refactor(session): fold the session family into packages/session/

git mv the 12 packages from session-persistence/, session-projection/,
session-title/, and telemetry/ into one session/ group per the
regrouping RFC; merge the four group READMEs into one bilingual
triplet; rewrite the group segment in tsconfig references (intra-group
references shorten to ../<pkg>), tsconfig.base.json paths/globs,
knip.json keys, vitest include, gate scripts, and authored doc/note
citations; regenerate module graph, doc graphs, catalogs, and the
lockfile importer keys. No npm names change.

Full unit suite: 8779 passed; the 18 reported failures reproduce as
env flakes (ambient-proxy IPv6 tunneling, watched-dir inotify
timeouts under parallel load) — each passes in isolation with
NO_PROXY set, matching their known pre-existing behavior on master.
This commit is contained in:
Tianyi Cui
2026-08-09 01:21:11 +08:00
parent 645fcf5713
commit 7e445c3a67
220 files changed
+258 -286

No files matched your search

@@ -0,0 +1,407 @@
/**
* SQLite durable session-persistence backend. It maps each session header and
* event to rows, and delegates write-path orchestration to
* {@link PersistenceCoordinator}. It has no independent per-session artifact,
* so its locator returns `undefined`.
* @module @deepseek-ai/dsh-session-persistence-sqlite
*/
import { Context } from 'cordis'
import z from 'schemastery'
import { randomUUID } from 'node:crypto'
import { statSync } from 'node:fs'
import { DatabaseSync } from 'node:sqlite'
import { mkdir, open } from 'node:fs/promises'
import { dirname, resolve } from 'node:path'
import {
DEFAULT_PREPARED_SESSION_CACHE_SIZE, DEFAULT_WRITE_BATCH_MAX_DELAY_MS, MAX_WRITE_BATCH_DELAY_MS,
SessionPersistence, SessionPersistenceRevision, PersistenceCoordinator,
type PersistenceBackend, type SessionLocation, type SessionPersistenceSnapshot,
type SessionInspection, type SessionPersistenceRevision as PersistenceRevision,
type StoredPrefix, type StoredSuffix,
} from '@deepseek-ai/dsh-session-persistence'
import type { SessionEvent, SurfaceEventType, SessionId, SessionHeader, SessionPreparation } from '@deepseek-ai/dsh-session'
import {
type JournalMode, openDatabase, rowToMeta, scanRows, type EventRow, type SessionRow,
} from './schema.ts'
export { SCHEMA_VERSION } from './schema.ts'
/**
* Serialize an event's surface-metadata fields for SQL binding. Both fields are
* nullable TEXT columns — null when the event has no surface metadata (non-surface
* events, events written before surface support).
*/
function surfaceBindings(event: SessionEvent): [string | null, string | null] {
const se = event as SessionEvent<SurfaceEventType>
return [
se.sourceEventSeqs ? JSON.stringify(se.sourceEventSeqs) : null,
se.surfaceOp !== undefined ? JSON.stringify(se.surfaceOp) : null,
]
}
/** Build the source-qualified revision shared by full and lightweight reads. */
function sqliteRevision(storeIdentity: string, row: SessionRow): PersistenceRevision {
return SessionPersistenceRevision(
`${storeIdentity}:incarnation:${row.incarnation}:revision:${row.revision}`,
)
}
/**
* Exclusively create a missing database file with owner-only permissions.
* Existing files retain their modes, and errors other than `EEXIST` propagate.
* `DatabaseSync` reopens by path, so this does not protect confidentiality or
* integrity when another principal can replace the database entry in its parent
* directory.
*/
async function createDatabaseFile(path: string): Promise<void> {
try {
const handle = await open(path, 'wx', 0o600)
await handle.close()
} catch (error) {
if ((error as NodeJS.ErrnoException).code !== 'EEXIST') throw error
}
}
/** Plugin configuration. */
export interface Config {
/**
* Filesystem path to the SQLite database file. The special value `:memory:`
* opens an in-process database (tests). On filesystems with POSIX modes,
* missing directories and databases are created owner-only; existing path
* modes are preserved. Filesystem setup errors other than an existing database
* fail initialization. The backend does not protect confidentiality or
* integrity when another principal can replace the database entry in its
* parent directory.
