Implements full bug lifecycle management (open → in_progress → resolved): Bug Watcher (testing/oversight/bug_watcher.py): - Add BugStatus enum with open/in_progress/resolved states - Add SQLite persistence with status tracking and indexes - New methods: update_bug_status(), get_bug(), log_bug() - Extended CLI: update, get, log commands with filters API Endpoints (ui/server.ts): - GET /api/bugs - List bugs with status/severity/phase filters - GET /api/bugs/summary - Bug statistics by status and severity - GET /api/bugs/:id - Single bug details - POST /api/bugs - Log new bug - PATCH /api/bugs/:id - Update bug status UI Dashboard: - New "Bugs" tab with summary cards (Total/Open/In Progress/Resolved) - Filter dropdowns for status and severity - Bug list with status badges and severity indicators - Detail panel with action buttons for status transitions - WebSocket broadcasts for real-time updates CLI Wrapper (bin/bugs): - bugs list [--status X] [--severity Y] - bugs get <id> - bugs log -m "message" [--severity high] - bugs update <id> <status> [--notes "..."] - bugs status Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
1067 lines
39 KiB
Python
1067 lines
39 KiB
Python
"""
|
|
Bug Window Watcher
|
|
==================
|
|
Real-time monitoring of every pipeline stage with anomaly detection.
|
|
|
|
Features:
|
|
- Monitors all stages in real-time
|
|
- Surfaces anomalies, regressions, unhandled errors
|
|
- Links findings to phase, directory, STATUS, and checkpoint entries
|
|
"""
|
|
|
|
import json
|
|
import time
|
|
import hashlib
|
|
import sqlite3
|
|
import subprocess
|
|
from datetime import datetime, timezone, timedelta
|
|
from dataclasses import dataclass, field, asdict
|
|
from enum import Enum
|
|
from pathlib import Path
|
|
from typing import Any, Optional
|
|
import redis
|
|
|
|
|
|
class AnomalyType(str, Enum):
|
|
"""Types of anomalies the watcher can detect"""
|
|
UNHANDLED_ERROR = "unhandled_error"
|
|
REGRESSION = "regression"
|
|
PERFORMANCE_DEGRADATION = "performance_degradation"
|
|
MISSING_ARTIFACT = "missing_artifact"
|
|
STATE_INCONSISTENCY = "state_inconsistency"
|
|
HEALTH_CHECK_FAILURE = "health_check_failure"
|
|
DEPENDENCY_UNAVAILABLE = "dependency_unavailable"
|
|
TIMEOUT = "timeout"
|
|
UNEXPECTED_OUTPUT = "unexpected_output"
|
|
SECURITY_VIOLATION = "security_violation"
|
|
|
|
|
|
class Severity(str, Enum):
|
|
"""Severity levels for anomalies"""
|
|
CRITICAL = "critical" # System compromised, immediate action
|
|
HIGH = "high" # Major functionality impacted
|
|
MEDIUM = "medium" # Degraded but functional
|
|
LOW = "low" # Minor issue, informational
|
|
INFO = "info" # Tracking only
|
|
|
|
|
|
class BugStatus(str, Enum):
|
|
"""Status tracking for bugs/anomalies"""
|
|
OPEN = "open" # Newly detected, not yet addressed
|
|
IN_PROGRESS = "in_progress" # Being worked on
|
|
RESOLVED = "resolved" # Fixed and verified
|
|
|
|
|
|
@dataclass
|
|
class Anomaly:
|
|
"""Represents a detected anomaly"""
|
|
id: str
|
|
type: AnomalyType
|
|
severity: Severity
|
|
phase: int
|
|
phase_name: str
|
|
directory: str
|
|
message: str
|
|
details: dict = field(default_factory=dict)
|
|
stack_trace: Optional[str] = None
|
|
checkpoint_id: Optional[str] = None
|
|
status_file: Optional[str] = None
|
|
detected_at: str = ""
|
|
# Status tracking
|
|
status: BugStatus = BugStatus.OPEN
|
|
resolved: bool = False # Kept for backwards compatibility
|
|
resolution_notes: Optional[str] = None
|
|
assigned_to: Optional[str] = None
|
|
updated_at: Optional[str] = None
|
|
|
|
def __post_init__(self):
|
|
if not self.detected_at:
|
|
self.detected_at = datetime.now(timezone.utc).isoformat()
|
|
if not self.id:
|
|
self.id = f"anom-{hashlib.sha256(f'{self.type}{self.phase}{self.message}{self.detected_at}'.encode()).hexdigest()[:12]}"
|
|
# Sync resolved with status for backwards compatibility
|
|
if self.resolved and self.status == BugStatus.OPEN:
|
|
self.status = BugStatus.RESOLVED
|
|
elif self.status == BugStatus.RESOLVED:
|
|
self.resolved = True
|
|
|
|
|
|
@dataclass
|
|
class WatcherState:
|
|
"""Current state of the bug watcher"""
|
|
active: bool = False
|
|
started_at: Optional[str] = None
|
|
anomalies_detected: int = 0
|
|
phases_watched: list = field(default_factory=list)
|
|
last_scan_at: Optional[str] = None
|
|
error_count: int = 0
|
|
|
|
|
|
class BugWindowWatcher:
|
|
"""
|
|
Real-time anomaly detection across all pipeline stages.
