(enh) add caching@v4 action in workflows (#3780)

* dummy test change

* regen yml: 1st install python 3.11, then poetry

* fix caching for poetry; old entry for python was rather useless

* fix steps order (cache before poetry)

* add poetry caching to ghcr_runtime; fix fork conditions

* ghcr_runtime: more caching actions; condition fixes

* fix interim action error (order of steps)

* cache@v4 instead of v3

* fixed interim typo for 2 fork conditions

* runtime/test_env_vars: compacted multiple tests into one to reduce time

* ugh if fork condition changes again

.github/workflows/ghcr_runtime.yml

@@ -38,10 +38,6 @@ jobs:
         base_image:
           - image: 'nikolaik/python-nodejs:python3.11-nodejs22'
             tag: nikolaik
-          - image: 'python:3.11-bookworm'
-            tag: python
-          - image: 'node:22-bookworm'
-            tag: node
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -70,31 +66,39 @@ jobs:
       - name: Set up Docker Buildx
         id: buildx
         uses: docker/setup-buildx-action@v3
-      - name: Install poetry via pipx
-        run: pipx install poetry
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
           python-version: '3.11'
-          cache: 'poetry'
+      - name: Cache Poetry dependencies
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.virtualenvs
+          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-poetry-
+      - name: Install poetry via pipx
+        run: pipx install poetry
       - name: Install Python dependencies using Poetry
         run: make install-python-dependencies
       - name: Create source distribution and Dockerfile
         run: poetry run python3 openhands/runtime/utils/runtime_build.py --base_image ${{ matrix.base_image.image }} --build_folder containers/runtime --force_rebuild
       - name: Build and push runtime image ${{ matrix.base_image.image }}
-        if: "!github.event.pull_request.head.repo.fork"
+        if: github.event.pull_request.head.repo.fork != true
         run: |
           ./containers/build.sh runtime ${{ github.repository_owner }} --push ${{ matrix.base_image.tag }}
       # Forked repos can't push to GHCR, so we need to upload the image as an artifact
       - name: Build runtime image ${{ matrix.base_image.image }} for fork
-        if: "github.event.pull_request.head.repo.fork"
+        if: github.event.pull_request.head.repo.fork
         uses: docker/build-push-action@v6
         with:
           tags: ghcr.io/all-hands-ai/runtime:${{ github.sha }}-${{ matrix.base_image.tag }}
           outputs: type=docker,dest=/tmp/runtime-${{ matrix.base_image.tag }}.tar
           context: containers/runtime
       - name: Upload runtime image for fork
-        if: "github.event.pull_request.head.repo.fork"
+        if: github.event.pull_request.head.repo.fork != true
         uses: actions/upload-artifact@v4
         with:
           name: runtime-${{ matrix.base_image.tag }}
@@ -107,7 +111,7 @@ jobs:
     needs: [ghcr_build_runtime]
     strategy:
       matrix:
-        base_image: ['nikolaik', 'python', 'node']
+        base_image: ['nikolaik']
     steps:
       - uses: actions/checkout@v4
       - name: Free Disk Space (Ubuntu)
@@ -121,22 +125,30 @@ jobs:
           swap-storage: true
       # Forked repos can't push to GHCR, so we need to download the image as an artifact
       - name: Download runtime image for fork
-        if: "github.event.pull_request.head.repo.fork"
+        if: github.event.pull_request.head.repo.fork
         uses: actions/download-artifact@v4
         with:
           name: runtime-${{ matrix.base_image }}
           path: /tmp
       - name: Load runtime image for fork
-        if: "github.event.pull_request.head.repo.fork"
+        if: github.event.pull_request.head.repo.fork
         run: |
           docker load --input /tmp/runtime-${{ matrix.base_image }}.tar
-      - name: Install poetry via pipx
+      - name: Cache Poetry dependencies
-        run: pipx install poetry
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.virtualenvs
+          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-poetry-
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
           python-version: '3.11'
-          cache: 'poetry'
+      - name: Install poetry via pipx
+        run: pipx install poetry
       - name: Install Python dependencies using Poetry
         run: make install-python-dependencies
       - name: Run runtime tests
@@ -162,27 +174,35 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        base_image: ['nikolaik', 'python', 'node']
+        base_image: ['nikolaik']
     steps:
       - uses: actions/checkout@v4
       # Forked repos can't push to GHCR, so we need to download the image as an artifact
       - name: Download runtime image for fork
-        if: "github.event.pull_request.head.repo.fork"
+        if: github.event.pull_request.head.repo.fork
         uses: actions/download-artifact@v4
         with:
           name: runtime-${{ matrix.base_image }}
           path: /tmp
       - name: Load runtime image for fork
-        if: "github.event.pull_request.head.repo.fork"
+        if: github.event.pull_request.head.repo.fork
         run: |
           docker load --input /tmp/runtime-${{ matrix.base_image }}.tar
-      - name: Install poetry via pipx
+      - name: Cache Poetry dependencies
-        run: pipx install poetry
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.virtualenvs
+          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-poetry-
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
           python-version: '3.11'
-          cache: 'poetry'
+      - name: Install poetry via pipx
+        run: pipx install poetry
       - name: Install Python dependencies using Poetry
         run: make install-python-dependencies
       - name: Run integration tests

.github/workflows/py-unit-tests.yml

@@ -22,13 +22,21 @@ jobs:
         python-version: ['3.11']
     steps:
       - uses: actions/checkout@v4
-      - name: Install poetry via pipx
-        run: pipx install poetry
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-          cache: 'poetry'
+      - name: Cache Poetry dependencies
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.virtualenvs
+          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-poetry-
+      - name: Install poetry via pipx
+        run: pipx install poetry
       - name: Install Python dependencies using Poetry
         run: poetry install --without evaluation,llama-index
       - name: Install & Start Docker

.github/workflows/regenerate_integration_tests.yml

@@ -29,18 +29,25 @@ jobs:
     steps:
     - name: Checkout repository
       uses: actions/checkout@v4
-    - name: Install poetry via pipx
-      run: pipx install poetry
     - name: Set up Python
       uses: actions/setup-python@v5
       with:
         python-version: "3.11"
-        cache: 'poetry'
+    - name: Cache Poetry dependencies
+      uses: actions/cache@v4
+      with:
+        path: |
+          ~/.cache/pypoetry
+          ~/.virtualenvs
+        key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
+        restore-keys: |
+          ${{ runner.os }}-poetry-
+    - name: Install poetry via pipx
+      run: pipx install poetry
     - name: Install Python dependencies using Poetry
-      run: poetry install --without evaluation,llama-index
+      run: make install-python-dependencies
     - name: Build Environment
       run: make build
-
     - name: Regenerate integration tests
       run: |
         DEBUG=${{ inputs.debug }} \
@@ -48,7 +55,6 @@ jobs:
         FORCE_REGENERATE_TESTS=${{ inputs.force_regenerate_tests }} \
         FORCE_USE_LLM=${{ inputs.force_use_llm }} \
         ./tests/integration/regenerate.sh
-
     - name: Commit changes
       run: |
         if git diff --quiet --exit-code; then

openhands/runtime/client/runtime.py

@@ -165,7 +165,7 @@ class EventStreamRuntime(Runtime):
             return docker.from_env()
         except Exception as ex:
             logger.error(
-                'Launch docker client failed. Please make sure you have installed docker and started the docker daemon.'
+                'Launch docker client failed. Please make sure you have installed docker and started docker desktop/daemon.'
             )
             raise ex
 

tests/runtime/test_env_vars.py

@@ -34,71 +34,37 @@ def test_env_vars_os_environ(temp_dir, box_class, run_as_openhands):
         time.sleep(1)
 
