scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/47250/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:28 +00:00
2e427c6247 chore(deps): require anyio>=4.14.0 to rule out the lock-waiter deadlock (#47378)
f07596a5fd fix(helm): stop litellm-helm from injecting placeholder models into every install (#47056)
d7620c77a1 fix(openai): drop unsupported reasoning effort for gpt-6.1-sol (#43935)
40e4ade6a6 feat(proxy): opt-in self-serve budget edits for key owners on /key/update (#44763)
Compare 35 commits »
scriptoriumadmin synced commits to refs/pull/47257/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:28 +00:00
df008323ae fix(proxy): drop a malformed router_settings_override under drop_params
e5e776823f fix(proxy): answer 400 for a non-object router_settings_override and treat null as absent
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/47257/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:28 +00:00
8884f461af feat(proxy): spend log storage probe and the reclaimable-bytes count (#47449)
6edbc4bc5e chore(pricing): add github_copilot deprecation dates for models retired on 2026-10-19 (#47487)
b690225956 fix(proxy): resync configuration after Redis reconnect (#43313)
df008323ae fix(proxy): drop a malformed router_settings_override under drop_params
Compare 93 commits »
scriptoriumadmin synced commits to refs/pull/47259/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:28 +00:00
b2f0f4d54c fix(vertex-ai): drop floor deprecation_date from gemini-4-argon (#47404)
365d7342c0 fix(prometheus): label deployment failures with the deployment's provider instead of None (#47384)
1212260ab1 fix(logging): report the cost-map entry billing used in model_map_information (#47182)
c0d88b46c9 fix(azure): cache the remaining per-request Entra credentials and keep token refresh off the event loop (#47348)
Compare 44 commits »
scriptoriumadmin synced commits to refs/pull/47260/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:28 +00:00
c6c303a618 fix(batches): apply the Vertex regional endpoint uplift to batch cost (#47466)
783cf06f31 fix(sdk): decide MCP gateway routing without importing the proxy handler (#45961)
6c4c134f23 fix(secret_managers)!: resolve oidc/file and oidc/env refs in admin-configured api_key per request (#47341)
923b7d1784 test(integration): read router cooldown failure rows from the proxy that served them (#47457)
Compare 78 commits »
scriptoriumadmin synced commits to refs/pull/47262/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:28 +00:00
8b9cd12a89 test: catch regressions in the validation lines #44798 added (#47420)
3fa1587f43 fix(logging): do not stamp a provider handoff when pre_call runs for a proxy-only failure (#47456)
f98168e73d test(e2e/perf): read the memory baseline after a one minute warm-up (#47455)
b2eda10bef perf(router): resolve deployment usage limits once per deployment instead of every request (#47393)
Compare 70 commits »
scriptoriumadmin synced commits to refs/pull/47194/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:27 +00:00
2d181e6633 fix(token_counter): count DeepSeek V4 text with DeepSeek's own tokenizer (#47353)
d56ff281de fix(router): key prompt caching affinity on tools and the /v1/messages system prompt (#46411)
fb555b00dc fix(proxy): price a billed failure row at the deployment's own rate like the success path (#47437)
2196943195 fix(proxy): match partial wildcards against prefix-stripped model ids (#46390)
Compare 86 commits »
scriptoriumadmin synced commits to refs/pull/47197/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:27 +00:00
0811b75845 Merge litellm_customer_proxy into litellm_customer_proxy_redis_round_trips
6dc59535e3 feat(gateway): Anthropic and Bedrock chat completions streaming (#47077)
3bc3ce9536 feat(gateway): Azure OpenAI chat completions through the OpenAI passthrough (#47074)
2fa1d8e52b feat(gateway): s3_v2 observer writing the proxy's logging payload to S3 (#47063)
9688179335 feat(gateway): prometheus observer with the proxy's metric and label names (#47060)
Compare 11 commits »
scriptoriumadmin synced commits to refs/pull/47210/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:27 +00:00
c45d05ca23 fix(otel v2): send only the already-exported end user as user.id outside Langfuse
abc7fe5a67 fix(otel v2): keep the end user off user.id when the metadata allowlist drops it
d7f270ff03 fix(otel v2): send the request user as user.id from every OTel v2 callback
bd31a196a1 test(langfuse_otel): type the shared-root test's parameters
Compare 5 commits »
scriptoriumadmin synced commits to refs/pull/47220/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:27 +00:00
365257678f fix(gateway): stop hooks pinning connection read buffers for a stream's life
0faa5b2bee fix(gateway): find anthropic stream usage by event name (#47206)
693dae2a86 feat(gateway): claude chat completions on vertex ai (#47101)
3a6853ff2a feat(gateway): native chat for openai-compatible providers (#47099)
b6669b4684 feat(gateway): gemini chat completions on google ai studio and vertex ai (#47098)
