Skip to content

intake: upstream #1612 (intake/lote-C-pr-1612)#73

Closed
nsalvacao wants to merge 1 commit intobaseline/main-sync-2026-02-17from
intake/lote-C-pr-1612
Closed

intake: upstream #1612 (intake/lote-C-pr-1612)#73
nsalvacao wants to merge 1 commit intobaseline/main-sync-2026-02-17from
intake/lote-C-pr-1612

Conversation

@nsalvacao
Copy link
Owner

Intake PR (Review Phase)

Policy

  • This PR is for review and validation only.
  • Do not merge until Gemini/Copilot review + local validation are complete.
  • We will follow the 7-step integration workflow.

Introduces a new command that enables targeted spec amendments after
implementation is complete. When edge cases, missing scenarios, or
behavioral corrections are discovered post-implementation, this command
cascades the change through spec → tests → code → traceability without
requiring a full re-run of the specify/plan/tasks/implement pipeline.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
@gemini-code-assist
Copy link

Summary of Changes

Hello @nsalvacao, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request integrates a new /speckit.amend command, providing a structured and automated process for handling minor, post-implementation adjustments to features. It ensures that discovered edge cases, behavioral corrections, or new scenarios are consistently propagated across specifications, tests, and code, maintaining the integrity of the development lifecycle without requiring a full re-run of the initial feature development pipeline.

Highlights

  • New Command Introduction: Introduced a new /speckit.amend command designed to manage post-implementation changes to features, addressing edge cases, behavioral corrections, or new scenarios discovered after initial development.
  • Structured Amendment Workflow: Defined a comprehensive 7-phase workflow for the /speckit.amend command, covering context loading, spec amendment, affected implementation location, test amendment, implementation amendment, traceability updates, and reporting.
  • Clear Usage Guidelines: Established explicit guidelines for when to use and when NOT to use the /speckit.amend command, emphasizing its role in targeted, minimal-impact changes to maintain consistency across documentation, tests, and code.
Changelog
  • templates/commands/amend.md
    • Added the definition and detailed workflow for the new /speckit.amend command.
Activity
  • The pull request is currently in a review and validation phase.
  • It requires Gemini/Copilot review and local validation before merging.
  • The team plans to follow a 7-step integration workflow for this change.
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

Copy link

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request introduces a new /speckit.amend command, which provides a well-defined workflow for making post-implementation changes. The process is thorough, incorporating best practices like spec-as-source-of-truth and a test-first approach. The different phases, from context loading to reporting, are logical and cover the amendment lifecycle comprehensively. My review focuses on clarifying a few edge cases and alternative paths to make the process even more robust. I've added a couple of comments to address underspecified parts of the workflow.

```

d. Present the impact map to the user and ask: "Proceed with these changes? (yes/no)"
- If "no", halt and suggest adjustments

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The recovery path when the user rejects the proposed impact map is a bit vague. The instruction to "halt and suggest adjustments" could be more specific to ensure a helpful user interaction. Consider guiding the agent to explicitly ask the user to either provide the correct list of affected files or to refine the amendment description for a more accurate impact analysis.


9. Run the new test to confirm it **fails** (RED state):
- Execute only the new test using the project's test runner
- If the test **passes** (the behavior already works): Report that the amendment is already handled in code but was missing from the spec. Mark as "spec-only amendment" and skip Phase 5.

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

In the case of a "spec-only amendment" where the implementation already exists and Phase 5 is skipped, the instructions for Phase 6 (Traceability Update) are incomplete. It's not specified what should be written for the Code: <implementation file path> entry in tasks.md (line 166).

To ensure complete and unambiguous traceability, the process should define this. For example, it could instruct the agent to record Code: No change required or to list the file(s) that were identified as already containing the correct implementation.

@nsalvacao nsalvacao closed this Feb 25, 2026
@nsalvacao
Copy link
Owner Author

Superseded by #148, which carries the same /speckit.amend intake content into the active baseline lane (baseline/upstream-intake-2026-02-25).

This PR is now closed to keep intake flow coherent.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants