"
|
||||
},
|
||||
{
|
||||
"type": "request/header",
|
||||
"seq": 0,
|
||||
"time": 2,
|
||||
"data": {
|
||||
"header": {
|
||||
"config": {
|
||||
"model": "fake"
|
||||
},
|
||||
"system": "SYS PROMPT",
|
||||
"tools": [
|
||||
{
|
||||
"name": "t1",
|
||||
"description": "D1",
|
||||
"parameters": {
|
||||
"type": "object"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
"reason": "initial"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
2
packages/support/acp-snapshot/tests/fixtures/record-suite/rec-pin/session.1.jsonl
vendored
Normal file
2
packages/support/acp-snapshot/tests/fixtures/record-suite/rec-pin/session.1.jsonl
vendored
Normal file
@@ -0,0 +1,2 @@
|
||||
{"type":"session","id":"abababab-cdcd-4efe-8ada-badabadabada","createdAt":800,"cwd":"/var/folders/2g/b32ct0qn1d728l_v6tdkjytr0000gn/T/acp-snap-cwd-KBQJbW","parentSession":"f6fa7fcf-dd9c-4b39-8815-b25ddcebfd88"}
|
||||
{"type":"request/header","seq":0,"time":2,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
@@ -1,2 +1,2 @@
|
||||
{"type":"session","id":"ccdc749f-56f3-4267-9750-598b5c60b7b2","createdAt":600,"cwd":"/var/folders/2g/b32ct0qn1d728l_v6tdkjytr0000gn/T/acp-snap-cwd-nOQ4Gy"}
|
||||
{"type":"request/header","seq":0,"time":4,"data":{"header":{"config":{"model":"fake"},"system":"SYS PROMPT","tools":[{"name":"t1","description":"D1","parameters":{"type":"object"}}]},"reason":"initial"}}
|
||||
{"type":"request/header","seq":0,"time":4,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":[{"name":"t1","description":"D1","parameters":{"type":"object"}}]},"reason":"initial"}}
|
||||
|
||||
1
packages/support/acp-snapshot/tests/fixtures/record-suite/rec-pin/system-prompt.golden.md
vendored
Normal file
1
packages/support/acp-snapshot/tests/fixtures/record-suite/rec-pin/system-prompt.golden.md
vendored
Normal file
@@ -0,0 +1 @@
|
||||
SYS PROMPT
|
||||
1
packages/support/acp-snapshot/tests/fixtures/suite/no-model-unpinned/behavior.json
vendored
Normal file
1
packages/support/acp-snapshot/tests/fixtures/suite/no-model-unpinned/behavior.json
vendored
Normal file
@@ -0,0 +1 @@
|
||||
{}
|
||||
1
packages/support/acp-snapshot/tests/fixtures/suite/no-model-unpinned/input.json
vendored
Normal file
1
packages/support/acp-snapshot/tests/fixtures/suite/no-model-unpinned/input.json
vendored
Normal file
@@ -0,0 +1 @@
|
||||
{ "steps": [{ "op": "initialize" }] }
|
||||
1
packages/support/acp-snapshot/tests/fixtures/suite/no-model-unpinned/session.jsonl
vendored
Normal file
1
packages/support/acp-snapshot/tests/fixtures/suite/no-model-unpinned/session.jsonl
vendored
Normal file
@@ -0,0 +1 @@
|
||||
{"type":"session","id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}"}
|
||||
1
packages/support/acp-snapshot/tests/fixtures/suite/no-model-unpinned/stdout.golden.jsonl
vendored
Normal file
1
packages/support/acp-snapshot/tests/fixtures/suite/no-model-unpinned/stdout.golden.jsonl
vendored
Normal file
@@ -0,0 +1 @@
|
||||
{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentCapabilities":{"loadSession":false}}}
|
||||
@@ -5,7 +5,8 @@
|
||||
"lines": [
|
||||
{ "type": "session", "id": "{{SID}}", "createdAt": 100, "cwd": "{{CWD}}" },
|
||||
