scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/48305/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:15:11 +00:00
f96200bcea fix(vertex_ai): bound shared credential cache retention (#48442)
52c11bf383 feat(bedrock): add global. and us. openai.gpt-6.1-terra rows (#48441)
c69e82f538 chore(cost-map): add openai batch and ultrafast 12-hour cache write rates from the pricing page (#48433)
dab39d7402 fix(azure): set azure_ai/Microsoft-Decision-1 max_input_tokens to 32768 (#48434)
Compare 15 commits »
scriptoriumadmin synced commits to refs/pull/48307/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:15:11 +00:00
85871f791c fix(ui): render string inputs in general settings (#48431)
1ecc782986 fix(vertex_ai): reuse rerank credential cache (#48430)
38f318e736 fix(otel): decide per-team Arize sampling from the trace id so every pod agrees (#47468)
1c022d1d06 chore(cost-map): add openai gpt-6.1-terra from the pricing page (#48429)
Compare 10 commits »
scriptoriumadmin synced commits to refs/pull/48309/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:15:11 +00:00
85871f791c fix(ui): render string inputs in general settings (#48431)
1ecc782986 fix(vertex_ai): reuse rerank credential cache (#48430)
38f318e736 fix(otel): decide per-team Arize sampling from the trace id so every pod agrees (#47468)
1c022d1d06 chore(cost-map): add openai gpt-6.1-terra from the pricing page (#48429)
Compare 10 commits »
scriptoriumadmin synced commits to refs/pull/48308/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:15:11 +00:00
cfe0100e1f fix(router): preserve tag fail-open policy through affinity and cooldown (#48470)
aa33b052d2 fix(messages): honor OpenAI stop_sequences (#37118) (#48534)
74ce6d1d66 fix(databricks): reuse base OAuth for decisions (#48395) (#48527)
e5757934fd fix(azure): add keyless Decisions authentication (#48386) (#48529)
Compare 84 commits »
scriptoriumadmin synced commits to refs/pull/48310/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:15:11 +00:00
3b8ad37296 fix(anthropic): raise DEFAULT_ANTHROPIC_CHAT_MAX_TOKENS from 4096 to 128000 (#48502)
7e14638001 refactor(llms): rename model-version transformation files to family names (#48509)
5276e5435f fix(ui): persist model parameter deletions after refresh (#48456)
9ed502f375 fix(decisions): honor base_url alias for custom backends (#48505)
Compare 73 commits »
scriptoriumadmin synced commits to refs/pull/48314/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:15:11 +00:00
100529391a fix(ui): show the budget period date range instead of "cycle" on team member spend (#48488)
549e6d4f46 fix(router): keep DB-only deployments priced across price data reloads (#48486)
833d82bb4e fix(mcp): reject revoked browser sessions during gateway authorization (#48494)
9873128b42 fix(team): keep the team reset schedule when a temp budget increase is set on a member inheriting the team default (#48495)
Compare 58 commits »
scriptoriumadmin synced commits to refs/pull/48318/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:15:11 +00:00
3b8ad37296 fix(anthropic): raise DEFAULT_ANTHROPIC_CHAT_MAX_TOKENS from 4096 to 128000 (#48502)
7e14638001 refactor(llms): rename model-version transformation files to family names (#48509)
5276e5435f fix(ui): persist model parameter deletions after refresh (#48456)
9ed502f375 fix(decisions): honor base_url alias for custom backends (#48505)
Compare 73 commits »
scriptoriumadmin synced commits to refs/pull/48317/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:15:11 +00:00
c905cd065d feat(refuseless): add provider and model pricing (#48497)
b1f40b042b feat(abliteration): add model pricing and capabilities (#48498)
45183428a5 feat(ui): persist model group alias display ordering (#48500)
11779b260e fix(ui): include endpoint-qualified models in Decisions Playground (#48504)
Compare 64 commits »
scriptoriumadmin synced commits to refs/pull/48319/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:15:11 +00:00
ebf829c2fa fix: support Python 3.15 (#48359)
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/48320/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:15:11 +00:00
3b8ad37296 fix(anthropic): raise DEFAULT_ANTHROPIC_CHAT_MAX_TOKENS from 4096 to 128000 (#48502)
7e14638001 refactor(llms): rename model-version transformation files to family names (#48509)
5276e5435f fix(ui): persist model parameter deletions after refresh (#48456)
