garrytan f175f8554a fix(cso-eval): run the trusted launcher outside Claude's sandbox; keep every other command sandboxed ...

Claude Code 2.1.263 forces every Bash command into its bubblewrap sandbox
while CLAUDE_CODE_SUBPROCESS_ENV_SCRUB is set, excludedCommands
notwithstanding. Inside it the launcher's owner check sees root as nobody
and the Docker socket is unreachable, so comprehensive cells degraded to
static-only results.

- drop CLAUDE_CODE_SUBPROCESS_ENV_SCRUB for producers; pass --settings with
  sandbox enabled, failIfUnavailable, no unsandboxed fallback, no
  auto-allow, and excludedCommands naming only the exact launcher path
- ClaudeAdapter.run refuses to start the agent
  (CLAUDE_PRODUCER_SANDBOX_POLICY_MISMATCH) unless args and env carry
  exactly that policy
- README containment note and CHANGELOG updated

2026-10-09 05:07:52 +00:00

..

claude.ts

fix(cso-eval): run the trusted launcher outside Claude's sandbox; keep every other command sandboxed

2026-10-09 05:07:52 +00:00

gemini.test.ts

test(benchmark): full post-CLI gemini e2e + GEMINI_API_KEY auth path

2026-07-10 09:38:06 -07:00

gemini.ts

v1.91.66.0 fix: /autoplan without permission prompts after background reviewers, 34 contributor PRs from the backlog triage (#3087)

2026-10-08 17:40:06 +00:00

gpt.ts

v1.91.66.0 fix: /autoplan without permission prompts after background reviewers, 34 contributor PRs from the backlog triage (#3087)

2026-10-08 17:40:06 +00:00

types.ts

v1.91.8.0 test: smaller suite, derived paid selection, retired never-green evals (#2994)

2026-09-29 08:58:49 -07:00