From 9de562f747cd02525c7467d6d6b5a0bfeae9e1ee Mon Sep 17 00:00:00 2001
From: Erick Friis <erick@langchain.dev>
Date: Thu, 11 Jul 2024 00:45:18 +0200
Subject: [PATCH] infra: create individual jobs in check_diff, do max milvus
 testing in 3.11 (#23829)

pickup from #23721
---
 .github/scripts/check_diff.py                 | 66 ++++++++++++---
 .../workflows/_compile_integration_test.yml   | 10 ++-
 .github/workflows/_dependencies.yml           | 18 ++--
 .github/workflows/_integration_test.yml       | 15 ++--
 .github/workflows/_lint.yml                   | 26 ++----
 .github/workflows/_test.yml                   | 18 ++--
 .github/workflows/_test_doc_imports.yml       | 11 ++-
 .github/workflows/check_diffs.yml             | 83 ++++++++++---------
 8 files changed, 144 insertions(+), 103 deletions(-)

diff --git a/.github/scripts/check_diff.py b/.github/scripts/check_diff.py
index ed0cab169cd..c3b25593037 100644
--- a/.github/scripts/check_diff.py
+++ b/.github/scripts/check_diff.py
@@ -53,6 +53,44 @@ def add_dependents(dirs_to_eval: Set[str], dependents: dict) -> List[str]:
     return list(updated)
 
 
+def _get_configs_for_single_dir(job: str, dir_: str) -> List[Dict[str, str]]:
+    min_python = "3.8"
+    max_python = "3.12"
+
+    # custom logic for specific directories
+    if dir_ == "libs/partners/milvus":
+        # milvus poetry doesn't allow 3.12 because they
+        # declare deps in funny way
+        max_python = "3.11"
+
+    return [
+        {"working-directory": dir_, "python-version": min_python},
+        {"working-directory": dir_, "python-version": max_python},
+    ]
+
+
+def _get_configs_for_multi_dirs(
+    job: str, dirs_to_run: List[str], dependents: dict
+) -> List[Dict[str, str]]:
+    if job == "lint":
+        dirs = add_dependents(
+            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"],
+            dependents,
+        )
+    elif job in ["test", "compile-integration-tests", "dependencies"]:
+        dirs = add_dependents(
+            dirs_to_run["test"] | dirs_to_run["extended-test"], dependents
+        )
+    elif job == "extended-tests":
+        dirs = list(dirs_to_run["extended-test"])
+    else:
+        raise ValueError(f"Unknown job: {job}")
+
+    return [
+        config for dir_ in dirs for config in _get_configs_for_single_dir(job, dir_)
+    ]
+
+
 if __name__ == "__main__":
     files = sys.argv[1:]
 
@@ -126,17 +164,23 @@ if __name__ == "__main__":
 
     dependents = dependents_graph()
 
-    outputs = {
-        "dirs-to-lint": add_dependents(
-            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"],
-            dependents,
-        ),
-        "dirs-to-test": add_dependents(
-            dirs_to_run["test"] | dirs_to_run["extended-test"], dependents
-        ),
-        "dirs-to-extended-test": list(dirs_to_run["extended-test"]),
-        "docs-edited": "true" if docs_edited else "",
+    # we now have dirs_by_job
+    # todo: clean this up
+
+    map_job_to_configs = {
+        job: _get_configs_for_multi_dirs(job, dirs_to_run, dependents)
+        for job in [
+            "lint",
+            "test",
+            "extended-tests",
+            "compile-integration-tests",
+            "dependencies",
+        ]
     }
-    for key, value in outputs.items():
+    map_job_to_configs["test-doc-imports"] = (
+        [{"python-version": "3.12"}] if docs_edited else []
+    )
+
+    for key, value in map_job_to_configs.items():
         json_output = json.dumps(value)
         print(f"{key}={json_output}")
diff --git a/.github/workflows/_compile_integration_test.yml b/.github/workflows/_compile_integration_test.yml
index d8dc9987155..491151ac573 100644
--- a/.github/workflows/_compile_integration_test.yml
+++ b/.github/workflows/_compile_integration_test.yml
@@ -7,6 +7,10 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
+      python-version:
+        required: true
+        type: string
+        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -25,14 +29,14 @@ jobs:
           - "3.10"
           - "3.11"
           - "3.12"
-    name: "poetry run pytest -m compile tests/integration_tests #${{ matrix.python-version }}"
+    name: "poetry run pytest -m compile tests/integration_tests #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: compile-integration
diff --git a/.github/workflows/_dependencies.yml b/.github/workflows/_dependencies.yml
index cbc9caf16e7..b96fe04ed0b 100644
--- a/.github/workflows/_dependencies.yml
+++ b/.github/workflows/_dependencies.yml
@@ -11,6 +11,10 @@ on:
         required: false
         type: string
         description: "Relative path to the langchain library folder"
+      python-version:
+        required: true
+        type: string
+        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -21,22 +25,14 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-          - "3.12"
-    name: dependency checks ${{ matrix.python-version }}
+    name: dependency checks ${{ inputs.python-version }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: pydantic-cross-compat
diff --git a/.github/workflows/_integration_test.yml b/.github/workflows/_integration_test.yml
index 700a8d10146..05971e1dfc5 100644
--- a/.github/workflows/_integration_test.yml
+++ b/.github/workflows/_integration_test.yml
@@ -6,6 +6,10 @@ on:
       working-directory:
         required: true
         type: string
+      python-version:
+        required: true
+        type: string
+        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -16,19 +20,14 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.11"
-    name: Python ${{ matrix.python-version }}
+    name: Python ${{ inputs.python-version }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: core
diff --git a/.github/workflows/_lint.yml b/.github/workflows/_lint.yml
index e48f360ddc4..264dfa6eb81 100644
--- a/.github/workflows/_lint.yml
+++ b/.github/workflows/_lint.yml
@@ -11,6 +11,10 @@ on:
         required: false
         type: string
         description: "Relative path to the langchain library folder"
+      python-version:
+        required: true
+        type: string
+        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -21,27 +25,15 @@ env:
 