{ "type": "request/header", "seq": 0, "time": 100, "data": { "header": { "config": { "model": "fake" }, "system": "SYS PROMPT", "tools": [{ "name": "t1", "description": "D1", "parameters": { "type": "object" } }] }, "reason": "initial" } },
|
||||
{ "type": "turn/start", "seq": 1, "time": 100, "data": { "turn": 1 } }
|
||||
{ "type": "request/header-delta", "seq": 1, "time": 100, "data": { "system": { "keepStart": 1, "keepEnd": 0, "insert": ["NEW PROMPT LINE"] } } },
|
||||
{ "type": "turn/start", "seq": 2, "time": 100, "data": { "turn": 1 } }
|
||||
]
|
||||
}]
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"type":"session","id":"12121212-3434-4545-8686-787878787878","createdAt":7,"cwd":"/rec/pin-cwd"}
|
||||
{"type":"request/header","seq":0,"time":7,"data":{"header":{"config":{"model":"fake"},"system":"SYS PROMPT","tools":[{"name":"t1","description":"D1","parameters":{"type":"object"}}]},"reason":"initial"}}
|
||||
{"type":"turn/start","seq":1,"time":7,"data":{"turn":1}}
|
||||
{"type":"request/header","seq":0,"time":7,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":[{"name":"t1","description":"D1","parameters":{"type":"object"}}]},"reason":"initial"}}
|
||||
{"type":"request/header-delta","seq":1,"time":7,"data":{"system":{"keepStart":1,"keepEnd":0,"insert":["{{system}}"]}}}
|
||||
{"type":"turn/start","seq":2,"time":7,"data":{"turn":1}}
|
||||
|
||||
5
packages/support/acp-snapshot/tests/fixtures/suite/pin-turn/system-prompt.golden.md
vendored
Normal file
5
packages/support/acp-snapshot/tests/fixtures/suite/pin-turn/system-prompt.golden.md
vendored
Normal file
@@ -0,0 +1,5 @@
|
||||
SYS PROMPT
|
||||
|
||||
<!-- request/header-delta 1: keepStart=1, keepEnd=0 -->
|
||||
|
||||
NEW PROMPT LINE
|
||||
@@ -168,6 +168,8 @@ describe('runScenario', () => {
|
||||
[{ op: 'promptExpectError', text: 'x' }, /promptExpectError before newSession/],
|
||||
[{ op: 'promptAndCancel', text: 'x' }, /promptAndCancel before newSession/],
|
||||
[{ op: 'cancel' }, /cancel before newSession/],
|
||||
[{ op: 'setConfigOption', configId: 'sandbox-mode', value: 'read-only' }, /setConfigOption before newSession/],
|
||||
[{ op: 'setConfigOptionExpectError', configId: 'sandbox-mode', value: 'yolo' }, /setConfigOptionExpectError before newSession/],
|
||||
] as [InputStep, RegExp][])('rejects %j before newSession', { timeout: 20_000 }, async (step, message) => {
|
||||
const { fixtureFile } = await scenario({})
|
||||
await expect(runScenario(
|
||||
@@ -176,6 +178,53 @@ describe('runScenario', () => {
|
||||
)).rejects.toThrow(message)
|
||||
})
|
||||
|
||||
it('setConfigOption switches a value and receives the complete refreshed option state', { timeout: 20_000 }, async () => {
|
||||
const { fixtureFile } = await scenario({
|
||||
configOptions: { 'sandbox-mode': ['read-only', 'workspace-write'], 'approval-policy': ['ask', 'never'] },
|
||||
})
|
||||
const result = await runScenario(
|
||||
{
|
||||
steps: [...boot,
|
||||
{ op: 'setConfigOption', configId: 'sandbox-mode', value: 'workspace-write' },
|
||||
{ op: 'setConfigOption', configId: 'approval-policy', value: 'never' }],
|
||||
},
|
||||
{ agent: AGENT, mode: 'replay', fixtureFile },
|
||||
)
|
||||
// Every set answers with the FULL state: the second response carries the
|
||||
// first switch's value too — the complete-refreshed-state contract.
