scriptoriumadmin
  • Joined on 2026-03-01
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/48916/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:18 +00:00
fcfe57e7a7 fix(token_counter): let a process that exits during a background tokenizer retry exit cleanly instead of aborting
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/48880/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:17 +00:00
feda51453a fix!: retain unattributed daily activity across reports and exports (#48925)
4bc157e281 feat(proxy): replace the pre-migration row check with a rolled-back dry run of the pending migrations (#48961)
c45b264024 fix(proxy): persist tag spend and drain success callbacks within the shutdown budget (#48988)
c98641fd5a feat(dashscope)!: derive protocol bases from one domain (#47812)
Compare 114 commits »
scriptoriumadmin synced commits to refs/pull/48895/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:17 +00:00
d11ec38acb Merge branch 'main' into fix/prisma-engine-reap
2de99c276a fix(proxy): satisfy lint gates for prisma engine reap
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 127 commits »
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/48899/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:17 +00:00
e3fbb6583d fix(mcp): send the MCP stream usage chunk under the billed row id and count the partial off the loop
f23da840b5 fix(mcp): bill round 2's partial when a routed stream's client hangs up between reads
c0a2b3ff63 fix(mcp): count the follow-up's own messages in round 2's partial prompt
69d30186bf fix(mcp): bill round 2's partial answer when a client hangs up on a routed stream
7da4c7fcdb fix(mcp): count the fixed margin once in the combined stream row's usage cost
Compare 27 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/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
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/48886/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:17 +00:00
643cdfc4f0 fix(spend): read a failure filter's sessions once on the session page
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 112 commits »
scriptoriumadmin synced commits to refs/pull/48882/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:17 +00:00
98cbd9af71 fix(logging): preserve retry diagnostics without exceptions
c3ed358cec fix(logging): preserve deferred config warnings after failed loads
60601ca995 feat(pass-through): add eu/jev decision API pass-through with spend tracking (#46875)
bbc68e21f9 feat(dashscope): add image edits and text-to-speech (#48998)
a6fda5a17e bump: litellm-enterprise 0.1.80 -> 0.1.81, litellm-proxy-extras 0.4.111 -> 0.4.112 (#49149)
Compare 177 commits »
scriptoriumadmin synced commits to refs/pull/48895/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:17 +00:00
d11ec38acb Merge branch 'main' into fix/prisma-engine-reap
2de99c276a fix(proxy): satisfy lint gates for prisma engine reap
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)
Compare 128 commits »
scriptoriumadmin synced commits to refs/pull/48892/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:17 +00:00
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 28 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/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/48867/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:16 +00:00
3f5e42d032 fix(proxy): enforce team and key Allowed Vector Stores when no vector store registry is loaded (#48915)
c666df3dac docs(qa): allow focused proof for mechanical PRs (#49031)
bad98c4b02 fix(responses): call the renamed drops_params helper on the compact path (#49030)
b7da9a2755 fix(credentials): keep the stored secret when PATCH echoes its masked read-back (#48950)
Compare 97 commits »