Compare commits
4 Commits
fix/889
...
fix/921-ha
| Author | SHA1 | Date | |
|---|---|---|---|
| 4cdda8701d | |||
| a80d30b342 | |||
| f098cf8c4a | |||
| c6f2855745 |
78
.githooks/pre-commit-hardcoded-path.py
Normal file
78
.githooks/pre-commit-hardcoded-path.py
Normal file
@@ -0,0 +1,78 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Pre-commit hook: Reject hardcoded home-directory paths.
|
||||
|
||||
Install:
|
||||
cp pre-commit-hardcoded-path.py .git/hooks/pre-commit-hardcoded-path
|
||||
chmod +x .git/hooks/pre-commit-hardcoded-path
|
||||
|
||||
Or add to .pre-commit-config.yaml
|
||||
"""
|
||||
|
||||
import sys
|
||||
import subprocess
|
||||
import re
|
||||
|
||||
PATTERNS = [
|
||||
(r"/Users/[\w.\-]+/", "macOS home directory"),
|
||||
(r"/home/[\w.\-]+/", "Linux home directory"),
|
||||
(r"(?<![\w/])~/", "unexpanded tilde"),
|
||||
]
|
||||
|
||||
NOQA = re.compile(r"#\s*noqa:?\s*hardcoded-path-ok")
|
||||
|
||||
def get_staged_files():
|
||||
result = subprocess.run(
|
||||
["git", "diff", "--cached", "--name-only", "--diff-filter=ACM"],
|
||||
capture_output=True, text=True
|
||||
)
|
||||
return [f for f in result.stdout.strip().split("\n") if f.endswith(".py")]
|
||||
|
||||
def check_file(filepath):
|
||||
try:
|
||||
result = subprocess.run(
|
||||
["git", "show", f":{filepath}"],
|
||||
capture_output=True, text=True
|
||||
)
|
||||
content = result.stdout
|
||||
except Exception:
|
||||
return []
|
||||
|
||||
violations = []
|
||||
for i, line in enumerate(content.split("\n"), 1):
|
||||
if line.strip().startswith("#"):
|
||||
continue
|
||||
if line.strip().startswith(("import ", "from ")):
|
||||
continue
|
||||
if NOQA.search(line):
|
||||
continue
|
||||
for pattern, desc in PATTERNS:
|
||||
if re.search(pattern, line):
|
||||
violations.append((filepath, i, line.strip(), desc))
|
||||
break
|
||||
return violations
|
||||
|
||||
def main():
|
||||
files = get_staged_files()
|
||||
if not files:
|
||||
sys.exit(0)
|
||||
|
||||
all_violations = []
|
||||
for f in files:
|
||||
all_violations.extend(check_file(f))
|
||||
|
||||
if all_violations:
|
||||
print("ERROR: Hardcoded home directory paths detected:")
|
||||
print()
|
||||
for filepath, line_no, line, desc in all_violations:
|
||||
print(f" {filepath}:{line_no}: {desc}")
|
||||
print(f" {line[:100]}")
|
||||
print()
|
||||
print("Fix: Use $HOME, relative paths, or get_hermes_home().")
|
||||
print("Override: Add '# noqa: hardcoded-path-ok' to the line.")
|
||||
sys.exit(1)
|
||||
|
||||
sys.exit(0)
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,146 +0,0 @@
|
||||
"""Time-aware model routing for cron jobs.
|
||||
|
||||
Routes cron tasks to more capable models during off-hours when the user
|
||||
is not present to correct errors. Reduces error rates during high-error
|
||||
time windows (e.g., 18:00 evening batches).
|
||||
|
||||
Usage:
|
||||
from agent.time_aware_routing import resolve_time_aware_model
|
||||
model = resolve_time_aware_model(base_model="mimo-v2-pro", is_cron=True)
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import time
|
||||
from dataclasses import dataclass
|
||||
from typing import Dict, Optional
|
||||
|
||||
|
||||
# Error rate data from empirical audit (2026-04-12)
|
||||
# Higher error rates during these hours suggest routing to better models
|
||||
_HIGH_ERROR_HOURS = {
|
||||
18: 9.4, # 18:00 — 9.4% error rate (evening cron batches)
|
||||
19: 8.1,
|
||||
20: 7.5,
|
||||
21: 6.8,
|
||||
22: 6.2,
|
||||
23: 5.9,
|
||||
0: 5.5,
|
||||
1: 5.2,
|
||||
}
|
||||
|
||||
# Low error hours — default model is fine
|
||||
_LOW_ERROR_HOURS = set(range(6, 18)) # 06:00-17:59
|
||||
|
||||
# Default fallback models by time zone
|
||||
_DEFAULT_STRONG_MODEL = os.getenv("CRON_STRONG_MODEL", "xiaomi/mimo-v2-pro")
|
||||
_DEFAULT_CHEAP_MODEL = os.getenv("CRON_CHEAP_MODEL", "qwen2.5:7b")
|
||||
_ERROR_THRESHOLD = float(os.getenv("CRON_ERROR_THRESHOLD", "6.0")) # % error rate
|
||||
|
||||
|
||||
@dataclass
|
||||
class RoutingDecision:
|
||||
"""Result of time-aware routing."""
|
||||
model: str
|
||||
provider: str
|
||||
reason: str
|
||||
hour: int
|
||||
error_rate: float
|
||||
is_off_hours: bool
|
||||
|
||||
|
||||
def get_hour_error_rate(hour: int) -> float:
|
||||
"""Get expected error rate for a given hour (0-23)."""
|
||||
return _HIGH_ERROR_HOURS.get(hour, 4.0) # Default 4% for unlisted hours
|
||||
|
||||
|
||||
def is_off_hours(hour: int) -> bool:
|
||||
"""Check if hour is considered off-hours (higher error rates)."""
|
||||
return hour not in _LOW_ERROR_HOURS
|
||||
|
||||
|
||||
def resolve_time_aware_model(
|
||||
base_model: str = "",
|
||||
base_provider: str = "",
|
||||
is_cron: bool = False,
|
||||
hour: Optional[int] = None,
|
||||
) -> RoutingDecision:
|
||||
"""Resolve model based on time of day and task type.
|
||||
|
||||
During off-hours (evening/night), routes to stronger models for cron
|
||||
jobs to compensate for lack of human oversight.
|
||||
|
||||
Args:
|
||||
base_model: The model that would normally be used.
|
||||
base_provider: The provider for the base model.
|
||||
is_cron: Whether this is a cron job (vs interactive session).
|
||||
hour: Override hour (for testing). Defaults to current hour.
|
||||
|
||||
Returns:
|
||||
RoutingDecision with model, provider, and reasoning.
|
||||
"""
|
||||
if hour is None:
|
||||
hour = time.localtime().tm_hour
|
||||
|
||||
error_rate = get_hour_error_rate(hour)
|
||||
off_hours = is_off_hours(hour)
|
||||
|
||||
# Interactive sessions always use the base model (user can correct errors)
|
||||
if not is_cron:
|
||||
return RoutingDecision(
|
||||
model=base_model or _DEFAULT_CHEAP_MODEL,
|
||||
provider=base_provider,
|
||||
reason="Interactive session — user can correct errors",
|
||||
hour=hour,
|
||||
error_rate=error_rate,
|
||||
is_off_hours=off_hours,
|
||||
)
|
||||
|
||||
# Cron jobs during low-error hours: use base model
|
||||
if not off_hours and error_rate < _ERROR_THRESHOLD:
|
||||
return RoutingDecision(
|
||||
model=base_model or _DEFAULT_CHEAP_MODEL,
|
||||
provider=base_provider,
|
||||
reason=f"Low-error hours ({hour}:00, {error_rate}% expected)",
|
||||
hour=hour,
|
||||
error_rate=error_rate,
|
||||
is_off_hours=False,
|
||||
)
|
||||
|
||||
# Cron jobs during high-error hours: upgrade to stronger model
|
||||
if error_rate >= _ERROR_THRESHOLD:
|
||||
return RoutingDecision(
|
||||
model=_DEFAULT_STRONG_MODEL,
|
||||
provider="nous",
|
||||
reason=f"High-error hours ({hour}:00, {error_rate}% expected) — using stronger model",
|
||||
hour=hour,
|
||||
error_rate=error_rate,
|
||||
is_off_hours=True,
|
||||
)
|
||||
|
||||
# Off-hours but low error: use base model
|
||||
return RoutingDecision(
|
||||
model=base_model or _DEFAULT_CHEAP_MODEL,
|
||||
provider=base_provider,
|
||||
reason=f"Off-hours but low error ({hour}:00, {error_rate}%)",
|
||||
hour=hour,
|
||||
error_rate=error_rate,
|
||||
is_off_hours=off_hours,
|
||||
)
|
||||
|
||||
|
||||
def get_routing_report() -> str:
|
||||
"""Get a report of time-based routing decisions for the next 24 hours."""
|
||||
lines = ["Time-Aware Model Routing (24h forecast)", "=" * 40, ""]
|
||||
lines.append(f"Error threshold: {_ERROR_THRESHOLD}%")
|
||||
lines.append(f"Strong model: {_DEFAULT_STRONG_MODEL}")
|
||||
lines.append(f"Cheap model: {_DEFAULT_CHEAP_MODEL}")
|
||||
lines.append("")
|
||||
|
||||
for h in range(24):
|
||||
decision = resolve_time_aware_model(is_cron=True, hour=h)
|
||||
icon = "\U0001f7e2" if decision.model == _DEFAULT_CHEAP_MODEL else "\U0001f534"
|
||||
lines.append(f" {h:02d}:00 {icon} {decision.model:25s} ({decision.error_rate}% error)")
|
||||
|
||||
return "\n".join(lines)
|
||||
@@ -28,6 +28,7 @@ from typing import Dict, Any, List, Optional, Tuple
|
||||
|
||||
from tools.registry import discover_builtin_tools, registry
|
||||
from tools.tool_pokayoke import validate_tool_call, reset_circuit_breaker, get_hallucination_stats
|
||||
from tools.hardcoded_path_guard import guard_tool_dispatch as _guard_hardcoded_paths
|
||||
from toolsets import resolve_toolset, validate_toolset
|
||||
from agent.tool_orchestrator import orchestrator
|
||||
|
||||
@@ -501,6 +502,12 @@ def handle_function_call(
|
||||
# Prefer the caller-provided list so subagents can't overwrite
|
||||
# the parent's tool set via the process-global.
|
||||
sandbox_enabled = enabled_tools if enabled_tools is not None else _last_resolved_tool_names
|
||||
# Poka-yoke #921: guard against hardcoded home-directory paths
|
||||
_hardcoded_err = _guard_hardcoded_paths(function_name, function_args)
|
||||
if _hardcoded_err:
|
||||
logger.warning(f"Hardcoded path blocked: {function_name}")
|
||||
return _hardcoded_err
|
||||
|
||||
# Poka-yoke: validate tool call before dispatch
|
||||
is_valid, corrected_name, corrected_params, pokayoke_messages = validate_tool_call(function_name, function_args)
|
||||
if not is_valid:
|
||||
|
||||
@@ -1,58 +0,0 @@
|
||||
"""Tests for time-aware model routing."""
|
||||
|
||||
import pytest
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
||||
|
||||
from agent.time_aware_routing import (
|
||||
resolve_time_aware_model,
|
||||
get_hour_error_rate,
|
||||
is_off_hours,
|
||||
get_routing_report,
|
||||
)
|
||||
|
||||
|
||||
class TestErrorRates:
|
||||
def test_evening_high_error(self):
|
||||
assert get_hour_error_rate(18) == 9.4
|
||||
assert get_hour_error_rate(19) == 8.1
|
||||
|
||||
def test_morning_low_error(self):
|
||||
assert get_hour_error_rate(9) == 4.0
|
||||
assert get_hour_error_rate(12) == 4.0
|
||||
|
||||
def test_default_for_unknown(self):
|
||||
assert get_hour_error_rate(15) == 4.0
|
||||
|
||||
|
||||
class TestOffHours:
|
||||
def test_evening_is_off_hours(self):
|
||||
assert is_off_hours(20) is True
|
||||
assert is_off_hours(2) is True
|
||||
|
||||
def test_business_hours_not_off(self):
|
||||
assert is_off_hours(9) is False
|
||||
assert is_off_hours(14) is False
|
||||
|
||||
|
||||
class TestRouting:
|
||||
def test_interactive_uses_base_model(self):
|
||||
d = resolve_time_aware_model("my-model", "my-provider", is_cron=False, hour=18)
|
||||
assert d.model == "my-model"
|
||||
assert "Interactive" in d.reason
|
||||
|
||||
def test_cron_low_error_uses_base(self):
|
||||
d = resolve_time_aware_model("cheap-model", is_cron=True, hour=10)
|
||||
assert d.model == "cheap-model"
|
||||
|
||||
def test_cron_high_error_upgrades(self):
|
||||
d = resolve_time_aware_model("cheap-model", is_cron=True, hour=18)
|
||||
assert d.model != "cheap-model"
|
||||
assert d.is_off_hours is True
|
||||
|
||||
def test_routing_report(self):
|
||||
report = get_routing_report()
|
||||
assert "Time-Aware Model Routing" in report
|
||||
assert "18:00" in report
|
||||
113
tools/hardcoded_path_guard.py
Normal file
113
tools/hardcoded_path_guard.py
Normal file
@@ -0,0 +1,113 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Hardcoded Path Guard — Poka-Yoke #921
|
||||
|
||||
Detects and blocks hardcoded home-directory paths in tool arguments.
|
||||
These paths work on one machine but break on others, VPS deployments,
|
||||
or when HOME changes.
|
||||
|
||||
Usage:
|
||||
from tools.hardcoded_path_guard import check_path, validate_tool_args
|
||||
|
||||
# Check a single path
|
||||
err = check_path("/Users/apayne/.hermes/config.yaml")
|
||||
|
||||
# Validate all path-like args in a tool call
|
||||
clean_args, warnings = validate_tool_args("read_file", {"path": "/home/user/file.txt"})
|
||||
"""
|
||||
|
||||
import os
|
||||
import re
|
||||
import json as _json
|
||||
from typing import Dict, List, Optional, Tuple, Any
|
||||
|
||||
# Patterns that indicate hardcoded home directories
|
||||
HARDCODED_PATTERNS = [
|
||||
(r"/Users/[\w.\-]+/", "macOS home directory (/Users/...)"),
|
||||
(r"/home/[\w.\-]+/", "Linux home directory (/home/...)"),
|
||||
(r"(?<![\w/])~/", "unexpanded tilde (~/)"),
|
||||
(r"/root/", "root home directory (/root/)"),
|
||||
]
|
||||
|
||||
_COMPILED_PATTERNS = [(re.compile(p), desc) for p, desc in HARDCODED_PATTERNS]
|
||||
_NOQA_PATTERN = re.compile(r"#\s*noqa:?\s*hardcoded-path-ok")
|
||||
|
||||
_PATH_ARG_NAMES = frozenset({
|
||||
"path", "file_path", "filepath", "dir", "directory", "dest", "source",
|
||||
"input", "output", "src", "dst", "target", "location", "file",
|
||||
"image_path", "script", "config", "log_file",
|
||||
})
|
||||
|
||||
|
||||
def has_hardcoded_path(text: str) -> Optional[str]:
|
||||
if _NOQA_PATTERN.search(text):
|
||||
return None
|
||||
for pattern, desc in _COMPILED_PATTERNS:
|
||||
if pattern.search(text):
|
||||
return desc
|
||||
return None
|
||||
|
||||
|
||||
def check_path(path_value: str) -> Optional[str]:
|
||||
if not isinstance(path_value, str):
|
||||
return None
|
||||
match_desc = has_hardcoded_path(path_value)
|
||||
if match_desc:
|
||||
return (
|
||||
f"Path contains hardcoded home directory ({match_desc}): '{path_value}'. "
|
||||
f"Use $HOME, relative paths, or get_hermes_home(). "
|
||||
f"Add '# noqa: hardcoded-path-ok' if intentional."
|
||||
)
|
||||
return None
|
||||
|
||||
|
||||
def validate_tool_args(tool_name: str, args: Dict[str, Any]) -> Tuple[Dict[str, Any], List[str]]:
|
||||
warnings = []
|
||||
for key, value in args.items():
|
||||
if key.lower() not in _PATH_ARG_NAMES:
|
||||
continue
|
||||
if isinstance(value, str):
|
||||
err = check_path(value)
|
||||
if err:
|
||||
warnings.append(err)
|
||||
elif isinstance(value, list):
|
||||
for item in value:
|
||||
if isinstance(item, str):
|
||||
err = check_path(item)
|
||||
if err:
|
||||
warnings.append(err)
|
||||
return args, warnings
|
||||
|
||||
|
||||
def scan_source_for_violations(source_code: str, filename: str = "") -> List[Tuple[int, str, str]]:
|
||||
violations = []
|
||||
lines = source_code.split("\n")
|
||||
for i, line in enumerate(lines, 1):
|
||||
stripped = line.strip()
|
||||
if stripped.startswith("#"):
|
||||
if _NOQA_PATTERN.search(line):
|
||||
continue
|
||||
continue
|
||||
if stripped.startswith("import ") or stripped.startswith("from "):
|
||||
continue
|
||||
for pattern, desc in _COMPILED_PATTERNS:
|
||||
match = pattern.search(line)
|
||||
if match:
|
||||
if _NOQA_PATTERN.search(line):
|
||||
continue
|
||||
violations.append((i, line.strip(), desc))
|
||||
break
|
||||
return violations
|
||||
|
||||
|
||||
def guard_tool_dispatch(tool_name: str, args: Dict[str, Any]) -> Optional[str]:
|
||||
_, warnings = validate_tool_args(tool_name, args)
|
||||
if warnings:
|
||||
return _json.dumps({
|
||||
"error": "Hardcoded home directory path detected",
|
||||
"details": warnings,
|
||||
"suggestion": "Use $HOME, relative paths, or get_hermes_home() instead of hardcoded paths.",
|
||||
"pokayoke": True,
|
||||
"rule": "hardcoded-path-guard"
|
||||
})
|
||||
return None
|
||||
@@ -44,6 +44,34 @@ from typing import Dict, Any, Optional, Tuple
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _format_error(
|
||||
message: str,
|
||||
skill_name: str = None,
|
||||
file_path: str = None,
|
||||
suggestion: str = None,
|
||||
context: dict = None,
|
||||
) -> Dict[str, Any]:
|
||||
"""Format an error with rich context for better debugging."""
|
||||
parts = [message]
|
||||
if skill_name:
|
||||
parts.append(f"Skill: {skill_name}")
|
||||
if file_path:
|
||||
parts.append(f"File: {file_path}")
|
||||
if suggestion:
|
||||
parts.append(f"Suggestion: {suggestion}")
|
||||
if context:
|
||||
for key, value in context.items():
|
||||
parts.append(f"{key}: {value}")
|
||||
return {
|
||||
"success": False,
|
||||
"error": " | ".join(parts),
|
||||
"skill_name": skill_name,
|
||||
"file_path": file_path,
|
||||
"suggestion": suggestion,
|
||||
}
|
||||
|
||||
|
||||
# Import security scanner — agent-created skills get the same scrutiny as
|
||||
# community hub installs.
|
||||
try:
|
||||
|
||||
Reference in New Issue
Block a user