*/
path: string
/**
* SQLite `journal_mode` pragma. `wal` (the default) is the recorded
* durability model; pick a rollback-journal mode (`delete`/`truncate`/
* `persist`) on filesystems where WAL's shared-memory files do not work
* (network mounts). See {@link JournalMode}.
*/
journalMode?: JournalMode
/** Maximum cold Session preparations retained for history-to-resume reuse. */
preparedSessionCacheSize?: number
/** Fixed live-event coalescing window; not a backend completion deadline. */
writeBatchMaxDelayMs?: number
}
/**
* The SQLite persistence backend. Load as a plugin; it registers as
* `ctx.sessionPersistence` and (via the coordinator) installs the write-path
* listeners. Its torn-tail marker is the seq to delete from.
*/
export class SessionPersistenceSqlite extends SessionPersistence implements PersistenceBackend<number> {
static inject = ['sessions']
static Config: z<Config> = z.object({
path: z.string().required(),
journalMode: z.union(['wal', 'delete', 'truncate', 'persist'] as const).default('wal'),
preparedSessionCacheSize: z.number().step(1).min(1).default(DEFAULT_PREPARED_SESSION_CACHE_SIZE),
writeBatchMaxDelayMs: z.number().step(1).min(1).max(MAX_WRITE_BATCH_DELAY_MS)
.default(DEFAULT_WRITE_BATCH_MAX_DELAY_MS),
})
/**
* Backend label for the coordinator's dispose diagnostics. Intentionally
* shadows cordis `Service.name` (set to `'sessionPersistence'` by the base);
* see the JSONL backend for why this does not affect service resolution.
*/
override readonly name = 'session-persistence-sqlite'
private db!: DatabaseSync
private storeIdentity!: string
private ready: Promise<void>
private coordinator: PersistenceCoordinator<number>
constructor(ctx: Context, public config: Config) {
super(ctx)
// Programmatic wrappers may construct the backend without Schemastery normalization.
const preparedSessionCacheSize = config.preparedSessionCacheSize
?? DEFAULT_PREPARED_SESSION_CACHE_SIZE
const writeBatchMaxDelayMs = config.writeBatchMaxDelayMs
?? DEFAULT_WRITE_BATCH_MAX_DELAY_MS
// Open asynchronously so directory creation does not block plugin apply;
// every storage hook awaits the same readiness promise.
this.ready = this.openDb(config.path, (config as Required<Config>).journalMode)
this.coordinator = new PersistenceCoordinator<number>(this.ctx, this, {
preparedSessionCacheSize,
writeBatchMaxDelayMs,
})
}
private async openDb(path: string, journalMode: JournalMode): Promise<void> {
const actual = path === ':memory:' ? path : resolve(path)
if (actual !== ':memory:') {
await mkdir(dirname(actual), { recursive: true, mode: 0o700 })
await createDatabaseFile(actual)
}
this.db = openDatabase(actual, journalMode)
try {
const row = this.db.prepare(
'SELECT store_id FROM persistence_state WHERE singleton = 1',
).get() as { store_id: string } | undefined
/* v8 ignore next -- openDatabase inserts the singleton before returning. */
if (row === undefined) {
throw new Error(`session database at "${actual}" has no store identity`)
}
if (row.store_id.length === 0) {
throw new Error(`session database at "${actual}" has no valid store identity`)
}
if (actual !== ':memory:') {
const identity = statSync(actual, { bigint: true })
this.storeIdentity = `file:${identity.dev}:${identity.ino}:${identity.birthtimeNs}:store:${row.store_id}`
} else {
this.storeIdentity = `memory:store:${row.store_id}`
}
} catch (error: unknown) {
this.db.close()
throw error
}
}
// --- SessionPersistence service surface (delegated to the coordinator) ---
/** SQLite has one database, not an independent local artifact per session. */
locate(_meta: SessionHeader): SessionLocation | undefined {
return undefined
}
create(meta: SessionHeader): Promise<void> {
return this.coordinator.create(meta)
}
append(id: SessionId, events: readonly SessionEvent[]): Promise<void> {
return this.coordinator.append(id, events)
}
override prepare(id: SessionId, signal?: AbortSignal): Promise<SessionPreparation> {
return this.coordinator.prepare(id, signal)
}
load(id: SessionId): Promise<SessionInspection> {
return this.coordinator.load(id)
}
inspect(id: SessionId, signal?: AbortSignal): Promise<SessionInspection> {
return this.coordinator.inspect(id, signal)
}
readFrom(id: SessionId, fromSeq: number, signal?: AbortSignal): Promise<{ meta: SessionHeader; events: SessionEvent[] }> {
return this.coordinator.readFrom(id, fromSeq, signal)
}
// One method serves both public `list` and the backend hook; delegating it to
// the coordinator would call this hook recursively.
