Merge pull request #1 from Mike-Jenkins-Org/copilot/help-with-issue

Fix linux-portable mode: install codex/claude in VM guest via cloud-init and switch CI to Blacksmith

Author: mjenkinsx9

.github/workflows/ci.yml

@@ -12,7 +12,7 @@ permissions:
 
 jobs:
   portable-ci:
-    runs-on: depot-ubuntu-24.04
+    runs-on: blacksmith-2vcpu-ubuntu-2404
     steps:
       - name: Checkout
         uses: actions/checkout@v4

.github/workflows/claude-pr-runner.yml

@@ -30,7 +30,7 @@ jobs:
        contains(github.event.comment.body, '@claude')) ||
       (github.event_name == 'pull_request_review' &&
        contains(github.event.review.body, '@claude'))
-    runs-on: depot-ubuntu-24.04
+    runs-on: blacksmith-2vcpu-ubuntu-2404
     steps:
       - name: Checkout
         uses: actions/checkout@v4

README.md

@@ -40,12 +40,12 @@ Windows smoke test:
 
 ## CI
 - GitHub Actions workflow: `.github/workflows/ci.yml`
-- Runner target: Depot-hosted runner label `depot-ubuntu-24.04`
+- Runner target: Blacksmith runner label `blacksmith-2vcpu-ubuntu-2404`
 
 ## Claude PR Runner
 - Workflow: `.github/workflows/claude-pr-runner.yml`
 - Trigger: mention `@claude` in PR comments/reviews (or run manually via `workflow_dispatch`)
-- Runner target: Depot-hosted runner label `depot-ubuntu-24.04`
+- Runner target: Blacksmith runner label `blacksmith-2vcpu-ubuntu-2404`
 - Configure one auth secret:
   - `ANTHROPIC_API_KEY` (API key mode), or
   - `CLAUDE_CODE_OAUTH_TOKEN` (OAuth mode)

docs/RUNBOOKS.md

@@ -58,9 +58,15 @@ Backend spec:
 ## Linux-Portable Run Flow
 1. `pcoder` starts/ensures VM via `start-vm.cmd`.
 2. VM launcher attempts WHPX acceleration, then auto-fallback to TCG.
-3. Project is copied into guest over SCP.
-4. Tool command runs over SSH in guest project directory.
-5. Project is copied back to host after run (unless `--no-sync-back`).
+3. On first boot, cloud-init installs Node.js, `codex`, and `claude` CLI tools (may take several minutes).
+4. `pcoder run` waits for cloud-init to complete before running the tool.
+5. Project is copied into guest over SCP.
+6. Tool command runs over SSH in guest project directory.
+7. Project is copied back to host after run (unless `--no-sync-back`).
+
+**First-boot note:** The first time you boot the VM, cloud-init provisions the guest (creates the `portable` user, installs Node.js and the coding CLI tools). This can take 5–15 minutes depending on network speed and host performance. `pcoder run` automatically waits for cloud-init to finish before launching the tool. Subsequent boots skip provisioning and start much faster.
+
+**Smoke check with tool checks:** Run `scripts/runtime/windows/smoke-check.cmd` after the first boot completes to verify that `codex` and `claude` are installed in the guest. Use `-SkipToolChecks` to skip tool presence checks if only testing VM boot and SSH connectivity.
 
 Acceleration override (Windows troubleshooting):
 - `PCODER_VM_ACCEL_MODE=auto` (default): try WHPX then fallback to TCG if launch fails.

runtime/linux/cloud-init/user-data

@@ -1,8 +1,18 @@
 #cloud-config
 users:
   - name: portable
-    sudo: ALL=(ALL) NOPASSWD:ALL
     shell: /bin/bash
+    sudo: ALL=(ALL) NOPASSWD:ALL
+    lock_passwd: true
+    groups:
+      - sudo
+    ssh_authorized_keys:
+      - <SSH_PUBLIC_KEY_PLACEHOLDER>
 ssh_pwauth: false
 
-# Placeholder for VM provisioning during image bake.
+packages:
+  - nodejs
+  - npm
+
+runcmd:
+  - npm install -g @openai/codex @anthropic-ai/claude-code

scripts/pcoder.cjs

@@ -1258,6 +1258,18 @@ function buildRemoteRunScript(options) {
 
   const lines = [
     'set -e',
+    'if command -v cloud-init >/dev/null 2>&1; then',
+    '  _ci_to=${PCODER_CLOUD_INIT_TIMEOUT:-900}',
+    '  if ! timeout "$_ci_to" cloud-init status --wait 2>/dev/null; then',
+    '    _ci_rc=$?',
+    '    if [ "$_ci_rc" -eq 124 ]; then',
+    '      echo "pcoder: cloud-init wait exceeded ${_ci_to}s; provisioning may be incomplete" >&2',
+    '    else',
+    '      echo "pcoder: cloud-init finished with errors (exit ${_ci_rc}); provisioning may have failed" >&2',
+    '    fi',
+    '    exit 1',
+    '  fi',
+    'fi',
     `cd ${shellEscape(remoteProjectPath)}`
   ];
 

scripts/runtime/windows/start-vm.ps1

@@ -106,6 +106,13 @@ users:
     ssh_authorized_keys:
       - $PublicKey
 ssh_pwauth: false
+
+packages:
+  - nodejs
+  - npm
+
+runcmd:
+  - npm install -g @openai/codex @anthropic-ai/claude-code
 "@
   $userData | Out-File -Encoding utf8 -FilePath $cloudInitUserDataPath
 }