0.5.1 — refresh model recommendations for mid-2026 codex lineup#5
Merged
Conversation
The 2025-era per-role split (gpt-5.2-codex / gpt-5 / o3) collapsed. gpt-5.5 now handles implementation, review, and planning; the dial that matters is reasoning effort, configured via codex CLI profiles ([profiles.coding], [profiles.deep], [profiles.fast]). README and magic-codex.toml.example now lead with "leave model unset, configure your ~/.codex/config.toml" and only show in-magic-codex pinning for the budget-cap case (e.g., generic role -> mini). Also fixes: - magic-codex.toml.example header referenced the wrong filename (codex-team.toml). Loader actually reads magic-codex.toml. - README role table still showed implementer's old workspace-write sandbox; corrected to danger-full-access (default since 0.4.0). No code changes; tests still 117 passing. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Docs-only refresh of the model recommendations to match the mid-2026 codex CLI surface (`gpt-5.5` baseline + reasoning-effort profiles), plus two real bug fixes in the example files.
Why
The 2025-era per-role split was `gpt-5.2-codex` for implementer / `gpt-5` for reviewer / `o3` for planner — three different models, each playing to a different strength. In 2026, `gpt-5.5` handles all three workloads at the top of the lineup, and the dial that matters is reasoning effort, configured at the codex CLI level via profiles (`[profiles.coding]`, `[profiles.deep]`, `[profiles.fast]`). The previous docs were prescribing the wrong abstraction.
Changes
Test plan
🤖 Generated with Claude Code