Files
openclaw/test/scripts/sqlite-sessions-transcripts-flip-proof.e2e.test.ts
Peter Steinberger 4273ca9dbd refactor(sessions): remove file-era transcript runtime (#113233)
* refactor(sessions): keep helper transcripts in memory

* refactor(sessions): remove file-era transcript storage

* test(sessions): use SQLite identity in attempt persistence

* test(codex): isolate legacy transcript fixtures

* fix(sessions): preserve SQLite transcript identity

* fix(sessions): harden transcript lifecycle invariants

* fix(sessions): validate transcript identities

* fix(sessions): close identity compatibility gaps

* fix(sessions): preserve leaf and plugin identities

* fix(sessions): retain dispatch transcript targets

* fix(sessions): preserve active transcript context

* fix(sessions): isolate artifact accounting

* fix(sessions): bound SQLite usage accounting

* fix(sessions): retain bounded latest usage

* fix(sessions): align rebased transcript targets

* test(sessions): align accessor scope fixture

* fix(telegram): derive SQLite transcript identity

* refactor(sessions): remove file-era compaction residue

* chore(sessions): lower max-lines baseline

* fix(sessions): preserve structured transcript identity

* test(sessions): align doctor identity assertions

* fix(sessions): isolate default SDK database

* refactor(sessions): remove dead file-era exports

* fix(sessions): reconcile SQLite transcript identity

* fix(sessions): pass checkpoint identity explicitly

* test(sessions): make entry field probe explicit

* test(sessions): satisfy transcript cleanup lint

* test(sessions): align diagnostics identity proof

* fix(sessions): finish transcript runtime teardown

* fix(sessions): preserve transcript identity invariants

* fix(sessions): harden transcript compatibility edges

* fix(sessions): preserve checkpoint transcript anchors

* fix(sessions): preserve SQLite lifecycle invariants

* fix(sessions): retarget compaction successors

* test(sessions): preserve transcript fixture semantics

* feat(plugin-sdk): add command transcript targets

* fix(sessions): serialize transcript rewrites

* fix(sessions): validate legacy successor identity

* fix(sessions): normalize compaction ownership

* fix(sessions): validate successor identity before adoption

* fix(sessions): preserve plugin transcript ownership

* fix(sessions): carry transcript identity through commands

* fix(sessions): import legacy checkpoint artifacts into SQLite

* fix(sessions): preserve successor transcript ownership

* fix(sessions): align transcript consumers with target identity

* fix(sessions): scope transcript token estimates

* fix(sessions): retain agent identity across lifecycle hooks

* fix(sessions): resolve scoped SQLite targets

* fix(sessions): isolate lifecycle transcript targets

* fix(sessions): validate compaction agent ownership

* fix(sessions): preserve reset and cleanup lifecycle

* fix(sessions): serialize prompt cleanup lifecycle

* fix(sessions): remove stale lock import

* fix(sessions): preserve reset target context

* fix(sessions): fence prompt reload takeover

* fix(sessions): unblock abort and default lifecycle reads

* fix(sessions): validate legacy successor scope

* fix(sessions): reject metadata-only runtime rows

* fix(sessions): propagate custom transcript stores

* fix(sessions): preserve adopted retry targets

* fix(sessions): allow unkeyed usage reads

* fix(sessions): harden runtime target boundaries

* fix(sessions): serialize retry transcript writes

* fix(sessions): bound prompt reload disposal

* fix(sessions): complete retry marker identity

* fix(sessions): keep legacy marker identity minimal

* test(sessions): tighten teardown fixture types

* fix(sessions): preserve compatibility target identity

* test(sessions): persist post-checkpoint boundary turn

* test(sessions): align runtime store mock contracts

* style(sessions): simplify persisted identity guard

* fix(sessions): prefer complete typed targets

* fix(sessions): recover legacy marker targets

* test(sessions): align marker lookup fixture scope

* fix(sessions): validate partial transcript targets

* fix(sessions): reconcile partial transcript identities

* fix(sessions): canonicalize compatibility identities

* test(sessions): cover compatibility aliases

* fix(sessions): adopt legacy successor identity

