scriptoriumadmin
0 followers · 0 following
  • Joined on 2026-03-01
Repositories
21
 Projects Packages Public activity Starred repositories
scriptoriumadmin synced commits to refs/pull/46810/merge at scriptoriumadmin/litellm from mirror 2026-10-21 05:17:39 +00:00
dbde350826 Merge 64b27eea92 into 41890bdf64
41890bdf64 fix(token_counter): stop re-downloading a HuggingFace tokenizer after a failed download (#47586)
1e1770aa48 test(perf): emit event_loop_stalls hold counts as perf_ JUnit properties (#47706)
e333ccabdb fix(scim)!: delete a group through the team delete's bulk path instead of one member at a time (#47544)
3c28f4bf1e fix(ui): show the budget spend limit and rate limits without a collapsed section (#47662)
Compare 159 commits »
scriptoriumadmin synced commits to refs/pull/46811/merge at scriptoriumadmin/litellm from mirror 2026-10-21 05:17:39 +00:00
d691fee288 Merge bcd2fa52ae into 8d6b8dab3d
8d6b8dab3d fix(cli): send pi's session id from lite pi so sessions group and stick (#47700)
8fe0a7358e ci(integration): keep the MCP SDK1 peer on mcp 1.x and autovacuum off the size cleanup test (#47651)
0e24bbb8a2 fix(responses): bill every round of a streamed MCP auto-execute on one spend row (#47445)
647ebd63e0 test(perf): emit per-location seconds, offending locations and the ten longest holds as event_loop_stalls breakdowns (#47757)
Compare 227 commits »
scriptoriumadmin synced commits to refs/pull/46820/head at scriptoriumadmin/litellm from mirror 2026-10-21 05:17:39 +00:00
af3d5c1518 refactor: call execute_chat from the Messages to chat bridge
aff2f9dc43 refactor: extract execute_chat from completion()
7f0e9e9584 refactor: call execute_responses from the Messages to Responses bridge
e649ebcac4 refactor: extract execute_messages and execute_responses native executors
cd10e367ff refactor: decide the native API format once with plan_route
Compare 113 commits »
scriptoriumadmin synced commits to refs/pull/46820/merge at scriptoriumadmin/litellm from mirror 2026-10-21 05:17:39 +00:00
39423e794a Merge af3d5c1518 into 7d2c9f08b0
7d2c9f08b0 Merge aff2f9dc43 into 2f92d444af
2f92d444af Merge 7f0e9e9584 into 60e4afb6a6
60e4afb6a6 Merge e649ebcac4 into 0cf754b9b9
0cf754b9b9 Merge cd10e367ff into 5c341e7308
Compare 121 commits »
scriptoriumadmin synced commits to refs/pull/46821/head at scriptoriumadmin/litellm from mirror 2026-10-21 05:17:39 +00:00
5cbc378ddd refactor: plan forced-chat thinking on OpenAI straight to Responses
af3d5c1518 refactor: call execute_chat from the Messages to chat bridge
aff2f9dc43 refactor: extract execute_chat from completion()
7f0e9e9584 refactor: call execute_responses from the Messages to Responses bridge
e649ebcac4 refactor: extract execute_messages and execute_responses native executors
Compare 114 commits »
scriptoriumadmin synced commits to refs/pull/46821/merge at scriptoriumadmin/litellm from mirror 2026-10-21 05:17:39 +00:00
df6ecac9e6 Merge 5cbc378ddd into 39423e794a
39423e794a Merge af3d5c1518 into 7d2c9f08b0
7d2c9f08b0 Merge aff2f9dc43 into 2f92d444af
2f92d444af Merge 7f0e9e9584 into 60e4afb6a6
60e4afb6a6 Merge e649ebcac4 into 0cf754b9b9
Compare 123 commits »
scriptoriumadmin synced commits to refs/pull/46825/head at scriptoriumadmin/litellm from mirror 2026-10-21 05:17:39 +00:00
7aab20c882 refactor: call execute_chat from the Responses to chat bridge
5cbc378ddd refactor: plan forced-chat thinking on OpenAI straight to Responses
af3d5c1518 refactor: call execute_chat from the Messages to chat bridge
aff2f9dc43 refactor: extract execute_chat from completion()
7f0e9e9584 refactor: call execute_responses from the Messages to Responses bridge
Compare 115 commits »
