feat(consult,debate): update Gemini 3.1 and Codex model defaults (#234)

[avifenesh]

Summary

Updates model defaults across consult and debate skills for all platforms (Claude Code, OpenCode, Codex adapter).

• Gemini low/medium: gemini-2.5-flash / gemini-3-flash-preview → gemini-3-flash-preview (unified)
• Gemini high/max: gemini-3-pro-preview → gemini-3.1-pro-preview
• Codex all tiers: o4-mini / o3 → gpt-5.3-codex

Picker labels and example invocations updated to use full gemini-3.1-pro-preview API name consistently.

Files Changed

• Skill files: plugins/consult, plugins/debate, adapters/opencode/skills, adapters/codex/skills
• Command files: plugins/consult/commands, plugins/debate/commands, adapters/opencode/commands
• Tests: __tests__/debate-command.test.js — updated expectedModels, added regression guards
• Docs: README.md, CHANGELOG.md, docs/consult-command-test-strategy.md

Test Plan

• All 4,062 tests pass (npm test)
• All 7 validators pass (npx agentsys-dev validate)
• /enhance run on all modified skill files — no issues
• Effort tables use correct model names across all adapter variants
• No gemini-2.5-flash, o4-mini, or o3 in any effort table rows
• Regression guard: not.toMatch(/\|\s*(?:high|max)\s*\|\s*gemini-3-pro-preview/) added

Closes #234

[gemini-code-assist]

Summary of Changes

Hello @avifenesh, 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 streamlines the default model configurations for the 'consult' and 'debate' skills across various platforms, including Claude Code, OpenCode, and Codex adapters. The primary goal is to align with the latest model versions and simplify model selection by unifying Gemini's low/medium tiers and consolidating Codex models to a single, updated version. These changes ensure that the skills leverage the most current and efficient AI models, improving performance and consistency.

Highlights

• Gemini Model Updates: Unified low/medium effort tiers to use 'gemini-3-flash-preview' and updated high/max effort tiers to 'gemini-3.1-pro-preview' across all platforms for consult and debate skills.
• Codex Model Consolidation: Standardized all Codex effort tiers to use 'gpt-5.3-codex', replacing the previous 'o4-mini' and 'o3' models.
• Documentation and Test Alignment: Updated picker labels, example invocations, README, CHANGELOG, and test files to reflect the new model defaults and ensure robust regression guards are in place.

Changelog

• CHANGELOG.md
  • Added an entry detailing the update of Gemini and Codex model defaults for /consult and /debate skills across all platforms.
• README.md
  • Updated the default model names for Gemini and Codex in the main project README's tool comparison table.

Activity

• All 4,062 tests passed (npm test).
• All 7 validators passed (npx agentsys-dev validate).
• /enhance was run on all modified skill files with no issues.
• Effort tables now use correct model names across all adapter variants.
• Confirmed no 'gemini-2.5-flash', 'o4-mini', or 'o3' appear in any effort table rows.
• A regression guard 'not.toMatch(/|\s*(?:high|max)\s*|\s*gemini-3-pro-preview/)' was added to tests.

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. ↩

[Copilot]

Pull request overview

This PR updates model defaults for the consult and debate skills across all three platforms (Claude Code plugin, OpenCode adapter, and Codex adapter) to use newer Gemini 3.1 and unified Codex models.

Changes:

• Unified Gemini low/medium effort to gemini-3-flash-preview (replacing gemini-2.5-flash at low tier)
• Updated Gemini high/max effort to gemini-3.1-pro-preview (replacing gemini-3-pro-preview)
• Unified all Codex effort tiers to gpt-5.3-codex (replacing o4-mini and o3)

Reviewed changes

Copilot reviewed 14 out of 14 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
plugins/debate/skills/debate/SKILL.md	Updated effort-to-model mapping table and state schema example
plugins/debate/commands/debate.md	Updated effort-to-model mapping table
plugins/consult/skills/consult/SKILL.md	Updated Gemini and Codex effort tables, model picker examples, and example invocations
plugins/consult/commands/consult.md	Updated model picker labels and example invocations
docs/consult-command-test-strategy.md	Updated test expectations for model selection across all test scenarios
adapters/opencode/skills/debate/SKILL.md	Updated effort-to-model mapping table and state schema example
adapters/opencode/skills/consult/SKILL.md	Updated Gemini and Codex effort tables, "Top picks" list, and example invocations
adapters/opencode/commands/debate.md	Updated effort-to-model mapping table
adapters/opencode/commands/consult.md	Updated model picker labels and example invocations
adapters/codex/skills/debate/SKILL.md	Updated effort-to-model mapping table
adapters/codex/skills/consult/SKILL.md	Updated model picker labels and example invocations
tests/debate-command.test.js	Updated test expectations and added regression guards for new models
README.md	Updated main feature table with new default models
CHANGELOG.md	Added entry documenting the model updates

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.