scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/47982/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:24 +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 213 commits »
scriptoriumadmin synced commits to refs/pull/48021/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:24 +00:00
eafa64591e fix(ci): retain upstream Python lockfile
31732518a7 fix(ci): preserve current security scan configuration
6465d79ba3 merge: sync main and preserve stream regression
0cb7651312 merge: sync main (take upstream filelock range from #49137)
ccc56d27ad fix(azure): add batch prices to the unversioned o3, o4-mini, o3-mini, gpt-4o and gpt-4o-mini rows (#49182)
Compare 331 commits »
scriptoriumadmin synced commits to refs/pull/48021/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:24 +00:00
eafa64591e fix(ci): retain upstream Python lockfile
31732518a7 fix(ci): preserve current security scan configuration
6465d79ba3 merge: sync main and preserve stream regression
0cb7651312 merge: sync main (take upstream filelock range from #49137)
Compare 267 commits »
scriptoriumadmin synced commits to refs/pull/48024/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:24 +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/47909/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:23 +00:00
3cd585ee29 Merge remote-tracking branch 'upstream/main' into fix/otel-v2-langfuse-trace-controls-47898
71babd931b fix(llms): move later developer messages for models declared system-first (#48897)
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)
Compare 416 commits »
scriptoriumadmin synced commits to refs/pull/47891/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:23 +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 144 commits »
scriptoriumadmin synced commits to refs/pull/47883/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:23 +00:00
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 81 commits »
scriptoriumadmin synced commits to refs/pull/47880/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:23 +00:00
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)
4ce724e3df fix(caching): key cached async clients by a per-loop token instead of id(loop) (#48877)
Compare 302 commits »
scriptoriumadmin synced commits to refs/pull/47869/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:23 +00:00
7aa0393cb6 feat(providers): add CLF AI Gateway as an OpenAI-compatible provider with ten models (#39324)
fd594ab0cf fix: enforce LiteAdmin MCP route permissions (#48080)
e0778bc9dd refactor(types): replace Any with proven types in 21 files (#48921)
19e538ab11 fix(cost-map): set together_ai Qwen3.7-Max back to the published price (#49125)
Compare 328 commits »
scriptoriumadmin synced commits to refs/pull/47942/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:23 +00:00
9252709cab feat(ui): add i18next plumbing and move the Workflows page onto it (#49144)
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)
Compare 85 commits »
scriptoriumadmin synced commits to refs/pull/47925/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:23 +00:00
5eb1042bbf fix(token_counter): count OpenAI models newer than tiktoken's table with o200k_base (#48728)
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)
3f5e42d032 fix(proxy): enforce team and key Allowed Vector Stores when no vector store registry is loaded (#48915)
Compare 157 commits »
scriptoriumadmin synced commits to refs/pull/47900/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:23 +00:00
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 306 commits »
scriptoriumadmin synced commits to refs/pull/47916/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:23 +00:00
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)
594f862bf3 fix(streaming): rebuild each choice of an n>1 chat stream on its own (#49002)
Compare 288 commits »
scriptoriumadmin synced commits to refs/pull/47916/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:23 +00:00
8f310e37dc refactor(logging): replace nested blind except in model cost lookup with a helper
scriptoriumadmin synced commits to refs/pull/47909/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:23 +00:00
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)
594f862bf3 fix(streaming): rebuild each choice of an n>1 chat stream on its own (#49002)
Compare 326 commits »
scriptoriumadmin synced commits to refs/pull/47846/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:22 +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 336 commits »
scriptoriumadmin synced commits to refs/pull/47850/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:22 +00:00
83d6779158 fix(guardrails)!: make lakera_v2 on_flagged block reject PII-only detections, add mask (#48944)
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)
Compare 152 commits »
scriptoriumadmin synced commits to refs/pull/47845/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:22 +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 337 commits »
scriptoriumadmin synced commits to refs/pull/47861/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:22 +00:00
3728024e49 fix(context_management): keep a malformed system prompt from failing clear_tool_uses on the Responses API
9e23ea41d9 fix(count_tokens): pass the system prompt into clearing so count_tokens matches inference
d8648dccd3 Merge remote-tracking branch 'origin/main' into HEAD
71babd931b fix(llms): move later developer messages for models declared system-first (#48897)
d037d86a94 fix(token_counter)!: keep a loaded Hugging Face tokenizer when a slower download fails (#48916)
Compare 153 commits »
scriptoriumadmin synced commits to refs/pull/47816/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:22 +00:00
d037d86a94 fix(token_counter)!: keep a loaded Hugging Face tokenizer when a slower download fails (#48916)
b5c0bd166f Merge remote-tracking branch 'origin/main' into litellm_deflake_20261021
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)
Compare 90 commits »