BerriAI/litellm - CodSpeed

litellm

Blog Docs Changelog

Performance History

Latest Results

fix(guardrails): add missing return type to Reco's initialize_guardrail Greptile flagged this initializer as untyped in review; add the return annotation to satisfy the repo's full-typing convention.

RecoLabs:add-reco-guardrail-provider

22 seconds ago

refactor(rust): align the cache crates with Python and activate every backend The cache port had drifted: lifecycle and Redis-only operations sat on `BaseCache`, counters were pinned to `f64`, each semantic backend defined its own embedder and prompt handling, and only the in-memory backend could be selected natively. - Split `disconnect` and `test_connection` out of `BaseCache` into optional capabilities, implemented only where the Python class defines them, and give every Redis-only operation its own capability trait. - Decouple counters from the stored value type, so one backend can serve both responses and counters as Python's `RedisCache` does. - Share one `Embedder` and prompt contract in `litellm_cache::semantic`, and make the Redis and Valkey semantic backends generic over their codec. - Port the Python operations that were missing: `async_refresh_ttl`, `async_rpush_and_trim`, `async_set_cache_pipeline_with_ttls`, the DualCache pipeline, sadd, bulk delete and TTL reads, and the semantic-similarity write-back. - Take the HTTP client from the host pool in the GCS, S3 and Azure backends. - Activate all nine backends through the Rust catalog, whose rules all stay `PYTHON_ONLY`, and route the `Cache` facade's storage calls to the native runtime when one is selected. - Give every crate the same layout, move all tests to `tests/` on rstest, and add the shared `litellm-cache-testing` contract suite. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

rust-cache-alignment

23 seconds ago

test(observability): build the callback config without in-place mutation Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

litellm_responses-callback-cost-zero

2 minutes ago

test(e2e): trim blank S3 env gateway config Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

litellm_bedrock_blank_s3_env

2 minutes ago

feat(proxy): admin-only /debug/report sharing the bug report environment (#42440) * feat(proxy): add admin-only /debug/report sharing the bug report environment fields Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * feat(proxy): add verbose=true to /debug/report listing every config key with typed values Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(proxy): inject auth into /debug/report through Annotated to keep the B008 budget flat Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(proxy): bound the verbose config walk, drop nested-list recursion from the safe renderer, regenerate schema.d.ts Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(proxy): count pass-through and mcp header maps plus operator-named budget maps in verbose /debug/report, single-exit scalar renderers Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * chore(ui): regenerate schema.d.ts after dropping the verbose query from /debug/report Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: ryan <ryan@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

main

2 minutes ago

style(tests): wrap the anthropic bare string wire test to the 120 column limit Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

litellm_anthropic-is-pdf-used-string

4 minutes ago

fix(otel): stop reading the replayed payload's session id, the generated marker does not survive replay Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

litellm_otel_v2_gen_ai_conversation_id

4 minutes ago

chore(prices): sync Baseten prices: 10 models, 8 new [4 with gaps, enrichment failed: Baseten, 21 held] baseten/deepseek-ai/DeepSeek-V4.1-Flash: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost, supports_tool_choice baseten/moonshotai/Kimi-K2.6: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost baseten/moonshotai/Kimi-K2.7-Code: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost, supports_tool_choice baseten/moonshotai/Kimi-K3: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost, supports_tool_choice baseten/openai/gpt-oss-120b: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_prompt_caching, supports_response_schema, supports_function_calling, cache_read_input_token_cost baseten/thinkingmachines/inkling: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost baseten/thinkingmachines/inkling-small: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost baseten/zai-org/GLM-4.7: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_prompt_caching, supports_response_schema, supports_function_calling, cache_read_input_token_cost baseten/zai-org/GLM-5.2: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost, supports_tool_choice

litellm-providers/price-sync-baseten

5 minutes ago

Latest Branches

0%

refactor(rust): align the cache crates with Python and activate every backend#42530

1 hour ago

3ed3f9b

rust-cache-alignment

0%

fix(logging): price a None hidden response_cost instead of logging it as 0#42427

8 minutes ago

a869127

litellm_responses-callback-cost-zero

0%

fix(bedrock): treat blank AWS_S3_* env vars as unset for batch jobs#42528

17 minutes ago

894ac4f

litellm_bedrock_blank_s3_env

© 2026 CodSpeed Technology

Home Terms Privacy Docs