* fix(sessions): preserve usage read identity

* fix(sessions): preserve partial marker compatibility

* fix(sessions): validate legacy successor mappings

* fix(sessions): reconcile marker store mappings

* fix(sessions): preserve legacy fallback identity

* fix(sessions): harden marker alias resolution

* fix(sessions): prefer verified successor aliases

* fix(sessions): resolve preferred marker aliases

* fix(sessions): serialize cleanup admission

* fix(sessions): align marker lookup scopes

* fix(codex): type marker alias summaries

* style(sessions): satisfy changed lint

* test(sessions): align structured target assertions

* fix(sessions): reconcile latest identity contracts

* fix(sessions): validate transcript identity boundaries

* docs(sessions): explain stable registry keys

* fix(sessions): harden compatibility target round trips

* fix(sessions): port usage identity to split modules

* test(sessions): align subagent transcript identity

* fix(sessions): finish transcript identity migration

* fix(agents): route subagent completion capture through transcript targets

* fix(agents): settle SQLite prompt handoff during cleanup

* chore: shrink max-lines baseline after teardown

* fix(sessions): port teardown across split runtime owners

* fix(sessions): carry transcript targets through split owners

* test(agents): use SQLite compaction target in abort coverage

* chore: retain unrelated max-lines suppressions

* chore: shrink max-lines baseline after main splits

* style(agents): const compaction checkpoint locals

* fix(sessions): harden SQLite teardown boundaries

* test(sessions): use typed metadata in predicate isolation fixture

* test(agents): cover malformed settlement rejections lint-safely

* fix(sessions): close remaining SQLite identity races

* fix(agents): fail closed on incomplete successor targets

* fix(sessions): preserve transcript identity fallbacks

* fix(agents): preserve session-key abort admission

* fix(trajectory): validate incomplete export targets

* test(sessions): drop retired pricing cache imports

* fix(sessions): validate partial transcript identities

* fix(sessions): close transcript identity edge cases

* fix(plugins): reserve retired transcript locator slot

* fix(sessions): scope transcript locks by target

* style(sessions): simplify SDK initialization error

* fix(sessions): preserve initialized transcript state

* fix(codex): verify mirrored history session keys

* fix(sessions): reject stale transcript ownership

* fix(sessions): anchor asynchronous transcript ownership

* fix(sessions): measure active transcript state

* fix(sessions): preserve scoped transcript compaction

* fix(sessions): harden transcript identity and lifecycle

* fix(sessions): resolve scoped command transcript stores

* fix(sessions): make transcript appends failure-atomic

* fix(sessions): enforce scoped transcript ownership

* fix(sessions): reject cross-owner transcript handoffs

* fix(sessions): fence cleanup transcript ownership

* fix(sessions): retire stale write ownership contexts

* fix(sessions): preserve pending session migration state

* fix(sessions): validate migrated transcript ownership

* fix(sessions): validate usage transcript targets

* fix(sessions): clear predecessor transcript metadata

* fix(sessions): align durable session event targets

* fix(sessions): fence late prompt handoffs

* fix(sessions): fence lifecycle transcript fallbacks

* fix(sessions): bound zero-length memory capture

* fix(sessions): preserve transcript teardown ownership

* fix(sessions): reject duplicate cleanup ownership

* fix(sessions): serialize runtime writes with sqlite leases

* fix(sessions): close sqlite teardown concurrency gaps

* fix(sessions): preserve nested lifecycle failures

* fix(sessions): canonicalize sqlite transcript ownership

* fix(sessions): settle disposed prompt handoffs

* fix(sessions): resolve canonical attempt lock targets

* test(sessions): align canonical target fixtures

* test(sessions): retire redundant jsonl parser coverage

* refactor(sessions): split active transcript cursors

* test(memory): retire legacy marker fixture

* fix(sessions): preserve canonical transcript access after rebase

* fix(sessions): fence prompt lease and return transcript targets

* fix(sessions): colocate transcript leases with target store

* fix(sessions): canonicalize transcript lease and worker targets

