perf: unify Ollama num_ctx so a voice turn keeps one resident model

Ollama keeps a separate loaded model instance per (model, num_ctx). The
main agentic chat used num_ctx=8192 while the router/enrichment/digest
passes used 4096, so every voice turn forced at least one cold reload
(~3.4s) when switching context sizes — the dominant per-turn latency
(measured: resident chat call 0.27s vs cold 3.4s).

Introduce a single OLLAMA_NUM_CTX (default 8192, env-tunable for tight
VRAM) used by call_llm_direct, chat_with_messages, call_llm_streaming and
the planner, collapsing a turn to one resident instance.

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

src/jarvis/llm.py

@@ -2,24 +2,37 @@
 
 from __future__ import annotations
 from typing import Optional, Any, Dict, List, Generator, Callable
+import os
 import requests
 import json
 
 from .debug import debug_log
 
 
+# Single context-window size shared by EVERY Ollama call (chat, router,
+# enrichment, digests, streaming). Ollama keeps a SEPARATE loaded model
+# instance per (model, num_ctx): mixing 4096 and 8192 in one voice turn made
+# it evict and cold-reload the model (~3.4s each) on every context switch —
+# the dominant per-turn latency. Keeping one value collapses this to a single
+# resident instance, so only the very first call of a cold model pays a load.
+# 8192 is the floor the main agentic chat needs (system prompt + tool schema +
+# memory) without silent truncation. Tunable via env for tight-VRAM hosts.
+OLLAMA_NUM_CTX = int(os.environ.get("OLLAMA_NUM_CTX", "8192"))
+
+
 class ToolsNotSupportedError(Exception):
     """Raised when the model returns HTTP 400 because native tool calling is not supported."""
     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 = 4096, temperature: Optional[float] = None) -> Optional[str]:
+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.
 
-    ``num_ctx`` controls Ollama's context window for this call. Default 4096 is
+    ``num_ctx`` controls Ollama's context window for this call. It defaults to
-    fine for small classification-shaped passes; callers that assemble richer
+    the shared ``OLLAMA_NUM_CTX`` so small classification-shaped passes load the
-    prompts (planner with dialogue + memory + tool catalogue) should pass a
+    SAME Ollama instance as the main chat loop (no cold reload on context
-    larger value to avoid silent truncation.
+    switch). Callers may still override it, but diverging from the shared value
+    reintroduces a per-turn model reload.
 
     ``temperature`` is forwarded to Ollama when set. Pass ``0.0`` for
     classification / extraction calls where determinism beats creativity —
@@ -102,7 +115,7 @@ def call_llm_streaming(
         "model": chat_model,
         "messages": messages,
         "stream": True,
-        "options": {"num_ctx": 4096},
+        "options": {"num_ctx": OLLAMA_NUM_CTX},
         "think": thinking,
         # Keep the chat model resident between calls (see call_llm_direct).
         "keep_alive": "30m",
@@ -207,7 +220,7 @@ def chat_with_messages(
         "model": chat_model,
         "messages": messages,
         "stream": False,
-        "options": {"num_ctx": 8192},
+        "options": {"num_ctx": OLLAMA_NUM_CTX},
         "think": thinking,
         # Keep the chat model resident between turns (see call_llm_direct).
         "keep_alive": "30m",

src/jarvis/reply/planner.py

@@ -40,7 +40,7 @@ import re
 from typing import List, Optional, Sequence, Tuple
 
 from ..debug import debug_log
-from ..llm import call_llm_direct
+from ..llm import call_llm_direct, OLLAMA_NUM_CTX
 
 
 # Hard cap on plan length. Small models happily emit 10+ step plans that
@@ -441,7 +441,7 @@ def plan_query(
             user_content=user_content,
             timeout_sec=effective_timeout,
             thinking=False,
-            num_ctx=8192,
+            num_ctx=OLLAMA_NUM_CTX,
         )
     except Exception as exc:  # pragma: no cover — defensive
         debug_log(f"planner: LLM call failed — {exc}", "planning")
@@ -716,7 +716,7 @@ def resolve_next_tool_call(
             user_content=user_content,
             timeout_sec=effective_timeout,
             thinking=False,
-            num_ctx=8192,
+            num_ctx=OLLAMA_NUM_CTX,
         )
     except Exception as exc:  # pragma: no cover — defensive
         debug_log(f"planner.resolve_next_tool_call: LLM failed — {exc}", "planning")