Files
openclaw/src/trajectory/runtime-store.sqlite.test.ts
Josh Lehman 0a8e3604ba refactor: flip sessions and transcripts to sqlite storage (#98236)
* refactor(sessions): migrate runtime storage to sqlite

* test(sessions): fix sqlite CI regressions

* test(sessions): align remaining sqlite fixtures

* fix(codex): require sqlite trajectory recorder

* test(sessions): align orphan recovery sqlite fixture

* test(sessions): align sqlite rebase fixtures

* fix(sessions): finish current-main integration of the sqlite flip

Resolve the whole-store SDK removal across its owner boundary: drop the
loadSessionStore re-export and the registry whole-store wrappers, wire
hasTrackedActiveSessionRun into gateway chat, complete the
preserveLockedHarnessIds cleanup contract, flip the codex thread-history
import to storePath targets, and port remaining main-side tests from
file-store helpers to session accessor reads.

* chore: drop committed pebbles log, revert plugin-inspector bump, refresh generated docs

Remove the 1.8k-line .pebbles/events.jsonl work log from the branch, restore
the plugin-inspector advisory lane to main's pinned 0.3.10 so the supply-chain
bump gets its own review, and regenerate docs_map, the plugin SDK API baseline,
and the export-surface ratchet for the merged tree.

* feat(sessions): keep archived transcripts by default with zstd cold storage

Codex-style retention: deleting or resetting a session archives its
transcript as a zstd-compressed JSONL artifact (plain when the runtime
lacks node:zlib zstd) and keeps it until the disk budget evicts oldest
first. resetArchiveRetention now governs both deleted and reset archives
and defaults to keep; maxDiskBytes defaults to 2gb so retention stays
bounded, with archives evicted before live sessions. The cron reaper
follows the same knob instead of deleting archives on its own timer.

* fix(state): converge agent DB migration lineages and bound database growth

Merge coherence: run both structure-gated legacy memory-schema repairs
(flip-lineage drop, main-lineage identity rebuild) before the flip
migration so pre-flip v1/v2 and pre-merge flip v1/v4 databases all
converge, and hoist foreign_keys=OFF outside the schema transaction
where the pragma was silently ignored and the v1 sessions rebuild
cascade-deleted session_entries.

Growth guards: fresh agent DBs enable auto_vacuum=INCREMENTAL, WAL
maintenance releases freed pages in bounded passes (never a blocking
full VACUUM), and doctor reports state/agent DB bloat from freelist
stats.

* fix(codex): resolve the store path for thread-history import via the SDK

The supervision catalog passed the legacy sessionFile locator to the
storePath-targeted transcript mirror; resolve the agent store path with
the session-store SDK helper instead of a runtime-object seam so test
fakes and headless callers need no extra surface. Drop the obsolete
missing-session-id preprocessing case: sessions rows are NOT NULL on
session_id and upsert repairs id-less patches at write time.

* fix(sessions): fail safe on malformed disk-budget config and doctor stat errors

A malformed explicit maxDiskBytes disables the budget instead of
falling back to the destructive 2gb default the user never chose, and
the doctor bloat check skips databases whose paths stat-fail instead of
aborting doctor.

* fix(sessions): complete sqlite conflict translations

* test(sqlite): align hardening checks with maintenance

* test(sessions): inspect compressed transcript archives

* fix(tests): await session seeds and drop unused helpers flagged by CI lint

The five unawaited writeSessionStoreSeed calls raced their SQLite seeds
against the assertions, failing compact shards; the bloat probe drops a
useless initializer and the merged tests drop now-unused helpers.

* test(sessions): type legacy proof events directly

* test(sessions): align hardening contracts

* perf(sessions): read usage transcript sizes from SQL aggregates

Usage/cost scans walked every session and materialized every transcript
event just to re-stringify it for a byte estimate — the #86718 stall
class reborn on the DB. readTranscriptStatsSync sums stored JSON bytes
in SQLite without loading a single row.

* fix(sessions): re-root foreign-root transcript paths onto the current sessions dir

Restored backups, moved OPENCLAW_STATE_DIR, and rehearsal copies carry
absolute sessionFile paths from the old root; the containment fallback
kept those foreign paths, so migration read (and would archive) files in
the original root and reported local copies missing. Re-root the
canonical agents/<id>/sessions suffix onto the current dir when the file
exists there; genuine cross-root layouts still fall through unchanged.

* test(agents): seed harness admission through sqlite

* fix(sqlite): close agent db on pragma setup failure

* fix(doctor): compact and retrofit incremental auto-vacuum after session import

The migration is the sanctioned offline window: post-import compact
reclaims import churn and applies auto_vacuum=INCREMENTAL to databases
created before the fresh-DB pragma existed, so runtime maintenance can
release pages in bounded passes on every install.

