You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm trying to run Claude Code inside an OpenShell sandbox on Fedora (Podman driver, SELinux enforcing, v0.0.71) with a Vertex AI provider and I've hit two issues. Wondering if I'm missing something in my setup or if these are known gaps.
1) context_management: Extra inputs are not permitted
Claude Code sends a context_management field in the request body (part of the context-management-2025-06-27 beta). The router strips the anthropic-beta header for Vertex rawPredict routes (makes sense — Vertex rejects it), but the corresponding body field isn't stripped. Vertex then rejects the unknown field with 400.
I'm working around it with CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1, which works but disables all experimental features. Would it make sense for the router to strip beta-only body fields (like context_management) alongside stripping the anthropic-beta header?
2) User bind mounts don't get SELinux relabeling
On Fedora with SELinux enforcing, the bind-mounted /sandbox/repos is inaccessible to the sandbox user — SELinux blocks it because the source files have user_home_t context. I noticed that internal TLS bind mounts get the z (shared relabel) option when SELinux is detected, but user-configured bind mounts via --driver-config-json don't. Is there a way to pass mount options I'm missing, or would adding automatic z relabeling for user bind mounts on SELinux systems be a reasonable enhancement?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
Hi,
I'm trying to run Claude Code inside an OpenShell sandbox on Fedora (Podman driver, SELinux enforcing, v0.0.71) with a Vertex AI provider and I've hit two issues. Wondering if I'm missing something in my setup or if these are known gaps.
Setup:
1)
context_management: Extra inputs are not permittedClaude Code sends a
context_managementfield in the request body (part of thecontext-management-2025-06-27beta). The router strips theanthropic-betaheader for Vertex rawPredict routes (makes sense — Vertex rejects it), but the corresponding body field isn't stripped. Vertex then rejects the unknown field with 400.I'm working around it with
CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1, which works but disables all experimental features. Would it make sense for the router to strip beta-only body fields (likecontext_management) alongside stripping theanthropic-betaheader?2) User bind mounts don't get SELinux relabeling
On Fedora with SELinux enforcing, the bind-mounted
/sandbox/reposis inaccessible to the sandbox user — SELinux blocks it because the source files haveuser_home_tcontext. I noticed that internal TLS bind mounts get thez(shared relabel) option when SELinux is detected, but user-configured bind mounts via--driver-config-jsondon't. Is there a way to pass mount options I'm missing, or would adding automaticzrelabeling for user bind mounts on SELinux systems be a reasonable enhancement?Thanks for any pointers.
Beta Was this translation helpful? Give feedback.
All reactions