refactor(model-routing): centralize explicit foreground fallback policy (#6020)

* refactor(model-routing): centralize explicit foreground fallback policy

Make foreground fallback an explicit per-user, availability-only policy shared by streaming Chat, non-stream Chat, and Agent runs.

Preserve strict defaults, owner/model and credential boundaries, pinned Agent routes, and truthful per-round provenance/accounting. Carry provider-reported model identifiers through native streaming adapters, non-stream responses, and caches, and keep legacy default_model_fallbacks as tombstoned raw storage that generic settings APIs and agent tools cannot expose or mutate.

* fix(agent-loop): restore rebase-dropped qwen routing, workspace prompt, and temperature clamp

* fix(model-routing): thread selected endpoint identity, fix cost classification and fallback eligibility

* fix(chat): restore stream helpers and harden run stop lifecycle

* fix(model-routing): let numeric provider codes win over symbolic rate-limit statuses

* fix(agent-loop): apply qwen temperature and notes-tool clamps per fallback candidate

* fix(chat): honor queued stop across resend and reload canonical terminal on EOF

* fix(chat): track stop queue and cleanup ownership by per-send generation

* fix(agent-loop): preserve requested temperature for non-qwen fallback candidates

* fix(chat): reserve send ownership before any await and scope stop to the current send

* fix(chat): clear the previous run identity at send reservation

---------

Co-authored-by: RaresKeY <158580472+RaresKeY@users.noreply.github.com>
Co-authored-by: StressTestor <212606152+StressTestor@users.noreply.github.com>

routes/auth_routes.py

@@ -22,6 +22,8 @@ from src.settings import (
     load_features as _load_features,
     save_features as _save_features,
     DEFAULT_SETTINGS,
+    RETIRED_SETTING_KEYS,
+    without_retired_settings,
 )
 from src.integrations import (
     load_integrations,
@@ -689,7 +691,7 @@ def setup_auth_routes(auth_manager: AuthManager) -> APIRouter:
         a scrubbed copy with secret keys blanked. The frontend uses this
         for keybinds + TTS prefs, so it stays callable without admin."""
         user = _get_current_user(request)
-        settings = _load_settings()
+        settings = without_retired_settings(_load_settings())
         if user and auth_manager.is_admin(user):
             return settings
         return scrub_settings(settings)
@@ -709,6 +711,8 @@ def setup_auth_routes(auth_manager: AuthManager) -> APIRouter:
             "agent_max_tool_calls": (0, 1000),  # 0 = unlimited
         }
         for key in DEFAULT_SETTINGS:
+            if key in RETIRED_SETTING_KEYS:
+                continue
             if key not in body:
                 continue
             val = body[key]
@@ -721,7 +725,7 @@ def setup_auth_routes(auth_manager: AuthManager) -> APIRouter:
                 val = max(lo, min(val, hi))
             current[key] = val
         _save_settings(current)
-        return current
+        return without_retired_settings(current)
 
     # ---- Integrations CRUD ----