mirror of
https://github.com/openclaw/openclaw.git
synced 2026-03-14 19:40:40 +00:00
* fix: enforce embedding model token limit to prevent 8192 overflow - Replace EMBEDDING_APPROX_CHARS_PER_TOKEN=1 with UTF-8 byte length estimation (safe upper bound for tokenizer output) - Add EMBEDDING_MODEL_MAX_TOKENS=8192 hard cap - Add splitChunkToTokenLimit() that binary-searches for the largest safe split point, with surrogate pair handling - Add enforceChunkTokenLimit() wrapper called in indexFile() after chunkMarkdown(), before any embedding API call - Fixes: session files with large JSONL entries could produce chunks exceeding text-embedding-3-small's 8192 token limit Tests: 2 new colocated tests in manager.embedding-token-limit.test.ts - Verifies oversized ASCII chunks are split to <=8192 bytes each - Verifies multibyte (emoji) content batching respects byte limits * fix: make embedding token limit provider-aware - Add optional maxInputTokens to EmbeddingProvider interface - Each provider (openai, gemini, voyage) reports its own limit - Known-limits map as fallback: openai 8192, gemini 2048, voyage 32K - Resolution: provider field > known map > default 8192 - Backward compatible: local/llama uses fallback * fix: enforce embedding input size limits (#13455) (thanks @rodrigouroz) --------- Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
31 lines
894 B
TypeScript
31 lines
894 B
TypeScript
import type { EmbeddingProvider } from "./embeddings.js";
|
|
import { estimateUtf8Bytes, splitTextToUtf8ByteLimit } from "./embedding-input-limits.js";
|
|
import { resolveEmbeddingMaxInputTokens } from "./embedding-model-limits.js";
|
|
import { hashText, type MemoryChunk } from "./internal.js";
|
|
|
|
export function enforceEmbeddingMaxInputTokens(
|
|
provider: EmbeddingProvider,
|
|
chunks: MemoryChunk[],
|
|
): MemoryChunk[] {
|
|
const maxInputTokens = resolveEmbeddingMaxInputTokens(provider);
|
|
const out: MemoryChunk[] = [];
|
|
|
|
for (const chunk of chunks) {
|
|
if (estimateUtf8Bytes(chunk.text) <= maxInputTokens) {
|
|
out.push(chunk);
|
|
continue;
|
|
}
|
|
|
|
for (const text of splitTextToUtf8ByteLimit(chunk.text, maxInputTokens)) {
|
|
out.push({
|
|
startLine: chunk.startLine,
|
|
endLine: chunk.endLine,
|
|
text,
|
|
hash: hashText(text),
|
|
});
|
|
}
|
|
}
|
|
|
|
return out;
|
|
}
|