@bitkyc08/opencodex
Version:
Universal provider proxy for OpenAI Codex & Claude Code — use any LLM with Codex CLI/App/SDK and Claude Code
72 lines (67 loc) • 3.89 kB
text/typescript
/**
* Gemini progress-text history trimming.
*
* Gemini models, observed on Gemini 4 Argon over Cloud Code Assist, sometimes skip their thinking
* channel on a tool-calling turn and plan in the visible text instead. The provider sends that
* planning as an ordinary text part without a thought marker, for example a progress line in the
* user's language followed by "Let's read google.ts 580-1700 first." Once one turn like that is
* replayed as history, the model copies the pattern on the turns that follow, so the leak grows
* through the rest of the session. Replaying the same 300K-token request with the leaked tails
* removed from the history stopped the leak, while stronger system-prompt wording did not.
*
* The fix is on the history side only. Text that precedes the tool call of a replayed model turn is
* intermediate progress, and the Google brevity instruction already asks for a single short line
* there, so it is replayed as its lead sentence. A turn Codex marks `final_answer` and text after a
* tool call are replayed whole. Visible output is never rewritten, final
* answers (turns without tool calls) are replayed in full, and the split is punctuation-based so
* it works the same in every language without matching any wording.
*/
/**
* Sentence end: ASCII terminal punctuation followed by whitespace or the end (so "google.ts" and
* "3.5" are not boundaries), a script's own sentence terminator (CJK 。!?, Devanagari
* ।॥, Arabic ۔؟, Armenian ։, Ethiopic ።, Myanmar ။), or a line break. Closing quotes, brackets and
* Markdown emphasis right after the punctuation belong to the sentence.
*/
const SENTENCE_END = /[.!?]["'\u201D\u2019)\]*_`]*(?=\s|$)|[\u3002\uFF01\uFF1F\u0964\u0965\u06D4\u061F\u0589\u1362\u104B]["'\u201D\u2019\u300D\u300F)\]*_`]*|\n/g;
/** A boundary that only closes a leading list marker ("1.", "a.") or a common abbreviation ("e.g."). */
const NOT_A_SENTENCE = /^(?:\d{1,3}|[a-z])\.$|(?:^|\s)(?:e\.g|i\.e|etc|vs)\.$/i;
const WHITESPACE = /\s/;
/** Whether replayed progress text for this model is trimmed to its lead sentence. */
export function trimsGeminiProgressHistory(modelId: string): boolean {
return /gemini/i.test(modelId);
}
/**
* The lead sentence of a replayed progress text, or undefined when nothing usable remains.
* Text without a sentence boundary is already a single sentence and is returned whole.
*/
export function geminiProgressLead(text: string): string | undefined {
const trimmed = text.trim();
if (trimmed.length === 0) return undefined;
SENTENCE_END.lastIndex = 0;
let end = trimmed.length;
let checked = 0;
let contentEnd = 0;
for (let match = SENTENCE_END.exec(trimmed); match; match = SENTENCE_END.exec(trimmed)) {
const boundary = match.index + match[0].length;
// Only a newline boundary can end in whitespace. Scan its new interval once; repeated
// blank lines retain the previous content end without rescanning the preceding text.
if (match[0] === "\n") {
for (let index = checked; index < boundary; index++) {
if (!WHITESPACE.test(trimmed[index])) contentEnd = index + 1;
}
} else {
contentEnd = boundary;
}
checked = boundary;
// The longest exception is four characters plus its preceding whitespace. The list
// marker alternative is anchored to the whole prefix, so allow it only at the start.
const start = Math.max(0, contentEnd - 5);
const suffix = trimmed.slice(start, contentEnd);
const exception = NOT_A_SENTENCE.exec(suffix);
if (!exception || (exception.index === 0 && start > 0 && !/^\s/.test(suffix))) { end = boundary; break; }
}
const lead = trimmed.slice(0, end).trim();
// A code-fence opener is not a sentence; replaying it alone would leave an unclosed fence.
if (lead.length === 0 || lead.startsWith("```")) return undefined;
return lead;
}