scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/48820/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:15 +00:00
4b3c273fad refactor(proxy): fold the cached listing lookup back into the provider listing function
c45b264024 fix(proxy): persist tag spend and drain success callbacks within the shutdown budget (#48988)
c98641fd5a feat(dashscope)!: derive protocol bases from one domain (#47812)
06cdee91da fix(guardrails): scan and rewrite streamed /v1/completions under post_call guardrails (#49035)
Compare 97 commits »
scriptoriumadmin synced commits to refs/pull/48819/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:15 +00:00
e92fc8ba93 test(responses): replay a real stream in the billing test and type the fake wrapper chunks
544f526157 fix(responses): resolve conflicts with main
3f01341f0a fix(health)!: openai realtime health check reports healthy with a missing or invalid api key (#41233)
904c092ffe feat(providers): add BigModel support and model pricing (#48563)
9a68573e9b fix(responses): keep each Codex tool once when its tool list repeats across turns (#49006)
Compare 32 commits »
scriptoriumadmin synced commits to refs/pull/48840/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:15 +00:00
1477b9b29e refactor(router): add router entry points and keep the old members as a deprecated mixin
c45b264024 fix(proxy): persist tag spend and drain success callbacks within the shutdown budget (#48988)
c98641fd5a feat(dashscope)!: derive protocol bases from one domain (#47812)
06cdee91da fix(guardrails): scan and rewrite streamed /v1/completions under post_call guardrails (#49035)
961fabbb76 feat(secret_managers): resolve oidc/google api_key references per request (#47703)
Compare 82 commits »
scriptoriumadmin synced commits to refs/pull/48841/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:15 +00:00
3f5e42d032 fix(proxy): enforce team and key Allowed Vector Stores when no vector store registry is loaded (#48915)
c666df3dac docs(qa): allow focused proof for mechanical PRs (#49031)
bad98c4b02 fix(responses): call the renamed drops_params helper on the compact path (#49030)
b7da9a2755 fix(credentials): keep the stored secret when PATCH echoes its masked read-back (#48950)
Compare 115 commits »
scriptoriumadmin synced commits to refs/pull/48829/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:15 +00:00
78f3cd9d3e fix(spend): keep the dropped-cost flag out of reach of provider usage keys
3f1d7e2c31 Merge remote-tracking branch 'origin/main' into HEAD
d74b3e9a0d Merge remote-tracking branch 'origin/main' into HEAD
6cdb9959df feat(router): opt in to non-chat deployment filtering (#46257)
77064d6c70 feat(vector_stores): add OpenSearch k-NN search as a vector store provider (#47759)
Compare 58 commits »
scriptoriumadmin synced commits to refs/pull/48843/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:15 +00:00
ccc56d27ad fix(azure): add batch prices to the unversioned o3, o4-mini, o3-mini, gpt-4o and gpt-4o-mini rows (#49182)
b91fc92b6d fix(router): cap the default OTPM reservation and reconcile token counters after each call (#49054)
342ce6ae4a feat(zai): support response_format and max_completion_tokens, add glm-5v-turbo pricing (#48335)
733cfeba93 fix(cost): bill a provider reported usage.cost on every path unless the deployment is priced (#48953)
Compare 223 commits »
scriptoriumadmin synced commits to refs/pull/48843/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:15 +00:00
59b9d68ad9 fix(proxy): skip key max-budget check on discovery routes
364c7cd378 fix(proxy): skip key max-budget check on discovery routes
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/48829/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:15 +00:00
d884167bf2 fix(responses): only merge repeated Codex tools when drop_params is on (#49112)
62b8ee78de ci: run the integration groups on GitHub Actions (#48985)
ffcc4f7a70 fix(otel)!: print OTel v2 spans to stdout only when the operator asks (#48723)
a54204b583 feat(guardrails): scan sampled stream windows in the background (#48952)
Compare 78 commits »
scriptoriumadmin synced commits to refs/pull/48824/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:15 +00:00
a297a7d7ad Merge remote-tracking branch 'origin/main' into litellm_mcp_auto_execute_parallel_slot
3f5e42d032 fix(proxy): enforce team and key Allowed Vector Stores when no vector store registry is loaded (#48915)
c666df3dac docs(qa): allow focused proof for mechanical PRs (#49031)
bad98c4b02 fix(responses): call the renamed drops_params helper on the compact path (#49030)
b7da9a2755 fix(credentials): keep the stored secret when PATCH echoes its masked read-back (#48950)
Compare 6 commits »
scriptoriumadmin synced commits to refs/pull/48811/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:15 +00:00
b91fc92b6d fix(router): cap the default OTPM reservation and reconcile token counters after each call (#49054)
