scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/48932/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:18 +00:00
3c24e51e04 test(perf): require only the always-built request-log indexes in the nightly database upgrade test
4471416c1a test(spend): type the error code index parameter in the Logs filter tests
b0bf5a0049 fix(spend): keep main's Error Code query until the prefix index is valid, and print operator statements one per line
2616c71da8 fix(spend-logs): cap the error index build by table size and log non-blocking partitioned steps
Compare 4 commits »
scriptoriumadmin synced commits to refs/pull/48931/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:18 +00:00
9252709cab feat(ui): add i18next plumbing and move the Workflows page onto it (#49144)
95f7af2eb4 fix(messages): honor additional_drop_params for mcp_servers and read the beta map only for hosted MCP tools
68b5a737a1 fix(anthropic): retry /v1/messages without strict when Claude rejects strict tools under drop_params (#49102)
08b539e6a8 fix(proxy)!: bill streamed /v1/completions without stream_options like chat (#45366)
Compare 110 commits »
scriptoriumadmin synced commits to refs/pull/48917/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:18 +00:00
35500573ec fix(caching): keep main's model group lookup for calls outside the router
scriptoriumadmin synced commits to refs/pull/48922/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:18 +00:00
64ef80f244 chore(ui): regenerate dashboard API types
c408cd6350 Merge remote-tracking branch 'origin/main' into litellm_autorouter_tool_turns_classifier
4d9c6aa09b fix(complexity_router): keep the opening tool reads when a failed read comes first
c068d1350b fix(responses): stream every citation batch before completion (#48747)
ff22f3de06 build(deps): bump langgraph and tornado and add dated scan ignores to clear osv-scan and image-scan (#48302)
Compare 72 commits »
scriptoriumadmin synced commits to refs/pull/48922/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:18 +00:00
b93d26bc85 fix(responses): drop a malformed prompt_cache_breakpoint under drop_params on the direct /v1/responses path (#45330)
310c96162b fix(anthropic): drop the non-spec custom object from /v1/messages tool definitions (#48893)
42d2909210 test(integration): scope the signoz, otel conversation id, and series cap proxy fixtures to their module (#48965)
032342d2b7 fix(responses): resume background response streams with stream and starting_after (#48819)
Compare 28 commits »
scriptoriumadmin synced commits to refs/pull/48933/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:18 +00:00
a0a8ca97d9 fix(cost): finalize synchronous response cost once for header, spend log and rollups (#48993)
a1bd5feebe feat(router): infer custom classifier tiers from model mappings (#48987)
5dcc3a1bbf docs: link README to Python SDK and autorouter guides (#48986)
2e5cc9e08f fix(proxy)!: honor litellm_settings.drop_params for Claude Code and Codex requests (#49058)
Compare 102 commits »
scriptoriumadmin synced commits to refs/pull/48932/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:18 +00:00
85af2f65c9 refactor(helm)!: connect both charts to a separately deployed Lens (#49169)
44cd858697 fix(cost): bill the requested model's rates when the response names an unpriced model (#48900)
a7030a5a2c fix(vertex_ai): batch Claude models in Anthropic's native row shape (#45715)
7aa0393cb6 feat(providers): add CLF AI Gateway as an OpenAI-compatible provider with ten models (#39324)
Compare 126 commits »
scriptoriumadmin synced commits to refs/pull/48929/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:18 +00:00
f9dd972b9e Merge remote-tracking branch 'origin/main' into litellm_hosted_vllm_keep_strict_tool_schema
ebf84f8649 fix(caching): read the cache key's model group from the router's metadata for the call (#48917)
41602e318d fix(proxy): stream a guardrail block on /v1/messages as Anthropic events (#49010)
444423a5ca fix(cost): bill a deployment's per-second rates on native Anthropic /v1/messages (#42417)
cd42694b48 feat(providers): add Kyma API as an OpenAI-compatible provider (#48756)
Compare 96 commits »
scriptoriumadmin synced commits to refs/pull/48921/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:18 +00:00
17822fd186 Merge remote-tracking branch 'origin/main' into HEAD
68b5a737a1 fix(anthropic): retry /v1/messages without strict when Claude rejects strict tools under drop_params (#49102)
08b539e6a8 fix(proxy)!: bill streamed /v1/completions without stream_options like chat (#45366)
e93e01ca4b fix(ci): build base native extension for OpenAPI lint (#49136)
fd8b89fbec fix(mcp)!: restore upstream-token admission for legacy delegate servers (#48939)
Compare 115 commits »
