Docs: global policy support for LLM Providers and Proxies#353
Merged
Conversation
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Run ID: ⛔ Files ignored due to path filters (1)
📒 Files selected for processing (3)
🚧 Files skipped from review as they are similar to previous changes (3)
📝 WalkthroughSummary
WalkthroughUpdated AI Workspace documentation to describe global and per-resource policy scopes, rate-limit counter behavior, and guardrail evaluation order. Provider documentation now explains Provider-wide hard ceilings, shared counters, request-attempt counting, HTTP 429 responses, and global-before-resource guardrail evaluation. Document metadata dates were updated to 2026-07-21. 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ 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: 4
🤖 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 `@en/docs/next/ai-workspace/llm-providers/manage-provider.md`:
- Around line 169-170: Update the rate-limiting mode description in the provider
configuration documentation to state that only the Backend section supports
these configurable modes. Do not imply that Per Consumer is currently available;
label it as planned only if that matches the surrounding documentation.
In `@en/docs/next/ai-workspace/policies/guardrails/overview.md`:
- Line 50: Update the guardrail evaluation description to reconcile “all of them
are evaluated” with intervention behavior: state that applicable guardrails run
in the documented provider/proxy and global/per-resource order, and explicitly
document whether evaluation stops or continues after an earlier guardrail
intervenes.
In `@en/docs/next/ai-workspace/policies/overview.md`:
- Around line 77-83: Revise the policy-ordering explanation in the request flow
section to explicitly scope “global policies → per-resource policies” to each
provider or proxy, matching the terminology and precedence described in the
guardrails overview. Clarify that this is not a single ordering across all
provider and proxy levels, while preserving the existing rate-limit behavior
explanation.
- Around line 79-81: Specify the fenced code block language as text for the
ASCII flow diagram in the policy overview, changing the opening fence to ```text
while leaving the diagram content and closing fence unchanged.
🪄 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: CHILL
Plan: Pro
Run ID: 879325d2-8f5f-4651-bcc5-8034295851c6
⛔ Files ignored due to path filters (1)
en/docs/assets/img/ai-gateway/standalone-ai-workspace/llm-provider/rate-limiting-tab.pngis excluded by!**/*.png
📒 Files selected for processing (3)
en/docs/next/ai-workspace/llm-providers/manage-provider.mden/docs/next/ai-workspace/policies/guardrails/overview.mden/docs/next/ai-workspace/policies/overview.md
Krishanx92
previously approved these changes
Jul 21, 2026
Krishanx92
approved these changes
Jul 23, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Purpose
This pull request updates and clarifies the documentation for rate limiting and guardrail policy scopes in the AI Workspace. The main improvements are clearer explanations of global vs. per-resource policy behavior, updated diagrams and examples, and better cross-referencing between relevant sections.
Documentation improvements for policy scope and behavior:
policies/overview.md, detailing the difference between global and per-resource policies for both rate limits and guardrails, including tables and evaluation order.llm-providers/manage-provider.mdhow provider-wide (global) and per-resource rate limits work, including counter behavior, evaluation order, and added a diagram to illustrate configuration modes.llm-providers/manage-provider.mdandpolicies/guardrails/overview.md, emphasizing that global guardrails run before per-resource guardrails and referencing the new policy scope documentation. [1] [2]General maintenance:
last_updatedmetadata in all affected files to reflect the latest changes. [1] [2] [3]