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>

apps/server/src/services/inference/sentinels.ts

@@ -0,0 +1,53 @@
+import type { Message, ToolCall } from '../../types/api.js';
+
+// v1.11.6: doom-loop guard. When the model calls the same tool with the
+// same arguments DOOM_LOOP_THRESHOLD times in a row within one user-message
+// turn, abort the recursion and run the same wrap-up summary path as the
+// cap-hit case. Ported from opencode (DOOM_LOOP_THRESHOLD in
+// session/processor.ts). Threshold of 3 is the smallest value that doesn't
+// false-positive on a model that retries once after a transient error.
+export const DOOM_LOOP_THRESHOLD = 3;
+
+// Returns the name + args of the looping tool when the LAST
+// DOOM_LOOP_THRESHOLD entries in `recentToolCalls` are identical (same name
+// AND deep-equal args via JSON.stringify). Returns null otherwise.
+// Pure; exported for unit-test access.
+export function detectDoomLoop(
+  recentToolCalls: ToolCall[],
+): { name: string; args: Record<string, unknown> } | null {
+  if (recentToolCalls.length < DOOM_LOOP_THRESHOLD) return null;
+  const last = recentToolCalls.slice(-DOOM_LOOP_THRESHOLD);
+  const ref = last[0]!;
+  const refArgs = JSON.stringify(ref.args);
+  for (let i = 1; i < last.length; i++) {
+    const tc = last[i]!;
+    if (tc.name !== ref.name) return null;
+    if (JSON.stringify(tc.args) !== refArgs) return null;
+  }
+  return { name: ref.name, args: ref.args };
+}
+
+export function isCapHitSentinel(m: Message): boolean {
+  return (
+    m.role === 'system' &&
+    m.metadata !== null &&
+    typeof m.metadata === 'object' &&
+    (m.metadata as { kind?: unknown }).kind === 'cap_hit'
+  );
+}
+
+// v1.11.6: parallel predicate. Same UI-only semantics as cap-hit sentinels —
+// never sent to the LLM (filtered by buildMessagesPayload through the
+// isAnySentinel check below).
+export function isDoomLoopSentinel(m: Message): boolean {
+  return (
+    m.role === 'system' &&
+    m.metadata !== null &&
+    typeof m.metadata === 'object' &&
+    (m.metadata as { kind?: unknown }).kind === 'doom_loop'
+  );
+}
+
+export function isAnySentinel(m: Message): boolean {
+  return isCapHitSentinel(m) || isDoomLoopSentinel(m);
+}