mirror of
https://github.com/openclaw/openclaw.git
synced 2026-07-24 19:01:17 +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>
151 lines
5.2 KiB
TypeScript
151 lines
5.2 KiB
TypeScript
/**
|
|
* Reads prior session transcript context for `/btw` side-question handoffs.
|
|
*/
|
|
import { readFile } from "node:fs/promises";
|
|
import {
|
|
resolveSessionFilePath,
|
|
resolveSessionFilePathOptions,
|
|
type SessionEntry as StoredSessionEntry,
|
|
} from "../config/sessions.js";
|
|
import { loadTranscriptEvents } from "../config/sessions/session-accessor.js";
|
|
import { parseSqliteSessionFileMarker } from "../config/sessions/sqlite-marker.js";
|
|
import {
|
|
scanSessionTranscriptTree,
|
|
type SessionTranscriptTree,
|
|
} from "../config/sessions/transcript-tree.js";
|
|
import { diagnosticLogger as diag } from "../logging/diagnostic.js";
|
|
import {
|
|
buildSessionContext,
|
|
migrateSessionEntries,
|
|
parseSessionEntries,
|
|
type SessionEntry as AgentSessionEntry,
|
|
} from "./sessions/session-manager.js";
|
|
|
|
/** Resolves the persisted transcript file for a BTW session handoff. */
|
|
export function resolveBtwSessionTranscriptPath(params: {
|
|
sessionId: string;
|
|
sessionEntry?: StoredSessionEntry;
|
|
sessionKey?: string;
|
|
storePath?: string;
|
|
}): string | undefined {
|
|
try {
|
|
const agentId = params.sessionKey?.split(":")[1];
|
|
const pathOpts = resolveSessionFilePathOptions({
|
|
agentId,
|
|
storePath: params.storePath,
|
|
});
|
|
return resolveSessionFilePath(params.sessionId, params.sessionEntry, pathOpts);
|
|
} catch (error) {
|
|
diag.debug(
|
|
`resolveSessionTranscriptPath failed: sessionId=${params.sessionId} err=${String(error)}`,
|
|
);
|
|
return undefined;
|
|
}
|
|
}
|
|
|
|
// Session entries can come from older transcript formats, so id fields are
|
|
// narrowed at this boundary before branch reconstruction trusts them.
|
|
function readSessionEntryId(entry: AgentSessionEntry): string | undefined {
|
|
const id = (entry as { id?: unknown }).id;
|
|
return typeof id === "string" && id.trim().length > 0 ? id : undefined;
|
|
}
|
|
|
|
// Reconstructs the selected branch from leaf to root. Missing links or cycles
|
|
// mean the snapshot cannot be trusted, so callers fall back to a safe branch.
|
|
function buildSessionBranchEntries(
|
|
tree: SessionTranscriptTree<AgentSessionEntry>,
|
|
leafId: string | null | undefined,
|
|
): AgentSessionEntry[] | undefined {
|
|
if (leafId === null) {
|
|
return [];
|
|
}
|
|
if (!leafId) {
|
|
return undefined;
|
|
}
|
|
const branch: AgentSessionEntry[] = [];
|
|
const seen = new Set<string>();
|
|
let currentId: string | undefined = leafId;
|
|
while (currentId) {
|
|
if (seen.has(currentId)) {
|
|
return undefined;
|
|
}
|
|
seen.add(currentId);
|
|
const node = tree.byId.get(currentId);
|
|
if (!node) {
|
|
return undefined;
|
|
}
|
|
if ((node.entry as { type?: unknown }).type !== "leaf") {
|
|
branch.push(
|
|
node.entry.parentId === node.parentId
|
|
? node.entry
|
|
: ({ ...node.entry, parentId: node.parentId } as AgentSessionEntry),
|
|
);
|
|
}
|
|
currentId = node.parentId ?? undefined;
|
|
}
|
|
return branch.toReversed();
|
|
}
|
|
|
|
function isTrailingUserMessage(entry: AgentSessionEntry | undefined): boolean {
|
|
return (
|
|
entry?.type === "message" &&
|
|
(entry as { message?: { role?: unknown } }).message?.role === "user"
|
|
);
|
|
}
|
|
|
|
/**
|
|
* Reads prior messages for BTW continuation.
|
|
*
|
|
* When a transcript has fork links, this returns the selected snapshot branch
|
|
* instead of the full file so a resumed agent does not inherit sibling-branch
|
|
* messages.
|
|
*/
|
|
export async function readBtwTranscriptMessages(params: {
|
|
sessionFile: string;
|
|
sessionId: string;
|
|
sessionKey?: string;
|
|
snapshotLeafId?: string | null;
|
|
}): Promise<unknown[]> {
|
|
try {
|
|
const marker = parseSqliteSessionFileMarker(params.sessionFile);
|
|
const entries = marker
|
|
? ((await loadTranscriptEvents({
|
|
agentId: marker.agentId,
|
|
sessionId: marker.sessionId,
|
|
...(params.sessionKey ? { sessionKey: params.sessionKey } : {}),
|
|
storePath: marker.storePath,
|
|
})) as AgentSessionEntry[])
|
|
: parseSessionEntries(await readFile(params.sessionFile, "utf-8"));
|
|
migrateSessionEntries(entries);
|
|
const sessionEntries = entries.filter(
|
|
(entry): entry is AgentSessionEntry => entry.type !== "session",
|
|
);
|
|
const tree = scanSessionTranscriptTree(sessionEntries);
|
|
if (!tree.hasLeafUpdate) {
|
|
return buildSessionContext(sessionEntries).messages;
|
|
}
|
|
|
|
const hasSnapshotLeaf = params.snapshotLeafId !== undefined;
|
|
let branchEntries = hasSnapshotLeaf
|
|
? buildSessionBranchEntries(tree, params.snapshotLeafId)
|
|
: undefined;
|
|
if (hasSnapshotLeaf && branchEntries === undefined) {
|
|
diag.debug(
|
|
`btw snapshot leaf unavailable: sessionId=${params.sessionId} leaf=${params.snapshotLeafId}`,
|
|
);
|
|
}
|
|
branchEntries ??= buildSessionBranchEntries(tree, tree.leafId);
|
|
if (!hasSnapshotLeaf && isTrailingUserMessage(branchEntries?.at(-1))) {
|
|
// Auto-selecting the newest branch must not include the current user turn
|
|
// that triggered BTW handoff; the subagent should continue from its parent.
|
|
const trailingId = readSessionEntryId(branchEntries!.at(-1)!);
|
|
const parentId = trailingId ? tree.byId.get(trailingId)?.parentId : null;
|
|
branchEntries = parentId ? (buildSessionBranchEntries(tree, parentId) ?? []) : [];
|
|
}
|
|
const sessionContext = buildSessionContext(branchEntries ?? sessionEntries);
|
|
return Array.isArray(sessionContext.messages) ? sessionContext.messages : [];
|
|
} catch {
|
|
return [];
|
|
}
|
|
}
|