Commit graph

7 commits

Author SHA1 Message Date
mateo-berri
3030e974b8 fix(runwayml): skip progress scaling when Runway returns a null progress 2026-08-24 12:20:00 -07:00
mateo-berri
6407a66375 fix(runwayml): route every generation endpoint and fix video cost tracking
Six defects in the RunwayML video provider:

- transform_video_create_request hardcoded /image_to_video, so text-to-video 400'd and video-to-video was unreachable; the endpoint is now selected from the inputs present (promptVideo/videoUri, promptImage, or text only)
- get_error_class raised instead of returning, turning a provider 4xx into a proxy 500 APIConnectionError; it now returns a RunwayMLError
- VideoObject.progress was typed int while Runway sends a 0..1 float, 500'ing status polls while RUNNING; it is now scaled to a 0..100 percent
- custom per-deployment pricing stored under litellm_metadata was ignored for video; the deployment model_info lookup now checks both metadata keys
- stale cost-map entries (gen3a_turbo, gen4_aleph) were removed and current models added, with output_cost_per_second_480p/_4k tier keys plumbed through the model-info and router types
- video cost now falls back to Runway's estimatedCost from the create response when no custom pricing is configured, and custom pricing always wins over it

Fixes #36483
2026-08-24 11:23:03 -07:00
yuneng-jiang
6a0d03914c
test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)
* test: drop the cwd-relative sys.path.insert calls from the test suite

TQ003 stands at 1,077 across 1,058 files, and 1,015 of them are the same shape:
sys.path.insert(0, os.path.abspath("../..")) and its deeper siblings. The
argument resolves against the working directory rather than the file, so from
the repo root, where every job runs pytest, it inserts the directory two levels
above the checkout. It has never pointed at litellm. The package is installed
into the environment anyway, which is what actually makes the import work, and
what the rule's message has said all along.

Removing them leaves 1,634 imports of sys and os with no remaining reference,
and those go too, except where another test module imports the name back out of
the file. The rest of TQ003 is 62 call sites that resolve against __file__ or a
variable, which are a different question and are left alone.

Collection is identical either way: 45,871 tests and the same 51 pre-existing
collection errors before and after, and ruff reports no new undefined name.

* test: drop the duplicate imports the sys.path sweep exposed to F811

* test(pre-call-utils): restore the os import the new bedrock tests need
2026-08-22 09:25:58 -07:00
user
d4dd865b1a fix: encode upstream URL path identifiers 2026-04-29 22:02:39 -07:00
Ishaan Jaffer
e8461b5b97
style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
Ishaan Jaff
124ba463f8
[Feat] RunwayML - Add support for /audio/speech eleven_multilingual_v2 endpoint (#16604)
* init RunwayMLTextToSpeechConfig

* add RunwayMLTextToSpeechConfig

* add  RunwayMLTextToSpeechConfig

* test_runwayml_tts_async

* runway ml speech

* fix voices

* fix test

* docs runway lm

* add runwayml here

* fix RunwayMLTextToSpeechConfig

* test_openai_voice_mapping_to_runwayml
2025-11-13 14:32:09 -08:00
Ishaan Jaff
b30439257b
[Feat] Add RunwayML Img Gen API support (#16557)
* TestRunwaymlImageGeneration

* fix RUNWAYML

* rename

* fix rename

* get_runwayml_image_generation_config

* get_runwayml_image_generation_config

* TestRunwaymlImageGeneration

* add RUNWAYML_POLLING_TIMEOUT

* fix rnwayml transform img gen

* runwayml_image_cost_calculator

* runwayml_image_cost_calculator

* docs runwayml

* fix runwayML polling

* test_get_first_default_fallback
2025-11-12 18:20:14 -08:00