feat: Python parity for wol / banter / conversation / ddg_answer + 11 tests

New `wave59_handlers.py` (~250 lines) mirroring four Rust-only packs:

- wol: pure-Python magic packet via socket + SO_BROADCAST. No PowerShell
  shellout (unlike the Rust pack). Reads MAC from memory_store under
  'wol_<alias>' or JARVIS_WOL_TARGET env. Same MAC format tolerance
  (colons / dashes / dots / bare) as the Rust normaliser.

- banter: pause/resume state + fire-one. Python edition doesn't run a
  background banter thread (the Rust daemon already does), so this is
  just the user-facing surface — same voice phrases work.

- conversation: do_conversation_summary calls Groq with last 12 turns
  from main.py's `message_log`. set_history_ref() injects the live list
  reference at startup so the handler reads up-to-date history without
  a circular import. Offline-safe: GROQ_TOKEN missing → speak the last
  user message instead. do_conversation_repeat re-speaks the last
  assistant turn.

- ddg_answer: urllib + DuckDuckGo Instant Answer JSON. Picks
  AbstractText → Answer → Definition → RelatedTopics[0]. Opens
  duckduckgo.com search fallback when nothing instant.

extensions.py / main.py / commands.yaml: 7 new dispatch entries +
proxy fns. commands.yaml now at 207 entries.

tests/test_wave59_handlers.py: 11 unit tests for MAC normalisation,
magic packet shape, WOL error paths, banter state machine, DDG trigger
stripping, conversation history handling. Network calls deliberately
NOT exercised here — they belong to integration tests.

Tests: 104 → 115 (+11).

main.py

@@ -112,6 +112,15 @@ system_message = {"role": "system", "content": (
 )}
 message_log = [system_message]
 
+# Let wave59_handlers.do_conversation_* read the live history without
+# circular-importing main.py. The reference is shared (the list is mutated
+# in-place by `va_respond`), so summary/repeat always see the latest turns.
+try:
+    import wave59_handlers as _w59
+    _w59.set_history_ref(message_log)
+except ImportError:
+    pass
+
 client = OpenAI(api_key=config.GROQ_TOKEN, base_url=config.GROQ_BASE_URL)
 
 model = vosk.Model("model_small")
@@ -1805,6 +1814,20 @@ def run_action(action):
         extensions.do_expenses_week(action, _current_voice or '')
     elif t == 'expenses_breakdown':
         extensions.do_expenses_breakdown(action, _current_voice or '')
+    elif t == 'wol':
+        extensions.do_wol(action, _current_voice or '')
+    elif t == 'banter_fire':
+        extensions.do_banter_fire(action, _current_voice or '')
+    elif t == 'banter_pause':
+        extensions.do_banter_pause(action, _current_voice or '')
+    elif t == 'banter_resume':
+        extensions.do_banter_resume(action, _current_voice or '')
+    elif t == 'conversation_summary':
+        extensions.do_conversation_summary(action, _current_voice or '')
+    elif t == 'conversation_repeat':
+        extensions.do_conversation_repeat(action, _current_voice or '')
+    elif t == 'ddg_answer':
+        extensions.do_ddg_answer(action, _current_voice or '')
 
 
 _current_voice: str = ''