Mark Claude and Codex engines as experimental#4368
Conversation
- Set Claude engine experimental flag to true in claude_engine.go - Update Claude engine test to expect experimental status - Remove Claude and Codex from main documentation in engines.md - Add note about experimental engines in engines.md - Update frontmatter-full.md to mark Claude/Codex as experimental - Update mcps.md example from codex to copilot - Generalize firewall error message in errors.md - Update github-agentic-workflows.instructions.md to mark engines as experimental - All tests pass successfully Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
|
✅ Agentic Changeset Generator completed successfully. |
There was a problem hiding this comment.
Pull Request Overview
This PR marks Claude and Codex engines as experimental to reflect their current support status and updates all documentation to recommend GitHub Copilot as the primary engine. The Claude engine's experimental flag is changed from false to true (Codex was already experimental). All references to Claude and Codex engines in documentation have been removed or marked as experimental, with examples updated to use Copilot instead.
Reviewed Changes
Copilot reviewed 38 out of 38 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
pkg/workflow/claude_engine.go |
Sets experimental: true for Claude engine |
pkg/workflow/claude_engine_test.go |
Updates test assertions to expect experimental status |
pkg/cli/templates/github-agentic-workflows.instructions.md |
Updates engine documentation to mark Claude/Codex as experimental and recommends Copilot |
.github/instructions/github-agentic-workflows.instructions.md |
Mirror of templates file with same experimental markings |
docs/src/content/docs/reference/frontmatter-full.md |
Updates frontmatter reference to mark experimental engines and removes engine-specific config fields |
docs/src/content/docs/reference/engines.md |
Adds experimental note and removes detailed Claude/Codex documentation sections |
docs/src/content/docs/troubleshooting/errors.md |
Updates error example to be engine-agnostic |
docs/src/content/docs/guides/mcps.md |
Changes example from Codex to Copilot |
.github/workflows/*.lock.yml |
Updates compiled workflows to reflect experimental status (32 lock files) |
Comments suppressed due to low confidence (1)
docs/src/content/docs/reference/engines.md:28
- This line shows 'gpt-5' as the example model but states it defaults to 'claude-sonnet-4', which is inconsistent. If the Copilot engine defaults to claude-sonnet-4, the comment is correct but the example model name is confusing. Consider using a different example model that's actually available for Copilot, or clarifying that this is demonstrating how to override the default.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| # Optional specific LLM model to use (e.g., 'gpt-5', 'claude-sonnet-4'). Has | ||
| # sensible defaults and can typically be omitted. |
There was a problem hiding this comment.
The model name 'gpt-5' appears to be incorrect. OpenAI's latest models are GPT-4 series (as of January 2025). This should likely be 'gpt-4' or 'gpt-4-turbo'. If 'gpt-5' is intentional for future-proofing, this inconsistency should be documented.
Claude and Codex engines are marked as experimental to reflect their current support status. Documentation now recommends Copilot as the primary engine.
Changes
Engine Configuration
experimental: truefor Claude engine (Codex was already experimental)Documentation
user-agentfor Codex)User-Facing Behavior
When compiling with
--verbose:Engines remain fully functional. Users can still set
engine: claudeorengine: codexin workflow frontmatter.Original prompt
💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.