test(acp): snapshot system prompts as Markdown

This commit is contained in:
Tianyi Cui
2026-07-11 22:24:20 +08:00
parent ee3e4ea8f9
commit 9339622d3b
20 changed files with 543 additions and 135 deletions

View File

@@ -3,7 +3,7 @@
* tier (`pnpm run test:snapshot`). Three layers, composable per example:
* the subprocess scenario harness ({@link runScenario}), the pure golden
* normalizers ({@link normalizeStdout} / {@link normalizeSessionLog} /
* {@link scrubRequestHeaders}), and the suite factory
* {@link scrubRequestHeaders} / {@link scrubSystemPrompts}), and the suite factory
* ({@link defineAcpSnapshotSuite}) that registers a scenario table as a full
* describe/it tree. An example's `*.snapshot.ts` supplies only its
* {@link AgentUnderTest} paths, its snapshots directory, and its
@@ -29,6 +29,7 @@ export {
normalizeSessionLog,
normalizeStdout,
scrubRequestHeaders,
scrubSystemPrompts,
type NormalizeContext,
} from './normalize.ts'
export {

View File

@@ -12,14 +12,14 @@
* `durationMs` (wall-clock hook runtime) → 0. NOT scrubbed: the log's `seq`
* (deterministic — `seq = log.length`, part of the event-log contract).
*
* A separate, composable normalizer — {@link scrubRequestHeaders} — replaces
* the bulky request-header CONTENT (the composed system prompt, the tool
* schema list, and the session prefix) with
* `{{system}}`/`{{tools}}`/`{{messagePrefix}}` tokens. It is deliberately NOT
* folded into {@link normalizeSessionLog}: each suite's one header-pinning
* scenario compares that content verbatim, every other scenario composes the
* scrub in (the `pinsHeader` flag on the scenario table, consumed by the suite
* factory in ./suite.ts; see the pinned-header RFC,
* Separate, composable normalizers keep bulky request-header content out of
* session fixtures. {@link scrubSystemPrompts} replaces the composed system
* prompt in EVERY fixture; {@link scrubRequestHeaders} additionally replaces
* tool schemas and the session prefix outside each suite's header-pinning
* scenario. They are deliberately NOT folded into
* {@link normalizeSessionLog}: the suite factory composes the right scrub for
* each scenario and snapshots the pin's actual prompt as Markdown (see the
* pinned-header RFC,
* docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md).
*
* See docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md.
@@ -135,37 +135,37 @@ export function normalizeSessionLog(rawLog: string, ctx: NormalizeContext): stri
}
/**
* Replace request-header CONTENT in a session JSONL with stable tokens,
* keeping its structure: a `request/header` event's `data.header.system` →
* `{{system}}`, `data.header.tools` → `{{tools}}`, and
* `data.header.messagePrefix` → one `{{messagePrefix}}` token per message
* (the session prefix is model-visible bulk — an AGENTS digest, a skills
* catalog — so its COUNT stays a structural fact while its text never lands
* in a fixture); a
* `request/header-delta` event keeps every structural fact — the system
* delta's `keepStart`/`keepEnd` line positions and inserted-line COUNT (one
* `{{system}}` token per inserted line), the tools delta's
* added/removed/changed tool NAMES, the prefix replacement's message COUNT —
* and tokenizes only the bulk (prompt
* text; each added/changed schema's fields other than `name` → `{{tools}}`;
* each replacement prefix message → `{{messagePrefix}}`),
* so two different deltas still compare different.
* Absent fields stay absent — WHETHER a header carried a system prompt,
* tools, or a prefix is behavior and stays visible; `config` and `reason`
* are small and
* stable, so they stay verbatim (a model swap churns every fixture by design
* — it invalidates the recorded responses; a prompt/schema edit churns none —
