ton/pi_harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(ai): stop defaulting max token request caps

Browse Source 
closes #4675
This commit is contained in:
Mario Zechner
2026-05-19 11:49:44 +02:00
parent 5e8f0cf45e
commit 2787b601d7
6 changed files with 51 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/ai/src/providers/simple-options.ts
+6 -14
View File
@@ -1,19 +1,9 @@
import type { Api, Model, SimpleStreamOptions, StreamOptions, ThinkingBudgets, ThinkingLevel } from "../types.js";
const DEFAULT_MAX_OUTPUT_TOKENS = 32000;
const CONTEXT_WINDOW_OUTPUT_TOLERANCE = 1024;
export function buildBaseOptions(model: Model<Api>, options?: SimpleStreamOptions, apiKey?: string): StreamOptions {
const defaultMaxTokens =
model.maxTokens > 0
? model.maxTokens >= model.contextWindow - CONTEXT_WINDOW_OUTPUT_TOLERANCE
? Math.min(model.maxTokens, DEFAULT_MAX_OUTPUT_TOKENS)
: model.maxTokens
: undefined;
export function buildBaseOptions(_model: Model<Api>, options?: SimpleStreamOptions, apiKey?: string): StreamOptions {
return {
temperature: options?.temperature,
maxTokens: options?.maxTokens ?? defaultMaxTokens,
maxTokens: options?.maxTokens,
signal: options?.signal,
apiKey: apiKey || options?.apiKey,
transport: options?.transport,
@@ -34,7 +24,8 @@ export function clampReasoning(effort: ThinkingLevel | undefined): Exclude<Think
}
export function adjustMaxTokensForThinking(
baseMaxTokens: number,
// Undefined means no explicit caller cap. Use the model cap and fit thinking inside it.
baseMaxTokens: number | undefined,
modelMaxTokens: number,
reasoningLevel: ThinkingLevel,
customBudgets?: ThinkingBudgets,
@@ -50,7 +41,8 @@ export function adjustMaxTokensForThinking(
const minOutputTokens = 1024;
const level = clampReasoning(reasoningLevel)!;
let thinkingBudget = budgets[level]!;
const maxTokens = Math.min(baseMaxTokens + thinkingBudget, modelMaxTokens);
const maxTokens =
baseMaxTokens === undefined ? modelMaxTokens : Math.min(baseMaxTokens + thinkingBudget, modelMaxTokens);
if (maxTokens <= thinkingBudget) {
thinkingBudget = Math.max(0, maxTokens - minOutputTokens);