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>

src/task_endpoint.py

@@ -1,7 +1,6 @@
 """Shared resolver for background-task AI endpoints."""
 
 from src.endpoint_resolver import (
-    resolve_chat_fallback_candidates,
     resolve_endpoint,
     resolve_utility_fallback_candidates,
 )
@@ -32,7 +31,6 @@ def resolve_task_candidates(
     2. Utility endpoint/model
     3. Default endpoint/model
     4. Utility fallback chain
-    5. Retired default-fallback compatibility hook (currently empty)
     """
     candidates = []
 
@@ -49,9 +47,6 @@ def resolve_task_candidates(
     _append(*resolve_endpoint("default", owner=owner))
     for url, model, headers in resolve_utility_fallback_candidates(owner=owner):
         _append(url, model, headers)
-    for url, model, headers in resolve_chat_fallback_candidates(owner=owner):
-        _append(url, model, headers)
-
     return candidates