Merge branch 'main' into add-file

Signed-off-by: Huamin Chen <[email protected]>

Author: rootfs

.github/ISSUE_TEMPLATE/001_feature_request.yaml

@@ -0,0 +1,31 @@
+name: Feature Request
+description: Feature request
+labels: ["feature request"]
+title: "feature: <title>"
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to fill out this feature request!
+  - type: textarea
+    attributes:
+      label: Describe the feature
+      description: A clear and concise description of what the feature is.
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: Why do you need this feature?
+      description: A clear and concise description of why you need this feature.
+    validations:
+      required: false
+  - type: textarea
+    attributes:
+      label: Additional context
+      description: Add any other context about the problem here.
+    validations:
+      required: false
+  - type: markdown
+    attributes:
+      value: |
+        Love this enhancement proposal? Give it a 👍. We prioritise the proposals with the most 👍.

.github/ISSUE_TEMPLATE/002_bug_report.yaml

@@ -0,0 +1,37 @@
+name: Bug Report
+description: Bug report
+labels: ["bug"]
+title: "bug: <title>"
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to fill out this bug report!
+  - type: textarea
+    attributes:
+      label: Describe the bug
+      description: A clear and concise description of what the bug is.
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: To Reproduce
+      description: Steps to reproduce the behavior.
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: Expected behavior
+      description: A clear and concise description of what you expected to happen.
+    validations:
+      required: false
+  - type: textarea
+    attributes:
+      label: Additional context
+      description: Add any other context about the problem here.
+    validations:
+      required: false
+  - type: markdown
+    attributes:
+      value: |
+        Impacted by this bug? Give it a 👍. We prioritise the issues with the most 👍.

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,9 @@
+blank_issues_enabled: true
+
+contact_links:
+  - name: Have you read the tutorials?
+    url: https://vllm-semantic-router.com
+    about: Much help can be found in the docs
+  - name: Chat on Slack
+    url: https://slack.vllm.ai/
+    about: Maybe chatting with the community can help @semantic-router channel