|
||||
const frames = result.rawStdout.trim().split('\n').map(line => JSON.parse(line) as { result?: { configOptions?: { id: string; currentValue: string }[] } })
|
||||
const states = frames
|
||||
.map(f => f.result?.configOptions)
|
||||
.filter(options => options !== undefined)
|
||||
.map(options => Object.fromEntries((options as { id: string; currentValue: string }[]).map(o => [o.id, o.currentValue])))
|
||||
expect(states).toEqual([
|
||||
{ 'sandbox-mode': 'workspace-write', 'approval-policy': 'ask' },
|
||||
{ 'sandbox-mode': 'workspace-write', 'approval-policy': 'never' },
|
||||
])
|
||||
})
|
||||
|
||||
it('setConfigOptionExpectError swallows the rejection for unknown ids and out-of-vocabulary values', { timeout: 20_000 }, async () => {
|
||||
const { fixtureFile } = await scenario({ configOptions: { 'sandbox-mode': ['read-only'] } })
|
||||
const result = await runScenario(
|
||||
{
|
||||
steps: [...boot,
|
||||
{ op: 'setConfigOptionExpectError', configId: 'sandbox-mode', value: 'yolo' },
|
||||
{ op: 'setConfigOptionExpectError', configId: 'reasoning-effort', value: 'max' }],
|
||||
},
|
||||
{ agent: AGENT, mode: 'replay', fixtureFile },
|
||||
)
|
||||
expect(result.rawStdout).toContain('unknown sandbox-mode value yolo')
|
||||
expect(result.rawStdout).toContain('unknown config option reasoning-effort')
|
||||
})
|
||||
|
||||
it('setConfigOptionExpectError throws when the set unexpectedly succeeds', { timeout: 20_000 }, async () => {
|
||||
const { fixtureFile } = await scenario({ configOptions: { 'sandbox-mode': ['read-only'] } })
|
||||
await expect(runScenario(
|
||||
{ steps: [...boot, { op: 'setConfigOptionExpectError', configId: 'sandbox-mode', value: 'read-only' }] },
|
||||
{ agent: AGENT, mode: 'replay', fixtureFile },
|
||||
)).rejects.toThrow(/expected set_config_option to be rejected/)
|
||||
})
|
||||
|
||||
it('rejects an unknown input op', { timeout: 20_000 }, async () => {
|
||||
const { fixtureFile } = await scenario({})
|
||||
const bogus = { op: 'reticulate' } as unknown as InputStep
|
||||
|
||||
@@ -1,5 +1,11 @@
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { type NormalizeContext, normalizeSessionLog, normalizeStdout, scrubRequestHeaders } from '../src/normalize.ts'
|
||||
import {
|
||||
type NormalizeContext,
|
||||
normalizeSessionLog,
|
||||
normalizeStdout,
|
||||
scrubRequestHeaders,
|
||||
scrubSystemPrompts,
|
||||
} from '../src/normalize.ts'
|
||||
|
||||
/**
|
||||
* Unit tests for the pure snapshot normalizers. Live as a *.spec.ts (runs in
|
||||
@@ -260,3 +266,43 @@ describe('scrubRequestHeaders', () => {
|
||||
expect(scrubRequestHeaders(once)).toBe(once)
|
||||
})
|
||||
})
|
||||
|
||||
describe('scrubSystemPrompts', () => {
|
||||
it('scrubs only system prompt payloads while keeping tools and prefixes verbatim', () => {
|
||||
const header = JSON.stringify({
|
||||
type: 'request/header', seq: 1, time: 2,
|
||||
data: {
|
||||
header: {
|
||||
system: 'full prompt',
|
||||
tools: [{ name: 'read', description: 'full schema' }],
|
||||
messagePrefix: [{ role: 'user', content: [{ type: 'text', text: 'full prefix' }] }],
|
||||
},
|
||||
reason: 'initial',
|
||||
},
|
||||
})
|
||||
const delta = JSON.stringify({
|
||||
type: 'request/header-delta', seq: 2, time: 3,
|
||||
data: {
|
||||
system: { keepStart: 1, keepEnd: 2, insert: ['new prompt line'] },
|
||||
tools: { changed: [{ name: 'read', description: 'changed schema' }] },
|
||||
messagePrefix: [{ role: 'user', content: [{ type: 'text', text: 'changed prefix' }] }],
|
||||
},
|
||||
})
|
||||
const toolsOnly = JSON.stringify({
|
||||
type: 'request/header', seq: 3, time: 4,
|
||||
data: { header: { tools: [{ name: 'read', description: 'schema only' }] }, reason: 'resume' },
|
||||
})
|
||||
