feat(voice): unify Discord voice↔text session (squash of voice/text-unify)

Voice utterances and text messages on the same Discord channel now share
one Claude session, and Echo's voice replies are mirrored back into the
text channel. Replaces the old voice:<id> session-key split.

Changes:
- src/adapters/_text_chunks.py: new leaf module for split_message
  (used by both discord_bot and voice pipeline)
- src/router.py: drop voice: prefix from session_key; add [voice] marker;
  strip leading [speaker:/[voice] tokens from user input (anti-jailbreak);
  remove dead double-clear of voice: key
- src/claude_session.py: include personality/VOICE_MODE.md unconditionally
  (rules become per-turn-aware via [speaker:] prefix instead of session flag)
- src/voice/pipeline.py: VoiceSession splits text_channel_id +
  voice_channel_id; resolve text channel per-send (no stale refs); mirror
  Echo's reply text into the text channel after route_message returns
- src/adapters/discord_voice.py: /voice join passes both channel ids
- src/adapters/discord_bot.py: import split_message from leaf module
- personality/VOICE_MODE.md: rewrite as per-turn dynamic rules;
  add synthesis instructions for text turns after voice turns

Tests:
- tests/test_router.py: 4 new cases (plain channel_id, anti-jailbreak,
  text-adapter regression, no-double-clear)
- tests/test_pipeline_mirror.py: new — Echo reply mirror chunking,
  empty guard, mirror_enabled=False, send-raises resilience
- tests/test_voice_session_channel_ids.py: new — split-attr contract
  + metrics payload schema
- tests/test_voice_session_cleanup.py: update for new kwargs

Plan: /home/moltbot/.claude/plans/vreau-ca-tot-textul-greedy-rivest.md

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

src/router.py

@@ -3,6 +3,7 @@
 import json
 import logging
 import os
+import re
 import signal
 from datetime import datetime, timezone
 from pathlib import Path
@@ -31,6 +32,20 @@ log = logging.getLogger(__name__)
 
 APPROVED_TASKS_FILE = Path(__file__).parent.parent / "approved-tasks.json"
 
+# Anti-jailbreak: strip user-controlled leading [voice] / [speaker:...]
+# tokens so they cannot impersonate the system-injected prefix on voice turns.
+_LEADING_VOICE_TOKEN_RE = re.compile(
+    r'^\s*(?:\[voice\]|\[speaker:[^\]]*\])\s*', re.IGNORECASE
+)
+
+
+def _strip_leading_voice_tokens(text: str) -> str:
+    while True:
+        stripped = _LEADING_VOICE_TOKEN_RE.sub('', text, count=1)
+        if stripped == text:
+            return text
+        text = stripped
+
 # Module-level config instance (lazy singleton)
 _config: Config | None = None
 
@@ -63,6 +78,7 @@ def route_message(
     adapter-specific response shaping (e.g., redirect line on WhatsApp).
     """
     text = text.strip()
+    text = _strip_leading_voice_tokens(text)
 
     # ---- Planning state-aware routing -----------------------------------
     # If the channel is in an active planning session, the user's message is
@@ -124,8 +140,6 @@ def route_message(
     if text.lower() == "/clear":
         default_model = _get_config().get("bot.default_model", "sonnet")
         cleared_text = clear_session(channel_id)
-        # Also drop the isolated voice session if one exists on this channel.
-        clear_session(f"voice:{channel_id}")
         if cleared_text:
             return f"Session cleared. Model reset to {default_model}.", True
         return "No active session.", True
@@ -156,18 +170,15 @@ def route_message(
             channel_cfg = _get_channel_config(channel_id)
             model = (channel_cfg or {}).get("default_model") or _get_config().get("bot.default_model", "sonnet")
 
-    # Voice-mode augment: prepend speaker prefix so Claude knows who spoke
-    # in a voice channel. Cheap now, future-proof for multi-speaker later.
-    # (Engineering decision #14 in the plan.) Only the discord-voice adapter
-    # triggers it — text adapters keep the message verbatim.
+    # Voice turns get a system-controlled [voice] [speaker:NAME] prefix so
+    # VOICE_MODE.md rules self-activate per-turn. Session key is the plain
+    # channel_id — voice + text share one Claude session on the same channel.
     claude_text = text
     voice_mode = adapter_name == "discord-voice"
     if voice_mode:
         user_name = _get_config().get("voice.user_name", "user") or "user"
-        claude_text = f"[speaker:{user_name}] {text}"
-    # Voice sessions use an isolated session key so they start fresh with
-    # VOICE_MODE.md and don't pollute the text channel's conversation.
-    session_key = f"voice:{channel_id}" if voice_mode else channel_id
+        claude_text = f"[voice] [speaker:{user_name}] {text}"
+    session_key = channel_id
 
     try:
         response = send_message(