merge(main): sync trace timing PR

Signed-off-by: Carlos Villela <cvillela@nvidia.com>

Author: cv

.github/workflows/brev-nightly-e2e.yaml

@@ -49,4 +49,4 @@ jobs:
     secrets:
       BREV_API_KEY: ${{ secrets.BREV_API_KEY }}
       BREV_ORG_ID: ${{ secrets.BREV_ORG_ID }}
-      NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
+      NVIDIA_INFERENCE_API_KEY: ${{ secrets.NVIDIA_INFERENCE_API_KEY }}

.github/workflows/e2e-branch-validation.yaml

@@ -48,7 +48,7 @@ name: E2E / Branch Validation
 #   all                      — Runs credential-sanitization + telegram-injection (NOT full,
 #                              which destroys the sandbox the security tests need).
 #
-# Required secrets: BREV_API_KEY + BREV_ORG_ID (or legacy BREV_API_TOKEN), NVIDIA_API_KEY
+# Required secrets: BREV_API_KEY + BREV_ORG_ID (or legacy BREV_API_TOKEN), NVIDIA_INFERENCE_API_KEY
 # Instance cost: Brev CPU credits (~$0.10/run for 4x16 instance)
 
 on:
@@ -157,7 +157,7 @@ on:
         required: false
       BREV_ORG_ID:
         required: false
-      NVIDIA_API_KEY:
+      NVIDIA_INFERENCE_API_KEY:
         required: true
 
 permissions:
@@ -253,7 +253,7 @@ jobs:
         env:
           NEMOCLAW_RUN_BRANCH_VALIDATION_E2E: "1"
           BREV_API_TOKEN: ${{ inputs.brev_token || secrets.BREV_API_TOKEN }}
-          NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
+          NVIDIA_INFERENCE_API_KEY: ${{ secrets.NVIDIA_INFERENCE_API_KEY }}
           GITHUB_TOKEN: ${{ github.token }}
           INSTANCE_NAME: ${{ env.BREV_E2E_INSTANCE_NAME }}
           TEST_SUITE: ${{ inputs.test_suite }}

.github/workflows/e2e-script.yaml

@@ -58,7 +58,12 @@ on:
         type: string
         default: ""
       nvidia_api_key:
-        description: Pass the NVIDIA_API_KEY secret to the script.
+        description: Pass the NVIDIA_INFERENCE_API_KEY secret to the script.
+        required: false
+        type: boolean
+        default: false
+      nvidia_secret_as_compatible_api_key:
+        description: Expose NVIDIA_INFERENCE_API_KEY as COMPATIBLE_API_KEY for CI-only OpenAI-compatible inference.
         required: false
         type: boolean
         default: false
@@ -78,7 +83,7 @@ on:
         type: boolean
         default: false
     secrets:
-      NVIDIA_API_KEY:
+      NVIDIA_INFERENCE_API_KEY:
         required: false
       BRAVE_API_KEY:
         required: false
@@ -212,6 +217,28 @@ jobs:
             echo "::warning::Docker Hub login failed after 3 attempts; continuing with anonymous pulls."
           fi
 
+      - name: Export CI compatible inference environment
+        if: ${{ inputs.nvidia_secret_as_compatible_api_key }}
+        env:
+          NVIDIA_INFERENCE_API_KEY: ${{ secrets.NVIDIA_INFERENCE_API_KEY }}
+        shell: bash
+        run: |
+          set -euo pipefail
+
+          if [ -z "${NVIDIA_INFERENCE_API_KEY:-}" ]; then
+            echo "::error::NVIDIA_INFERENCE_API_KEY secret is required for CI compatible inference." >&2
+            exit 1
+          fi
+
+          {
+            printf 'NEMOCLAW_E2E_USE_NVIDIA_SECRET_AS_COMPATIBLE=1\n'
+            printf 'NEMOCLAW_PROVIDER=custom\n'
+            printf 'NEMOCLAW_ENDPOINT_URL=https://inference-api.nvidia.com/v1\n'
+            printf 'NEMOCLAW_MODEL=nvidia/nvidia/nemotron-3-super-v3\n'
+            printf 'NEMOCLAW_COMPAT_MODEL=nvidia/nvidia/nemotron-3-super-v3\n'
+            printf 'COMPATIBLE_API_KEY=%s\n' "${NVIDIA_INFERENCE_API_KEY}"
+          } >> "$GITHUB_ENV"
+
       - name: Run E2E script
         uses: ./workflow-actions/.github/actions/run-e2e-script
         with:
@@ -225,7 +252,7 @@ jobs:
         env:
           BRAVE_API_KEY: ${{ inputs.brave_api_key && secrets.BRAVE_API_KEY || '' }}
           GITHUB_TOKEN: ${{ inputs.github_token && github.token || '' }}
-          NVIDIA_API_KEY: ${{ inputs.nvidia_api_key && secrets.NVIDIA_API_KEY || '' }}
+          NVIDIA_INFERENCE_API_KEY: ${{ inputs.nvidia_api_key && secrets.NVIDIA_INFERENCE_API_KEY || '' }}
           TELEGRAM_BOT_TOKEN_REAL: ${{ inputs.messaging_live_secrets && secrets.TELEGRAM_BOT_TOKEN_REAL || '' }}
           TELEGRAM_CHAT_ID_E2E: ${{ inputs.messaging_live_secrets && secrets.TELEGRAM_CHAT_ID_E2E || '' }}
           DISCORD_BOT_TOKEN_REAL: ${{ inputs.messaging_live_secrets && secrets.DISCORD_BOT_TOKEN_REAL || '' }}