v1.13.16-xml-parser: Anthropic <invoke> support + unknown-tool recovery hints

Two-part fix for the model-emitted XML drift the v1.13.15-codecontext-synth
investigation surfaced (1 raw <invoke> leak observed out of 190 qwen3.6
turns — qwen3.6-35b-a3b-mxfp4 drifts to the Anthropic format when prompted
as an Architect-style agent because Claude Code documentation in its
pre-training corpus uses that shape).

## Parser extension

xml-parser.ts now recognizes BOTH XML tool-call flavors:

  - Qwen/Hermes:   <tool_call><function=NAME>...<parameter=K>V</parameter>...</function></tool_call>
  - Anthropic:     <invoke name="NAME"><parameter name="K">V</parameter></invoke>

Both route through the same synthetic-id xml_call_${idx} ToolCall path.
extractToolCallBlocks() and partialXmlOpenerStart() handle both openers
(<tool_call> and <invoke...) so partial buffers don't get prematurely
flushed during streaming.

The existing Qwen parser was tightened to tolerate whitespace around `=`
(<function = name>, <parameter = key>...) so a stray space doesn't get
absorbed into the function name. Name capture is non-whitespace,
non-`>`.

## Unknown-tool recovery hint

New tool-suggestions.ts exports levenshtein() + suggestToolName() +
formatUnknownToolError(). When tool-phase.ts:executeToolCall receives a
toolCall.name that isn't in TOOLS_BY_NAME, the error returned to the
model now includes a "Did you mean: X?" hint based on Levenshtein
distance ≤3 or substring match against Object.keys(TOOLS_BY_NAME).
Targets the qwen3.6 drift to read_file → suggest view_file. Applies to
all unknown tool names, not just <invoke>-derived ones — at the
dispatch layer we no longer know which format produced the call, and
the extra signal is harmless for Qwen-derived calls.

## Test coverage

xml-parser.test.ts: 46 tests, all green. Covers both parsers
(well-formed, malformed, multi-parameter, nested-content), the
partial-opener detector for both flavors, the unified extraction
helper, and the unknown-tool error formatter.

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

apps/server/src/services/inference/xml-parser.ts

@@ -1,23 +1,42 @@
 // 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.
+// The streaming loop in stream-phase.ts extracts these blocks via these helpers.
+//
+// v1.13.16: also recognize Anthropic <invoke name="..."><parameter name="...">
+// markup. qwen3.6-35b-a3b-mxfp4 drifts to this format when prompted as an
+// "Architect"-style agent because Claude Code documentation in its
+// pre-training data uses this shape. Both formats route through the same
+// synthetic ToolCall path with shared xml_call_${idx} IDs; downstream
+// dispatch handles unknown tool names with a richer error (see
+// tool-suggestions.ts + tool-phase.ts).
 
 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=([^>]+)>/);
+// v1.13.16: Anthropic <invoke> opener is matched by prefix (not the full
+// `<invoke ...>` tag) because attributes follow. Closer is the literal tag.
+export const INVOKE_TOOL_OPEN = '<invoke';
+export const INVOKE_TOOL_CLOSE = '</invoke>';
+
+export interface ParsedCall {
+  name: string;
+  args: Record<string, unknown>;
+}
+
+// v1.10.5: Qwen-flavor parser. Tightened in v1.13.16 to tolerate whitespace
+// around `=` (e.g. `<function = view_file>`). Name capture is non-whitespace,
+// non-`>` so a stray space doesn't get absorbed into the function name.
+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> = {};
-  // 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)) {
+  for (const m of block.matchAll(QWEN_PARAM_RE)) {
     const key = (m[1] ?? '').trim();
     if (!key) continue;
     const raw = (m[2] ?? '').trim();
@@ -30,24 +49,121 @@ export function parseXmlToolCall(
   return { name, args };
 }
 
+// v1.13.16: Anthropic-flavor parser. Same JSON-parse-with-string-fallback
+// shape as parseXmlToolCall so the dispatch layer doesn't need to care which
+// flavor produced the call.
+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 };
+}
+
 // 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.
+// unfinished opener (either flavor) in `s`. Returns -1 when `s` can be
+// flushed to the client in full without risking a partial tag leak.
+//   Case 1: a full opener (`<tool_call>` or `<invoke`) 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 either opener (e.g. `<tool_c`
+//           or `<invo`). 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.
+// block before reaching this check.
+const ALL_OPENERS = [XML_TOOL_OPEN, INVOKE_TOOL_OPEN] as const;
+
 export function partialXmlOpenerStart(s: string): number {
-  const fullOpener = s.indexOf(XML_TOOL_OPEN);
-  if (fullOpener !== -1) return fullOpener;
+  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);
-  if (XML_TOOL_OPEN.startsWith(suffix) && suffix.length < XML_TOOL_OPEN.length) {
-    return lastLt;
+  for (const op of ALL_OPENERS) {
+    if (op.startsWith(suffix) && suffix.length < op.length) return lastLt;
   }
   return -1;
 }
+
+// v1.13.16: unified extraction. Replaces the inline loop that used to live
+// in stream-phase.ts. Pure function — returns the visible text to flush,
+// the parsed tool-call payloads in source order, and the buffer remainder
+// to retain for the next streaming chunk. Parse failures are silently
+// dropped (matches the pre-v1.13.16 behavior — leaking partial XML to the
+// chat looks worse than swallowing a bad block).
+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) 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) };
+}