|
|
|
@@ -10,20 +10,23 @@
|
|
|
|
|
* (recorded scenarios) and the expected produced log (both sides normalized
|
|
|
|
|
* before comparing).
|
|
|
|
|
*
|
|
|
|
|
* Request-header content (the composed system prompt + tool schemas riding on
|
|
|
|
|
* `request/header` events) is pinned by exactly ONE scenario per suite — the
|
|
|
|
|
* one with `pinsHeader` — and scrubbed to `{{system}}`/`{{tools}}` tokens in
|
|
|
|
|
* every other fixture and compare, so a prompt or tool-schema edit churns one
|
|
|
|
|
* committed line instead of every fixture. A per-run uniformity guard keeps
|
|
|
|
|
* the single pin sound: every live header must equal the pinned one, and no
|
|
|
|
|
* header-delta may appear outside the pinning scenario (see the
|
|
|
|
|
* Request-header content is pinned by exactly ONE scenario per HEADER CLASS —
|
|
|
|
|
* scenarios that boot the same config compose the same header. Every JSONL
|
|
|
|
|
* fixture scrubs the system prompt to `{{system}}`; each class's pinning
|
|
|
|
|
* scenario stores the readable prompt in `system-prompt.golden.md` and keeps its full
|
|
|
|
|
* tool schemas in `session.jsonl`, while every other fixture also scrubs tools
|
|
|
|
|
* to `{{tools}}`. A per-run uniformity guard compares both artifacts against
|
|
|
|
|
* every live header and forbids unrepresented header deltas (see the
|
|
|
|
|
* pinned-header RFC,
|
|
|
|
|
* docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md).
|
|
|
|
|
*
|
|
|
|
|
* `pnpm run test:snapshot:record` (DSH_SNAPSHOT=record + -u) re-records the
|
|
|
|
|
* `session.jsonl` fixtures against the real API and refreshes the stdout golden
|
|
|
|
|
* in one pass; the caller resolves that env into {@link SnapshotSuiteOptions}
|
|
|
|
|
* (env reading stays at the suite edge, not in this library).
|
|
|
|
|
* in one pass. `pnpm run test:snapshot:refresh` (DSH_SNAPSHOT=refresh) instead
|
|
|
|
|
* replays the committed model scripts keylessly and writes the current stdout
|
|
|
|
|
* + persisted-log goldens back without calling a live LLM. The caller resolves
|
|
|
|
|
* that env into {@link SnapshotSuiteOptions} (env reading stays at the suite
|
|
|
|
|
* edge, not in this library).
|
|
|
|
|
*
|
|
|
|
|
* @module @deepseek-ai/dsh-acp-snapshot/suite
|
|
|
|
|
*/
|
|
|
|
@@ -33,7 +36,16 @@ import { existsSync } from 'node:fs'
|
|
|
|
|
import { join } from 'node:path'
|
|
|
|
|
import { describe, expect, it } from 'vitest'
|
|
|
|
|
import { type AgentUnderTest, type HarvestedLog, type InputScript, runScenario } from './harness.ts'
|
|
|
|
|
import { type NormalizeContext, normalizeSessionLog, normalizeStdout, scrubRequestHeaders } from './normalize.ts'
|
|
|
|
|
import {
|
|
|
|
|
type NormalizeContext,
|
|
|
|
|
normalizeSessionLog,
|
|
|
|
|
normalizeStdout,
|
|
|
|
|
scrubRequestHeaders,
|
|
|
|
|
scrubSystemPrompts,
|
|
|
|
|
} from './normalize.ts'
|
|
|
|
|
|
|
|
|
|
/** The readable system-prompt snapshot beside each header-pinning fixture. */
|
|
|
|
|
const SYSTEM_PROMPT_SNAPSHOT = 'system-prompt.golden.md'
|
|
|
|
|
|
|
|
|
|
/** A snapshot scenario and how its fixtures are produced. */
|
|
|
|
|
export interface Scenario {
|
|
|
|
@@ -77,21 +89,49 @@ export interface Scenario {
|
|
|
|
|
*/
|
|
|
|
|
childSessions?: number
|
|
|
|
|
/**
|
|
|
|
|
* Whether THIS scenario's fixtures keep the full request-header content (the
|
|
|
|
|
* composed system prompt and tool schema list on `request/header` /
|
|
|
|
|
* `request/header-delta` events) and compare it verbatim. Exactly one
|
|
|
|
|
* scenario per suite pins it; every other scenario stores and compares that
|
|
|
|
|
* content as `{{system}}`/`{{tools}}` tokens ({@link scrubRequestHeaders}),
|
|
|
|
|
* so a system prompt or tool-schema change shows up as ONE committed-fixture
|
|
|
|
|
* diff, not one per scenario. One pin suffices because header composition is
|
|
|
|
|
* suite-uniform (parent, spawn child, and fork child all compose the same
|
|
|
|
|
* prompt-modulo-cwd and the same tools) — and that premise is ASSERTED, not
|
|
|
|
|
* assumed: every non-pinning run's live headers must equal the pinned
|
|
|
|
|
* fixture's (normalized), so a session-dependent header (say, a restricted
|
|
|
|
|
* subagent toolset) fails loud until it gets its own pinning scenario.
|
|
|
|
|
* Whether THIS scenario pins its header class's model-facing request-header
|
|
|
|
|
* content. Its actual composed prompt is maintained as a readable
|
|
|
|
|
* `system-prompt.golden.md`; its JSONL keeps full tool schemas but stores the prompt
|
|
|
|
|
* as `{{system}}`. Every other scenario of the class stores tools as
|
|
|
|
|
* `{{tools}}` too ({@link scrubRequestHeaders}). A prompt or tool-schema
|
|
|
|
|
* change therefore shows up in one focused artifact per class, not every
|
|
|
|
|
* session fixture. One pin per class suffices because
|
|
|
|
|
* header composition is class-uniform (parent, spawn child, and fork child
|
|
|
|
|
* all compose the same prompt-modulo-cwd and the same tools) — and that
|
|
|
|
|
* premise is ASSERTED, not assumed: every non-pinning run's live headers
|
|
|
|
|
* must equal its class's pinned fixture's (normalized), so a
|
|
|
|
|
* session-dependent header (say, a restricted subagent toolset) fails loud
|
|
|
|
|
* until it gets its own pinning scenario.