9ed502f375 fix(decisions): honor base_url alias for custom backends (#48505)
Compare 73 commits »
scriptoriumadmin synced commits to refs/pull/48315/head at scriptoriumadmin/litellm from mirror 2026-10-27 06:15:11 +00:00
ce9e5f0f02 fix(ci): resolve OSV dependency findings
2b4c9a65c5 fix(search): skip dashboard sentinel team lookup
dab39d7402 fix(azure): set azure_ai/Microsoft-Decision-1 max_input_tokens to 32768 (#48434)
07a82a287b fix(guardrails): exclude litellm_metadata from pass-through guardrail scan text (#48276)
85871f791c fix(ui): render string inputs in general settings (#48431)
Compare 13 commits »
scriptoriumadmin synced commits to refs/pull/48322/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:15:11 +00:00
ebf829c2fa fix: support Python 3.15 (#48359)
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/48316/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:15:11 +00:00
3b8ad37296 fix(anthropic): raise DEFAULT_ANTHROPIC_CHAT_MAX_TOKENS from 4096 to 128000 (#48502)
7e14638001 refactor(llms): rename model-version transformation files to family names (#48509)
5276e5435f fix(ui): persist model parameter deletions after refresh (#48456)
9ed502f375 fix(decisions): honor base_url alias for custom backends (#48505)
Compare 73 commits »
scriptoriumadmin synced commits to refs/pull/48295/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:15:10 +00:00
3b8ad37296 fix(anthropic): raise DEFAULT_ANTHROPIC_CHAT_MAX_TOKENS from 4096 to 128000 (#48502)
7e14638001 refactor(llms): rename model-version transformation files to family names (#48509)
5276e5435f fix(ui): persist model parameter deletions after refresh (#48456)
9ed502f375 fix(decisions): honor base_url alias for custom backends (#48505)
Compare 73 commits »
scriptoriumadmin synced commits to refs/pull/48291/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:15:10 +00:00
ebf829c2fa fix: support Python 3.15 (#48359)
dddbaa803d build(docker): refresh base images and ship only runtime files in component images (#48279)
Compare 3 commits »
scriptoriumadmin synced commits to refs/pull/48290/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:15:10 +00:00
2503430a38 chore: defer dependency remediation to canonical branch
e2a5bc1ce7 build(deps): remediate filelock and MSAL advisories
9ec36abc31 build(deps): pin patched compatible filelock and MSAL versions
25d64fbb6e test(proxy): make tokenizer offload check deterministic
Compare 6 commits »
scriptoriumadmin synced commits to refs/pull/48290/head at scriptoriumadmin/litellm from mirror 2026-10-27 06:15:10 +00:00
2503430a38 chore: defer dependency remediation to canonical branch
e2a5bc1ce7 build(deps): remediate filelock and MSAL advisories
9ec36abc31 build(deps): pin patched compatible filelock and MSAL versions
25d64fbb6e test(proxy): make tokenizer offload check deterministic
Compare 4 commits »
scriptoriumadmin synced commits to refs/pull/48288/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:15:10 +00:00
3b8ad37296 fix(anthropic): raise DEFAULT_ANTHROPIC_CHAT_MAX_TOKENS from 4096 to 128000 (#48502)
7e14638001 refactor(llms): rename model-version transformation files to family names (#48509)
5276e5435f fix(ui): persist model parameter deletions after refresh (#48456)
9ed502f375 fix(decisions): honor base_url alias for custom backends (#48505)
Compare 76 commits »
scriptoriumadmin synced commits to refs/pull/48287/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:15:10 +00:00
de17bca0ac fix(cost): keep the provider's usage.cost marker through the metadata pass
3b8ad37296 fix(anthropic): raise DEFAULT_ANTHROPIC_CHAT_MAX_TOKENS from 4096 to 128000 (#48502)
15670c78e8 chore(cost): sort the litellm import in response_metadata
7e14638001 refactor(llms): rename model-version transformation files to family names (#48509)
Compare 84 commits »
scriptoriumadmin synced commits to refs/pull/48287/head at scriptoriumadmin/litellm from mirror 2026-10-27 06:15:10 +00:00
de17bca0ac fix(cost): keep the provider's usage.cost marker through the metadata pass
15670c78e8 chore(cost): sort the litellm import in response_metadata
df818a8e62 feat(cost): include_cost_in_streaming_usage puts the bill on plain replies without an upstream usage.cost too
e4b9584ea6 fix(cost): stamp the bill on a plain reply only where the upstream reported usage.cost
a20609a6f2 fix(cost): show litellm's bill in usage.cost on chat non-stream and both Responses paths
Compare 8 commits »