docs: clarify token precedence and silently-ignored inputs#6
Conversation
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
✅ Files skipped from review due to trivial changes (1)
📝 WalkthroughWalkthroughREADME updated to clarify isAuthorizedWithToken() token precedence (uses identityToken when both tokens present) and to expand unsupported features: entity tags are ignored and cedarJson-based ChangesAVP Compatibility Documentation
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
README.md (1)
356-357: ⚡ Quick winClarify the exact key path as
context.cedarJsonfor consistency with the request shape section.This is already correct behavior-wise; specifying the nested path makes it unambiguous for callers.
✏️ Suggested wording
-- Passing `context` as raw Cedar JSON via the `cedarJson` key. Only - `contextMap` is supported; a `cedarJson` context is silently ignored. +- Passing raw Cedar JSON via `context.cedarJson`. Only + `context.contextMap` is supported; `context.cedarJson` is silently ignored.🤖 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` around lines 356 - 357, Update the README sentence to explicitly reference the nested key path as context.cedarJson to match the request shape section and avoid ambiguity; state that only context.contextMap is supported and that context.cedarJson (i.e., passing cedar JSON under the context.cedarJson key) will be silently ignored so callers use context.contextMap instead.
🤖 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 347-348: The README incorrectly refers to a top-level entities[]
array; update the wording to reference the actual request shape
entities.entityList[] so callers know to provide the list under the entityList
key; also keep the note about Entity tags (.hasTag() / .getTag()) and state that
a tags key on an entities.entityList[] entry is silently ignored rather than
raising an error to avoid integration mistakes.
---
Nitpick comments:
In `@README.md`:
- Around line 356-357: Update the README sentence to explicitly reference the
nested key path as context.cedarJson to match the request shape section and
avoid ambiguity; state that only context.contextMap is supported and that
context.cedarJson (i.e., passing cedar JSON under the context.cedarJson key)
will be silently ignored so callers use context.contextMap instead.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
- Explain that isAuthorizedWithToken uses identityToken and ignores accessToken, and how this differs from AVP. - Note that a tags key on entities[] entries is silently ignored. - Note that a cedarJson context key is silently ignored; only contextMap is supported.
|
@coderabbitai review |
✅ Action performedReview finished.
|
1 participant
Summary by CodeRabbit