litellm
1343 issues found
[Feature]: Preserve Anthropic cache_creation TTL breakdown in Chat Completions usage
6/9/2026
stale key spend counter remains after budget reset or manual reset
6/9/2026
EmbeddingResponse(**response_json) fails with `must be a mapping, not list` when using openai_like/lm_studio provider with llama.cpp server
6/9/2026
Custom redaction tags (keyword_redaction_tag, pattern_redaction_format) not working in v1.87.1
6/9/2026
Preserve original PR authorship when squashing staging branches into main
6/9/2026
[Bug]: Anthropic `/v1/messages` streaming adapter drops the first non-empty text delta when proxying to `/v1/chat/completions`
6/9/2026
[Bug]: OpenAI responses API not using configured `base_url`
6/9/2026
[Feature]: Auto-tag generic pass-through requests by upstream URL for observability (Langfuse / Spend Logs)
6/9/2026
Output exceeds size limit
6/9/2026
[Critical Hotfix Request]: No stable LiteLLM path for Claude Code → vLLM
6/9/2026
bug(streaming): fast_path in async_streaming_data_generator breaks tool-call continuation — client receives XML instead of text (introduced v1.87.0, PR #28289)
6/9/2026
[Feature]: Bedrock Guardrails contextual grounding via the guardrail hook (request-side qualifiers)
6/9/2026
[Bug]: OTEL NoneType crash
6/9/2026
[Bug]: _group_keys_by_hash_tag() skips slot grouping for non-OSS-Cluster Redis, causing CROSSSLOT errors on Azure Redis Enterprise
6/9/2026
[Bug]: `/key/update` cannot clear `budget_limits` — both empty array and null return HTTP 400
6/9/2026
[Feature]: Configure a Bedrock project / data-retention mode per model in litellm.yaml
6/10/2026
[Bug]: github_copilot /v1/responses streaming breaks Vercel AI SDK with "reasoning part <id> not found" / "text part <id> not found"
6/10/2026
Information Disclosure - litellm-unauth-model-exposure
6/8/2026
[Bug]: Internal-user max_budget blocks zero-cost models — _PROXY_MaxBudgetLimiter ignores skip_budget_checks
6/8/2026
[Bug]: Streaming /v1/responses success logger crashes with "'dict' object has no attribute 'usage'" → no spend log written, request goes uncharged
6/8/2026