Chore!: Update ci/cd bot default behaviour to match CLI behaviour

Author: erindru

docs/integrations/github.md

@@ -293,12 +293,12 @@ Below is an example of how to define the default config for the bot in either YA
 | `enable_deploy_command`               | Indicates if the `/deploy` command should be enabled in order to allowed synchronized deploys to production. Default: `False`                                                                                                                                                                                                                                                                            |  bool  |    N     |
 | `command_namespace`                   | The namespace to use for SQLMesh commands. For example if you provide `#SQLMesh` as a value then commands will be expected in the format of `#SQLMesh/<command>`. Default: `None` meaning no namespace is used.                                                                                                                                                                                          | string |    N     |
 | `auto_categorize_changes`             | Auto categorization behavior to use for the bot. If not provided then the project-wide categorization behavior is used. See [Auto-categorize model changes](https://sqlmesh.readthedocs.io/en/stable/guides/configuration/#auto-categorize-model-changes) for details.                                                                                                                                   |  dict  |    N     |
-| `default_pr_start`                    | Default start when creating PR environment plans. If running in a mode where the bot automatically backfills models (based on `auto_categorize_changes` behavior) then this can be used to limit the amount of data backfilled. Defaults to `None` meaning the start date is set to the earliest model's start or to 1 day ago if [data previews](../concepts/plans.md#data-preview) need to be computed. |  str   |    N     |
-| `skip_pr_backfill`                    | Indicates if the bot should skip backfilling models in the PR environment. Default: `True`                                                                                                                                                                                                                                                                                                               |  bool  |    N     |
+| `default_pr_start`                    | Default start when creating PR environment plans. If running in a mode where the bot automatically backfills models (based on `auto_categorize_changes` behavior) then this can be used to limit the amount of data backfilled. Defaults to `None` meaning the start date is set to the earliest model's start or to 1 day ago if [data previews](../concepts/plans.md#data-preview) need to be computed.|  str   |    N     |
+| `skip_pr_backfill`                    | Indicates if the bot should skip backfilling models in the PR environment. Default: `False`                                                                                                                                                                                                                                                                                                              |  bool  |    N     |
 | `pr_include_unmodified`               | Indicates whether to include unmodified models in the PR environment. Default to the project's config value (which defaults to `False`)                                                                                                                                                                                                                                                                  |  bool  |    N     |
 | `run_on_deploy_to_prod`               | Indicates whether to run latest intervals when deploying to prod. If set to false, the deployment will backfill only the changed models up to the existing latest interval in production, ignoring any missing intervals beyond this point. Default: `False`                                                                                                                                             |  bool  |    N     |
 | `pr_environment_name`                 | The name of the PR environment to create for which a PR number will be appended to. Defaults to the repo name if not provided. Note: The name will be normalized to alphanumeric + underscore and lowercase.                                                                                                                                                                                             |  str   |    N     |
-| `prod_branch_name`                    | The name of the git branch associated with production. Ex: `prod`. Default: `main` or `master` is considered prod                                                                                                                                                                                                                                                                                         |  str   |    N     |
+| `prod_branch_name`                    | The name of the git branch associated with production. Ex: `prod`. Default: `main` or `master` is considered prod                                                                                                                                                                                                                                                                                        |  str   |    N     |
 
 Example with all properties defined:
 

sqlmesh/core/config/root.py

@@ -260,6 +260,18 @@ def _normalize_identifiers(key: str) -> None:
 
         return self
 
+    @model_validator(mode="after")
+    def _inherit_project_config_in_cicd_bot(self) -> Self:
+        if self.cicd_bot:
+            # inherit the project-level settings into the CICD bot if they have not been explicitly overridden
+            if self.cicd_bot.auto_categorize_changes_ is None:
+                self.cicd_bot.auto_categorize_changes_ = self.plan.auto_categorize_changes
+
+            if self.cicd_bot.pr_include_unmodified_ is None:
+                self.cicd_bot.pr_include_unmodified_ = self.plan.include_unmodified
+
+        return self
+
     def get_default_test_connection(
         self,
         default_catalog: t.Optional[str] = None,

sqlmesh/integrations/github/cicd/config.py

@@ -22,10 +22,12 @@ class GithubCICDBotConfig(BaseConfig):
     enable_deploy_command: bool = False
     merge_method: t.Optional[MergeMethod] = None
     command_namespace: t.Optional[str] = None
-    auto_categorize_changes: CategorizerConfig = CategorizerConfig.all_off()
+    auto_categorize_changes_: t.Optional[CategorizerConfig] = Field(
+        default=None, alias="auto_categorize_changes"
+    )
     default_pr_start: t.Optional[TimeLike] = None
-    skip_pr_backfill: bool = True
-    pr_include_unmodified: t.Optional[bool] = None
+    skip_pr_backfill: bool = False  # to align with the CLI default
+    pr_include_unmodified_: t.Optional[bool] = Field(default=None, alias="pr_include_unmodified")
     run_on_deploy_to_prod: bool = False
     pr_environment_name: t.Optional[str] = None
     prod_branch_names_: t.Optional[str] = Field(default=None, alias="prod_branch_name")
@@ -49,6 +51,14 @@ def prod_branch_names(self) -> t.List[str]:
             return [self.prod_branch_names_]
         return ["main", "master"]
 
