/astra-review now runs on Opus (model: opus). Opus verifies findings,
checks every diff, and runs the tests; fixes go to a Fable subagent.
When that Agent call fails with a rate_limit / HTTP 429 API error, the
command switches to Astra for the rest of the session:
- astra-review.js --fix-findings <file> sends confirmed findings to
Codex in a workspace-write sandbox with the review isolation intact
(no web search, MCP disabled, user config ignored, no API keys) and
/tmp, $TMPDIR, and the network excluded from the writable roots.
- New scripts/lib/astra-review/fix.js builds the fix prompt, validates
the structured fix result, and formats the report.
- codex.js shares one exec runner between review and fix; the sandbox
is allowlisted (danger-full-access is refused).
- The command snapshots git diff and untracked files before any writer
runs, so Opus reverts only the writer's hunks and never the user's
uncommitted work.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The guides referenced a non-existent /ecc:tdd command; the TDD entry
point is the tdd-workflow skill (/ecc:tdd-workflow), optionally fed a
*.plan.md from /ecc:plan.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Step-by-step section in the English and Japanese guides: plugin refresh
and Codex login check, creating the project and starting Claude Code
there, running /ecc:astra-review, committing on PASS, and gating the push.
Notes that the project does not need to live under the ECC checkout and
gives the installed script path.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Full manual for /astra-review: setup (Codex CLI, ChatGPT login, plugin
freshness), scopes, script options and exit codes, verdict format, the fix
loop, push gating, what leaves the machine, troubleshooting, and limits.
Linked from both READMEs, the Japanese quick reference, and the command docs.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