|
|
|
|
Monitors:
|
|
- Phase transitions and state changes
|
|
- Error logs and stack traces
|
|
- Performance metrics and timeouts
|
|
- Dependency availability
|
|
- Artifact integrity
|
|
- Security boundaries
|
|
"""
|
|
|
|
# Phase definitions
|
|
PHASES = {
|
|
1: "Foundation (Vault + Basic Infrastructure)",
|
|
2: "Vault Policy Engine",
|
|
3: "Execution Pipeline",
|
|
4: "Promotion and Revocation Engine",
|
|
5: "Agent Bootstrapping",
|
|
6: "Pipeline DSL, Agent Templates, Testing Framework",
|
|
7: "Hierarchical Teams & Learning System",
|
|
8: "Production Hardening",
|
|
9: "External Integrations",
|
|
10: "Multi-Tenant Support",
|
|
11: "Agent Marketplace",
|
|
12: "Observability",
|
|
}
|
|
|
|
# Phase -> key directories mapping
|
|
PHASE_DIRECTORIES = {
|
|
1: ["ledger", "bin"],
|
|
2: ["runtime"],
|
|
3: ["preflight", "wrappers", "evidence"],
|
|
4: ["runtime"],
|
|
5: ["agents", "checkpoint", "orchestrator"],
|
|
6: ["pipeline", "tests"],
|
|
7: ["teams", "analytics", "memory"],
|
|
8: ["runtime", "testing/oversight"],
|
|
9: ["integrations"],
|
|
10: ["teams"],
|
|
11: ["agents"],
|
|
12: ["analytics", "ui"],
|
|
}
|
|
|
|
def __init__(self, base_path: str = "/opt/agent-governance"):
|
|
self.base_path = Path(base_path)
|
|
self.ledger_db = self.base_path / "ledger" / "governance.db"
|
|
self.bug_db = self.base_path / "testing" / "oversight" / "bug_watcher.db"
|
|
self.checkpoint_dir = self.base_path / "checkpoint" / "storage"
|
|
self.state = WatcherState()
|
|
self.anomalies: list[Anomaly] = []
|
|
self._redis: Optional[redis.Redis] = None
|
|
self._setup_redis()
|
|
self._setup_bug_db()
|
|
|
|
def _setup_redis(self):
|
|
"""Connect to DragonflyDB for real-time state"""
|
|
try:
|
|
self._redis = redis.Redis(
|
|
host='127.0.0.1',
|
|
port=6379,
|
|
password='governance2026',
|
|
decode_responses=True
|
|
)
|
|
self._redis.ping()
|
|
except Exception:
|
|
self._redis = None
|
|
|
|
def _setup_bug_db(self):
|
|
"""Initialize SQLite database for bug tracking"""
|
|
conn = sqlite3.connect(self.bug_db)
|
|
cursor = conn.cursor()
|
|
cursor.execute("""
|
|
CREATE TABLE IF NOT EXISTS bugs (
|
|
id TEXT PRIMARY KEY,
|
|
type TEXT NOT NULL,
|
|
severity TEXT NOT NULL,
|
|
status TEXT NOT NULL DEFAULT 'open',
|
|
phase INTEGER NOT NULL,
|
|
phase_name TEXT NOT NULL,
|
|
directory TEXT NOT NULL,
|
|
message TEXT NOT NULL,
|
|
details TEXT,
|
|
stack_trace TEXT,
|
|
checkpoint_id TEXT,
|
|
status_file TEXT,
|
|
detected_at TEXT NOT NULL,
|
|
updated_at TEXT,
|
|
resolved_at TEXT,
|
|
resolution_notes TEXT,
|
|
assigned_to TEXT
|
|
)
|
|
""")
|
|
cursor.execute("""
|
|
CREATE INDEX IF NOT EXISTS idx_bugs_status ON bugs(status)
|
|
""")
|
|
cursor.execute("""
|
|
CREATE INDEX IF NOT EXISTS idx_bugs_severity ON bugs(severity)
|
|
""")
|
|
cursor.execute("""
|
|
CREATE INDEX IF NOT EXISTS idx_bugs_phase ON bugs(phase)
|
|
""")
|
|
conn.commit()
|
|
conn.close()
|
|
|
|
def _now(self) -> str:
|
|
return datetime.now(timezone.utc).isoformat()
|
|
|
|
def start(self) -> WatcherState:
|
|
"""Start the bug watcher"""
|
|
self.state.active = True
|
|
self.state.started_at = self._now()
|
|
self.state.phases_watched = list(self.PHASES.keys())
|
|
|
|
if self._redis:
|
|
self._redis.hset("oversight:watcher", mapping={
|
|
"active": "true",
|
|
"started_at": self.state.started_at,
|
|
"phases": json.dumps(self.state.phases_watched)
|
|
})
|
|
|
|
return self.state
|
|
|
|
def stop(self) -> WatcherState:
|
|
"""Stop the bug watcher"""
|
|
self.state.active = False
|
|
|
|
if self._redis:
|
|
self._redis.hset("oversight:watcher", "active", "false")
|
|
|
|
return self.state
|
|
|
|
def scan_all_phases(self) -> list[Anomaly]:
|
|
"""Scan all phases for anomalies"""
|
|
all_anomalies = []
|
|
|
|
for phase_num in self.PHASES:
|
|
anomalies = self.scan_phase(phase_num)
|
|
all_anomalies.extend(anomalies)
|
|
|
|
self.state.last_scan_at = self._now()
|
|
self.state.anomalies_detected = len(all_anomalies)
|
|
|
|
return all_anomalies
|
|
|
|
def scan_phase(self, phase_num: int) -> list[Anomaly]:
|
|
"""Scan a specific phase for anomalies"""
|
|
anomalies = []
|
|
phase_name = self.PHASES.get(phase_num, f"Phase {phase_num}")
|
|
directories = self.PHASE_DIRECTORIES.get(phase_num, [])
|
|
|
|
# 1. Check STATUS.md files for issues
|
|
for dir_name in directories:
|
|
dir_path = self.base_path / dir_name
|
|
if dir_path.exists():
|
|
status_anomalies = self._check_status_file(dir_path, phase_num, phase_name)
|
|
anomalies.extend(status_anomalies)
|
|
|
|
# 2. Check for recent errors in ledger
|
|
ledger_anomalies = self._check_ledger_errors(phase_num, phase_name)
|
|
anomalies.extend(ledger_anomalies)
|
|
|
|
# 3. Check dependency health
|
|
dep_anomalies = self._check_dependencies(phase_num, phase_name)
|
|
anomalies.extend(dep_anomalies)
|
|
|
|
# 4. Check checkpoint consistency
|
|
ckpt_anomalies = self._check_checkpoint_consistency(phase_num, phase_name)
|
|
anomalies.extend(ckpt_anomalies)
|
|
|
|
# 5. Phase-specific checks
|
|
specific_anomalies = self._run_phase_specific_checks(phase_num, phase_name)
|
|
anomalies.extend(specific_anomalies)
|
|
|
|
# Store anomalies
|
|
self.anomalies.extend(anomalies)
|
|
self._persist_anomalies(anomalies)
|
|
|
|
return anomalies
|
|
|
|
def _check_status_file(self, dir_path: Path, phase_num: int, phase_name: str) -> list[Anomaly]:
|
|
"""Check STATUS.md file for issues"""
|
|
anomalies = []
|
|
status_file = dir_path / "STATUS.md"
|
|
|
|
if not status_file.exists():
|
|
anomalies.append(Anomaly(
|
|
id="",
|
|
type=AnomalyType.MISSING_ARTIFACT,
|
|
severity=Severity.LOW,
|
|
phase=phase_num,
|
|
phase_name=phase_name,
|
|
directory=str(dir_path.relative_to(self.base_path)),
|
|
message=f"Missing STATUS.md in {dir_path.name}",
|
|
status_file=None
|
|
))
|
|
return anomalies
|
|
|
|
try:
|
|
content = status_file.read_text()
|
|
|
|
# Check for blocked status
|
|
if "BLOCKED" in content.upper() or "❗" in content:
|
|
anomalies.append(Anomaly(
|
|
id="",
|
|
type=AnomalyType.STATE_INCONSISTENCY,
|
|
severity=Severity.HIGH,
|
|
phase=phase_num,
|
|
phase_name=phase_name,
|
|
directory=str(dir_path.relative_to(self.base_path)),
|
|
message=f"Directory {dir_path.name} is BLOCKED",
|
|
status_file=str(status_file),
|
|
details={"content_preview": content[:500]}
|
|
))
|
|
|
|
# Check for stale status (not updated in 7 days)
|
|
if "Last updated:" in content:
|
|
try:
|
|
# Extract date from "Last updated: YYYY-MM-DD"
|
|
for line in content.split('\n'):
|
|
if 'Last updated:' in line or 'last_updated' in line.lower():
|
|
# Try to find a date pattern
|
|
import re
|
|
date_match = re.search(r'(\d{4}-\d{2}-\d{2})', line)
|
|
if date_match:
|
|
last_update = datetime.fromisoformat(date_match.group(1))
|
|
if datetime.now() - last_update > timedelta(days=7):
|
|
anomalies.append(Anomaly(
|
|
id="",
|
|
type=AnomalyType.STATE_INCONSISTENCY,
|
|
severity=Severity.LOW,
|
|
phase=phase_num,
|
|
phase_name=phase_name,
|
|
directory=str(dir_path.relative_to(self.base_path)),
|
|
message=f"Stale STATUS.md - last updated {date_match.group(1)}",
|
|
status_file=str(status_file)
|
|
))
|
|
break
|
|
except Exception:
|
|
pass
|
|
|
|
except Exception as e:
|
|
anomalies.append(Anomaly(
|
|
id="",
|
|
type=AnomalyType.UNHANDLED_ERROR,
|
|
severity=Severity.MEDIUM,
|
|
phase=phase_num,
|
|
phase_name=phase_name,
|
|
directory=str(dir_path.relative_to(self.base_path)),
|
|
message=f"Error reading STATUS.md: {e}",
|
|
status_file=str(status_file)
|
|
))
|
|
|
|
return anomalies
|
|
|
|
def _check_ledger_errors(self, phase_num: int, phase_name: str) -> list[Anomaly]:
|
|
"""Check governance ledger for recent errors"""
|
|
anomalies = []
|
|
|
|
if not self.ledger_db.exists():
|
|
return anomalies
|
|
|
|
try:
|
|
conn = sqlite3.connect(self.ledger_db)
|
|
conn.row_factory = sqlite3.Row
|
|
cursor = conn.cursor()
|
|
|
|
# Check violations table
|
|
cursor.execute("""
|
|
SELECT * FROM violations
|
|
WHERE severity IN ('critical', 'high')
|
|
AND acknowledged = 0
|
|
ORDER BY timestamp DESC LIMIT 10
|
|
""")
|
|
|
|
for row in cursor.fetchall():
|
|
anomalies.append(Anomaly(
|
|
id="",
|
|
type=AnomalyType.SECURITY_VIOLATION,
|
|
severity=Severity.CRITICAL if row['severity'] == 'critical' else Severity.HIGH,
|
|
phase=phase_num,
|
|
phase_name=phase_name,
|
|
directory="ledger",
|
|
message=f"Unacknowledged {row['severity']} violation: {row['violation_type']}",
|
|
details={
|
|
"violation_id": row['id'],
|
|
"agent_id": row['agent_id'],
|
|
"description": row['description'],
|
|
"timestamp": row['timestamp']
