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>
This commit is contained in:
Alexandre Teixeira
2026-08-14 08:10:30 +01:00
committed by GitHub
co-authored by RaresKeY StressTestor
parent b52296471b
commit c4369305f0
46 changed files with 11418 additions and 1006 deletions
+5 -3
View File
@@ -8,15 +8,15 @@ from bs4 import BeautifulSoup
_REPO = Path(__file__).resolve().parents[1]
def test_legacy_default_fallback_editor_is_hidden():
def test_legacy_default_fallback_editor_is_absent():
soup = BeautifulSoup(
(_REPO / "static" / "index.html").read_text(encoding="utf-8"),
"html.parser",
)
editor = soup.find(id="set-defaultFallbacks")
assert editor is not None
assert editor.find_parent(class_="settings-row").has_attr("hidden")
assert editor is None
assert soup.find(id="set-defaultAddFallback") is None
def test_default_model_save_does_not_rewrite_legacy_fallbacks():
@@ -27,3 +27,5 @@ def test_default_model_save_does_not_rewrite_legacy_fallbacks():
assert "settings.default_model_fallbacks" not in default_chat_source
assert "default_model_fallbacks:" not in default_chat_source
assert "set-defaultFallbacks" not in default_chat_source
assert "set-defaultAddFallback" not in default_chat_source