Files
openclaw/src/gateway/server-methods/chat-transcript-inject.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

161 lines
5.5 KiB
TypeScript

// Chat transcript injection appends gateway-authored assistant rows while
// preserving agent-session parent links and transcript update notifications.
import type { SessionManager } from "../../agents/sessions/session-manager.js";
import { persistSessionTranscriptTurn } from "../../config/sessions/session-accessor.js";
import type { OpenClawConfig } from "../../config/types.openclaw.js";
import { formatErrorMessage } from "../../infra/errors.js";
type AppendMessageArg = Parameters<SessionManager["appendMessage"]>[0];
/** Metadata persisted on gateway-injected assistant messages that mark a stopped run. */
export type GatewayInjectedAbortMeta = {
aborted: true;
origin: "rpc" | "stop-command";
runId: string;
};
/** Result shape returned after appending an assistant row to a session transcript. */
export type GatewayInjectedTranscriptAppendResult = {
ok: boolean;
messageId?: string;
message?: Record<string, unknown>;
error?: string;
};
/** Hash marker used to dedupe companion TTS text/audio supplements. */
export type GatewayInjectedTtsSupplementMarker = {
textSha256: string;
};
function resolveInjectedAssistantContent(params: {
message: string;
label?: string;
content?: Array<Record<string, unknown>>;
}): Array<Record<string, unknown>> {
const labelPrefix = params.label ? `[${params.label}]\n\n` : "";
// Preserve rich content arrays when callers already prepared media blocks;
// only the first text block is rewritten so block ordering stays intact.
if (params.content && params.content.length > 0) {
if (!labelPrefix) {
return params.content;
}
const first = params.content[0];
if (
first &&
typeof first === "object" &&
first.type === "text" &&
typeof first.text === "string"
) {
return [{ ...first, text: `${labelPrefix}${first.text}` }, ...params.content.slice(1)];
}
return [{ type: "text", text: labelPrefix.trim() }, ...params.content];
}
return [{ type: "text", text: `${labelPrefix}${params.message}` }];
}
/** Append a gateway-authored assistant message while preserving transcript parent links. */
export async function appendInjectedAssistantMessageToTranscript(params: {
transcriptPath?: string;
storePath?: string;
sessionId?: string;
sessionKey?: string;
agentId?: string;
message: string;
label?: string;
/** When set, used as the assistant `content` array (e.g. text + embedded audio blocks). */
content?: Array<Record<string, unknown>>;
idempotencyKey?: string;
abortMeta?: GatewayInjectedAbortMeta;
ttsSupplement?: GatewayInjectedTtsSupplementMarker;
now?: number;
config?: OpenClawConfig;
}): Promise<GatewayInjectedTranscriptAppendResult> {
const now = params.now ?? Date.now();
const usage = {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
totalTokens: 0,
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
total: 0,
},
};
const resolvedContent = resolveInjectedAssistantContent({
message: params.message,
label: params.label,
content: params.content,
});
const messageBody: AppendMessageArg & Record<string, unknown> = {
role: "assistant",
// Gateway-injected assistant messages can include non-model content blocks (e.g. embedded TTS audio).
content: resolvedContent as unknown as Extract<
AppendMessageArg,
{ role: "assistant" }
>["content"],
timestamp: now,
// stopReason is a strict runner enum; this is not model output, but we still store it as a
// normal assistant message so it participates in the session parentId chain.
stopReason: "stop",
usage,
// Make these explicit so downstream tooling never treats this as model output.
api: "openai-responses",
provider: "openclaw",
model: "gateway-injected",
...(params.idempotencyKey ? { idempotencyKey: params.idempotencyKey } : {}),
...(params.ttsSupplement ? { openclawTtsSupplement: params.ttsSupplement } : {}),
...(params.abortMeta
? {
openclawAbort: {
aborted: true,
origin: params.abortMeta.origin,
runId: params.abortMeta.runId,
},
}
: {}),
};
try {
if (!params.transcriptPath && (!params.storePath || !params.sessionId || !params.sessionKey)) {
return { ok: false, error: "transcript identity not resolved" };
}
const turn = await persistSessionTranscriptTurn(
{
sessionKey: params.sessionKey ?? "",
...(params.transcriptPath ? { sessionFile: params.transcriptPath } : {}),
...(params.storePath ? { storePath: params.storePath } : {}),
...(params.sessionId ? { sessionId: params.sessionId } : {}),
...(params.agentId ? { agentId: params.agentId } : {}),
},
{
updateMode: "inline",
touchSessionEntry: Boolean(params.storePath && params.sessionId && params.sessionKey),
...(params.config ? { config: params.config } : {}),
messages: [
{
message: messageBody,
idempotencyLookup: "scan-assistant",
now,
useRawWhenLinear: true,
},
],
},
);
const appended = turn.messages[0];
if (!appended) {
return { ok: false, error: "gateway-injected assistant message was not appended" };
}
return {
ok: true,
messageId: appended.messageId,
message: appended.message as Record<string, unknown>,
};
} catch (err) {
return { ok: false, error: formatErrorMessage(err) };
}
}