Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 517e2c571e |
@@ -1,156 +0,0 @@
|
||||
"""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
|
||||
224
gateway/config_validator.py
Normal file
224
gateway/config_validator.py
Normal file
@@ -0,0 +1,224 @@
|
||||
"""
|
||||
Gateway Config Validator & Fallback Fix — #892.
|
||||
|
||||
Validates gateway configuration and provides sensible defaults
|
||||
for missing keys to prevent fallback chain breaks.
|
||||
"""
|
||||
|
||||
import logging
|
||||
import os
|
||||
from typing import Dict, Any, List, Optional
|
||||
from dataclasses import dataclass, field
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@dataclass
|
||||
class ConfigIssue:
|
||||
"""A configuration issue found during validation."""
|
||||
key: str
|
||||
severity: str # error, warning, info
|
||||
message: str
|
||||
fix: str
|
||||
|
||||
|
||||
@dataclass
|
||||
class ConfigValidation:
|
||||
"""Result of config validation."""
|
||||
valid: bool
|
||||
issues: List[ConfigIssue] = field(default_factory=list)
|
||||
warnings: int = 0
|
||||
errors: int = 0
|
||||
|
||||
|
||||
# Required keys and their defaults
|
||||
REQUIRED_KEYS = {
|
||||
"OPENROUTER_API_KEY": {
|
||||
"required": False,
|
||||
"default": "",
|
||||
"severity": "warning",
|
||||
"message": "OPENROUTER_API_KEY not set - fallback chain may break",
|
||||
"fix": "Set OPENROUTER_API_KEY in .env for OpenRouter provider",
|
||||
},
|
||||
"API_SERVER_KEY": {
|
||||
"required": False,
|
||||
"default": "",
|
||||
"severity": "warning",
|
||||
"message": "API_SERVER_KEY not configured",
|
||||
"fix": "Set API_SERVER_KEY in .env for API server auth",
|
||||
},
|
||||
"GITEA_TOKEN": {
|
||||
"required": False,
|
||||
"default": "",
|
||||
"severity": "info",
|
||||
"message": "GITEA_TOKEN not set - Gitea features disabled",
|
||||
"fix": "Set GITEA_TOKEN in .env for Gitea integration",
|
||||
},
|
||||
}
|
||||
|
||||
# Config validation rules
|
||||
VALIDATION_RULES = [
|
||||
{
|
||||
"key": "idle_minutes",
|
||||
"validate": lambda v: isinstance(v, (int, float)) and v > 0,
|
||||
"message": "Invalid idle_minutes={v} - must be > 0",
|
||||
"fix": "Set idle_minutes to positive integer (default: 30)",
|
||||
},
|
||||
{
|
||||
"key": "max_skills_discord",
|
||||
"validate": lambda v: isinstance(v, int) and v <= 100,
|
||||
"message": "Discord slash command limit reached ({v}/100) - skills not registered",
|
||||
"fix": "Reduce skills or paginate registration",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
def validate_config(config: Dict[str, Any]) -> ConfigValidation:
|
||||
"""
|
||||
Validate gateway configuration.
|
||||
|
||||
Args:
|
||||
config: Configuration dictionary
|
||||
|
||||
Returns:
|
||||
ConfigValidation with issues found
|
||||
"""
|
||||
issues = []
|
||||
|
||||
# Check required keys
|
||||
for key, spec in REQUIRED_KEYS.items():
|
||||
value = config.get(key) or os.environ.get(key) or spec["default"]
|
||||
if spec["required"] and not value:
|
||||
issues.append(ConfigIssue(
|
||||
key=key,
|
||||
severity=spec["severity"],
|
||||
message=spec["message"],
|
||||
fix=spec["fix"],
|
||||
))
|
||||
elif not value and spec["severity"] != "error":
|
||||
issues.append(ConfigIssue(
|
||||
key=key,
|
||||
severity=spec["severity"],
|
||||
message=spec["message"],
|
||||
fix=spec["fix"],
|
||||
))
|
||||
|
||||
# Check validation rules
|
||||
for rule in VALIDATION_RULES:
|
||||
value = config.get(rule["key"])
|
||||
if value is not None:
|
||||
if not rule["validate"](value):
|
||||
issues.append(ConfigIssue(
|
||||
key=rule["key"],
|
||||
severity="error",
|
||||
message=rule["message"].format(v=value),
|
||||
fix=rule["fix"],
|
||||
))
|
||||
|
||||
errors = sum(1 for i in issues if i.severity == "error")
|
||||
warnings = sum(1 for i in issues if i.severity == "warning")
|
||||
|
||||
return ConfigValidation(
|
||||
valid=errors == 0,
|
||||
issues=issues,
|
||||
warnings=warnings,
|
||||
errors=errors,
|
||||
)
|
||||
|
||||
|
||||
def apply_defaults(config: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""
|
||||
Apply default values for missing config keys.
|
||||
|
||||
Args:
|
||||
config: Configuration dictionary
|
||||
|
||||
Returns:
|
||||
Config with defaults applied
|
||||
"""
|
||||
result = dict(config)
|
||||
|
||||
for key, spec in REQUIRED_KEYS.items():
|
||||
if key not in result or not result[key]:
|
||||
default = os.environ.get(key) or spec["default"]
|
||||
if default:
|
||||
result[key] = default
|
||||
logger.debug("Applied default for %s", key)
|
||||
|
||||
# Apply validation defaults
|
||||
if "idle_minutes" not in result or not result["idle_minutes"] or result["idle_minutes"] <= 0:
|
||||
result["idle_minutes"] = 30
|
||||
logger.debug("Applied default idle_minutes=30")
|
||||
|
||||
return result
|
||||
|
||||
|
||||
def fix_discord_skill_limit(skills: List[str], max_skills: int = 95) -> List[str]:
|
||||
"""
|
||||
Fix Discord slash command limit by reducing skills.
