Files
shannon/src/queue-validation.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

326 lines
9.4 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.
import { fs, path } from 'zx';
import { PentestError } from './error-handling.js';
import { asyncPipe } from './utils/functional.js';
export type VulnType = 'injection' | 'xss' | 'auth' | 'ssrf' | 'authz';
interface VulnTypeConfigItem {
deliverable: string;
queue: string;
}
type VulnTypeConfig = Record<VulnType, VulnTypeConfigItem>;
type ErrorMessageResolver = string | ((existence: FileExistence) => string);
interface ValidationRule {
predicate: (existence: FileExistence) => boolean;
errorMessage: ErrorMessageResolver;
retryable: boolean;
}
interface FileExistence {
deliverableExists: boolean;
queueExists: boolean;
}
interface PathsBase {
vulnType: VulnType;
deliverable: string;
queue: string;
sourceDir: string;
}
interface PathsWithExistence extends PathsBase {
existence: FileExistence;
}
interface PathsWithQueue extends PathsWithExistence {
queueData: QueueData;
}
interface PathsWithError {
error: PentestError;
}
interface QueueData {
vulnerabilities: unknown[];
[key: string]: unknown;
}
interface QueueValidationResult {
valid: boolean;
data: QueueData | null;
error: string | null;
}
export interface ExploitationDecision {
shouldExploit: boolean;
shouldRetry: boolean;
vulnerabilityCount: number;
vulnType: VulnType;
}
export interface SafeValidationResult {
success: boolean;
data?: ExploitationDecision;
error?: PentestError;
}
// Vulnerability type configuration as immutable data
const VULN_TYPE_CONFIG: VulnTypeConfig = Object.freeze({
injection: Object.freeze({
deliverable: 'injection_analysis_deliverable.md',
queue: 'injection_exploitation_queue.json',
}),
xss: Object.freeze({
deliverable: 'xss_analysis_deliverable.md',
queue: 'xss_exploitation_queue.json',
}),
auth: Object.freeze({
deliverable: 'auth_analysis_deliverable.md',
queue: 'auth_exploitation_queue.json',
}),
ssrf: Object.freeze({
deliverable: 'ssrf_analysis_deliverable.md',
queue: 'ssrf_exploitation_queue.json',
}),
authz: Object.freeze({
deliverable: 'authz_analysis_deliverable.md',
queue: 'authz_exploitation_queue.json',
}),
}) as VulnTypeConfig;
// Pure function to create validation rule
function createValidationRule(
predicate: (existence: FileExistence) => boolean,
errorMessage: ErrorMessageResolver,
retryable: boolean = true
): ValidationRule {
return Object.freeze({ predicate, errorMessage, retryable });
}
// Symmetric deliverable rules: queue and deliverable must exist together (prevents partial analysis from triggering exploitation)
const fileExistenceRules: readonly ValidationRule[] = Object.freeze([
createValidationRule(
({ deliverableExists, queueExists }) => deliverableExists && queueExists,
getExistenceErrorMessage
),
]);
// Generate appropriate error message based on which files are missing
function getExistenceErrorMessage(existence: FileExistence): string {
const { deliverableExists, queueExists } = existence;
if (!deliverableExists && !queueExists) {
return 'Analysis failed: Neither deliverable nor queue file exists. Analysis agent must create both files.';
}
if (!queueExists) {
return 'Analysis incomplete: Deliverable exists but queue file missing. Analysis agent must create both files.';
}
return 'Analysis incomplete: Queue exists but deliverable file missing. Analysis agent must create both files.';
}
// Pure function to create file paths
const createPaths = (
vulnType: VulnType,
sourceDir: string
): PathsBase | PathsWithError => {
const config = VULN_TYPE_CONFIG[vulnType];
if (!config) {
return {
error: new PentestError(
`Unknown vulnerability type: ${vulnType}`,
'validation',
false,
{ vulnType }
),
};
}
return Object.freeze({
vulnType,
deliverable: path.join(sourceDir, 'deliverables', config.deliverable),
queue: path.join(sourceDir, 'deliverables', config.queue),
sourceDir,
});
};
// Pure function to check file existence
const checkFileExistence = async (
paths: PathsBase | PathsWithError
): Promise<PathsWithExistence | PathsWithError> => {
if ('error' in paths) return paths;
const [deliverableExists, queueExists] = await Promise.all([
fs.pathExists(paths.deliverable),
fs.pathExists(paths.queue),
]);
return Object.freeze({
...paths,
existence: Object.freeze({ deliverableExists, queueExists }),
