Merge main into feat/voice-core

Keeps the voice-core prompt rules and adds main's world-query and
vessels-vs-visuals rules; the tool catalog wraps the deixis-aware runner.

Also fixes two things the branch had before the merge:
- Live voice could not start: OpenAI rejects track_entity's top-level
  anyOf. Model-facing tools now omit top-level combinators; the runner
  and benchmark still require a query or a referent.
- The Contacts-centred analyst answer dropped the viewport coverage note.

server/providers/openai/debug-log.js

@@ -114,10 +114,11 @@ function createDebugLogHandler({
       const body = await readRequestBody(req, REALTIME_DEBUG_LOG_MAX_BYTES);
       const parsed = JSON.parse(body || '{}');
       const record = includeContent ? parsed : omitVoiceContent(parsed);
+      // The server's own timestamp comes last, so a record cannot supply one.
       await append(
         `${JSON.stringify({
-          loggedAt: new Date().toISOString(),
           ...record,
+          loggedAt: new Date().toISOString(),
         })}\n`,
       );
       res.statusCode = 204;