|
||||
|
||||
Args:
|
||||
skills: List of skill names
|
||||
max_skills: Maximum skills to register (default 95, leaving room for built-ins)
|
||||
|
||||
Returns:
|
||||
Reduced skill list
|
||||
"""
|
||||
if len(skills) <= max_skills:
|
||||
return skills
|
||||
|
||||
logger.warning(
|
||||
"Discord skill limit: %d skills exceeds %d limit, truncating",
|
||||
len(skills), max_skills
|
||||
)
|
||||
|
||||
# Keep first max_skills (alphabetical priority)
|
||||
return sorted(skills)[:max_skills]
|
||||
|
||||
|
||||
def validate_provider_config(provider: str, config: Dict[str, Any]) -> ConfigIssue:
|
||||
"""
|
||||
Validate provider-specific configuration.
|
||||
|
||||
Args:
|
||||
provider: Provider name
|
||||
config: Provider config
|
||||
|
||||
Returns:
|
||||
ConfigIssue if invalid, None if valid
|
||||
"""
|
||||
if provider == "local-llama.cpp":
|
||||
# Check if llama.cpp is configured
|
||||
if not config.get("model_path") and not config.get("base_url"):
|
||||
return ConfigIssue(
|
||||
key=f"provider.{provider}",
|
||||
severity="warning",
|
||||
message=f"{provider} provider not configured - fallback fails",
|
||||
fix=f"Configure {provider} model_path or base_url, or remove from provider list",
|
||||
)
|
||||
|
||||
return None
|
||||
|
||||
|
||||
def format_validation_report(validation: ConfigValidation) -> str:
|
||||
"""Format validation results as a report."""
|
||||
lines = [
|
||||
"=" * 50,
|
||||
"GATEWAY CONFIG VALIDATION",
|
||||
"=" * 50,
|
||||
"",
|
||||
f"Status: {'VALID' if validation.valid else 'INVALID'}",
|
||||
f"Errors: {validation.errors}",
|
||||
f"Warnings: {validation.warnings}",
|
||||
"",
|
||||
]
|
||||
|
||||
if validation.issues:
|
||||
lines.append("Issues:")
|
||||
for issue in validation.issues:
|
||||
icon = "❌" if issue.severity == "error" else "⚠️" if issue.severity == "warning" else "ℹ️"
|
||||
lines.append(f" {icon} [{issue.key}] {issue.message}")
|
||||
lines.append(f" Fix: {issue.fix}")
|
||||
lines.append("")
|
||||
|
||||
return "\n".join(lines)
|
||||
@@ -1,76 +0,0 @@
|
||||
"""Tests for tool fixation detection."""
|
||||
|
||||
import pytest
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
||||
|
||||
from agent.tool_fixation_detector import ToolFixationDetector, get_fixation_detector
|
||||
|
||||
|
||||
class TestFixationDetection:
|
||||
def test_no_fixation_below_threshold(self):
|
||||
d = ToolFixationDetector(threshold=5)
|
||||
for i in range(4):
|
||||
assert d.record("execute_code") is None
|
||||
|
||||
def test_fixation_at_threshold(self):
|
||||
d = ToolFixationDetector(threshold=3)
|
||||
d.record("execute_code")
|
||||
d.record("execute_code")
|
||||
nudge = d.record("execute_code")
|
||||
assert nudge is not None
|
||||
assert "execute_code" in nudge
|
||||
assert "3 times" in nudge
|
||||
|
||||
def test_fixation_above_threshold(self):
|
||||
d = ToolFixationDetector(threshold=3)
|
||||
d.record("execute_code")
|
||||
d.record("execute_code")
|
||||
d.record("execute_code") # threshold hit
|
||||
nudge = d.record("execute_code") # still nudging
|
||||
assert nudge is not None
|
||||
|
||||
def test_streak_resets_on_different_tool(self):
|
||||
d = ToolFixationDetector(threshold=3)
|
||||
d.record("execute_code")
|
||||
d.record("execute_code")
|
||||
d.record("terminal") # breaks streak
|
||||
assert d._streak_count == 1
|
||||
assert d._current_streak == "terminal"
|
||||
|
||||
def test_nudges_sent_counter(self):
|
||||
d = ToolFixationDetector(threshold=2)
|
||||
d.record("a")
|
||||
d.record("a") # nudge 1
|
||||
d.record("a") # nudge 2
|
||||
assert d.nudges_sent == 2
|
||||
|
||||
def test_events_recorded(self):
|
||||
d = ToolFixationDetector(threshold=2)
|
||||
d.record("x")
|
||||
d.record("x")
|
||||
assert len(d.events) == 1
|
||||
assert d.events[0].tool_name == "x"
|
||||
assert d.events[0].streak_length == 2
|
||||
|
||||
def test_report(self):
|
||||
d = ToolFixationDetector(threshold=2)
|
||||
d.record("x")
|
||||
d.record("x")
|
||||
report = d.format_report()
|
||||
assert "x" in report
|
||||
|
||||
def test_reset(self):
|
||||
d = ToolFixationDetector(threshold=2)
|
||||
d.record("x")
|
||||
d.record("x")
|
||||
d.reset()
|
||||
assert d._streak_count == 0
|
||||
assert d._current_streak == ""
|
||||
|
||||
def test_singleton(self):
|
||||
d1 = get_fixation_detector()
|
||||
d2 = get_fixation_detector()
|
||||
assert d1 is d2
|
||||
Reference in New Issue
Block a user