scriptoriumadmin synced commits to refs/pull/46832/head at scriptoriumadmin/litellm from mirror 2026-10-21 05:17:39 +00:00
2166698de6 refactor(responses): send bridged chat calls to the Responses executor
7aab20c882 refactor: call execute_chat from the Responses to chat bridge
5cbc378ddd refactor: plan forced-chat thinking on OpenAI straight to Responses
af3d5c1518 refactor: call execute_chat from the Messages to chat bridge
aff2f9dc43 refactor: extract execute_chat from completion()
Compare 116 commits »
scriptoriumadmin synced commits to refs/pull/46833/merge at scriptoriumadmin/litellm from mirror 2026-10-21 05:17:39 +00:00
a984bffc61 Merge 85e3967a28 into 17db64ef78
17db64ef78 test(perf): record the row count and size of each table the Admin UI journeys query (#47683)
735ebc466c chore(deps-dev): bump vite from 8.3.0 to 8.3.4 in /vscode-extension (#47627)
6083cf9776 fix(mcp): list per-user auth MCP tools without a shared token (#47677)
49b5444ef9 fix(mcp): list per-user auth MCP tools without a shared token (#47677)
Compare 187 commits »
scriptoriumadmin synced commits to refs/pull/46838/head at scriptoriumadmin/litellm from mirror 2026-10-21 05:17:39 +00:00
e3a4ec7387 refactor(chat): keep responses-mode models on chat when the provider has no Responses API
2166698de6 refactor(responses): send bridged chat calls to the Responses executor
7aab20c882 refactor: call execute_chat from the Responses to chat bridge
5cbc378ddd refactor: plan forced-chat thinking on OpenAI straight to Responses
af3d5c1518 refactor: call execute_chat from the Messages to chat bridge
Compare 117 commits »
scriptoriumadmin synced commits to refs/pull/46744/head at scriptoriumadmin/litellm from mirror 2026-10-21 05:17:38 +00:00
ca876562ca feat: add Engy as OpenAI-compatible provider
8d6b8dab3d fix(cli): send pi's session id from lite pi so sessions group and stick (#47700)
8fe0a7358e ci(integration): keep the MCP SDK1 peer on mcp 1.x and autovacuum off the size cleanup test (#47651)
0e24bbb8a2 fix(responses): bill every round of a streamed MCP auto-execute on one spend row (#47445)
647ebd63e0 test(perf): emit per-location seconds, offending locations and the ten longest holds as event_loop_stalls breakdowns (#47757)
Compare 177 commits »
scriptoriumadmin synced commits to refs/pull/46744/merge at scriptoriumadmin/litellm from mirror 2026-10-21 05:17:38 +00:00
716064377d Merge ca876562ca into 8d6b8dab3d
ca876562ca feat: add Engy as OpenAI-compatible provider
8d6b8dab3d fix(cli): send pi's session id from lite pi so sessions group and stick (#47700)
8fe0a7358e ci(integration): keep the MCP SDK1 peer on mcp 1.x and autovacuum off the size cleanup test (#47651)
0e24bbb8a2 fix(responses): bill every round of a streamed MCP auto-execute on one spend row (#47445)
Compare 178 commits »
scriptoriumadmin synced commits to refs/pull/46756/merge at scriptoriumadmin/litellm from mirror 2026-10-21 05:17:38 +00:00
a92661614b Merge a376411676 into 8d6b8dab3d
8d6b8dab3d fix(cli): send pi's session id from lite pi so sessions group and stick (#47700)
8fe0a7358e ci(integration): keep the MCP SDK1 peer on mcp 1.x and autovacuum off the size cleanup test (#47651)
0e24bbb8a2 fix(responses): bill every round of a streamed MCP auto-execute on one spend row (#47445)
647ebd63e0 test(perf): emit per-location seconds, offending locations and the ten longest holds as event_loop_stalls breakdowns (#47757)
Compare 227 commits »
scriptoriumadmin synced commits to refs/pull/46757/merge at scriptoriumadmin/litellm from mirror 2026-10-21 05:17:38 +00:00
f94212bdbb Merge a7d2fccf66 into 17db64ef78
17db64ef78 test(perf): record the row count and size of each table the Admin UI journeys query (#47683)
735ebc466c chore(deps-dev): bump vite from 8.3.0 to 8.3.4 in /vscode-extension (#47627)