// --- PersistenceBackend hooks (the SQLite storage primitives) ---
/** Read a stored prefix by id (ids are globally unique — no scope to scan). */
loadStored(id: SessionId, signal?: AbortSignal): Promise<StoredPrefix<number> | undefined> {
return this.readPrefix(id, signal)
}
/** Read one row's revision without loading its events. */
async readStoredRevision(id: SessionId, signal?: AbortSignal): Promise<PersistenceRevision | undefined> {
signal?.throwIfAborted()
await this.ready
signal?.throwIfAborted()
const row = this.rowFor(id)
return row === undefined ? undefined : sqliteRevision(this.storeIdentity, row)
}
/**
* Seek-capable suffix read: SQL selects `seq >= fromSeq` directly, so the
* read scales with the suffix, not the log. Torn rows past the preserved
* region are dropped, never repaired (non-mutating read).
*/
async loadStoredFrom(id: SessionId, fromSeq: number, signal?: AbortSignal): Promise<StoredSuffix | undefined> {
signal?.throwIfAborted()
await this.ready
signal?.throwIfAborted()
const row = this.rowFor(id)
if (row === undefined) return undefined
const meta = rowToMeta(row)
const eventRows = this.db
.prepare('SELECT seq, type, time, data, source_event_seqs, surface_op FROM events WHERE session_id = ? AND seq >= ? ORDER BY seq')
.all(id, fromSeq) as unknown as EventRow[]
signal?.throwIfAborted()
const { preserved } = scanRows(eventRows, fromSeq)
return { meta, events: preserved }
}
/**
* Read a session's row + ordered events into a {@link StoredPrefix}. The
* torn-tail marker is the seq from which a never-committed tail must be deleted
* (`scanRows` already returns it as `number | undefined`).
*/
private async readPrefix(id: SessionId, signal?: AbortSignal): Promise<StoredPrefix<number> | undefined> {
signal?.throwIfAborted()
await this.ready
signal?.throwIfAborted()
this.db.exec('BEGIN')
let snapshot: { row: SessionRow; eventRows: EventRow[] } | undefined
try {
const row = this.rowFor(id)
if (row !== undefined) {
const eventRows = this.db
.prepare('SELECT seq, type, time, data, source_event_seqs, surface_op FROM events WHERE session_id = ? ORDER BY seq')
.all(id) as unknown as EventRow[]
snapshot = { row, eventRows }
}
this.db.exec('COMMIT')
} catch (error: unknown) {
/* v8 ignore start -- synchronous read failures only need transaction cleanup before propagation. */
this.db.exec('ROLLBACK')
throw error
/* v8 ignore stop */
}
signal?.throwIfAborted()
if (snapshot === undefined) return undefined
const { row, eventRows } = snapshot
const { preserved, tornFrom } = scanRows(eventRows)
return {
meta: rowToMeta(row),
events: preserved,
revision: sqliteRevision(this.storeIdentity, row),
...tornFrom !== undefined ? { tornMarker: tornFrom } : {},
}
}
/**
* Durably append a batch in ONE transaction: materialize the sessions row (if
* lazy) and INSERT every event, or roll back entirely. The transaction is the
* atomicity + durability boundary, so a mid-batch failure (a UNIQUE violation
* on a duplicated seq) leaves the stored log untouched.
