mirror of
https://github.com/openclaw/openclaw.git
synced 2026-07-15 10:06:03 +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>
253 lines
7.3 KiB
TypeScript
253 lines
7.3 KiB
TypeScript
// Session Log Mentions tests cover session log mentions script behavior.
|
|
import { mkdtempSync, rmSync } from "node:fs";
|
|
import fs from "node:fs/promises";
|
|
import { tmpdir } from "node:os";
|
|
import path from "node:path";
|
|
import { DatabaseSync } from "node:sqlite";
|
|
import { afterEach, describe, expect, it } from "vitest";
|
|
import {
|
|
countSessionLogMentions,
|
|
readSessionLogMentionLimits,
|
|
} from "../../scripts/e2e/lib/session-log-mentions.ts";
|
|
|
|
const tempRoots: string[] = [];
|
|
|
|
function makeTempRoot() {
|
|
const root = mkdtempSync(path.join(tmpdir(), "openclaw-session-log-mentions-"));
|
|
tempRoots.push(root);
|
|
return root;
|
|
}
|
|
|
|
afterEach(() => {
|
|
for (const root of tempRoots.splice(0)) {
|
|
rmSync(root, { force: true, recursive: true });
|
|
}
|
|
});
|
|
|
|
describe("session log mention scanner", () => {
|
|
it("counts mentions across bounded session logs", async () => {
|
|
const root = makeTempRoot();
|
|
await fs.writeFile(path.join(root, "one.jsonl"), "API.read MCP.fixture API.read\n");
|
|
await fs.writeFile(path.join(root, "two.jsonl"), "MCP.fixture\n");
|
|
await fs.writeFile(path.join(root, "ignored.txt"), "API.read\n");
|
|
|
|
await expect(
|
|
countSessionLogMentions({
|
|
sessionsDir: root,
|
|
needles: {
|
|
apiFileRead: "API.read",
|
|
mcpNamespace: "MCP.fixture",
|
|
},
|
|
}),
|
|
).resolves.toEqual({
|
|
apiFileRead: 2,
|
|
mcpNamespace: 2,
|
|
});
|
|
});
|
|
|
|
it("does not count user prompt lines as runtime mention proof", async () => {
|
|
const root = makeTempRoot();
|
|
await fs.writeFile(
|
|
path.join(root, "prompts.jsonl"),
|
|
[
|
|
JSON.stringify({
|
|
role: "user",
|
|
content: 'Use API.read("mcp/index.d.ts") and MCP.fixture.lookupNote.',
|
|
}),
|
|
JSON.stringify({
|
|
message: {
|
|
role: "user",
|
|
content: "Call fixture__lookup_note.",
|
|
},
|
|
}),
|
|
JSON.stringify({
|
|
role: "assistant",
|
|
content: 'API.read MCP.fixture fixture__lookup_note tools.search("lookup note")',
|
|
}),
|
|
"raw transcript fallback API.read",
|
|
"",
|
|
].join("\n"),
|
|
);
|
|
|
|
await expect(
|
|
countSessionLogMentions({
|
|
sessionsDir: root,
|
|
needles: {
|
|
apiFileRead: "API.read",
|
|
mcpNamespace: "MCP.fixture",
|
|
mcpTool: "fixture__lookup_note",
|
|
toolSearchPollution: 'tools.search("lookup note"',
|
|
},
|
|
}),
|
|
).resolves.toEqual({
|
|
apiFileRead: 2,
|
|
mcpNamespace: 1,
|
|
mcpTool: 1,
|
|
toolSearchPollution: 1,
|
|
});
|
|
});
|
|
|
|
it("counts mentions from SQLite transcript rows", async () => {
|
|
const root = makeTempRoot();
|
|
const sessionsDir = path.join(root, "agents", "main", "sessions");
|
|
const sqlitePath = path.join(root, "agents", "main", "agent", "openclaw-agent.sqlite");
|
|
await fs.mkdir(path.dirname(sqlitePath), { recursive: true });
|
|
const db = new DatabaseSync(sqlitePath);
|
|
try {
|
|
db.exec(`
|
|
CREATE TABLE transcript_events (
|
|
session_id TEXT NOT NULL,
|
|
seq INTEGER NOT NULL,
|
|
event_json TEXT NOT NULL,
|
|
created_at INTEGER NOT NULL,
|
|
PRIMARY KEY (session_id, seq)
|
|
);
|
|
`);
|
|
const insert = db.prepare(
|
|
"INSERT INTO transcript_events (session_id, seq, event_json, created_at) VALUES (?, ?, ?, ?)",
|
|
);
|
|
insert.run(
|
|
"sqlite-session",
|
|
1,
|
|
JSON.stringify({
|
|
message: {
|
|
role: "user",
|
|
content: "Use API.read and MCP.fixture from the prompt.",
|
|
},
|
|
}),
|
|
1,
|
|
);
|
|
insert.run(
|
|
