* fix(tests): keep foreign asyncio task noise out of the budget limiter caplog asserts
The two gc.collect()-under-caplog tests in test_budget_limiter_hotpath.py asserted
on every captured record, so a LoggingWorker task another test had parked on the
session fixture loop got destroyed inside their window and asyncio's "Task was
destroyed but it is pending!" error failed them. They now assert only the limiter
logger's records and park a pending task on a closed loop in the window themselves,
so the noise is exercised on every run
The edenai and sail spend_capture fixtures no longer start the worker from the
session loop: the test's own call and its flush bind the worker to the test loop
* test(router_strategy): drop only asyncio records in the limiter caplog asserts and drain the response cache worker on the test loop
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Register Sail (providers.json, LlmProviders.SAIL, OpenAI-compatible lists,
ProviderConfigManager) for chat, Responses and /v1/messages, and add its 12
models to both cost maps with asap, balanced and flex price columns.
Sail picks speed and price with metadata.completion_window and rejects
service_tier, so the Sail chat and Responses configs translate the tier:
default and priority to asap, flex to flex, balanced to balanced, auto to no
window. Billing prices the window that was sent. A tier Sail has no window
for, or a window or tier set where billing cannot see it (request metadata,
extra_body), is a 400 unless drop_params is set.
Add balanced to ServiceTier and its _balanced price columns to the model
info types, the Rust catalog and the dashboard schema. A transform_extra_body
hook on the chat and Responses base configs, which returns extra_body
unchanged by default, lets Sail keep the window when a caller also sends
extra_body.metadata. Sail is listed in the Add Model form and model picker.
Co-authored-by: shrey kharbanda <shrey@berri.ai>
