v1.10.5: inference XML tool-call fallback parser

Some local models (qwen3-coder via llama-swap) emit tool calls as inline XML
inside delta.content rather than structured delta.tool_calls. streamCompletion
now buffers delta.content, extracts complete <tool_call>...</tool_call> blocks
via parseXmlToolCall, and pushes synthetic entries (id prefix xml_call_) into
the existing toolCallsBuffer. Native JSON path unchanged — both coexist.
Partial openers are held back so a tool tag never leaks to the chat mid-tag.
Unclosed XML at end-of-stream is flushed as plain content (no silent drops).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

apps/server/src/services/inference.ts

@@ -310,6 +310,70 @@ interface StreamOptions {
   temperature?: number;
 }
 
+// v1.10.5 Qwen-coder XML fallback. Some local models (notably qwen3-coder via
+// llama-swap) emit tool calls as inline XML inside delta.content rather than
+// the structured delta.tool_calls field. The XML shape is:
+//   <tool_call>
+//   <function=NAME>
+//   <parameter=KEY>
+//   VALUE
+//   </parameter>
+//   ...more parameters...
+//   </function>
+//   </tool_call>
+// Multiple <tool_call> blocks may appear back-to-back; they never nest.
+// streamCompletion buffers delta.content, extracts complete blocks, parses
+// them via parseXmlToolCall, and pushes synthetic entries into the existing
+// toolCallsBuffer alongside any native JSON-format tool calls.
+const XML_TOOL_OPEN = '<tool_call>';
+const XML_TOOL_CLOSE = '</tool_call>';
+
+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.
+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;
+}
+
 async function streamCompletion(
   ctx: InferenceContext,
   model: string,
@@ -344,6 +408,10 @@ async function streamCompletion(
   }
 
   let content = '';
+  // v1.10.5: holds delta.content bytes that may contain a partial XML tool
+  // call. Anything not part of a (possibly forming) <tool_call>…</tool_call>
+  // pair is flushed to content + onDelta as soon as we know it's safe.
+  let pendingBuffer = '';
   let finishReason: string | null = null;
   let promptTokens: number | null = null;
   let completionTokens: number | null = null;
@@ -377,8 +445,50 @@ async function streamCompletion(
     if (!choice) continue;
     const delta = choice.delta ?? {};
     if (typeof delta.content === 'string' && delta.content.length > 0) {
-      content += delta.content;
-      onDelta(delta.content);
+      // v1.10.5 XML fallback. Append, then extract any complete tool_call
+      // blocks before deciding what's safe to flush as visible content.
+      pendingBuffer += delta.content;
+      while (true) {
+        const startIdx = pendingBuffer.indexOf(XML_TOOL_OPEN);
+        if (startIdx === -1) break;
+        const closeIdx = pendingBuffer.indexOf(XML_TOOL_CLOSE, startIdx);
+        if (closeIdx === -1) break;
+        const blockEnd = closeIdx + XML_TOOL_CLOSE.length;
+        const block = pendingBuffer.slice(startIdx, blockEnd);
+        // Any text before the opener is plain content — flush it now.
+        if (startIdx > 0) {
+          const before = pendingBuffer.slice(0, startIdx);
+          content += before;
+          onDelta(before);
+        }
+        const parsedCall = parseXmlToolCall(block);
+        if (parsedCall) {
+          const synthIdx = toolCallsBuffer.size;
+          toolCallsBuffer.set(synthIdx, {
+            id: `xml_call_${synthIdx}`,
+            name: parsedCall.name,
+            argsText: JSON.stringify(parsedCall.args),
+          });
+        }
+        // If parsing failed we still drop the block — emitting unparseable
+        // XML to the chat would look worse than silently swallowing it.
+        pendingBuffer = pendingBuffer.slice(blockEnd);
+      }
+      // After all complete blocks are out, hold back any (partial or full)
+      // unclosed opener; flush the rest.
+      const partialIdx = partialXmlOpenerStart(pendingBuffer);
+      if (partialIdx >= 0) {
+        if (partialIdx > 0) {
+          const flush = pendingBuffer.slice(0, partialIdx);
+          content += flush;
+          onDelta(flush);
+        }
+        pendingBuffer = pendingBuffer.slice(partialIdx);
+      } else if (pendingBuffer.length > 0) {
+        content += pendingBuffer;
+        onDelta(pendingBuffer);
+        pendingBuffer = '';
+      }
     }
     if (Array.isArray(delta.tool_calls)) {
       for (const tc of delta.tool_calls) {
@@ -393,6 +503,15 @@ async function streamCompletion(
     if (choice.finish_reason) finishReason = choice.finish_reason;
   }
 
+  // v1.10.5: if the stream ended mid-XML (e.g. model truncated, no closer
+  // ever arrived), flush whatever was buffered as plain content so it isn't
+  // silently dropped. Better to show a stray `<tool_call>` than vanish text.
+  if (pendingBuffer.length > 0) {
+    content += pendingBuffer;
+    onDelta(pendingBuffer);
+    pendingBuffer = '';
+  }
+
   const toolCalls: ToolCall[] = [];
   for (const [, t] of [...toolCallsBuffer.entries()].sort(([a], [b]) => a - b)) {
     let args: Record<string, unknown> = {};