Files
shannon/src/audit/metrics-tracker.ts
T
Arjun Malleswaran 51e621d0d5 Feat/temporal (#46)
* refactor: modularize claude-executor and extract shared utilities

- Extract message handling into src/ai/message-handlers.ts with pure functions
- Extract output formatting into src/ai/output-formatters.ts
- Extract progress management into src/ai/progress-manager.ts
- Add audit-logger.ts with Null Object pattern for optional logging
- Add shared utilities: formatting.ts, file-io.ts, functional.ts
- Consolidate getPromptNameForAgent into src/types/agents.ts

* feat: add Claude Code custom commands for debug and review

* feat: add Temporal integration foundation (phase 1-2)

- Add Temporal SDK dependencies (@temporalio/client, worker, workflow, activity)
- Add shared types for pipeline state, metrics, and progress queries
- Add classifyErrorForTemporal() for retry behavior classification
- Add docker-compose for Temporal server with SQLite persistence

* feat: add Temporal activities for agent execution (phase 3)

- Add activities.ts with heartbeat loop, git checkpoint/rollback, and error classification
- Export runClaudePrompt, validateAgentOutput, ClaudePromptResult for Temporal use
- Track attempt number via Temporal Context for accurate audit logging
- Rollback git workspace before retry to ensure clean state

* feat: add Temporal workflow for 5-phase pipeline orchestration (phase 4)

* feat: add Temporal worker, client, and query tools (phase 5)

- Add worker.ts with workflow bundling and graceful shutdown
- Add client.ts CLI to start pipelines with progress polling
- Add query.ts CLI to inspect running workflow state
- Fix buffer overflow by truncating error messages and stack traces
- Skip git operations gracefully on non-git repositories
- Add kill.sh/start.sh dev scripts and Dockerfile.worker

* feat: fix Docker worker container setup

- Install uv instead of deprecated uvx package
- Add mcp-server and configs directories to container
- Mount target repo dynamically via TARGET_REPO env variable

* fix: add report assembly step to Temporal workflow

- Add assembleReportActivity to concatenate exploitation evidence files before report agent runs
- Call assembleFinalReport in workflow Phase 5 before runReportAgent
- Ensure deliverables directory exists before writing final report
- Simplify pipeline-testing report prompt to just prepend header

* refactor: consolidate Docker setup to root docker-compose.yml

* feat: improve Temporal client UX and env handling

- Change default to fire-and-forget (--wait flag to opt-in)
- Add splash screen and improve console output formatting
- Add .env to gitignore, remove from dockerignore for container access
- Add Taskfile for common development commands

* refactor: simplify session ID handling and improve Taskfile options

- Include hostname in workflow ID for better audit log organization
- Extract sanitizeHostname utility to audit/utils.ts for reuse
- Remove unused generateSessionLogPath and buildLogFilePath functions
- Simplify Taskfile with CONFIG/OUTPUT/CLEAN named parameters

* chore: add .env.example and simplify .gitignore

* docs: update README and CLAUDE.md for Temporal workflow usage

- Replace Docker CLI instructions with Task-based commands
- Add monitoring/stopping sections and workflow examples
- Document Temporal orchestration layer and troubleshooting
- Simplify file structure to key files overview

* refactor: replace Taskfile with bash CLI script

- Add shannon bash script with start/logs/query/stop/help commands
- Remove Taskfile.yml dependency (no longer requires Task installation)
- Update README.md and CLAUDE.md to use ./shannon commands
- Update client.ts output to show ./shannon commands

* docs: fix deliverable filename in README

* refactor: remove direct CLI and .shannon-store.json in favor of Temporal

- Delete src/shannon.ts direct CLI entry point (Temporal is now the only mode)
- Remove .shannon-store.json session lock (Temporal handles workflow deduplication)
- Remove broken scripts/export-metrics.js (imported non-existent function)
- Update package.json to remove main, start script, and bin entry
- Clean up CLAUDE.md and debug.md to remove obsolete references

* chore: remove licensing comments from prompt files to prevent leaking into actual prompts

* fix: resolve parallel workflow race conditions and retry logic bugs

- Fix save_deliverable race condition using closure pattern instead of global variable
- Fix error classification order so OutputValidationError matches before generic validation
- Fix ApplicationFailure re-classification bug by checking instanceof before re-throwing
- Add per-error-type retry limits (3 for output validation, 50 for billing)
- Add fast retry intervals for pipeline testing mode (10s vs 5min)
- Increase worker concurrent activities to 25 for parallel workflows

* refactor: pipeline vuln→exploit workflow for parallel execution

- Replace sync barrier between vuln/exploit phases with independent pipelines
- Each vuln type runs: vuln agent → queue check → conditional exploit
- Add checkExploitationQueue activity to skip exploits when no vulns found
- Use Promise.allSettled for graceful failure handling across pipelines
- Add PipelineSummary type for aggregated cost/duration/turns metrics