Compare 17 commits »
scriptoriumadmin synced commits to refs/pull/47221/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:27 +00:00
b2f0f4d54c fix(vertex-ai): drop floor deprecation_date from gemini-4-argon (#47404)
365d7342c0 fix(prometheus): label deployment failures with the deployment's provider instead of None (#47384)
1212260ab1 fix(logging): report the cost-map entry billing used in model_map_information (#47182)
c0d88b46c9 fix(azure): cache the remaining per-request Entra credentials and keep token refresh off the event loop (#47348)
Compare 44 commits »
scriptoriumadmin synced commits to refs/pull/47203/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:27 +00:00
da80552897 test(translation): add sonnet 5.5 converse and gemini direct cross-model mid rows (#47328)
c4d24ec2f1 test(integration): remove BUG skips for 3 tests that pass on main (#47364)
daa133da5c fix(mcp)!: bill both model calls of a chat completions MCP auto-execute on one spend row (#47422)
7b82b2a3c3 feat(bedrock): route token counts from model metadata (#47441)
Compare 96 commits »
scriptoriumadmin synced commits to refs/pull/47204/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:27 +00:00
da80552897 test(translation): add sonnet 5.5 converse and gemini direct cross-model mid rows (#47328)
c4d24ec2f1 test(integration): remove BUG skips for 3 tests that pass on main (#47364)
daa133da5c fix(mcp)!: bill both model calls of a chat completions MCP auto-execute on one spend row (#47422)
7b82b2a3c3 feat(bedrock): route token counts from model metadata (#47441)
Compare 96 commits »
scriptoriumadmin synced commits to refs/pull/47206/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:27 +00:00
917036d09b fix(gateway): find anthropic stream usage by event name
693dae2a86 feat(gateway): claude chat completions on vertex ai (#47101)
3a6853ff2a feat(gateway): native chat for openai-compatible providers (#47099)
b6669b4684 feat(gateway): gemini chat completions on google ai studio and vertex ai (#47098)
3d976a5791 feat(gateway): full openai chat request translation for anthropic and bedrock (#47088)
Compare 16 commits »
scriptoriumadmin synced commits to refs/pull/47207/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:27 +00:00
d4e10685f5 feat(loadtest): s3stub -max-string keeps long runs' logs in memory
0fec539445 feat(loadtest): full-feature mode with recorded-data verification
365257678f fix(gateway): stop hooks pinning connection read buffers for a stream's life
0faa5b2bee fix(gateway): find anthropic stream usage by event name (#47206)
693dae2a86 feat(gateway): claude chat completions on vertex ai (#47101)
Compare 19 commits »
scriptoriumadmin synced commits to refs/pull/47210/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:27 +00:00
c45d05ca23 fix(otel v2): send only the already-exported end user as user.id outside Langfuse
abc7fe5a67 fix(otel v2): keep the end user off user.id when the metadata allowlist drops it
d7f270ff03 fix(otel v2): send the request user as user.id from every OTel v2 callback
bd31a196a1 test(langfuse_otel): type the shared-root test's parameters
Compare 4 commits »
scriptoriumadmin synced commits to refs/pull/47219/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:27 +00:00
da80552897 test(translation): add sonnet 5.5 converse and gemini direct cross-model mid rows (#47328)
c4d24ec2f1 test(integration): remove BUG skips for 3 tests that pass on main (#47364)
daa133da5c fix(mcp)!: bill both model calls of a chat completions MCP auto-execute on one spend row (#47422)
7b82b2a3c3 feat(bedrock): route token counts from model metadata (#47441)
Compare 92 commits »
scriptoriumadmin synced commits to refs/pull/47225/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:27 +00:00
5b8889142d fix(otel v2): stamp the stream the caller got on the trace root
4999477148 fix(otel v2): keep redacted messages off the Arize AX and Phoenix trace root
Compare 3 commits »
scriptoriumadmin synced commits to refs/pull/47227/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:27 +00:00
b2f0f4d54c fix(vertex-ai): drop floor deprecation_date from gemini-4-argon (#47404)
365d7342c0 fix(prometheus): label deployment failures with the deployment's provider instead of None (#47384)
1212260ab1 fix(logging): report the cost-map entry billing used in model_map_information (#47182)
c0d88b46c9 fix(azure): cache the remaining per-request Entra credentials and keep token refresh off the event loop (#47348)
Compare 44 commits »
scriptoriumadmin synced commits to refs/pull/47222/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:27 +00:00
da80552897 test(translation): add sonnet 5.5 converse and gemini direct cross-model mid rows (#47328)
c4d24ec2f1 test(integration): remove BUG skips for 3 tests that pass on main (#47364)
daa133da5c fix(mcp)!: bill both model calls of a chat completions MCP auto-execute on one spend row (#47422)
7b82b2a3c3 feat(bedrock): route token counts from model metadata (#47441)
Compare 95 commits »