|
|
}
|
|
))
|
|
|
|
conn.close()
|
|
except Exception as e:
|
|
self.state.error_count += 1
|
|
|
|
return anomalies
|
|
|
|
def _check_dependencies(self, phase_num: int, phase_name: str) -> list[Anomaly]:
|
|
"""Check dependency availability"""
|
|
anomalies = []
|
|
|
|
# Check Vault
|
|
try:
|
|
result = subprocess.run(
|
|
["docker", "exec", "vault", "vault", "status", "-format=json"],
|
|
capture_output=True, text=True, timeout=5
|
|
)
|
|
if result.returncode != 0:
|
|
anomalies.append(Anomaly(
|
|
id="",
|
|
type=AnomalyType.DEPENDENCY_UNAVAILABLE,
|
|
severity=Severity.CRITICAL,
|
|
phase=phase_num,
|
|
phase_name=phase_name,
|
|
directory="infrastructure",
|
|
message="Vault is unavailable or sealed",
|
|
details={"stderr": result.stderr[:500] if result.stderr else ""}
|
|
))
|
|
except Exception as e:
|
|
anomalies.append(Anomaly(
|
|
id="",
|
|
type=AnomalyType.DEPENDENCY_UNAVAILABLE,
|
|
severity=Severity.CRITICAL,
|
|
phase=phase_num,
|
|
phase_name=phase_name,
|
|
directory="infrastructure",
|
|
message=f"Cannot check Vault status: {e}"
|
|
))
|
|
|
|
# Check DragonflyDB
|
|
if self._redis:
|
|
try:
|
|
self._redis.ping()
|
|
except Exception:
|
|
anomalies.append(Anomaly(
|
|
id="",
|
|
type=AnomalyType.DEPENDENCY_UNAVAILABLE,
|
|
severity=Severity.HIGH,
|
|
phase=phase_num,
|
|
phase_name=phase_name,
|
|
directory="infrastructure",
|
|
message="DragonflyDB is unavailable"
|
|
))
|
|
|
|
# Check Ledger DB
|
|
if not self.ledger_db.exists():
|
|
anomalies.append(Anomaly(
|
|
id="",
|
|
type=AnomalyType.DEPENDENCY_UNAVAILABLE,
|
|
severity=Severity.HIGH,
|
|
phase=phase_num,
|
|
phase_name=phase_name,
|
|
directory="ledger",
|
|
message="Governance ledger database not found"
|
|
))
|
|
|
|
return anomalies
|
|
|
|
def _check_checkpoint_consistency(self, phase_num: int, phase_name: str) -> list[Anomaly]:
|
|
"""Check checkpoint data for consistency issues"""
|
|
anomalies = []
|
|
|
|
if not self.checkpoint_dir.exists():
|
|
return anomalies
|
|
|
|
checkpoints = sorted(self.checkpoint_dir.glob("ckpt-*.json"), reverse=True)
|
|
|
|
if not checkpoints:
|
|
anomalies.append(Anomaly(
|
|
id="",
|
|
type=AnomalyType.MISSING_ARTIFACT,
|
|
severity=Severity.MEDIUM,
|
|
phase=phase_num,
|
|
phase_name=phase_name,
|
|
directory="checkpoint",
|
|
message="No checkpoints found"
|
|
))
|
|
return anomalies
|
|
|
|
# Check latest checkpoint
|
|
try:
|
|
latest = json.loads(checkpoints[0].read_text())
|
|
|
|
# Verify content hash
|
|
if 'content_hash' in latest:
|
|
# Could verify hash here
|
|
pass
|
|
|
|
# Check for stale checkpoint (older than 1 hour)
|
|
if 'created_at' in latest:
|
|
created = datetime.fromisoformat(latest['created_at'].replace('Z', '+00:00'))
|
|
if datetime.now(timezone.utc) - created > timedelta(hours=1):
|
|
anomalies.append(Anomaly(
|
|
id="",
|
|
type=AnomalyType.STATE_INCONSISTENCY,
|
|
severity=Severity.LOW,
|
|
phase=phase_num,
|
|
phase_name=phase_name,
|
|
directory="checkpoint",
|
|
message=f"Last checkpoint is stale: {latest['created_at']}",
|
|
checkpoint_id=latest.get('checkpoint_id')
|
|
))
|
|
|
|
except Exception as e:
|
|
anomalies.append(Anomaly(
|
|
id="",
|
|
type=AnomalyType.UNHANDLED_ERROR,
|
|
severity=Severity.MEDIUM,
|
|
phase=phase_num,
|
|
phase_name=phase_name,
|
|
directory="checkpoint",
|
|
message=f"Error reading checkpoint: {e}"
|
|
))
|
|
|
|
return anomalies
|
|
|
|
def _run_phase_specific_checks(self, phase_num: int, phase_name: str) -> list[Anomaly]:
|
|
"""Run checks specific to each phase"""
|
|
anomalies = []
|
|
|
|
if phase_num == 3: # Execution Pipeline
|
|
# Check preflight module
|
|
preflight_path = self.base_path / "preflight" / "preflight.py"
|
|
if not preflight_path.exists():
|
|
anomalies.append(Anomaly(
|
|
id="",
|
|
type=AnomalyType.MISSING_ARTIFACT,
|
|
severity=Severity.HIGH,
|
|
phase=phase_num,
|
|
phase_name=phase_name,
|
|
directory="preflight",
|
|
message="Preflight module missing"
|
|
))
|
|
|
|
elif phase_num == 4: # Promotion/Revocation
|
|
# Check for agents with high violation counts
|
|
if self._redis:
|
|
try:
|
|
keys = self._redis.keys("agent:*:errors")
|
|
for key in keys[:10]: # Limit check
|
|
errors = self._redis.hgetall(key)
|
|
total = int(errors.get('total_errors', 0))
|
|
if total > 5:
|
|
agent_id = key.split(':')[1]