* fix(sessions): preserve plugin and fork identity markers

* fix(sessions): complete sqlite transcript target migration

* fix(sessions): integrate canonical followup identity

* fix(sessions): preserve bounded transcript topology

* fix(sessions): validate transcript identity boundaries

* fix(context): separate caller and successor targets

* test(sessions): split persistence compatibility coverage

* test(sessions): preserve fixture topology efficiently

* chore(sdk): refresh plugin api baseline

* test(agents): align compaction lock target mocks

* test(sessions): seed malformed transcript fixtures directly

* fix(agents): canonicalize transcript compatibility inputs

* fix(agents): type optional tool result ids

* test(ci): stabilize loaded process timing

* test(tui): wait for collect queue admission
2026-07-27 22:33:24 -04:00

235 lines
9.1 KiB
TypeScript

// SQLite sessions/transcripts flip proof test runs the script-style gateway lifecycle probe.
import { describe, expect, it } from "vitest";
import { assertSqliteFlipProofCore } from "../helpers/sqlite-sessions-transcripts-flip-proof-assertions.ts";
import { runSqliteSessionsTranscriptsFlipProof } from "../helpers/sqlite-sessions-transcripts-flip-proof.ts";
describe("SQLite sessions/transcripts flip proof harness", () => {
it("proves isolated gateway lifecycle state stays SQLite-first", async () => {
const report = await runSqliteSessionsTranscriptsFlipProof();
assertSqliteFlipProofCore(report);
expect(report.checkpoints.map((checkpoint) => checkpoint.label)).toEqual([
"seeded-legacy-store",
"after-startup-import",
"after-doctor-inspect",
"after-doctor-validate",
"after-rollback-restore",
"after-gateway-restart",
"after-chat-send",
"after-full-agent-turn",
"after-manual-compaction",
"after-plugin-sdk-consumer",
"after-cleanup-pruning",
"after-doctor-import-idempotence",
"after-downgrade-reupgrade-import",
"after-sqlite-busy-contention",
"after-concurrent-multi-client",
"after-sessions-reset",
"after-second-startup-after-reset",
"after-transcript-append",
"after-sessions-delete",
"after-shared-first-delete",
"after-shared-final-delete",
"after-final-doctor-inspect",
]);
const startupImportCheckpoint = report.checkpoints.find(
(checkpoint) => checkpoint.label === "after-startup-import",
);
expect(
startupImportCheckpoint?.archiveArtifacts.some(
(artifact) =>
artifact.path.includes("old-orphan.deleted.jsonl") &&
artifact.textTail?.includes("old-orphan") === true,
),
).toBe(true);
expect(report.rollbackRestore).toMatchObject({
archivedBeforeRestore: true,
failedManifestIssueCode: "e2e_forced_post_archive_failure",
sourceRestored: true,
sqliteStillExists: true,
});
expect(report.rollbackRestore?.manifestPath).toContain("session-sqlite-migration-runs");
expect(
report.rollbackRestore?.restoredFiles.some((filePath) =>
filePath.endsWith("/sqlite-rollback-restore.jsonl"),
),
).toBe(true);
expect(
report.rollbackRestore?.idempotentRestoreSkippedFiles.some((filePath) =>
filePath.endsWith("/sqlite-rollback-restore.jsonl"),
),
).toBe(true);
expect(report.scaleMigration).toMatchObject({
minTranscriptEventsPerSession: 4,
seededEvents: 96,
seededSessions: 24,
});
expect(report.scaleMigration?.importedSessionKeys).toHaveLength(24);
expect(report.scaleMigration?.startupImportElapsedMs).toBeGreaterThanOrEqual(0);
expect(
report.checkpoints.some(
(checkpoint) =>
checkpoint.label === "after-full-agent-turn" &&
checkpoint.sqlite.trackedEntries.some(
(entry) =>
entry.sessionKey === report.fullTurnSessionKey &&
entry.transcriptEvents >= 2 &&
entry.trajectoryEvents >= 1,
),
),
).toBe(true);
expect(report.manualCompaction).toMatchObject({
checkpointCount: 1,
compacted: true,
sessionKey: report.manualCompactionSessionKey,
});
expect(report.manualCompaction?.transcriptIdentity).toBe(report.manualCompactionSessionKey);
expect(report.manualCompaction?.rowCountBefore).toBeGreaterThanOrEqual(2);
expect(report.manualCompaction?.rowCountAfter).toBeGreaterThanOrEqual(1);
expect(
report.checkpoints.some(
(checkpoint) =>
checkpoint.label === "after-manual-compaction" &&
checkpoint.activeJsonl.length === 0 &&
checkpoint.sqlite.trackedEntries.some(
(entry) =>
entry.sessionKey === report.manualCompactionSessionKey &&
Array.isArray(entry.entry?.compactionCheckpoints) &&
entry.entry.compactionCheckpoints.length >= 1,
),
),
).toBe(true);