|
|
|
|
|
* Defaults to false.
|
|
|
|
|
*/
|
|
|
|
|
pinsHeader?: boolean
|
|
|
|
|
/**
|
|
|
|
|
* How many `request/header-delta` events this PINNING scenario's fixture
|
|
|
|
|
* legitimately carries (default 0). A recorded mid-run header change — a
|
|
|
|
|
* config-option switch rewriting a prompt section — is part of the pinned
|
|
|
|
|
* surface, with readable prompt text in Markdown; any OTHER count
|
|
|
|
|
* still fails, so fixture rot stays caught. Meaningless off the pin (the
|
|
|
|
|
* live uniformity guard keeps non-pinning scenarios delta-free).
|
|
|
|
|
*/
|
|
|
|
|
expectedHeaderDeltas?: number
|
|
|
|
|
/**
|
|
|
|
|
* Which header-composition class this scenario belongs to. Scenarios that
|
|
|
|
|
* boot the same config compose the same header; each class has exactly one
|
|
|
|
|
* {@link pinsHeader} scenario, and the uniformity guard compares every
|
|
|
|
|
* other member against ITS class's pin. Defaults to `'default'`; a
|
|
|
|
|
* scenario booting an alternate config ({@link configPath}) whose tool
|
|
|
|
|
* list or prompt sections differ by construction carries its own class.
|
|
|
|
|
*/
|
|
|
|
|
headerClass?: string
|
|
|
|
|
/**
|
|
|
|
|
* Alternate LIVE config path (absolute) this scenario boots instead of
|
|
|
|
|
* {@link AgentUnderTest.configPath} — an overlay composing a different
|
|
|
|
|
* tree (its basename must still end in `cordis.yml` so the bin's replay
|
|
|
|
|
* swap finds the sibling `*cordis.snapshot.yml`). A scenario whose
|
|
|
|
|
* overlay changes the composed header also needs its own
|
|
|
|
|
* {@link headerClass}.
|
|
|
|
|
*/
|
|
|
|
|
configPath?: string
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/** One suite's inputs: the agent to boot, where its fixtures live, and its scenario table. */
|
|
|
|
@@ -100,15 +140,16 @@ export interface SnapshotSuiteOptions {
|
|
|
|
|
agent: AgentUnderTest
|
|
|
|
|
/** Absolute path of the suite's `snapshots/` directory (one subdir per scenario). */
|
|
|
|
|
snapshotsDir: string
|
|
|
|
|
/** The scenario table; exactly one entry must set `pinsHeader`. */
|
|
|
|
|
/** The scenario table; exactly one entry per header class must set `pinsHeader`. */
|
|
|
|
|
scenarios: Scenario[]
|
|
|
|
|
/**
|
|
|
|
|
* `replay` (keyless, the default tier) or `record` (live API; re-records the
|
|
|
|
|
* `recorded` scenarios' fixtures and refreshes the vitest goldens under
|
|
|
|
|
* `--update`). The caller derives this from `$DSH_SNAPSHOT` — env reading
|
|
|
|
|
* stays outside this library.
|
|
|
|
|
* `replay` (keyless, the default tier), `record` (live API; re-records the
|
|
|
|
|
* `recorded` scenarios' fixtures and refreshes the Vitest goldens under
|
|
|
|
|
* `--update`), or `refresh` (keyless replay that rewrites stdout goldens and
|
|
|
|
|
* comparable session fixtures from the replay run). The caller derives this
|
|
|
|
|
* from `$DSH_SNAPSHOT` — env reading stays outside this library.
|
|
|
|
|
*/
|
|
|
|
|
mode: 'replay' | 'record'
|
|
|
|
|
mode: 'replay' | 'record' | 'refresh'
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
@@ -167,6 +208,86 @@ export function normalizedHeaders(rawLog: string, ctx: NormalizeContext): unknow
|
|
|
|
|
.map(record => record.data?.header)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* The normalized string-valued system prompts carried by request headers in a
|
|
|
|
|
* session JSONL, in log order. Headers without a string prompt are omitted so
|
|
|
|
|
* callers can assert one prompt per header explicitly.
|
|
|
|
|
*
|
|
|
|
|
* @param rawLog The session `.jsonl` content to inspect.
|
|
|
|
|
* @param ctx The volatile values of the run that produced it.
|
|
|
|
|
* @returns The normalized system prompts, in header order.
|
|
|
|
|
*/
|
|
|
|
|
export function normalizedSystemPrompts(rawLog: string, ctx: NormalizeContext): string[] {
|
|
|
|
|
return normalizedHeaders(rawLog, ctx).flatMap((header) => {
|
|
|
|
|
if (header === null || typeof header !== 'object') return []
|
|
|
|
|
const system = (header as { system?: unknown }).system
|
|
|
|
|
return typeof system === 'string' ? [system] : []
|
|
|
|
|
})
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/** One normalized system-prompt edit carried by a `request/header-delta`. */
|
|
|
|
|
export interface SystemPromptDeltaSnapshot {
|
|
|
|
|
/** How many leading lines remain from the prior prompt. */
|
|
|
|
|
keepStart: number
|
|
|
|
|
/** How many trailing lines remain from the prior prompt. */
|
|
|
|
|
keepEnd: number
|
|
|
|
|
/** The normalized replacement lines inserted between the retained ranges. */
|
|
|
|
|
insert: string[]
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Extract normalized system-prompt edits from request-header deltas in log
|
|
|
|
|
* order. Deltas without a well-formed system edit are omitted; their non-prompt
|
|
|
|
|
* structure remains pinned in JSONL.
