mirror of
https://github.com/openclaw/openclaw.git
synced 2026-07-14 10:16:14 +00:00
* 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>
149 lines
5.0 KiB
TypeScript
149 lines
5.0 KiB
TypeScript
// Builds the SQLite sessions/transcripts schema baseline used by CI drift checks.
|
|
import { createHash } from "node:crypto";
|
|
import fs from "node:fs/promises";
|
|
import path from "node:path";
|
|
|
|
/** Rendered baseline artifact for the sessions/transcripts SQLite schema. */
|
|
export type SqliteSessionSchemaBaselineRender = {
|
|
/** Normalized SQL for the session, conversation, and transcript schema objects. */
|
|
sql: string;
|
|
};
|
|
|
|
/** Result returned after writing or checking SQLite schema baseline artifacts. */
|
|
export type SqliteSessionSchemaBaselineWriteResult = {
|
|
/** True when generated artifact content differs from disk. */
|
|
changed: boolean;
|
|
/** True when changed artifacts were actually written. */
|
|
wrote: boolean;
|
|
/** Local inspection SQL artifact path. */
|
|
sqlPath: string;
|
|
/** SHA-256 hash artifact path. */
|
|
hashPath: string;
|
|
};
|
|
|
|
const DEFAULT_SCHEMA_INPUT = "src/state/openclaw-agent-schema.sql";
|
|
const DEFAULT_SQL_OUTPUT = ".artifacts/sqlite-session-transcript-schema-baseline.sql";
|
|
const DEFAULT_HASH_OUTPUT = "docs/.generated/sqlite-session-transcript-schema-baseline.sha256";
|
|
|
|
const TARGET_TABLES = new Set([
|
|
"sessions",
|
|
"session_routes",
|
|
"conversations",
|
|
"session_conversations",
|
|
"session_entries",
|
|
"transcript_events",
|
|
"transcript_event_identities",
|
|
]);
|
|
|
|
function sha256(value: string): string {
|
|
return createHash("sha256").update(value).digest("hex");
|
|
}
|
|
|
|
function normalizeIdentifier(value: string): string {
|
|
return value.replace(/^"|"$/g, "").toLowerCase();
|
|
}
|
|
|
|
function splitSqlStatements(sourceSql: string): string[] {
|
|
return sourceSql
|
|
.split(/;\s*(?:\r?\n|$)/u)
|
|
.map((statement) => statement.trim())
|
|
.filter(Boolean);
|
|
}
|
|
|
|
function normalizeStatement(statement: string): string {
|
|
const lines = statement
|
|
.split(/\r?\n/u)
|
|
.map((line) => line.trimEnd())
|
|
.filter((line, index, allLines) => line.trim() !== "" || index < allLines.length - 1);
|
|
return `${lines.join("\n")};`;
|
|
}
|
|
|
|
function readCreatedTableName(statement: string): string | null {
|
|
const match = statement.match(
|
|
/^CREATE\s+TABLE\s+IF\s+NOT\s+EXISTS\s+("[^"]+"|[A-Za-z_][A-Za-z0-9_]*)\b/iu,
|
|
);
|
|
return match ? normalizeIdentifier(match[1]) : null;
|
|
}
|
|
|
|
function readIndexedTableName(statement: string): string | null {
|
|
const match = statement.match(
|
|
/^CREATE\s+(?:UNIQUE\s+)?INDEX\s+IF\s+NOT\s+EXISTS\s+("[^"]+"|[A-Za-z_][A-Za-z0-9_]*)\s+ON\s+("[^"]+"|[A-Za-z_][A-Za-z0-9_]*)\b/isu,
|
|
);
|
|
return match ? normalizeIdentifier(match[2]) : null;
|
|
}
|
|
|
|
function isTargetSessionSchemaStatement(statement: string): boolean {
|
|
const tableName = readCreatedTableName(statement);
|
|
if (tableName) {
|
|
return TARGET_TABLES.has(tableName);
|
|
}
|
|
|
|
const indexedTableName = readIndexedTableName(statement);
|
|
return indexedTableName ? TARGET_TABLES.has(indexedTableName) : false;
|
|
}
|
|
|
|
/** Render the normalized sessions/transcripts SQLite schema baseline. */
|
|
export function renderSqliteSessionSchemaBaseline(
|
|
agentSchemaSql: string,
|
|
): SqliteSessionSchemaBaselineRender {
|
|
const statements = splitSqlStatements(agentSchemaSql)
|
|
.filter(isTargetSessionSchemaStatement)
|
|
.map(normalizeStatement);
|
|
|
|
return {
|
|
sql: `${statements.join("\n\n")}\n`,
|
|
};
|
|
}
|
|
|
|
/** Build the sha256 hash file content for the sessions/transcripts SQLite schema baseline. */
|
|
export function computeSqliteSessionSchemaBaselineHashFileContent(
|
|
rendered: SqliteSessionSchemaBaselineRender,
|
|
): string {
|
|
return `${sha256(rendered.sql)} sqlite-session-transcript-schema-baseline.sql\n`;
|
|
}
|
|
|
|
async function readIfExists(filePath: string): Promise<string | null> {
|
|
try {
|
|
return await fs.readFile(filePath, "utf8");
|
|
} catch (error) {
|
|
if (error && typeof error === "object" && "code" in error && error.code === "ENOENT") {
|
|
return null;
|
|
}
|
|
throw error;
|
|
}
|
|
}
|
|
|
|
/** Write or check SQLite sessions/transcripts schema baseline artifacts. */
|
|
export async function writeSqliteSessionSchemaBaselineArtifacts(params: {
|
|
repoRoot: string;
|
|
check: boolean;
|
|
schemaInputPath?: string;
|
|
sqlOutputPath?: string;
|
|
hashOutputPath?: string;
|
|
}): Promise<SqliteSessionSchemaBaselineWriteResult> {
|
|
const schemaPath = path.resolve(params.repoRoot, params.schemaInputPath ?? DEFAULT_SCHEMA_INPUT);
|
|
const sqlPath = path.resolve(params.repoRoot, params.sqlOutputPath ?? DEFAULT_SQL_OUTPUT);
|
|
const hashPath = path.resolve(params.repoRoot, params.hashOutputPath ?? DEFAULT_HASH_OUTPUT);
|
|
const sourceSql = await fs.readFile(schemaPath, "utf8");
|
|
const rendered = renderSqliteSessionSchemaBaseline(sourceSql);
|
|
const hash = computeSqliteSessionSchemaBaselineHashFileContent(rendered);
|
|
const existingHash = await readIfExists(hashPath);
|
|
const existingSql = await readIfExists(sqlPath);
|
|
const changed = params.check
|
|
? existingHash !== hash
|
|
: existingHash !== hash || existingSql !== rendered.sql;
|
|
|
|
if (!params.check && changed) {
|
|
await fs.mkdir(path.dirname(sqlPath), { recursive: true });
|
|
await fs.writeFile(sqlPath, rendered.sql);
|
|
await fs.writeFile(hashPath, hash);
|
|
}
|
|
|
|
return {
|
|
changed,
|
|
wrote: !params.check && changed,
|
|
sqlPath,
|
|
hashPath,
|
|
};
|
|
}
|