feat(acp): browser control via MCP-over-ACP + stdio bridge (Phase 2) #1789
Workflow file for this run
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Docker Smoke Test | |
| on: | |
| pull_request: | |
| types: [opened, synchronize, reopened, ready_for_review] | |
| paths: | |
| - 'Dockerfile*' | |
| - 'src/**' | |
| - 'crates/**' | |
| - 'Cargo.*' | |
| concurrency: | |
| group: smoke-test-${{ github.event.pull_request.number }} | |
| cancel-in-progress: true | |
| jobs: | |
| smoke-test: | |
| if: github.event.pull_request.draft == false | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| variant: | |
| - { dockerfile: Dockerfile, suffix: "", agent: "kiro-cli", agent_args: "acp --trust-all-tools", build_args: "" } | |
| - { dockerfile: Dockerfile, suffix: "-unified", agent: "kiro-cli", agent_args: "acp --trust-all-tools", build_args: "--build-arg BUILD_MODE=unified" } | |
| - { dockerfile: Dockerfile.claude, suffix: "-claude", agent: "claude-agent-acp", agent_args: "", build_args: "" } | |
| - { dockerfile: Dockerfile.codex, suffix: "-codex", agent: "codex-acp", agent_args: "", build_args: "" } | |
| - { dockerfile: Dockerfile.gemini, suffix: "-gemini", agent: "gemini", agent_args: "--acp", build_args: "" } | |
| - { dockerfile: Dockerfile.copilot, suffix: "-copilot", agent: "copilot", agent_args: "--acp", build_args: "" } | |
| - { dockerfile: Dockerfile.opencode, suffix: "-opencode", agent: "opencode", agent_args: "acp", build_args: "" } | |
| - { dockerfile: Dockerfile.cursor, suffix: "-cursor", agent: "cursor-agent", agent_args: "acp", build_args: "" } | |
| - { dockerfile: Dockerfile.kimi, suffix: "-kimi", agent: "kimi", agent_args: "acp", build_args: "" } | |
| - { dockerfile: Dockerfile.mimocode, suffix: "-mimocode", agent: "mimo", agent_args: "acp", build_args: "" } | |
| - { dockerfile: Dockerfile.hermes, suffix: "-hermes", agent: "hermes-acp", agent_args: "", build_args: "" } | |
| - { dockerfile: Dockerfile.grok, suffix: "-grok", agent: "grok", agent_args: "agent stdio", build_args: "" } | |
| - { dockerfile: Dockerfile.devin, suffix: "-devin", agent: "devin", agent_args: "acp", build_args: "" } | |
| - { dockerfile: Dockerfile.antigravity, suffix: "-antigravity", agent: "agy-acp", agent_args: "", build_args: "" } | |
| - { dockerfile: Dockerfile.pi, suffix: "-pi", agent: "pi-acp", agent_args: "", build_args: "" } | |
| - { dockerfile: openshell/Dockerfile, suffix: "-native-sandbox", agent: "openab-agent", agent_args: "", build_args: "" } | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v6 | |
| - name: Build image | |
| run: docker build ${{ matrix.variant.build_args }} -t openab-test${{ matrix.variant.suffix }} -f ${{ matrix.variant.dockerfile }} . | |
| - name: Verify openab CMD does not crash | |
| run: | | |
| OUTPUT=$(docker run --rm openab-test${{ matrix.variant.suffix }} 2>&1 || true) | |
| if echo "$OUTPUT" | grep -q "unrecognized subcommand"; then | |
| echo "❌ CMD regression: $OUTPUT" | |
| exit 1 | |
| fi | |
| echo "✅ openab CMD ok" | |
| - name: Verify agent CLI exists | |
| run: docker run --rm --entrypoint which openab-test${{ matrix.variant.suffix }} ${{ matrix.variant.agent }} | |
| - name: Verify Codex runtime versions | |
| if: matrix.variant.suffix == '-codex' | |
| run: | | |
