scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/46849/merge at scriptoriumadmin/litellm from mirror 2026-10-19 04:56:00 +00:00
8b90649fb7 fix(proxy): sanitize unexpected /key/info database failures (#46190)
2dfeb80e04 fix(bedrock): take the 256K context window from the Qwen3 Coder 480B model card (#47283)
19f69ed6b6 test(integration): wait for every worker in Scenario.model (#47277)
9c958aff34 fix(logging): deliver completed batch success callbacks consistently (#47192)
Compare 31 commits »
scriptoriumadmin synced commits to refs/pull/46744/head at scriptoriumadmin/litellm from mirror 2026-10-19 04:55:59 +00:00
91ebec7c63 feat: add Engy as OpenAI-compatible provider
eb114e638d test(integration): look up owned cache keys and clean up sweep models (#47255)
44d99475a5 test(integration): stop GET /__observations from draining the upstream log (#47256)
cfee0ffe41 fix(pricing): refresh github_copilot rows on current main (#47254)
df71873102 chore(cost-map): add fireworks deepseek v4.1 flash 1017 (#47253)
Compare 11 commits »
scriptoriumadmin synced commits to refs/pull/46750/head at scriptoriumadmin/litellm from mirror 2026-10-19 04:55:59 +00:00
aaf491e80e refactor(rust-bridge): decide native routing in the catalog, drop the bypass predicates
2dfeb80e04 fix(bedrock): take the 256K context window from the Qwen3 Coder 480B model card (#47283)
19f69ed6b6 test(integration): wait for every worker in Scenario.model (#47277)
9c958aff34 fix(logging): deliver completed batch success callbacks consistently (#47192)
7e6fb09da3 fix(streaming)!: map stream read timeouts to litellm.Timeout on chat, messages, and responses (#47198)
Compare 32 commits »
scriptoriumadmin synced commits to refs/pull/46750/merge at scriptoriumadmin/litellm from mirror 2026-10-19 04:55:59 +00:00
aaf491e80e refactor(rust-bridge): decide native routing in the catalog, drop the bypass predicates
8b90649fb7 fix(proxy): sanitize unexpected /key/info database failures (#46190)
2dfeb80e04 fix(bedrock): take the 256K context window from the Qwen3 Coder 480B model card (#47283)
19f69ed6b6 test(integration): wait for every worker in Scenario.model (#47277)
Compare 34 commits »
scriptoriumadmin synced commits to refs/pull/46744/merge at scriptoriumadmin/litellm from mirror 2026-10-19 04:55:59 +00:00
91ebec7c63 feat: add Engy as OpenAI-compatible provider
9c958aff34 fix(logging): deliver completed batch success callbacks consistently (#47192)
7e6fb09da3 fix(streaming)!: map stream read timeouts to litellm.Timeout on chat, messages, and responses (#47198)
5012083b72 feat(vertex_ai): let operators drop chosen anthropic-beta values on the Vertex AI pass-through routes (#47185)
Compare 15 commits »
scriptoriumadmin synced commits to refs/pull/46754/head at scriptoriumadmin/litellm from mirror 2026-10-19 04:55:59 +00:00
7cfab05960 fix(spend-logs): keep main's stored tail for a negative prompt length limit
506339246c fix(spend-logs): keep main's stored value for a prompt length limit under 2
6621c117ec fix(responses): replay a compacted session only through the referenced response
Compare 3 commits »
scriptoriumadmin synced commits to refs/pull/46754/merge at scriptoriumadmin/litellm from mirror 2026-10-19 04:55:59 +00:00
2dfeb80e04 fix(bedrock): take the 256K context window from the Qwen3 Coder 480B model card (#47283)
19f69ed6b6 test(integration): wait for every worker in Scenario.model (#47277)
9c958aff34 fix(logging): deliver completed batch success callbacks consistently (#47192)
7e6fb09da3 fix(streaming)!: map stream read timeouts to litellm.Timeout on chat, messages, and responses (#47198)
Compare 33 commits »
scriptoriumadmin synced commits to refs/pull/46756/merge at scriptoriumadmin/litellm from mirror 2026-10-19 04:55:59 +00:00
2dfeb80e04 fix(bedrock): take the 256K context window from the Qwen3 Coder 480B model card (#47283)
19f69ed6b6 test(integration): wait for every worker in Scenario.model (#47277)
9c958aff34 fix(logging): deliver completed batch success callbacks consistently (#47192)
7e6fb09da3 fix(streaming)!: map stream read timeouts to litellm.Timeout on chat, messages, and responses (#47198)
Compare 47 commits »
scriptoriumadmin synced commits to refs/pull/46757/head at scriptoriumadmin/litellm from mirror 2026-10-19 04:55:59 +00:00
23ac1aaab3 fix(webwright): align supported parameters with the published abilities
scriptoriumadmin synced commits to refs/pull/46757/merge at scriptoriumadmin/litellm from mirror 2026-10-19 04:55:59 +00:00
2dfeb80e04 fix(bedrock): take the 256K context window from the Qwen3 Coder 480B model card (#47283)
19f69ed6b6 test(integration): wait for every worker in Scenario.model (#47277)
9c958aff34 fix(logging): deliver completed batch success callbacks consistently (#47192)
7e6fb09da3 fix(streaming)!: map stream read timeouts to litellm.Timeout on chat, messages, and responses (#47198)
