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>

tests/test_model_routes.py

@@ -98,6 +98,9 @@ def test_endpoint_cleanup_preserves_legacy_default_fallback_data():
             {"endpoint_id": "dead", "model": "fallback-a"},
             {"endpoint_id": "keep", "model": "fallback-b"},
         ],
+        "foreground_model_fallbacks": [
+            {"endpoint_id": "dead", "model": "foreground"},
+        ],
         "utility_model_fallbacks": [{"endpoint_id": "dead", "model": "utility"}],
         "vision_model_fallbacks": [{"endpoint_id": "dead", "model": "vision"}],
         "stt_provider": "endpoint:dead",
@@ -106,12 +109,14 @@ def test_endpoint_cleanup_preserves_legacy_default_fallback_data():
 
     assert _endpoint_settings_using_endpoint(settings, "dead", include_speech=True) == [
         "Default Model",
+        "Foreground Model Fallbacks",
         "Utility Model Fallbacks",
         "Vision Model Fallbacks",
         "Speech to Text",
     ]
     assert _clear_endpoint_settings_for_endpoint(settings, "dead", include_speech=True) == [
         "Default Model",
+        "Foreground Model Fallbacks",
         "Utility Model Fallbacks",
         "Vision Model Fallbacks",
         "Speech to Text",
@@ -122,6 +127,7 @@ def test_endpoint_cleanup_preserves_legacy_default_fallback_data():
         {"endpoint_id": "dead", "model": "fallback-a"},
         {"endpoint_id": "keep", "model": "fallback-b"},
     ]
+    assert settings["foreground_model_fallbacks"] == []
     assert settings["utility_model_fallbacks"] == []
     assert settings["vision_model_fallbacks"] == []
     assert settings["stt_provider"] == "disabled"
@@ -130,10 +136,19 @@ def test_endpoint_cleanup_preserves_legacy_default_fallback_data():
 
 def test_endpoint_cleanup_updates_active_scoped_prefs_but_preserves_legacy_data():
     scoped = {
+        "foreground_model_fallbacks": [
+            {"endpoint_id": "dead", "model": "ownerless"},
+        ],
+        "default_model_fallbacks": [
+            {"endpoint_id": "dead", "model": "legacy-ownerless"},
+        ],
         "_users": {
             "alice": {
                 "utility_endpoint_id": "dead",
                 "utility_model": "utility",
+                "foreground_model_fallbacks": [
+                    {"endpoint_id": "dead", "model": "foreground"},
+                ],
                 "vision_model_fallbacks": [{"endpoint_id": "dead", "model": "vision"}],
             },
             "bob": {
@@ -142,10 +157,15 @@ def test_endpoint_cleanup_updates_active_scoped_prefs_but_preserves_legacy_data(
             },
         },
     }
-    assert _clear_user_pref_endpoint_refs(scoped, "dead") == 1
+    assert _clear_user_pref_endpoint_refs(scoped, "dead") == 2
+    assert scoped["foreground_model_fallbacks"] == []
+    assert scoped["default_model_fallbacks"] == [
+        {"endpoint_id": "dead", "model": "legacy-ownerless"},
+    ]
     assert scoped["_users"]["alice"] == {
         "utility_endpoint_id": "",
         "utility_model": "",
+        "foreground_model_fallbacks": [],
         "vision_model_fallbacks": [],
     }
     assert scoped["_users"]["bob"]["default_endpoint_id"] == "keep"