-
Notifications
You must be signed in to change notification settings - Fork 1
hygiene(#231 follow-up): 3 Codex post-merge parity reclassifications #472
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
Merged
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change | ||||
|---|---|---|---|---|---|---|
|
|
@@ -88,9 +88,17 @@ CLI in the 2026 coding-agent landscape. | |||||
| ## 2 · The big, non-obvious win — `AGENTS.md` is already universal | ||||||
|
|
||||||
| Claude Code reads `CLAUDE.md` first. Codex CLI reads `AGENTS.md` | ||||||
| first. **Zeta's setup already has both, and the `CLAUDE.md` | ||||||
| explicitly delegates to `AGENTS.md`** as the universal | ||||||
| onboarding handbook. The relevant lines of `CLAUDE.md`: | ||||||
| following a precedence chain: global `~/.codex/AGENTS.override.md` | ||||||
| / `~/.codex/AGENTS.md` first, then walks project root → CWD with | ||||||
| `AGENTS.override.md` taking precedence per directory (and a byte | ||||||
| cap; see [Codex AGENTS guide](https://developers.openai.com/codex/guides/agents-md)). | ||||||
| **Zeta's setup already has both `CLAUDE.md` and `AGENTS.md`, and | ||||||
| `CLAUDE.md` explicitly delegates to `AGENTS.md`** as the universal | ||||||
| onboarding handbook. Stage-2 readiness checks must account for | ||||||
| the precedence chain — environments with global overrides at | ||||||
| `~/.codex/AGENTS.override.md` can pass/fail ingestion checks for | ||||||
| reasons unrelated to the repo's `AGENTS.md` content. The relevant | ||||||
| lines of `CLAUDE.md`: | ||||||
|
|
||||||
| > 1. **[`AGENTS.md`](../../AGENTS.md)** — the universal | ||||||
| > onboarding handbook. Pre-v1 status, the three | ||||||
|
|
@@ -190,24 +198,29 @@ and Codex-specific. | |||||
| | Plan Mode | `plan_mode_reasoning_effort` config | **Parity** | Named differently; same concept. | | ||||||
| | Output styles (e.g., explanatory) | Not documented; may go via system-prompt override | **Gap (minor)** | Factory-side impact is small; output styles are Claude-Code-session features, not substrate. | | ||||||
| | Hooks (`.claude/settings.json` PreToolUse, UserPromptSubmit) | `notify` hook + shell-only PreToolUse (per OpenAI release notes for `rust-v0.117.0`, March 26 2026, [openai/codex#15211](https://github.com/openai/codex/pull/15211)) | **Partial (narrowing)** | Codex now has shell-only PreToolUse alongside the existing `notify` hook for turn completion. UserPromptSubmit and other Claude-Code-specific hook types are still gaps. Zeta's ASCII-clean pre-commit + prompt-injection lints run via git-pre-commit (harness-neutral) so the gap-impact on Zeta substrate is small. SessionStart hooks (e.g., for output style) still have no Codex equivalent. | | ||||||
| | Slash commands (`/loop`, `/fast`, `/help`, `/status-line-setup`) | `-m` / `--model`, profiles, plan-mode commands | **Partial** | Codex exposes fewer user-visible slash commands; model selection is via `-m` / `--model` flags + `--profile` (per `docs/research/openai-codex-cli-capability-map.md`), not via a `/model` slash command. Project-specific commands (e.g., Zeta's `/loop`) need re-authoring or re-routing through `codex exec`. | | ||||||
| | Slash commands (`/loop`, `/fast`, `/help`, `/status-line-setup`) | Built-in `/model`, `/compact`, etc. (per [`developers.openai.com/codex/cli/slash-commands`](https://developers.openai.com/codex/cli/slash-commands)) + `-m`/`--model` flags + `--profile` | **Parity (different roster)** | Codex CLI ships built-in slash commands including `/model` for model + reasoning-effort selection, `/compact` for context compaction, etc. Both harnesses expose slash commands; the rosters differ (Claude Code has Zeta-defined `/loop`, `/fast`; Codex has its own built-in roster). Project-specific commands (e.g., Zeta's `/loop`) need re-authoring or re-routing through `codex exec`. The capability surface is parity; the specific commands aren't 1-to-1. | | ||||||
|
||||||
| | Slash commands (`/loop`, `/fast`, `/help`, `/status-line-setup`) | Built-in `/model`, `/compact`, etc. (per [`developers.openai.com/codex/cli/slash-commands`](https://developers.openai.com/codex/cli/slash-commands)) + `-m`/`--model` flags + `--profile` | **Parity (different roster)** | Codex CLI ships built-in slash commands including `/model` for model + reasoning-effort selection, `/compact` for context compaction, etc. Both harnesses expose slash commands; the rosters differ (Claude Code has Zeta-defined `/loop`, `/fast`; Codex has its own built-in roster). Project-specific commands (e.g., Zeta's `/loop`) need re-authoring or re-routing through `codex exec`. The capability surface is parity; the specific commands aren't 1-to-1. | | |
| | Slash commands (`/loop`, `/fast`, `/help`, `/status-line-setup`) | Built-in `/model`, `/compact`, etc. (per [`developers.openai.com/codex/cli/slash-commands`](https://developers.openai.com/codex/cli/slash-commands)) + `-m`/`--model` flags + `--profile` | **Parity (different roster)** | Codex CLI ships built-in slash commands including `/model` for model selection and `/compact` for context compaction. Any reasoning-effort change should be understood through the active profile/config surface (`--profile`, `plan_mode_reasoning_effort`), not as a separate standalone effort-tier picker implied by `/model`. Both harnesses expose slash commands; the rosters differ (Claude Code has Zeta-defined `/loop`, `/fast`; Codex has its own built-in roster). Project-specific commands (e.g., Zeta's `/loop`) need re-authoring or re-routing through `codex exec`. The capability surface is parity; the specific commands aren't 1-to-1. | |
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
P1: This section warns that global
~/.codex/AGENTS.override.mdcan change ingestion, but it doesn’t say how Stage-2 checks should control for / detect that (e.g., instruct running in a clean home/CODEX home, or explicitly verifying which AGENTS file was loaded). Adding a concrete test precondition would make the readiness guidance actionable and less error-prone.