+    @property
+    def auto_categorize_changes(self) -> CategorizerConfig:
+        return self.auto_categorize_changes_ or CategorizerConfig.all_off()
+
+    @property
+    def pr_include_unmodified(self) -> bool:
+        return self.pr_include_unmodified_ or False
+
     FIELDS_FOR_ANALYTICS: t.ClassVar[t.Set[str]] = {
         "invalidate_environment_after_deploy",
         "enable_deploy_command",

tests/core/analytics/test_collector.py

@@ -145,7 +145,7 @@ def test_on_cicd_command(collector: AnalyticsCollector, mocker: MockerFixture):
                 {
                     "seq_num": 1,
                     "event_type": "CICD_COMMAND",
-                    "event": '{"command_name": "test_cicd", "command_args": ["arg_1", "arg_2"], "parent_command_names": ["parent_a", "parent_b"], "cicd_bot_config": {"invalidate_environment_after_deploy": true, "enable_deploy_command": false, "auto_categorize_changes": {"external": "off", "python": "off", "sql": "off", "seed": "off"}, "skip_pr_backfill": true, "run_on_deploy_to_prod": false}}',
+                    "event": '{"command_name": "test_cicd", "command_args": ["arg_1", "arg_2"], "parent_command_names": ["parent_a", "parent_b"], "cicd_bot_config": {"invalidate_environment_after_deploy": true, "enable_deploy_command": false, "skip_pr_backfill": false, "run_on_deploy_to_prod": false}}',
                     **common_fields,
                 }
             ),

tests/integrations/github/cicd/test_config.py

@@ -34,11 +34,11 @@ def test_load_yaml_config_default(tmp_path):
     assert config.cicd_bot.invalidate_environment_after_deploy
     assert config.cicd_bot.merge_method is None
     assert config.cicd_bot.command_namespace is None
-    assert config.cicd_bot.auto_categorize_changes == CategorizerConfig.all_off()
+    assert config.cicd_bot.auto_categorize_changes == config.plan.auto_categorize_changes
     assert config.cicd_bot.default_pr_start is None
     assert not config.cicd_bot.enable_deploy_command
-    assert config.cicd_bot.skip_pr_backfill
-    assert config.cicd_bot.pr_include_unmodified is None
+    assert not config.cicd_bot.skip_pr_backfill
+    assert not config.cicd_bot.pr_include_unmodified
     assert config.cicd_bot.pr_environment_name is None
     assert config.cicd_bot.prod_branch_names == ["main", "master"]
 
@@ -112,11 +112,11 @@ def test_load_python_config_defaults(tmp_path):
     assert config.cicd_bot.invalidate_environment_after_deploy
     assert config.cicd_bot.merge_method is None
     assert config.cicd_bot.command_namespace is None
-    assert config.cicd_bot.auto_categorize_changes == CategorizerConfig.all_off()
+    assert config.cicd_bot.auto_categorize_changes == config.plan.auto_categorize_changes
     assert config.cicd_bot.default_pr_start is None
     assert not config.cicd_bot.enable_deploy_command
-    assert config.cicd_bot.skip_pr_backfill
-    assert config.cicd_bot.pr_include_unmodified is None
+    assert not config.cicd_bot.skip_pr_backfill
+    assert not config.cicd_bot.pr_include_unmodified
     assert config.cicd_bot.pr_environment_name is None
     assert config.cicd_bot.prod_branch_names == ["main", "master"]
 
@@ -252,3 +252,35 @@ def test_ttl_in_past(tmp_path):
             match="TTL '1 week' is in the past. Please specify a relative time in the future. Ex: `in 1 week` instead of `1 week`.",
         ):
             load_config_from_paths(Config, project_paths=[tmp_path / "config.yaml"])
+
+
+def test_properties_inherit_from_project_config(tmp_path):
+    (tmp_path / "config.yaml").write_text("""
+plan:
+  auto_categorize_changes:
+    external: off
+    python: full
+    sql: off
+    seed: full
+  include_unmodified: true
+                                          
+cicd_bot:
+  type: github
+
+model_defaults:
+  dialect: duckdb
+""")
+
+    config = load_config_from_paths(Config, [tmp_path / "config.yaml"])
+
+    assert (
+        config.cicd_bot.auto_categorize_changes
+        == config.plan.auto_categorize_changes
+        == CategorizerConfig(
+            external=AutoCategorizationMode.OFF,
+            python=AutoCategorizationMode.FULL,
+            sql=AutoCategorizationMode.OFF,
+            seed=AutoCategorizationMode.FULL,
+        )
+    )
+    assert config.cicd_bot.pr_include_unmodified == config.plan.include_unmodified == True

tests/integrations/github/cicd/test_github_controller.py

@@ -223,7 +223,7 @@ def test_pr_plan(github_client, make_controller):
         "tests/fixtures/github/pull_request_synchronized.json", github_client
     )
     assert controller.pr_plan.environment.name == "hello_world_2"
-    assert controller.pr_plan.skip_backfill
+    assert not controller.pr_plan.skip_backfill
     assert not controller.pr_plan.no_gaps
     assert not controller._context.apply.called
     assert controller._context._run_plan_tests.call_args == call(skip_tests=True)
@@ -241,7 +241,9 @@ def test_pr_plan_auto_categorization(github_client, make_controller):
         "tests/fixtures/github/pull_request_synchronized.json",
         github_client,
         bot_config=GithubCICDBotConfig(
-            auto_categorize_changes=custom_categorizer_config, default_pr_start=default_start
+            auto_categorize_changes=custom_categorizer_config,
+            default_pr_start=default_start,
+            skip_pr_backfill=True,
         ),
     )
     assert controller.pr_plan.environment.name == "hello_world_2"