scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/47694/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:20 +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 129 commits »
scriptoriumadmin synced commits to refs/pull/47703/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:20 +00:00
18b7773c9e Merge remote-tracking branch 'origin/main' into litellm_hosted_vllm_google_oidc_api_key
d037d86a94 fix(token_counter)!: keep a loaded Hugging Face tokenizer when a slower download fails (#48916)
c87a25a357 feat(proxy)!: general_settings.claude_code_marketplace_auth_required puts the Claude Code marketplace behind a LiteLLM key (#48980)
e8f0735d8a feat(proxy): let a Claude Code gateway user choose the session team (#49001)
c489aa7117 feat(proxy)!: add suppress_startup_output to turn off startup prints (#47708)
Compare 86 commits »
scriptoriumadmin synced commits to refs/pull/47692/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:20 +00:00
e93e01ca4b fix(ci): build base native extension for OpenAPI lint (#49136)
fd8b89fbec fix(mcp)!: restore upstream-token admission for legacy delegate servers (#48939)
d8f162ea22 fix(guardrails): allow MCP call modes on the generic guardrail API (#48060)
1a2b443a32 ci: run the extensions integration group with 48 workers (#49134)
Compare 87 commits »
scriptoriumadmin synced commits to refs/pull/47596/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:20 +00:00
19731511e8 Merge remote-tracking branch 'origin/main' into litellm_spend_log_guardrail_index_retention
fd8b89fbec fix(mcp)!: restore upstream-token admission for legacy delegate servers (#48939)
d8f162ea22 fix(guardrails): allow MCP call modes on the generic guardrail API (#48060)
1a2b443a32 ci: run the extensions integration group with 48 workers (#49134)
8d441ebc15 test(otel): give the Langfuse destination tests the otel callback's stdout exporter (#49129)
Compare 555 commits »
scriptoriumadmin synced commits to refs/pull/47532/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:19 +00:00
dff474e450 fix(responses): replay the original Responses item order, phase, and boundaries on the next chat turn (#48912)
3f01341f0a fix(health)!: openai realtime health check reports healthy with a missing or invalid api key (#41233)
904c092ffe feat(providers): add BigModel support and model pricing (#48563)
9a68573e9b fix(responses): keep each Codex tool once when its tool list repeats across turns (#49006)
Compare 127 commits »
scriptoriumadmin synced commits to refs/pull/47485/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:19 +00:00
ccc56d27ad fix(azure): add batch prices to the unversioned o3, o4-mini, o3-mini, gpt-4o and gpt-4o-mini rows (#49182)
b91fc92b6d fix(router): cap the default OTPM reservation and reconcile token counters after each call (#49054)
342ce6ae4a feat(zai): support response_format and max_completion_tokens, add glm-5v-turbo pricing (#48335)
733cfeba93 fix(cost): bill a provider reported usage.cost on every path unless the deployment is priced (#48953)
Compare 128 commits »
scriptoriumadmin synced commits to refs/pull/47507/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:19 +00:00
3f01341f0a fix(health)!: openai realtime health check reports healthy with a missing or invalid api key (#41233)
904c092ffe feat(providers): add BigModel support and model pricing (#48563)
9a68573e9b fix(responses): keep each Codex tool once when its tool list repeats across turns (#49006)
3c1eb73a06 fix(proxy)!: list every priced Vertex family under a vertex_ai/* grant (#41959)
Compare 165 commits »
scriptoriumadmin synced commits to refs/pull/47578/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:19 +00:00
e63fc85b7b fix(anthropic): keep Mistral thinking text on streaming /v1/messages (#49059)
c213234783 feat(vertex_ai)!: use HTTP/2 httpx client for search_api vector store (#40631)
ead221995e refactor(router): move router callers onto the entry points and invert the proxy imports (#48847)
57f6e1b39f fix(proxy): keep the litellm command light so spawned workers answer uvicorn's first health ping (#45039)
Compare 287 commits »
scriptoriumadmin synced commits to refs/pull/47543/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:19 +00:00
d884167bf2 fix(responses): only merge repeated Codex tools when drop_params is on (#49112)
62b8ee78de ci: run the integration groups on GitHub Actions (#48985)
ffcc4f7a70 fix(otel)!: print OTel v2 spans to stdout only when the operator asks (#48723)
a54204b583 feat(guardrails): scan sampled stream windows in the background (#48952)
Compare 140 commits »
scriptoriumadmin synced commits to refs/pull/47556/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:19 +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 274 commits »
