Merge remote-tracking branch 'origin/master' into session-query-search

# Conflicts:
#	docs/config-catalog.md
#	docs/cordis-catalog/services.md
#	docs/module-graph.md
#	packages/session-persistence/session-persistence-jsonl/README.md
#	packages/session-persistence/session-persistence-jsonl/src/index.ts
#	packages/session-persistence/session-persistence-sqlite/README.md
#	packages/session-persistence/session-persistence-sqlite/src/index.ts
#	packages/session-persistence/session-persistence-sqlite/src/schema.ts
#	packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts
#	packages/session-persistence/session-persistence/README.md
#	packages/session-persistence/session-persistence/src/coordinator.ts
#	packages/session-persistence/session-persistence/tests/persistence.spec.ts
#	packages/session-query/session-query/README.md
This commit is contained in:
Hypatia May
2026-07-15 16:17:59 +08:00
841 files changed
+18816 -16117

No files matched your search

@@ -1,19 +1,7 @@
/**
* SQLite durable session-persistence backend (`@deepseek-ai/dsh-session-persistence-sqlite`).
*
* A SECOND {@link SessionPersistence} implementation, built to validate that the
* abstract seam + the shared `runPersistenceContract` suite are genuinely
* backend-agnostic: the same append-only / contiguous-seq / lazy-materialization
* / interrupted-turn-close-on-load semantics the JSONL backend expresses over
* file bytes, expressed here over `node:sqlite` rows. Each `SessionEvent` maps
* 1:1 onto a row `(session_id, seq, type, time, data, source_event_seqs, surface_op)`.
*
* Like the JSONL backend it supplies ONLY the storage primitives (the
* {@link PersistenceBackend} hooks below — INSERT/DELETE/SELECT inside
* transactions); all the write-path orchestration lives in the backend-agnostic
* {@link PersistenceCoordinator} this class composes. The stateful public
* {@link SessionPersistence} methods delegate to the coordinator.
*
* SQLite durable session-persistence backend. It maps each session header and
* event to rows, and delegates write-path orchestration to
* {@link PersistenceCoordinator}.
* @module @deepseek-ai/dsh-session-persistence-sqlite
*/
@@ -27,7 +15,7 @@ import {
SessionPersistence, SessionPersistenceRevision, PersistenceCoordinator,
type PersistenceBackend, type SessionPersistenceSnapshot, type StoredPrefix,
} from '@deepseek-ai/dsh-session-persistence'
import type { Session, SessionEvent, SurfaceEventType, SessionId, SessionHeader } from '@deepseek-ai/dsh-session'
import type { SessionEvent, SurfaceEventType, SessionId, SessionHeader } from '@deepseek-ai/dsh-session'
import {
type JournalMode, openDatabase, rowToMeta, scanRows, type EventRow, type SessionRow,
} from './schema.ts'
@@ -91,10 +79,8 @@ export class SessionPersistenceSqlite extends SessionPersistence implements Pers
constructor(ctx: Context, public config: Config) {
super(ctx)
// Open the database asynchronously (the parent directory may need creating);
// every hook awaits `ready` first. Opening synchronously would force a sync
// mkdir and block plugin apply. schemastery (static Config) has already
// filled `journalMode`; the cast records that runtime fact.
// 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)
}
@@ -140,18 +126,8 @@ export class SessionPersistenceSqlite extends SessionPersistence implements Pers
return this.coordinator.load(id)
}
// `list` is BOTH the public service method and the PersistenceBackend hook —
// one method (the SELECT below). The coordinator adds no orchestration for
// listing, so routing it through the coordinator would just recurse. Defined
// once, in the "PersistenceBackend hooks" section.
/**
* The per-session init promises, exposed for white-box tests that await a
* specific session's onCreated (there is no public API to await one init).
*/
get inits(): Map<Session, Promise<void>> {
return this.coordinator.inits
}
// 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) ---
@@ -60,23 +60,11 @@ export interface EventRow {
export type JournalMode = 'wal' | 'delete' | 'truncate' | 'persist'
/**
* Open the database at `path` and apply the schema + pragmas. `foreign_keys`
* makes `ON DELETE CASCADE` drop a session's events with its row; the
* `journal_mode` pragma is set from the plugin's `journalMode` config (`wal`
* default — the durability model the ADR records; the row shape maps 1:1
* onto `SessionEvent`; opencode runs this exact shape on SQLite/WAL).
*
* The table-layout version is persisted in SQLite's `PRAGMA user_version` and
* checked on open: a fresh database (user_version 0) is stamped with the