|
||||
const out = scrubSystemPrompts(`${header}\n${delta}\n${toolsOnly}\n`)
|
||||
expect(out).toContain('"system":"{{system}}"')
|
||||
expect(out).toContain('"insert":["{{system}}"]')
|
||||
expect(out).not.toContain('full prompt')
|
||||
expect(out).not.toContain('new prompt line')
|
||||
expect(out).toContain('full schema')
|
||||
expect(out).toContain('full prefix')
|
||||
expect(out).toContain('changed schema')
|
||||
expect(out).toContain('changed prefix')
|
||||
expect(out.split('\n')[2]).toBe(toolsOnly)
|
||||
expect(scrubSystemPrompts(out)).toBe(out)
|
||||
})
|
||||
})
|
||||
|
||||
@@ -1,11 +1,21 @@
|
||||
import { cpSync, mkdtempSync } from 'node:fs'
|
||||
import { cpSync, mkdtempSync, readFileSync, writeFileSync } from 'node:fs'
|
||||
import { rm } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import { fileURLToPath } from 'node:url'
|
||||
import { afterAll, describe, expect, it } from 'vitest'
|
||||
import { defineAcpSnapshotSuite, type Scenario } from '../src/index.ts'
|
||||
import { childFixturePaths, fixtureContext, headerDeltaCount, normalizedHeaders } from '../src/suite.ts'
|
||||
import { defineAcpSnapshotSuite, type HarvestedLog, type Scenario } from '../src/index.ts'
|
||||
import {
|
||||
childFixturePaths,
|
||||
fixtureContext,
|
||||
formatSystemPromptSnapshot,
|
||||
headerDeltaCount,
|
||||
normalizedHeaders,
|
||||
normalizedSystemPromptDeltas,
|
||||
normalizedSystemPrompts,
|
||||
refreshFixtureReplacements,
|
||||
stabilizeRefreshLog,
|
||||
} from '../src/suite.ts'
|
||||
|
||||
/**
|
||||
* Unit tests for the suite factory, by running it: two synthetic suites over
|
||||
@@ -41,30 +51,58 @@ const RECORD_SRC = fileURLToPath(new URL('./fixtures/record-suite', import.meta.
|
||||
// is what this suite can exercise; the real overlay boot is the acp-agent
|
||||
// example's code-mode scenarios).
|
||||
const REPLAY_SCENARIOS: Scenario[] = [
|
||||
{ name: 'pin-turn', hasModelTurn: true, recorded: true, pinsHeader: true, headerClass: 'main' },
|
||||
{ name: 'pin-turn', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderDeltas: 1, headerClass: 'main' },
|
||||
{ name: 'plain-turn', hasModelTurn: true, recorded: true, childSessions: 1, headerClass: 'main', configPath: AGENT.configPath },
|
||||
{ name: 'no-model', hasModelTurn: false, recorded: false, headerClass: 'main' },
|
||||
// A pin-LESS class: protocol-only scenarios have no header content to
|
||||
// anchor, so the factory demands no pin and the uniformity guard skips.
|
||||
{ name: 'no-model-unpinned', hasModelTurn: false, recorded: false, headerClass: 'unpinned' },
|
||||
{ name: 'blocked-log', hasModelTurn: false, comparesLog: true, recorded: false, headerClass: 'main' },
|
||||
{ name: 'authored-error', hasModelTurn: true, recorded: false, overridden: true, headerClass: 'main' },
|
||||
]
|
||||
|
||||
const RECORD_SCENARIOS: Scenario[] = [
|
||||
{ name: 'rec-pin', hasModelTurn: true, recorded: true, pinsHeader: true },
|
||||
{ name: 'rec-pin', hasModelTurn: true, recorded: true, pinsHeader: true, childSessions: 1 },
|
||||
{ name: 'rec-child', hasModelTurn: true, recorded: true, childSessions: 1 },
|
||||
// recorded:false in record mode → registered but skipped (never re-recorded).
|
||||
{ name: 'rec-skip', hasModelTurn: true, recorded: false, overridden: true },
|
||||
]
|
||||
|
||||
// Record mode mutates its snapshots dir, so run it on a throwaway copy —
|
||||
// except under the documented bootstrap knob, which regenerates the committed
|
||||
// fixtures/goldens in place.
|
||||
// Record/refresh modes mutate their snapshots dir, so run them on throwaway
|
||||
// copies — except record's documented bootstrap knob, which regenerates the
|
||||
// committed record fixtures/goldens in place.