 jobs:
   build:
-    name: "make lint #${{ matrix.python-version }}"
+    name: "make lint #${{ inputs.python-version }}"
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        # Only lint on the min and max supported Python versions.
-        # It's extremely unlikely that there's a lint issue on any version in between
-        # that doesn't show up on the min or max versions.
-        #
-        # GitHub rate-limits how many jobs can be running at any one time.
-        # Starting new jobs is also relatively slow,
-        # so linting on fewer versions makes CI faster.
-        python-version:
-          - "3.8"
-          - "3.12"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: lint-with-extras
@@ -86,7 +78,7 @@ jobs:
         with:
           path: |
             ${{ env.WORKDIR }}/.mypy_cache
-          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
+          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ inputs.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
 
 
       - name: Analysing the code with our lint
@@ -120,7 +112,7 @@ jobs:
         with:
           path: |
             ${{ env.WORKDIR }}/.mypy_cache_test
-          key: mypy-test-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
+          key: mypy-test-${{ runner.os }}-${{ runner.arch }}-py${{ inputs.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
 
       - name: Analysing the code with our lint
         working-directory: ${{ inputs.working-directory }}
diff --git a/.github/workflows/_test.yml b/.github/workflows/_test.yml
index ee04fb5e236..841f3796f32 100644
--- a/.github/workflows/_test.yml
+++ b/.github/workflows/_test.yml
@@ -11,6 +11,10 @@ on:
         required: false
         type: string
         description: "Relative path to the langchain library folder"
+      python-version:
+        required: true
+        type: string
+        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -21,22 +25,14 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-          - "3.12"
-    name: "make test #${{ matrix.python-version }}"
+    name: "make test #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: core
diff --git a/.github/workflows/_test_doc_imports.yml b/.github/workflows/_test_doc_imports.yml
index cd2827903b7..17a92a59330 100644
--- a/.github/workflows/_test_doc_imports.yml
+++ b/.github/workflows/_test_doc_imports.yml
@@ -2,6 +2,11 @@ name: test_doc_imports
 
 on:
   workflow_call:
+    inputs:
+      python-version:
+        required: true
+        type: string
+        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -13,14 +18,14 @@ jobs:
       matrix:
         python-version:
           - "3.12"
-    name: "check doc imports #${{ matrix.python-version }}"
+    name: "check doc imports #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           cache-key: core
 
