Resolve ai-service directly from the RAG routes, never the gateway

2026-08-19 10:16:44 +07:00
parent f50ccfc5f7
commit 24c55d1627
13 changed files with 470 additions and 22 deletions
@@ -97,6 +97,26 @@ jobs:
      - name: Install
        run: pnpm install --frozen-lockfile

+      # api-gateway proxies /auth/* and nothing else (a single
+      # AuthProxyController). Preferring API_GATEWAY_URL in a RAG route
+      # therefore breaks chat, suggest, history, sections, section-text and
+      # feedback the moment apiGateway is enabled -- which is exactly what
+      # shipped in PR #27 and stayed invisible until the config was first
+      # rendered on 2026-08-19. Nothing else in CI would have caught it: the
+      # code compiles and lints fine, and it only misbehaves once a specific
+      # Helm value is set. Assert the boundary directly.
+      - name: Assert RAG routes never resolve through api-gateway
+        run: |
+          offenders=$(grep -rln 'API_GATEWAY_URL'             apps/web/app/api/chat             apps/web/app/api/suggest             apps/web/app/api/history             apps/web/app/api/sections             apps/web/app/api/section-text             apps/web/app/api/feedback || true)
+          if [ -n "$offenders" ]; then
+            echo "::error::RAG routes must use AI_SERVICE_URL, not API_GATEWAY_URL: $offenders"
+            exit 1
+          fi
+          # ...and auth must keep using it, or login silently talks to the
+          # wrong service instead.
+          grep -q 'API_GATEWAY_URL' apps/web/app/api/auth/login/route.ts
+          grep -q 'API_GATEWAY_URL' apps/web/app/api/auth/me/route.ts
+
      - name: Lint
        run: pnpm --filter @duoc-thu/web lint

@@ -0,0 +1,22 @@
+name: Disable apiGateway on production (restore chat)
+
+# Emergency: enabling apiGateway sets API_GATEWAY_URL on the web pod, which
+# every BFF route prefers over AI_SERVICE_URL -- but the gateway only proxies
+# /auth/*, so chat/suggest/history/sections/section-text/feedback all break.
+# See the script docstring for the full trace.
+
+on:
+  workflow_dispatch: {}
+
+jobs:
+  disable:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    steps:
+      - uses: actions/checkout@v4
+      - name: Disable apiGateway and sync
+        env:
+          ARGOCD_PRACTICE_URL: ${{ secrets.ARGOCD_PRACTICE_URL }}
+          ARGOCD_PRACTICE_PASSWORD: ${{ secrets.ARGOCD_PRACTICE_PASSWORD }}
+        run: python3 .github/scripts/disable_api_gateway_live.py
@@ -0,0 +1,23 @@
+name: Repair ArgoCD inline values
+
+# One-off repair for the folded-block-scalar corruption a manual UI edit left
+# on medical-chatbot-app's inline helm values on 2026-08-18 -- see the module
+# docstring in .github/scripts/repair_argocd_inline_values.py for the full
+# diagnosis. The script refuses to write unless it finds that exact
+# corruption, so running it once the Application is healthy is a no-op.
+
+on:
+  workflow_dispatch: {}
+
+jobs:
+  repair:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    steps:
+      - uses: actions/checkout@v4
+      - name: Repair and sync
+        env:
+          ARGOCD_PRACTICE_URL: ${{ secrets.ARGOCD_PRACTICE_URL }}
+          ARGOCD_PRACTICE_PASSWORD: ${{ secrets.ARGOCD_PRACTICE_PASSWORD }}
+        run: python3 .github/scripts/repair_argocd_inline_values.py