scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/43882/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:23:59 +00:00
8f31c7171d fix(router): keep a lone deployment warm under router allowed_fails unless the policy names the exception (#48644)
a53ea5bd77 fix(proxy): keep every startup line JSON when json_logs is on (#47035)
2a9c630182 fix(proxy): release concurrency slots when synthetic streams complete (#48628)
ad4b35d791 fix(mcp): accept YAML OpenAPI documents (#48622)
Compare 43 commits »
scriptoriumadmin synced commits to refs/pull/44189/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:23:59 +00:00
41336b09e2 ci: run spend-logs-guard and cost-map-guard without installing the litellm project (#48683)
6e09664118 fix(decisions): catch ValidationError from validate_json in transform_decisions_response (#48660) (#48662)
4ad5a003b1 feat(search): add native xAI X Search support (#38505) (#48677)
c17faa1a27 fix(mcp): refuse calls to guardrail-hidden tools (#48669)
Compare 70 commits »
scriptoriumadmin synced commits to refs/pull/44163/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:23:59 +00:00
78c241da7b Merge remote-tracking branch 'upstream/main' into feat/add-tokenify-provider
b9e4298506 fix: preserve media across Responses and Gemini conversions (#48484)
696ff615d4 feat(morph): support open models and cached input pricing (#48676)
e5fe716d69 test(cost): cover unpriced provider slugs and explicit zero rates (#42467)
Compare 53 commits »
scriptoriumadmin synced commits to refs/pull/44163/head at scriptoriumadmin/litellm from mirror 2026-10-28 06:23:59 +00:00
78c241da7b Merge remote-tracking branch 'upstream/main' into feat/add-tokenify-provider
b9e4298506 fix: preserve media across Responses and Gemini conversions (#48484)
696ff615d4 feat(morph): support open models and cached input pricing (#48676)
e5fe716d69 test(cost): cover unpriced provider slugs and explicit zero rates (#42467)
7a23e497bd fix: honor empty mock completion responses (#48162) (#48266)
Compare 53 commits »
scriptoriumadmin synced commits to refs/pull/44060/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:23:59 +00:00
017e08aba3 fix(databricks): price the openjev decision model at its published 0.6 DBU per 1M input tokens (#48694)
b9e3587721 fix(embeddings): forward Gemini and Vertex request timeouts (#48690)
cd01c73dd9 fix(responses): preserve typed parts when logprobs is omitted (#48686)
4bdeb1378b chore: bump litellm-enterprise 0.1.79 -> 0.1.80, litellm 1.108.0 -> 1.109.0 (#48673)
Compare 70 commits »
scriptoriumadmin synced commits to refs/pull/44014/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:23:59 +00:00
14193435b8 refactor(anthropic): rename llms/anthropic/pass_through to llms/anthropic/messages (#48510)
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/44010/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:23:59 +00:00
0657ed46cf fix(langfuse_otel)!: derive trace-level name, input, output and tags on traces litellm starts (#42705)
14193435b8 refactor(anthropic): rename llms/anthropic/pass_through to llms/anthropic/messages (#48510)
Compare 3 commits »
scriptoriumadmin synced commits to refs/pull/43991/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:23:59 +00:00
e0d1e64591 feat(router): respect caller output budgets in complexity routing (#48632)
52562c47f8 refactor(proxy-extras): drop the spend-log api_key special case from the row check remedy (#48636)
34c10829b1 fix(ui): percent-encode request id in spend log detail URL (#48630)
9e01b3c37b fix(complexity_router): keep the held user_turn route for Codex compaction requests (#48627)
Compare 97 commits »
scriptoriumadmin synced commits to refs/pull/44273/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:23:59 +00:00
c7c895db45 fix(proxy)!: paginate customer lists and usage filters (#48700)
7acdf9f00d fix(anthropic): count search results and reject unsupported token-count blocks (#48699)
e4832c5d06 fix(cohere): map string stop parameter to list of strings for stop_sequences (#47091)
1171273511 fix(langfuse otel): emit request metadata under langfuse.observation.metadata and langfuse.trace.metadata on the OTEL v2 Langfuse mapper (#42697)
Compare 76 commits »
scriptoriumadmin synced commits to refs/pull/44263/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:23:59 +00:00
e0d1e64591 feat(router): respect caller output budgets in complexity routing (#48632)