* replay never reads this content, see dsh-llm-replay).
*
* Only lines with something to scrub are re-serialized; every other line
* passes through byte-for-byte, so the transform is idempotent and applying
* it to an already-scrubbed fixture is a no-op — the on-disk-fixtures guard
* in ./suite.ts relies on exactly that.
* Replace system-prompt content in request headers and header deltas with
* `{{system}}` tokens while retaining field presence and delta structure.
* Other header content stays verbatim, so a header-pinning fixture can keep
* its complete tool schemas while every JSONL fixture omits the prompt text.
* Lines without a system payload pass through byte-for-byte; the transform is
* idempotent.
*
* @param rawLog The raw session `.jsonl` content.
* @returns The JSONL with header content tokenized, other lines byte-identical.
* @returns The JSONL with system-prompt content tokenized.
*/
export function scrubSystemPrompts(rawLog: string): string {
return scrubHeaderContent(rawLog, false)
}
/**
* Replace all bulky request-header content in a session JSONL with stable
* tokens. This includes the system-prompt fields handled by
* {@link scrubSystemPrompts}, tool schemas, and session-prefix messages. It
* keeps system-delta line positions and arity, tool-delta names, prefix
* message counts, field presence, config, and reason. Lines without content
* to scrub pass through byte-for-byte, and the transform is idempotent.
*
* @param rawLog The raw session `.jsonl` content.
* @returns The JSONL with all header bulk tokenized, other lines byte-identical.
*/
export function scrubRequestHeaders(rawLog: string): string {
return scrubHeaderContent(rawLog, true)
}
/** Transform header content, optionally including tool schemas and the session prefix. */
function scrubHeaderContent(rawLog: string, scrubToolsAndPrefix: boolean): string {
const lines = rawLog.split('\n')
const out = lines.map((line) => {
if (line.trim().length === 0) return line
@@ -175,11 +175,14 @@ export function scrubRequestHeaders(rawLog: string): string {
if (record.type === 'request/header') {
const header = data.header as Record<string, unknown> | null | undefined
if (header === null || typeof header !== 'object') return line
if (!('system' in header) && !('tools' in header) && !('messagePrefix' in header)) return line
if ('system' in header) header.system = SYSTEM
if ('tools' in header) header.tools = TOOLS
if (Array.isArray(header.messagePrefix)) header.messagePrefix = header.messagePrefix.map(() => MESSAGE_PREFIX)
return JSON.stringify(record)
let touched = false
if ('system' in header) { header.system = SYSTEM; touched = true }
if (scrubToolsAndPrefix && 'tools' in header) { header.tools = TOOLS; touched = true }
if (scrubToolsAndPrefix && Array.isArray(header.messagePrefix)) {
header.messagePrefix = header.messagePrefix.map(() => MESSAGE_PREFIX)
touched = true
}
return touched ? JSON.stringify(record) : line
}
if (record.type === 'request/header-delta') {
let touched = false
@@ -189,11 +192,11 @@ export function scrubRequestHeaders(rawLog: string): string {
touched = true
}
const tools = data.tools as Record<string, unknown> | null | undefined
if (tools !== null && typeof tools === 'object') {
if (scrubToolsAndPrefix && tools !== null && typeof tools === 'object') {
if (Array.isArray(tools.added)) { tools.added = tools.added.map(scrubToolSchema); touched = true }
if (Array.isArray(tools.changed)) { tools.changed = tools.changed.map(scrubToolSchema); touched = true }
}
if (Array.isArray(data.messagePrefix)) {
if (scrubToolsAndPrefix && Array.isArray(data.messagePrefix)) {
data.messagePrefix = data.messagePrefix.map(() => MESSAGE_PREFIX)
touched = true
}

View File

@@ -10,15 +10,14 @@
* (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 HEADER CLASS
* — scenarios that boot the same config compose the same header; each class's
* `pinsHeader` scenario commits it verbatim — and scrubbed to
* `{{system}}`/`{{tools}}` tokens in every other fixture and compare, so a
* prompt or tool-schema edit churns one committed line per class instead of
* every fixture. A per-run uniformity guard keeps each pin sound: every live
* header must equal its class's pinned one, and no header-delta may appear
* outside a pinning scenario (see the pinned-header RFC,
* 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
@@ -37,7 +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 {
@@ -81,14 +89,13 @@ 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 HEADER CLASS ({@link headerClass}) pins it; every other
* scenario of that class 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 per class, not one per scenario. One pin per class suffices because
* 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
@@ -124,7 +131,7 @@ 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), `record` (live API; re-records the
@@ -192,6 +199,35 @@ 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] : []
})
}
/**
* 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.
* @returns Markdown snapshot text ending in a newline.
*/
export function formatSystemPromptSnapshot(prompt: string): string {
return prompt.endsWith('\n') ? prompt : `${prompt}\n`
}
/**
* Count the `request/header-delta` events in a session JSONL.
*
@@ -289,7 +325,8 @@ export function stabilizeRefreshLog(fresh: string, existing: string, replacement
* Register the suite: one `describe` per scenario (the golden/log compares and
* the header-uniformity guard) plus the fixture guard block (no orphan
* scenario dirs, required files present, exactly one pin per header class,
* pinning fixtures well-formed, non-pinning fixtures header-scrubbed). Must
* pinning fixtures well-formed, every JSONL prompt-scrubbed, non-pinning
* fixtures fully header-scrubbed). Must
* run at vitest collection time — it calls `describe`/`it`. Throws
* immediately if any header class lacks a pinning scenario or carries two
* (the uniformity guard needs exactly one comparison anchor per class).
@@ -364,11 +401,12 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
// keyless replay run for every comparable log, including authored
// scenarios that live record deliberately skips. The primary goes to
// session.jsonl, each child to session.<n>.jsonl in harvest order. A
// non-pinning scenario's fixtures are written header-scrubbed, so a
// re-record/refresh can never smuggle the full prompt/schema content
// back into every fixture.
// Every fixture is written with its system prompt scrubbed. A pinning
// scenario keeps the remaining header content (notably tool schemas);
// every other scenario scrubs that bulk too. Record/refresh therefore
// cannot smuggle prompt text back into JSONL or duplicate schemas.
const scrub = scenario.pinsHeader === true
? (log: string): string => log
? scrubSystemPrompts
: scrubRequestHeaders
const fixtureFiles = ['session.jsonl', ...Array.from({ length: childSessions }, (_, i) => `session.${i + 1}.jsonl`)]
const existingFixtures = REFRESHING
@@ -391,6 +429,16 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
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 snapshot = formatSystemPromptSnapshot(prompts[0] as string)
for (const prompt of prompts) {
expect(formatSystemPromptSnapshot(prompt), 'the pinning run produced divergent system prompts')
.toEqual(snapshot)
}
await writeFile(join(dir, SYSTEM_PROMPT_SNAPSHOT), snapshot)
}
}
const stdout = normalizeStdout(result.rawStdout, ctx)
@@ -406,12 +454,10 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
// 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)
for (let i = 0; i < fixtureFiles.length; i++) {
const harvested = scrub((result.sessionLogs[i] as HarvestedLog).content)
@@ -421,34 +467,30 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
}
}
// Header-uniformity guard: a class's single pin is sound only while
// every session in that class 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 CLASS's 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 and
// class).
if (scenario.pinsHeader !== true) {
/* 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 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 (${pinningScenario.name}) header`)
.toEqual(pinned[0])
}
// Header-uniformity guard: every live header in a class must equal the
// class pin split across its JSONL header (system token + real tools)
// and readable Markdown prompt. No header delta is representable by
// those two static artifacts, so any delta fails loud.
/* v8 ignore next -- construction guarantees the pin exists; a miss would fail the one-header assertion loudly. */
const pinningScenario = pinningByClass.get(classOf(scenario)) ?? scenario
const pinningDir = join(snapshotsDir, pinningScenario.name)
const pinnedFixture = await readFile(join(pinningDir, 'session.jsonl'), 'utf8')
const pinned = normalizedHeaders(pinnedFixture, fixtureContext(pinnedFixture))
const promptSnapshot = await readFile(join(pinningDir, SYSTEM_PROMPT_SNAPSHOT), 'utf8')
expect(pinned.length, `the pinning fixture (${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 is not represented by the class pin`)
.toBe(0)
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 ${log.id}: system prompt #${k + 1} diverged from ${pinningScenario.name}/${SYSTEM_PROMPT_SNAPSHOT}`)
.toEqual(promptSnapshot)
}
}
})
@@ -479,13 +521,15 @@ 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)) {
@@ -511,7 +555,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
}
})
it('every pinning fixture carries exactly one request/header and no deltas', async () => {
it('every pinning fixture carries exactly one request/header, one readable prompt, and no 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 a mid-run header-delta —
@@ -520,19 +564,18 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
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 no request/header-delta`).toBe(0)
}
})
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 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 = [
@@ -541,8 +584,10 @@ 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`)