scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/50253/head at scriptoriumadmin/litellm from mirror 2026-11-07 08:00:01 +00:00
abd3f90101 fix(usage): keep spend when the team, organization, customer, or agent name lookup drops
d9677dd761 fix(usage): keep the guardrail breakdown fallback for any Prisma error
d7d7ef02da fix(proxy): skip the key metadata lookup when the daily rows carry no keys
2c32b2d554 fix(usage): fall back only on database outages, on every daily activity route
ee95ac14a5 fix(usage): keep spend when metadata lookups hit database failures
Compare 5 commits »
scriptoriumadmin synced commits to refs/pull/50250/merge at scriptoriumadmin/litellm from mirror 2026-11-07 08:00:01 +00:00
e84859ae4e fix(bedrock): sync published Kimi K3.1 Highspeed prices (#50451)
156bda3e5b fix(gemini): sync documented model successors (#50468)
77b4644523 feat(ui): format dashboard numbers, money and dates through i18next (#50443)
e555a79cee test(e2e): follow the Aria sidebar move and the Skills Hub rename in UI specs (#50453)
Compare 95 commits »
scriptoriumadmin synced commits to refs/pull/50249/merge at scriptoriumadmin/litellm from mirror 2026-11-07 08:00:01 +00:00
72228db5c6 fix(caching): don't cache or replay a reply that has no output (#50057)
c36acd6e29 feat(azure_ai): add cohere-rerank-v5-pro and -fast from the Azure retail price feed (#50499)
8f19607259 fix(proxy)!: preserve Responses SSE event framing (#47980)
b3c4a1c3e4 feat(spend-logs): turn off prompt storage per key or team (#50135)
Compare 84 commits »
scriptoriumadmin synced commits to refs/pull/50246/merge at scriptoriumadmin/litellm from mirror 2026-11-07 08:00:01 +00:00
aeede53112 feat(guardrails): add mcp_block_behavior to raise 400 on MCP tool blocks (#50284)
0057804dca fix(ui): stop parsing formatted dates and spend back into values (#50350)
de0b389205 feat(router): add the Switchyard stage router as an auto router strategy (#50407)
8013d5b8c1 chore(model_prices): absorb #50415 and #50332, add Perplexity gpt-5.5 cached >272k rate (#50436)
Compare 96 commits »
scriptoriumadmin synced commits to refs/pull/50234/merge at scriptoriumadmin/litellm from mirror 2026-11-07 08:00:01 +00:00
cd076fb13a fix(tool-choice): leave a malformed allowed_tools choice unrewritten in the interception hooks
4755727276 fix(tool-choice): match named mcp entries by server label and let built-in entries allow their interception call
939034d8a4 fix(tool-choice): honor server-level and null-name mcp entries and stop hooks running excluded calls
bbc7de1ccb chore(cost-map): add the openai o1 deprecation source from the deprecations page (#50402)
Compare 31 commits »
scriptoriumadmin synced commits to refs/pull/50234/head at scriptoriumadmin/litellm from mirror 2026-11-07 08:00:01 +00:00
6be4f0b9ea fix(tool-choice): resolve mcp entries like the gateway and keep the choice on every hook path
cd076fb13a fix(tool-choice): leave a malformed allowed_tools choice unrewritten in the interception hooks
4755727276 fix(tool-choice): match named mcp entries by server label and let built-in entries allow their interception call
939034d8a4 fix(tool-choice): honor server-level and null-name mcp entries and stop hooks running excluded calls
2ac020c070 fix(tool-choice): refuse an allowed_tools entry whose name is not a string
Compare 6 commits »
scriptoriumadmin synced commits to refs/pull/50207/merge at scriptoriumadmin/litellm from mirror 2026-11-07 08:00:00 +00:00
ab3b12b951 feat(proxy): serve Codex its own release's model catalog, fetched from GitHub (#50318)
3f38730d2c refactor(typing): clear about 1,100 basedpyright Any errors across 303 files (#49986)
2d2290067c fix(bedrock): run realtime guardrails on Nova Sonic sessions (#49833)
b5a72c2042 fix(router): pin /v1/responses requests for prompt caching affinity (#50321)
Compare 55 commits »
scriptoriumadmin synced commits to refs/pull/50221/head at scriptoriumadmin/litellm from mirror 2026-11-07 08:00:00 +00:00
daa03979f0 fix(bedrock): count only a true fake_stream and keep the deployment by-default key out of /model/info
71e2ac5226 fix(bedrock): keep the JSON tool retry buffered after a denied stream's schema is rejected
728423f626 Merge remote-tracking branch 'origin/main' into litellm_bedrock_native_so_fix_00842951
7e9366f100 fix(bedrock): answer a buffered invoke stream from the non-streaming reply
6b68ac0063 fix(bedrock): send a buffered schema stream to /invoke and keep the by-default key on its deployment
Compare 41 commits »
scriptoriumadmin synced commits to refs/pull/50225/merge at scriptoriumadmin/litellm from mirror 2026-11-07 08:00:00 +00:00
72228db5c6 fix(caching): don't cache or replay a reply that has no output (#50057)
c36acd6e29 feat(azure_ai): add cohere-rerank-v5-pro and -fast from the Azure retail price feed (#50499)
8f19607259 fix(proxy)!: preserve Responses SSE event framing (#47980)
b3c4a1c3e4 feat(spend-logs): turn off prompt storage per key or team (#50135)
Compare 64 commits »
