From 5f8e991ed8cc4725a3b64ec958bdf0a0885d4e66 Mon Sep 17 00:00:00 2001
From: "J. Nick Koston" <nick@home-assistant.io>
Date: Sat, 25 Apr 2026 04:44:35 -0500
Subject: [PATCH] [api] Populate schema defaults for transitive cpp test deps;
 add json override

- script/build_helpers.py: when injecting a non-MULTI_CONF component
  into the post-validation config, run its CONFIG_SCHEMA with {} so
  defaults are populated. Without this, socket got config = {} and
  socket.FILTER_SOURCE_FILES crashed with KeyError on
  'implementation' (the schema's defaulted key was never filled in).
  Falls back to {} if the schema can't validate empty input.

- tests/components/json/__init__.py: enable codegen for json so its
  to_code runs during cpp unit test builds, registering the
  ArduinoJson library. Required for any api dep test, since
  json_util.cpp #includes <ArduinoJson.h>.

Locally verified 'script/cpp_unit_test.py api' now compiles and runs;
ProtoMacVarint test suite (9 cases) passes.
---
 script/build_helpers.py           | 20 +++++++++++++++-----
 tests/components/json/__init__.py |  9 +++++++++
 2 files changed, 24 insertions(+), 5 deletions(-)
 create mode 100644 tests/components/json/__init__.py

diff --git a/script/build_helpers.py b/script/build_helpers.py
index 59dded66dd..4cf2f93fbb 100644
--- a/script/build_helpers.py
+++ b/script/build_helpers.py
@@ -326,11 +326,21 @@ def compile_and_get_binary(
         # system, not a real loadable component (get_component returns None)
         elif (component := get_component(component_name)) is not None:
             # MULTI_CONF components store their config as a list of dicts,
-            # everything else stores a single dict. Using the wrong shape
-            # breaks code paths that subscript CORE.config[component] with
-            # a string key (e.g. socket.FILTER_SOURCE_FILES).
-            default = [] if component.multi_conf else {}
-            config.setdefault(component_name, default)
+            # everything else stores a single dict. Run the component's
+            # schema with {} so defaults get populated -- code paths like
+            # socket.FILTER_SOURCE_FILES expect a fully-populated mapping.
+            if component.multi_conf:
+                config.setdefault(component_name, [])
+            elif component_name not in config:
+                schema = component.config_schema
+                try:
+                    config[component_name] = schema({}) if schema is not None else {}
+                except Exception:  # noqa: BLE001
+                    # Schema requires explicit input we can't synthesize; fall
+                    # back to an empty mapping so subscripting at least returns
+                    # KeyError on missing keys rather than crashing on the
+                    # wrong type.
+                    config[component_name] = {}
 
     # Register platforms from the extra config (benchmark.yaml) so
     # USE_SENSOR, USE_LIGHT, etc. defines are emitted without needing
diff --git a/tests/components/json/__init__.py b/tests/components/json/__init__.py
new file mode 100644
index 0000000000..40ec1f996e
--- /dev/null
+++ b/tests/components/json/__init__.py
@@ -0,0 +1,9 @@
+from tests.testing_helpers import ComponentManifestOverride
+
+
+def override_manifest(manifest: ComponentManifestOverride) -> None:
+    # json's to_code calls cg.add_library("bblanchon/ArduinoJson", ...). C++
+    # unit test builds that pull json in transitively (e.g. api) need that
+    # library registration to happen, otherwise json_util.cpp fails to find
+    # ArduinoJson.h.
+    manifest.enable_codegen()