mirror of
https://github.com/KeygraphHQ/shannon.git
synced 2026-05-17 22:54:46 +02:00
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>
This commit is contained in:
committed by
GitHub
parent
45acb16711
commit
51e621d0d5
+40
-35
@@ -6,6 +6,7 @@
|
||||
|
||||
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';
|
||||
|
||||
@@ -16,9 +17,11 @@ interface VulnTypeConfigItem {
|
||||
|
||||
type VulnTypeConfig = Record<VulnType, VulnTypeConfigItem>;
|
||||
|
||||
type ErrorMessageResolver = string | ((existence: FileExistence) => string);
|
||||
|
||||
interface ValidationRule {
|
||||
predicate: (existence: FileExistence) => boolean;
|
||||
errorMessage: string;
|
||||
errorMessage: ErrorMessageResolver;
|
||||
retryable: boolean;
|
||||
}
|
||||
|
||||
@@ -94,40 +97,36 @@ const VULN_TYPE_CONFIG: VulnTypeConfig = Object.freeze({
|
||||
}),
|
||||
}) as VulnTypeConfig;
|
||||
|
||||
// Functional composition utilities - async pipe for promise chain
|
||||
type PipeFunction = (x: any) => any | Promise<any>;
|
||||
|
||||
const pipe =
|
||||
(...fns: PipeFunction[]) =>
|
||||
(x: any): Promise<any> =>
|
||||
fns.reduce(async (v, f) => f(await v), Promise.resolve(x));
|
||||
|
||||
// Pure function to create validation rule
|
||||
const createValidationRule = (
|
||||
function createValidationRule(
|
||||
predicate: (existence: FileExistence) => boolean,
|
||||
errorMessage: string,
|
||||
errorMessage: ErrorMessageResolver,
|
||||
retryable: boolean = true
|
||||
): ValidationRule => Object.freeze({ predicate, errorMessage, retryable });
|
||||
): ValidationRule {
|
||||
return Object.freeze({ predicate, errorMessage, retryable });
|
||||
}
|
||||
|
||||
// Validation rules for file existence (following QUEUE_VALIDATION_FLOW.md)
|
||||
// Symmetric deliverable rules: queue and deliverable must exist together (prevents partial analysis from triggering exploitation)
|
||||
const fileExistenceRules: readonly ValidationRule[] = Object.freeze([
|
||||
// Rule 1: Neither deliverable nor queue exists
|
||||
createValidationRule(
|
||||
({ deliverableExists, queueExists }) => deliverableExists || queueExists,
|
||||
'Analysis failed: Neither deliverable nor queue file exists. Analysis agent must create both files.'
|
||||
),
|
||||
// Rule 2: Queue doesn't exist but deliverable exists
|
||||
createValidationRule(
|
||||
({ deliverableExists, queueExists }) => !(!queueExists && deliverableExists),
|
||||
'Analysis incomplete: Deliverable exists but queue file missing. Analysis agent must create both files.'
|
||||
),
|
||||
// Rule 3: Queue exists but deliverable doesn't exist
|
||||
createValidationRule(
|
||||
({ deliverableExists, queueExists }) => !(queueExists && !deliverableExists),
|
||||
'Analysis incomplete: Queue exists but deliverable file missing. Analysis agent must create both files.'
|
||||
({ 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,
|
||||
@@ -170,7 +169,7 @@ const checkFileExistence = async (
|
||||
});
|
||||
};
|
||||
|
||||
// Pure function to validate existence rules
|
||||
// Validates deliverable/queue symmetry - both must exist or neither
|
||||
const validateExistenceRules = (
|
||||
pathsWithExistence: PathsWithExistence | PathsWithError
|
||||
): PathsWithExistence | PathsWithError => {
|
||||
@@ -182,9 +181,14 @@ const validateExistenceRules = (
|
||||
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(
|
||||
`${failedRule.errorMessage} (${vulnType})`,
|
||||
`${message} (${vulnType})`,
|
||||
'validation',
|
||||
failedRule.retryable,
|
||||
{
|
||||
@@ -224,7 +228,7 @@ const validateQueueStructure = (content: string): QueueValidationResult => {
|
||||
}
|
||||
};
|
||||
|
||||
// Pure function to read and validate queue content
|
||||
// Queue parse failures are retryable - agent can fix malformed JSON on retry
|
||||
const validateQueueContent = async (
|
||||
pathsWithExistence: PathsWithExistence | PathsWithError
|
||||
): Promise<PathsWithQueue | PathsWithError> => {
|
||||
@@ -273,7 +277,7 @@ const validateQueueContent = async (
|
||||
}
|
||||
};
|
||||
|
||||
// Pure function to determine exploitation decision
|
||||
// Final decision: skip if queue says no vulns, proceed if vulns found, error otherwise
|
||||
const determineExploitationDecision = (
|
||||
validatedData: PathsWithQueue | PathsWithError
|
||||
): ExploitationDecision => {
|
||||
@@ -294,17 +298,18 @@ const determineExploitationDecision = (
|
||||
};
|
||||
|
||||
// Main functional validation pipeline
|
||||
export const validateQueueAndDeliverable = async (
|
||||
export async function validateQueueAndDeliverable(
|
||||
vulnType: VulnType,
|
||||
sourceDir: string
|
||||
): Promise<ExploitationDecision> =>
|
||||
(await pipe(
|
||||
() => createPaths(vulnType, sourceDir),
|
||||
): Promise<ExploitationDecision> {
|
||||
return asyncPipe<ExploitationDecision>(
|
||||
createPaths(vulnType, sourceDir),
|
||||
checkFileExistence,
|
||||
validateExistenceRules,
|
||||
validateQueueContent,
|
||||
determineExploitationDecision
|
||||
)(() => createPaths(vulnType, sourceDir))) as ExploitationDecision;
|
||||
);
|
||||
}
|
||||
|
||||
// Pure function to safely validate (returns result instead of throwing)
|
||||
export const safeValidateQueueAndDeliverable = async (
|
||||
|
||||
Reference in New Issue
Block a user