Sync release docs and marketing#3
Conversation
📝 WalkthroughWalkthroughDocumentation-only update for v0.2.22: adds Vercel AI Gateway, Cloudflare AI Gateway, Workers AI, and custom provider support across all reference docs; refreshes OpenCode Zen and OpenRouter model catalogs with new model IDs and changes the default model to Changesv0.2.22 Documentation Release
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
![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: 6728fa9f74
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".
| | `hy3-preview-free` | Hy3 preview model | | ||
| | `nemotron-3-super-free` | NVIDIA Nemotron free trial model | | ||
| | `trinity-large-preview-free` | Trinity large preview model | | ||
| | `deepseek-v4-flash-free` | DeepSeek's free fast open-source model (default) | |
There was a problem hiding this comment.
This table now tells users to use deepseek-v4-flash-free as the default, but the current registry does not contain that ID: OPENCODE_ZEN_MODELS still starts with minimax-m2.5-free, and DEFAULT_CONFIG.defaultModel is still minimax-m2.5-free. With this docs state, following msh --model deepseek-v4-flash-free hits the CLI's unknown-model path instead of selecting the documented default.
Useful? React with 👍 / 👎.
| |--------|-------------| | ||
| | `--setup` | Run the setup wizard for API key configuration | | ||
| | `--provider <name>` | Set AI provider (`opencode-zen` or `openrouter`) | | ||
| | `--provider <name>` | Set AI provider (`opencode-zen`, `openrouter`, `vercel-ai-gateway`, `cloudflare-ai-gateway`, `workers-ai`, or `custom`) | |
There was a problem hiding this comment.
custom from the --provider documentation
The CLI docs now advertise msh --provider custom, but the handler for --provider only accepts opencode-zen, openrouter, vercel-ai-gateway, cloudflare-ai-gateway, and workers-ai; custom is only reached by adding/selecting a custom model. Users following this option will get the unknown-provider error instead of switching to custom endpoints.
Useful? React with 👍 / 👎.
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 5
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@README.md`:
- Around line 588-590: Add a blank line between the release heading "### v0.2.22
- Model Catalog and Release Prep" and the bulleted list items that follow it to
comply with markdown linting rule MD022, which requires a blank line after
headings. Insert an empty line after the heading line to separate it from the
first bullet point starting with "Refreshed OpenCode Zen".
In `@website/src/components/Schema.astro`:
- Around line 27-31: Update the founder.url and author.url fields in the
Schema.astro file to point to the author's GitHub profile instead of the
repository. For the founder object at lines 27-31, change the url from the full
repository path (ending in /magic-shell) to just the author's profile path.
Apply the same change to the author.url fields mentioned at lines 71-75 and
209-213. Keep the repository URL in codeRepository or sameAs fields as
appropriate for the schema type.
In `@website/src/content/docs/getting-started/installation.mdx`:
- Around line 26-30: The package.json file has outdated Bun version constraints
that conflict with the documented prerequisites. Update the package.json file by
changing the "packageManager" field from "bun@1.3.9" to "bun@1.3.14" and the
"bun" field from ">=1.3.9" to ">=1.3.14" to align with the Bun 1.3.14+
requirement specified in the installation documentation and other website files
like Schema.astro.
In `@website/src/content/docs/reference/cli-options.mdx`:
- Line 28: The documentation table for the `--provider` flag at line 28 in
website/src/content/docs/reference/cli-options.mdx includes `custom` as a valid
option, but this provider is not included in the CLI validation allowlist in
src/index.ts. Remove `custom` from the provider options list in the
documentation table to match the actual supported providers (opencode-zen,
openrouter, vercel-ai-gateway, cloudflare-ai-gateway, and workers-ai only).
In `@website/src/content/docs/reference/config-file.mdx`:
- Line 21: The documentation in config-file.mdx incorrectly states the default
model as deepseek-v4-flash-free on lines 21, 62, 252, and 264, but the actual
runtime default in src/lib/config.ts initializes DEFAULT_CONFIG.defaultModel as
minimax-m2.5-free. Update all four occurrences of deepseek-v4-flash-free in the
config-file.mdx documentation to minimax-m2.5-free to match the actual
DEFAULT_CONFIG.defaultModel value.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro
Run ID: c36fbe27-5b95-4394-88d7-578ecc13fb71
📒 Files selected for processing (17)
README.mdwebsite/SCHEMA-IMPLEMENTATION.mdwebsite/SCHEMA-SUMMARY.mdwebsite/SCHEMA-VALIDATION.mdwebsite/TEST-SCHEMA.mdwebsite/src/components/FAQSchema.astrowebsite/src/components/Schema.astrowebsite/src/components/TransformHero.astrowebsite/src/content/docs/features/providers.mdxwebsite/src/content/docs/getting-started/configuration.mdxwebsite/src/content/docs/getting-started/installation.mdxwebsite/src/content/docs/index.mdxwebsite/src/content/docs/reference/changelog.mdxwebsite/src/content/docs/reference/cli-options.mdxwebsite/src/content/docs/reference/config-file.mdxwebsite/src/content/docs/reference/keyboard-shortcuts.mdxwebsite/src/pages/index.astro
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
README.md (1)
45-45:⚠️ Potential issue | 🟡 MinorUpdate README.md line 45 to reflect Bun v1.3.14+
README.md still specifies Bun v1.3.9 or higher while other documentation files in this release (installation.mdx, Schema.astro) reference v1.3.14 or higher. Update this prerequisite to match the current baseline.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@README.md` at line 45, The Prerequisite line in README.md specifies an outdated Bun runtime version requirement of v1.3.9, which is inconsistent with the v1.3.14 or higher baseline referenced in other documentation files like installation.mdx and Schema.astro. Update the version number in the Bun prerequisite statement from v1.3.9 to v1.3.14 to ensure consistency across all documentation and reflect the current minimum supported version.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Outside diff comments:
In `@README.md`:
- Line 45: The Prerequisite line in README.md specifies an outdated Bun runtime
version requirement of v1.3.9, which is inconsistent with the v1.3.14 or higher
baseline referenced in other documentation files like installation.mdx and
Schema.astro. Update the version number in the Bun prerequisite statement from
v1.3.9 to v1.3.14 to ensure consistency across all documentation and reflect the
current minimum supported version.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro
Run ID: 02a0ae1b-71c4-494e-8848-1b0fb33ba419
📒 Files selected for processing (3)
README.mdwebsite/src/components/Schema.astrowebsite/src/content/docs/reference/cli-options.mdx
1 participant
Summary
Test plan
Notes
Note
Update docs and website to reflect v0.2.22 release with new providers and default model
minimax-m2.5-freetodeepseek-v4-flash-freeacross all examples and config snippets.designxdeveloptoaustin-thesingacross the website, schema files, and homepage.Macroscope summarized 450cd8d.
Summary by CodeRabbit
deepseek-v4-flash-free.