* [Feat] add ElevenLabs `eleven_v3` and `eleven_multilingual_v2` to model cost map
Register ElevenLabs TTS models for cost tracking:
- elevenlabs/eleven_v3: most expressive model, 70+ languages, audio tags
- elevenlabs/eleven_multilingual_v2: default TTS model, 29 languages
Also update ElevenLabs docs with supported models table and eleven_v3 audio tags example.
* docs: remove model-agnostic tip from ElevenLabs docs
* docs(web_search): clarify OpenAI search model requirements
- Add gpt-5-search-api to supported OpenAI search models
- Add warning that regular models (gpt-5, gpt-4.1) do NOT support web_search_options
- Add tip that web_search_options is optional for search models
* feat(models): add gpt-5-search-api pricing for OpenAI and Azure
Create fresh mock objects within the test instead of reusing mocks
from setUp that have side_effect configured. The setUp's side_effect
on mock_langfuse_client.trace can interfere with return_value settings
when tests try to reset and reconfigure mocks.
Using dedicated mock objects for this test avoids state pollution
from setUp's side_effect configuration and makes the test more
deterministic in parallel execution environments.
Set cached tokenizer config directly and mock both sync and async
tokenizer functions to avoid race conditions when running with
parallel test execution (-n 16).
The issue was that parallel tests could populate the
litellm.known_tokenizer_config cache between clearing it and
when the code checked it. This caused the sync code path to be
used instead of the async path, bypassing the mocked async functions.
Fix:
1. Set cache directly instead of clearing it
2. Also mock sync versions _get_tokenizer_config and _get_chat_template_file
This ensures the test is deterministic regardless of test execution order.
Unify follow-up fixes for Opus 4.6 pricing and routing metadata into
a single changeset.
Set long-context-capable Opus 4.6 entries to 1M input tokens where
>200K pricing is defined, align alias and dated capability metadata,
and add Bedrock Converse v1 IDs with and without :0 suffixes.
Keep regional endpoint pricing at a 10% premium over global entries
and mirror all cost-map changes in the backup file used for local
loading and offline fallback behavior.
Extend Opus 4.6 regression tests to verify metadata parity, Bedrock
regional pricing parity across :0 and non-:0 IDs, and converse model
registration in constants and runtime model sets.
Add Claude Opus 4.6 entries for Anthropic, Bedrock Converse, and Vertex AI.
Align pricing and capability metadata with Anthropic docs, including
long-context rates, above-200k prompt-caching rates, prefill removal,
and tool-use system prompt token counts.
Register the Bedrock Converse model ID in constants and add targeted
tests to validate model map values and converse registration.
The daily spend tables store dates in UTC, but the UI sends dates in the
user's local timezone. This causes a mismatch where records from the
user's evening (stored as the next UTC day) don't appear when filtering
by "today".
Changes:
- Add `_adjust_dates_for_timezone()` helper to expand date range based
on timezone offset
- Add `timezone` query parameter to `/user/daily/activity` and
`/user/daily/activity/aggregated` endpoints
- Frontend sends `timezone` using `Date.getTimezoneOffset()`
For users west of UTC (e.g., PST), end_date is extended by 1 day.
For users east of UTC (e.g., IST), start_date is extended by 1 day earlier.
This ensures all records within the user's local date range are captured.
This PR:Fixes a frontend regression where the
PublicModelHub
page would crash with TypeError: e.filter is not a function when the API returned an error object (e.g. { "detail": "..." }) instead of the expected data array.
Changes:
Added defensive Array.isArray() checks in
src/components/public_model_hub.tsx
for:
modelHubData
agentHubData
mcpHubData
Updated useMemo hooks and helper functions to handle invalid data gracefully.
Added a regression test in
src/components/public_model_hub.test.tsx
that mocks a non-array API response to ensure the component renders without crashing.
