Add ai gateway installation instructions to doc site#582
Conversation
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (2)
📝 WalkthroughWalkthroughDocumentation updates across three deployment guides (managed cluster, quick-start, and self-hosted cluster) that remove the Build Extension verification from managed-cluster, introduce a new AI Gateway Extension installation step (final step) with configuration, Helm install commands, and verification instructions; the AI Gateway step is optional in self-hosted. Changes
Sequence Diagram(s)sequenceDiagram
participant Admin
participant Helm
participant AI_Gateway as AI Gateway
participant AgentMgr as Agent Manager
participant IDP
Admin->>Helm: run helm install amp-ai-gateway (config vars)
Helm->>AI_Gateway: deploy pods & service
AI_Gateway->>AgentMgr: register as LLM Provider (agentManager.apiUrl)
AgentMgr->>IDP: validate identity (agentManager.idp.tokenUrl)
AgentMgr-->>AI_Gateway: return registration confirmation
Admin->>AgentMgr: verify registration (kubectl/health)
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
📝 Coding Plan
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 |
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@website/docs/getting-started/managed-cluster.mdx`:
- Around line 633-659: The "Step 9: Install AI Gateway Extension" section
conflicts with its own "must be last" requirement and duplicates Step 9; move
the entire AI Gateway Extension section (heading "Step 9: Install AI Gateway
Extension", the configuration variables table including
apiGateway.controlPlane.host, agentManager.apiUrl, agentManager.idp.tokenUrl,
and the Helm install block) to the end of Phase 2 so it becomes the final step,
update its step number accordingly (renumber from Step 9 to the appropriate
final step), and ensure the surrounding sections (e.g., Evaluation Extension)
retain correct sequential numbering after the move.
In `@website/docs/getting-started/self-hosted-cluster.mdx`:
- Line 644: The document duplicates the "Step 8" heading for the AI Gateway
installation; change the heading "### Step 8: Install AI Gateway Extension" to
"### Step 9: Install AI Gateway Extension" and update any adjacent references to
step numbers (including the earlier "Evaluation Extension" which is Step 8) so
the final "must be done last" instruction is unambiguous and reflects the
corrected ordering.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: dcec2f8d-856e-438c-bb72-c5e2e51e4a47
📒 Files selected for processing (3)
website/docs/getting-started/managed-cluster.mdxwebsite/docs/getting-started/quick-start.mdxwebsite/docs/getting-started/self-hosted-cluster.mdx
There was a problem hiding this comment.
Actionable comments posted: 4
🧹 Nitpick comments (1)
website/docs/getting-started/managed-cluster.mdx (1)
703-705: Missing verification steps for AI Gateway Extension.Unlike the self-hosted cluster guide, this section lacks verification commands to confirm the bootstrap job completion and APIGateway CR status. Consider adding verification for consistency:
✏️ Suggested verification section
**Wait for the bootstrap job to complete:** ```bash kubectl wait --for=condition=complete job/amp-gateway-bootstrap \ -n ${DATA_PLANE_NS} --timeout=300sVerify the AI Gateway is running:
# Check the APIGateway CR kubectl get apigateway -n ${DATA_PLANE_NS} # Check the bootstrap job kubectl get jobs -n ${DATA_PLANE_NS}Note: This extension is optional. The platform will function without it, but the AI Gateway will not be available.
</details> <details> <summary>🤖 Prompt for AI Agents</summary>Verify each finding against the current code and only fix it if needed.
In
@website/docs/getting-started/managed-cluster.mdxaround lines 703 - 705, The
AI Gateway Extension section is missing verification steps; add a short
verification subsection that waits for and checks the bootstrap job and
APIGateway CR by using kubectl to wait for job/amp-gateway-bootstrap completion
(namespace variable DATA_PLANE_NS) and to list the apigateway CR and jobs in
that namespace so users can confirm bootstrap success and APIGateway status.</details> </blockquote></details> </blockquote></details> <details> <summary>🤖 Prompt for all review comments with AI agents</summary>Verify each finding against the current code and only fix it if needed.
Inline comments:
In@website/docs/getting-started/managed-cluster.mdx:
- Around line 677-703: Add the missing THUNDER_NS configuration variable to the
Phase 2 "Configuration Variables" section so the helm install command for the AI
Gateway Extension (helm install amp-ai-gateway / token URL using ${THUNDER_NS})
won't break; add an entry named THUNDER_NS with a short description like
"Thunder Extension namespace" and the default value used elsewhere (amp-thunder)
so the installation command and agentManager.idp.tokenUrl have a defined
variable.- Around line 683-689: Update the default value for the
agentManager.idp.tokenUrl entry in the configuration table: replace the
incorrect service name "thunder-service" with the Helm-chart correct
"amp-thunder-extension-service" so the default becomes the full URL for
agentManager.idp.tokenUrl
(http://amp-thunder-extension-service.amp-thunder.svc.cluster.local:8090/oauth2/token);
ensure the change is applied to theagentManager.idp.tokenUrlrow in the table
so docs match the Helm chart default.In
@website/docs/getting-started/self-hosted-cluster.mdx:
- Around line 652-656: The default value shown for agentManager.idp.tokenUrl is
wrong: update the documented default for agentManager.idp.tokenUrl from
http://thunder-service.amp-thunder.svc.cluster.local:8090/oauth2/token to match
the Helm chart's actual default
(http://amp-thunder-extension-service.amp-thunder.svc.cluster.local:8090/oauth2/token),
and apply the same correction in the corresponding managed-cluster.mdx file;
also verify the Helm chart value to ensure both docs and chart are consistent.- Around line 679-687: The verification command uses the wrong APIGateway CR
name; update the kubectl check that currently references "ai-gateway" to use the
configured gateway name (gateway.name) – e.g., "default-ai" (the default) or
substitute a variable that reflects gateway.name – so the APIGateway CR check
matches the value set in values.yaml and reliably verifies the correct resource.
