scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/46323/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:35 +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 7 commits »
scriptoriumadmin synced commits to refs/pull/46262/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:34 +00:00
cf4ee17844 fix(streaming_handler): rebase on current main with the coercion hardening
f1e7d661ce Merge main into the delta-content coercion fix
c69e82f538 chore(cost-map): add openai batch and ultrafast 12-hour cache write rates from the pricing page (#48433)
be69d8c753 fix(streaming_handler): skip content parts without usable text
Compare 16 commits »
scriptoriumadmin synced commits to refs/pull/46248/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:34 +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/46223/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:34 +00:00
099c599449 fix(terraform): honor HTTP_PROXY/HTTPS_PROXY in the provider's HTTP client
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)
Compare 85 commits »
scriptoriumadmin synced commits to refs/pull/46262/head at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:34 +00:00
cf4ee17844 fix(streaming_handler): rebase on current main with the coercion hardening
f1e7d661ce Merge main into the delta-content coercion fix
c69e82f538 chore(cost-map): add openai batch and ultrafast 12-hour cache write rates from the pricing page (#48433)
be69d8c753 fix(streaming_handler): skip content parts without usable text
dab39d7402 fix(azure): set azure_ai/Microsoft-Decision-1 max_input_tokens to 32768 (#48434)
Compare 443 commits »
scriptoriumadmin synced commits to refs/pull/46253/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:34 +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/46223/head at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:34 +00:00
099c599449 fix(terraform): honor HTTP_PROXY/HTTPS_PROXY in the provider's HTTP client
scriptoriumadmin synced commits to refs/pull/46219/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:34 +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/46268/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:34 +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/46278/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:34 +00:00
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)
c843cee062 feat(pricing): add github_copilot/gpt-6.1-terra (#48450)
Compare 63 commits »
scriptoriumadmin synced commits to refs/pull/46222/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:34 +00:00
c7bc3fdb66 Merge remote-tracking branch 'upstream/main' into litellm_tts_true_streaming
dddbaa803d build(docker): refresh base images and ship only runtime files in component images (#48279)
72f1ac4a27 revert(proxy): revert large-integer request parsing (#48289)
d3b70c42ed fix(proxy): keep JSON integers outside the 64-bit range exact when parsing request bodies (#48213)
Compare 88 commits »
scriptoriumadmin synced commits to refs/pull/46222/head at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:34 +00:00
c7bc3fdb66 Merge remote-tracking branch 'upstream/main' into litellm_tts_true_streaming
dddbaa803d build(docker): refresh base images and ship only runtime files in component images (#48279)
72f1ac4a27 revert(proxy): revert large-integer request parsing (#48289)
d3b70c42ed fix(proxy): keep JSON integers outside the 64-bit range exact when parsing request bodies (#48213)
de5dc5b238 feat(mistral): add zai-glm-5-3-flash to the cost map (#48270)
Compare 90 commits »
scriptoriumadmin synced commits to refs/pull/46298/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:34 +00:00
76d001a7c0 fix(router): serve a team's wildcard deployment before a proxy-wide wildcard (#48490)
1263f70ab6 feat(ui): budget period tooltip on key, team, user and org spend tiles (#48487)
b9825e1f87 docs: document incremental database access migration (#48476)
a783f8e78b feat(db): add typed daily end-user spend upsert (#48237)
Compare 54 commits »
scriptoriumadmin synced commits to refs/pull/46265/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:34 +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/46188/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:33 +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 65 commits »
scriptoriumadmin synced commits to refs/pull/46188/head at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:33 +00:00
44941c5344 fix(anthropic): reject malformed tool choices with a 400
dddbaa803d build(docker): refresh base images and ship only runtime files in component images (#48279)
72f1ac4a27 revert(proxy): revert large-integer request parsing (#48289)
d3b70c42ed fix(proxy): keep JSON integers outside the 64-bit range exact when parsing request bodies (#48213)
de5dc5b238 feat(mistral): add zai-glm-5-3-flash to the cost map (#48270)
Compare 91 commits »
scriptoriumadmin synced commits to refs/pull/46183/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:33 +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/46181/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:33 +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/46174/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:33 +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/46193/merge at scriptoriumadmin/litellm from mirror 2026-10-27 06:14:33 +00:00
76d001a7c0 fix(router): serve a team's wildcard deployment before a proxy-wide wildcard (#48490)
1263f70ab6 feat(ui): budget period tooltip on key, team, user and org spend tiles (#48487)
b9825e1f87 docs: document incremental database access migration (#48476)
a783f8e78b feat(db): add typed daily end-user spend upsert (#48237)
Compare 97 commits »