Compare 48 commits »
scriptoriumadmin synced commits to refs/pull/46764/head at scriptoriumadmin/litellm from mirror 2026-10-19 04:55:59 +00:00
e7c036d1a8 fix(rust-messages): filter body params with Python's rules and send the missing betas
8b90649fb7 fix(proxy): sanitize unexpected /key/info database failures (#46190)
2dfeb80e04 fix(bedrock): take the 256K context window from the Qwen3 Coder 480B model card (#47283)
19f69ed6b6 test(integration): wait for every worker in Scenario.model (#47277)
9c958aff34 fix(logging): deliver completed batch success callbacks consistently (#47192)
Compare 200 commits »
scriptoriumadmin synced commits to refs/pull/46764/merge at scriptoriumadmin/litellm from mirror 2026-10-19 04:55:59 +00:00
e7c036d1a8 fix(rust-messages): filter body params with Python's rules and send the missing betas
8b90649fb7 fix(proxy): sanitize unexpected /key/info database failures (#46190)
2dfeb80e04 fix(bedrock): take the 256K context window from the Qwen3 Coder 480B model card (#47283)
19f69ed6b6 test(integration): wait for every worker in Scenario.model (#47277)
Compare 101 commits »
scriptoriumadmin synced commits to refs/pull/46765/merge at scriptoriumadmin/litellm from mirror 2026-10-19 04:55:59 +00:00
8b90649fb7 fix(proxy): sanitize unexpected /key/info database failures (#46190)
2dfeb80e04 fix(bedrock): take the 256K context window from the Qwen3 Coder 480B model card (#47283)
19f69ed6b6 test(integration): wait for every worker in Scenario.model (#47277)
9c958aff34 fix(logging): deliver completed batch success callbacks consistently (#47192)
Compare 31 commits »
scriptoriumadmin synced commits to refs/pull/46766/merge at scriptoriumadmin/litellm from mirror 2026-10-19 04:55:59 +00:00
2dfeb80e04 fix(bedrock): take the 256K context window from the Qwen3 Coder 480B model card (#47283)
19f69ed6b6 test(integration): wait for every worker in Scenario.model (#47277)
9c958aff34 fix(logging): deliver completed batch success callbacks consistently (#47192)
7e6fb09da3 fix(streaming)!: map stream read timeouts to litellm.Timeout on chat, messages, and responses (#47198)
Compare 84 commits »
scriptoriumadmin synced commits to refs/pull/46771/head at scriptoriumadmin/litellm from mirror 2026-10-19 04:55:59 +00:00
84daa2b9a2 feat(reasoning): add disable_inline_reasoning_extraction to keep inline think tags in content
2dfeb80e04 fix(bedrock): take the 256K context window from the Qwen3 Coder 480B model card (#47283)
19f69ed6b6 test(integration): wait for every worker in Scenario.model (#47277)
9c958aff34 fix(logging): deliver completed batch success callbacks consistently (#47192)
7e6fb09da3 fix(streaming)!: map stream read timeouts to litellm.Timeout on chat, messages, and responses (#47198)
Compare 349 commits »
scriptoriumadmin synced commits to refs/pull/46775/merge at scriptoriumadmin/litellm from mirror 2026-10-19 04:55:59 +00:00
1a77147fad fix(azure): set azure/container code interpreter session price from the azure openai pricing page (#47292)
d07e3c5cd2 feat(cost-map): add together_ai DeepSeek-V4.1-Flash-1017 (#47291)
bcd80b6aa1 feat(rust): encode LiteLLM response ids on native responses (#46572)
4995d319ed test(rust): add native vs Python parity harness for responses (#46567)
Compare 23 commits »
scriptoriumadmin synced commits to refs/pull/46788/head at scriptoriumadmin/litellm from mirror 2026-10-19 04:55:59 +00:00
ea0898fae2 fix(rust-responses): filter body params with Python's Responses param rules
1d72fee475 feat(rust-messages): inject cache_control breakpoints natively
120fa92e55 docs(rust): design Python drift audits and review enforcement
e3163aa98b fix(rust-bridge): stamp num_retries and timeout on async native failures
33e5d9168e refactor(rust-bridge): let cache adapters own request preparation
Compare 207 commits »
scriptoriumadmin synced commits to refs/pull/46695/merge at scriptoriumadmin/litellm from mirror 2026-10-19 04:55:58 +00:00
2dfeb80e04 fix(bedrock): take the 256K context window from the Qwen3 Coder 480B model card (#47283)
19f69ed6b6 test(integration): wait for every worker in Scenario.model (#47277)
9c958aff34 fix(logging): deliver completed batch success callbacks consistently (#47192)
7e6fb09da3 fix(streaming)!: map stream read timeouts to litellm.Timeout on chat, messages, and responses (#47198)
Compare 64 commits »
scriptoriumadmin synced commits to refs/pull/46697/head at scriptoriumadmin/litellm from mirror 2026-10-19 04:55:58 +00:00
d6a4b71cd1 feat(rust): stream native Responses calls
0423ac1164 feat(rust): serve Bedrock Mantle responses natively
c9e699b191 feat(rust): serve Databricks GPT responses natively
700a2c3307 feat(rust): serve Fireworks AI responses natively
33c932959a feat(rust): serve xAI and hosted vLLM responses natively
Compare 201 commits »