342ce6ae4a feat(zai): support response_format and max_completion_tokens, add glm-5v-turbo pricing (#48335)
733cfeba93 fix(cost): bill a provider reported usage.cost on every path unless the deployment is priced (#48953)
369f3cb5f0 feat(cost-map): add baseten joey-1 decision model (#49123)
Compare 144 commits »
scriptoriumadmin synced commits to refs/pull/48790/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:14 +00:00
4ce724e3df fix(caching): key cached async clients by a per-loop token instead of id(loop) (#48877)
d884167bf2 fix(responses): only merge repeated Codex tools when drop_params is on (#49112)
62b8ee78de ci: run the integration groups on GitHub Actions (#48985)
ffcc4f7a70 fix(otel)!: print OTel v2 spans to stdout only when the operator asks (#48723)
Compare 212 commits »
scriptoriumadmin synced commits to refs/pull/48779/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:14 +00:00
9f7fc215f6 fix(router): list cache prices at the input rate billing charges when a deployment has none
cd52bb0960 Merge branch 'main' of https://github.com/BerriAI/litellm into litellm_model_group_info_carry_prices
23d99b42fe fix(router): list tier and batch prices at the most any deployment bills, and scope team deployment prices
dff474e450 fix(responses): replay the original Responses item order, phase, and boundaries on the next chat turn (#48912)
3f01341f0a fix(health)!: openai realtime health check reports healthy with a missing or invalid api key (#41233)
Compare 26 commits »
scriptoriumadmin synced commits to refs/pull/48756/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:14 +00:00
b4da0ce74a Merge remote-tracking branch 'origin/main' into litellm_kyma_provider
d037d86a94 fix(token_counter)!: keep a loaded Hugging Face tokenizer when a slower download fails (#48916)
c87a25a357 feat(proxy)!: general_settings.claude_code_marketplace_auth_required puts the Claude Code marketplace behind a LiteLLM key (#48980)
e8f0735d8a feat(proxy): let a Claude Code gateway user choose the session team (#49001)
c489aa7117 feat(proxy)!: add suppress_startup_output to turn off startup prints (#47708)
Compare 50 commits »
scriptoriumadmin synced commits to refs/pull/48757/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:14 +00:00
f32ac94ad1 fix(openai): keep the upstream error body on e.response for OpenAI and Azure errors (#49079)
ccc56d27ad fix(azure): add batch prices to the unversioned o3, o4-mini, o3-mini, gpt-4o and gpt-4o-mini rows (#49182)
b91fc92b6d fix(router): cap the default OTPM reservation and reconcile token counters after each call (#49054)
342ce6ae4a feat(zai): support response_format and max_completion_tokens, add glm-5v-turbo pricing (#48335)
Compare 110 commits »
scriptoriumadmin synced commits to refs/pull/48761/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:14 +00:00
e082861b55 fix(wrapper): pin known partially-unknown member accesses in failure cleanup
scriptoriumadmin synced commits to refs/pull/48772/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:14 +00:00
b2bbc31923 feat(router): clamp completion token budgets with per-deployment max_output_tokens_cap
cd42694b48 feat(providers): add Kyma API as an OpenAI-compatible provider (#48756)
3e3362d461 fix(cohere): price native Cohere embed calls on Foundry relays and the Cohere passthrough (#48978)
e7d3b24d7c fix(logging): mark mirrored silent_model calls with is_silent_experiment in spend logs (#48888)
Compare 49 commits »
scriptoriumadmin synced commits to refs/pull/48811/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:14 +00:00
28c7c2401c fix(gemini): report tool_calls when a streamed call ends with MAX_TOKENS
scriptoriumadmin synced commits to refs/pull/48810/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:14 +00:00
a1bd5feebe feat(router): infer custom classifier tiers from model mappings (#48987)
5dcc3a1bbf docs: link README to Python SDK and autorouter guides (#48986)
2e5cc9e08f fix(proxy)!: honor litellm_settings.drop_params for Claude Code and Codex requests (#49058)
4a4c9cf7e3 feat(guardrails): opt-in response_masked_data on PANW Prisma AIRS block (#46219)
Compare 71 commits »
scriptoriumadmin synced commits to refs/pull/48797/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:14 +00:00
b91fc92b6d fix(router): cap the default OTPM reservation and reconcile token counters after each call (#49054)
342ce6ae4a feat(zai): support response_format and max_completion_tokens, add glm-5v-turbo pricing (#48335)
733cfeba93 fix(cost): bill a provider reported usage.cost on every path unless the deployment is priced (#48953)
369f3cb5f0 feat(cost-map): add baseten joey-1 decision model (#49123)
Compare 146 commits »
scriptoriumadmin synced commits to refs/pull/48797/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:14 +00:00
52635a9c69 fix(streaming): report tool_calls when a streamed call ends with stop