perf: cap chat output tokens via ollama_num_predict to bound reply latency

Spoken (TTS) replies are 1-2 sentences, so an unbounded num_predict only
exposes the worst case where the chat model rambles or loops. Add an
ollama_num_predict config (default 512, 0 disables) wired into the reply
loop's chat call on both the native- and text-tool paths. The 512-token
headroom stays well above this app's short tool-call JSON, so capping never
truncates a tool call. This keeps the user's quality model instead of
downgrading it. Configurable in the container via OLLAMA_NUM_PREDICT.

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

tests/test_ollama_num_predict.py

@@ -0,0 +1,112 @@
+"""Tests for the ``ollama_num_predict`` chat-output cap.
+
+The cap bounds worst-case reply latency by limiting how many tokens the chat
+model may generate per turn. Spoken (TTS) answers are 1-2 sentences, so the
+default headroom never clips a normal answer and stays above tool-call JSON.
+
+These tests verify behaviour:
+- the config default is present,
+- the value is threaded into the Ollama request as the ``num_predict`` option,
+- the reply loop forwards it to the chat call (and disables it at 0).
+"""
+
+from unittest.mock import Mock, patch
+
+import pytest
+
+from src.jarvis.config import get_default_config
+from src.jarvis.memory.conversation import DialogueMemory
+from src.jarvis.reply.engine import run_reply_engine
+
+
+# ---------------------------------------------------------------------------
+# Config default
+# ---------------------------------------------------------------------------
+
+def test_default_config_has_num_predict_cap():
+    config = get_default_config()
+    assert config["ollama_num_predict"] == 512
+
+
+# ---------------------------------------------------------------------------
+# Transport: extra_options.num_predict reaches the Ollama payload options
+# ---------------------------------------------------------------------------
+
+@patch("jarvis.llm.requests.post")
+def test_chat_with_messages_forwards_num_predict(mock_post):
+    from jarvis.llm import chat_with_messages
+
+    mock_resp = Mock()
+    mock_resp.status_code = 200
+    mock_resp.json.return_value = {"message": {"content": "ok"}}
+    mock_resp.raise_for_status = Mock()
+    mock_post.return_value = mock_resp
+
+    chat_with_messages(
+        "http://localhost:11434",
+        "test-large",
+        [{"role": "user", "content": "hi"}],
+        extra_options={"num_predict": 512},
+    )
+    _, kwargs = mock_post.call_args
+    options = (kwargs.get("json") or {}).get("options") or {}
+    assert options.get("num_predict") == 512
+
+
+# ---------------------------------------------------------------------------
+# Reply loop wiring
+# ---------------------------------------------------------------------------
+
+def _mock_cfg(num_predict):
+    cfg = Mock()
+    cfg.ollama_base_url = "http://localhost:11434"
+    cfg.ollama_chat_model = "test-large"  # avoid SMALL-model text-tool path
+    cfg.ollama_num_predict = num_predict
+    cfg.voice_debug = False
+    cfg.llm_tools_timeout_sec = 8.0
+    cfg.llm_embed_timeout_sec = 10.0
+    cfg.llm_chat_timeout_sec = 45.0
+    cfg.llm_digest_timeout_sec = 8.0
+    cfg.memory_enrichment_max_results = 5
+    cfg.memory_enrichment_source = "diary"
+    cfg.memory_digest_enabled = False
+    cfg.tool_result_digest_enabled = False
+    cfg.location_ip_address = None
+    cfg.location_auto_detect = False
+    cfg.location_enabled = False
+    cfg.agentic_max_turns = 8
+    cfg.tool_search_max_calls = 3
+    cfg.tool_selection_strategy = "all"
+    cfg.tool_carryover_max_turns = 2
+    cfg.tool_carryover_per_entry_chars = 1200
+    cfg.mcps = {}
+    cfg.llm_thinking_enabled = False
+    cfg.tts_engine = "none"
+    cfg.ollama_embed_model = "test-embed"
+    return cfg
+
+
+def _run_single_turn(cfg):
+    """Drive one reply turn that answers in plain text and capture the
+    chat call's extra_options."""
+    with patch("src.jarvis.reply.engine.plan_query", return_value=[]), \
+         patch("src.jarvis.reply.engine.extract_search_params_for_memory", return_value={}), \
+         patch("src.jarvis.reply.engine.extract_text_from_response", return_value="Hello."), \
+         patch("src.jarvis.reply.engine.chat_with_messages") as mock_chat:
+        mock_chat.return_value = {"message": {"content": "Hello."}}
+        run_reply_engine(db=Mock(), cfg=cfg, tts=None,
+                         text="hi", dialogue_memory=DialogueMemory())
+        assert mock_chat.called
+        return mock_chat.call_args.kwargs.get("extra_options")
+
+
+@pytest.mark.unit
+def test_reply_loop_caps_output_when_enabled():
+    extra = _run_single_turn(_mock_cfg(512))
+    assert extra == {"num_predict": 512}
+
+
+@pytest.mark.unit
+def test_reply_loop_no_cap_when_zero():
+    extra = _run_single_turn(_mock_cfg(0))
+    assert extra is None