Merge remote-tracking branch 'origin/master' into jsonl-packed-chunk-rows

Conflicts: the four generated catalog docs (regenerated over merged sources),
session index.ts exports (keep chunk-rows exports + master's SessionSurface
re-export), stdio/acp demo config schema and persistence wiring (thread
packChunks through master's DEFAULT_PERSISTENCE_ROOT/UI shape), stdio README
config table, and the jsonl spec import line. The packed-chunk fixture also
gains the provenance field master made required on assistant/message.
This commit is contained in:
kingwl
2026-07-20 15:24:58 +08:00
1331 changed files with 74129 additions and 16289 deletions

View File

@@ -14,6 +14,16 @@ const MESSAGE_PREFIX = '{{messagePrefix}}'
/** A UUID v4 string, the shape `randomUUID()` produces for session ids. */
const UUID_RE = /[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}/gi
const LOCAL_SPILL_PATH_RE = new RegExp(
String.raw`\{\{cwd\}\}/\.spill/session-[0-9a-f]{12}/[0-9a-f]{12}-([A-Za-z0-9._~-]+?)`
+ String.raw`(?=\. Use read with offset/limit|[\s)]|$)`,
'g',
)
const SNAPSHOT_SPILL_PATH_RE = new RegExp(
String.raw`/tmp/dsh-acp-snapshot-spill/session-[0-9a-f]{12}/[0-9a-f]{12}-([A-Za-z0-9._~-]+?)`
+ String.raw`(?=\. Use read with offset/limit|[\s)]|$)`,
'g',
)
/** Inputs the normalizers need to recognize a run's volatile values. */
export interface NormalizeContext {
@@ -29,6 +39,9 @@ function scrubString(value: string, ctx: NormalizeContext): string {
// cwd first (longest, most specific), then explicit session ids, then any
// residual UUID (covers ids that appear in places we didn't enumerate).
out = out.split(ctx.cwd).join(CWD)
out = out.split(`/private${CWD}`).join(CWD)
out = out.replace(LOCAL_SPILL_PATH_RE, (_match, name: string) => `{{spillLocator:${name}}}`)
out = out.replace(SNAPSHOT_SPILL_PATH_RE, (_match, name: string) => `{{spillLocator:${name}}}`)
for (const id of ctx.sessionIds) out = out.split(id).join(SESSION_ID)
out = out.replace(UUID_RE, SESSION_ID)
return out
@@ -47,7 +60,7 @@ function scrubValue(value: unknown, ctx: NormalizeContext): unknown {
}
/**
* Normalize a raw stdout transcript (newline-delimited JSON-RPC frames) into a stable golden
* Normalize a raw stdout transcript (newline-delimited JSON-RPC frames) into a stable expected output
* in the same shape as the wire: one compact JSON frame per line (NDJSON), with the JSON-RPC
* `id` rewritten to a per-transcript sequence (1, 2, 3, …) and all volatile strings scrubbed.
* Invalid JSON throws, doubling as a protocol-stdout purity check.
@@ -59,7 +72,7 @@ function scrubValue(value: unknown, ctx: NormalizeContext): unknown {
export function normalizeStdout(rawStdout: string, ctx: NormalizeContext): string {
const lines = rawStdout.split('\n').filter(line => line.trim().length > 0)
// Map each distinct JSON-RPC id (request/response correlate by id) to a stable
// sequence number, in first-seen order, so id churn doesn't perturb the golden.
// sequence number, in first-seen order, so id churn doesn't perturb the expected output.
const idSeq = new Map<string, number>()
const stableId = (id: unknown): number => {
const key = JSON.stringify(id)
@@ -78,7 +91,7 @@ export function normalizeStdout(rawStdout: string, ctx: NormalizeContext): strin
}
/**
* Normalize a session JSONL log into a stable golden: the header line's
* Normalize a session JSONL log into a stable expected output: the header line's
* volatile fields (`createdAt`, `id`, `cwd`) and every event's `time` are
* zeroed/scrubbed, all volatile strings scrubbed, and `seq` is LEFT INTACT
* (deterministic by contract). A packed chunk row's timing (`time0`, the `dt`
@@ -108,7 +121,7 @@ export function normalizeSessionLog(rawLog: string, ctx: NormalizeContext): stri
// Event line: zero the epoch-ms timestamp; keep seq (deterministic).
record.time = 0
// A hook/result carries the hook's wall-clock runtime (`data.durationMs`),
// which is run-to-run noise like `time` — zero it so the golden reflects
// which is run-to-run noise like `time` — zero it so the expected output reflects
// the hook's decision/exit, not how long the shell took.
if (record.type === 'hook/result' && record.data !== null && typeof record.data === 'object') {
const data = record.data as Record<string, unknown>
@@ -121,8 +134,8 @@ export function normalizeSessionLog(rawLog: string, ctx: NormalizeContext): stri
}
/**
* Replace system-prompt content in request headers and header deltas with
* `{{system}}` tokens while retaining field presence and delta structure.
* Replace system-prompt content in request headers with `{{system}}` tokens
* while retaining field presence.
* 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
@@ -136,11 +149,11 @@ export function scrubSystemPrompts(rawLog: string): string {
}
/**
* Replace tool schemas in request headers and header deltas with `{{tools}}`
* tokens while retaining field presence, tool names, and delta structure.
* System prompts and session-prefix messages stay verbatim so pinning fixtures
* can move only schema bulk into their dedicated JSON sidecar. Lines without a
* tool payload pass through byte-for-byte; the transform is idempotent.
* Replace tool schemas in full request-header snapshots with `{{tools}}`
* tokens while retaining field presence. System prompts and session-prefix
* messages stay verbatim so pinning fixtures can move only schema bulk into
* their dedicated JSON sidecar. Lines without a tool payload pass through
* byte-for-byte; the transform is idempotent.
*
* @param rawLog The raw session `.jsonl` content.
* @returns The JSONL with tool-schema content tokenized.
@@ -153,9 +166,9 @@ export function scrubToolSchemas(rawLog: string): string {
* 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.
* keeps 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.
@@ -191,33 +204,7 @@ function scrubHeaderContent(rawLog: string, options: HeaderScrubOptions): string
}
return touched ? JSON.stringify(record) : line
}
if (record.type === 'request/header-delta') {
let touched = false
const system = data.system as Record<string, unknown> | null | undefined
if (options.system === true && system !== null && typeof system === 'object' && Array.isArray(system.insert)) {
system.insert = system.insert.map(() => SYSTEM)
touched = true
}
const tools = data.tools as Record<string, unknown> | null | undefined
if (options.tools === true && 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 (options.prefix === true && Array.isArray(data.messagePrefix)) {
data.messagePrefix = data.messagePrefix.map(() => MESSAGE_PREFIX)
touched = true
}
return touched ? JSON.stringify(record) : line
}
return line
})
return out.join('\n')
}
/** Tokenize one tool schema's bulk (description, parameters, anything else), keeping its identifying `name`. */
function scrubToolSchema(tool: unknown): unknown {
if (tool === null || typeof tool !== 'object' || Array.isArray(tool)) return tool
const out: Record<string, unknown> = {}
for (const [k, v] of Object.entries(tool)) out[k] = k === 'name' ? v : TOOLS
return out
}