|
|
anomalies.append(Anomaly(
|
|
id="",
|
|
type=AnomalyType.REGRESSION,
|
|
severity=Severity.MEDIUM,
|
|
phase=phase_num,
|
|
phase_name=phase_name,
|
|
directory="runtime",
|
|
message=f"Agent {agent_id} has {total} errors",
|
|
details=errors
|
|
))
|
|
except Exception:
|
|
pass
|
|
|
|
elif phase_num == 5: # Agent Bootstrapping - SPECIAL ATTENTION
|
|
# Check tier0-agent
|
|
tier0_config = self.base_path / "agents" / "tier0-agent" / "config" / "agent.json"
|
|
if not tier0_config.exists():
|
|
anomalies.append(Anomaly(
|
|
id="",
|
|
type=AnomalyType.MISSING_ARTIFACT,
|
|
severity=Severity.HIGH,
|
|
phase=phase_num,
|
|
phase_name=phase_name,
|
|
directory="agents/tier0-agent",
|
|
message="Tier 0 agent config missing"
|
|
))
|
|
|
|
# Check orchestrator
|
|
model_controller = self.base_path / "orchestrator" / "model_controller.py"
|
|
if not model_controller.exists():
|
|
anomalies.append(Anomaly(
|
|
id="",
|
|
type=AnomalyType.MISSING_ARTIFACT,
|
|
severity=Severity.MEDIUM,
|
|
phase=phase_num,
|
|
phase_name=phase_name,
|
|
directory="orchestrator",
|
|
message="Model controller missing"
|
|
))
|
|
|
|
elif phase_num == 8: # Production Hardening
|
|
# Check if health_manager exists
|
|
health_manager = self.base_path / "runtime" / "health_manager.py"
|
|
if not health_manager.exists():
|
|
anomalies.append(Anomaly(
|
|
id="",
|
|
type=AnomalyType.MISSING_ARTIFACT,
|
|
severity=Severity.HIGH,
|
|
phase=phase_num,
|
|
phase_name=phase_name,
|
|
directory="runtime",
|
|
message="health_manager.py not implemented - Phase 8 blocked"
|
|
))
|
|
|
|
return anomalies
|
|
|
|
def _persist_anomalies(self, anomalies: list[Anomaly]):
|
|
"""Persist anomalies to storage (Redis + SQLite)"""
|
|
# Persist to SQLite
|
|
conn = sqlite3.connect(self.bug_db)
|
|
cursor = conn.cursor()
|
|
|
|
for anomaly in anomalies:
|
|
# Convert enum values to strings for storage
|
|
type_val = anomaly.type.value if hasattr(anomaly.type, 'value') else anomaly.type
|
|
sev_val = anomaly.severity.value if hasattr(anomaly.severity, 'value') else anomaly.severity
|
|
status_val = anomaly.status.value if hasattr(anomaly.status, 'value') else anomaly.status
|
|
|
|
cursor.execute("""
|
|
INSERT OR REPLACE INTO bugs
|
|
(id, type, severity, status, phase, phase_name, directory, message,
|
|
details, stack_trace, checkpoint_id, status_file, detected_at,
|
|
updated_at, resolution_notes, assigned_to)
|
|
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
|
|
""", (
|
|
anomaly.id,
|
|
type_val,
|
|
sev_val,
|
|
status_val,
|
|
anomaly.phase,
|
|
anomaly.phase_name,
|
|
anomaly.directory,
|
|
anomaly.message,
|
|
json.dumps(anomaly.details) if anomaly.details else None,
|
|
anomaly.stack_trace,
|
|
anomaly.checkpoint_id,
|
|
anomaly.status_file,
|
|
anomaly.detected_at,
|
|
anomaly.updated_at,
|
|
anomaly.resolution_notes,
|
|
anomaly.assigned_to
|
|
))
|
|
|
|
conn.commit()
|
|
conn.close()
|
|
|
|
# Also persist to Redis for real-time access
|
|
if not self._redis:
|
|
return
|
|
|
|
for anomaly in anomalies:
|
|
# Store in Redis list
|
|
self._redis.lpush(
|
|
"oversight:anomalies",
|
|
json.dumps(asdict(anomaly))
|
|
)
|
|
|
|
# Keep only last 1000
|
|
self._redis.ltrim("oversight:anomalies", 0, 999)
|
|
|
|
# Index by severity
|
|
sev_val = anomaly.severity.value if hasattr(anomaly.severity, 'value') else anomaly.severity
|
|
self._redis.sadd(f"oversight:anomalies:{sev_val}", anomaly.id)
|
|
|
|
# Index by phase
|
|
self._redis.sadd(f"oversight:anomalies:phase:{anomaly.phase}", anomaly.id)
|
|
|
|
# Index by status
|
|
status_val = anomaly.status.value if hasattr(anomaly.status, 'value') else anomaly.status
|
|
self._redis.sadd(f"oversight:anomalies:status:{status_val}", anomaly.id)
|
|
|
|
def get_anomalies(
|
|
self,
|
|
severity: Optional[Severity] = None,
|
|
phase: Optional[int] = None,
|
|
status: Optional[BugStatus] = None,
|
|
limit: int = 50
|
|
) -> list[Anomaly]:
|
|
"""Retrieve anomalies with optional filters from SQLite"""
|
|
conn = sqlite3.connect(self.bug_db)
|
|
conn.row_factory = sqlite3.Row
|
|
cursor = conn.cursor()
|
|
|
|
query = "SELECT * FROM bugs WHERE 1=1"
|
|
params = []
|
|
|
|
if severity:
|
|
sev_val = severity.value if hasattr(severity, 'value') else severity
|
|
query += " AND severity = ?"
