[prompting] updated plan mode prompt#29301
Conversation
![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: f06de8becd
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".
| Only produce at most one `<proposed_plan>` block per turn, and only when you are presenting a complete spec. | ||
|
|
||
| If the user stays in Plan mode and asks for revisions after a prior `<proposed_plan>`, any new `<proposed_plan>` must be a complete replacement. | ||
| If the user stays in Plan mode and asks for revisions after a prior `<proposed_plan>`, any new `<proposed_plan>` must be a complete replacement. If the user indicates that the prior plan is not acceptable but does not provide enough information to produce a complete replacement, address the concern and continue planning without producing a `<proposed_plan>` block. If the follow-up neither requires changes nor calls the plan into question (e.g. clarifying question), answer it before the block, then reproduce the prior `<proposed_plan>` unchanged. |
There was a problem hiding this comment.
This changes Plan Mode behavior after an existing <proposed_plan> by requiring clarifying/non-revision follow-ups to re-emit the prior plan, but the commit only updates the prompt template. Because this is a user-facing agent-logic change, it needs an integration test, for example under core/suite, that exercises a prior proposed plan followed by a clarifying question and verifies the plan item is re-emitted; otherwise prompt regressions or parser/UI mismatches won’t be caught.
AGENTS.md reference: AGENTS.md:L113-L119
Useful? React with 👍 / 👎.
2 participants
Update plan mode prompt to render the implementation plan to the user on relevant follow-ups, such that the user can exit out of plan mode to implement rather than manually switch of plan mode.