scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/47107/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:13 +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/47106/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:13 +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/47111/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:13 +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)
cfe0100e1f fix(router): preserve tag fail-open policy through affinity and cooldown (#48470)
aa33b052d2 fix(messages): honor OpenAI stop_sequences (#37118) (#48534)
Compare 72 commits »
scriptoriumadmin synced commits to refs/pull/47112/head at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:13 +00:00
f7ae2b3058 ci: empty commit to re-run flaky proxy-infra-root / db-and-spend
94f508e2b2 style(proxy): ruff format blank line before get_spend_routes helper
b5a2877947 test(proxy): cover _has_truthy_permission shapes for codecov
a879762be3 fix(proxy): avoid reportArgumentType when writing parsed permissions
d120703560 fix(proxy): cast permission maps for basedpyright unknown-type gate
Compare 94 commits »
scriptoriumadmin synced commits to refs/pull/47121/head at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:13 +00:00
63ce629155 fix(anthropic): order messages after system and tools in /v1/messages request body
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 346 commits »
scriptoriumadmin synced commits to refs/pull/47121/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:13 +00:00
63ce629155 fix(anthropic): order messages after system and tools in /v1/messages request body
c23cff7e45 fix(mcp): enforce deny-first tool policy consistently (#48625)
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)
Compare 40 commits »
scriptoriumadmin synced commits to refs/pull/46860/head at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:12 +00:00
ae1ccac316 Merge remote-tracking branch 'upstream/main' into litellm_guardrail_choice_isolation
dddbaa803d build(docker): refresh base images and ship only runtime files in component images (#48279)
72f1ac4a27 revert(proxy): revert large-integer request parsing (#48289)
d3b70c42ed fix(proxy): keep JSON integers outside the 64-bit range exact when parsing request bodies (#48213)
de5dc5b238 feat(mistral): add zai-glm-5-3-flash to the cost map (#48270)
Compare 226 commits »
scriptoriumadmin synced commits to refs/pull/46858/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:12 +00:00
b783f41a6a Merge branch 'litellm_guardrail_choice_isolation' into litellm_guardrail_stream_inspection
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 129 commits »
scriptoriumadmin synced commits to refs/pull/46901/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:12 +00:00
403f8f5a20 feat: add Decision Models decisions provider
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/46938/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:12 +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 77 commits »
scriptoriumadmin synced commits to refs/pull/46858/head at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:12 +00:00
b783f41a6a Merge branch 'litellm_guardrail_choice_isolation' into litellm_guardrail_stream_inspection
ae1ccac316 Merge remote-tracking branch 'upstream/main' into litellm_guardrail_choice_isolation
dddbaa803d build(docker): refresh base images and ship only runtime files in component images (#48279)
72f1ac4a27 revert(proxy): revert large-integer request parsing (#48289)
d3b70c42ed fix(proxy): keep JSON integers outside the 64-bit range exact when parsing request bodies (#48213)
Compare 227 commits »
scriptoriumadmin synced commits to refs/pull/46901/head at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:12 +00:00
403f8f5a20 feat: add Decision Models decisions provider
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/46900/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:12 +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/46897/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:12 +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)
cfe0100e1f fix(router): preserve tag fail-open policy through affinity and cooldown (#48470)
aa33b052d2 fix(messages): honor OpenAI stop_sequences (#37118) (#48534)
Compare 65 commits »
scriptoriumadmin synced commits to refs/pull/46882/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:12 +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/46867/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:12 +00:00
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 12 commits »
scriptoriumadmin synced commits to refs/pull/46860/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:12 +00:00
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 12 commits »
scriptoriumadmin synced commits to refs/pull/46643/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:11 +00:00
e214ac1801 refactor: clean up fresh tech debt in responses bridge check, chatgpt authenticator and image header adapters
bff981c621 Merge remote-tracking branch 'origin/main' into litellm_techdebt_20261015
cfe0100e1f fix(router): preserve tag fail-open policy through affinity and cooldown (#48470)
aa33b052d2 fix(messages): honor OpenAI stop_sequences (#37118) (#48534)
Compare 85 commits »
scriptoriumadmin synced commits to refs/pull/46695/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:11 +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 48 commits »
scriptoriumadmin synced commits to refs/pull/46833/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:11 +00:00
e5fe716d69 test(cost): cover unpriced provider slugs and explicit zero rates (#42467)
7a23e497bd fix: honor empty mock completion responses (#48162) (#48266)
f277f1e260 fix(bedrock): add token_count_model to three Mantle-native Claude rows (#48682)
41336b09e2 ci: run spend-logs-guard and cost-map-guard without installing the litellm project (#48683)
Compare 68 commits »