ci: fix kafka scheduler, split langgraph and kafka into separate test jobs (#1677)

.github/workflows/_test.yml

@@ -21,11 +21,8 @@ jobs:
           - "3.10"
           - "3.11"
           - "3.12"
-        core-version:
-          - ">=0.3.0.dev4,<0.4.0"
-          - "latest"
 
-    name: "test #${{ matrix.python-version }} (langchain-core: ${{ matrix.core-version }})"
+    name: "test #${{ matrix.python-version }}"
     steps:
       - uses: actions/checkout@v4
       - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
@@ -41,11 +38,8 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
         run: |
           poetry install --with dev
-          if [ "${{ matrix.core-version }}" != "latest" ]; then
-            poetry run pip install "langchain-core${{ matrix.core-version }}"
-          fi
 
-      - name: Run core tests
+      - name: Run tests
         shell: bash
         working-directory: ${{ inputs.working-directory }}
         run: |

.github/workflows/_test_langgraph.yml

@@ -0,0 +1,59 @@
+name: test
+
+on:
+  workflow_call:
+
+env:
+  POETRY_VERSION: "1.7.1"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version:
+          - "3.9"
+          - "3.10"
+          - "3.11"
+          - "3.12"
+        core-version:
+          - ">=0.3.0.dev4,<0.4.0"
+          - "latest"
+
+    defaults:
+      run:
+        working-directory: libs/langgraph
+    name: "test #${{ matrix.python-version }} (langchain-core: ${{ matrix.core-version }})"
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          cache-key: test-langgraph
+
+      - name: Install dependencies
+        shell: bash
+        run: |
+          poetry install --with dev
+          if [ "${{ matrix.core-version }}" != "latest" ]; then
+            poetry run pip install "langchain-core${{ matrix.core-version }}"
+          fi
+
+      - name: Run tests
+        shell: bash
+        run: |
+          make test
+
+      - name: Ensure the tests did not create any additional files
+        shell: bash
+        run: |
+          set -eu
+
+          STATUS="$(git status)"
+          echo "$STATUS"
+
+          # grep will exit non-zero if the target message isn't found,
+          # and `set -e` above will cause the step to fail.
+          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/_test_scheduler_kafka.yml

@@ -0,0 +1,51 @@
+name: test
+
+on:
+  workflow_call:
+
+env:
+  POETRY_VERSION: "1.7.1"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version:
+          - "3.11"
+          - "3.12"
+
+    defaults:
+      run:
+        working-directory: libs/scheduler-kafka
+    name: "test #${{ matrix.python-version }}"
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          cache-key: test-scheduler-kafka
+
+      - name: Install dependencies
+        shell: bash
+        run: |
+          poetry install --with dev
+
+      - name: Run tests
+        shell: bash
+        run: |
+          make test
+
+      - name: Ensure the tests did not create any additional files
+        shell: bash
+        run: |
+          set -eu
+
+          STATUS="$(git status)"
+          echo "$STATUS"
+
+          # grep will exit non-zero if the target message isn't found,
+          # and `set -e` above will cause the step to fail.
+          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/ci.yml

@@ -44,18 +44,28 @@ jobs:
     strategy:
       matrix:
         working-directory: [
-            "libs/langgraph",
             "libs/cli",
             "libs/checkpoint",
             "libs/checkpoint-sqlite",
-            "libs/checkpoint-postgres",
-            # "libs/scheduler-kafka"
+            "libs/checkpoint-postgres"
           ]
     uses: ./.github/workflows/_test.yml
     with:
       working-directory: ${{ matrix.working-directory }}
     secrets: inherit
 
+  # NOTE: we're testing langgraph separately because it requires a different matrix
+  test-langgraph:
+    name: "cd libs/langgraph"
+    uses: ./.github/workflows/_test_langgraph.yml
+    secrets: inherit
+
+  # NOTE: we're testing scheduler-kafka separately because it requires a different matrix
+  test-scheduler-kafka:
+    name: "cd libs/scheduler-kafka"
+    uses: ./.github/workflows/_test_scheduler_kafka.yml
+    secrets: inherit
+
   integration-test:
     name: CLI integration test
     uses: ./.github/workflows/_integration_test.yml

libs/scheduler-kafka/tests/messages.py

@@ -0,0 +1,28 @@
+"""Redefined messages as a work-around for pydantic issue with AnyStr.
+
+The code below creates version of pydantic models
+that will work in unit tests with AnyStr as id field
+Please note that the `id` field is assigned AFTER the model is created
+to workaround an issue with pydantic ignoring the __eq__ method on
+subclassed strings.
+"""
+
+from typing import Any
+
+from langchain_core.messages import AIMessage, HumanMessage
+
+from tests.any import AnyStr
+
+
+def _AnyIdAIMessage(**kwargs: Any) -> AIMessage:
+    """Create ai message with an any id field."""
+    message = AIMessage(**kwargs)
+    message.id = AnyStr()
+    return message
+
+
+def _AnyIdHumanMessage(**kwargs: Any) -> HumanMessage:
+    """Create a human message with an any id field."""
+    message = HumanMessage(**kwargs)
+    message.id = AnyStr()
+    return message

libs/scheduler-kafka/tests/test_subgraph.py

@@ -5,7 +5,7 @@ from aiokafka import AIOKafkaProducer
 from langchain_core.language_models.fake_chat_models import (
     FakeMessagesListChatModel,
 )
-from langchain_core.messages import AIMessage, HumanMessage, ToolCall
+from langchain_core.messages import AIMessage, ToolCall
 from langchain_core.tools import tool
 
 from langgraph.checkpoint.base import BaseCheckpointSaver
@@ -17,6 +17,7 @@ from langgraph.scheduler.kafka import serde
 from langgraph.scheduler.kafka.types import MessageToOrchestrator, Topics
 from tests.any import AnyDict, AnyStr
 from tests.drain import drain_topics
+from tests.messages import _AnyIdAIMessage, _AnyIdHumanMessage
 
 pytestmark = pytest.mark.anyio
 
@@ -135,7 +136,7 @@ async def test_subgraph_w_interrupt(
     state = await graph.aget_state(config)
     assert state.next == ("weather_graph",)
     assert state.values == {
-        "messages": [HumanMessage(id=AnyStr(), content="what's the weather in sf")],
+        "messages": [_AnyIdHumanMessage(content="what's the weather in sf")],
         "route": "weather",
     }
 
@@ -421,8 +422,8 @@ async def test_subgraph_w_interrupt(
     assert state.next == ()
     assert state.values == {
         "messages": [
-            HumanMessage(id=AnyStr(), content="what's the weather in sf"),
-            AIMessage(content="I'ts sunny in San Francisco!", id=AnyStr()),
+            _AnyIdHumanMessage(content="what's the weather in sf"),
+            _AnyIdAIMessage(content="I'ts sunny in San Francisco!"),
         ],
         "route": "weather",
     }