|
|
|
|
|
*
|
|
|
|
|
* @param rawLog The session `.jsonl` content to inspect.
|
|
|
|
|
* @param ctx The volatile values of the run that produced it.
|
|
|
|
|
* @returns The normalized system-prompt edits, in event order.
|
|
|
|
|
*/
|
|
|
|
|
export function normalizedSystemPromptDeltas(rawLog: string, ctx: NormalizeContext): SystemPromptDeltaSnapshot[] {
|
|
|
|
|
return normalizeSessionLog(rawLog, ctx)
|
|
|
|
|
.split('\n')
|
|
|
|
|
.filter(line => line.trim().length > 0)
|
|
|
|
|
.map(line => JSON.parse(line) as { type?: unknown; data?: { system?: unknown } })
|
|
|
|
|
.filter(record => record.type === 'request/header-delta')
|
|
|
|
|
.flatMap((record) => {
|
|
|
|
|
const system = record.data?.system
|
|
|
|
|
if (system === null || typeof system !== 'object') return []
|
|
|
|
|
const { keepStart, keepEnd, insert } = system as { keepStart?: unknown; keepEnd?: unknown; insert?: unknown }
|
|
|
|
|
if (typeof keepStart !== 'number' || typeof keepEnd !== 'number' || !Array.isArray(insert)) return []
|
|
|
|
|
if (!insert.every(line => typeof line === 'string')) return []
|
|
|
|
|
return [{ keepStart, keepEnd, insert: insert }]
|
|
|
|
|
})
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Render a normalized prompt as a repository-friendly Markdown snapshot.
|
|
|
|
|
* Prompt text is unchanged except that a missing terminal newline is added so
|
|
|
|
|
* the committed file follows the repository newline contract.
|
|
|
|
|
*
|
|
|
|
|
* @param prompt The normalized system prompt.
|
|
|
|
|
* @param deltas Normalized prompt edits to append as readable sections.
|
|
|
|
|
* @returns Markdown snapshot text ending in a newline.
|
|
|
|
|
*/
|
|
|
|
|
export function formatSystemPromptSnapshot(
|
|
|
|
|
prompt: string,
|
|
|
|
|
deltas: readonly SystemPromptDeltaSnapshot[] = [],
|
|
|
|
|
): string {
|
|
|
|
|
let snapshot = prompt.endsWith('\n') ? prompt : `${prompt}\n`
|
|
|
|
|
for (const [index, delta] of deltas.entries()) {
|
|
|
|
|
snapshot += `\n<!-- request/header-delta ${index + 1}: keepStart=${delta.keepStart}, keepEnd=${delta.keepEnd} -->\n\n`
|
|
|
|
|
const insert = delta.insert.join('\n')
|
|
|
|
|
snapshot += insert.endsWith('\n') ? insert : `${insert}\n`
|
|
|
|
|
}
|
|
|
|
|
return snapshot
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/** Return the initial-prompt portion of a possibly delta-bearing snapshot. */
|
|
|
|
|
function initialSystemPromptSnapshot(snapshot: string): string {
|
|
|
|
|
const marker = snapshot.indexOf('\n<!-- request/header-delta ')
|
|
|
|
|
return marker < 0 ? snapshot : snapshot.slice(0, marker)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Count the `request/header-delta` events in a session JSONL.
|
|
|
|
|
*
|
|
|
|
@@ -180,43 +301,147 @@ export function headerDeltaCount(rawLog: string): number {
|
|
|
|
|
.length
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/** A literal string replacement used to carry an existing fixture's volatile value into a refreshed log. */
|
|
|
|
|
export interface FixtureReplacement {
|
|
|
|
|
/** The fresh replay-run value to replace. */
|
|
|
|
|
from: string
|
|
|
|
|
/** The existing fixture value to keep. */
|
|
|
|
|
to: string
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function parseJsonlRecords(text: string): Record<string, unknown>[] {
|
|
|
|
|
return text.split('\n')
|
|
|
|
|
.filter(line => line.trim().length > 0)
|
|
|
|
|
.map(line => JSON.parse(line) as Record<string, unknown>)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Build the cross-log id/cwd replacements used by refresh write-back.
|
|
|
|
|
*
|
|
|
|
|
* @param logs The freshly harvested logs, in fixture order.
|
|
|
|
|
* @param fixtures The existing fixture contents, in matching order.
|
|
|
|
|
* @returns Literal replacements from fresh volatile values to the fixture's old values.
|
|
|
|
|
*/
|
|
|
|
|
export function refreshFixtureReplacements(logs: HarvestedLog[], fixtures: string[]): FixtureReplacement[] {
|
|
|
|
|
const replacements: FixtureReplacement[] = []
|
|
|
|
|
for (let i = 0; i < logs.length; i++) {
|
|
|
|
|
const fresh = parseJsonlRecords((logs[i] as HarvestedLog).content)[0]
|
|
|
|
|
const existing = parseJsonlRecords(fixtures[i] ?? '')[0]
|
|
|
|
|
for (const field of ['id', 'cwd'] as const) {
|
|
|
|
|
const from = fresh?.[field]
|
|
|
|
|
const to = existing?.[field]
|
|
|
|
|
if (typeof from === 'string' && typeof to === 'string' && from.length > 0 && from !== to) {
|
|
|
|
|
replacements.push({ from, to })
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
return replacements
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function preserveFixtureVolatiles(record: Record<string, unknown>, existing: Record<string, unknown> | undefined): void {
|
|
|
|
|
if (existing === undefined || existing.type !== record.type) return
|
|
|
|
|
if (record.type === 'session') {
|
|
|
|
|
for (const field of ['id', 'createdAt', 'cwd', 'parentSession'] as const) {
|
|
|
|
|
if (field in record && field in existing) record[field] = existing[field]
|
|
|
|
|
}
|
|
|
|
|
return
|
|
|
|
|
}
|
|
|
|
|
if ('time' in record && 'time' in existing) record.time = existing.time
|
|
|
|
|
if (record.type !== 'hook/result') return
|
|
|
|
|
const data = record.data
|
|
|
|
|
const existingData = existing.data
|
|
|
|
|
if (
|
|
|
|
|
data !== null && typeof data === 'object'
|
|
|
|
|
&& existingData !== null && typeof existingData === 'object'
|
|
|
|
|
&& 'durationMs' in data && 'durationMs' in existingData
|
|
|
|
|
) {
|
|
|
|
|
(data as Record<string, unknown>).durationMs = (existingData as Record<string, unknown>).durationMs
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Rewrite a fresh replay-produced log so repeated refreshes do not churn
|
|
|
|
|
* volatile fixture fields. Meaningful event payloads come from `fresh`; the
|
|
|
|
|
* existing fixture lends session ids, cwd, creation times, event times, and
|
|
|
|
|
* hook durations where the record shape still matches.
|
|
|
|
|
*
|
|
|
|
|
* @param fresh The newly harvested session JSONL.
|
|
|
|
|
* @param existing The committed fixture JSONL being refreshed.
|
|
|
|
|
* @param replacements Cross-log literal replacements from {@link refreshFixtureReplacements}.
|
|
|
|
|
* @returns The stabilized JSONL content to write back.
|
|
|
|
|
*/
|
|
|
|
|
export function stabilizeRefreshLog(fresh: string, existing: string, replacements: FixtureReplacement[]): string {
|
|
|
|
|
let stable = fresh
|
|
|
|
|
for (const { from, to } of replacements) stable = stable.split(from).join(to)
|
|
|
|
|
const existingRecords = parseJsonlRecords(existing)
|
|
|
|
|
const records = parseJsonlRecords(stable)
|
|
|
|
|
for (let i = 0; i < records.length; i++) {
|
|
|
|
|
preserveFixtureVolatiles(records[i] as Record<string, unknown>, existingRecords[i])
|
|
|
|
|
}
|
|
|
|
|
return records.map(record => JSON.stringify(record)).join('\n') + '\n'
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Register the suite: one `describe` per scenario (the golden/log compares and
|
|
|
|
|
* the header-uniformity guard) plus the fixture guard block (no orphan
|
|
|
|
|
* scenario dirs, required files present, exactly one pin, non-pinning fixtures
|
|
|
|
|
* header-scrubbed). Must run at vitest collection time — it calls
|
|
|
|
|
* `describe`/`it`. Throws immediately if no scenario pins the header (the
|
|
|
|
|
* uniformity guard would have nothing to compare against).
|
|
|
|
|
* scenario dirs, required files present, exactly one pin per header class,
|
|
|
|
|
* pinning fixtures well-formed, every JSONL prompt-scrubbed, non-pinning
|
|
|
|
|
* fixtures fully header-scrubbed). Must
|
|
|
|
|
* run at vitest collection time — it calls `describe`/`it`. Throws
|
|
|
|
|
* immediately if any header class lacks a pinning scenario or carries two
|
|
|
|
|
* (the uniformity guard needs exactly one comparison anchor per class).
|
|
|
|
|
*
|
|
|
|
|
* @param options The agent, snapshots directory, scenario table, and mode.
|
|
|
|
|
*/
|
|
|
|
|
export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
|
|
|
|
|
const { agent, snapshotsDir, scenarios, mode } = options
|
|
|
|
|
const RECORDING = mode === 'record'
|
|
|
|
|
const REFRESHING = mode === 'refresh'
|
|
|
|
|
const childMode: 'replay' | 'record' = RECORDING ? 'record' : 'replay'
|
|
|
|
|
|
|
|
|
|
/** The suite's single header-pinning scenario. Guarded here (and by a meta-test) so the pin cannot silently vanish. */
|
|
|
|
|
const pinningScenario = scenarios.find(s => s.pinsHeader === true)
|
|
|
|
|
if (pinningScenario === undefined) throw new Error('acp-snapshot: no scenario pins the request-header content')
|
|
|
|
|
/** The class a scenario's header composition belongs to (see {@link Scenario.headerClass}). */
|
|
|
|
|
const classOf = (scenario: Scenario): string => scenario.headerClass ?? 'default'
|
|
|
|
|
|
|
|
|
|
/** Each header class's single pinning scenario. Guarded here (and by meta-tests) so a pin cannot silently vanish or split. */
|
|
|
|
|
const pinningByClass = new Map<string, Scenario>()
|
|
|
|
|
for (const scenario of scenarios) {
|
|
|
|
|
if (scenario.pinsHeader !== true) continue
|
|
|
|
|
const cls = classOf(scenario)
|
|
|
|
|
const existing = pinningByClass.get(cls)
|
|
|
|
|
if (existing) throw new Error(`acp-snapshot: header class "${cls}" pinned by both ${existing.name} and ${scenario.name}`)
|
|
|
|
|
pinningByClass.set(cls, scenario)
|
|
|
|
|
}
|
|
|
|
|
for (const scenario of scenarios) {
|
|
|
|
|
if (!pinningByClass.has(classOf(scenario))) {
|
|
|
|
|
throw new Error(`acp-snapshot: no scenario pins the request-header content of class "${classOf(scenario)}" (needed by ${scenario.name})`)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
for (const scenario of scenarios) {
|
|
|
|
|
describe(`snapshot: ${scenario.name}`, () => {
|
|
|
|
|
// In RECORD mode, only re-run the `recorded` (live-API) scenarios; the
|
|
|
|
|
// `authored` ones (sidecar-driven errors/cancel) are never re-recorded.
