scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/38200/merge at scriptoriumadmin/litellm from mirror 2026-09-05 08:09:57 +00:00
d23bec84c4 Merge pull request #39196 from BerriAI/litellm_guardrail_usage_cost_rollup
6dff3a5f72 fix(complexity_router): fall back to a live peer when the decided tier model is fully cooled down (#39675)
df68edca76 Merge pull request #39808 from BerriAI/litellm_lit_5379_jwt_mapping_cache_invalidation
922659fb15 Merge pull request #39388 from BerriAI/litellm_registry_audit_2026_09_02
Compare 1876 commits »
scriptoriumadmin synced commits to refs/pull/38186/merge at scriptoriumadmin/litellm from mirror 2026-09-05 08:09:56 +00:00
b310688134 Merge d48bfc9298d5a8ddb06ee59df7eae068175149ce into 32291c9ad2
32291c9ad2 Merge pull request #38942 from BerriAI/litellm_lite_claude_enable_tool_search-8eee
43c64e2471 fix(cli): keep an existing ENABLE_TOOL_SEARCH value
096e016baf fix(cli): sort claude_settings __all__ for ruff RUF022
cafdfda8ba feat(cli): set ENABLE_TOOL_SEARCH=true for lite claude
Compare 642 commits »
scriptoriumadmin synced commits to refs/pull/38181/merge at scriptoriumadmin/litellm from mirror 2026-09-05 08:09:56 +00:00
40edeaaecb fix(otel): emit cache token counts on OTel v2 LLM spans (#38716)
be3386f3ce Merge pull request #38995 from BerriAI/litellm_openai_wif
66295e7da7 Merge pull request #34696 from cat0825/fix/34379-unblock-customer
1249f84b10 fix(vertex_ai): graft default vertex path when api_base has a version-only path (#38986)
Compare 629 commits »
scriptoriumadmin synced commits to refs/pull/38175/merge at scriptoriumadmin/litellm from mirror 2026-09-05 08:09:56 +00:00
43fafbc42a Merge c244e5fca42b23c740d096432825e5db28596d0b into c8635ecc67
c8635ecc67 feat: page the public model hub table off /public/v1/model_hub, keeping every filter (#39691)
eb67e5402b test(ocr): complete Rust unit test parity (#39689)
ee08c36fc0 refactor(tests): restructure rust python harness around strategy definitions (#39628)
8fc0663198 fix(ci): pin setup-uv to v10.0.1 (#39111)
Compare 1807 commits »
scriptoriumadmin synced commits to refs/pull/38191/merge at scriptoriumadmin/litellm from mirror 2026-09-05 08:09:56 +00:00
f92b1b461e Merge e10ff102475afe31f9df51f9ce9c047025148fd8 into aa3d59d086
aa3d59d086 fix(anthropic): never carry cache_control on translated thinking blocks (#39815)
da09976c16 Merge pull request #39572 from BerriAI/litellm_spend_logs_keep_service_account_key_readable
a6b7384094 feat(cli): sync OpenCode models from /v1/models in lite opencode (#39789)
c373645e21 fix(proxy): recognize opencode's bare x-session-id header for session affinity (#39802)
Compare 1886 commits »
scriptoriumadmin synced commits to refs/pull/38191/head at scriptoriumadmin/litellm from mirror 2026-09-05 08:09:56 +00:00
e10ff10247 fix(chatgpt): re-normalize Responses string input after extra_body merge
03f7a4b1f1 Add ChatGPT Responses string input test
50daae5b81 fix(chatgpt): normalize Responses string input
4d7144160a Merge pull request #38715 from BerriAI/litellm_/restrictedpython-security-update-c0aee7
c80dc68445 Merge branch 'litellm_internal_staging' into litellm_/restrictedpython-security-update-c0aee7
Compare 795 commits »
scriptoriumadmin synced commits to refs/pull/38189/merge at scriptoriumadmin/litellm from mirror 2026-09-05 08:09:56 +00:00
10631eb834 Merge pull request #38805 from BerriAI/litellm_internal_staging
6b33d17563 Merge pull request #38850 from BerriAI/litellm_e2e_retry_transient_upstream
df848d85ff Merge pull request #38833 from BerriAI/litellm_deflake_reliability_fallbacks
3c2fa5fafb fix(otel/v2): detach credential-routed tenant spans into their own trace (#38847)
Compare 938 commits »
scriptoriumadmin synced commits to refs/pull/38188/head at scriptoriumadmin/litellm from mirror 2026-09-05 08:09:56 +00:00
6a4e558f61 fix(responses): unwrap completed response for cost tracking on bridge path
ca0b951a43 feat(spend): report prompt caching savings as total and gateway-attributed (#38134)
2b10dc5a7a Merge pull request #38304 from BerriAI/litellm_fix_staging_ci_regressions
74bc1efe65 Merge branch 'litellm_internal_staging' into litellm_fix_staging_ci_regressions
02c1c45b53 fix(complexity_router): route client housekeeping calls to the cheapest tier (#38598)
Compare 2728 commits »
scriptoriumadmin synced commits to refs/pull/38184/merge at scriptoriumadmin/litellm from mirror 2026-09-05 08:09:56 +00:00
d6f097f79f Merge c78d409e70b17c4d57d41ad1969fba47d9e30297 into 2e734004f9
2e734004f9 Merge pull request #39399 from BerriAI/litellm_python_version_ci
6675e1fd9c fix: preserve Python 3.10 harness compatibility
fae3d224eb Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_python_version_ci
b75ac5cf52 feat(python): rename Rust rollout API (#39704)
Compare 1754 commits »
scriptoriumadmin synced commits to refs/pull/38168/head at scriptoriumadmin/litellm from mirror 2026-09-05 08:09:55 +00:00
bea74c144e fix: use Python 3.10-compatible spend log timeout
445b209e42 fix: avoid Final binding inside drain loop
6b10d551ab fix: time out spend drain writes without parking a coroutine
e125a98605 test: tighten spend-drain helper types
29efcc50d3 fix: bound spend log shutdown drain
Compare 5 commits »
scriptoriumadmin synced commits to refs/pull/38165/merge at scriptoriumadmin/litellm from mirror 2026-09-05 08:09:55 +00:00
ec3f8183c3 Merge pull request #39066 from BerriAI/litellm_aws_external_id_files_batches
9f6024bf97 Merge pull request #39044 from BerriAI/litellm_fix_bedrock_guardrail_token_log
b11f0bcb92 fix(proxy): include litellm_model_table in GET /v2/team/list (#39045)
db46973ec4 feat(ui): modality routing toggle on the auto-router create and edit forms (#39059)
Compare 931 commits »
scriptoriumadmin synced commits to refs/pull/38164/merge at scriptoriumadmin/litellm from mirror 2026-09-05 08:09:55 +00:00
b82a7deb7a Merge 784f7b92a52f9a83a3852ef597115876e028530f into 2ce4e3f8a9
2ce4e3f8a9 fix(guardrails): run apply_guardrail-only providers in logging_only mode (#39297)
8588a2ea42 fix(docker): install saml extra in litellm-backend image (#39291)
31ca4ddf32 Merge pull request #39166 from BerriAI/litellm_bedrock_bearer_token_converse_crash
e2c3f51c46 fix(search): forward search-tool params through the router, complete Parallel AI v1 param mapping (#37883)
Compare 1141 commits »
scriptoriumadmin synced commits to refs/pull/38160/merge at scriptoriumadmin/litellm from mirror 2026-09-05 08:09:55 +00:00
68c47418b5 refactor(sso): share role hierarchy and highest_privilege_role across SSO paths
04138c9156 merge: litellm_internal_staging into devin_ai_sso_highest_privilege_role
2ce4e3f8a9 fix(guardrails): run apply_guardrail-only providers in logging_only mode (#39297)
8588a2ea42 fix(docker): install saml extra in litellm-backend image (#39291)
Compare 1206 commits »
scriptoriumadmin synced commits to refs/pull/38162/merge at scriptoriumadmin/litellm from mirror 2026-09-05 08:09:55 +00:00
78ff5ac9cd feat(router): arm safeguard-refusal fallback on generic chains when no content-policy list exists (#39274)
