mirror of
https://github.com/pewdiepie-archdaemon/odysseus.git
synced 2026-09-28 02:52:20 +02:00
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:
co-authored by
RaresKeY
StressTestor
parent
b52296471b
commit
c4369305f0
@@ -314,17 +314,21 @@ class TestComputeFinalMetrics:
|
||||
def test_tool_events_included(self):
|
||||
events = [{"tool": "bash", "duration": 1.0}]
|
||||
texts = ["round 1 text"]
|
||||
models = ["round-1-model"]
|
||||
m = _compute_final_metrics(**self._base_args(
|
||||
tool_events=events,
|
||||
round_texts=texts,
|
||||
round_models=models,
|
||||
))
|
||||
assert m["tool_events"] == events
|
||||
assert m["round_texts"] == texts
|
||||
assert m["round_models"] == models
|
||||
|
||||
def test_no_tool_events_excluded(self):
|
||||
m = _compute_final_metrics(**self._base_args(tool_events=[], round_texts=[]))
|
||||
assert "tool_events" not in m
|
||||
assert "round_texts" not in m
|
||||
assert "round_models" not in m
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
Reference in New Issue
Block a user