|
|
|
|
|
// REFRESH mode is replay-backed and deterministic, so it runs every
|
|
|
|
|
// scenario and rewrites the comparable fixtures from that replay run.
|
|
|
|
|
it.skipIf(RECORDING && !scenario.recorded)('matches the goldens', async () => {
|
|
|
|
|
const dir = join(snapshotsDir, scenario.name)
|
|
|
|
|
const input = JSON.parse(await readFile(join(dir, 'input.json'), 'utf8')) as InputScript
|
|
|
|
|
const overrideFile = join(dir, 'replay.override.json')
|
|
|
|
|
const workspaceDir = join(dir, 'workspace')
|
|
|
|
|
const childSessions = scenario.childSessions ?? 0
|
|
|
|
|
const comparesLog = scenario.comparesLog ?? scenario.hasModelTurn
|
|
|
|
|
const result = await runScenario(input, {
|
|
|
|
|
agent,
|
|
|
|
|
mode,
|
|
|
|
|
mode: childMode,
|
|
|
|
|
fixtureFile: join(dir, 'session.jsonl'),
|
|
|
|
|
...existsSync(overrideFile) ? { overrideFile } : {},
|
|
|
|
|
// In REPLAY, forward the recorded child fixtures so each subagent session
|
|
|
|
|
// replays from its own script. In RECORD they are harvested, not read.
|
|
|
|
|
...!RECORDING && childSessions > 0 ? { childFiles: childFixturePaths(dir, childSessions) } : {},
|
|
|
|
|
...existsSync(workspaceDir) ? { workspaceDir } : {},
|
|
|
|
|
// A scenario booting an overlay tree passes its own live config; the
|
|
|
|
|
// bin's replay swap derives the sibling `*cordis.snapshot.yml` from it.
|
|
|
|
|
...scenario.configPath !== undefined ? { configPath: scenario.configPath } : {},
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
// Scrub every volatile id the run produced: the ACP server-issued session
|
|
|
|
@@ -232,43 +457,73 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// RECORD mode (recorded model scenarios only): persist the freshly-harvested
|
|
|
|
|
// logs back to their fixtures — the primary to session.jsonl, each child to
|
|
|
|
|
// session.<n>.jsonl in harvest order. `--update` refreshes the Vitest
|
|
|
|
|
// goldens but NOT these fixtures, so write them here. A non-pinning
|
|
|
|
|
// scenario's fixtures are written header-scrubbed, so a re-record can
|
|
|
|
|
// never smuggle the full prompt/schema content back into every fixture.
|
|
|
|
|
// live logs back to their fixtures. REFRESH mode does the same from a
|
|
|
|
|
// keyless replay run for every comparable log, including authored
|
|
|
|
|
// scenarios that live record deliberately skips. The primary goes to
|
|
|
|
|
// session.jsonl, each child to session.<n>.jsonl in harvest order. A
|
|
|
|
|
// Every fixture is written with its system prompt scrubbed. A pinning
|
|
|
|
|
// scenario keeps the remaining header content (notably tool schemas);
|
|
|
|
|
// every other scenario scrubs that bulk too. Record/refresh therefore
|
|
|
|
|
// cannot smuggle prompt text back into JSONL or duplicate schemas.
|
|
|
|
|
const scrub = scenario.pinsHeader === true
|
|
|
|
|
? (log: string): string => log
|
|
|
|
|
? scrubSystemPrompts
|
|
|
|
|
: scrubRequestHeaders
|
|
|
|
|
if (RECORDING && scenario.recorded && scenario.hasModelTurn) {
|
|
|
|
|
expect(result.sessionLogs.length, 'record produced no session log to harvest').toBeGreaterThan(0)
|
|
|
|
|
const fixtureFiles = ['session.jsonl', ...Array.from({ length: childSessions }, (_, i) => `session.${i + 1}.jsonl`)]
|
|
|
|
|
const existingFixtures = REFRESHING
|
|
|
|
|
? await Promise.all(fixtureFiles.map(file => readFile(join(dir, file), 'utf8')))
|
|
|
|
|
: []
|
|
|
|
|
const replacements = REFRESHING ? refreshFixtureReplacements(result.sessionLogs, existingFixtures) : []
|
|
|
|
|
const writesSessionFixtures = (RECORDING && scenario.recorded && scenario.hasModelTurn)
|
|
|
|
|
|| (REFRESHING && comparesLog)
|
|
|
|
|
if (writesSessionFixtures) {
|
|
|
|
|
expect(result.sessionLogs.length, `${mode} produced no session log to harvest`).toBeGreaterThan(0)
|
|
|
|
|
expect(result.sessionLogs.length, `expected ${childSessions + 1} session logs (parent + children)`)
|
|
|
|
|
.toBe(childSessions + 1)
|
|
|
|
|
await writeFile(join(dir, 'session.jsonl'), scrub((result.sessionLogs[0] as HarvestedLog).content))
|
|
|
|
|
const primary = (result.sessionLogs[0] as HarvestedLog).content
|
|
|
|
|
await writeFile(join(dir, 'session.jsonl'), scrub(
|
|
|
|
|
REFRESHING ? stabilizeRefreshLog(primary, existingFixtures[0] as string, replacements) : primary,
|
|
|
|
|
))
|
|
|
|
|
for (let i = 1; i < result.sessionLogs.length; i++) {
|
|
|
|
|