|
||||
const BOOTSTRAP = process.env.ACP_SNAPSHOT_SPEC_BOOTSTRAP === '1'
|
||||
const recordDir = BOOTSTRAP ? RECORD_SRC : mkdtempSync(join(tmpdir(), 'acp-snap-record-suite-'))
|
||||
if (!BOOTSTRAP) cpSync(RECORD_SRC, recordDir, { recursive: true })
|
||||
const refreshDir = mkdtempSync(join(tmpdir(), 'acp-snap-refresh-suite-'))
|
||||
cpSync(REPLAY_DIR, refreshDir, { recursive: true })
|
||||
staleRefreshFixtures(refreshDir)
|
||||
afterAll(async () => {
|
||||
if (!BOOTSTRAP) await rm(recordDir, { recursive: true, force: true })
|
||||
await rm(refreshDir, { recursive: true, force: true })
|
||||
})
|
||||
|
||||
function staleRefreshFixtures(dir: string): void {
|
||||
writeFileSync(join(dir, 'plain-turn', 'stdout.golden.jsonl'), 'stale stdout\n')
|
||||
writeFileSync(join(dir, 'pin-turn', 'system-prompt.golden.md'), 'STALE PROMPT\n')
|
||||
|
||||
const plainBehaviorFile = join(dir, 'plain-turn', 'behavior.json')
|
||||
const plainBehavior = JSON.parse(readFileSync(plainBehaviorFile, 'utf8')) as Record<string, unknown>
|
||||
plainBehavior.echoEnv = true
|
||||
writeFileSync(plainBehaviorFile, `${JSON.stringify(plainBehavior, null, 2)}\n`)
|
||||
|
||||
writeFileSync(join(dir, 'blocked-log', 'session.jsonl'), [
|
||||
'{"type":"session","id":"99999999-8888-4777-8666-555555555555","createdAt":13,"cwd":"/rec/blocked-cwd"}',
|
||||
'{"type":"hook/result","seq":1,"time":13,"data":{"decision":"stale","durationMs":99}}',
|
||||
'',
|
||||
].join('\n'))
|
||||
writeFileSync(join(dir, 'authored-error', 'session.jsonl'), [
|
||||
'{"type":"session","id":"77777777-8888-4777-8666-555555555555","createdAt":13,"cwd":"/rec/error-cwd"}',
|
||||
'{"type":"turn/end","seq":1,"time":9,"data":{"error":"stale"}}',
|
||||
'',
|
||||
].join('\n'))
|
||||
}
|
||||
|
||||
describe('defineAcpSnapshotSuite: replay mode', () => {
|
||||
defineAcpSnapshotSuite({ agent: AGENT, snapshotsDir: REPLAY_DIR, scenarios: REPLAY_SCENARIOS, mode: 'replay' })
|
||||
})
|
||||
@@ -75,6 +113,36 @@ describe('defineAcpSnapshotSuite: record mode', () => {
|
||||
defineAcpSnapshotSuite({ agent: AGENT, snapshotsDir: recordDir, scenarios: RECORD_SCENARIOS, mode: 'record' })
|
||||
})
|
||||
|
||||
describe('defineAcpSnapshotSuite: refresh mode', () => {
|
||||
defineAcpSnapshotSuite({ agent: AGENT, snapshotsDir: refreshDir, scenarios: REPLAY_SCENARIOS, mode: 'refresh' })
|
||||
})
|
||||
|
||||
describe('defineAcpSnapshotSuite: refresh write-back', () => {
|
||||
it('rewrites stdout and comparable logs from a replay-mode child run', () => {
|
||||
const stdout = readFileSync(join(refreshDir, 'plain-turn', 'stdout.golden.jsonl'), 'utf8')
|
||||
expect(stdout).not.toContain('stale stdout')
|
||||
expect(stdout).toContain('env:{\\"mode\\":\\"replay\\"')
|
||||
expect(stdout).not.toContain('\\"mode\\":\\"refresh\\"')
|
||||
|
||||
const blocked = readFileSync(join(refreshDir, 'blocked-log', 'session.jsonl'), 'utf8')
|
||||
expect(blocked).toContain('"decision":"block"')
|
||||
expect(blocked).not.toContain('"decision":"stale"')
|
||||
|
||||
const authored = readFileSync(join(refreshDir, 'authored-error', 'session.jsonl'), 'utf8')
|
||||
expect(authored).toContain('"error":"model exploded"')
|
||||
expect(authored).not.toContain('"error":"stale"')
|
||||
|
||||
expect(readFileSync(join(refreshDir, 'pin-turn', 'system-prompt.golden.md'), 'utf8')).toBe([
|
||||
'SYS PROMPT',
|
||||
'',
|
||||
