scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/47834/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:12 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 34 commits »
scriptoriumadmin synced commits to refs/pull/47858/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:12 +00:00
572832dea1 fix(gemini)!: answer 400 for an unsupported chat audio format, drop it under drop_params (#49423)
ff3983c1f6 fix(wandb): set DeepSeek-V3.1 and Llama-3.1-8B max_input_tokens from the CoreWeave Forge page (#49616)
Compare 3 commits »
scriptoriumadmin synced commits to refs/pull/47860/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:12 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 34 commits »
scriptoriumadmin synced commits to refs/pull/47833/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:12 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 279 commits »
scriptoriumadmin synced commits to refs/pull/47845/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:12 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 34 commits »
scriptoriumadmin synced commits to refs/pull/47850/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:12 +00:00
fcef9cd0a3 feat(videos): serve custom_provider_map BaseVideoConfig providers on /v1/videos (#49785)
34314a99f0 fix(messages): make rust messages copy python messages behaviour (#49611)
5e08cb0e63 test(messages): add rust vs python messages parity characterization suite (#49610)
216041e243 feat(decisions): add Parallel AI web-grounded decisions (#49188)
Compare 66 commits »
scriptoriumadmin synced commits to refs/pull/47865/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:12 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 93 commits »
scriptoriumadmin synced commits to refs/pull/47844/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:12 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 111 commits »
scriptoriumadmin synced commits to refs/pull/47846/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:12 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 34 commits »
scriptoriumadmin synced commits to refs/pull/47817/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:12 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 196 commits »
scriptoriumadmin synced commits to refs/pull/47679/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:11 +00:00
ee402443f3 fix(count_tokens): leave count_tokenizer out of responses that no named tokenizer counted
3e0c4f6e5d refactor(count_tokens): return local tokenizer failures as values and raise them at one boundary
9f0042e207 refactor(count_tokens): keep the count handler as simple as before and its annotations read-only
c2c152f060 refactor(count_tokens): share the tokenizer count call and keep estimate types exact
a6e10cdcdd merge: origin/main into litellm_bedrock-local-token-count-marker
Compare 768 commits »
scriptoriumadmin synced commits to refs/pull/47679/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:11 +00:00
ee402443f3 fix(count_tokens): leave count_tokenizer out of responses that no named tokenizer counted
0bd677afef test(integration): look up streamed Responses spend rows by the client-facing id (#49752)
3e0c4f6e5d refactor(count_tokens): return local tokenizer failures as values and raise them at one boundary
4187e1ae89 fix(managed_files): keep the upload the managed id encodes when two target models share a deployment (#49420)
Compare 762 commits »
scriptoriumadmin synced commits to refs/pull/47801/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:11 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 34 commits »
scriptoriumadmin synced commits to refs/pull/47713/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:11 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 34 commits »
scriptoriumadmin synced commits to refs/pull/47816/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:11 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 180 commits »
scriptoriumadmin synced commits to refs/pull/47629/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:11 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 91 commits »
scriptoriumadmin synced commits to refs/pull/47795/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:11 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 177 commits »
scriptoriumadmin synced commits to refs/pull/47734/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:11 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 168 commits »
scriptoriumadmin synced commits to refs/pull/47733/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:11 +00:00
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
3af23024bc test(e2e): share the coding-CLI harness between suites (#49370)
0ea7e96a66 test(integration): repair agent reads and bulk deletion setup (#49719)
b4a80d175c ci: remove workflows whose secrets are dead (#49722)
Compare 89 commits »
scriptoriumadmin synced commits to refs/pull/47676/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:11 +00:00
838467fea6 test(proxy): check the shared cold seed wait limit with a controlled clock
0ad56125d2 fix(proxy): set a missing cold counter with SET NX instead of a timed re-read
2e83346cb2 fix(proxy): give a cold seed's re-read its own time after a late add
58b3e1b6d8 fix(proxy): run a cold seed in the request's own task and bound its re-read
Compare 4 commits »