Brandon/eng 290 make tool inputs actual objects and not strings (#1868)

* Improving tool calling to pass dictionaries instead of strings

* Fix issues with parsing none/null

* remove prints and unnecessary comments

* Fix crew_test issues with function calling

* improve prompting

* add back in support for add_image

* add tests for tool validation

* revert back to figure out why tests are timing out

* Update cassette

* trying to find what is timing out

* add back in guardrails

* add back in manager delegation tests

* Trying to fix tests

* Force test to pass

* Trying to fix tests

* add in more role tests

* add back old tool validation

* updating tests

* vcr

* Fix tests

* improve function llm logic

* vcr 2

* drop llm

* Failing test

* add more tests back in

* Revert tool validation
This commit is contained in:
Brandon Hancock (bhancock_ai)
2025-01-10 17:16:46 -05:00
committed by GitHub
parent be8e33daf6
commit b8d07fee83
14 changed files with 857 additions and 3981 deletions

View File

@@ -1,9 +1,13 @@
import ast
import datetime
import json
import re
import time
from difflib import SequenceMatcher
from textwrap import dedent
from typing import Any, List, Union
from typing import Any, Dict, List, Union
from json_repair import repair_json
import crewai.utilities.events as events
from crewai.agents.tools_handler import ToolsHandler
@@ -19,7 +23,15 @@ try:
import agentops # type: ignore
except ImportError:
agentops = None
OPENAI_BIGGER_MODELS = ["gpt-4", "gpt-4o", "o1-preview", "o1-mini", "o1", "o3", "o3-mini"]
OPENAI_BIGGER_MODELS = [
"gpt-4",
"gpt-4o",
"o1-preview",
"o1-mini",
"o1",
"o3",
"o3-mini",
]
class ToolUsageErrorException(Exception):
@@ -80,7 +92,7 @@ class ToolUsage:
self._max_parsing_attempts = 2
self._remember_format_after_usages = 4
def parse(self, tool_string: str):
def parse_tool_calling(self, tool_string: str):
"""Parse the tool string and return the tool calling."""
return self._tool_calling(tool_string)
@@ -94,7 +106,6 @@ class ToolUsage:
self.task.increment_tools_errors()
return error
# BUG? The code below seems to be unreachable
try:
tool = self._select_tool(calling.tool_name)
except Exception as e:
@@ -116,7 +127,7 @@ class ToolUsage:
self._printer.print(content=f"\n\n{error}\n", color="red")
return error
return f"{self._use(tool_string=tool_string, tool=tool, calling=calling)}" # type: ignore # BUG?: "_use" of "ToolUsage" does not return a value (it only ever returns None)
return f"{self._use(tool_string=tool_string, tool=tool, calling=calling)}"
def _use(
self,
@@ -349,13 +360,13 @@ class ToolUsage:
tool_name = self.action.tool
tool = self._select_tool(tool_name)
try:
tool_input = self._validate_tool_input(self.action.tool_input)
arguments = ast.literal_eval(tool_input)
arguments = self._validate_tool_input(self.action.tool_input)
except Exception:
if raise_error:
raise
else:
return ToolUsageErrorException( # type: ignore # Incompatible return value type (got "ToolUsageErrorException", expected "ToolCalling | InstructorToolCalling")
return ToolUsageErrorException(
f'{self._i18n.errors("tool_arguments_error")}'
)
@@ -363,14 +374,14 @@ class ToolUsage:
if raise_error:
raise
else:
return ToolUsageErrorException( # type: ignore # Incompatible return value type (got "ToolUsageErrorException", expected "ToolCalling | InstructorToolCalling")
return ToolUsageErrorException(
f'{self._i18n.errors("tool_arguments_error")}'
)
return ToolCalling(
tool_name=tool.name,
arguments=arguments,
log=tool_string, # type: ignore
log=tool_string,
)
def _tool_calling(
@@ -396,57 +407,28 @@ class ToolUsage:
)
return self._tool_calling(tool_string)
def _validate_tool_input(self, tool_input: str) -> str:
def _validate_tool_input(self, tool_input: str) -> Dict[str, Any]:
try:
ast.literal_eval(tool_input)
return tool_input
except Exception:
# Clean and ensure the string is properly enclosed in braces
tool_input = tool_input.strip()
if not tool_input.startswith("{"):
tool_input = "{" + tool_input
if not tool_input.endswith("}"):
tool_input += "}"
# Replace Python literals with JSON equivalents
replacements = {
r"'": '"',
r"None": "null",
r"True": "true",
r"False": "false",
}
for pattern, replacement in replacements.items():
tool_input = re.sub(pattern, replacement, tool_input)
# Manually split the input into key-value pairs
entries = tool_input.strip("{} ").split(",")
formatted_entries = []
arguments = json.loads(tool_input)
except json.JSONDecodeError:
# Attempt to repair JSON string
repaired_input = repair_json(tool_input)
try:
arguments = json.loads(repaired_input)
except json.JSONDecodeError as e:
raise Exception(f"Invalid tool input JSON: {e}")
for entry in entries:
if ":" not in entry:
continue # Skip malformed entries
key, value = entry.split(":", 1)
# Remove extraneous white spaces and quotes, replace single quotes
key = key.strip().strip('"').replace("'", '"')
value = value.strip()
# Handle replacement of single quotes at the start and end of the value string
if value.startswith("'") and value.endswith("'"):
value = value[1:-1] # Remove single quotes
value = (
'"' + value.replace('"', '\\"') + '"'
) # Re-encapsulate with double quotes
elif value.isdigit(): # Check if value is a digit, hence integer
value = value
elif value.lower() in [
"true",
"false",
]: # Check for boolean and null values
value = value.lower().capitalize()
elif value.lower() == "null":
value = "None"
else:
# Assume the value is a string and needs quotes
value = '"' + value.replace('"', '\\"') + '"'
# Rebuild the entry with proper quoting
formatted_entry = f'"{key}": {value}'
formatted_entries.append(formatted_entry)
# Reconstruct the JSON string
new_json_string = "{" + ", ".join(formatted_entries) + "}"
return new_json_string
return arguments
def on_tool_error(self, tool: Any, tool_calling: ToolCalling, e: Exception) -> None:
event_data = self._prepare_event_data(tool, tool_calling)