|
|
params.append(sev_val)
|
|
|
|
if phase:
|
|
query += " AND phase = ?"
|
|
params.append(phase)
|
|
|
|
if status:
|
|
status_val = status.value if hasattr(status, 'value') else status
|
|
query += " AND status = ?"
|
|
params.append(status_val)
|
|
|
|
query += " ORDER BY detected_at DESC LIMIT ?"
|
|
params.append(limit)
|
|
|
|
cursor.execute(query, params)
|
|
rows = cursor.fetchall()
|
|
conn.close()
|
|
|
|
anomalies = []
|
|
for row in rows:
|
|
try:
|
|
anomaly = Anomaly(
|
|
id=row['id'],
|
|
type=AnomalyType(row['type']),
|
|
severity=Severity(row['severity']),
|
|
status=BugStatus(row['status']),
|
|
phase=row['phase'],
|
|
phase_name=row['phase_name'],
|
|
directory=row['directory'],
|
|
message=row['message'],
|
|
details=json.loads(row['details']) if row['details'] else {},
|
|
stack_trace=row['stack_trace'],
|
|
checkpoint_id=row['checkpoint_id'],
|
|
status_file=row['status_file'],
|
|
detected_at=row['detected_at'],
|
|
updated_at=row['updated_at'],
|
|
resolution_notes=row['resolution_notes'],
|
|
assigned_to=row['assigned_to'],
|
|
resolved=row['status'] == 'resolved'
|
|
)
|
|
anomalies.append(anomaly)
|
|
except Exception:
|
|
continue
|
|
|
|
return anomalies
|
|
|
|
def update_bug_status(
|
|
self,
|
|
bug_id: str,
|
|
new_status: BugStatus,
|
|
notes: Optional[str] = None,
|
|
assigned_to: Optional[str] = None
|
|
) -> bool:
|
|
"""Update bug status with optional notes and assignment"""
|
|
conn = sqlite3.connect(self.bug_db)
|
|
cursor = conn.cursor()
|
|
|
|
now = self._now()
|
|
status_val = new_status.value if hasattr(new_status, 'value') else new_status
|
|
|
|
# Build update query
|
|
updates = ["status = ?", "updated_at = ?"]
|
|
params = [status_val, now]
|
|
|
|
if notes is not None:
|
|
updates.append("resolution_notes = ?")
|
|
params.append(notes)
|
|
|
|
if assigned_to is not None:
|
|
updates.append("assigned_to = ?")
|
|
params.append(assigned_to)
|
|
|
|
if new_status == BugStatus.RESOLVED:
|
|
updates.append("resolved_at = ?")
|
|
params.append(now)
|
|
|
|
params.append(bug_id)
|
|
|
|
cursor.execute(f"""
|
|
UPDATE bugs SET {', '.join(updates)} WHERE id = ?
|
|
""", params)
|
|
|
|
updated = cursor.rowcount > 0
|
|
conn.commit()
|
|
conn.close()
|
|
|
|
# Update Redis index if available
|
|
if self._redis and updated:
|
|
# Remove from old status sets, add to new
|
|
for s in BugStatus:
|
|
self._redis.srem(f"oversight:anomalies:status:{s.value}", bug_id)
|
|
self._redis.sadd(f"oversight:anomalies:status:{status_val}", bug_id)
|
|
|
|
self._redis.hset(f"oversight:anomaly:{bug_id}", mapping={
|
|
"status": status_val,
|
|
"updated_at": now,
|
|
"resolution_notes": notes or "",
|
|
"assigned_to": assigned_to or ""
|
|
})
|
|
|
|
return updated
|
|
|
|
def acknowledge_anomaly(self, anomaly_id: str, notes: str = "") -> bool:
|
|
"""Mark an anomaly as resolved (backwards compatible)"""
|
|
return self.update_bug_status(anomaly_id, BugStatus.RESOLVED, notes)
|
|
|
|
def get_bug(self, bug_id: str) -> Optional[Anomaly]:
|
|
"""Get a single bug by ID"""
|
|
conn = sqlite3.connect(self.bug_db)
|
|
conn.row_factory = sqlite3.Row
|
|
cursor = conn.cursor()
|
|
|
|
cursor.execute("SELECT * FROM bugs WHERE id = ?", (bug_id,))
|
|
row = cursor.fetchone()
|
|
conn.close()
|
|
|
|
if not row:
|
|
return None
|
|
|
|
return Anomaly(
|
|
id=row['id'],
|
|
type=AnomalyType(row['type']),
|
|
severity=Severity(row['severity']),
|
|
status=BugStatus(row['status']),
|
|
phase=row['phase'],
|
|
phase_name=row['phase_name'],
|
|
directory=row['directory'],
|
|
message=row['message'],
|
|
details=json.loads(row['details']) if row['details'] else {},
|
|
stack_trace=row['stack_trace'],
|
|
checkpoint_id=row['checkpoint_id'],
|
|
status_file=row['status_file'],
|
|
detected_at=row['detected_at'],
|
|
updated_at=row['updated_at'],
|
|
resolution_notes=row['resolution_notes'],
|
|
assigned_to=row['assigned_to'],
|
|
resolved=row['status'] == 'resolved'
|
|
)
|
|
|
|
def log_bug(
|
|
self,
|
|
message: str,
|
|
severity: Severity = Severity.MEDIUM,
|
|
bug_type: AnomalyType = AnomalyType.UNHANDLED_ERROR,
|
|
phase: int = 0,
|
|
directory: str = "unknown",
|
|
details: Optional[dict] = None,
|
|
stack_trace: Optional[str] = None
|
|
) -> Anomaly:
|
|
"""Manually log a bug (for API/CLI use)"""
|
|
anomaly = Anomaly(
|
|
id="",
|
|
type=bug_type,
|
|
severity=severity,
|
|
status=BugStatus.OPEN,
|
|
phase=phase,
|
|
phase_name=self.PHASES.get(phase, f"Phase {phase}"),
|
|
directory=directory,
|
|
message=message,
|
|
details=details or {},
|
|
stack_trace=stack_trace
|
|
)
|
|
|
|
self._persist_anomalies([anomaly])
|
|
self.anomalies.append(anomaly)
|
|
|
|
return anomaly
|
|
|
|
def get_summary(self) -> dict:
|
|
"""Get summary of watcher state and anomalies"""