scriptoriumadmin synced commits to refs/pull/50226/merge at scriptoriumadmin/litellm from mirror 2026-11-07 08:00:00 +00:00
72228db5c6 fix(caching): don't cache or replay a reply that has no output (#50057)
c36acd6e29 feat(azure_ai): add cohere-rerank-v5-pro and -fast from the Azure retail price feed (#50499)
8f19607259 fix(proxy)!: preserve Responses SSE event framing (#47980)
b3c4a1c3e4 feat(spend-logs): turn off prompt storage per key or team (#50135)
Compare 65 commits »
scriptoriumadmin synced commits to refs/pull/50233/merge at scriptoriumadmin/litellm from mirror 2026-11-07 08:00:00 +00:00
5103d8a0ee fix(azure): align chat-latest retirement metadata with its documented alias (#50509)
0eb6816081 fix(gemini): add Gemini 2.5 Pro flex cache price above 200k tokens (#50480)
72228db5c6 fix(caching): don't cache or replay a reply that has no output (#50057)
c36acd6e29 feat(azure_ai): add cohere-rerank-v5-pro and -fast from the Azure retail price feed (#50499)
Compare 65 commits »
scriptoriumadmin synced commits to refs/pull/50215/merge at scriptoriumadmin/litellm from mirror 2026-11-07 08:00:00 +00:00
72228db5c6 fix(caching): don't cache or replay a reply that has no output (#50057)
c36acd6e29 feat(azure_ai): add cohere-rerank-v5-pro and -fast from the Azure retail price feed (#50499)
8f19607259 fix(proxy)!: preserve Responses SSE event framing (#47980)
b3c4a1c3e4 feat(spend-logs): turn off prompt storage per key or team (#50135)
Compare 67 commits »
scriptoriumadmin synced commits to refs/pull/50223/merge at scriptoriumadmin/litellm from mirror 2026-11-07 08:00:00 +00:00
2a4f8b1d19 fix(bedrock): drop another model's signed thinking when replaying to a non-Claude Converse target (#50073)
b02bb99b08 feat: add OpenRouter-style -latest model aliases for first-party providers (#50315)
80194a7d70 fix(anthropic): preserve Azure Responses reasoning replay (#50024) (#50381)
a12100b33b fix(anthropic): default Responses JSON schemas through a helper (#50023) (#50375)
Compare 59 commits »
scriptoriumadmin synced commits to refs/pull/50209/merge at scriptoriumadmin/litellm from mirror 2026-11-07 08:00:00 +00:00
8f19607259 fix(proxy)!: preserve Responses SSE event framing (#47980)
b3c4a1c3e4 feat(spend-logs): turn off prompt storage per key or team (#50135)
a3bf1f4399 fix(router): record retries and fallback hops past a request's first logged failure (#50445)
e9b1c11098 fix(xai): honor deployment image pixel pricing (#50490)
Compare 72 commits »
scriptoriumadmin synced commits to refs/pull/50207/head at scriptoriumadmin/litellm from mirror 2026-11-07 08:00:00 +00:00
21d1975723 feat: update provider_endpoints_support.json to add Verda
scriptoriumadmin synced commits to refs/pull/50210/merge at scriptoriumadmin/litellm from mirror 2026-11-07 08:00:00 +00:00
72228db5c6 fix(caching): don't cache or replay a reply that has no output (#50057)
c36acd6e29 feat(azure_ai): add cohere-rerank-v5-pro and -fast from the Azure retail price feed (#50499)
8f19607259 fix(proxy)!: preserve Responses SSE event framing (#47980)
b3c4a1c3e4 feat(spend-logs): turn off prompt storage per key or team (#50135)
Compare 74 commits »
scriptoriumadmin synced commits to refs/pull/50214/merge at scriptoriumadmin/litellm from mirror 2026-11-07 08:00:00 +00:00
fc1e47e580 chore: remove paragraph-ending period restriction (#50419)
4fe1cfe097 feat(router-core): derive serialize on router events (#50416)
bc1309f18e fix(responses): map streamed flex_unavailable errors to 429 not 500 (#50336)
75d4e15e64 test(spend): exercise TTL-preserving increments through rate limit store (#50418)
Compare 25 commits »
scriptoriumadmin synced commits to refs/pull/50220/merge at scriptoriumadmin/litellm from mirror 2026-11-07 08:00:00 +00:00
fc1e47e580 chore: remove paragraph-ending period restriction (#50419)
4fe1cfe097 feat(router-core): derive serialize on router events (#50416)
bc1309f18e fix(responses): map streamed flex_unavailable errors to 429 not 500 (#50336)
75d4e15e64 test(spend): exercise TTL-preserving increments through rate limit store (#50418)
Compare 25 commits »
scriptoriumadmin synced commits to refs/pull/50204/merge at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:59 +00:00
98acc01e0d feat(videos): add first-class OpenRouter video request fields (#50319)
527c094abe fix(wandb): sync CoreWeave Forge prices and add DeepSeek V4.1-Flash-1017 (#50476)
d32a6d75f8 fix(baseten): sync Kimi K3.1 Pro output limit (#50477)
169024c8fe test(routing): expect /v1/responses to pin the served deployment for an hour after #50321 (#50474)
Compare 97 commits »
scriptoriumadmin synced commits to refs/pull/50205/merge at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:59 +00:00
c36acd6e29 feat(azure_ai): add cohere-rerank-v5-pro and -fast from the Azure retail price feed (#50499)
8f19607259 fix(proxy)!: preserve Responses SSE event framing (#47980)
b3c4a1c3e4 feat(spend-logs): turn off prompt storage per key or team (#50135)
a3bf1f4399 fix(router): record retries and fallback hops past a request's first logged failure (#50445)
Compare 71 commits »