Always strip Markdown fences from structured output (#3475)

Author: DouweM

pydantic_ai_slim/pydantic_ai/_output.py

@@ -470,7 +470,7 @@ def __init__(
         allows_image: bool,
     ):
         super().__init__(
-            processor=PromptedOutputProcessor(processor),
+            processor=processor,
             allows_deferred_tools=allows_deferred_tools,
             allows_image=allows_image,
         )
@@ -494,13 +494,6 @@ def build_instructions(cls, template: str, object_def: OutputObjectDefinition) -
 
         return template.format(schema=json.dumps(schema))
 
-    def instructions(self, default_template: str) -> str:  # pragma: no cover
-        """Get instructions to tell model to output JSON matching the schema."""
-        template = self.template or default_template
-        object_def = self.object_def
-        assert object_def is not None
-        return self.build_instructions(template, object_def)
-
 
 @dataclass(init=False)
 class ToolOutputSchema(OutputSchema[OutputDataT]):
@@ -542,28 +535,6 @@ class BaseObjectOutputProcessor(BaseOutputProcessor[OutputDataT]):
     object_def: OutputObjectDefinition
 
 
-@dataclass(init=False)
-class PromptedOutputProcessor(BaseObjectOutputProcessor[OutputDataT]):
-    wrapped: BaseObjectOutputProcessor[OutputDataT]
-
-    def __init__(self, wrapped: BaseObjectOutputProcessor[OutputDataT]):
-        self.wrapped = wrapped
-        super().__init__(object_def=wrapped.object_def)
-
-    async def process(
-        self,
-        data: str,
-        run_context: RunContext[AgentDepsT],
-        allow_partial: bool = False,
-        wrap_validation_errors: bool = True,
-    ) -> OutputDataT:
-        text = _utils.strip_markdown_fences(data)
-
-        return await self.wrapped.process(
-            text, run_context, allow_partial=allow_partial, wrap_validation_errors=wrap_validation_errors
-        )
-
-
 @dataclass(init=False)
 class ObjectOutputProcessor(BaseObjectOutputProcessor[OutputDataT]):
     outer_typed_dict_key: str | None = None
@@ -653,6 +624,9 @@ async def process(
         Returns:
             Either the validated output data (left) or a retry message (right).
         """
+        if isinstance(data, str):
+            data = _utils.strip_markdown_fences(data)
+
         try:
             output = self.validate(data, allow_partial)
         except ValidationError as e:

pydantic_ai_slim/pydantic_ai/_utils.py

@@ -467,12 +467,14 @@ def validate_empty_kwargs(_kwargs: dict[str, Any]) -> None:
         raise exceptions.UserError(f'Unknown keyword arguments: {unknown_kwargs}')
 
 
+_MARKDOWN_FENCES_PATTERN = re.compile(r'```(?:\w+)?\n(\{.*\})', flags=re.DOTALL)
+
+
 def strip_markdown_fences(text: str) -> str:
     if text.startswith('{'):
         return text
 
-    regex = r'```(?:\w+)?\n(\{.*\})\n```'
-    match = re.search(regex, text, re.DOTALL)
+    match = re.search(_MARKDOWN_FENCES_PATTERN, text)
     if match:
         return match.group(1)
 

tests/test_utils.py

@@ -495,6 +495,7 @@ def test_merge_json_schema_defs():
 def test_strip_markdown_fences():
     assert strip_markdown_fences('{"foo": "bar"}') == '{"foo": "bar"}'
     assert strip_markdown_fences('```json\n{"foo": "bar"}\n```') == '{"foo": "bar"}'
+    assert strip_markdown_fences('```json\n{\n  "foo": "bar"\n}') == '{\n  "foo": "bar"\n}'
     assert (
         strip_markdown_fences('{"foo": "```json\\n{"foo": "bar"}\\n```"}')
         == '{"foo": "```json\\n{"foo": "bar"}\\n```"}'