Feat/improve yaml extraction (#2428)

* Support wildcard handling in `emit()`

Change `emit()` to call handlers registered for parent classes using
`isinstance()`. Ensures that base event handlers receive derived
events.

* Fix failing test

* Remove unused variable

* update interpolation to work with example response types in yaml docs

* make tests

* fix circular deps

* Fixing interpolation imports

* Improve test

---------

Co-authored-by: Vinicius Brasil <vini@hey.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>

src/crewai/agents/agent_builder/base_agent.py

@@ -25,6 +25,7 @@ from crewai.tools.base_tool import BaseTool, Tool
 from crewai.utilities import I18N, Logger, RPMController
 from crewai.utilities.config import process_config
 from crewai.utilities.converter import Converter
+from crewai.utilities.string_utils import interpolate_only
 
 T = TypeVar("T", bound="BaseAgent")
 
@@ -333,9 +334,15 @@ class BaseAgent(ABC, BaseModel):
             self._original_backstory = self.backstory
 
         if inputs:
-            self.role = self._original_role.format(**inputs)
-            self.goal = self._original_goal.format(**inputs)
-            self.backstory = self._original_backstory.format(**inputs)
+            self.role = interpolate_only(
+                input_string=self._original_role, inputs=inputs
+            )
+            self.goal = interpolate_only(
+                input_string=self._original_goal, inputs=inputs
+            )
+            self.backstory = interpolate_only(
+                input_string=self._original_backstory, inputs=inputs
+            )
 
     def set_cache_handler(self, cache_handler: CacheHandler) -> None:
         """Set the cache handler for the agent.

src/crewai/task.py

@@ -2,6 +2,7 @@ import datetime
 import inspect
 import json
 import logging
+import re
 import threading
 import uuid
 from concurrent.futures import Future
@@ -49,6 +50,7 @@ from crewai.utilities.events import (
 from crewai.utilities.events.crewai_event_bus import crewai_event_bus
 from crewai.utilities.i18n import I18N
 from crewai.utilities.printer import Printer
+from crewai.utilities.string_utils import interpolate_only
 
 
 class Task(BaseModel):
@@ -507,7 +509,9 @@ class Task(BaseModel):
             return
 
         try:
-            self.description = self._original_description.format(**inputs)
+            self.description = interpolate_only(
+                input_string=self._original_description, inputs=inputs
+            )
         except KeyError as e:
             raise ValueError(
                 f"Missing required template variable '{e.args[0]}' in description"
@@ -516,7 +520,7 @@ class Task(BaseModel):
             raise ValueError(f"Error interpolating description: {str(e)}") from e
 
         try:
-            self.expected_output = self.interpolate_only(
+            self.expected_output = interpolate_only(
                 input_string=self._original_expected_output, inputs=inputs
             )
         except (KeyError, ValueError) as e:
@@ -524,7 +528,7 @@ class Task(BaseModel):
 
         if self.output_file is not None:
             try:
-                self.output_file = self.interpolate_only(
+                self.output_file = interpolate_only(
                     input_string=self._original_output_file, inputs=inputs
                 )
             except (KeyError, ValueError) as e:
@@ -555,72 +559,6 @@ class Task(BaseModel):
                 f"\n\n{conversation_instruction}\n\n{conversation_history}"
             )
 
-    def interpolate_only(
-        self,
-        input_string: Optional[str],
-        inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]],
-    ) -> str:
-        """Interpolate placeholders (e.g., {key}) in a string while leaving JSON untouched.
-
-        Args:
-            input_string: The string containing template variables to interpolate.
-                         Can be None or empty, in which case an empty string is returned.
-            inputs: Dictionary mapping template variables to their values.
-                   Supported value types are strings, integers, floats, and dicts/lists
-                   containing only these types and other nested dicts/lists.
-
-        Returns:
-            The interpolated string with all template variables replaced with their values.
-            Empty string if input_string is None or empty.
-
-        Raises:
-            ValueError: If a value contains unsupported types
-        """
-
-        # Validation function for recursive type checking
-        def validate_type(value: Any) -> None:
-            if value is None:
-                return
-            if isinstance(value, (str, int, float, bool)):
-                return
-            if isinstance(value, (dict, list)):
-                for item in value.values() if isinstance(value, dict) else value:
-                    validate_type(item)
-                return
-            raise ValueError(
-                f"Unsupported type {type(value).__name__} in inputs. "
-                "Only str, int, float, bool, dict, and list are allowed."
-            )
-
-        # Validate all input values
-        for key, value in inputs.items():
-            try:
-                validate_type(value)
-            except ValueError as e:
-                raise ValueError(f"Invalid value for key '{key}': {str(e)}") from e
-
-        if input_string is None or not input_string:
-            return ""
-        if "{" not in input_string and "}" not in input_string:
-            return input_string
-        if not inputs:
-            raise ValueError(
-                "Inputs dictionary cannot be empty when interpolating variables"
-            )
-        try:
-            escaped_string = input_string.replace("{", "{{").replace("}", "}}")
-
-            for key in inputs.keys():
-                escaped_string = escaped_string.replace(f"{{{{{key}}}}}", f"{{{key}}}")
-
-            return escaped_string.format(**inputs)
-        except KeyError as e:
-            raise KeyError(
-                f"Template variable '{e.args[0]}' not found in inputs dictionary"
-            ) from e
-        except ValueError as e:
-            raise ValueError(f"Error during string interpolation: {str(e)}") from e
-
     def increment_tools_errors(self) -> None:
         """Increment the tools errors counter."""
         self.tools_errors += 1