52562c47f8 refactor(proxy-extras): drop the spend-log api_key special case from the row check remedy (#48636)
34c10829b1 fix(ui): percent-encode request id in spend log detail URL (#48630)
9e01b3c37b fix(complexity_router): keep the held user_turn route for Codex compaction requests (#48627)
Compare 38 commits »
scriptoriumadmin synced commits to refs/pull/43977/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:23:59 +00:00
73cd296418 fix(chatgpt): send system input items to Codex as developer (#48668)
1b932332c1 fix(ui): omit blank expiry from key edit and regenerate payloads (#48634)
59b8c73930 fix(proxy): abort the request with a 499 when the client disconnects during the body upload (#48640)
cedae29cc7 fix(ui): keep vendor names and agent instructions in AI wording under SI terminology (#48670)
Compare 51 commits »
scriptoriumadmin synced commits to refs/pull/44037/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:23:59 +00:00
b9fe3d4c13 Merge branch 'main' into fix/pass-through-spend-tag-headers-44032
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 13 commits »
scriptoriumadmin synced commits to refs/pull/43895/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:23:59 +00:00
4bdeb1378b chore: bump litellm-enterprise 0.1.79 -> 0.1.80, litellm 1.108.0 -> 1.109.0 (#48673)
b5fb898d03 feat(passthrough): let upstreams report the model name via x-litellm-upstream-model (#48275)
8d30009b78 chore: update Next.js build artifacts (2026-10-28 01:11 UTC, node v24.19.0) (#48692)
8ced2cf433 fix(router): keep session tier pins coherent across workers (#48645)
Compare 139 commits »
scriptoriumadmin synced commits to refs/pull/43893/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:23:59 +00:00
4bdeb1378b chore: bump litellm-enterprise 0.1.79 -> 0.1.80, litellm 1.108.0 -> 1.109.0 (#48673)
b5fb898d03 feat(passthrough): let upstreams report the model name via x-litellm-upstream-model (#48275)
8d30009b78 chore: update Next.js build artifacts (2026-10-28 01:11 UTC, node v24.19.0) (#48692)
8ced2cf433 fix(router): keep session tier pins coherent across workers (#48645)
Compare 139 commits »
scriptoriumadmin synced commits to refs/pull/44222/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:23:59 +00:00
0657ed46cf fix(langfuse_otel)!: derive trace-level name, input, output and tags on traces litellm starts (#42705)
14193435b8 refactor(anthropic): rename llms/anthropic/pass_through to llms/anthropic/messages (#48510)
Compare 3 commits »
scriptoriumadmin synced commits to refs/pull/44037/head at scriptoriumadmin/litellm from mirror 2026-10-28 06:23:59 +00:00
b9fe3d4c13 Merge branch 'main' into fix/pass-through-spend-tag-headers-44032
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)
e5757934fd fix(azure): add keyless Decisions authentication (#48386) (#48529)
Compare 84 commits »
scriptoriumadmin synced commits to refs/pull/43753/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:23:58 +00:00
e0d1e64591 feat(router): respect caller output budgets in complexity routing (#48632)
52562c47f8 refactor(proxy-extras): drop the spend-log api_key special case from the row check remedy (#48636)
34c10829b1 fix(ui): percent-encode request id in spend log detail URL (#48630)
9e01b3c37b fix(complexity_router): keep the held user_turn route for Codex compaction requests (#48627)
Compare 39 commits »
scriptoriumadmin synced commits to refs/pull/43697/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:23:58 +00:00
41336b09e2 ci: run spend-logs-guard and cost-map-guard without installing the litellm project (#48683)
6e09664118 fix(decisions): catch ValidationError from validate_json in transform_decisions_response (#48660) (#48662)
4ad5a003b1 feat(search): add native xAI X Search support (#38505) (#48677)
c17faa1a27 fix(mcp): refuse calls to guardrail-hidden tools (#48669)
Compare 90 commits »
scriptoriumadmin synced commits to refs/pull/43799/head at scriptoriumadmin/litellm from mirror 2026-10-28 06:23:58 +00:00
8a1c7b82ad fix(redact_messages): guard against None output_items in Responses API redaction helpers
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)
e5757934fd fix(azure): add keyless Decisions authentication (#48386) (#48529)
Compare 1930 commits »
scriptoriumadmin synced commits to refs/pull/43697/head at scriptoriumadmin/litellm from mirror 2026-10-28 06:23:58 +00:00
0a813aecee test(integration): tie the auth span to its request trace and prove post-restart calls reach the provider