engineering/uncloseai.com
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fix token estimation: use 3 chars/token instead of 4

Browse source
This commit is contained in:
Russell Ballestrini 2026-01-01 12:22:11 -05:00
parent bd312f0979
commit 1ec196275f
4 changed files with 6 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

4
public/src/chat.js
View file

@ -5,9 +5,9 @@ import { API_KEY, getAPIConfig } from "./config.js";
import { getSelectedModel, getSelectedModelEndpoint, getSelectedModelMaxTokens, getSelectedModelMaxCompletionTokens } from "./models.js";
import { groqAwareStreamingFetch } from "./groq-fetch.js";
// Rough token estimation (4 chars = 1 token average for English)
// Rough token estimation (3 chars = 1 token to be conservative)
function estimateTokens(text) {
return Math.ceil(text.length / 4);
return Math.ceil(text.length / 3);
}
// Calculate available output tokens

2
public/src/translation.js
View file

@ -75,7 +75,7 @@ async function* sendMessageWithHistory(messageHistory) {
// Calculate available tokens for output based on current prompt
const modelMaxTokens = getSelectedModelMaxTokens();
const inputText = messageHistory.map(msg => msg.content).join('');
const inputTokens = Math.ceil(inputText.length / 4); // Simple token estimation
const inputTokens = Math.ceil(inputText.length / 3); // Conservative token estimation
const outputReserve = Math.floor(modelMaxTokens * 0.4); // Reserve 40% for output
let availableTokens = Math.max(512, modelMaxTokens - inputTokens - outputReserve);

2
public/src/tts.js
View file

@ -143,7 +143,7 @@ Your task:
7. Start with the article title, then the main content
Return only the article text ready for TTS, nothing else.`;
const inputTokens = Math.ceil((systemPrompt + preCleanedContent).length / 4);
const inputTokens = Math.ceil((systemPrompt + preCleanedContent).length / 3);
const buffer = Math.max(2048, Math.floor(inputTokens * 1.5)); // Use 1.5x input tokens as buffer, minimum 2048
const calculatedAvailable = Math.max(100, modelMaxTokens - inputTokens - buffer);

4
public/src/ui.js
View file

@ -141,9 +141,9 @@ async function* sendMessageWithCustomHistory(messageHistory) {
const { getSelectedModelMaxTokens, getSelectedModelMaxCompletionTokens } = await import("./models.js");
const modelMaxTokens = getSelectedModelMaxTokens();
// Estimate input tokens for intro generation
// Estimate input tokens for intro generation (3 chars = 1 token to be conservative)
const inputText = messageHistory.map(msg => msg.content).join('');
const inputTokens = Math.ceil(inputText.length / 4);
const inputTokens = Math.ceil(inputText.length / 3);
// For intro generation, be more generous - we want complete intros
// With large context models, we have plenty of room