await writeFile(join(dir, `session.${i}.jsonl`), scrub((result.sessionLogs[i] as HarvestedLog).content))
|
|
|
|
|
const child = (result.sessionLogs[i] as HarvestedLog).content
|
|
|
|
|
await writeFile(join(dir, `session.${i}.jsonl`), scrub(
|
|
|
|
|
REFRESHING ? stabilizeRefreshLog(child, existingFixtures[i] as string, replacements) : child,
|
|
|
|
|
))
|
|
|
|
|
}
|
|
|
|
|
if (scenario.pinsHeader === true) {
|
|
|
|
|
const prompts = result.sessionLogs.flatMap(log => normalizedSystemPrompts(log.content, ctx))
|
|
|
|
|
expect(prompts.length, `${mode} produced no system prompt to snapshot`).toBeGreaterThan(0)
|
|
|
|
|
const initialSnapshot = formatSystemPromptSnapshot(prompts[0] as string)
|
|
|
|
|
for (const prompt of prompts) {
|
|
|
|
|
expect(formatSystemPromptSnapshot(prompt), 'the pinning run produced divergent system prompts')
|
|
|
|
|
.toEqual(initialSnapshot)
|
|
|
|
|
}
|
|
|
|
|
const primary = result.sessionLogs[0] as HarvestedLog
|
|
|
|
|
const snapshot = formatSystemPromptSnapshot(
|
|
|
|
|
prompts[0] as string,
|
|
|
|
|
normalizedSystemPromptDeltas(primary.content, ctx),
|
|
|
|
|
)
|
|
|
|
|
await writeFile(join(dir, SYSTEM_PROMPT_SNAPSHOT), snapshot)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
await expect(normalizeStdout(result.rawStdout, ctx))
|
|
|
|
|
.toMatchFileSnapshot(join(dir, 'stdout.golden.jsonl'))
|
|
|
|
|
const stdout = normalizeStdout(result.rawStdout, ctx)
|
|
|
|
|
if (REFRESHING) {
|
|
|
|
|
await writeFile(join(dir, 'stdout.golden.jsonl'), stdout)
|
|
|
|
|
}
|
|
|
|
|
await expect(stdout).toMatchFileSnapshot(join(dir, 'stdout.golden.jsonl'))
|
|
|
|
|
|
|
|
|
|
// A model turn always produces a log worth comparing; a hook scenario can
|
|
|
|
|
// produce one without a model turn (a `rejected` turn carrying `hook/*`).
|
|
|
|
|
const comparesLog = scenario.comparesLog ?? scenario.hasModelTurn
|
|
|
|
|
if (comparesLog) {
|
|
|
|
|
// The harvested logs (primary-first) must match their committed fixtures
|
|
|
|
|
// 1:1. Each side passes through normalizeSessionLog, scrubbed against ITS
|
|
|
|
|
// OWN volatile values — the live run's via `ctx`, the committed fixture's
|
|
|
|
|
// via its own header (a committed file cannot share the live run's ids).
|
|
|
|
|
// Unless this scenario pins the header, both sides ALSO pass through
|
|
|
|
|
// scrubRequestHeaders: the live log carries the real prompt/schemas, the
|
|
|
|
|
// fixture carries the `{{system}}`/`{{tools}}` tokens, and the scrub is
|
|
|
|
|
// idempotent — so the compare checks the header's presence, position,
|
|
|
|
|
// reason, and config, but not its bulk content (pinned once, in the
|
|
|
|
|
// `pinsHeader` scenario).
|
|
|
|
|
// Both sides pass through the scenario's idempotent scrub: every live
|
|
|
|
|
// prompt becomes the fixture's `{{system}}`; non-pinning scenarios
|
|
|
|
|
// additionally tokenize tools/prefix. The dedicated header guard below
|
|
|
|
|
// compares those omitted values against their class's pin artifacts.
|
|
|
|
|
expect(result.sessionLogs.length, 'this scenario must persist a session log').toBe(childSessions + 1)
|
|
|
|
|
const fixtureFiles = ['session.jsonl', ...Array.from({ length: childSessions }, (_, i) => `session.${i + 1}.jsonl`)]
|
|
|
|
|
for (let i = 0; i < fixtureFiles.length; i++) {
|
|
|
|
|
const harvested = scrub((result.sessionLogs[i] as HarvestedLog).content)
|
|
|
|
|
const fixture = scrub(await readFile(join(dir, fixtureFiles[i] as string), 'utf8'))
|
|
|
|
@@ -277,31 +532,42 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Header-uniformity guard: the single pin is sound only while every
|
|
|
|
|
// session in the suite composes the SAME header and keeps it for the
|
|
|
|
|
// whole run. Assert both halves live. (1) Every request/header the run
|
|
|
|
|
// produced (parent, spawn child, fork child, initial or resume) must
|
|
|
|
|
// equal the pinned fixture's header after each side is normalized
|
|
|
|
|
// against its own volatile values. (2) No request/header-delta may
|
|
|
|
|
// appear at all — a mid-run header change diverges from the pin by
|
|
|
|
|
// construction, and its content would be invisible under the scrub. If
|
|
|
|
|
// either fails, either the header changed (update the pin: re-record or
|
|
|
|
|
// hand-edit the pinning scenario's fixture) or composition became
|
|
|
|
|
// session-dependent by design (give the divergent shape its own
|
|
|
|
|
// pinning scenario).
