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
+19 -2
View File
@@ -1491,8 +1491,25 @@ def _migrate_assign_legacy_owner():
with open(prefs_path, "r", encoding="utf-8") as f:
prefs = _json.load(f)
if "_users" not in prefs and prefs:
# Flat format → nest under admin user
new_prefs = {"_users": {admin_user: prefs}}
# Flat format → nest ordinary preferences under the admin
# user. Foreground fallback is an explicit per-owner opt-in,
# so auth-disabled consent must remain inert at the flat root
# rather than becoming consent for the first named owner.
foreground_keys = {
"foreground_fallback_enabled",
"foreground_model_fallbacks",
}
named_prefs = {
key: value
for key, value in prefs.items()
if key not in foreground_keys
}
new_prefs = {
key: prefs[key]
for key in foreground_keys
if key in prefs
}
new_prefs["_users"] = {admin_user: named_prefs}
with open(prefs_path, "w", encoding="utf-8") as f:
_json.dump(new_prefs, f, indent=2)
logger.info(f"Migrated user_prefs.json to per-user format under '{admin_user}'")