scriptoriumadmin synced commits to refs/pull/48912/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:18 +00:00
5da507af70 test(responses): read the expected chat message without JSON validation so the replay matcher stays
a4983736bf fix(streaming): keep the served service tier on the finish chunk the stream adds
69477467e0 test(responses): expect the replay record in bridged chat translation cases
1136a6333e test(responses): expect the replay record on bridged chat replies
48c266b3cf test(responses): add black box tests for chat turn history replay
Compare 5 commits »
scriptoriumadmin synced commits to refs/pull/48900/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:18 +00:00
29e2390a56 fix(cost): bill the requested model's listed rates over a served size-bucket guess
f996f84787 fix(cost): keep the served model's filled-in and size-bucket rates, and cache misses
cac4192449 Merge remote-tracking branch 'origin/main' into litellm_fireworks_display_name_cost
05db116dfa perf(cost): read the response model's price row without building full model info
032342d2b7 fix(responses): resume background response streams with stream and starting_after (#48819)
Compare 140 commits »
scriptoriumadmin synced commits to refs/pull/48928/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:18 +00:00
985fe342cc fix(types): keep policy suggestion and auto router parsing on main's code
8682c5d4dd fix(types): keep text completion, batch ids and guardrail callback on main's code
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/48931/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:18 +00:00
95f7af2eb4 fix(messages): honor additional_drop_params for mcp_servers and read the beta map only for hosted MCP tools
5bb6fff01e fix(ollama): leave JSON mode off when drop_params drops every hosted MCP tool
aa4e8c552e Merge remote-tracking branch 'origin/main' into litellm_fix_hosted_mcp_tool_silent_drop
4a4c9cf7e3 feat(guardrails): opt-in response_masked_data on PANW Prisma AIRS block (#46219)
e63fc85b7b fix(anthropic): keep Mistral thinking text on streaming /v1/messages (#49059)
Compare 93 commits »
scriptoriumadmin synced commits to refs/pull/48929/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:18 +00:00
85af2f65c9 refactor(helm)!: connect both charts to a separately deployed Lens (#49169)
44cd858697 fix(cost): bill the requested model's rates when the response names an unpriced model (#48900)
a7030a5a2c fix(vertex_ai): batch Claude models in Anthropic's native row shape (#45715)
7aa0393cb6 feat(providers): add CLF AI Gateway as an OpenAI-compatible provider with ten models (#39324)
Compare 110 commits »
scriptoriumadmin synced commits to refs/pull/48886/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:17 +00:00
4c36fc1e52 refactor(spend): split the session page's growing read into named steps
643cdfc4f0 fix(spend): read a failure filter's sessions once on the session page
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/48888/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:17 +00:00
eeee71c889 fix(datadog): keep client request tags from setting the silent experiment cost tag
192eed8b4a test: type the new parametrized tests and keep the recorder from changing its argument
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/48882/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:17 +00:00
98cbd9af71 fix(logging): preserve retry diagnostics without exceptions
53ce41625f chore(databricks): retirement dates for DeepSeek V4 Flash (0731), V4 Pro (0813) and Inkling (#49124)
d25cde4792 chore(cost-map): add fireworks ultramarine 1 flash us and date deepseek v4 flash (#49146)
326f17594e fix(batches): return real batch token counts next to OpenAI's batch usage fields (#47740)
Compare 167 commits »
scriptoriumadmin synced commits to refs/pull/48892/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:17 +00:00
543c9917aa fix(proxy): apply the semantic cache veto to grouped and nested fallback targets and forward only skip controls through generateContent
scriptoriumadmin synced commits to refs/pull/48899/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:17 +00:00
44cd858697 fix(cost): bill the requested model's rates when the response names an unpriced model (#48900)
a7030a5a2c fix(vertex_ai): batch Claude models in Anthropic's native row shape (#45715)
7aa0393cb6 feat(providers): add CLF AI Gateway as an OpenAI-compatible provider with ten models (#39324)
fd594ab0cf fix: enforce LiteAdmin MCP route permissions (#48080)
Compare 111 commits »
scriptoriumadmin synced commits to refs/pull/48897/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:17 +00:00
d9e0adf715 fix: count non-string roles as turns, keep the Fireworks fold for twins, and copy closing developer content