6083cf9776 fix(mcp): list per-user auth MCP tools without a shared token (#47677)
49b5444ef9 fix(mcp): list per-user auth MCP tools without a shared token (#47677)
Compare 171 commits »
scriptoriumadmin synced commits to refs/pull/46766/merge at scriptoriumadmin/litellm from mirror 2026-10-21 05:17:38 +00:00
e2368b022d Merge 9a108263c9 into 11b5d1a817
11b5d1a817 feat(gemini): set the long decode budget for requests with no output limit from LITELLM_GEMINI_DEFAULT_MAX_OUTPUT_TOKENS (#47542)
c8ed5ccca8 fix(router): unregister strategy selectors from global callbacks on discard (#45795)
8d9b9926d1 test(perf): add chat_completions_2rps, responses_2rps and messages_2rps direct vs bridge cases (#47752)
f768fb32ef fix(streaming)!: send the include_usage chunk with an empty choices array (#47109)
Compare 202 commits »
scriptoriumadmin synced commits to refs/pull/46769/head at scriptoriumadmin/litellm from mirror 2026-10-21 05:17:38 +00:00
cf871205f8 Update litellm/litellm_core_utils/litellm_logging.py
3af818f00f feat(otel): add nOps preset for OpenTelemetry v2
dd20bb0ae9 fix(bedrock): apply the 16 maxTokens floor to Kimi K3 on Converse (#43875)
d776277647 fix(responses): count billed background responses toward the creator's project and per-model budgets (#47504)
06e3e32c88 fix(vertex_ai): reuse known context caches instead of listing on every request (#46857)
Compare 116 commits »
scriptoriumadmin synced commits to refs/pull/46769/merge at scriptoriumadmin/litellm from mirror 2026-10-21 05:17:38 +00:00
975e137595 Merge cf871205f8 into 8d9b9926d1
8d9b9926d1 test(perf): add chat_completions_2rps, responses_2rps and messages_2rps direct vs bridge cases (#47752)
f768fb32ef fix(streaming)!: send the include_usage chunk with an empty choices array (#47109)
5e189c7267 test(perf): allowlist anyio TaskHandle._run_coro in event_loop_stalls (#47746)
cc156a73b8 fix(fine_tuning): stop forwarding api_version to the OpenAI client (#44995)
Compare 160 commits »
scriptoriumadmin synced commits to refs/pull/46771/merge at scriptoriumadmin/litellm from mirror 2026-10-21 05:17:38 +00:00
55eef38335 Merge 84daa2b9a2 into 4b1928387f
4b1928387f test(bedrock): detect Vault reads on the event-loop thread (#47597)
208cac49f0 fix(vertex_ai)!: send integer enums to Gemini instead of dropping them (#44908)
ad8ca533ca feat(proxy): write one spend row per billed timed-out retry attempt (#47416)
2484f5dd6d test(integration): call the renamed metadata deployment helper in the Mantle count_tokens wire tests (#47592)
Compare 61 commits »
scriptoriumadmin synced commits to refs/pull/46775/merge at scriptoriumadmin/litellm from mirror 2026-10-21 05:17:38 +00:00
37fcbb7574 Merge e8d21eb72e into 2c6b280755
2c6b280755 chore: lead the PR template with a short plain description and collapse the rest (#47594)
5ab0130abc test(integration): call _fallback_deployment in the count_tokens wire tests #47363 added (#47593)
9bbf70edb6 fix(completion): send prompt_cache_retention to OpenAI instead of silently dropping it (#47480)
8d2bf426f5 fix(cost): price base_model deployments past rule-only cost map entries (#47497)
Compare 50 commits »
scriptoriumadmin synced commits to refs/pull/46779/head at scriptoriumadmin/litellm from mirror 2026-10-21 05:17:38 +00:00
7f0e9e9584 refactor: call execute_responses from the Messages to Responses bridge
e649ebcac4 refactor: extract execute_messages and execute_responses native executors
cd10e367ff refactor: decide the native API format once with plan_route
6e385f2f9f chore: remove description heading from PR template (#47631)
dc9c31ee93 chore(cost-map): add fireworks glm 5.3 flash us deprecation date from the changelog (#47591)
Compare 111 commits »