.github/ISSUE_TEMPLATE/config.yml

@@ -1,30 +1,45 @@
-**What type of PR is this?**
-<!--
-Your PR title should be descriptive, and generally start with type that contains a subsystem name with `()` if necessary
-and summary followed by a colon. format `chore/docs/api/feat/fix/refactor/style/test: summary`.
-Examples:
-* "docs: fix grammar error"
-* "feat(translator): add new feature"
-* "fix: fix xx bug"
-* "chore: change ci & build tools etc"
-* "api: add xxx fields in ClientTrafficPolicy"
--->
-
-<!--
-NOTE: If your PR contains any API changes (changes under `/api`), we recommend you to separate these API changes into
-a new PR, and we will review the API part first. It will save you lots of implementation time if the API get accepted.
--->
-
-**What this PR does / why we need it**:
-
-**Which issue(s) this PR fixes**:
-<!--
-*Automatically closes linked issue when PR is merged.
-Usage: `Fixes #<issue number>`, or `Fixes (paste link of issue)`.
--->
-Fixes #
-
-<!--
-For any non-trivial changes, you need to provide a brief description of the changes in the release notes.
--->
-Release Notes: Yes/No
+FILL IN THE PR DESCRIPTION HERE
+
+FIX #xxxx (*link existing issues this PR will resolve*)
+
+**BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE**
+
+---
+
+- [ ] Make sure the code changes pass the [pre-commit](https://github.com/vllm-project/semantic-router/blob/main/CONTRIBUTING.md) checks.
+- [ ] Sign-off your commit by using <code>-s</code> when doing <code>git commit</code>
+- [ ] Try to classify PRs for easy understanding of the type of changes, such as `[Bugfix]`, `[Feat]`, and `[CI]`.
+
+<details>
+<!-- inside this <details> section, markdown rendering does not work, so we use raw html here. -->
+<summary><b> Detailed Checklist (Click to Expand) </b></summary>
+
+<p>Thank you for your contribution to semantic-router! Before submitting the pull request, please ensure the PR meets the following criteria. This helps us maintain the code quality and improve the efficiency of the review process.</p>
+
+<h3>PR Title and Classification</h3>
+<p>Please try to classify PRs for easy understanding of the type of changes. The PR title is prefixed appropriately to indicate the type of change. Please use one of the following:</p>
+<ul>
+    <li><code>[Bugfix]</code> for bug fixes.</li>
+    <li><code>[CI/Build]</code> for build or continuous integration improvements.</li>
+    <li><code>[Doc]</code> for documentation fixes and improvements.</li>
+    <li><code>[Feat]</code> for new features in the cluster (e.g., autoscaling, disaggregated prefill, etc.).</li>
+    <li><code>[Router]</code> for changes to the <code>vllm_router</code> (e.g., routing algorithm, router observability, etc.).</li>
+    <li><code>[Misc]</code> for PRs that do not fit the above categories. Please use this sparingly.</li>
+</ul>
+<p><strong>Note:</strong> If the PR spans more than one category, please include all relevant prefixes.</p>
+
+<h3>Code Quality</h3>
+
+<p>The PR need to meet the following code quality standards:</p>
+
+<ul>
+    <li>Pass all linter checks. Please use <code>pre-commit</code> to format your code. See <code>README.md</code> for installation.</li>
+    <li>The code need to be well-documented to ensure future contributors can easily understand the code.</li>
+    <li> Please include sufficient tests to ensure the change is stay correct and robust. This includes both unit tests and integration tests.</li>
+</ul>
+
+<h3>DCO and Signed-off-by</h3>
+<p>When contributing changes to this project, you must agree to the <a href="https://github.com/vllm-project/vllm/blob/main/DCO">DCO</a>. Commits must include a <code>Signed-off-by:</code> header which certifies agreement with the terms of the DCO.</p>
+<p>Using <code>-s</code> with <code>git commit</code> will automatically add this header.</p>
+
+<h3>What to Expect for the Reviews</h3>

.github/ISSUE_TEMPLATE/feature_request.md

@@ -27,7 +27,7 @@ jobs:
       - name: Test kustomize with different overlays
         run: |
           echo "Testing base kustomization..."
-          kustomize build deploy/kubernetes > /tmp/base-manifests.yaml
+          kustomize build deploy/kubernetes/ai-gateway/semantic-router > /tmp/base-manifests.yaml
 
           echo "Validating generated resources..."
 
@@ -57,22 +57,22 @@ jobs:
       - name: Verify ConfigMap generation
         run: |
           echo "Checking ConfigMap generation..."
-          kustomize build deploy/kubernetes | grep -A 20 "kind: ConfigMap"
+          kustomize build deploy/kubernetes/ai-gateway/semantic-router | grep -A 20 "kind: ConfigMap"
 
           # Verify config files are included
-          if ! kustomize build deploy/kubernetes | grep -q "config.yaml"; then
+          if ! kustomize build deploy/kubernetes/ai-gateway/semantic-router | grep -q "config.yaml"; then
             echo "Warning: config.yaml might not be properly included in ConfigMap"
           fi
 
-          if ! kustomize build deploy/kubernetes | grep -q "tools_db.json"; then
+          if ! kustomize build deploy/kubernetes/ai-gateway/semantic-router | grep -q "tools_db.json"; then
             echo "Warning: tools_db.json might not be properly included in ConfigMap"
           fi
 
       - name: Validate observability kustomization
         run: |
           echo "Validating observability stack kustomization..."
-          if [ -d "deploy/kubernetes/observability" ]; then
-            kustomize build deploy/kubernetes/observability > /tmp/observability-manifests.yaml
+          if [ -d "deploy/kubernetes/ai-gateway/semantic-router/observability" ]; then
+            kustomize build deploy/kubernetes/ai-gateway/semantic-router/observability > /tmp/observability-manifests.yaml
             echo "✓ Observability kustomization is valid"
             