* fix: re-throw retryable errors in checkExploitationQueue

* fix: detect and retry on Claude Code spending cap errors

- Add spending cap pattern detection in detectApiError() with retryable error
- Add matching patterns to classifyErrorForTemporal() for proper Temporal retry
- Add defense-in-depth safeguard in runClaudePrompt() for $0 cost / low turn detection
- Add final sanity check in activities before declaring success

* fix: increase heartbeat timeout to prevent false worker-dead detection

Original 30s timeout was from POC spec assuming <5min activities. With
hour-long activities and multiple concurrent workflows sharing one worker,
resource contention causes event loop stalls exceeding 30s, triggering
false heartbeat timeouts. Increased to 10min (prod) and 5min (testing).

* fix: temporal db init

* fix: persist home dir

* feat: add per-workflow unified logging with ./shannon logs ID=<workflow-id>

- Add WorkflowLogger class for human-readable, per-workflow log files
- Create workflow.log in audit-logs/{workflowId}/ with phase, agent, tool, and LLM events
- Update ./shannon logs to require ID param and tail specific workflow log
- Add phase transition logging at workflow boundaries
- Include workflow completion summary with agent breakdown (duration, cost)
- Mount audit-logs volume in docker-compose for host access

---------

Co-authored-by: ezl-keygraph <ezhil@keygraph.io>
2026-01-15 10:36:11 -08:00

314 lines
8.1 KiB
TypeScript

// Copyright (C) 2025 Keygraph, Inc.
//
// This program is free software: you can redistribute it and/or modify
// it under the terms of the GNU Affero General Public License version 3
// as published by the Free Software Foundation.
/**
* Metrics Tracker
*
* Manages session.json with comprehensive timing, cost, and validation metrics.
* Tracks attempt-level data for complete forensic trail.
*/
import {
generateSessionJsonPath,
type SessionMetadata,
} from './utils.js';
import { atomicWrite, readJson, fileExists } from '../utils/file-io.js';
import { formatTimestamp, calculatePercentage } from '../utils/formatting.js';
import { AGENT_PHASE_MAP, type PhaseName } from '../session-manager.js';
import type { AgentName } from '../types/index.js';
interface AttemptData {
attempt_number: number;
duration_ms: number;
cost_usd: number;
success: boolean;
timestamp: string;
error?: string;
}
interface AgentMetrics {
status: 'in-progress' | 'success' | 'failed';
attempts: AttemptData[];
final_duration_ms: number;
total_cost_usd: number;
checkpoint?: string;
}
interface PhaseMetrics {
duration_ms: number;
duration_percentage: number;
cost_usd: number;
agent_count: number;
}
interface SessionData {
session: {
id: string;
webUrl: string;
repoPath?: string;
status: 'in-progress' | 'completed' | 'failed';
createdAt: string;
completedAt?: string;
};
metrics: {
total_duration_ms: number;
total_cost_usd: number;
phases: Record<string, PhaseMetrics>;
agents: Record<string, AgentMetrics>;
};
}
interface AgentEndResult {
attemptNumber: number;
duration_ms: number;
cost_usd: number;
success: boolean;
error?: string;
checkpoint?: string;
isFinalAttempt?: boolean;
}
interface ActiveTimer {
startTime: number;
attemptNumber: number;
}
/**
* MetricsTracker - Manages metrics for a session
*/
export class MetricsTracker {
private sessionMetadata: SessionMetadata;
private sessionJsonPath: string;
private data: SessionData | null = null;
private activeTimers: Map<string, ActiveTimer> = new Map();
constructor(sessionMetadata: SessionMetadata) {
this.sessionMetadata = sessionMetadata;
this.sessionJsonPath = generateSessionJsonPath(sessionMetadata);
}
/**
* Initialize session.json (idempotent)
*/
async initialize(): Promise<void> {
// Check if session.json already exists
const exists = await fileExists(this.sessionJsonPath);
if (exists) {
// Load existing data
this.data = await readJson<SessionData>(this.sessionJsonPath);
} else {
// Create new session.json
this.data = this.createInitialData();
await this.save();
}
}
/**
* Create initial session.json structure
*/
private createInitialData(): SessionData {
const sessionData: SessionData = {
session: {
id: this.sessionMetadata.id,
webUrl: this.sessionMetadata.webUrl,
status: 'in-progress',
createdAt: (this.sessionMetadata as { createdAt?: string }).createdAt || formatTimestamp(),
},
metrics: {
total_duration_ms: 0,
total_cost_usd: 0,
phases: {}, // Phase-level aggregations
