fix: force tool calls for drifted intents and harden tool-use prompt

Small local models (qwen2.5-vl-3b, gemma-4-e4b) narrate actions ('Sure,
I'll pause the music') without emitting the tool call once the full
system prompt and 26-tool set are in context. Measured: qwen emitted
tools in 2/8 realistic intents, gemma 5/8; single-tool tests pass 100%,
so this is context-induced drift, not plumbing.

- agent/intent_router.py: deterministic forced-call router for
  high-frequency intents — media controls, now_playing/list_library,
  'remember that ...' memory saves, explicit YouTube Music searches,
  and personal-fact recall (memory_recall/search_notes/skill_recall,
  excluded for weather/time questions). Fires only when the tool is
  available; guards against how-do-I questions.
- agent.py: generalize _ForcedToolCallStream to any tool; route through
  intent_router after the dispatch check. System prompt adds a hard
  'call, don't narrate' rule and reconditions 'answer directly'.
- tests/test_intent_router.py: 30 unit tests pinning router behavior.

Verified against the live LLM with the full fidelity harness: combined
forced-or-emitted coverage 8/8 on qwen2.5-vl-3b (was 2/8) and 8/8 on
gemma-4-e4b (was 5/8). Full suite: 79 passed.

Dockerfile

@@ -47,6 +47,7 @@ COPY agent/weather_mcp.py /opt/voice-agent/weather_mcp.py
 COPY agent/skills_mcp.py /opt/voice-agent/skills_mcp.py
 COPY agent/task_registry.py /opt/voice-agent/task_registry.py
 COPY agent/task_router.py /opt/voice-agent/task_router.py
+COPY agent/intent_router.py /opt/voice-agent/intent_router.py
 COPY agent/task_worker.py /opt/voice-agent/task_worker.py
 COPY agent/dispatch_mcp.py /opt/voice-agent/dispatch_mcp.py
 COPY agent/media_mcp.py /opt/voice-agent/media_mcp.py