Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
0b72884750 |
146
agent/time_aware_routing.py
Normal file
146
agent/time_aware_routing.py
Normal file
@@ -0,0 +1,146 @@
|
||||
"""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)
|
||||
@@ -1,224 +0,0 @@
|
||||
"""
|
||||
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)
|
||||
58
tests/test_time_aware_routing.py
Normal file
58
tests/test_time_aware_routing.py
Normal file
@@ -0,0 +1,58 @@
|
||||
"""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
|
||||
Reference in New Issue
Block a user