expect(report.pluginSdkConsumer).toMatchObject({
activeTrajectoryPointerForSessionExists: false,
activeTrajectoryRuntimeSidecarForSessionExists: false,
activeTrajectorySessionSidecarForSessionExists: false,
});
expect(report.pluginSdkConsumer?.sessionIdentity).toBe(report.pluginSdkSessionKey);
expect(report.pluginSdkConsumer?.listedSessionKeys).toContain(report.pluginSdkSessionKey);
expect(report.pluginSdkConsumer?.transcriptEventsAfterAppend).toBeGreaterThan(
report.pluginSdkConsumer?.transcriptEventsBeforeAppend ?? 0,
);
expect(
report.checkpoints.some(
(checkpoint) =>
checkpoint.label === "after-plugin-sdk-consumer" &&
checkpoint.sqlite.trajectoryRuntimeEvents >= 1 &&
checkpoint.sqlite.trackedEntries.some(
(entry) =>
entry.sessionKey === report.pluginSdkSessionKey &&
entry.trajectoryEvents >= 1 &&
entry.transcriptEvents >= 3,
),
),
).toBe(true);
expect(report.downgradeReupgrade).toMatchObject({
activeJsonlArchived: true,
doctorImportedEntries: 1,
doctorImportedTranscriptEvents: 2,
sessionId: "sqlite-downgrade-reupgrade",
sessionKey: "agent:main:dashboard:sqlite-downgrade-reupgrade",
trajectoryPointerArchived: true,
trajectoryPointerSourceRemoved: true,
trajectorySidecarArchived: true,
trajectorySidecarSourceRemoved: true,
transcriptEvents: 2,
});
const downgradeCheckpoint = report.checkpoints.find(
(checkpoint) => checkpoint.label === "after-downgrade-reupgrade-import",
);
expect(
downgradeCheckpoint?.archiveArtifacts.some(
(artifact) =>
artifact.path.includes("sqlite-downgrade-reupgrade.trajectory.jsonl") &&
artifact.textTail?.includes("trajectory") === true,
),
).toBe(true);
expect(
downgradeCheckpoint?.archiveArtifacts.some((artifact) =>
artifact.path.includes("sqlite-downgrade-reupgrade.trajectory-path.json"),
),
).toBe(true);
expect(
report.checkpoints.some(
(checkpoint) =>
checkpoint.label === "after-downgrade-reupgrade-import" &&
checkpoint.sqlite.trackedEntries.some(
(entry) =>
entry.sessionKey === "agent:main:dashboard:sqlite-downgrade-reupgrade" &&
entry.transcriptEvents === 2,
),
),
).toBe(true);
expect(report.busyContention).toMatchObject({
childExitCode: 0,
childSignal: null,
holdMs: 500,
sessionId: "sqlite-busy-contention",
sessionKey: "agent:main:dashboard:sqlite-busy-contention",
transcriptEvents: 2,
});
expect(report.busyContention?.elapsedMs).toBeGreaterThanOrEqual(250);
expect(report.secondStartupAfterReset).toMatchObject({
activeJsonlForSessionExists: false,
historyContainsPostResetAppend: true,
sessionKey: report.resetSessionKey,
});
expect(report.secondStartupAfterReset?.transcriptEvents).toBeGreaterThanOrEqual(1);
expect(
report.checkpoints.some(
(checkpoint) =>
checkpoint.label === "after-transcript-append" &&
checkpoint.sqlite.trackedEntries.some(
(entry) => entry.sessionKey === report.resetSessionKey && entry.transcriptEvents >= 1,
),
),
).toBe(true);
const deleteCheckpoint = report.checkpoints.find(
(checkpoint) => checkpoint.label === "after-sessions-delete",
);
const deleteArchive = deleteCheckpoint?.archiveArtifacts.find(
(artifact) =>
artifact.archiveReason === "deleted" &&
artifact.archiveSessionId === "sqlite-delete-session",
);
expect(deleteArchive?.messageTexts).toContain("delete me");
const sharedFinalCheckpoint = report.checkpoints.find(
(checkpoint) => checkpoint.label === "after-shared-final-delete",
);
const sharedFinalArchive = sharedFinalCheckpoint?.archiveArtifacts.find(
(artifact) =>
artifact.archiveReason === "deleted" &&
artifact.archiveSessionId === "sqlite-shared-session",
);
const retainedSharedImportSources = sharedFinalCheckpoint?.archiveArtifacts.filter(
(artifact) =>
artifact.path.includes("session-sqlite-import-archive") &&
(artifact.path.includes("sqlite-shared-a.jsonl") ||
artifact.path.includes("sqlite-shared-b.jsonl")),
);
expect(
sharedFinalArchive?.messageTexts?.includes("shared") ||
(retainedSharedImportSources?.length === 2 &&
retainedSharedImportSources.every((artifact) =>
artifact.messageTexts?.some((text) => text.includes("shared")),
)),
).toBe(true);
expect(
report.checkpoints.some(
(checkpoint) =>
checkpoint.label === "after-shared-first-delete" &&
checkpoint.sqlite.trackedEntries.some(
(entry) => entry.sessionKey === report.sharedSessionKeys[1],
),
),
).toBe(true);
expect(
report.checkpoints.some(
(checkpoint) =>
checkpoint.label === "after-shared-final-delete" &&
checkpoint.archiveArtifacts.length > 0,
),
).toBe(true);
}, 180_000);
});