* current {@link SCHEMA_VERSION}; an existing database whose version is NOT the
* current one (written by a different, incompatible build — older or newer) is
* REJECTED rather than opened against a layout this build does not understand.
* There are no migrations: an incompatible layout is rejected. The current
* persistence-state row carries an immutable random store id, the sessions row
* carries every header field plus its monotonic snapshot revision, and the
* events row carries the complete surface metadata.
* Open the database and apply its schema and pragmas. A zero `user_version` is
* stamped with {@link SCHEMA_VERSION}; every other non-current version rejects
* rather than being migrated in place.
* @param path - the SQLite database file to open (created when absent).
* @param journalMode - the journal pragma to apply — a closed in-code union, validated by the plugin Config.
* @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 {
@@ -92,8 +80,7 @@ export function openDatabase(path: string, journalMode: JournalMode): DatabaseSy
function configureDatabase(db: DatabaseSync, path: string, journalMode: JournalMode): void {
db.exec('PRAGMA foreign_keys = ON')
// journalMode is a closed in-code union (validated by the plugin Config), not
// user-controlled SQL — safe to interpolate (PRAGMA takes no bound params).
// The validated union is safe to interpolate into a non-bindable PRAGMA.
db.exec(`PRAGMA journal_mode = ${journalMode.toUpperCase()}`)
// `PRAGMA user_version` always returns exactly one row { user_version }.
const { user_version: onDisk } = db.prepare('PRAGMA user_version').get() as { user_version: number }
@@ -101,9 +88,7 @@ function configureDatabase(db: DatabaseSync, path: string, journalMode: JournalM
throw new Error(`session database at "${path}" has schema version ${onDisk}, incompatible with this build (${SCHEMA_VERSION})`)
}
if (onDisk === 0) {
// Fresh (or pre-versioning) database: stamp the current layout version.
// PRAGMA does not accept bound parameters, so interpolate the integer
// constant (SCHEMA_VERSION is a trusted in-code number, not user input).
// Stamp fresh or pre-versioning databases.
db.exec(`PRAGMA user_version = ${SCHEMA_VERSION}`)
}
db.exec(`
@@ -179,28 +164,11 @@ export function rowToEvent(row: EventRow): SessionEvent {
}
/**
* The preserved prefix of an ordered event-row list (mirrors the JSONL
* backend's `scanLog`): the longest prefix of complete, seq-contiguous,
* parseable rows, PLUS the seq from which a never-committed torn tail must be
* deleted (or `undefined` if the whole list is intact).
* 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.
*
* A crash can leave a durable log whose final turn never closed: real,
* fully-written rows sit after the last `turn/end`. Those are PRESERVED — a
* single turn can be huge in a long-horizon task, so truncating it would
* destroy real work; the backend closes the orphaned open turn with a synthetic
* `turn/end {kind:'interrupted'}` on load (the session-persistence RFC). The ONLY thing excluded is
* a torn trailing fragment — a row whose `data` never parses, or a seq gap —
* AFTER the last committed `turn/end`; that bounds the preserved region and its
* seq is returned as `tornFrom` so `load` can physically delete it.
*
* The last `turn/end` is computed from the `type` COLUMN (never parsing tail
* `data`), so a malformed `data` in an uncommitted tail row is discarded rather
* than making the session unloadable. A parse error or seq gap AT OR BEFORE the
* last committed `turn/end` is committed-data corruption and throws.
*
* This relies on the session-log invariant that every event lives inside a turn
* (`Session.append` enforces it): only the final turn can be open, so the
* preserved tail is at most one unclosed turn.
* @param rows - one session's event rows, ordered by seq ascending.
* @returns the preserved event prefix, plus `tornFrom` — the seq the physical
* delete starts at — when a torn tail exists.
@@ -224,12 +192,8 @@ export function scanRows(rows: readonly EventRow[]): { preserved: SessionEvent[]
if (parsed[i]?.ok && rows[i]?.type === 'turn/end') { lastTurnEnd = i; break }
}
// Walk the longest PREFIX of complete, seq-contiguous, parseable rows
// (row i has seq === i). This includes the fully-written rows of an
// interrupted final turn AFTER the last turn/end — real work, never
// truncated. The walk stops at the first hole:
// - at or before the last committed turn/end → committed corruption (throw);
// - after it (or no committed turn/end) → tolerated torn tail (stop).
// 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]