|
|
|
|
|
if (scenario.pinsHeader !== true) {
|
|
|
|
|
const pinnedFixture = await readFile(join(snapshotsDir, pinningScenario.name, 'session.jsonl'), 'utf8')
|
|
|
|
|
const pinned = normalizedHeaders(pinnedFixture, fixtureContext(pinnedFixture))
|
|
|
|
|
expect(pinned.length, `the pinning fixture (${pinningScenario.name}) must carry exactly one request/header`)
|
|
|
|
|
.toBe(1)
|
|
|
|
|
for (const log of result.sessionLogs) {
|
|
|
|
|
expect(headerDeltaCount(log.content), `session ${log.id}: a request/header-delta in a non-pinning scenario`)
|
|
|
|
|
.toBe(0)
|
|
|
|
|
const headers = normalizedHeaders(log.content, ctx)
|
|
|
|
|
for (const [k, header] of headers.entries()) {
|
|
|
|
|
expect(header, `session ${log.id}: request/header #${k + 1} diverged from the pinned (${pinningScenario.name}) header`)
|
|
|
|
|
.toEqual(pinned[0])
|
|
|
|
|
}
|
|
|
|
|
// Header-uniformity guard: every live header in a class must equal the
|
|
|
|
|
// class pin split across its JSONL header (system token + real tools)
|
|
|
|
|
// and readable Markdown prompt. A pinning scenario may carry its
|
|
|
|
|
// declared header deltas; their prompt edits live in the Markdown
|
|
|
|
|
// golden while JSONL retains the tokenized edit structure.
|
|
|
|
|
/* v8 ignore next -- construction guarantees the pin exists; a miss would fail the one-header assertion loudly. */
|
|
|
|
|
const pinningScenario = pinningByClass.get(classOf(scenario)) ?? scenario
|
|
|
|
|
const pinningDir = join(snapshotsDir, pinningScenario.name)
|
|
|
|
|
const pinnedFixture = await readFile(join(pinningDir, 'session.jsonl'), 'utf8')
|
|
|
|
|
const pinned = normalizedHeaders(pinnedFixture, fixtureContext(pinnedFixture))
|
|
|
|
|
const promptSnapshot = await readFile(join(pinningDir, SYSTEM_PROMPT_SNAPSHOT), 'utf8')
|
|
|
|
|
const initialPromptSnapshot = initialSystemPromptSnapshot(promptSnapshot)
|
|
|
|
|
expect(pinned.length, `the pinning fixture (${pinningScenario.name}) must carry exactly one request/header`)
|
|
|
|
|
.toBe(1)
|
|
|
|
|
for (const [logIndex, log] of result.sessionLogs.entries()) {
|
|
|
|
|
const expectedDeltas = scenario.pinsHeader === true && logIndex === 0
|
|
|
|
|
? scenario.expectedHeaderDeltas ?? 0
|
|
|
|
|
: 0
|
|
|
|
|
expect(headerDeltaCount(log.content), `session ${log.id}: request/header-delta count`)
|
|
|
|
|
.toBe(expectedDeltas)
|
|
|
|
|
const headers = normalizedHeaders(scrubSystemPrompts(log.content), ctx)
|
|
|
|
|
const prompts = normalizedSystemPrompts(log.content, ctx)
|
|
|
|
|
expect(prompts.length, `session ${log.id}: every request/header must carry a string system prompt`)
|
|
|
|
|
.toBe(headers.length)
|
|
|
|
|
for (const [k, header] of headers.entries()) {
|
|
|
|
|
expect(header, `session ${log.id}: request/header #${k + 1} diverged from the pinned (${pinningScenario.name}) header`)
|
|
|
|
|
.toEqual(pinned[0])
|
|
|
|
|
expect(formatSystemPromptSnapshot(prompts[k] as string), `session ${log.id}: initial system prompt #${k + 1} diverged from ${pinningScenario.name}/${SYSTEM_PROMPT_SNAPSHOT}`)
|
|
|
|
|
.toEqual(initialPromptSnapshot)
|
|
|
|
|
}
|
|
|
|
|
if (scenario.pinsHeader === true && logIndex === 0) {
|
|
|
|
|
expect(formatSystemPromptSnapshot(
|
|
|
|
|
prompts[0] as string,
|
|
|
|
|
normalizedSystemPromptDeltas(log.content, ctx),
|
|
|
|
|
), `session ${log.id}: system-prompt deltas diverged from ${pinningScenario.name}/${SYSTEM_PROMPT_SNAPSHOT}`)
|
|
|
|
|
.toEqual(promptSnapshot)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
})
|
|
|
|
@@ -332,13 +598,15 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
|
|
|
|
|
// `overridden` flag: required when set, forbidden when not — the harness
|
|
|
|
|
// forwards the file purely on existence, so an unregistered stray sidecar
|
|
|
|
|
// would silently replace the derived script.
|
|
|
|
|
for (const { name, overridden, childSessions } of scenarios) {
|
|
|
|
|
for (const { name, overridden, childSessions, pinsHeader } of scenarios) {
|
|
|
|
|
const dir = join(snapshotsDir, name)
|
|
|
|
|
expect(existsSync(join(dir, 'input.json')), `${name}/input.json`).toBe(true)
|
|
|
|
|
expect(existsSync(join(dir, 'stdout.golden.jsonl')), `${name}/stdout.golden.jsonl`).toBe(true)
|
|
|
|
|
expect(existsSync(join(dir, 'session.jsonl')), `${name}/session.jsonl`).toBe(true)
|
|
|
|
|
expect(existsSync(join(dir, 'replay.override.json')), `${name}/replay.override.json presence must match \`overridden\``)
|
|
|
|
|
.toBe(overridden === true)
|
|
|
|
|
expect(existsSync(join(dir, SYSTEM_PROMPT_SNAPSHOT)), `${name}/${SYSTEM_PROMPT_SNAPSHOT} presence must match \`pinsHeader\``)
|
|
|
|
|
.toBe(pinsHeader === true)
|
|
|
|
|
// A nested-agent scenario ships one child fixture per recorded subagent
|
|
|
|
|
// session (`session.1.jsonl` …), the replay source for that child session.
|
|
|
|
|
for (const childFixture of childFixturePaths(dir, childSessions ?? 0)) {
|
|
|
|
@@ -347,21 +615,46 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
|
|
|
|
|
}
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
it('exactly one scenario pins the request-header content', () => {
|
|
|
|
|
// Zero pins would drop the prompt/schema surface from the suite entirely;
|
|
|
|
|
// two would split it. One pin per suite is the design (pinned-header RFC);
|
|
|
|
|
// WHICH scenario pins is the scenario table's reviewable choice.
