asepharyana
16becd5340
- pickBatchWithinBudget: stop di overflow pertama (break), bukan skip — batch tetap prefix kronologis tanpa gap analisis di tengah timeline. Diekstrak ke batchBudget.ts (pure, estimator di-inject) + regression test. - callModerationLLM: param opsional maxTokens; text/media caller menghitung ceiling dari estimasi prompt (floor 2048, cap 16384) — batch kecil tak lagi reserve window completion 16k. - getPending/IncompleteMessagesByConversation: sort hasil UPDATE..RETURNING by created_at ASC — Postgres tak menjamin urutan, konsumen (anchor konteks messages[0], prefix batch) bergantung pada urutan kronologis.
46 lines
1.5 KiB
TypeScript
46 lines
1.5 KiB
TypeScript
/**
|
|
* batchBudget.ts
|
|
*
|
|
* Pure batch-sizing helper extracted from batchProcessor.ts so it can be
|
|
* unit-tested without pulling in the Piscina worker pool, message store,
|
|
* or any other side-effectful import chain.
|
|
*/
|
|
import type { MessageRecord } from "../message-capture/types.js";
|
|
|
|
/** Token estimator contract (satisfied by conversationContext.estimateTokens). */
|
|
export type TokenEstimator = (text: string) => number;
|
|
|
|
/**
|
|
* Picks a batch of messages within a token budget.
|
|
* `tokensPerMessage` accounts for JSON structure overhead around each entry.
|
|
* The estimator is injected so this stays a pure function — callers in the
|
|
* batch pipeline pass the tiktoken-based estimateTokens.
|
|
*/
|
|
export function pickBatchWithinBudget(
|
|
messages: MessageRecord[],
|
|
maxTokens: number,
|
|
tokensPerMessage: number,
|
|
estimateTokens: TokenEstimator,
|
|
): MessageRecord[] {
|
|
const batch: MessageRecord[] = [];
|
|
let usedTokens = 0;
|
|
|
|
for (const msg of messages) {
|
|
const content = msg.edited_content ?? msg.content;
|
|
const msgTokens = estimateTokens(content) + tokensPerMessage;
|
|
|
|
// Stop at the first overflow instead of skipping: input is ordered
|
|
// created_at ASC, so a contiguous chronological prefix keeps the batch
|
|
// gap-free. Skipped-over messages would leave unanalyzed holes mid-
|
|
// timeline; anything past the budget is picked up by the next wave
|
|
// (processBatch always re-schedules after success).
|
|
if (usedTokens + msgTokens > maxTokens) {
|
|
break;
|
|
}
|
|
batch.push(msg);
|
|
usedTokens += msgTokens;
|
|
}
|
|
|
|
return batch;
|
|
}
|