refactor(cli): consolidate automation discovery#758
Conversation
|
Codex review: needs maintainer review before merge. Reviewed June 11, 2026, 6:05 PM ET / 22:05 UTC. Summary Reproducibility: unclear. The review failed before ClawSweeper could establish a reproduction path. Review metrics: none identified. Merge readiness Overall follows the weaker of proof and patch quality, so missing proof can cap an otherwise strong patch. Risk before merge
Maintainer options:
Next step before merge
Review detailsBest possible solution: Retry the Codex review after fixing the execution failure. Do we have a high-confidence way to reproduce the issue? Unclear. The review failed before ClawSweeper could establish a reproduction path. Is this the best way to solve the issue? Unclear. Retry the review first so ClawSweeper can evaluate the actual issue and fix direction. AGENTS.md: unclear because the file could not be read completely. Codex review notes: model internal, reasoning high; reviewed against 1d2246317f44. Label changesLabel justifications:
Evidence reviewedWhat I checked:
Likely related people:
What the crustacean ranks mean
Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics. How this review workflow works
|
clawsweeper
Bot
added
the
rating: 🌊 off-meta tidepool
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 1042e8b07f
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| Discovery: capabilityDiscovery{ | ||
| SchemaCommand: "gog schema --json", | ||
| ExitCodesCommand: "gog exit-codes --json", | ||
| MCPToolsCommand: "gog mcp --list-tools", | ||
| }, |
There was a problem hiding this comment.
When capabilities is run under an active command guard that allows this command but blocks the advertised discovery commands, the snapshot still tells automation to run commands that will immediately fail; for example, gog --enable-commands=capabilities capabilities --json reports gog schema --json, gog exit-codes --json, and gog mcp --list-tools even though the same --enable-commands setting rejects each of them. Since this endpoint is meant to describe the active runtime capability surface, please omit or mark discovery commands that are blocked by the current allow/deny rules or baked profile.
Useful? React with 👍 / 👎.
steipete
changed the title
1 participant
Summary
gog agent,gog capabilities, andgog exit-codesdiscovery commands--helpgog schema --jsontools/listandgog mcp --list-tools; remove the redundant model-callable discovery toolAutomation behavior belongs to the CLI as a whole, not a special command namespace.
Closes #677.
Safety
GOG_ACCOUNT, account aliases, global config, and command-line flagsVerification
make ciNo live Google API smoke is required: this change only exposes local CLI metadata and removes discovery commands; it does not alter authenticated service behavior.