guardrails · Issues· 80 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #1629
Proposal: EvalPort adapter for Guardrails Validators (portable eval test cases + results)
Updated Sep 19, 2026 - #1657
[bug] LiteLLMCallable default model is gpt-3.5-turbo, which OpenAI shuts down 2026-10-23
Updated Sep 17, 2026 - #1538
[feat] Add Hub manifest entries for pan-African validators (+ WAF bug blocking hub submit CLI)
enhancementStaleUpdated Sep 17, 2026 - #1656
RAIL defaults on_fail to NOOP while the Python API defaults to EXCEPTION
Updated Sep 14, 2026 - #1559
Bug: coerce_to_type treats string "false" as True for BOOLEAN schema
Updated Sep 13, 2026 - #1633
Sequential and async validator services disagree: the default path silently discards fixes when several validators use on_fail=fix
Updated Sep 10, 2026 - #1488
Feature request: OWASP ASI06 memory poisoning guard validator
Updated Sep 6, 2026 - #1502
[bug] Hub website: "Unable to parse markdown" — validator descriptions render with newlines stripped
StaleUpdated Sep 5, 2026 - #1558
Bug: DELETE query in _truncate runs on every call, bypassing TIME_BETWEEN_CLEANUPS throttle
StaleUpdated Sep 4, 2026 - #1505
[bug] typer<0.20 and click<=8.2.0 pins block huggingface-hub>=1.18.0 compatibility
bugStaleUpdated Sep 1, 2026 - #1457
Portable evidence artifacts for validation outcomes
enhancementStaleUpdated Aug 24, 2026 - #1631
[bug] llm.invocation_parameters is a Python repr and embeds the full prompt
Updated Aug 22, 2026 - #1560
SUNSET REMOTE INFERENCING AND HUB on 8/25
Updated Aug 18, 2026 - #1485
Best-practice: litellm pin excludes patched CVE versions, unverified-jwt-decode duplication, workflow inputs interpolation
Updated Aug 18, 2026 - #1630
[feat] Add native Langfuse observability integration
enhancementUpdated Aug 17, 2026