Files
boocode/apps/server/src/services/inference/xml-parser.ts
indifferentketchup ea468ca7fb v1.12.4-rc1: extract budget, sentinels, xml-parser from inference.ts
Pure file moves. No behavior change. inference.ts retains createInferenceRunner
public surface; new files are internal to services/inference/.

- budget.ts: resolveToolBudget
- sentinels.ts: detectDoomLoop (re-exported through inference.ts),
  isCapHitSentinel, isDoomLoopSentinel, isAnySentinel
- xml-parser.ts: parseXmlToolCall, partialXmlOpenerStart

First of four refactor batches preparing inference.ts for the v1.13
AI SDK migration. inference.ts goes from 1780 LoC to ~1620.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-21 21:42:41 +00:00

54 lines
2.2 KiB
TypeScript

// v1.10.5: XML-tag tool-call fallback. Some models emit
// <tool_call><function=foo><parameter=key>value</parameter></function></tool_call>
// in plain content instead of using the OpenAI tool_calls JSON channel.
// The streaming loop in inference.ts extracts these blocks via these helpers.
export const XML_TOOL_OPEN = '<tool_call>';
export const XML_TOOL_CLOSE = '</tool_call>';
export function parseXmlToolCall(
block: string,
): { name: string; args: Record<string, unknown> } | null {
const nameMatch = block.match(/<function=([^>]+)>/);
if (!nameMatch || !nameMatch[1]) return null;
const name = nameMatch[1].trim();
if (!name) return null;
const args: Record<string, unknown> = {};
// Non-greedy body so each <parameter=…>…</parameter> pair is matched
// independently even when multiple appear in the same block.
const paramRe = /<parameter=([^>]+)>([\s\S]*?)<\/parameter>/g;
for (const m of block.matchAll(paramRe)) {
const key = (m[1] ?? '').trim();
if (!key) continue;
const raw = (m[2] ?? '').trim();
try {
args[key] = JSON.parse(raw);
} catch {
args[key] = raw;
}
}
return { name, args };
}
// Locate the first character that begins (or completely contains) an
// unfinished <tool_call> opener in `s`. Returns -1 when `s` can be flushed
// to the client in full without risking a partial tag leak.
// Case 1: a full `<tool_call>` opener with no matching closer — caller
// must keep everything from that index forward until the next
// chunk arrives with the closer.
// Case 2: `s` ends with a strict prefix of `<tool_call>` (e.g. `<tool_c`).
// Caller must keep just that suffix in the buffer.
// Note: case 1 assumes the calling loop already extracted every complete
// <tool_call>…</tool_call> pair before reaching this check.
export function partialXmlOpenerStart(s: string): number {
const fullOpener = s.indexOf(XML_TOOL_OPEN);
if (fullOpener !== -1) return fullOpener;
const lastLt = s.lastIndexOf('<');
if (lastLt === -1) return -1;
const suffix = s.slice(lastLt);
if (XML_TOOL_OPEN.startsWith(suffix) && suffix.length < XML_TOOL_OPEN.length) {
return lastLt;
}
return -1;
}