scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/48963/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:20 +00:00
863ede9105 Merge remote-tracking branch 'origin/main' into litellm_sso_team_id_upsert
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 92 commits »
scriptoriumadmin synced commits to refs/pull/48953/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:20 +00:00
d2b17a9d26 fix(cost): keep the upstream's usage.cost beside litellm's bill and stamp a zero operator price on the stream frame
84042736c3 refactor(cost): name the providers billed from their own usage fields for what they are
7520be3585 fix(cost): read the stored breakdown total through the logging object's typed field
9a1e0f868d fix(cost): keep the token breakdown when a header reported cost repeats an already priced bill
b324599f0d fix(cost): mark usage.cost litellm wrote as its own bill and keep a breakdown for a reported cost
Compare 57 commits »
scriptoriumadmin synced commits to refs/pull/48951/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:20 +00:00
4613c265fa fix(guardrails): name failed handler packages in the skip warning and drop the wrong remedy
6bab3b9fc1 fix(guardrails): keep rejecting during_call requests whose call type is outside CallTypes
bf52898fec fix(guardrails): retry a handler package caught mid-import, skip unscannable during_call call types, and warn once per call type
Compare 3 commits »
scriptoriumadmin synced commits to refs/pull/48962/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:20 +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 72 commits »
scriptoriumadmin synced commits to refs/pull/48961/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:20 +00:00
c8dd84fa4a ci(codecov): stop carrying forward the roi-postgres and redis-compat flags
18714c523b chore: merge main into litellm_migration_dry_run_cli
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)
bee9f679dc fix(github_copilot): treat a malformed api-key.json like a missing one (#44723)
Compare 58 commits »
scriptoriumadmin synced commits to refs/pull/48958/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:20 +00:00
dfe33af19d refactor(redis): make the helpers the transport imports public
a6202af364 refactor(redis): plain-method transport, store layer and response polling store
d04bf18333 Merge branch 'main' into litellm_redis_transport_base_48956
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)
Compare 148 commits »
scriptoriumadmin synced commits to refs/pull/48958/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:20 +00:00
dbcacc7ab7 fix(health): probe only models a partial wildcard serves (#49060)
dfe33af19d refactor(redis): make the helpers the transport imports public
f32ac94ad1 fix(openai): keep the upstream error body on e.response for OpenAI and Azure errors (#49079)
a6202af364 refactor(redis): plain-method transport, store layer and response polling store
Compare 150 commits »
scriptoriumadmin synced commits to refs/pull/48936/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:19 +00:00
f32ac94ad1 fix(openai): keep the upstream error body on e.response for OpenAI and Azure errors (#49079)
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)
Compare 132 commits »
scriptoriumadmin synced commits to refs/pull/48936/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:19 +00:00
0f160e9042 fix(vector stores): confirm a provider delete when a concurrent delete already removed the managed row
15e6516fe1 fix(managed files): skip chat messages and content items that are not objects
8cc51b31d7 fix(managed files): answer 400 for a chat file part with no file object instead of 500
2065b40fa5 Merge remote-tracking branch 'origin/main' into HEAD
a66dc50efb test(json_fragment_accumulator): assert peak allocation instead of a drain timing ratio (#43370)
Compare 65 commits »
scriptoriumadmin synced commits to refs/pull/48939/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:19 +00:00
2519ef52eb Merge remote-tracking branch 'origin/main' into litellm_restore_mcp_delegate_upstream_auth
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)
d884167bf2 fix(responses): only merge repeated Codex tools when drop_params is on (#49112)
62b8ee78de ci: run the integration groups on GitHub Actions (#48985)
Compare 136 commits »
scriptoriumadmin synced commits to refs/pull/48940/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:19 +00:00
3108082d76 build(deps): bump filelock from 3.32.7 to 4.1.0
636e707089 fix(proxy)!: stop answering with the literal string "None" as error type and param on the proxy-server, auth, spend, and key health routes (#39540)
dacaaad72e build: allow filelock 4.x and sync package metadata (#49137)
d302096b5a feat(lite): offer each model group's reasoning efforts in pi, OpenCode and Codex (#48949)
d76db470f9 test: update integration tests left stale by recent product changes (#49143)
Compare 149 commits »
scriptoriumadmin synced commits to refs/pull/48946/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:19 +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 151 commits »
scriptoriumadmin synced commits to refs/pull/48948/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:19 +00:00
be6d082bdc fix(anthropic)!: send /v1/messages PDF documents to OpenAI-shaped providers as file parts (#47166)
c13ecb3085 fix(exceptions)!: honor status code when mapping OpenAI invalid_request_error exceptions (#32537)
cd58014315 feat(soniox): add realtime speech-to-text on /v1/realtime (#44822)
2a61f12f78 ci(model-catalog): check the cost map by loading it through model-catalog (#48908)
Compare 86 commits »
scriptoriumadmin synced commits to refs/pull/48942/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:19 +00:00
f32ac94ad1 fix(openai): keep the upstream error body on e.response for OpenAI and Azure errors (#49079)
ae4f9e72ac fix(proxy): hold a candidate count only when every deployment generates it, and drop n when every deployment drops it
ccc56d27ad fix(azure): add batch prices to the unversioned o3, o4-mini, o3-mini, gpt-4o and gpt-4o-mini rows (#49182)
8a962649a7 chore: merge main into litellm_vertex_passthrough_single_auth
Compare 118 commits »
scriptoriumadmin synced commits to refs/pull/48949/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:19 +00:00
0db4944d0f fix(lite): keep REASONING_EFFORT_STRENGTH_ORDER importable from router_utils and skip the Codex sync on undecodable debug models output
62e21014b5 fix(codex): treat a client_version too long to parse as an old Codex and keep undescribed stock levels
a0282e0643 Merge remote-tracking branch 'origin/main' into HEAD
d671708b98 Merge branch 'main' into litellm_lite_cli_reasoning_efforts
ead221995e refactor(router): move router callers onto the entry points and invert the proxy imports (#48847)
Compare 109 commits »
scriptoriumadmin synced commits to refs/pull/48946/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:19 +00:00
acb1b9e49c fix(guardrails): keep both scans' masks on an escaped systemone field
874c533084 Merge remote-tracking branch 'origin/main' into litellm_fix_native_guardrails_on_extraction
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 146 commits »
scriptoriumadmin synced commits to refs/pull/48942/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:19 +00:00
ae4f9e72ac fix(proxy): hold a candidate count only when every deployment generates it, and drop n when every deployment drops it
8a962649a7 chore: merge main into litellm_vertex_passthrough_single_auth
23595f7fe5 fix(bedrock): backfill published regional service tier prices (#49113)
85af2f65c9 refactor(helm)!: connect both charts to a separately deployed Lens (#49169)
e312dabac2 fix(proxy): count candidateCount in the budget hold only for models that generate the candidates
Compare 170 commits »
scriptoriumadmin synced commits to refs/pull/48940/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:19 +00:00
23ad8870b4 fix(token_counter): price PDF pages for OpenAI and Azure models the way they bill (#47554)
3108082d76 build(deps): bump filelock from 3.32.7 to 4.1.0
636e707089 fix(proxy)!: stop answering with the literal string "None" as error type and param on the proxy-server, auth, spend, and key health routes (#39540)
dacaaad72e build: allow filelock 4.x and sync package metadata (#49137)
Compare 151 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/48933/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:18 +00:00
62849d1f0a Merge remote-tracking branch 'origin/main' into litellm_warn_remaining_reasoning_drops
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 146 commits »