"sqlite-session",
|
|
2,
|
|
JSON.stringify({
|
|
message: {
|
|
role: "assistant",
|
|
content: 'API.read MCP.fixture fixture__lookup_note tools.search("lookup note")',
|
|
},
|
|
}),
|
|
2,
|
|
);
|
|
} finally {
|
|
db.close();
|
|
}
|
|
|
|
await expect(
|
|
countSessionLogMentions({
|
|
sessionsDir,
|
|
needles: {
|
|
apiFileRead: "API.read",
|
|
mcpNamespace: "MCP.fixture",
|
|
mcpTool: "fixture__lookup_note",
|
|
toolSearchPollution: 'tools.search("lookup note"',
|
|
},
|
|
}),
|
|
).resolves.toEqual({
|
|
apiFileRead: 1,
|
|
mcpNamespace: 1,
|
|
mcpTool: 1,
|
|
toolSearchPollution: 1,
|
|
});
|
|
});
|
|
|
|
it("rejects oversized SQLite transcript rows before counting them", async () => {
|
|
const root = makeTempRoot();
|
|
const sessionsDir = path.join(root, "agents", "main", "sessions");
|
|
const sqlitePath = path.join(root, "agents", "main", "agent", "openclaw-agent.sqlite");
|
|
await fs.mkdir(path.dirname(sqlitePath), { recursive: true });
|
|
const db = new DatabaseSync(sqlitePath);
|
|
try {
|
|
db.exec(`
|
|
CREATE TABLE transcript_events (
|
|
session_id TEXT NOT NULL,
|
|
seq INTEGER NOT NULL,
|
|
event_json TEXT NOT NULL,
|
|
created_at INTEGER NOT NULL,
|
|
PRIMARY KEY (session_id, seq)
|
|
);
|
|
`);
|
|
db.prepare(
|
|
"INSERT INTO transcript_events (session_id, seq, event_json, created_at) VALUES (?, ?, ?, ?)",
|
|
).run("sqlite-session", 1, "API.read ".repeat(16), 1);
|
|
} finally {
|
|
db.close();
|
|
}
|
|
|
|
await expect(
|
|
countSessionLogMentions({
|
|
limits: { fileMaxBytes: 32, totalMaxBytes: 1024 },
|
|
sessionsDir,
|
|
needles: {
|
|
apiFileRead: "API.read",
|
|
},
|
|
}),
|
|
).rejects.toMatchObject({
|
|
code: "ETOOBIG",
|
|
message: expect.stringContaining("per-file limit"),
|
|
});
|
|
});
|
|
|
|
it("returns zero counts when the sessions directory is absent", async () => {
|
|
await expect(
|
|
countSessionLogMentions({
|
|
sessionsDir: path.join(makeTempRoot(), "missing"),
|
|
needles: {
|
|
apiFileRead: "API.read",
|
|
},
|
|
}),
|
|
).resolves.toEqual({
|
|
apiFileRead: 0,
|
|
});
|
|
});
|
|
|
|
it("rejects oversized session log files before loading them", async () => {
|
|
const root = makeTempRoot();
|
|
await fs.writeFile(path.join(root, "huge.jsonl"), "x".repeat(64));
|
|
|
|
await expect(
|
|
countSessionLogMentions({
|
|
limits: { fileMaxBytes: 32, totalMaxBytes: 1024 },
|
|
sessionsDir: root,
|
|
needles: {
|
|
apiFileRead: "API.read",
|
|
},
|
|
}),
|
|
).rejects.toMatchObject({
|
|
code: "ETOOBIG",
|
|
message: expect.stringContaining("per-file limit"),
|
|
});
|
|
});
|
|
|
|
it("rejects aggregate session log scans that exceed the total ceiling", async () => {
|
|
const root = makeTempRoot();
|
|
await fs.writeFile(path.join(root, "one.jsonl"), "x".repeat(24));
|
|
await fs.writeFile(path.join(root, "two.jsonl"), "x".repeat(24));
|
|
|
|
await expect(
|
|
countSessionLogMentions({
|
|
limits: { fileMaxBytes: 64, totalMaxBytes: 32 },
|
|
sessionsDir: root,
|
|
needles: {
|
|
apiFileRead: "API.read",
|
|
},
|
|
}),
|
|
).rejects.toMatchObject({
|
|
code: "ETOOBIG",
|
|
message: expect.stringContaining("total limit"),
|
|
});
|
|
});
|
|
|
|
it("rejects loose numeric env limits instead of parsing prefixes", () => {
|
|
expect(() =>
|
|
readSessionLogMentionLimits({
|
|
OPENCLAW_SESSION_LOG_MENTION_FILE_MAX_BYTES: "1e3",
|
|
}),
|
|
).toThrow("invalid OPENCLAW_SESSION_LOG_MENTION_FILE_MAX_BYTES: 1e3");
|
|
expect(() =>
|
|
readSessionLogMentionLimits({
|
|
OPENCLAW_SESSION_LOG_MENTION_TOTAL_MAX_BYTES: "1000ms",
|
|
}),
|
|
).toThrow("invalid OPENCLAW_SESSION_LOG_MENTION_TOTAL_MAX_BYTES: 1000ms");
|
|
});
|
|
});
|