Auto-threading, history pagination, streaming toggle + tool/reasoning display settings

- Auto-threading (Telegram topic-mode workflow): message.send {auto_thread}
  mints a fresh AI-named thread (instant derived title, LLM upgrade via
  channel.renamed); channel.created {auto:true}; the app jumps into the new
  thread and relocates the optimistic pending bubble.
- history frame: paged full message history for initial channel open /
  scroll-up pagination (reconstructed from the outbox log).
- Streaming on/off: gateway side (display.platforms.android.streaming) plus a
  per-device app toggle (Settings → Streaming); reasoning/model/tokens carried
  on message frames.
- Context menu: long-press (touch) / right-click (desktop) thread affordances
  via a KMP rightClick expect/actual.
- Settings → Reasoning: auto-collapse long reasoning blocks (default on).
- Tool detail: the gateway now always supplies full tool data — it forces
  verbose tool progress (full args → tool.start.args) and captures each
  completed call via the post_tool_call hook (output/duration/ok → tool.end).
  The app reveals the full call + output on expand (Truncated) and
  auto-expands cards in Everything mode.

gateway-plugin/protocol.py

@@ -68,6 +68,9 @@ TYPE_SEARCH_RESULTS = "search.results"
 TYPE_SYNC = "sync"
 TYPE_SYNC_DONE = "sync.done"
 
+# Full message history (initial channel open / scroll-up pagination)
+TYPE_HISTORY = "history"
+
 # Media (M4)
 TYPE_MEDIA_UPLOAD_START = "media.upload.start"
 TYPE_MEDIA_UPLOAD_END = "media.upload.end"
@@ -430,9 +433,18 @@ def _channel_payload(entry: Dict[str, Any]) -> Dict[str, Any]:
     return payload
 
 
-def channel_created(entry: Dict[str, Any]) -> Frame:
-    """Broadcast: a channel/thread was created."""
-    return Frame(type=TYPE_CHANNEL_CREATED, payload=_channel_payload(entry))
+def channel_created(entry: Dict[str, Any], auto: bool = False) -> Frame:
+    """Broadcast: a channel/thread was created.
+
+    ``auto=True`` marks a thread the gateway minted itself for an incoming
+    message (auto-threading, docs/06 §6.3): the app jumps into it and the
+    name is an instant derived title, upgraded by the LLM via a follow-up
+    ``channel.renamed``.
+    """
+    payload = _channel_payload(entry)
+    if auto:
+        payload["auto"] = True
+    return Frame(type=TYPE_CHANNEL_CREATED, payload=payload)
 
 
 def channel_renamed(entry: Dict[str, Any]) -> Frame:
@@ -484,6 +496,38 @@ def sync_done(cursor: int, *, id: Optional[int] = None) -> Frame:
     return Frame(type=TYPE_SYNC_DONE, id=id, payload={"cursor": cursor})
 
 
+# ---------------------------------------------------------------------------
+# History frame (full message history for a chat/thread)
+# ---------------------------------------------------------------------------
+
+def history(
+    chat_id: str,
+    messages: List[Dict[str, Any]],
+    has_more: bool,
+    *,
+    thread_id: Optional[str] = None,
+    oldest_message_id: Optional[str] = None,
+    id: Optional[int] = None,
+) -> Frame:
+    """Response to a ``history`` request: a page of final messages for a
+    chat/thread, ordered oldest → newest. ``has_more`` signals older pages
+    exist; ``oldest_message_id`` is the ``before_message_id`` for the next
+    (older) page."""
+    payload: Dict[str, Any] = {
+        "messages": messages,
+        "has_more": has_more,
+    }
+    if oldest_message_id:
+        payload["oldest_message_id"] = oldest_message_id
+    return Frame(
+        type=TYPE_HISTORY,
+        id=id,
+        chat_id=chat_id,
+        thread_id=thread_id,
+        payload=payload,
+    )
+
+
 # ---------------------------------------------------------------------------
 # Push / notification frames (M5)
 # ---------------------------------------------------------------------------