fix: prevent full message history from being sent to container agents
When lastAgentTimestamp was missing (new group, corrupted state, or startup recovery), the empty-string fallback caused getMessagesSince to return up to 200 messages — the entire group history. This sent a massive prompt to the container agent instead of just recent messages. Fix: recover the cursor from the last bot reply timestamp in the DB (proof of what we already processed), and cap all prompt queries to a configurable MAX_MESSAGES_PER_PROMPT (default 10). Covers all three call sites: processGroupMessages, the piping path, and recoverPendingMessages. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -53,6 +53,10 @@ export const CONTAINER_MAX_OUTPUT_SIZE = parseInt(
|
||||
); // 10MB default
|
||||
export const ONECLI_URL =
|
||||
process.env.ONECLI_URL || envConfig.ONECLI_URL || 'http://localhost:10254';
|
||||
export const MAX_MESSAGES_PER_PROMPT = Math.max(
|
||||
1,
|
||||
parseInt(process.env.MAX_MESSAGES_PER_PROMPT || '10', 10) || 10,
|
||||
);
|
||||
export const IPC_POLL_INTERVAL = 1000;
|
||||
export const IDLE_TIMEOUT = parseInt(process.env.IDLE_TIMEOUT || '1800000', 10); // 30min default — how long to keep container alive after last result
|
||||
export const MAX_CONCURRENT_CONTAINERS = Math.max(
|
||||
|
||||
Reference in New Issue
Block a user