boocode/apps/server/src/services/inference/tool-call-parser.ts

// Streaming tool-call extraction for the qwen3.6 XML fallback path.
// `extractToolCallBlocks` is the incremental streaming scanner used by
// stream-phase.ts; `stripToolMarkup` removes tool-call wire markup from
// assistant prose (used by tool-phase.ts and error-handler.ts).

// ── Constants ────────────────────────────────────────────────────────────

export const XML_TOOL_OPEN = '<tool_call>';
export const XML_TOOL_CLOSE = '</tool_call>';
export const INVOKE_TOOL_OPEN = '<invoke';
export const INVOKE_TOOL_CLOSE = '</invoke>';

// ── Strip patterns ───────────────────────────────────────────────────────

const TOOL_CLOSED_PATS = [
  /<tool_call>.*?<\/tool_call>/gs,
  /<function=\w+>.*?<\/function>/gs,
  /<invoke\s[^>]*>.*?<\/invoke>/gs,
];

const TOOL_ALL_PATS = [
  ...TOOL_CLOSED_PATS,
  /<tool_call>.*$/gs,
  /<function=\w+>.*$/gs,
  /<invoke\s[^>]*>.*$/gs,
];

// ── Strip ────────────────────────────────────────────────────────────────

export function stripToolMarkup(text: string, opts?: { final?: boolean }): string {
  const pats = opts?.final ? TOOL_ALL_PATS : TOOL_CLOSED_PATS;
  for (const pat of pats) {
    text = text.replace(pat, '');
  }
  return opts?.final ? text.trim() : text;
}

// ── BooCode streaming helpers ────────────────────────────────────────────

export interface ParsedCall {
  name: string;
  args: Record<string, unknown>;
}

const PLACEHOLDER_LITERALS = new Set(['...', 'placeholder', '<path>', '<file>']);
const ANGLE_BRACKET_SENTINEL_RE = /^<[^>]+>$/;

export function isPlaceholderArgValue(value: unknown): boolean {
  if (typeof value !== 'string') return false;
  const trimmed = value.trim();
  if (trimmed === '') return true;
  if (PLACEHOLDER_LITERALS.has(trimmed)) return true;
  if (ANGLE_BRACKET_SENTINEL_RE.test(trimmed)) return true;
  return false;
}

function hasPlaceholderArgs(args: Record<string, unknown>): boolean {
  for (const value of Object.values(args)) {
    if (isPlaceholderArgValue(value)) return true;
  }
  return false;
}

function logRejectedPlaceholder(parsed: ParsedCall): void {
  console.debug(
    { toolName: parsed.name, args: parsed.args },
    'rejected placeholder tool call at parse time',
  );
}

const QWEN_FUNCTION_RE = /<function\s*=\s*([^>\s]+)\s*>/;
const QWEN_PARAM_RE = /<parameter\s*=\s*([^>\s]+)\s*>([\s\S]*?)<\/parameter>/g;

export function parseXmlToolCall(block: string): ParsedCall | null {
  const nameMatch = block.match(QWEN_FUNCTION_RE);
  if (!nameMatch || !nameMatch[1]) return null;
  const name = nameMatch[1].trim();
  if (!name) return null;
  const args: Record<string, unknown> = {};
  for (const m of block.matchAll(QWEN_PARAM_RE)) {
    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 };
}

const INVOKE_NAME_RE =
  /<invoke\s+name\s*=\s*("([^"]*)"|'([^']*)')\s*>/;
const INVOKE_PARAM_RE =
  /<parameter\s+name\s*=\s*("([^"]*)"|'([^']*)')\s*>([\s\S]*?)<\/parameter>/g;

export function parseInvokeToolCall(block: string): ParsedCall | null {
  const nameMatch = block.match(INVOKE_NAME_RE);
  if (!nameMatch) return null;
  const name = (nameMatch[2] ?? nameMatch[3] ?? '').trim();
  if (!name) return null;
  const args: Record<string, unknown> = {};
  for (const m of block.matchAll(INVOKE_PARAM_RE)) {
    const key = ((m[2] ?? m[3] ?? '') as string).trim();
    if (!key) continue;
    const raw = (m[4] ?? '').trim();
    try {
      args[key] = JSON.parse(raw);
    } catch {
      args[key] = raw;
    }
  }
  return { name, args };
}

const ALL_OPENERS = [XML_TOOL_OPEN, INVOKE_TOOL_OPEN] as const;

export function partialXmlOpenerStart(s: string): number {
  let earliest = -1;
  for (const op of ALL_OPENERS) {
    const idx = s.indexOf(op);
    if (idx === -1) continue;
    if (earliest === -1 || idx < earliest) earliest = idx;
  }
  if (earliest !== -1) return earliest;
  const lastLt = s.lastIndexOf('<');
  if (lastLt === -1) return -1;
  const suffix = s.slice(lastLt);
  for (const op of ALL_OPENERS) {
    if (op.startsWith(suffix) && suffix.length < op.length) return lastLt;
  }
  return -1;
}

export interface ToolCallExtraction {
  flushed: string;
  calls: ParsedCall[];
  remaining: string;
}

interface OpenerSpec {
  open: string;
  close: string;
  parse: (block: string) => ParsedCall | null;
}

const OPENER_SPECS: ReadonlyArray<OpenerSpec> = [
  { open: XML_TOOL_OPEN, close: XML_TOOL_CLOSE, parse: parseXmlToolCall },
  { open: INVOKE_TOOL_OPEN, close: INVOKE_TOOL_CLOSE, parse: parseInvokeToolCall },
];

export function extractToolCallBlocks(buffer: string): ToolCallExtraction {
  let flushed = '';
  const calls: ParsedCall[] = [];
  let pos = 0;

  while (pos < buffer.length) {
    let next: { spec: OpenerSpec; openIdx: number; closeIdx: number } | null = null;
    for (const spec of OPENER_SPECS) {
      const openIdx = buffer.indexOf(spec.open, pos);
      if (openIdx === -1) continue;
      const closeIdx = buffer.indexOf(spec.close, openIdx);
      if (closeIdx === -1) continue;
      if (next === null || openIdx < next.openIdx) {
        next = { spec, openIdx, closeIdx };
      }
    }
    if (next === null) break;

    if (next.openIdx > pos) {
      flushed += buffer.slice(pos, next.openIdx);
    }
    const blockEnd = next.closeIdx + next.spec.close.length;
    const block = buffer.slice(next.openIdx, blockEnd);
    const parsed = next.spec.parse(block);
    if (parsed) {
      if (hasPlaceholderArgs(parsed.args)) {
        logRejectedPlaceholder(parsed);
        flushed += block;
      } else {
        calls.push(parsed);
      }
    }
    pos = blockEnd;
  }

  const tail = buffer.slice(pos);
  const partialIdx = partialXmlOpenerStart(tail);
  if (partialIdx === -1) {
    flushed += tail;
    return { flushed, calls, remaining: '' };
  }
  if (partialIdx > 0) {
    flushed += tail.slice(0, partialIdx);
  }
  return { flushed, calls, remaining: tail.slice(partialIdx) };
}