mirror of
https://github.com/Nezumi-2711/9router.git
synced 2026-09-22 13:38:31 +00:00
46e6c01a01
On the translated OpenAI->Claude path, adjustMaxTokens capped max_tokens before applyThinking set thinking.budget_tokens, so max-effort budget (128000) could exceed a 64k-clamped max_tokens -> Anthropic 400. prepareClaudeRequest now reconciles after the budget is known: prefer raising max_tokens, only shrink budget when it meets/exceeds the ceiling. Also lift the global 64000 cap: the ceiling is now the model's real maxOutput, so high-output models (fable/mythos, opus-4.8/sonnet-4.6) get their full budget. adjustMaxTokens gains an optional ceiling arg (default unchanged, callers untouched); openai-to-claude passes the model maxOutput. Native Claude Code passthrough is unaffected. Co-Authored-By: Claude <noreply@anthropic.com> Co-authored-by: Cursor <cursoragent@cursor.com>
35 lines
1.3 KiB
JavaScript
35 lines
1.3 KiB
JavaScript
import { DEFAULT_MAX_TOKENS, DEFAULT_MIN_TOKENS } from "../../config/runtimeConfig.js";
|
|
|
|
/**
|
|
* Adjust max_tokens based on request context
|
|
* @param {object} body - Request body
|
|
* @param {number} [ceiling=DEFAULT_MAX_TOKENS] - Upper bound for max_tokens.
|
|
* Callers with model context (e.g. openai-to-claude) pass the model's real
|
|
* maxOutput so high-output models (Opus 4.8 = 128000) aren't pre-clamped to
|
|
* the conservative 64000 default before the model-aware step sees them.
|
|
* @returns {number} Adjusted max_tokens
|
|
*/
|
|
export function adjustMaxTokens(body, ceiling = DEFAULT_MAX_TOKENS) {
|
|
let maxTokens = body.max_tokens || DEFAULT_MAX_TOKENS;
|
|
|
|
// Auto-increase for tool calling to prevent truncated arguments (min never above max)
|
|
if (body.tools && Array.isArray(body.tools) && body.tools.length > 0) {
|
|
if (maxTokens < DEFAULT_MIN_TOKENS) {
|
|
maxTokens = DEFAULT_MIN_TOKENS;
|
|
}
|
|
}
|
|
|
|
// Ensure max_tokens > thinking.budget_tokens (Claude API requirement)
|
|
// Claude API requires strictly greater, so add buffer instead of using the
|
|
// ceiling which could equal budget_tokens when budget_tokens >= ceiling
|
|
if (body.thinking?.budget_tokens && maxTokens <= body.thinking.budget_tokens) {
|
|
maxTokens = body.thinking.budget_tokens + 1024;
|
|
}
|
|
|
|
// Never exceed the ceiling
|
|
if (maxTokens > ceiling) maxTokens = ceiling;
|
|
|
|
return maxTokens;
|
|
}
|
|
|