|
|
anomalies = self.get_anomalies(limit=1000)
|
|
|
|
by_severity = {s.value: 0 for s in Severity}
|
|
by_phase = {p: 0 for p in self.PHASES}
|
|
by_type = {t.value: 0 for t in AnomalyType}
|
|
by_status = {s.value: 0 for s in BugStatus}
|
|
|
|
for a in anomalies:
|
|
# Handle both enum and string values
|
|
sev_val = a.severity.value if hasattr(a.severity, 'value') else a.severity
|
|
type_val = a.type.value if hasattr(a.type, 'value') else a.type
|
|
status_val = a.status.value if hasattr(a.status, 'value') else a.status
|
|
|
|
by_severity[sev_val] = by_severity.get(sev_val, 0) + 1
|
|
by_phase[a.phase] = by_phase.get(a.phase, 0) + 1
|
|
by_type[type_val] = by_type.get(type_val, 0) + 1
|
|
by_status[status_val] = by_status.get(status_val, 0) + 1
|
|
|
|
return {
|
|
"state": asdict(self.state),
|
|
"total_anomalies": len(anomalies),
|
|
"open": by_status.get("open", 0),
|
|
"in_progress": by_status.get("in_progress", 0),
|
|
"resolved": by_status.get("resolved", 0),
|
|
"by_severity": by_severity,
|
|
"by_phase": by_phase,
|
|
"by_type": by_type,
|
|
"by_status": by_status,
|
|
"phases": self.PHASES
|
|
}
|
|
|
|
|
|
if __name__ == "__main__":
|
|
import argparse
|
|
|
|
parser = argparse.ArgumentParser(description="Bug Window Watcher")
|
|
parser.add_argument("command", choices=["scan", "status", "list", "update", "log", "get"], help="Command to run")
|
|
parser.add_argument("--phase", type=int, help="Specific phase to scan")
|
|
parser.add_argument("--severity", choices=["critical", "high", "medium", "low", "info"])
|
|
parser.add_argument("--bug-status", dest="bug_status", choices=["open", "in_progress", "resolved"], help="Filter by bug status")
|
|
parser.add_argument("--json", action="store_true", help="Output as JSON")
|
|
# For update command
|
|
parser.add_argument("--id", help="Bug ID to update or get")
|
|
parser.add_argument("--set-status", dest="set_status", choices=["open", "in_progress", "resolved"], help="New status to set")
|
|
parser.add_argument("--notes", help="Resolution or status notes")
|
|
parser.add_argument("--assign", help="Assign bug to person/team")
|
|
# For log command
|
|
parser.add_argument("--message", "-m", help="Bug message (for log command)")
|
|
parser.add_argument("--directory", "-d", default="unknown", help="Directory (for log command)")
|
|
parser.add_argument("--type", dest="bug_type", choices=[t.value for t in AnomalyType], default="unhandled_error")
|
|
|
|
args = parser.parse_args()
|
|
|
|
watcher = BugWindowWatcher()
|
|
watcher.start()
|
|
|
|
if args.command == "scan":
|
|
if args.phase:
|
|
anomalies = watcher.scan_phase(args.phase)
|
|
else:
|
|
anomalies = watcher.scan_all_phases()
|
|
|
|
if args.json:
|
|
print(json.dumps([asdict(a) for a in anomalies], indent=2))
|
|
else:
|
|
print(f"\n{'='*60}")
|
|
print(f"BUG WINDOW WATCHER - Scan Results")
|
|
print(f"{'='*60}")
|
|
print(f"Anomalies found: {len(anomalies)}")
|
|
print()
|
|
|
|
for a in anomalies:
|
|
sev_val = a.severity.value if hasattr(a.severity, 'value') else a.severity
|
|
status_val = a.status.value if hasattr(a.status, 'value') else a.status
|
|
icon = {"critical": "🔴", "high": "🟠", "medium": "🟡", "low": "🔵", "info": "⚪"}.get(sev_val, "⚪")
|
|
status_icon = {"open": "📋", "in_progress": "🔧", "resolved": "✅"}.get(status_val, "❓")
|
|
print(f"{icon} [{sev_val.upper()}] {status_icon} {status_val.upper()} | Phase {a.phase}: {a.message}")
|
|
print(f" ID: {a.id}")
|
|
print(f" Directory: {a.directory}")
|
|
if a.status_file:
|
|
print(f" Status: {a.status_file}")
|
|
print()
|
|
|
|
elif args.command == "status":
|
|
summary = watcher.get_summary()
|
|
if args.json:
|
|
print(json.dumps(summary, indent=2))
|
|
else:
|
|
print(f"\n{'='*60}")
|
|
print(f"BUG WINDOW WATCHER - Status")
|
|
print(f"{'='*60}")
|
|
print(f"Active: {summary['state']['active']}")
|
|
print(f"Total Bugs: {summary['total_anomalies']}")
|
|
print()
|
|
print("By Status:")
|
|
print(f" 📋 Open: {summary['open']}")
|
|
print(f" 🔧 In Progress: {summary['in_progress']}")
|
|
print(f" ✅ Resolved: {summary['resolved']}")
|
|
print()
|
|
print("By Severity:")
|
|
for sev, count in summary['by_severity'].items():
|
|
if count > 0:
|
|
icon = {"critical": "🔴", "high": "🟠", "medium": "🟡", "low": "🔵", "info": "⚪"}.get(sev, "⚪")
|
|
print(f" {icon} {sev}: {count}")
|
|
|
|
elif args.command == "list":
|
|
severity = Severity(args.severity) if args.severity else None
|
|
status = BugStatus(args.bug_status) if args.bug_status else None
|
|
anomalies = watcher.get_anomalies(severity=severity, phase=args.phase, status=status)
|
|
|
|
if args.json:
|
|
print(json.dumps([asdict(a) for a in anomalies], indent=2))
|
|
else:
|
|
if not anomalies:
|
|
print("No bugs found matching criteria.")