|
|
|
|
|
expect(scenarios.filter(s => s.pinsHeader === true).map(s => s.name)).toEqual([pinningScenario.name])
|
|
|
|
|
it('exactly one scenario pins the request-header content of each header class', () => {
|
|
|
|
|
// Zero pins would drop a class's prompt/schema surface from the suite
|
|
|
|
|
// entirely; two would split it. One pin per class is the design
|
|
|
|
|
// (pinned-header RFC); WHICH scenario pins is the scenario table's
|
|
|
|
|
// reviewable choice.
|
|
|
|
|
const pins = new Map<string, string[]>()
|
|
|
|
|
for (const scenario of scenarios.filter(s => s.pinsHeader === true)) {
|
|
|
|
|
const cls = classOf(scenario)
|
|
|
|
|
pins.set(cls, [...pins.get(cls) ?? [], scenario.name])
|
|
|
|
|
}
|
|
|
|
|
expect(Object.fromEntries([...pins].map(([cls, names]) => [cls, names.length]))).toEqual(
|
|
|
|
|
Object.fromEntries([...pinningByClass.keys()].map(cls => [cls, 1])))
|
|
|
|
|
for (const scenario of scenarios) {
|
|
|
|
|
expect(pinningByClass.has(classOf(scenario)), `class "${classOf(scenario)}" (scenario ${scenario.name}) has a pin`).toBe(true)
|
|
|
|
|
}
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
it('committed fixtures carry request-header content ONLY in the pinning scenario', async () => {
|
|
|
|
|
// The whole point of the pin: a system-prompt or tool-schema change must
|
|
|
|
|
// churn exactly one committed line. A non-pinning fixture that carries the
|
|
|
|
|
// full header (a hand-recorded file, or a header line hand-edited out of
|
|
|
|
|
// its canonical JSON form) silently reopens the suite-wide churn, so fail
|
|
|
|
|
// loud here: every non-pinning session*.jsonl must be a fixed point of
|
|
|
|
|
// scrubRequestHeaders (apply the scrub to fix a violation), and the
|
|
|
|
|
// pinning scenario's fixtures must NOT be (their content IS the pin).
|
|
|
|
|
it('every pinning fixture carries one request/header, one readable prompt, and its declared deltas', async () => {
|
|
|
|
|
// The live uniformity guard runs only in NON-pinning scenarios, so a
|
|
|
|
|
// class made of just its pinning scenario would otherwise accept a
|
|
|
|
|
// re-recorded pin with several headers or an undeclared mid-run
|
|
|
|
|
// header-delta — shapes the pin design cannot represent. Assert the
|
|
|
|
|
// committed pins directly; a scenario whose arc legitimately rewrites
|
|
|
|
|
// a prompt section declares the exact count via expectedHeaderDeltas.
|
|
|
|
|
for (const scenario of pinningByClass.values()) {
|
|
|
|
|
const fixture = await readFile(join(snapshotsDir, scenario.name, 'session.jsonl'), 'utf8')
|
|
|
|
|
const headers = normalizedHeaders(fixture, fixtureContext(fixture))
|
|
|
|
|
const promptSnapshot = await readFile(join(snapshotsDir, scenario.name, SYSTEM_PROMPT_SNAPSHOT), 'utf8')
|
|
|
|
|
expect(headers.length, `${scenario.name}: a pinning fixture must carry exactly one request/header`).toBe(1)
|
|
|
|
|
expect(promptSnapshot.length, `${scenario.name}/${SYSTEM_PROMPT_SNAPSHOT} must not be empty`).toBeGreaterThan(0)
|
|
|
|
|
expect(promptSnapshot.endsWith('\n'), `${scenario.name}/${SYSTEM_PROMPT_SNAPSHOT} must end in a newline`).toBe(true)
|
|
|
|
|
expect(headerDeltaCount(fixture), `${scenario.name}: a pinning fixture must carry exactly its declared request/header-deltas`)
|
|
|
|
|
.toBe(scenario.expectedHeaderDeltas ?? 0)
|
|
|
|
|
}
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
it('every committed JSONL omits system prompts and only pinning fixtures keep other header bulk', async () => {
|
|
|
|
|
// System prompts always live in the readable Markdown artifact. Header
|
|
|
|
|
// pins keep tool schemas/prefixes in JSONL; every other fixture tokenizes
|
|
|
|
|
// all header bulk. Fixed-point checks make both storage rules fail loud.
|
|
|
|
|
for (const scenario of scenarios) {
|
|
|
|
|
const dir = join(snapshotsDir, scenario.name)
|
|
|
|
|
const files = [
|
|
|
|
@@ -370,8 +663,10 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
|
|
|
|
|
]
|
|
|
|
|
for (const file of files) {
|
|
|
|
|
const fixture = await readFile(join(dir, file), 'utf8')
|
|
|
|
|
expect(scrubSystemPrompts(fixture), `${scenario.name}/${file} carries an unscrubbed system prompt`)
|
|
|
|
|
.toEqual(fixture)
|
|
|
|
|
if (scenario.pinsHeader === true) {
|
|
|
|
|
expect(scrubRequestHeaders(fixture), `${scenario.name}/${file} must PIN the full header content`)
|
|
|
|
|
expect(scrubRequestHeaders(fixture), `${scenario.name}/${file} must pin the non-system header content`)
|
|
|
|
|
.not.toEqual(fixture)
|
|
|
|
|
} else {
|
|
|
|
|
expect(scrubRequestHeaders(fixture), `${scenario.name}/${file} carries unscrubbed header content`)
|
|
|
|
|
Dudu-0223