docs: list gemini as a factory harness type and pair --claude-auth-secret with the claude-code alias - #699
Conversation
…cret with the claude-code alias Follow-up to #689, applying the two review suggestions that were not accepted there: - Harness identifiers: the factory definition bullet now lists the values the schema actually validates (oz, claude, codex, gemini plus the claude-code alias) instead of implying factories accept only the shared identifiers, matching factory-as-code.mdx. - CLI reference: --claude-auth-secret no longer says it is only valid with --harness claude, since the previous bullet documents claude-code as an accepted alias for the same harness. Co-Authored-By: Warp <agent@warp.dev>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
This PR was generated with Warp. Comment   |
|
I'm starting a first review of this pull request. You can view the conversation on Warp. I completed the review and no human review was requested for this pull request. Comment Powered by Oz |
![warp-for-oss[bot]](https://avatars.githubusercontent.com/in/3450139?s=60&v=4){kind=small}
There was a problem hiding this comment.
Overview
This PR narrows the harness identifier guidance in two docs reference sections: factory definition files now explicitly include gemini, and --claude-auth-secret now matches the documented claude-code alias behavior.
Concerns
- No blocking correctness, docs quality, security, or spec-alignment concerns were found in the changed lines.
Verdict
Found: 0 critical, 0 important, 0 suggestions
Approve
Comment /warp-agent-review on this pull request to retrigger a review (up to 3 times on the same pull request).
Powered by Oz
![warp-agent-staging[bot]](https://avatars.githubusercontent.com/in/2196476?s=60&v=4){kind=small}
There was a problem hiding this comment.
Overview
This updates the harness reference to match the factory schema and documents that --claude-auth-secret works with the CLI's claude-code alias. The implementation sources confirm both claims, and I found no material issues.
Verdict
Checks: build pass, tests n/a, CI green, visual proof n/a
Found: 0 critical, 0 important, 0 suggestions, 0 nits
Approve
Responding as wilson: Open session · View in factory
1 participant
Follow-up to #689. Applies the two review suggestions from that PR that were not accepted before merge; both were verified against source.
Changes
platform/harnesses/index.mdx— The factory definition files bullet under "Harness identifiers" now lists the values the schema actually validates:oz,claude,codex, orgemini, plusclaude-codeas an alias forclaude. Previously it said factories accept only the shared identifiers plus the alias, which contradictedfactory-as-code.mdx(which already documentsgemini). The intro sentence now also notes that the alias is fine where a surface explicitly accepts it. Source:warp-server/logic/factoryfile/schema/v1alpha1/common.schema.json(harness.typeenum).reference/cli/index.mdx—--claude-auth-secretno longer says it is "only valid with--harness claude", since the--harnessbullet directly above documentsclaude-codeas an accepted alias. It now reads "Use with--harness claudeor the--harness claude-codealias." Source:warp/crates/warp_cli/src/agent.rsdefinesclaude-codeas a clap alias for the sameclaudevalue.Validation
python3 .agents/skills/style_lint/style_lint.py --changed— no new issues (the two reported findings are pre-existing and on untouched lines).npm run build— passes.Co-Authored-By: Warp agent@warp.dev