feat: per-call LLM timing, speaker ID, cancel captures on leave

- llm.py: log each Ollama call's caller + total/load/prompt/gen durations
  so a slow voice turn is attributable to a specific internal call
  (router/enrichment/digest/main); a RELOAD marker flags cold reloads.
- voice.ts: track in-flight Opus captures and abort them on session
  destroy(); drop any utterance that finishes after the user left, so no
  trailing post-leave VAD turns are reported.
- userbot.ts: show the speaker's Discord user ID on each transcript line
  (answered and dropped) so it's clear whose audio produced the turn.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

src/jarvis/llm.py

@@ -3,9 +3,19 @@
 from __future__ import annotations
 from typing import Optional, Any, Dict, List, Generator, Callable
 import os
+import sys
 import requests
 import json
 
+
+def _caller_name() -> str:
+    """Best-effort name of the function that invoked the LLM wrapper, used to
+    label per-call timing (router / enrichment / digest / main)."""
+    try:
+        return sys._getframe(2).f_code.co_name
+    except Exception:
+        return "?"
+
 from .debug import debug_log
 
 
@@ -25,6 +35,33 @@ class ToolsNotSupportedError(Exception):
     pass
 
 
+def _log_ollama_timing(data: Dict[str, Any], num_ctx: int, caller: str) -> None:
+    """Emit a one-line per-call latency breakdown so a slow voice turn can be
+    attributed to a specific internal LLM call (router / enrichment / digest /
+    main) instead of just a total. ``load_duration`` > 0 means the model was
+    cold-reloaded for this call — the single most expensive thing to avoid.
+    """
+    if not isinstance(data, dict):
+        return
+    try:
+        ns = 1e9
+        total = data.get("total_duration", 0) / ns
+        load = data.get("load_duration", 0) / ns
+        peval = data.get("prompt_eval_duration", 0) / ns
+        pcount = data.get("prompt_eval_count")
+        gen = data.get("eval_duration", 0) / ns
+        gcount = data.get("eval_count")
+        reload_flag = " RELOAD" if load > 0.5 else ""
+        print(
+            f"  ⏱️ llm[{caller}] ctx={num_ctx} total={total:.2f}s "
+            f"load={load:.2f}s{reload_flag} prompt={peval:.2f}s({pcount}t) "
+            f"gen={gen:.2f}s({gcount}t)",
+            flush=True,
+        )
+    except Exception:  # pragma: no cover - logging must never break a reply
+        pass
+
+
 def call_llm_direct(base_url: str, chat_model: str, system_prompt: str, user_content: str, timeout_sec: float = 10.0, thinking: bool = False, num_ctx: int = OLLAMA_NUM_CTX, temperature: Optional[float] = None) -> Optional[str]:
     """Direct LLM call without temporal context, location, or other ask_coach features.
 
@@ -62,10 +99,12 @@ def call_llm_direct(base_url: str, chat_model: str, system_prompt: str, user_con
         "keep_alive": "30m",
     }
 
+    caller = _caller_name()
     try:
         with requests.post(f"{base_url.rstrip('/')}/api/chat", json=payload, timeout=timeout_sec) as resp:
             resp.raise_for_status()
             data = resp.json()
+        _log_ollama_timing(data, num_ctx, caller)
 
         if isinstance(data, dict):
             content = extract_text_from_response(data)
@@ -233,10 +272,12 @@ def chat_with_messages(
     if tools and isinstance(tools, list) and len(tools) > 0:
         payload["tools"] = tools
 
+    caller = _caller_name()
     try:
         with requests.post(f"{base_url.rstrip('/')}/api/chat", json=payload, timeout=timeout_sec) as resp:
             resp.raise_for_status()
             data = resp.json()
+        _log_ollama_timing(data, OLLAMA_NUM_CTX, caller)
         if isinstance(data, dict):
             return data
     except requests.exceptions.Timeout: