scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/30325/merge at scriptoriumadmin/litellm from mirror 2026-08-26 05:06:06 +00:00
3e2927de9a Merge pull request #38296 from BerriAI/litellm_fix_otel_provider_error_stack_trace
514cae1b3d fix(logging): keep the proxy's own budget rejection an expected client error
a6e1708e6c fix(logging): keep proxy-side rate limits as expected client errors
ac6deec529 fix(logging): keep tracebacks for unmapped provider exceptions too
Compare 309 commits »
scriptoriumadmin synced commits to refs/pull/30374/merge at scriptoriumadmin/litellm from mirror 2026-08-26 05:06:06 +00:00
5470c1bccb fix(ui): forward OAuth issuer/authorization/token/registration URLs from the MCP server edit form (#38154)
c3bcb6f64f test(mcp): drain the logging worker after each test so queued callbacks cannot leak into the next test (#38228)
751976db8b Merge pull request #38229 from BerriAI/litellm_vertex_ai_interactions
92fe35854b Merge pull request #38222 from BerriAI/litellm_fix_mantle_reasoning_effort_max
Compare 199 commits »
scriptoriumadmin synced commits to refs/pull/30565/merge at scriptoriumadmin/litellm from mirror 2026-08-26 05:06:06 +00:00
5470c1bccb fix(ui): forward OAuth issuer/authorization/token/registration URLs from the MCP server edit form (#38154)
c3bcb6f64f test(mcp): drain the logging worker after each test so queued callbacks cannot leak into the next test (#38228)
751976db8b Merge pull request #38229 from BerriAI/litellm_vertex_ai_interactions
92fe35854b Merge pull request #38222 from BerriAI/litellm_fix_mantle_reasoning_effort_max
Compare 199 commits »
scriptoriumadmin synced commits to refs/pull/30607/merge at scriptoriumadmin/litellm from mirror 2026-08-26 05:06:06 +00:00
d16c4dad4b feat(logging): add async_post_call_failure_deployment_hook (#36657)
ea6ac3dd99 Merge pull request #38283 from BerriAI/litellm_together_regression_tests
d0c527f3bb Merge pull request #36245 from BerriAI/litellm_fix_headroom_stream_leak
602bf1c0ac test(together_ai): close the injected async client after the streaming test
Compare 426 commits »
scriptoriumadmin synced commits to refs/pull/30840/merge at scriptoriumadmin/litellm from mirror 2026-08-26 05:06:06 +00:00
75c4565dde fix(cerebras): add max_retries and extra_headers to get_supported_openai_params (#36601)
d8d384eada Merge pull request #38230 from BerriAI/litellm_together_models_backfill
02cba40bb6 Merge pull request #37756 from BerriAI/litellm_jwt_team_allowed_routes_wildcard
c70b911122 fix(router): support mid-stream fallback for anthropic_messages route type (#38153)
Compare 374 commits »
scriptoriumadmin synced commits to refs/pull/30060/merge at scriptoriumadmin/litellm from mirror 2026-08-26 05:06:06 +00:00
0458accaa0 perf(auth): drop guaranteed-miss internal-cache Redis read from team object lookup (#38073)
896e2598da fix(caching): keep upstream RedisCluster on redis-py with per-connection recovery (#38171)
e25ce85dbc fix(proxy): stop expected 4xx responses from saturating worker CPU on failure logging (#38102)
c6082c5255 Merge pull request #37897 from BerriAI/litellm_reasoning_effort_capability_v2
Compare 260 commits »
scriptoriumadmin synced commits to refs/pull/30066/merge at scriptoriumadmin/litellm from mirror 2026-08-26 05:06:06 +00:00
bb22742025 fix(rerank): emit latency and cost headers on /rerank (#35419)
04818a3554 Merge pull request #38267 from BerriAI/litellm_fix_responses_user_document_drop
e4ff44f623 Merge pull request #38265 from BerriAI/litellm_together_tools_passthrough
