feat(codex-bridge): change the chat model by saying so; bridge 8, IDE 1.0.0-beta.27

A model picked on the phone only arrives with a typed message that starts a turn. The bridge now
handles "modeli X yap" itself: per-chat routing, same-turn handover when a model is working,
truthful answer to "which model", and a lone "." joining a running turn no longer cuts the work.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

apps/desktop/assets/codex-bridge/README.md

@@ -27,6 +27,24 @@ Run: `python bridge.py --home <data dir> --hermes-home <agent home>`. The IDE wr
 
 Tests: `python -m unittest discover` in this directory.
 
+## Version 8 (IDE beta.27): changing the model by saying so
+
+Measured on a live voice chat (11 Oct 2026): a model picked on the phone reaches this machine only with a typed
+message that STARTS a turn; a message that joins a running turn (including the lone `.`) does not carry it.
+`model_gecis.py` therefore handles the change in the bridge. A short user message such as "modeli gemini flash low
+yap" (spoken through the voice assistant or typed) is matched against the model list; the chat's requests are then
+routed to that model (`model-yonlendirme.json`, keyed by `prompt_cache_key`) until Codex sends a different model
+for the chat, i.e. until the user picks another one in the list.
+
+- Idle chat: the bridge answers itself ("Sohbetin modeli artık X ..."), which also tells the voice assistant.
+- Running turn: the command is replaced by a handover note and the SAME turn continues on the new model.
+- "seçili model hangisi" / "ana model kim" is answered by the bridge with the model actually in use.
+- An ambiguous name changes nothing and lists the closest names; a name matching no model is not a command.
+- A lone `.` that joins a running turn is dropped instead of answered (answering it cut the work short).
+- Handled commands left in the history are turned into notes so a later model does not answer them again.
+
+Setting: `sesle_model` (default on).
+
 ## Version 7 (IDE beta.26): external models behave like subscription models
 
 Measured on 10 Oct 2026 with the unmodified Codex binary (`codex exec`, same conversation, model switched per turn).