|
|
else:
|
|
print(f"\n{'='*70}")
|
|
print(f"{'ID':<20} {'Status':<12} {'Severity':<10} {'Message'}")
|
|
print(f"{'='*70}")
|
|
for a in anomalies:
|
|
sev_val = a.severity.value if hasattr(a.severity, 'value') else a.severity
|
|
status_val = a.status.value if hasattr(a.status, 'value') else a.status
|
|
msg = a.message[:40] + "..." if len(a.message) > 40 else a.message
|
|
print(f"{a.id:<20} {status_val:<12} {sev_val:<10} {msg}")
|
|
|
|
elif args.command == "update":
|
|
if not args.id:
|
|
print("Error: --id is required for update command")
|
|
exit(1)
|
|
if not args.set_status:
|
|
print("Error: --set-status is required for update command")
|
|
exit(1)
|
|
|
|
new_status = BugStatus(args.set_status)
|
|
success = watcher.update_bug_status(
|
|
args.id,
|
|
new_status,
|
|
notes=args.notes,
|
|
assigned_to=args.assign
|
|
)
|
|
|
|
if success:
|
|
bug = watcher.get_bug(args.id)
|
|
if args.json:
|
|
print(json.dumps(asdict(bug), indent=2))
|
|
else:
|
|
print(f"✅ Bug {args.id} updated to {args.set_status}")
|
|
if args.notes:
|
|
print(f" Notes: {args.notes}")
|
|
if args.assign:
|
|
print(f" Assigned to: {args.assign}")
|
|
else:
|
|
print(f"❌ Failed to update bug {args.id} - not found")
|
|
exit(1)
|
|
|
|
elif args.command == "get":
|
|
if not args.id:
|
|
print("Error: --id is required for get command")
|
|
exit(1)
|
|
|
|
bug = watcher.get_bug(args.id)
|
|
if bug:
|
|
if args.json:
|
|
print(json.dumps(asdict(bug), indent=2))
|
|
else:
|
|
sev_val = bug.severity.value if hasattr(bug.severity, 'value') else bug.severity
|
|
status_val = bug.status.value if hasattr(bug.status, 'value') else bug.status
|
|
type_val = bug.type.value if hasattr(bug.type, 'value') else bug.type
|
|
print(f"\n{'='*60}")
|
|
print(f"Bug: {bug.id}")
|
|
print(f"{'='*60}")
|
|
print(f"Status: {status_val}")
|
|
print(f"Severity: {sev_val}")
|
|
print(f"Type: {type_val}")
|
|
print(f"Phase: {bug.phase} - {bug.phase_name}")
|
|
print(f"Directory: {bug.directory}")
|
|
print(f"Message: {bug.message}")
|
|
print(f"Detected: {bug.detected_at}")
|
|
if bug.updated_at:
|
|
print(f"Updated: {bug.updated_at}")
|
|
if bug.assigned_to:
|
|
print(f"Assigned to: {bug.assigned_to}")
|
|
if bug.resolution_notes:
|
|
print(f"Notes: {bug.resolution_notes}")
|
|
else:
|
|
print(f"❌ Bug {args.id} not found")
|
|
exit(1)
|
|
|
|
elif args.command == "log":
|
|
if not args.message:
|
|
print("Error: --message/-m is required for log command")
|
|
exit(1)
|
|
|
|
severity = Severity(args.severity) if args.severity else Severity.MEDIUM
|
|
bug_type = AnomalyType(args.bug_type)
|
|
phase = args.phase or 0
|
|
|
|
bug = watcher.log_bug(
|
|
message=args.message,
|
|
severity=severity,
|
|
bug_type=bug_type,
|
|
phase=phase,
|
|
directory=args.directory
|
|
)
|
|
|
|
if args.json:
|
|
print(json.dumps(asdict(bug), indent=2))
|
|
else:
|
|
print(f"✅ Bug logged: {bug.id}")
|
|
print(f" Severity: {severity.value}")
|
|
print(f" Status: open")
|
|
print(f" Message: {args.message}")
|