| # Expected versions come from the Dockerfile ARG defaults (single | |
| # source of truth) so a version bump only touches the Dockerfiles. | |
| CODEX_ACP_VERSION=$(awk -F= '$1 == "ARG CODEX_ACP_VERSION" {print $2; exit}' Dockerfile.codex) | |
| CODEX_VERSION=$(awk -F= '$1 == "ARG CODEX_VERSION" {print $2; exit}' Dockerfile.codex) | |
| test -n "$CODEX_ACP_VERSION" && test -n "$CODEX_VERSION" | |
| docker run --rm --entrypoint codex-acp openab-test-codex --version \ | |
| | grep -F "@agentclientprotocol/codex-acp ${CODEX_ACP_VERSION}" | |
| docker run --rm --entrypoint codex openab-test-codex --version \ | |
| | grep -F "codex-cli ${CODEX_VERSION}" | |
| - name: Verify Codex agent command is a single token | |
| if: matrix.variant.suffix == '-codex' | |
| run: | | |
| # Regression guard: OPENAB_AGENT_COMMAND must stay a plain binary. | |
| # Packing env-var prefixes (e.g. "/usr/bin/env K=V codex-acp") breaks | |
| # configs that override [agent].args only — OAB keeps token 1 as the | |
| # command and replaces the rest, yielding "/usr/bin/env <user args>". | |
| docker inspect --format '{{range .Config.Env}}{{println .}}{{end}}' openab-test-codex \ | |
| | grep -Fx 'OPENAB_AGENT_COMMAND=codex-acp' | |
| - name: Verify bumped runtime versions | |
| if: matrix.variant.suffix == '' || matrix.variant.suffix == '-unified' || matrix.variant.suffix == '-copilot' || matrix.variant.suffix == '-devin' || matrix.variant.suffix == '-antigravity' | |
| shell: bash | |
| run: | | |
| set -euo pipefail | |
| case "${{ matrix.variant.suffix }}" in | |
| ''|-unified) | |
| expected=$(awk -F= '$1 == "ARG KIRO_CLI_VERSION" {print $2; exit}' Dockerfile) | |
| test -n "$expected" || { echo "❌ Failed to extract Kiro expected version"; exit 1; } | |
| docker run --rm --entrypoint kiro-cli openab-test${{ matrix.variant.suffix }} --version \ | |
| | grep -Fx "kiro-cli $expected" | |
| ;; | |
| -copilot) | |
| expected=$(awk -F= '$1 == "ARG COPILOT_VERSION" {print $2; exit}' Dockerfile.copilot) | |
| test -n "$expected" || { echo "❌ Failed to extract Copilot expected version"; exit 1; } | |
| docker run --rm --entrypoint sh openab-test-copilot \ | |
| -c 'NODE_PATH=$(npm root -g) node -e "process.stdout.write(require(\"@github/copilot/package.json\").version)"' \ | |
| | grep -Fx "$expected" | |
| ;; | |
| -devin) | |
| expected=$(awk -F= '$1 == "ARG DEVIN_VERSION" {print $2; exit}' Dockerfile.devin) | |
| test -n "$expected" || { echo "❌ Failed to extract Devin expected version"; exit 1; } | |
| docker run --rm --entrypoint devin openab-test-devin --version \ | |
| | grep -F "$expected" | |
| ;; | |
| -antigravity) | |
| expected=$(awk -F= '$1 == "ENV AGY_VERSION" {print $2; exit}' Dockerfile.antigravity) | |
| test -n "$expected" || { echo "❌ Failed to extract Antigravity expected version"; exit 1; } | |
| docker run --rm --entrypoint agy openab-test-antigravity --version \ | |
| | grep -F "$expected" | |
| ;; | |
| esac | |
| - name: Verify agent responds | |
| run: | | |
| if [ "${{ matrix.variant.suffix }}" = "-codex" ]; then | |
| INIT='{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":1,"clientCapabilities":{},"clientInfo":{"name":"ci-test","version":"0.0.1"}}}' | |
| else | |