8441dd6e8c fix(proxy): keep SpendLogs and callback session ids in sync when the request has none (#39450)
92edcb90db fix: keep litellm importable on Python 3.10 and guard 3.11-only typing imports in CI (#39448)
4f7b20ec10 fix(guardrails): skip streaming guardrail rounds that re-scan cleared output (#39386)
Compare 1393 commits »
scriptoriumadmin synced commits to refs/pull/38168/merge at scriptoriumadmin/litellm from mirror 2026-09-05 08:09:55 +00:00
a6b7384094 feat(cli): sync OpenCode models from /v1/models in lite opencode (#39789)
c373645e21 fix(proxy): recognize opencode's bare x-session-id header for session affinity (#39802)
b3c867c7b2 fix(auto_router): derive tier definitions in prompt editor (#39688)
d23bec84c4 Merge pull request #39196 from BerriAI/litellm_guardrail_usage_cost_rollup
Compare 1884 commits »
scriptoriumadmin synced commits to refs/pull/38170/merge at scriptoriumadmin/litellm from mirror 2026-09-05 08:09:55 +00:00
78ff5ac9cd feat(router): arm safeguard-refusal fallback on generic chains when no content-policy list exists (#39274)
8441dd6e8c fix(proxy): keep SpendLogs and callback session ids in sync when the request has none (#39450)
92edcb90db fix: keep litellm importable on Python 3.10 and guard 3.11-only typing imports in CI (#39448)
4f7b20ec10 fix(guardrails): skip streaming guardrail rounds that re-scan cleared output (#39386)
Compare 1277 commits »
scriptoriumadmin synced commits to refs/pull/38172/merge at scriptoriumadmin/litellm from mirror 2026-09-05 08:09:55 +00:00
78ff5ac9cd feat(router): arm safeguard-refusal fallback on generic chains when no content-policy list exists (#39274)
8441dd6e8c fix(proxy): keep SpendLogs and callback session ids in sync when the request has none (#39450)
92edcb90db fix: keep litellm importable on Python 3.10 and guard 3.11-only typing imports in CI (#39448)
4f7b20ec10 fix(guardrails): skip streaming guardrail rounds that re-scan cleared output (#39386)
Compare 1393 commits »
scriptoriumadmin synced commits to refs/pull/38173/merge at scriptoriumadmin/litellm from mirror 2026-09-05 08:09:55 +00:00
ec3f8183c3 Merge pull request #39066 from BerriAI/litellm_aws_external_id_files_batches
9f6024bf97 Merge pull request #39044 from BerriAI/litellm_fix_bedrock_guardrail_token_log
b11f0bcb92 fix(proxy): include litellm_model_table in GET /v2/team/list (#39045)
db46973ec4 feat(ui): modality routing toggle on the auto-router create and edit forms (#39059)
Compare 931 commits »
scriptoriumadmin synced commits to refs/pull/38175/head at scriptoriumadmin/litellm from mirror 2026-09-05 08:09:55 +00:00
c244e5fca4 style(guardrails): drop three whitespace-only leftovers from the narrowing
2452ea8de3 refactor(guardrails): drop an out-of-scope bin-packing rewrite, pin the source fallback
24359ce82d fix(guardrails): close patch-coverage gaps in bedrock image handling
a46896b436 fix(guardrails): avoid empty-dict default to satisfy type-discipline budget
2a47f157fe Merge branch 'litellm_internal_staging' into fix/bedrock-guardrail-image-input
Compare 1281 commits »
scriptoriumadmin synced commits to refs/pull/38150/merge at scriptoriumadmin/litellm from mirror 2026-09-05 08:09:54 +00:00
d23bec84c4 Merge pull request #39196 from BerriAI/litellm_guardrail_usage_cost_rollup
6dff3a5f72 fix(complexity_router): fall back to a live peer when the decided tier model is fully cooled down (#39675)
df68edca76 Merge pull request #39808 from BerriAI/litellm_lit_5379_jwt_mapping_cache_invalidation
922659fb15 Merge pull request #39388 from BerriAI/litellm_registry_audit_2026_09_02
Compare 1763 commits »