scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/49407/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:38 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 34 commits »
scriptoriumadmin synced commits to refs/pull/49398/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:38 +00:00
de28986123 fix(proxy): keep streaming when an unencodable value sits under non-string dict keys
fc59026674 fix(proxy): drop only the nested chunk value JSON cannot encode and keep lone surrogates
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/49397/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:38 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 34 commits »
scriptoriumadmin synced commits to refs/pull/49396/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:38 +00:00
414443ac58 fix(router): resolve a changed named credential at once in the cached boundary and take an injected clock
scriptoriumadmin synced commits to refs/pull/49389/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:38 +00:00
28b649e04a refactor(e2e): validate Codex rollout lines with the models directly
5b3694c39f test(e2e): add the Codex auto-compaction row
306d5ab5f6 test(e2e): make the Codex long session prove every earlier command output reached the model
cf71fbaeaa test(e2e): add the Codex file edit and long session rows
00a085fa6e test(e2e): record a step when the Codex harness sets up its home and workspace
Compare 115 commits »
scriptoriumadmin synced commits to refs/pull/49401/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:38 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 106 commits »
scriptoriumadmin synced commits to refs/pull/49383/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:38 +00:00
c106e92f07 fix(guardrails): scan the compact input and keep compact replies to one post_call scan
c01345a25b fix(guardrails): keep the skipped call type warning on one log line
9da5899763 Merge remote-tracking branch 'origin/main' into litellm_responses_calltypes
c43a1addf2 refactor(router): extract PythonCore behind RouterCore and pass the router its config (#49119)
a5f980600c fix(a2a): answer proxy refusals on /a2a POST routes as JSON-RPC errors (#49476)
Compare 35 commits »
scriptoriumadmin synced commits to refs/pull/49383/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:38 +00:00
34314a99f0 fix(messages): make rust messages copy python messages behaviour (#49611)
5e08cb0e63 test(messages): add rust vs python messages parity characterization suite (#49610)
216041e243 feat(decisions): add Parallel AI web-grounded decisions (#49188)
08b951a814 fix(vllm): list hosted_vllm wildcard models when the server has no api key (#40066)
Compare 126 commits »
scriptoriumadmin synced commits to refs/pull/49386/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:38 +00:00
d74a049427 test(e2e): Codex auto-compaction through LiteLLM (#49389)
098ce97763 test(e2e): make the Codex long session prove every earlier command output reached the model
2ee019985b test(e2e): add the Codex file edit and long session rows
6254860560 test(e2e): drive the Codex CLI through LiteLLM, command round trip (#49374)
6a7a469287 fix(vertex_ai): map Anthropic context overflow errors (#36963)
Compare 131 commits »
scriptoriumadmin synced commits to refs/pull/49405/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:38 +00:00
f91774e2f9 fix(fireworks): keep developer items in place for models that accept a later system message (#49399)
a2ab27373f fix(proxy): count the context_management edits /v1/messages applies on every bridged provider (#49234)
97cd5d0c6a fix(model-catalog): declare the tool and Responses token count framing keys (#49683)
aa95ac4cee fix(bedrock): price Web Search on the GPT-5.4 and later Mantle rows and the GovCloud West Mantle rows (#49687)
Compare 16 commits »
scriptoriumadmin synced commits to refs/pull/49402/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:38 +00:00
3d03261451 fix(responses): merge main and return a new request from the response id hook
704e73d6fe fix(cost-map): give the bare gpt-4o, gpt-4o-mini, gpt-4.1 and gpt-4.1-mini aliases their 2027-01-14 shutdown date (#49707)
28c80048ed fix(tool_choice): accept OpenAI allowed_tools on chat completions and flatten it for the Responses bridge (#49043)
20cb3ea439 test(integration): repair release qualification timing and labels (#49737)
94b5b6386a fix(bedrock): send native structured output for json_schema on Claude models that cannot force a tool (#49703)
Compare 136 commits »
scriptoriumadmin synced commits to refs/pull/49363/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:37 +00:00
1046716b6d fix(anthropic)!: sync the beta header allowlist with what anthropic, vertex_ai, and azure_ai accept (#49409)