'<!-- request/header-delta 1: keepStart=1, keepEnd=0 -->',
|
||||
'',
|
||||
'NEW PROMPT LINE',
|
||||
'',
|
||||
].join('\n'))
|
||||
})
|
||||
})
|
||||
|
||||
describe('defineAcpSnapshotSuite: registration contract', () => {
|
||||
it("throws when a scenario's header class has no pinning scenario", () => {
|
||||
expect(() => {
|
||||
@@ -167,6 +235,69 @@ describe('normalizedHeaders', () => {
|
||||
})
|
||||
})
|
||||
|
||||
describe('normalizedSystemPrompts', () => {
|
||||
it('extracts normalized string prompts and omits absent or non-string fields', () => {
|
||||
const log = [
|
||||
'{"type":"session","id":"a","createdAt":5,"cwd":"/w"}',
|
||||
'{"type":"request/header","seq":0,"time":9,"data":{"header":{"system":"work in /w"}}}',
|
||||
'{"type":"request/header","seq":1,"time":9,"data":{"header":{}}}',
|
||||
'{"type":"request/header","seq":2,"time":9,"data":{"header":{"system":null}}}',
|
||||
'{"type":"request/header","seq":3,"time":9,"data":{"header":null}}',
|
||||
'{"type":"request/header","seq":4,"time":9,"data":{"header":"invalid"}}',
|
||||
'',
|
||||
].join('\n')
|
||||
expect(normalizedSystemPrompts(log, { sessionIds: [], cwd: '/w' })).toEqual(['work in {{cwd}}'])
|
||||
})
|
||||
})
|
||||
|
||||
describe('normalizedSystemPromptDeltas', () => {
|
||||
it('extracts and normalizes well-formed system edits', () => {
|
||||
const log = [
|
||||
'{"type":"request/header-delta","data":{"system":{"keepStart":1,"keepEnd":0,"insert":["work in /w"]}}}',
|
||||
'{"type":"request/header-delta","data":{"tools":{"replace":[]}}}',
|
||||
'{"type":"request/header-delta","data":{"system":{"keepStart":"1","keepEnd":0,"insert":[]}}}',
|
||||
'{"type":"request/header-delta","data":{"system":{"keepStart":1,"keepEnd":0,"insert":[null]}}}',
|
||||
'',
|
||||
].join('\n')
|
||||
expect(normalizedSystemPromptDeltas(log, { sessionIds: [], cwd: '/w' })).toEqual([
|
||||
{ keepStart: 1, keepEnd: 0, insert: ['work in {{cwd}}'] },
|
||||
])
|
||||
})
|
||||
})
|
||||
|
||||
describe('formatSystemPromptSnapshot', () => {
|
||||
it('renders further header snapshots as their own sections, before delta sections', () => {
|
||||
// One further snapshot already newline-terminated, one not — both endings.
|
||||
expect(formatSystemPromptSnapshot('base\n', [], ['already terminated\n']))
|
||||
.toBe('base\n\n<!-- request/header 2 (snapshot) -->\n\nalready terminated\n')
|
||||
const out = formatSystemPromptSnapshot('base prompt', [{ keepStart: 1, keepEnd: 0, insert: ['edited'] }], ['widened prompt'])
|
||||
expect(out).toBe(
|
||||
'base prompt\n'
|
||||
+ '\n<!-- request/header 2 (snapshot) -->\n\n'
|
||||
+ 'widened prompt\n'
|
||||
+ '\n<!-- request/header-delta 1: keepStart=1, keepEnd=0 -->\n\n'
|
||||
+ 'edited\n',
|
||||
)
|
||||
})
|
||||
|
||||
it('adds a missing terminal newline without changing an existing one', () => {
|
||||
expect(formatSystemPromptSnapshot('prompt')).toBe('prompt\n')
|
||||
expect(formatSystemPromptSnapshot('prompt\n')).toBe('prompt\n')
|
||||
})
|
||||
|
||||
it('renders readable system-prompt delta sections', () => {
|
||||
expect(formatSystemPromptSnapshot('prompt', [
|
||||
{ keepStart: 1, keepEnd: 0, insert: ['new', 'lines'] },
|
||||
])).toBe('prompt\n\n<!-- request/header-delta 1: keepStart=1, keepEnd=0 -->\n\nnew\nlines\n')
|
||||
})
|
||||
|
||||
it('does not double the newline of a delta insert with a trailing blank line', () => {