Nitpick comments:
In@website/docs/getting-started/managed-cluster.mdx:
- Around line 703-705: The AI Gateway Extension section is missing verification
steps; add a short verification subsection that waits for and checks the
bootstrap job and APIGateway CR by using kubectl to wait for
job/amp-gateway-bootstrap completion (namespace variable DATA_PLANE_NS) and to
list the apigateway CR and jobs in that namespace so users can confirm bootstrap
success and APIGateway status.</details> --- <details> <summary>ℹ️ Review info</summary> <details> <summary>⚙️ Run configuration</summary> **Configuration used**: Path: .coderabbit.yaml **Review profile**: CHILL **Plan**: Pro **Run ID**: `36d761fd-5746-4ab3-ad56-de34504de69b` </details> <details> <summary>📥 Commits</summary> Reviewing files that changed from the base of the PR and between 805a7d873ecbf02cdb2c114e1bdcdc92dbbde26b and 393bfda9aa45d37ad1ee7a243e30c1e728952819. </details> <details> <summary>📒 Files selected for processing (2)</summary> * `website/docs/getting-started/managed-cluster.mdx` * `website/docs/getting-started/self-hosted-cluster.mdx` </details> </details> <!-- This is an auto-generated comment by CodeRabbit for review status -->
| ### Step 10: Install AI Gateway Extension | ||
|
|
||
| The AI Gateway Extension registers the AI Gateway with the Agent Manager for managing LLM Providers. | ||
|
|
||
| **Important:** This step must be done **last** — it depends on the Agent Manager service being healthy and the Thunder Extension (IDP) being ready for token exchange. | ||
|
|
||
| **Set configuration variables:** | ||
|
|
||
| | Variable | Description | Default | | ||
| |----------|-------------|---------| | ||
| | `apiGateway.controlPlane.host` | Agent Manager service URL | `amp-api-gateway-manager.wso2-amp.svc.cluster.local:9243` | | ||
| | `agentManager.apiUrl` | Agent Manager API URL (reachable from bootstrap job) | `http://amp-api.wso2-amp.svc.cluster.local:9000/api/v1` | | ||
| | `agentManager.idp.tokenUrl` | Thunder Extension token endpoint | `http://thunder-service.amp-thunder.svc.cluster.local:8090/oauth2/token` | | ||
|
|
||
| **Installation:** | ||
|
|
||
| ```bash | ||
| # Install AI Gateway Extension | ||
| helm install amp-ai-gateway \ | ||
| oci://${HELM_CHART_REGISTRY}/wso2-amp-ai-gateway-extension \ | ||
| --version 0.9.0 \ | ||
| --namespace ${DATA_PLANE_NS} \ | ||
| --set apiGateway.controlPlane.host="amp-api-gateway-manager.${AMP_NS}.svc.cluster.local:9243" \ | ||
| --set agentManager.apiUrl="http://amp-api.${AMP_NS}.svc.cluster.local:9000/api/v1" \ | ||
| --set agentManager.idp.tokenUrl="http://thunder-service.${THUNDER_NS}.svc.cluster.local:8090/oauth2/token" \ | ||
| --timeout 1800s | ||
| ``` |
There was a problem hiding this comment.
THUNDER_NS variable used but not defined in Phase 2 Configuration Variables.
The installation command at line 701 uses ${THUNDER_NS}, but this variable is only defined in Step 4 (line 464), not in the Configuration Variables section at lines 372-387. Users starting from Phase 2 or copying commands selectively may encounter undefined variable errors.
Consider adding THUNDER_NS to the Configuration Variables section:
✏️ Proposed fix
Add to the Configuration Variables section (around line 386):
export DATA_PLANE_NS="openchoreo-data-plane"
+export THUNDER_NS="amp-thunder"🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@website/docs/getting-started/managed-cluster.mdx` around lines 677 - 703, Add
the missing THUNDER_NS configuration variable to the Phase 2 "Configuration
Variables" section so the helm install command for the AI Gateway Extension
(helm install amp-ai-gateway / token URL using ${THUNDER_NS}) won't break; add
an entry named THUNDER_NS with a short description like "Thunder Extension
namespace" and the default value used elsewhere (amp-thunder) so the
installation command and agentManager.idp.tokenUrl have a defined variable.
Purpose
Goals
Approach
User stories
Release note
Documentation
Training
Certification
Marketing
Automation tests
Security checks
Samples
Related PRs
Migrations (if applicable)
Test environment
Learning
Summary by CodeRabbit