});
};
// Validates deliverable/queue symmetry - both must exist or neither
const validateExistenceRules = (
pathsWithExistence: PathsWithExistence | PathsWithError
): PathsWithExistence | PathsWithError => {
if ('error' in pathsWithExistence) return pathsWithExistence;
const { existence, vulnType } = pathsWithExistence;
// Find the first rule that fails
const failedRule = fileExistenceRules.find((rule) => !rule.predicate(existence));
if (failedRule) {
const message =
typeof failedRule.errorMessage === 'function'
? failedRule.errorMessage(existence)
: failedRule.errorMessage;
return {
error: new PentestError(
`${message} (${vulnType})`,
'validation',
failedRule.retryable,
{
vulnType,
deliverablePath: pathsWithExistence.deliverable,
queuePath: pathsWithExistence.queue,
existence,
}
),
};
}
return pathsWithExistence;
};
// Pure function to validate queue structure
const validateQueueStructure = (content: string): QueueValidationResult => {
try {
const parsed = JSON.parse(content) as unknown;
const isValid =
typeof parsed === 'object' &&
parsed !== null &&
'vulnerabilities' in parsed &&
Array.isArray((parsed as QueueData).vulnerabilities);
return Object.freeze({
valid: isValid,
data: isValid ? (parsed as QueueData) : null,
error: null,
});
} catch (parseError) {
return Object.freeze({
valid: false,
data: null,
error: parseError instanceof Error ? parseError.message : String(parseError),
});
}
};
// Queue parse failures are retryable - agent can fix malformed JSON on retry
const validateQueueContent = async (
pathsWithExistence: PathsWithExistence | PathsWithError
): Promise<PathsWithQueue | PathsWithError> => {
if ('error' in pathsWithExistence) return pathsWithExistence;
try {
const queueContent = await fs.readFile(pathsWithExistence.queue, 'utf8');
const queueValidation = validateQueueStructure(queueContent);
if (!queueValidation.valid) {
// Rule 6: Both exist, queue invalid
return {
error: new PentestError(
queueValidation.error
? `Queue validation failed for ${pathsWithExistence.vulnType}: Invalid JSON structure. Analysis agent must fix queue format.`
: `Queue validation failed for ${pathsWithExistence.vulnType}: Missing or invalid 'vulnerabilities' array. Analysis agent must fix queue structure.`,
'validation',
true, // retryable
{
vulnType: pathsWithExistence.vulnType,
queuePath: pathsWithExistence.queue,
originalError: queueValidation.error,
queueStructure: queueValidation.data ? Object.keys(queueValidation.data) : [],
}
),
};
}
return Object.freeze({
...pathsWithExistence,
queueData: queueValidation.data!,
});
} catch (readError) {
return {
error: new PentestError(
`Failed to read queue file for ${pathsWithExistence.vulnType}: ${readError instanceof Error ? readError.message : String(readError)}`,
'filesystem',
false,
{
vulnType: pathsWithExistence.vulnType,
queuePath: pathsWithExistence.queue,
originalError: readError instanceof Error ? readError.message : String(readError),
}
),
};
}
};
// Final decision: skip if queue says no vulns, proceed if vulns found, error otherwise
const determineExploitationDecision = (
validatedData: PathsWithQueue | PathsWithError
): ExploitationDecision => {
if ('error' in validatedData) {
throw validatedData.error;
}
const hasVulnerabilities = validatedData.queueData.vulnerabilities.length > 0;
// Rule 4: Both exist, queue valid and populated
// Rule 5: Both exist, queue valid but empty
return Object.freeze({
shouldExploit: hasVulnerabilities,
shouldRetry: false,
vulnerabilityCount: validatedData.queueData.vulnerabilities.length,
vulnType: validatedData.vulnType,
});
};
// Main functional validation pipeline
export async function validateQueueAndDeliverable(
vulnType: VulnType,
sourceDir: string
): Promise<ExploitationDecision> {
return asyncPipe<ExploitationDecision>(
createPaths(vulnType, sourceDir),
checkFileExistence,
validateExistenceRules,
validateQueueContent,
determineExploitationDecision
);
}
// Pure function to safely validate (returns result instead of throwing)
export const safeValidateQueueAndDeliverable = async (
vulnType: VulnType,
sourceDir: string
): Promise<SafeValidationResult> => {
try {
const result = await validateQueueAndDeliverable(vulnType, sourceDir);
return { success: true, data: result };
} catch (error) {
return { success: false, error: error as PentestError };
}
};