|
||||
expect(formatSystemPromptSnapshot('prompt\n', [
|
||||
{ keepStart: 2, keepEnd: 1, insert: ['tail', ''] },
|
||||
])).toBe('prompt\n\n<!-- request/header-delta 1: keepStart=2, keepEnd=1 -->\n\ntail\n')
|
||||
})
|
||||
})
|
||||
|
||||
describe('headerDeltaCount', () => {
|
||||
it('counts request/header-delta events, ignoring blanks and other lines', () => {
|
||||
const delta = JSON.stringify({ type: 'request/header-delta', seq: 2, time: 9, data: {} })
|
||||
@@ -175,3 +306,56 @@ describe('headerDeltaCount', () => {
|
||||
expect(headerDeltaCount(`${other}\n`)).toBe(0)
|
||||
})
|
||||
})
|
||||
|
||||
describe('refreshFixtureReplacements', () => {
|
||||
it('maps fresh ids and cwd values to the existing fixture values, skipping non-replacements', () => {
|
||||
const log = (content: string): HarvestedLog => ({ id: 'diagnostic', createdAt: 1, content })
|
||||
const logs = [
|
||||
log('{"type":"session","id":"","cwd":"/same"}\n'),
|
||||
log('{"type":"session","id":"new-parent","cwd":"/new"}\n'),
|
||||
log('{"type":"session","id":"new-child","cwd":"/new"}\n'),
|
||||
]
|
||||
const fixtures = [
|
||||
'{"type":"session","id":"","cwd":"/same"}\n',
|
||||
'{"type":"session","id":"old-parent","cwd":"/old"}\n',
|
||||
]
|
||||
expect(refreshFixtureReplacements(logs, fixtures)).toEqual([
|
||||
{ from: 'new-parent', to: 'old-parent' },
|
||||
{ from: '/new', to: '/old' },
|
||||
])
|
||||
})
|
||||
})
|
||||
|
||||
describe('stabilizeRefreshLog', () => {
|
||||
it('keeps volatile fixture fields while preserving fresh meaningful payloads', () => {
|
||||
const fresh = [
|
||||
'{"type":"session","id":"new-child","createdAt":200,"cwd":"/new","parentSession":"new-parent","seedLength":1}',
|
||||
'{"type":"hook/result","seq":1,"time":22,"data":{"decision":"block","durationMs":37}}',
|
||||
'{"type":"turn/end","seq":2,"time":33,"data":{"error":"fresh error"}}',
|
||||
'{"type":"tool/result","seq":3,"time":44,"data":{"text":"new-parent in /new"}}',
|
||||
'{"type":"hook/result","seq":4,"time":55,"data":{"decision":"allow","durationMs":5}}',
|
||||
'',
|
||||
].join('\n')
|
||||
const existing = [
|
||||
'{"type":"session","id":"old-child","createdAt":100,"cwd":"/old","parentSession":"old-parent","seedLength":5}',
|
||||
'{"type":"hook/result","seq":1,"time":11,"data":{"decision":"stale","durationMs":99}}',
|
||||
'{"type":"turn/end","seq":2,"data":{"error":"stale"}}',
|
||||
'{"type":"assistant/message","seq":3,"time":12,"data":{"text":"different type"}}',
|
||||
'{"type":"hook/result","seq":4,"time":13,"data":{"decision":"stale"}}',
|
||||
'',
|
||||
].join('\n')
|
||||
|
||||
expect(stabilizeRefreshLog(fresh, existing, [
|
||||
{ from: 'new-parent', to: 'old-parent' },
|
||||
{ from: 'new-child', to: 'old-child' },
|
||||
{ from: '/new', to: '/old' },
|
||||
])).toBe([
|
||||
'{"type":"session","id":"old-child","createdAt":100,"cwd":"/old","parentSession":"old-parent","seedLength":1}',
|
||||
'{"type":"hook/result","seq":1,"time":11,"data":{"decision":"block","durationMs":99}}',
|
||||
'{"type":"turn/end","seq":2,"time":33,"data":{"error":"fresh error"}}',
|
||||
'{"type":"tool/result","seq":3,"time":44,"data":{"text":"old-parent in /old"}}',
|
||||
'{"type":"hook/result","seq":4,"time":13,"data":{"decision":"allow","durationMs":5}}',
|
||||
'',
|
||||
].join('\n'))
|
||||
})
|
||||
})
|
||||
|
||||
Reference in New Issue
Block a user