scriptoriumadmin synced commits to refs/pull/47587/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:19 +00:00
b91fc92b6d fix(router): cap the default OTPM reservation and reconcile token counters after each call (#49054)
342ce6ae4a feat(zai): support response_format and max_completion_tokens, add glm-5v-turbo pricing (#48335)
733cfeba93 fix(cost): bill a provider reported usage.cost on every path unless the deployment is priced (#48953)
369f3cb5f0 feat(cost-map): add baseten joey-1 decision model (#49123)
Compare 305 commits »
scriptoriumadmin synced commits to refs/pull/47589/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:19 +00:00
27fd9ae0a6 fix(presidio): release session lock before analyzer and anonymizer calls (#47579)
c98641fd5a feat(dashscope)!: derive protocol bases from one domain (#47812)
06cdee91da fix(guardrails): scan and rewrite streamed /v1/completions under post_call guardrails (#49035)
961fabbb76 feat(secret_managers): resolve oidc/google api_key references per request (#47703)
6cdb9959df feat(router): opt in to non-chat deployment filtering (#46257)
Compare 489 commits »
scriptoriumadmin synced commits to refs/pull/47553/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:19 +00:00
4ce724e3df fix(caching): key cached async clients by a per-loop token instead of id(loop) (#48877)
d884167bf2 fix(responses): only merge repeated Codex tools when drop_params is on (#49112)
62b8ee78de ci: run the integration groups on GitHub Actions (#48985)
ffcc4f7a70 fix(otel)!: print OTel v2 spans to stdout only when the operator asks (#48723)
Compare 183 commits »
scriptoriumadmin synced commits to refs/pull/47496/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:19 +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 256 commits »
scriptoriumadmin synced commits to refs/pull/47485/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:19 +00:00
038a1bda1e Merge remote-tracking branch 'origin/main' into feat-content-filter-checksum-validators
b1f43cfe62 perf(content_filter): skip redaction tracking when no checksum can put a number back
06cdee91da fix(guardrails): scan and rewrite streamed /v1/completions under post_call guardrails (#49035)
961fabbb76 feat(secret_managers): resolve oidc/google api_key references per request (#47703)
6cdb9959df feat(router): opt in to non-chat deployment filtering (#46257)
Compare 180 commits »
scriptoriumadmin synced commits to refs/pull/47554/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:19 +00:00
89c34f9d34 fix(proxy): count routing-group and alias members with the caller's team, as routing serves them
1cc994bfd4 Merge remote-tracking branch 'origin/main' into litellm_openai_pdf_page_pricing
e63fc85b7b fix(anthropic): keep Mistral thinking text on streaming /v1/messages (#49059)
20dcfde079 fix(proxy): count a team's wildcard route the way routing serves it and reserve OpenAI chat's per-PDF charge
c213234783 feat(vertex_ai)!: use HTTP/2 httpx client for search_api vector store (#40631)
Compare 121 commits »
scriptoriumadmin synced commits to refs/pull/47484/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:19 +00:00
15f8086684 test(least-busy): give callback fixtures a fixed call-start time
19e538ab11 fix(cost-map): set together_ai Qwen3.7-Max back to the published price (#49125)
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)
Compare 110 commits »
scriptoriumadmin synced commits to refs/pull/47448/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:18 +00:00
c1157c3211 refactor(proxy): drop leftover group_by=tag branch and the tag page SQL-text test
29cdadc799 fix(proxy): honor exclude_team_ids on the team tags page
51b3032fb8 fix(proxy): allowlist team tag activity endpoint
e5efc050b9 refactor(proxy): paginated team tags report replaces group_by=tag
e99209d352 style(proxy): ruff format daily_activity_sql
Compare 400 commits »
scriptoriumadmin synced commits to refs/pull/47386/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:18 +00:00
dff474e450 fix(responses): replay the original Responses item order, phase, and boundaries on the next chat turn (#48912)
3f01341f0a fix(health)!: openai realtime health check reports healthy with a missing or invalid api key (#41233)
904c092ffe feat(providers): add BigModel support and model pricing (#48563)
9a68573e9b fix(responses): keep each Codex tool once when its tool list repeats across turns (#49006)
Compare 113 commits »
scriptoriumadmin synced commits to refs/pull/47398/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:18 +00:00
2e5cc9e08f fix(proxy)!: honor litellm_settings.drop_params for Claude Code and Codex requests (#49058)
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)
c213234783 feat(vertex_ai)!: use HTTP/2 httpx client for search_api vector store (#40631)
Compare 79 commits »