dc40377959 Merge pull request #38261 from BerriAI/litellm_fix_responses_tool_result_document_drop
Compare 159 commits »
scriptoriumadmin synced commits to refs/pull/30086/merge at scriptoriumadmin/litellm from mirror 2026-08-26 05:06:06 +00:00
e5adf7d926 Merge pull request #37493 from BerriAI/devin_ai_lit5815_guardrail_tag_mode_ui
104fe73113 fix(dashboard): don't show a stale provider prompt-cache chip on a response-cache hit (#37951)
27ca05a707 fix(ui): read reasoning tokens from Responses API output_tokens_details (#37952)
ece03ceafe Merge pull request #38248 from BerriAI/litellm_together_chat_config
Compare 363 commits »
scriptoriumadmin synced commits to refs/pull/30568/merge at scriptoriumadmin/litellm from mirror 2026-08-26 05:06:06 +00:00
5470c1bccb fix(ui): forward OAuth issuer/authorization/token/registration URLs from the MCP server edit form (#38154)
c3bcb6f64f test(mcp): drain the logging worker after each test so queued callbacks cannot leak into the next test (#38228)
751976db8b Merge pull request #38229 from BerriAI/litellm_vertex_ai_interactions
92fe35854b Merge pull request #38222 from BerriAI/litellm_fix_mantle_reasoning_effort_max
Compare 199 commits »
scriptoriumadmin synced commits to refs/pull/30872/merge at scriptoriumadmin/litellm from mirror 2026-08-26 05:06:06 +00:00
3e2927de9a Merge pull request #38296 from BerriAI/litellm_fix_otel_provider_error_stack_trace
514cae1b3d fix(logging): keep the proxy's own budget rejection an expected client error
a6e1708e6c fix(logging): keep proxy-side rate limits as expected client errors
ac6deec529 fix(logging): keep tracebacks for unmapped provider exceptions too
Compare 309 commits »
scriptoriumadmin synced commits to refs/pull/31026/merge at scriptoriumadmin/litellm from mirror 2026-08-26 05:06:06 +00:00
bb22742025 fix(rerank): emit latency and cost headers on /rerank (#35419)
04818a3554 Merge pull request #38267 from BerriAI/litellm_fix_responses_user_document_drop
e4ff44f623 Merge pull request #38265 from BerriAI/litellm_together_tools_passthrough
dc40377959 Merge pull request #38261 from BerriAI/litellm_fix_responses_tool_result_document_drop
Compare 265 commits »
scriptoriumadmin synced commits to refs/pull/31070/merge at scriptoriumadmin/litellm from mirror 2026-08-26 05:06:06 +00:00
1f8e8f61a4 Merge 7493da2bed19cb5d732e0903c0d959e328bcbdaf into 5470c1bccb
5470c1bccb fix(ui): forward OAuth issuer/authorization/token/registration URLs from the MCP server edit form (#38154)
c3bcb6f64f test(mcp): drain the logging worker after each test so queued callbacks cannot leak into the next test (#38228)
751976db8b Merge pull request #38229 from BerriAI/litellm_vertex_ai_interactions
92fe35854b Merge pull request #38222 from BerriAI/litellm_fix_mantle_reasoning_effort_max
Compare 199 commits »
scriptoriumadmin synced commits to refs/pull/31155/merge at scriptoriumadmin/litellm from mirror 2026-08-26 05:06:06 +00:00
6e569ee0c7 Merge pull request #38293 from BerriAI/litellm_internal_staging
3e2927de9a Merge pull request #38296 from BerriAI/litellm_fix_otel_provider_error_stack_trace
514cae1b3d fix(logging): keep the proxy's own budget rejection an expected client error
a6e1708e6c fix(logging): keep proxy-side rate limits as expected client errors
Compare 362 commits »
scriptoriumadmin synced commits to refs/pull/30032/merge at scriptoriumadmin/litellm from mirror 2026-08-26 05:06:05 +00:00
ea6ac3dd99 Merge pull request #38283 from BerriAI/litellm_together_regression_tests
d0c527f3bb Merge pull request #36245 from BerriAI/litellm_fix_headroom_stream_leak