ff91b89b8d fix(router): keep encrypted reasoning when a fallback hops between same-key deployments with no api_base (#49396)
572832dea1 fix(gemini)!: answer 400 for an unsupported chat audio format, drop it under drop_params (#49423)
ff3983c1f6 fix(wandb): set DeepSeek-V3.1 and Llama-3.1-8B max_input_tokens from the CoreWeave Forge page (#49616)
Compare 88 commits »
scriptoriumadmin synced commits to refs/pull/49361/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:37 +00:00
f8f12a270a test(integration): repair stale contract fixtures (#49700)
2fa02d6f72 fix(model_prices): verify Nebius and EmpirioLabs model metadata
508a98586e fix(databricks): join plain text blocks for non-Claude json_object requests (#49385)
ecc53f58c2 Merge remote-tracking branch 'origin/main' into litellm-providers/price-sync-databricks
Compare 61 commits »
scriptoriumadmin synced commits to refs/pull/49361/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:37 +00:00
2fa02d6f72 fix(model_prices): verify Nebius and EmpirioLabs model metadata
ecc53f58c2 Merge remote-tracking branch 'origin/main' into litellm-providers/price-sync-databricks
f91774e2f9 fix(fireworks): keep developer items in place for models that accept a later system message (#49399)
a2ab27373f fix(proxy): count the context_management edits /v1/messages applies on every bridged provider (#49234)
97cd5d0c6a fix(model-catalog): declare the tool and Responses token count framing keys (#49683)
Compare 59 commits »
scriptoriumadmin synced commits to refs/pull/49360/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:37 +00:00
aad396f15c Merge remote-tracking branch 'origin/main' into litellm_usage_export_key_user_metadata
acd084ab38 fix(mcp): answer bare OPTIONS on MCP routes without running LiteLLM auth (#49497)
e8e2fad99d fix(usage-export): only populate key and user metadata for admin view and strip credential and SCIM slots
81969e4afc refactor(ui): move admin and settings text onto i18n (#49546)
Compare 51 commits »
scriptoriumadmin synced commits to refs/pull/49378/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:37 +00:00
5114e1c515 test(mlflow): fake only the MLflow client in the failure event test
25844098bf fix(logging): scrub the prompt out of SDK failure logs when message logging is redacted
91aa6a16b2 fix(logging): replace a pydantic input_value whole instead of walking each cut
Compare 3 commits »
scriptoriumadmin synced commits to refs/pull/49380/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:37 +00:00
c8601d733b fix(logging): apply a callback's own message redaction to its failure events
c920180bac fix(otel): keep only the request text per span so a failed request's span can be freed
4fa1e66e4a fix(proxy): scrub the prompt out of proxy failure hook errors when message logging is redacted
5114e1c515 test(mlflow): fake only the MLflow client in the failure event test
25844098bf fix(logging): scrub the prompt out of SDK failure logs when message logging is redacted
Compare 6 commits »
scriptoriumadmin synced commits to refs/pull/49374/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:37 +00:00
ddcee65b7e Update run.py
00a085fa6e test(e2e): record a step when the Codex harness sets up its home and workspace
f2da92d092 test(e2e): clean up Codex test keys even when setup fails, and fail runs where Codex exits with an error
eebfd7a2bb test(e2e): type the Codex self-test event helper as a Mapping
fbcdc1f909 test(e2e): drive the real Codex CLI through the gateway and add the command round trip row
Compare 112 commits »
scriptoriumadmin synced commits to refs/pull/49367/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:37 +00:00
704e73d6fe fix(cost-map): give the bare gpt-4o, gpt-4o-mini, gpt-4.1 and gpt-4.1-mini aliases their 2027-01-14 shutdown date (#49707)
28c80048ed fix(tool_choice): accept OpenAI allowed_tools on chat completions and flatten it for the Responses bridge (#49043)
20cb3ea439 test(integration): repair release qualification timing and labels (#49737)
94b5b6386a fix(bedrock): send native structured output for json_schema on Claude models that cannot force a tool (#49703)
Compare 59 commits »
scriptoriumadmin synced commits to refs/pull/49364/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:37 +00:00
f8f12a270a test(integration): repair stale contract fixtures (#49700)
508a98586e fix(databricks): join plain text blocks for non-Claude json_object requests (#49385)
f91774e2f9 fix(fireworks): keep developer items in place for models that accept a later system message (#49399)
a2ab27373f fix(proxy): count the context_management edits /v1/messages applies on every bridged provider (#49234)
Compare 17 commits »