*/
async appendBatch(meta: SessionHeader, events: readonly SessionEvent[], isMaterialized: boolean): Promise<void> {
await this.ready
const insertEvent = this.db.prepare(
'INSERT INTO events (session_id, seq, type, time, data, source_event_seqs, surface_op) VALUES (?, ?, ?, ?, ?, ?, ?)',
)
this.db.exec('BEGIN')
try {
if (!isMaterialized) this.writeRow(meta)
for (const event of events) {
const [surfaceSeqs, surfaceOp] = surfaceBindings(event)
insertEvent.run(meta.id, event.seq, event.type, event.time, JSON.stringify(event.data), surfaceSeqs, surfaceOp)
}
this.db.prepare('UPDATE sessions SET revision = revision + 1 WHERE id = ?').run(meta.id)
this.db.exec('COMMIT')
} catch (error) {
this.db.exec('ROLLBACK')
throw error
}
}
/**
* Make a crash repair durable in ONE transaction: DELETE the torn tail (from
* `tornMarker`) and INSERT the synthetic `closers`. After COMMIT the stored rows
* == the balanced log.
*/
async commitRepair(meta: SessionHeader, tornMarker: number | undefined, closers: readonly SessionEvent[]): Promise<void> {
await this.ready
this.db.exec('BEGIN')
try {
if (tornMarker !== undefined) {
this.db.prepare('DELETE FROM events WHERE session_id = ? AND seq >= ?').run(meta.id, tornMarker)
}
if (closers.length > 0) {
const insertEvent = this.db.prepare(
'INSERT INTO events (session_id, seq, type, time, data, source_event_seqs, surface_op) VALUES (?, ?, ?, ?, ?, ?, ?)',
)
for (const event of closers) {
const [surfaceSeqs, surfaceOp] = surfaceBindings(event)
insertEvent.run(meta.id, event.seq, event.type, event.time, JSON.stringify(event.data), surfaceSeqs, surfaceOp)
}
}
if (tornMarker !== undefined || closers.length > 0) {
this.db.prepare('UPDATE sessions SET revision = revision + 1 WHERE id = ?').run(meta.id)
}
this.db.exec('COMMIT')
} catch (error) {
// The DELETE+INSERT cannot collide (a row at a closer's seq is preserved or
// deleted as torn first); this rolls back a DB-level failure (disk full,
// etc.), unreachable in test.
/* v8 ignore start */
this.db.exec('ROLLBACK')
throw error
/* v8 ignore stop */
}
}
/** List all materialized sessions' metadata (every row is a materialized session). */
async list(signal?: AbortSignal): Promise<SessionHeader[]> {
signal?.throwIfAborted()
await this.ready
signal?.throwIfAborted()
const rows = this.db
.prepare('SELECT * FROM sessions')
.all() as unknown as SessionRow[]
signal?.throwIfAborted()
return rows.map(rowToMeta)
}
/** List metadata with a source-qualified monotonic revision per session. */
async listSnapshots(signal?: AbortSignal): Promise<SessionPersistenceSnapshot[]> {
signal?.throwIfAborted()
await this.ready
signal?.throwIfAborted()
const rows = this.db.prepare('SELECT * FROM sessions').all() as unknown as SessionRow[]
signal?.throwIfAborted()
return rows.map(row => ({
header: rowToMeta(row),
revision: SessionPersistenceRevision(
`${this.storeIdentity}:incarnation:${row.incarnation}:revision:${row.revision}`,
),
}))
}
/** Close the database handle (awaited by the coordinator's dispose, post-drain). */
async close(): Promise<void> {
await this.ready
this.db.close()
}
// --- row helpers ---
/** Fetch a session's row, or undefined if absent. */
private rowFor(id: SessionId): SessionRow | undefined {
return this.db.prepare('SELECT * FROM sessions WHERE id = ?').get(id) as unknown as SessionRow | undefined
}
/**
* Insert-or-replace a session's metadata row. The only caller is the first
* materializing `appendBatch`, so writing the row IS the materialization (its
* existence is the signal `list` reads).