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-07-11 14:50:37 -07:00

129 lines
4.5 KiB
TypeScript

// SQLite trajectory runtime tests cover session-scoped event row storage.
import fs from "node:fs";
import os from "node:os";
import path from "node:path";
import { afterEach, beforeEach, describe, expect, it } from "vitest";
import { replaceSessionEntry } from "../config/sessions/session-accessor.js";
import { executeSqliteQuerySync, getNodeSqliteKysely } from "../infra/kysely-sync.js";
import type { DB as OpenClawAgentKyselyDatabase } from "../state/openclaw-agent-db.generated.js";
import {
closeOpenClawAgentDatabasesForTest,
openOpenClawAgentDatabase,
} from "../state/openclaw-agent-db.js";
import { closeOpenClawStateDatabaseForTest } from "../state/openclaw-state-db.js";
import {
appendSqliteTrajectoryRuntimeEvents,
loadSqliteTrajectoryRuntimeEvents,
readSqliteTrajectoryRuntimeStatsSync,
} from "./runtime-store.sqlite.js";
import type { TrajectoryEvent } from "./types.js";
type TrajectoryRuntimeTestDatabase = Pick<OpenClawAgentKyselyDatabase, "trajectory_runtime_events">;
describe("SQLite trajectory runtime store", () => {
let tempDir: string;
let storePath: string;
beforeEach(async () => {
tempDir = fs.mkdtempSync(path.join(os.tmpdir(), "openclaw-trajectory-sqlite-"));
storePath = path.join(tempDir, "agents", "main", "sessions", "sessions.json");
await replaceSessionEntry(
{ sessionKey: "agent:main:main", storePath },
{ sessionId: "session-1", updatedAt: 10 },
);
});
afterEach(() => {
closeOpenClawAgentDatabasesForTest();
closeOpenClawStateDatabaseForTest();
fs.rmSync(tempDir, { recursive: true, force: true });
});
it("appends events in database order without trusting recorder-local seq", async () => {
appendSqliteTrajectoryRuntimeEvents({ sessionId: "session-1", storePath }, [
createTrajectoryEvent({ seq: 1, type: "model.started" }),
createTrajectoryEvent({ seq: 1, type: "model.completed" }),
]);
await expect(
loadSqliteTrajectoryRuntimeEvents({ sessionId: "session-1", storePath }),
).resolves.toEqual([
expect.objectContaining({ seq: 1, type: "model.started" }),
expect.objectContaining({ seq: 1, type: "model.completed" }),
]);
const database = openOpenClawAgentDatabase({ agentId: "main", path: sqlitePath() });
const db = getNodeSqliteKysely<TrajectoryRuntimeTestDatabase>(database.db);
const rows = executeSqliteQuerySync(
database.db,
db
.selectFrom("trajectory_runtime_events")
.select(["seq", "run_id"])
.where("session_id", "=", "session-1")
.orderBy("seq", "asc"),
).rows;
expect(rows).toEqual([
{ run_id: "run-1", seq: 0 },
{ run_id: "run-1", seq: 1 },
]);
});
it("trims oldest rows beyond the configured byte window", async () => {
appendSqliteTrajectoryRuntimeEvents(
{ maxRuntimeBytes: 900, sessionId: "session-1", storePath },
[
createTrajectoryEvent({ type: "event-1" }),
createTrajectoryEvent({ type: "event-2" }),
createTrajectoryEvent({ type: "event-3" }),
createTrajectoryEvent({ type: "event-4" }),
],
);
const events = await loadSqliteTrajectoryRuntimeEvents({
sessionId: "session-1",
storePath,
});
expect(events.map((event) => event.type)).toEqual(["event-3", "event-4"]);
expect(readSqliteTrajectoryRuntimeStatsSync({ sessionId: "session-1", storePath })).toEqual({
eventCount: 2,
maxSeq: 3,
sizeBytes: expect.any(Number),
});
});
it("cascades trajectory rows when the session row is deleted", async () => {
appendSqliteTrajectoryRuntimeEvents({ sessionId: "session-1", storePath }, [
createTrajectoryEvent({ type: "model.started" }),
]);
const database = openOpenClawAgentDatabase({ agentId: "main", path: sqlitePath() });
database.db.prepare("DELETE FROM sessions WHERE session_id = ?").run("session-1");
await expect(
loadSqliteTrajectoryRuntimeEvents({ sessionId: "session-1", storePath }),
).resolves.toEqual([]);
});
function sqlitePath(): string {
return path.join(tempDir, "agents", "main", "agent", "openclaw-agent.sqlite");
}
});
function createTrajectoryEvent(options: { seq?: number; type: string }): TrajectoryEvent {
return {
traceSchema: "openclaw-trajectory",
schemaVersion: 1,
traceId: "session-1",
source: "runtime",
type: options.type,
ts: "2026-07-03T00:00:00.000Z",
seq: options.seq ?? 1,
sourceSeq: options.seq ?? 1,
sessionId: "session-1",
sessionKey: "agent:main:main",
runId: "run-1",
data: { payload: "x".repeat(120) },
};
}