diff --git a/.github/workflows/check_diffs.yml b/.github/workflows/check_diffs.yml
index 33d31bad7f3..0149f5ec11a 100644
--- a/.github/workflows/check_diffs.yml
+++ b/.github/workflows/check_diffs.yml
@@ -33,91 +33,96 @@ jobs:
         run: |
           python .github/scripts/check_diff.py ${{ steps.files.outputs.all }} >> $GITHUB_OUTPUT
     outputs:
-      dirs-to-lint: ${{ steps.set-matrix.outputs.dirs-to-lint }}
-      dirs-to-test: ${{ steps.set-matrix.outputs.dirs-to-test }}
-      dirs-to-extended-test: ${{ steps.set-matrix.outputs.dirs-to-extended-test }}
-      docs-edited: ${{ steps.set-matrix.outputs.docs-edited }}
+      lint: ${{ steps.set-matrix.outputs.lint }}
+      test: ${{ steps.set-matrix.outputs.test }}
+      extended-tests: ${{ steps.set-matrix.outputs.extended-tests }}
+      compile-integration-tests: ${{ steps.set-matrix.outputs.compile-integration-tests }}
+      dependencies: ${{ steps.set-matrix.outputs.dependencies }}
+      test-doc-imports: ${{ steps.set-matrix.outputs.test-doc-imports }}
   lint:
-    name: cd ${{ matrix.working-directory }}
+    name: cd ${{ matrix.job-configs.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-lint != '[]' }}
+    if: ${{ needs.build.outputs.lint != '[]' }}
     strategy:
       matrix:
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-lint) }}
+        job-configs: ${{ fromJson(needs.build.outputs.lint) }}
     uses: ./.github/workflows/_lint.yml
     with:
-      working-directory: ${{ matrix.working-directory }}
+      working-directory: ${{ matrix.job-configs.working-directory }}
+      python-version: ${{ matrix.job-configs.python-version }}
     secrets: inherit
 
   test:
-    name: cd ${{ matrix.working-directory }}
+    name: cd ${{ matrix.job-configs.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
+    if: ${{ needs.build.outputs.test != '[]' }}
     strategy:
       matrix:
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
+        job-configs: ${{ fromJson(needs.build.outputs.test) }}
     uses: ./.github/workflows/_test.yml
     with:
-      working-directory: ${{ matrix.working-directory }}
+      working-directory: ${{ matrix.job-configs.working-directory }}
+      python-version: ${{ matrix.job-configs.python-version }}
     secrets: inherit
 
   test-doc-imports:
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-test != '[]' || needs.build.outputs.docs-edited }}
-    uses: ./.github/workflows/_test_doc_imports.yml
-    secrets: inherit
-
-  compile-integration-tests:
-    name: cd ${{ matrix.working-directory }}
-    needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
+    if: ${{ needs.build.outputs.test-doc-imports != '[]' }}
     strategy:
       matrix:
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
+        job-configs: ${{ fromJson(needs.build.outputs.test-doc-imports) }}
+    uses: ./.github/workflows/_test_doc_imports.yml
+    secrets: inherit
+    with:
+      python-version: ${{ matrix.job-configs.python-version }}
+
+  compile-integration-tests:
+    name: cd ${{ matrix.job-configs.working-directory }}
+    needs: [ build ]
+    if: ${{ needs.build.outputs.compile-integration-tests != '[]' }}
+    strategy:
+      matrix:
+        job-configs: ${{ fromJson(needs.build.outputs.compile-integration-tests) }}
     uses: ./.github/workflows/_compile_integration_test.yml
     with:
-      working-directory: ${{ matrix.working-directory }}
+      working-directory: ${{ matrix.job-configs.working-directory }}
+      python-version: ${{ matrix.job-configs.python-version }}
     secrets: inherit
 
   dependencies:
-    name: cd ${{ matrix.working-directory }}
+    name: cd ${{ matrix.job-configs.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
+    if: ${{ needs.build.outputs.dependencies != '[]' }}
     strategy:
       matrix:
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
+        job-configs: ${{ fromJson(needs.build.outputs.dependencies) }}
     uses: ./.github/workflows/_dependencies.yml
     with:
-      working-directory: ${{ matrix.working-directory }}
+      working-directory: ${{ matrix.job-configs.working-directory }}
+      python-version: ${{ matrix.job-configs.python-version }}
     secrets: inherit
 
   extended-tests:
-    name: "cd ${{ matrix.working-directory }} / make extended_tests #${{ matrix.python-version }}"
+    name: "cd ${{ matrix.job-configs.working-directory }} / make extended_tests #${{ matrix.job-configs.python-version }}"
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-extended-test != '[]' }}
+    if: ${{ needs.build.outputs.extended-tests != '[]' }}
     strategy:
       matrix:
         # note different variable for extended test dirs
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-extended-test) }}
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-          - "3.12"
+        job-configs: ${{ fromJson(needs.build.outputs.extended-tests) }}
     runs-on: ubuntu-latest
     defaults:
       run:
-        working-directory: ${{ matrix.working-directory }}
+        working-directory: ${{ matrix.job-configs.working-directory }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.job-configs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ matrix.job-configs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ matrix.working-directory }}
+          working-directory: ${{ matrix.job-configs.working-directory }}
           cache-key: extended
 
       - name: Install dependencies