feat(server): add inference reliability - tool-shim and loop detectors

- ToolShim recovers XML/JSON tool calls from plain-text model output
- detectContentRepeat catches same-content loops
- detectToolLoop catches repeated tool invocations
- detectDoomLoop combines both detectors

apps/server/src/services/inference/tool-shim.ts

@@ -0,0 +1,45 @@
+// ToolShim — recovers structured tool calls from plain-text model output.
+// When the model emits tool calls as plain text instead of structured JSON,
+// this shim attempts to parse and recover them.
+
+export interface ParsedToolCall {
+  id: string;
+  name: string;
+  arguments: string;
+}
+
+const TOOL_CALL_PATTERN = /<tool_call>\s*<name>(.+?)<\/name>\s*<arguments>(.+?)<\/arguments>\s*<\/tool_call>/gs;
+const JSON_TOOL_PATTERN = /\{\s*"name":\s*"([^"]+)",\s*"arguments":\s*({.+?})\s*\}/gs;
+
+export function extractToolCalls(text: string): ParsedToolCall[] {
+  const calls: ParsedToolCall[] = [];
+  let match: RegExpExecArray | null;
+
+  // Try XML-style tool calls (common in Qwen output)
+  const xmlRegex = new RegExp(TOOL_CALL_PATTERN);
+  while ((match = xmlRegex.exec(text)) !== null) {
+    calls.push({
+      id: `call_${calls.length}`,
+      name: match[1]!.trim(),
+      arguments: match[2]!.trim(),
+    });
+  }
+
+  if (calls.length > 0) return calls;
+
+  // Try JSON-style tool calls
+  const jsonRegex = new RegExp(JSON_TOOL_PATTERN);
+  while ((match = jsonRegex.exec(text)) !== null) {
+    calls.push({
+      id: `call_${calls.length}`,
+      name: match[1]!.trim(),
+      arguments: match[2]!.trim(),
+    });
+  }
+
+  return calls;
+}
+
+export function hasToolCallMarkup(text: string): boolean {
+  return TOOL_CALL_PATTERN.test(text) || JSON_TOOL_PATTERN.test(text);
+}