 
-def test_env_vars_runtime_add_env_vars(temp_dir, box_class):
+def test_env_vars_runtime_operations(temp_dir, box_class):
     runtime = _load_runtime(temp_dir, box_class)
+
+    # Test adding single env var
     runtime.add_env_vars({'QUUX': 'abc"def'})
-
+    obs = runtime.run_action(CmdRunAction(command='echo $QUUX'))
-    obs: CmdOutputObservation = runtime.run_action(CmdRunAction(command='echo $QUUX'))
-    print(obs)
-    assert obs.exit_code == 0, 'The exit code should be 0.'
     assert (
-        obs.content.strip().split('\r\n')[0].strip() == 'abc"def'
+        obs.exit_code == 0 and obs.content.strip().split('\r\n')[0].strip() == 'abc"def'
-    ), f'Output: [{obs.content}] for {box_class}'
-
-    runtime.close()
-    time.sleep(1)
-
-
-def test_env_vars_runtime_add_empty_dict(temp_dir, box_class):
-    runtime = _load_runtime(temp_dir, box_class)
-
-    prev_obs = runtime.run_action(CmdRunAction(command='env'))
-    assert prev_obs.exit_code == 0, 'The exit code should be 0.'
-    print(prev_obs)
-
-    runtime.add_env_vars({})
-
-    obs = runtime.run_action(CmdRunAction(command='env'))
-    assert obs.exit_code == 0, 'The exit code should be 0.'
-    print(obs)
-    assert (
-        obs.content == prev_obs.content
-    ), 'The env var content should be the same after adding an empty dict.'
-
-    runtime.close()
-    time.sleep(1)
-
-
-def test_env_vars_runtime_add_multiple_env_vars(temp_dir, box_class):
-    runtime = _load_runtime(temp_dir, box_class)
-    runtime.add_env_vars({'QUUX': 'abc"def', 'FOOBAR': 'xyz'})
-
-    obs: CmdOutputObservation = runtime.run_action(
-        CmdRunAction(command='echo $QUUX $FOOBAR')
     )
-    print(obs)
+
-    assert obs.exit_code == 0, 'The exit code should be 0.'
+    # Test adding multiple env vars
+    runtime.add_env_vars({'FOOBAR': 'xyz'})
+    obs = runtime.run_action(CmdRunAction(command='echo $QUUX $FOOBAR'))
     assert (
-        obs.content.strip().split('\r\n')[0].strip() == 'abc"def xyz'
+        obs.exit_code == 0
-    ), f'Output: [{obs.content}] for {box_class}'
+        and obs.content.strip().split('\r\n')[0].strip() == 'abc"def xyz'
+    )
+
+    # Test adding empty dict
+    prev_env = runtime.run_action(CmdRunAction(command='env')).content
+    runtime.add_env_vars({})
+    current_env = runtime.run_action(CmdRunAction(command='env')).content
+    assert prev_env == current_env
+
+    # Test overwriting env vars
+    runtime.add_env_vars({'QUUX': 'new_value'})
+    obs = runtime.run_action(CmdRunAction(command='echo $QUUX'))
+    assert (
+        obs.exit_code == 0
+        and obs.content.strip().split('\r\n')[0].strip() == 'new_value'
+    )
 
     runtime.close()
     time.sleep(1)
-
-
-def test_env_vars_runtime_add_env_vars_overwrite(temp_dir, box_class):
-    with patch.dict(os.environ, {'SANDBOX_ENV_FOOBAR': 'BAZ'}):
-        runtime = _load_runtime(temp_dir, box_class)
-        runtime.add_env_vars({'FOOBAR': 'xyz'})
-
-        obs: CmdOutputObservation = runtime.run_action(
-            CmdRunAction(command='echo $FOOBAR')
-        )
-        print(obs)
-        assert obs.exit_code == 0, 'The exit code should be 0.'
-        assert (
-            obs.content.strip().split('\r\n')[0].strip() == 'xyz'
-        ), f'Output: [{obs.content}] for {box_class}'
-
-        runtime.close()
-        time.sleep(1)