Repository Issue Activity (beta)

#688 Persisted config can override a live env var, breaking the documented 'env wins' precedence

#703 [BUG] openai.agents DEBUG floods sandbox stdout -> fills host disk (80GB+); + Too many open files (Errno 24) on long runs

#685 view_request renderer never shows 'more content available' for >15-line output

#701 litellm.APIConnectionError: No module named 'google'

#698 [FEATURE] Add an agent-native Strix runtime using skills and MCP

#697 ss

#694 [BUG] Local source copy hangs on large repositories (per-file LocalDir exec loop)

#693 [BUG]

#680 [FEATURE] Expose manual /compact command for long-running sessions with local LLMs

#691 [FEATURE] AI/LLM application testing skills (new vulnerability class)

#684 Numbered-list markdown renders a double space after the marker

#682 build_root_task flattens multiple targets/constraints onto one line

#655 [BUG] Case-sensitive addresses lowercased automatically

#678 [FEATURE] Add skill for AI Agent Cross-Modal Leaks (Prompt Injection Data Exfiltration)

#520 [BUG] Tool calls returned as plain text instead of being executed when using Ollama backend

#672 [BUG] scarf.finding() + posthog.finding() block asyncio event loop up to 20s per finding

#671 Local-code scans fail on Windows Docker Desktop during sandbox workspace materialization (ExecTransportError / WorkspaceArchiveWriteError)

#670 [BUG] Todo tools silently fail on numeric-looking ids (e.g. "1e5230" parsed to inf)

#669 [BUG] SARIF: "regex denial of service" shadowed by "denial of service", collapsing distinct fingerprints

#660 [BUG] Tool events collide across agents and can regress from "completed" back to "running" in TuiLiveView

#658 [FEATURE]

#632 [FEATURE] Add support for OS/Arch: linux/arm64

#656 [FEATURE] Add first-class support for Groq API key and Groq-hosted models

#621 weak password

#624 Emit SARIF 2.1.0 for CI / code-scanning integration