| INIT='{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","clientCapabilities":{},"clientInfo":{"name":"ci-test","version":"0.0.1"}}}' | |
| fi | |
| # Start agent in background, send init, capture output with timeout | |
| CID=$(docker run -d -i --entrypoint sh openab-test${{ matrix.variant.suffix }} -c 'exec ${{ matrix.variant.agent }} ${{ matrix.variant.agent_args }} 2>/dev/null') | |
| echo "$INIT" | docker attach --no-stdin=false "$CID" & | |
| sleep 5 | |
| RESPONSE=$(docker logs "$CID" 2>/dev/null | grep -m1 '^{' || true) | |
| docker rm -f "$CID" >/dev/null 2>&1 | |
| echo "Response: $RESPONSE" | |
| if [ -n "$RESPONSE" ] && echo "$RESPONSE" | jq -e '.result.agentInfo.name' > /dev/null 2>&1; then | |
| AGENT_NAME=$(echo "$RESPONSE" | jq -r '.result.agentInfo.name') | |
| echo "✅ ACP handshake ok — agent=$AGENT_NAME" | |
| elif [ "${{ matrix.variant.suffix }}" = "-codex" ]; then | |
| echo "❌ Codex ACP handshake failed" | |
| exit 1 | |
| else | |
| echo "⚠️ ACP handshake returned no response — falling back to CLI check" | |
| docker run --rm --entrypoint ${{ matrix.variant.agent }} \ | |
| openab-test${{ matrix.variant.suffix }} --help >/dev/null 2>&1 | |
| echo "✅ Agent CLI responds (ACP skipped — likely needs auth)" | |
| fi | |
| validate-packaged-pins: | |
| if: github.event.pull_request.draft == false | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v6 | |
| - name: Validate package and legacy pin parity | |
| shell: bash | |
| run: | | |
| set -euo pipefail | |
| assert_line() { | |
| local expected="$1" | |
| shift | |
| for file in "$@"; do | |
| grep -Fx "$expected" "$file" | |
| done | |
| } | |
| assert_line 'ARG KIRO_CLI_VERSION=2.13.0' Dockerfile Dockerfile.package Dockerfile.unified | |
| assert_line 'ARG KIRO_SHA256_AMD64=d8c5277358b4a82b2d9a9ed2d52e110862536dc82b9e32c3719fc5f5a9834c94' Dockerfile Dockerfile.package Dockerfile.unified | |
| assert_line 'ARG KIRO_SHA256_ARM64=95972602568c2065b7d8cc28924730304d40e612c0984ee0144d8ba452000be3' Dockerfile Dockerfile.package Dockerfile.unified | |
| assert_line 'ARG CODEX_ACP_VERSION=1.1.4' Dockerfile.codex Dockerfile.package Dockerfile.unified | |
| assert_line 'ARG CODEX_VERSION=0.144.1' Dockerfile.codex Dockerfile.package Dockerfile.unified | |
| assert_line 'ARG COPILOT_VERSION=1.0.71' Dockerfile.copilot Dockerfile.package Dockerfile.unified | |
| assert_line 'ARG DEVIN_VERSION=3000.2.17' Dockerfile.devin Dockerfile.package Dockerfile.unified | |
| assert_line 'ARG DEVIN_SHA256_AMD64=f0e1e9363afc6ee68c4ef87bab4aeb7ff5cc08a5fa838350ef3ceefdbb2a2be2' Dockerfile.devin Dockerfile.package Dockerfile.unified | |
| assert_line 'ARG DEVIN_SHA256_ARM64=116dc71ef085a922bc3ff0ea0377d4b26c529a431d58246e36572913e2d25624' Dockerfile.devin Dockerfile.package Dockerfile.unified | |
| assert_line 'ENV AGY_VERSION=1.1.4' Dockerfile.antigravity Dockerfile.package Dockerfile.unified Dockerfile.final Dockerfile.ci | |
| assert_line 'ARG AGY_SHA256_AMD64=aaab42e395cb4e3bfe5ae88994a340865d949f7a9e7f0604ffa2a3f1e8aadbfa' Dockerfile.antigravity Dockerfile.package Dockerfile.unified Dockerfile.final Dockerfile.ci | |
| assert_line 'ARG AGY_SHA256_ARM64=333199327cc29e21cb8fcc4e19f7c02c462bf41dd876f1328d64e9922c631700' Dockerfile.antigravity Dockerfile.package Dockerfile.unified Dockerfile.final Dockerfile.ci |