agents: {}, // Agent-level metrics
},
};
// Only add repoPath if it exists
if (this.sessionMetadata.repoPath) {
sessionData.session.repoPath = this.sessionMetadata.repoPath;
}
return sessionData;
}
/**
* Start tracking an agent execution
*/
startAgent(agentName: string, attemptNumber: number): void {
this.activeTimers.set(agentName, {
startTime: Date.now(),
attemptNumber,
});
}
/**
* End agent execution and update metrics
*/
async endAgent(agentName: string, result: AgentEndResult): Promise<void> {
if (!this.data) {
throw new Error('MetricsTracker not initialized');
}
// Initialize agent metrics if not exists
const existingAgent = this.data.metrics.agents[agentName];
const agent = existingAgent ?? {
status: 'in-progress' as const,
attempts: [],
final_duration_ms: 0,
total_cost_usd: 0,
};
this.data.metrics.agents[agentName] = agent;
// Add attempt to array
const attempt: AttemptData = {
attempt_number: result.attemptNumber,
duration_ms: result.duration_ms,
cost_usd: result.cost_usd,
success: result.success,
timestamp: formatTimestamp(),
};
if (result.error) {
attempt.error = result.error;
}
agent.attempts.push(attempt);
// Update total cost (includes failed attempts)
agent.total_cost_usd = agent.attempts.reduce((sum, a) => sum + a.cost_usd, 0);
// If successful, update final metrics and status
if (result.success) {
agent.status = 'success';
agent.final_duration_ms = result.duration_ms;
if (result.checkpoint) {
agent.checkpoint = result.checkpoint;
}
} else {
// If this was the last attempt, mark as failed
if (result.isFinalAttempt) {
agent.status = 'failed';
}
}
// Clear active timer
this.activeTimers.delete(agentName);
// Recalculate aggregations
this.recalculateAggregations();
// Save to disk
await this.save();
}
/**
* Update session status
*/
async updateSessionStatus(status: 'in-progress' | 'completed' | 'failed'): Promise<void> {
if (!this.data) return;
this.data.session.status = status;
if (status === 'completed' || status === 'failed') {
this.data.session.completedAt = formatTimestamp();
}
await this.save();
}
/**
* Recalculate aggregations (total duration, total cost, phases)
*/
private recalculateAggregations(): void {
if (!this.data) return;
const agents = this.data.metrics.agents;
// Only count successful agents
const successfulAgents = Object.entries(agents).filter(
([, data]) => data.status === 'success'
);
// Calculate total duration and cost
const totalDuration = successfulAgents.reduce(
(sum, [, data]) => sum + data.final_duration_ms,
0
);
const totalCost = successfulAgents.reduce((sum, [, data]) => sum + data.total_cost_usd, 0);
this.data.metrics.total_duration_ms = totalDuration;
this.data.metrics.total_cost_usd = totalCost;
// Calculate phase-level metrics
this.data.metrics.phases = this.calculatePhaseMetrics(successfulAgents);
}
/**
* Calculate phase-level metrics
*/
private calculatePhaseMetrics(
successfulAgents: Array<[string, AgentMetrics]>
): Record<string, PhaseMetrics> {
const phases: Record<PhaseName, AgentMetrics[]> = {
'pre-recon': [],
'recon': [],
'vulnerability-analysis': [],
'exploitation': [],
'reporting': [],
};
// Group agents by phase using imported AGENT_PHASE_MAP
for (const [agentName, agentData] of successfulAgents) {
const phase = AGENT_PHASE_MAP[agentName as AgentName];
if (phase) {
phases[phase].push(agentData);
}
}
// Calculate metrics per phase
const phaseMetrics: Record<string, PhaseMetrics> = {};
const totalDuration = this.data!.metrics.total_duration_ms;
for (const [phaseName, agentList] of Object.entries(phases)) {
if (agentList.length === 0) continue;
const phaseDuration = agentList.reduce((sum, agent) => sum + agent.final_duration_ms, 0);
const phaseCost = agentList.reduce((sum, agent) => sum + agent.total_cost_usd, 0);
phaseMetrics[phaseName] = {
duration_ms: phaseDuration,
duration_percentage: calculatePercentage(phaseDuration, totalDuration),
cost_usd: phaseCost,
agent_count: agentList.length,
};
}
return phaseMetrics;
}
/**
* Get current metrics
*/
getMetrics(): SessionData {
return JSON.parse(JSON.stringify(this.data)) as SessionData;
}
/**
* Save metrics to session.json (atomic write)
*/
private async save(): Promise<void> {
if (!this.data) return;
await atomicWrite(this.sessionJsonPath, this.data);
}
/**
* Reload metrics from disk
*/
async reload(): Promise<void> {
this.data = await readJson<SessionData>(this.sessionJsonPath);
}
}