scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/47541/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:51 +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 41 commits »
scriptoriumadmin synced commits to refs/pull/47556/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:51 +00:00
b3af5f8c0f Fix Ruff formatting
ccd783d907 fix(proxy): reject negative RPM and TPM request limits (#48444)
6d93445350 fix(proxy): preserve limiter state across SSE keepalive tasks (#48452)
b7a2226f43 test(proxy): make tokenizer offload check deterministic (#48458)
Compare 24 commits »
scriptoriumadmin synced commits to refs/pull/47537/head at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:51 +00:00
160729380b fix(responses): preserve usage estimate defaults
7e85ceba27 fix(responses): skip the failure estimate once a completed response was already billed
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/47537/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:51 +00:00
160729380b fix(responses): preserve usage estimate defaults
7e85ceba27 fix(responses): skip the failure estimate once a completed response was already billed
ccd783d907 fix(proxy): reject negative RPM and TPM request limits (#48444)
6d93445350 fix(proxy): preserve limiter state across SSE keepalive tasks (#48452)
Compare 24 commits »
scriptoriumadmin synced commits to refs/pull/47539/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:51 +00:00
2e27a02a9f feat(chatgpt): forward client subscriptions through the gateway (#41522)
4da24fa01e fix(ui): show search tool errors instead of empty results (#48478)
7045139c3a fix(router): stop concurrent deployment deletes from crashing deployment lookups (#47680)
9a35ed93f9 feat(ui): simplify auto router setup with deployed model defaults (#48451)
Compare 35 commits »
scriptoriumadmin synced commits to refs/pull/47547/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:51 +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 109 commits »
scriptoriumadmin synced commits to refs/pull/47549/head at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:51 +00:00
647a962f41 test(anthropic): cover attempt-scoped interruption logging
6bd10f8adf fix(anthropic): preserve attempt failure logging after main update
e2ff54054d chore: merge main into anthropic stream fix
9892a69f11 fix(anthropic): handle fragmented SSE and log interrupted streams as failures
aa33b052d2 fix(messages): honor OpenAI stop_sequences (#37118) (#48534)
Compare 309 commits »
scriptoriumadmin synced commits to refs/pull/47549/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:51 +00:00
647a962f41 test(anthropic): cover attempt-scoped interruption logging
cfe0100e1f fix(router): preserve tag fail-open policy through affinity and cooldown (#48470)
6bd10f8adf fix(anthropic): preserve attempt failure logging after main update
e2ff54054d chore: merge main into anthropic stream fix
Compare 212 commits »
scriptoriumadmin synced commits to refs/pull/47550/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:51 +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/47551/head at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:51 +00:00
7397d2fc1c fix: align core distribution filelock requirement
8385a2cae2 fix: clear dependency alerts and stabilize tokenizer offload test
cd93c02838 fix: resolve main conflicts in model group spend tracking
dddbaa803d build(docker): refresh base images and ship only runtime files in component images (#48279)
72f1ac4a27 revert(proxy): revert large-integer request parsing (#48289)
Compare 99 commits »
scriptoriumadmin synced commits to refs/pull/47553/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:51 +00:00
e16d79d635 feat(decisions): support LM Studio decision models (#48448)
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)
Compare 117 commits »
scriptoriumadmin synced commits to refs/pull/47556/head at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:51 +00:00
b3af5f8c0f Fix Ruff formatting
scriptoriumadmin synced commits to refs/pull/47485/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:50 +00:00
e16d79d635 feat(decisions): support LM Studio decision models (#48448)
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)
Compare 74 commits »
scriptoriumadmin synced commits to refs/pull/47493/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:50 +00:00
e16d79d635 feat(decisions): support LM Studio decision models (#48448)
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)
Compare 117 commits »
scriptoriumadmin synced commits to refs/pull/47496/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:50 +00:00
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)
76d001a7c0 fix(router): serve a team's wildcard deployment before a proxy-wide wildcard (#48490)
Compare 57 commits »
scriptoriumadmin synced commits to refs/pull/47503/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:50 +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/47505/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:50 +00:00
e0982d6248 build(deps): bump webpki-roots and webpki-root-certs to 1.0.11 (#48301)
ebf829c2fa fix: support Python 3.15 (#48359)
Compare 3 commits »
scriptoriumadmin synced commits to refs/pull/47507/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:50 +00:00
ebf829c2fa fix: support Python 3.15 (#48359)
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/47516/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:50 +00:00
e0982d6248 build(deps): bump webpki-roots and webpki-root-certs to 1.0.11 (#48301)
ebf829c2fa fix: support Python 3.15 (#48359)
dddbaa803d build(docker): refresh base images and ship only runtime files in component images (#48279)
72f1ac4a27 revert(proxy): revert large-integer request parsing (#48289)
Compare 6 commits »
scriptoriumadmin synced commits to refs/pull/47521/head at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:50 +00:00
acdcad9769 fix(rate-limiter): charge token counters of calls that skipped admission without waiting for a window