Add conversation branching to insight chat (rewind preserves forks)

Store chat history as a tree in training_messages instead of a flat
array. Rewind now sets active_leaf_id to the target node rather than
truncating, so discarded paths survive as alternate branches. Fork
indicators ("X/Y") mark divergence points and let the client load or
switch to alternate paths.

- llm_client: StoredChatNode/ChatHistoryStore with tree traversal
  helpers (path_to_leaf, children_of, fork_at_node, leaves*, etc.) and
  from_flat_array for backward-compatible reads of the old flat format.
- insight_chat: load_history/chat_turn/rewind_history operate on the
  tree; new switch_branch and get_branches. render_tree_path walks every
  node (including non-rendered tool-dispatch nodes) when computing fork
  info, so a fork whose diverging child is a tool call still surfaces on
  the following rendered message.
- handlers: GET /insights/chat/branches, POST /insights/chat/switch-branch,
  and a branch_id param on the history endpoint.

Backward-compatible: flat arrays are converted to a tree lazily on read.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

src/ai/mod.rs

@@ -25,12 +25,12 @@ pub use daily_summary_job::{
     generate_daily_summaries, strip_summary_boilerplate,
 };
 pub use handlers::{
-    cancel_generation_handler, cancel_turn_handler, chat_history_handler, chat_rewind_handler,
-    chat_stream_handler, chat_turn_handler, delete_insight_handler, export_training_data_handler,
-    generate_agentic_insight_handler, generate_insight_handler, generation_status_handler,
-    get_all_insights_handler, get_available_models_handler, get_insight_handler,
-    get_insight_history_handler, get_openrouter_models_handler, rate_insight_handler,
-    turn_async_handler, turn_replay_handler,
+    cancel_generation_handler, cancel_turn_handler, chat_branches_handler, chat_history_handler,
+    chat_rewind_handler, chat_stream_handler, chat_switch_branch_handler, chat_turn_handler,
+    delete_insight_handler, export_training_data_handler, generate_agentic_insight_handler,
+    generate_insight_handler, generation_status_handler, get_all_insights_handler,
+    get_available_models_handler, get_insight_handler, get_insight_history_handler,
+    get_openrouter_models_handler, rate_insight_handler, turn_async_handler, turn_replay_handler,
 };
 pub use insight_generator::InsightGenerator;
 pub use llamacpp::LlamaCppClient;