602bf1c0ac test(together_ai): close the injected async client after the streaming test
7c3da429c7 test(together_ai): regression suite across chat, responses, and messages surfaces
Compare 425 commits »
scriptoriumadmin synced commits to refs/pull/30051/merge at scriptoriumadmin/litellm from mirror 2026-08-26 05:06:05 +00:00
c6b938367c Merge 528653d4c27bc36292d015ed60c48bb7ea6f3479 into 5470c1bccb
5470c1bccb fix(ui): forward OAuth issuer/authorization/token/registration URLs from the MCP server edit form (#38154)
c3bcb6f64f test(mcp): drain the logging worker after each test so queued callbacks cannot leak into the next test (#38228)
751976db8b Merge pull request #38229 from BerriAI/litellm_vertex_ai_interactions
92fe35854b Merge pull request #38222 from BerriAI/litellm_fix_mantle_reasoning_effort_max
Compare 207 commits »
scriptoriumadmin synced commits to refs/pull/30010/merge at scriptoriumadmin/litellm from mirror 2026-08-26 05:06:05 +00:00
75bf9f9452 fix(router): persist attempted_fallbacks and original_model_group into spend logs metadata (#38107)
1ff615c335 Merge pull request #38275 from BerriAI/litellm_together_chat_template_kwargs
6684bb343b perf(streaming): add shared JSONFragmentAccumulator for Vertex and Anthropic (#36610)
8a61b286d1 test(together_ai): annotate preserved-thinking test helper and capture list
Compare 164 commits »
scriptoriumadmin synced commits to refs/pull/29918/merge at scriptoriumadmin/litellm from mirror 2026-08-26 05:06:05 +00:00
6e569ee0c7 Merge pull request #38293 from BerriAI/litellm_internal_staging
3e2927de9a Merge pull request #38296 from BerriAI/litellm_fix_otel_provider_error_stack_trace
514cae1b3d fix(logging): keep the proxy's own budget rejection an expected client error
a6e1708e6c fix(logging): keep proxy-side rate limits as expected client errors
Compare 362 commits »
scriptoriumadmin synced commits to refs/pull/29915/merge at scriptoriumadmin/litellm from mirror 2026-08-26 05:06:05 +00:00
81890ce791 Merge 3b5eb7c610fe33ac07b2d882857c9d9fd473597b into c6082c5255
c6082c5255 Merge pull request #37897 from BerriAI/litellm_reasoning_effort_capability_v2
3db6c5ab18 Merge pull request #37770 from BerriAI/litellm_fix_model_router_spend_log_model
5b2d1874b0 Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_reasoning_effort_capability_v2
a9f42f0ccf Merge pull request #38227 from BerriAI/litellm_mantle_codex_input_items
Compare 57 commits »
scriptoriumadmin synced commits to refs/pull/29839/merge at scriptoriumadmin/litellm from mirror 2026-08-26 05:06:05 +00:00
ba8d8b6e14 fix(logging): redact tool call arguments to valid JSON and preserve null content (#38182)
75bf9f9452 fix(router): persist attempted_fallbacks and original_model_group into spend logs metadata (#38107)
1ff615c335 Merge pull request #38275 from BerriAI/litellm_together_chat_template_kwargs
6684bb343b perf(streaming): add shared JSONFragmentAccumulator for Vertex and Anthropic (#36610)
Compare 109 commits »
scriptoriumadmin synced commits to refs/pull/29805/merge at scriptoriumadmin/litellm from mirror 2026-08-26 05:06:05 +00:00
09fe890b90 Merge 04eac6ababfd12a818063372dff07600fc38085b into 31a67561ab
04eac6abab fix(logging): honor NO_COLOR / FORCE_COLOR / tty for non-JSON formatter
31a67561ab feat(complexity_router): bound the classifier context block, not each turn in it (#38145)
a9c7b848f2 fix(logging): skip parsing redacted tool call arguments (#38169)
5745313448 Merge pull request #38124 from BerriAI/litellm_codeowners_ui_infra_exemptions
Compare 3015 commits »