scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/45971/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:05:58 +00:00
c80f1c2ec8 fix(router)!: count native Responses WebSocket turns toward deployment limits and budgets (#45727)
492272a051 fix(azure): reuse the cached Entra token provider on the Responses path (#46421)
7ef92689da fix(azure): route WebRTC client_secrets and calls to the GA v1 realtime API (#47316)
a2773bdcad fix(azure): route WebRTC client_secrets and calls to the GA v1 realtime API (#47316)
Compare 12 commits »
scriptoriumadmin synced commits to refs/pull/45972/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:05:58 +00:00
d7620c77a1 fix(openai): drop unsupported reasoning effort for gpt-6.1-sol (#43935)
40e4ade6a6 feat(proxy): opt-in self-serve budget edits for key owners on /key/update (#44763)
714d84acb6 fix(cost-map): add fireworks minimax m3.1 flash standard prices (#47371)
037e805b97 build(deps): bump aiohttp to 3.14.5 to clear osv-scan (#47369)
Compare 31 commits »
scriptoriumadmin synced commits to refs/pull/45974/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:05:58 +00:00
492272a051 fix(azure): reuse the cached Entra token provider on the Responses path (#46421)
7ef92689da fix(azure): route WebRTC client_secrets and calls to the GA v1 realtime API (#47316)
a2773bdcad fix(azure): route WebRTC client_secrets and calls to the GA v1 realtime API (#47316)
748c973f42 chore(pricing): add meta muse-image-1.0 per-image price (#47318)
Compare 11 commits »
scriptoriumadmin synced commits to refs/pull/45978/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:05:58 +00:00
1ef59fab8b test(ui-e2e): read the virtual key from its own pre in the Save your Key dialog (#47408)
77bd7d6de8 test(integration): expect the requested model in streamed Responses events on the arize v2 rig (#47407)
b110c8cfa7 test(integration): check SSO sign-in removal without reaching the public internet (#47409)
cf9ebeda07 fix(proxy): stop billing every OpenAI pass-through /responses sub-route as a Responses call (#47171)
Compare 52 commits »
scriptoriumadmin synced commits to refs/pull/45984/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:05:58 +00:00
d7620c77a1 fix(openai): drop unsupported reasoning effort for gpt-6.1-sol (#43935)
40e4ade6a6 feat(proxy): opt-in self-serve budget edits for key owners on /key/update (#44763)
714d84acb6 fix(cost-map): add fireworks minimax m3.1 flash standard prices (#47371)
037e805b97 build(deps): bump aiohttp to 3.14.5 to clear osv-scan (#47369)
Compare 31 commits »
scriptoriumadmin synced commits to refs/pull/45990/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:05:58 +00:00
d29200fa05 fix(vertex_ai): bill per-character text embeddings on Google's billableCharacterCount (#47460)
8b9cd12a89 test: catch regressions in the validation lines #44798 added (#47420)
3fa1587f43 fix(logging): do not stamp a provider handoff when pre_call runs for a proxy-only failure (#47456)
f98168e73d test(e2e/perf): read the memory baseline after a one minute warm-up (#47455)
Compare 73 commits »
scriptoriumadmin synced commits to refs/pull/45992/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:05:58 +00:00
da80552897 test(translation): add sonnet 5.5 converse and gemini direct cross-model mid rows (#47328)
c4d24ec2f1 test(integration): remove BUG skips for 3 tests that pass on main (#47364)
daa133da5c fix(mcp)!: bill both model calls of a chat completions MCP auto-execute on one spend row (#47422)
7b82b2a3c3 feat(bedrock): route token counts from model metadata (#47441)
Compare 93 commits »
scriptoriumadmin synced commits to refs/pull/46003/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:05:58 +00:00
12d87a9888 Merge remote-tracking branch 'upstream/main' into litellm_router_failover_non_retryable
c80f1c2ec8 fix(router)!: count native Responses WebSocket turns toward deployment limits and budgets (#45727)
492272a051 fix(azure): reuse the cached Entra token provider on the Responses path (#46421)
7ef92689da fix(azure): route WebRTC client_secrets and calls to the GA v1 realtime API (#47316)
a2773bdcad fix(azure): route WebRTC client_secrets and calls to the GA v1 realtime API (#47316)
Compare 264 commits »
scriptoriumadmin synced commits to refs/pull/46003/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:05:58 +00:00
b690225956 fix(proxy): resync configuration after Redis reconnect (#43313)
2d181e6633 fix(token_counter): count DeepSeek V4 text with DeepSeek's own tokenizer (#47353)
d56ff281de fix(router): key prompt caching affinity on tools and the /v1/messages system prompt (#46411)
fb555b00dc fix(proxy): price a billed failure row at the deployment's own rate like the success path (#47437)
Compare 173 commits »
scriptoriumadmin synced commits to refs/pull/45919/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:05:57 +00:00
d0733bf98c Merge upstream/main into fix/otel-early-closed-stream-span
ca0ec627b6 fix(exa): return highlights, highlight scores, score and the response envelope from Exa search (#47423)
b67003162a test(integration): wait for every worker to report the websocket session cap instead of sleeping (#47412)