*/
private writeRow(meta: SessionHeader): void {
this.db.prepare(`
INSERT INTO sessions
(id, version, created_at, cwd, parent_session, seed_length, origin, delegation_depth, incarnation, revision)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, 0)
ON CONFLICT(id) DO UPDATE SET
version = excluded.version,
created_at = excluded.created_at,
cwd = excluded.cwd,
parent_session = excluded.parent_session,
seed_length = excluded.seed_length,
origin = excluded.origin,
delegation_depth = excluded.delegation_depth
`).run(
meta.id,
meta.version,
meta.createdAt,
meta.cwd ?? null,
meta.parentSession ?? null,
meta.seedLength ?? null,
meta.origin ?? null,
meta.delegationDepth ?? null,
randomUUID(),
)
}
}
export default SessionPersistenceSqlite
@@ -0,0 +1,30 @@
/**
* Package-owned invariant companion for `@deepseek-ai/dsh-session-persistence-sqlite`.
* @module @deepseek-ai/dsh-session-persistence-sqlite/invariant
*/
/* jscpd:ignore-start */
import type { Context } from 'cordis'
import type { InvariantInstaller } from '@deepseek-ai/dsh-invariants'
const PACKAGE_NAME = '@deepseek-ai/dsh-session-persistence-sqlite'
/** Cordis companion plugin name. */
export const name = 'session-persistence-sqlite-invariant'
/** Service required before the companion can reserve package ownership. */
export const inject = ['invariants']
/**
* No runtime invariant: persistence correctness requires backend round-trip and crash-tail tests;
* this package exposes no continuously observable in-process relation.
*/
const install: InvariantInstaller = () => {}
/**
* Register this package's invariant companion.
* @param ctx - Cordis context carrying the invariant service.
* @returns the installed registration's disposer after setup succeeds.
*/
export const apply = (ctx: Context): Promise<() => void> =>
Promise.resolve(ctx.invariants.register(PACKAGE_NAME, install))
/* jscpd:ignore-end */
@@ -0,0 +1,262 @@
/**
* Schema + load-time helpers for the SQLite session-persistence backend: the
* DDL (a store-identity row, `sessions` metadata, and a 1:1 `events` row per
* `SessionEvent`), the database open/configure step, and the last-`turn/end`
* cut that gives the SQLite backend the SAME crash-tail-on-load semantics as
* the JSONL backend.
*
* @module dsh-session-persistence-sqlite/schema
*/
import { randomUUID } from 'node:crypto'
import { DatabaseSync } from 'node:sqlite'
import type { SessionEvent, SessionId, SessionHeader, SurfaceOp } from '@deepseek-ai/dsh-session'
/**
* The on-disk schema version. Bumped only on a breaking change to the table
* layout; orthogonal to a session's own `version` (which versions the EVENT
* vocabulary, stored per session in the `sessions` row).
*/
export const SCHEMA_VERSION = 13
/** SQLite application id protecting unrelated databases from persistence writes. */
export const SESSION_PERSISTENCE_SQLITE_APPLICATION_ID = 0x44534850
/**
* A row of the `sessions` table — the out-of-log metadata ({@link SessionHeader}).
* The row's EXISTENCE is the materialization signal: it is written only by the
* first `append` (lazy materialization), so a created-but-never-appended
* session has no row and is absent from `list`, mirroring the JSONL
* backend's "no file until first append".
*/
export interface SessionRow {
id: string
version: number
created_at: number
cwd: string | null
parent_session: string | null
seed_length: number | null
origin: 'subagent' | null
/** Stable identity assigned when this log is materialized. */
incarnation: string
/** Monotonic log-change token incremented in each mutating transaction. */
revision: number
delegation_depth: number | null
}
/** An `events` table row: one `SessionEvent` mapped 1:1 (`data` is JSON text). */
export interface EventRow {
seq: number
type: string
time: number
data: string
/** JSON-encoded `number[]` — the event's sourceEventSeqs, or null. */
source_event_seqs: string | null
/** JSON-encoded `SurfaceOp` — how the event entered the surface, or null. */
surface_op: string | null
}
/**
* Journal modes the backend will run under. `wal` is the default and the
* durability model the persistence ADR records; the rollback-journal modes
* (`delete`/`truncate`/`persist`) exist for filesystems where WAL's
* shared-memory files do not work (network mounts). `memory`/`off` are
* excluded: dropping journal durability silently contradicts what this
* backend promises.