             # Verify expected resources
@@ -90,9 +90,9 @@ jobs:
           echo "Validating AI Gateway configurations..."
 
           # Check if ai-gateway directory exists
-          if [ -d "deploy/kubernetes/ai-gateway" ]; then
+          if [ -d "deploy/kubernetes/ai-gateway/semantic-router/ai-gateway" ]; then
             # Validate configuration yamls (without CRDs)
-            for yaml_file in deploy/kubernetes/ai-gateway/configuration/*.yaml; do
+            for yaml_file in deploy/kubernetes/ai-gateway/semantic-router/ai-gateway/configuration/*.yaml; do
               if [ -f "$yaml_file" ]; then
                 echo "Checking $yaml_file..."
                 # Basic YAML syntax check
@@ -101,7 +101,7 @@ jobs:
             done
             
             # Validate inference-pool manifests (skip CRD validation as they may not be installed)
-            for yaml_file in deploy/kubernetes/ai-gateway/inference-pool/*.yaml; do
+            for yaml_file in deploy/kubernetes/ai-gateway/semantic-router/ai-gateway/inference-pool/*.yaml; do
               if [ -f "$yaml_file" ]; then
                 echo "Checking $yaml_file for YAML syntax..."
                 # Just check if it's valid YAML

.github/PULL_REQUEST_TEMPLATE.md

@@ -26,7 +26,7 @@ name: Kubernetes Integration Test
 on:
   pull_request:
     paths:
-      - "deploy/kubernetes/**"
+      - "deploy/kubernetes/ai-gateway/semantic-router/**"
       - ".github/workflows/k8s-integration-test*.yml"
       - "Dockerfile.extproc"
       - "tools/kind/**"

.github/workflows/k8s-config-test.yml

@@ -138,7 +138,7 @@ jobs:
           echo "Preparing CI deployment configuration..."
 
           # Create a temporary kustomization file for CI
-          cd deploy/kubernetes
+          cd deploy/kubernetes/ai-gateway/semantic-router
 
           # Backup original kustomization.yaml
           cp kustomization.yaml kustomization.yaml.backup
@@ -241,7 +241,7 @@ jobs:
       - name: Deploy to kind cluster
         run: |
           echo "Deploying semantic-router to kind cluster..."
-          kustomize build deploy/kubernetes | kubectl apply -f -
+          kustomize build deploy/kubernetes/ai-gateway/semantic-router | kubectl apply -f -
 
           echo "Waiting for namespace to be active..."
           kubectl wait --for=jsonpath='{.status.phase}'=Active namespace/vllm-semantic-router-system --timeout=60s
@@ -394,7 +394,7 @@ jobs:
           echo "Cleaning up kind cluster..."
           kind delete cluster --name semantic-router-cluster || true
           echo "Restoring original kustomization..."
-          cd deploy/kubernetes
+          cd deploy/kubernetes/ai-gateway/semantic-router
           if [ -f kustomization.yaml.backup ]; then
             mv kustomization.yaml.backup kustomization.yaml
           fi

.github/workflows/k8s-integration-test.yml

@@ -28,7 +28,7 @@ jobs:
         uses: aquasecurity/trivy-action@master
         with:
           scan-type: "config"
-          scan-ref: "deploy/kubernetes"
+          scan-ref: "deploy/kubernetes/ai-gateway/semantic-router"
           format: "sarif"
           output: "trivy-results.sarif"
           severity: "CRITICAL,HIGH"
@@ -43,7 +43,7 @@ jobs:
       - name: Run Checkov scan
         uses: bridgecrewio/checkov-action@master
         with:
-          directory: deploy/kubernetes
+          directory: deploy/kubernetes/ai-gateway/semantic-router
           framework: kubernetes
           output_format: cli
           soft_fail: true # Don't fail the build