src/crewai/utilities/formatter.py

@@ -1,10 +1,12 @@
-from typing import List
+import re
+from typing import TYPE_CHECKING, List
 
-from crewai.task import Task
-from crewai.tasks.task_output import TaskOutput
+if TYPE_CHECKING:
+    from crewai.task import Task
+    from crewai.tasks.task_output import TaskOutput
 
 
-def aggregate_raw_outputs_from_task_outputs(task_outputs: List[TaskOutput]) -> str:
+def aggregate_raw_outputs_from_task_outputs(task_outputs: List["TaskOutput"]) -> str:
     """Generate string context from the task outputs."""
     dividers = "\n\n----------\n\n"
 
@@ -13,7 +15,7 @@ def aggregate_raw_outputs_from_task_outputs(task_outputs: List[TaskOutput]) -> s
     return context
 
 
-def aggregate_raw_outputs_from_tasks(tasks: List[Task]) -> str:
+def aggregate_raw_outputs_from_tasks(tasks: List["Task"]) -> str:
     """Generate string context from the tasks."""
     task_outputs = [task.output for task in tasks if task.output is not None]
 

src/crewai/utilities/string_utils.py

@@ -0,0 +1,82 @@
+import re
+from typing import Any, Dict, List, Optional, Union
+
+
+def interpolate_only(
+    input_string: Optional[str],
+    inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]],
+) -> str:
+    """Interpolate placeholders (e.g., {key}) in a string while leaving JSON untouched.
+    Only interpolates placeholders that follow the pattern {variable_name} where
+    variable_name starts with a letter/underscore and contains only letters, numbers, and underscores.
+
+    Args:
+        input_string: The string containing template variables to interpolate.
+                     Can be None or empty, in which case an empty string is returned.
+        inputs: Dictionary mapping template variables to their values.
+               Supported value types are strings, integers, floats, and dicts/lists
+               containing only these types and other nested dicts/lists.
+
+    Returns:
+        The interpolated string with all template variables replaced with their values.
+        Empty string if input_string is None or empty.
+
+    Raises:
+        ValueError: If a value contains unsupported types or a template variable is missing
+    """
+
+    # Validation function for recursive type checking
+    def validate_type(value: Any) -> None:
+        if value is None:
+            return
+        if isinstance(value, (str, int, float, bool)):
+            return
+        if isinstance(value, (dict, list)):
+            for item in value.values() if isinstance(value, dict) else value:
+                validate_type(item)
+            return
+        raise ValueError(
+            f"Unsupported type {type(value).__name__} in inputs. "
+            "Only str, int, float, bool, dict, and list are allowed."
+        )
+
+    # Validate all input values
+    for key, value in inputs.items():
+        try:
+            validate_type(value)
+        except ValueError as e:
+            raise ValueError(f"Invalid value for key '{key}': {str(e)}") from e
+
+    if input_string is None or not input_string:
+        return ""
+    if "{" not in input_string and "}" not in input_string:
+        return input_string
+    if not inputs:
+        raise ValueError(
+            "Inputs dictionary cannot be empty when interpolating variables"
+        )
+
+    # The regex pattern to find valid variable placeholders
+    # Matches {variable_name} where variable_name starts with a letter/underscore
+    # and contains only letters, numbers, and underscores
+    pattern = r"\{([A-Za-z_][A-Za-z0-9_]*)\}"
+
+    # Find all matching variables in the input string
+    variables = re.findall(pattern, input_string)
+    result = input_string
+
+    # Check if all variables exist in inputs
+    missing_vars = [var for var in variables if var not in inputs]
+    if missing_vars:
+        raise KeyError(
+            f"Template variable '{missing_vars[0]}' not found in inputs dictionary"
+        )
+
+    # Replace each variable with its value
+    for var in variables:
+        if var in inputs:
+            placeholder = "{" + var + "}"
+            value = str(inputs[var])
+            result = result.replace(placeholder, value)
+
+    return result