1525e4bce5 feat(cli): keep the claude.ai login with lite claude --subscription and save pkce in config (#47385)
d7b28840eb test(integration): read stream stall spend rows from the proxy that served them (#47410)
Compare 664 commits »
scriptoriumadmin synced commits to refs/pull/45941/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:05:57 +00:00
d7620c77a1 fix(openai): drop unsupported reasoning effort for gpt-6.1-sol (#43935)
40e4ade6a6 feat(proxy): opt-in self-serve budget edits for key owners on /key/update (#44763)
714d84acb6 fix(cost-map): add fireworks minimax m3.1 flash standard prices (#47371)
037e805b97 build(deps): bump aiohttp to 3.14.5 to clear osv-scan (#47369)
Compare 31 commits »
scriptoriumadmin synced commits to refs/pull/45884/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:05:57 +00:00
c4d24ec2f1 test(integration): remove BUG skips for 3 tests that pass on main (#47364)
daa133da5c fix(mcp)!: bill both model calls of a chat completions MCP auto-execute on one spend row (#47422)
7b82b2a3c3 feat(bedrock): route token counts from model metadata (#47441)
96f1bc02d8 feat(router)!: apply each deployment's reasoning_effort_levels on every provider and route (#46601)
Compare 90 commits »
scriptoriumadmin synced commits to refs/pull/45889/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:05:57 +00:00
d7620c77a1 fix(openai): drop unsupported reasoning effort for gpt-6.1-sol (#43935)
40e4ade6a6 feat(proxy): opt-in self-serve budget edits for key owners on /key/update (#44763)
714d84acb6 fix(cost-map): add fireworks minimax m3.1 flash standard prices (#47371)
037e805b97 build(deps): bump aiohttp to 3.14.5 to clear osv-scan (#47369)
Compare 30 commits »
scriptoriumadmin synced commits to refs/pull/45893/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:05:57 +00:00
d7620c77a1 fix(openai): drop unsupported reasoning effort for gpt-6.1-sol (#43935)
40e4ade6a6 feat(proxy): opt-in self-serve budget edits for key owners on /key/update (#44763)
714d84acb6 fix(cost-map): add fireworks minimax m3.1 flash standard prices (#47371)
037e805b97 build(deps): bump aiohttp to 3.14.5 to clear osv-scan (#47369)
Compare 31 commits »
scriptoriumadmin synced commits to refs/pull/45907/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:05:57 +00:00
d29200fa05 fix(vertex_ai): bill per-character text embeddings on Google's billableCharacterCount (#47460)
8b9cd12a89 test: catch regressions in the validation lines #44798 added (#47420)
3fa1587f43 fix(logging): do not stamp a provider handoff when pre_call runs for a proxy-only failure (#47456)
f98168e73d test(e2e/perf): read the memory baseline after a one minute warm-up (#47455)
Compare 74 commits »
scriptoriumadmin synced commits to refs/pull/45909/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:05:57 +00:00
d7620c77a1 fix(openai): drop unsupported reasoning effort for gpt-6.1-sol (#43935)
40e4ade6a6 feat(proxy): opt-in self-serve budget edits for key owners on /key/update (#44763)
714d84acb6 fix(cost-map): add fireworks minimax m3.1 flash standard prices (#47371)
037e805b97 build(deps): bump aiohttp to 3.14.5 to clear osv-scan (#47369)
Compare 31 commits »
scriptoriumadmin synced commits to refs/pull/45918/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:05:57 +00:00
d7620c77a1 fix(openai): drop unsupported reasoning effort for gpt-6.1-sol (#43935)
40e4ade6a6 feat(proxy): opt-in self-serve budget edits for key owners on /key/update (#44763)
714d84acb6 fix(cost-map): add fireworks minimax m3.1 flash standard prices (#47371)
037e805b97 build(deps): bump aiohttp to 3.14.5 to clear osv-scan (#47369)
Compare 31 commits »
scriptoriumadmin synced commits to refs/pull/45919/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:05:57 +00:00
d0733bf98c Merge upstream/main into fix/otel-early-closed-stream-span
24d92f77d5 test(perf): stop flagging load-balanced worker reads as restarts in database upgrade test (#47425)
48763ccb50 fix(scim)!: store PATCH enterprise extension attributes in metadata.scim_enterprise (#46738)
9b4f44135d fix(proxy): refresh cached team on /team/block and /team/unblock (#35643)
Compare 579 commits »
scriptoriumadmin synced commits to refs/pull/45920/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:05:57 +00:00
d56ff281de fix(router): key prompt caching affinity on tools and the /v1/messages system prompt (#46411)
fb555b00dc fix(proxy): price a billed failure row at the deployment's own rate like the success path (#47437)
2196943195 fix(proxy): match partial wildcards against prefix-stripped model ids (#46390)
ce4a6cbf5b perf(streaming): cut per-chunk pydantic round trips on openai-compatible streams (#47030)
Compare 86 commits »
scriptoriumadmin synced commits to refs/pull/45928/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:05:57 +00:00
da80552897 test(translation): add sonnet 5.5 converse and gemini direct cross-model mid rows (#47328)
c4d24ec2f1 test(integration): remove BUG skips for 3 tests that pass on main (#47364)
daa133da5c fix(mcp)!: bill both model calls of a chat completions MCP auto-execute on one spend row (#47422)
7b82b2a3c3 feat(bedrock): route token counts from model metadata (#47441)
Compare 95 commits »