Some checks failed
Contributor Attribution Check / check-attribution (pull_request) Failing after 37s
Docker Build and Publish / build-and-push (pull_request) Has been skipped
Supply Chain Audit / Scan PR for supply chain risks (pull_request) Successful in 43s
Tests / e2e (pull_request) Successful in 1m57s
Tests / test (pull_request) Failing after 18m57s
Marathon sessions show tool fixation: agent latches onto one tool and calls it repeatedly. Observed streaks of 8-25 identical calls. New agent/tool_fixation_detector.py: - ToolFixationDetector: tracks consecutive tool calls - record(tool_name): returns nudge prompt when threshold reached - Default threshold: 5 consecutive calls (configurable via TOOL_FIXATION_THRESHOLD env var) - Nudge prompt explains the fixation and suggests alternatives: 1. Read error carefully 2. Try different tool 3. Ask user for clarification 4. Check if task is complete - get_streak_info(): current streak state - format_report(): human-readable fixation events - Singleton via get_fixation_detector() Config: - TOOL_FIXATION_THRESHOLD (default: 5) - TOOL_FIXATION_WINDOW (default: 10) Tests: tests/test_tool_fixation_detector.py (9 tests) Closes #886
157 lines
4.8 KiB
Python
157 lines
4.8 KiB
Python
"""Tool fixation detection — break repetitive tool calling loops.
|
|
|
|
Detects when the agent latches onto one tool and calls it repeatedly
|
|
without making progress. Injects a nudge prompt to break the loop.
|
|
|
|
Usage:
|
|
from agent.tool_fixation_detector import ToolFixationDetector
|
|
detector = ToolFixationDetector()
|
|
nudge = detector.record("execute_code")
|
|
if nudge:
|
|
# Inject nudge into conversation
|
|
messages.append({"role": "system", "content": nudge})
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
from dataclasses import dataclass, field
|
|
from typing import Dict, List, Optional
|
|
|
|
|
|
# Default thresholds
|
|
_DEFAULT_THRESHOLD = int(os.getenv("TOOL_FIXATION_THRESHOLD", "5"))
|
|
_DEFAULT_WINDOW = int(os.getenv("TOOL_FIXATION_WINDOW", "10"))
|
|
|
|
|
|
@dataclass
|
|
class FixationEvent:
|
|
"""Record of a fixation detection."""
|
|
tool_name: str
|
|
streak_length: int
|
|
threshold: int
|
|
nudge_sent: bool = False
|
|
|
|
|
|
class ToolFixationDetector:
|
|
"""Detects and breaks tool fixation loops.
|
|
|
|
Tracks the sequence of tool calls and detects when the same tool
|
|
is called N times consecutively. When detected, returns a nudge
|
|
prompt to inject into the conversation.
|
|
"""
|
|
|
|
def __init__(self, threshold: int = 0, window: int = 0):
|
|
self.threshold = threshold or _DEFAULT_THRESHOLD
|
|
self.window = window or _DEFAULT_WINDOW
|
|
self._history: List[str] = []
|
|
self._current_streak: str = ""
|
|
self._streak_count: int = 0
|
|
self._nudges_sent: int = 0
|
|
self._events: List[FixationEvent] = []
|
|
|
|
@property
|
|
def nudges_sent(self) -> int:
|
|
return self._nudges_sent
|
|
|
|
@property
|
|
def events(self) -> List[FixationEvent]:
|
|
return list(self._events)
|
|
|
|
def record(self, tool_name: str) -> Optional[str]:
|
|
"""Record a tool call and return nudge prompt if fixation detected.
|
|
|
|
Args:
|
|
tool_name: Name of the tool that was called.
|
|
|
|
Returns:
|
|
Nudge prompt string if fixation detected, None otherwise.
|
|
"""
|
|
self._history.append(tool_name)
|
|
|
|
# Trim history to window
|
|
if len(self._history) > self.window:
|
|
self._history = self._history[-self.window:]
|
|
|
|
# Update streak
|
|
if tool_name == self._current_streak:
|
|
self._streak_count += 1
|
|
else:
|
|
self._current_streak = tool_name
|
|
self._streak_count = 1
|
|
|
|
# Check for fixation
|
|
if self._streak_count >= self.threshold:
|
|
event = FixationEvent(
|
|
tool_name=tool_name,
|
|
streak_length=self._streak_count,
|
|
threshold=self.threshold,
|
|
nudge_sent=True,
|
|
)
|
|
self._events.append(event)
|
|
self._nudges_sent += 1
|
|
|
|
return self._build_nudge(tool_name, self._streak_count)
|
|
|
|
return None
|
|
|
|
def _build_nudge(self, tool_name: str, count: int) -> str:
|
|
"""Build a nudge prompt to break the fixation loop."""
|
|
return (
|
|
f"[SYSTEM: You have called `{tool_name}` {count} times in a row "
|
|
f"without switching tools. This suggests a fixation loop. "
|
|
f"Consider:\n"
|
|
f"1. Is the tool returning an error? Read the error carefully.\n"
|
|
f"2. Is there a different tool that could help?\n"
|
|
f"3. Should you ask the user for clarification?\n"
|
|
f"4. Is the task actually complete?\n"
|
|
f"Break the loop by trying a different approach.]"
|
|
)
|
|
|
|
def reset(self) -> None:
|
|
"""Reset the detector state."""
|
|
self._history.clear()
|
|
self._current_streak = ""
|
|
self._streak_count = 0
|
|
|
|
def get_streak_info(self) -> dict:
|
|
"""Get current streak information."""
|
|
return {
|
|
"current_tool": self._current_streak,
|
|
"streak_count": self._streak_count,
|
|
"threshold": self.threshold,
|
|
"at_threshold": self._streak_count >= self.threshold,
|
|
"nudges_sent": self._nudges_sent,
|
|
}
|
|
|
|
def format_report(self) -> str:
|
|
"""Format fixation events as a report."""
|
|
if not self._events:
|
|
return "No tool fixation detected."
|
|
|
|
lines = [
|
|
f"Tool Fixation Report ({len(self._events)} events)",
|
|
"=" * 40,
|
|
]
|
|
for e in self._events:
|
|
lines.append(f" {e.tool_name}: {e.streak_length} consecutive calls (threshold: {e.threshold})")
|
|
return "\n".join(lines)
|
|
|
|
|
|
# Singleton
|
|
_detector: Optional[ToolFixationDetector] = None
|
|
|
|
|
|
def get_fixation_detector() -> ToolFixationDetector:
|
|
"""Get or create the singleton detector."""
|
|
global _detector
|
|
if _detector is None:
|
|
_detector = ToolFixationDetector()
|
|
return _detector
|
|
|
|
|
|
def reset_fixation_detector() -> None:
|
|
"""Reset the singleton."""
|
|
global _detector
|
|
_detector = None
|