*/
export type JournalMode = 'wal' | 'delete' | 'truncate' | 'persist'
/**
* Open the database and apply its schema and pragmas. An empty database with a
* zero `user_version` is initialized at {@link SCHEMA_VERSION}; a nonempty
* unversioned database and every other non-current version reject rather than
* being migrated in place.
* @param path - the SQLite database file to open (created when absent).
* @param journalMode - validated journal pragma.
* @returns the open handle with pragmas applied and all three tables ensured.
*/
export function openDatabase(path: string, journalMode: JournalMode): DatabaseSync {
const db = new DatabaseSync(path)
try {
configureDatabase(db, path, journalMode)
return db
} catch (error: unknown) {
db.close()
throw error
}
}
function configureDatabase(db: DatabaseSync, path: string, journalMode: JournalMode): void {
db.exec('PRAGMA foreign_keys = ON')
let began = false
try {
db.exec('BEGIN IMMEDIATE')
began = true
// Validate while holding the write lock so no other connection can change
// schema ownership between inspection and initialization.
const { user_version: onDisk } = db.prepare('PRAGMA user_version').get() as { user_version: number }
const { application_id: applicationId } = db.prepare('PRAGMA application_id').get() as { application_id: number }
const { count: userObjectCount } = db.prepare(
"SELECT COUNT(*) AS count FROM sqlite_schema WHERE name NOT GLOB 'sqlite_*'",
).get() as { count: number }
if (onDisk === 0 && (applicationId !== 0 || userObjectCount > 0)) {
throw new Error(`session database at "${path}" has an unversioned schema or application identity`)
}
if (onDisk !== 0 && onDisk !== SCHEMA_VERSION) {
throw new Error(`session database at "${path}" has schema version ${onDisk}, incompatible with this build (${SCHEMA_VERSION})`)
}
if (onDisk === SCHEMA_VERSION && applicationId !== SESSION_PERSISTENCE_SQLITE_APPLICATION_ID) {
throw new Error(
`session database at "${path}" has application id ${applicationId}, expected ${SESSION_PERSISTENCE_SQLITE_APPLICATION_ID}`,
)
}
db.exec(`
CREATE TABLE IF NOT EXISTS persistence_state (
singleton INTEGER PRIMARY KEY CHECK (singleton = 1),
store_id TEXT NOT NULL
) STRICT;
CREATE TABLE IF NOT EXISTS sessions (
id TEXT PRIMARY KEY,
version INTEGER NOT NULL,
created_at INTEGER NOT NULL,
cwd TEXT,
parent_session TEXT,
seed_length INTEGER,
origin TEXT,
delegation_depth INTEGER,
incarnation TEXT NOT NULL,
revision INTEGER NOT NULL
) STRICT;
CREATE TABLE IF NOT EXISTS events (
session_id TEXT NOT NULL REFERENCES sessions(id) ON DELETE CASCADE,
seq INTEGER NOT NULL,
type TEXT NOT NULL,
time INTEGER NOT NULL,
data TEXT NOT NULL,
source_event_seqs TEXT,
surface_op TEXT,
PRIMARY KEY (session_id, seq)
) STRICT
`)
db.prepare(
'INSERT OR IGNORE INTO persistence_state (singleton, store_id) VALUES (1, ?)',
).run(randomUUID())
if (onDisk === 0) {
db.exec(`PRAGMA application_id = ${SESSION_PERSISTENCE_SQLITE_APPLICATION_ID}`)
db.exec(`PRAGMA user_version = ${SCHEMA_VERSION}`)
}
db.exec('COMMIT')
began = false
} catch (error: unknown) {
/* v8 ignore next -- a BEGIN failure leaves no transaction to roll back. */
if (began) {
/* v8 ignore next 5 -- preserve the original schema failure if SQLite also refuses rollback. */
try {
db.exec('ROLLBACK')
} catch {
// The original SQLite failure remains the actionable cause.
}
}
throw error
}
// The validated union is safe to interpolate into a non-bindable PRAGMA.
// Apply it only after ownership validation and initialization commit.
db.exec(`PRAGMA journal_mode = ${journalMode.toUpperCase()}`)
}
/**
* Reconstruct the {@link SessionHeader} from a `sessions` row.
