Guardrails · Issues· 235 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #2327
feature: consistent input-length handling across all rails
enhancementstatus: needs triageUpdated Sep 22, 2026 - #2375
bug: mask sensitive data on output rail is unusable in 0.24.0: mask_sensitive_data() got an unexpected keyword argument 'context'
bugstatus: needs triageUpdated Sep 21, 2026 - #2395
doc: fix remaining broken docs.nvidia.com links in root README
documentationstatus: needs triageUpdated Sep 20, 2026 - #2346
doc: sequence diagram image asset is missing/broken
documentationstatus: needs triageUpdated Sep 20, 2026 - #2044
is_content_safe verdict parser fails OPEN, bypassing self-check / content-safety / fact-checking rails
Updated Sep 19, 2026 - #2391
bug: Presidio Sensitive Data Detection with custom recognizers cannot be called twice
bugstatus: needs triageUpdated Sep 17, 2026 - #2352
feature: Support tools param on /v1/chat/completions
enhancementstatus: needs triageUpdated Sep 17, 2026 - #2364
bug: jailbreak detection ONNX model classifies benign prompts as jailbreaks
bugstatus: needs triageUpdated Sep 13, 2026 - #2202
bug: require TLS for remote jailbreak detection NIM endpoints
good first issueUpdated Sep 12, 2026 - #2381
doc: Broken 'Getting Started Guide' link in root README
Updated Sep 12, 2026 - #1935
bug: streaming output rails reuse stale `$bot_message` / `$user_message` action params across chunks
Updated Sep 11, 2026 - #2367
ci: run a token-free Fern docs check on fork pull requests
enhancementstatus: triagedUpdated Sep 8, 2026 - #2179
Your project is on StackMap — a curated map of the AI stack
Updated Sep 6, 2026 - #2363
doc:add Conduct to third-party guardrail catalog
documentationstatus: needs triageUpdated Sep 5, 2026 - #2360
bug: events-history cache key ignores system messages, so a request is answered under an earlier request's system prompt
bugstatus: needs triageUpdated Sep 3, 2026