* @param row - the `sessions` table row.
* @returns the header, `NULL` columns mapped to omitted optional fields.
*/
export function rowToMeta(row: SessionRow): SessionHeader {
if (!Number.isSafeInteger(row.created_at) || row.created_at < 0) {
throw new Error('stored session createdAt must be a non-negative safe integer')
}
return {
version: row.version,
id: row.id as SessionId,
createdAt: row.created_at,
...row.cwd !== null ? { cwd: row.cwd } : {},
...row.parent_session !== null ? { parentSession: row.parent_session as SessionId } : {},
...row.seed_length !== null ? { seedLength: row.seed_length } : {},
...row.origin !== null ? { origin: row.origin } : {},
...row.delegation_depth !== null ? { delegationDepth: row.delegation_depth } : {},
}
}
/**
* Reconstruct a {@link SessionEvent} from an `events` row (parses `data`).
* @param row - the `events` table row; `data` and the surface columns hold JSON text.
* @returns the reconstructed event; throws when a JSON column fails to parse
* ({@link scanRows} treats that as a hole, not corruption, in the tail).
*/
export function rowToEvent(row: EventRow): SessionEvent {
// Surface-metadata fields are conditional on the event type in the type
// system; spread them so each variant gets only the fields it declares.
const surfaceFields = {
...row.source_event_seqs !== null ? { sourceEventSeqs: JSON.parse(row.source_event_seqs) as number[] } : {},
...row.surface_op !== null ? { surfaceOp: JSON.parse(row.surface_op) as SurfaceOp } : {},
}
return {
type: row.type as SessionEvent['type'],
seq: row.seq,
time: row.time,
data: JSON.parse(row.data) as SessionEvent['data'],
...surfaceFields,
} as SessionEvent
}
/**
* Find the preserved prefix of ordered event rows. Fully written rows in an
* interrupted final turn remain in the prefix. The first unparsable row or seq
* gap after the last `turn/end` marks a tolerated torn tail; the same hole in
* the committed region rejects.
*
* @param rows - one session's event rows, ordered by seq ascending.
* @param base - the seq the first row is expected to carry; `0` for a whole
* log, the requested `fromSeq` for a suffix read (`loadStoredFrom`).
* @returns the preserved event prefix, plus `tornFrom` — the seq the physical
* delete starts at — when a torn tail exists.
*/
export function scanRows(rows: readonly EventRow[], base = 0): { preserved: SessionEvent[]; tornFrom?: number } {
// Pass 1: parse each row's data; a row whose data is not valid JSON is a hole.
// (The seq/type COLUMNS are always present even when `data` is corrupt.)
interface Parsed { ok: boolean; event?: SessionEvent }
const parsed: Parsed[] = rows.map((row) => {
try {
return { ok: true, event: rowToEvent(row) }
} catch {
return { ok: false }
}
})
// The last index that is a valid `turn/end` — holes through a closed turn
// are always committed corruption.
let lastTurnEnd = -1
for (let i = parsed.length - 1; i >= 0; i--) {
if (parsed[i]?.ok && rows[i]?.type === 'turn/end') { lastTurnEnd = i; break }
}
// Preserve the contiguous prefix, including a complete interrupted turn;
// holes through the last committed boundary throw, while later holes stop.
const preserved: SessionEvent[] = []
for (let i = 0; i < rows.length; i++) {
const p = parsed[i]
if (!p?.ok || p.event === undefined) {
if (i <= lastTurnEnd) throw new Error(`corrupt session log: unparsable committed event at seq ${rows[i]?.seq}`)
break // torn tail fragment after the last turn/end — stop, tolerate
}
if (p.event.seq !== base + i) {
if (i <= lastTurnEnd) throw new Error(`corrupt session log: seq gap in committed region (expected ${base + i}, got ${p.event.seq})`)
break // gap after the last turn/end — torn tail, stop
}
preserved.push(p.event)
}
// Any rows past the preserved prefix are a never-committed torn tail; their
// first seq is the deletion point for load's physical repair.
return preserved.length < rows.length ? { preserved, tornFrom: base + preserved.length } : { preserved }
}