mirror of
https://github.com/KeygraphHQ/shannon.git
synced 2026-10-03 23:06:51 +02:00
* feat(worker): migrate agent runtime from Claude Agent SDK to pi harness * feat: remove Google Vertex AI provider support * fix(worker): route Bedrock and custom-base-URL providers from env * feat(prompts): instruct agents to call submit_exploitation_queue and submit_auth_result * fix(worker): count sub-agent cost and surface compaction failures * refactor(worker): rename claude-executor to pi-executor * feat(worker): pi-event-driven output formatting * fix(worker): gate adaptive thinking to Opus models, drop CLAUDE_THINKING_LEVEL * fix(worker): restore minLength/minItems on vuln-collector schemas * feat(worker): give task sub-agent write+bash, align tool descriptions * feat(worker): add glob custom tool and route code_path globs to it * refactor(prompts): use pi tool names (task, todo_write, read, bash, glob) * refactor(prompts): drop stale MCP terminology for collector tools * refactor(prompts): drop collector server names from deliverable instructions * fix(worker): restore minLength/minItems on pre-recon and exploit collector schemas * feat(worker): load playwright-cli skill via pi resource loader * refactor(cli): remove CLAUDE_CODE_MAX_OUTPUT_TOKENS config * build: drop @anthropic-ai/claude-code from worker image * docs: remove vertex references from llms context * docs(worker): update stale sdk comments * refactor(worker): unify provider precedence between preflight and executor * feat(worker): enforce bounded bash timeouts via pi extension * ci: bump the beta release line to 2.0.0 (#356) * fix(cli): pin npx command hints to beta tag * fix: render agent deliverables before the success commit so resume preserves them (#377) * feat(cli): restructure run folder and improve terminal UX (#383) * feat: surface report at run root and nest run internals under .shannon * feat: use plain-language wording in user-facing terminal messages * feat(cli): guide users to watch scan progress and surface report path on start * docs: sync run-folder layout and CLI wording across docs and comments * feat(cli): add version command reporting package version or git SHA * feat(cli): detect TTY for interactive prompts, color, and progress output * docs: document --yes flag, version command, and tty module * fix(cli): FORCE_COLOR precedence and plain uninstall --yes output * fix(cli): respect empty NO_COLOR * fix(cli): let NO_COLOR take precedence over FORCE_COLOR * docs: mark claude-code-router integration as removed * refactor(worker): converge shared core with shannon-oss (#388) * fix(worker): port keygraph shared-core correctness fixes * refactor(worker): adopt collectors/ and ai/pi/ layout; add task budget cap and cancellation * refactor(worker): drop inconsistent Collector "Server" suffix * refactor(worker): drop unused providerConfig/apiKey seams, resolve credentials from env only * refactor(worker): port oss code_path pattern expansion + external_directory allow * fix(worker): preserve dotfile paths in code_path avoid patterns (.env no longer stripped to env) * feat(worker): render Unprocessed Vulnerabilities section in exploit deliverable (align with oss) * feat(worker): request set_blind_spots for all vuln classes (align auth/ssrf with production prompts) * refactor(worker): adopt unified permissionSystem* naming and helper layout * refactor(worker): inline blind_spots into vuln deliverable section array * chore(worker): drop unused zod dependency (tree is typebox-native) * fix(worker): normalize base32 TOTP secret to accept padding and whitespace * refactor(worker): adopt shared toolResult helper and flatSchema naming in collectors * refactor(worker): use undefined over null in queue-schema builders * docs(worker): converge renderer/collector doc comments to current pi terminology * refactor(worker): adopt schema.ts cleanInput/stringEnum helpers in collectors * feat(worker): converge exploit-collector/renderer with vendored; capture and render overview for blocked findings * refactor(worker): converge session-tools/pipeline/exploitation-checker with vendored * refactor(worker): converge task-tool usage reporting with vendored onUsage callback * refactor(worker): converge structured output onto a submitTool executor channel * docs(worker): expand exploit-renderer docstring to match shannon-oss * docs(worker): adopt richer vuln-renderer docstring from shannon-oss * docs(worker): neutralize billing-detection wording for shannon-oss parity * fix(worker): verify checkpoint hash in the deliverables clone being reset * fix(worker): fail fast on malformed exploitation queue JSON * fix(worker): honor retryable flag when classifying exploitation-queue check failures * fix(worker): fail fast on corrupted session.json in run-scope validation * feat(worker): propagate Temporal cancellation signal into agent and auth pi sessions * fix(worker): mark exploit agent complete when exploitation is skipped so resume skips it * prompts: drop scan description from executive report prompt * refactor(worker): add createGenericSubmitTool for raw JSON-schema submit tools * refactor(worker): gate playwright-cli skill to browser agents via skillsOverride (adopt shannon-oss mechanism) * docs(worker): correct formatLogTime comment to UTC to match toISOString * refactor(worker): converge queue-schemas with shannon-oss (guarded count, decl order) * refactor(worker): converge task-tool with shannon-oss (byte-identical; modelRegistry optional) * fix(worker): use replaceLiteral for all prompt value insertions to prevent $-mangling * fix(worker): classify agent execution failures by error type instead of hardcoding validation * fix(worker): cap auth-failure detail at 250 chars to match shannon-oss * style(worker): apply biome formatting * refactor(worker): remove per-session task delegation cap from task tool * style(cli): collapse usage hint now that the beta tag is gone * chore: mark the pi harness migration as a breaking change BREAKING CHANGE: Google Vertex AI is no longer a supported provider. The CLAUDE_CODE_USE_VERTEX, ANTHROPIC_VERTEX_PROJECT, CLOUD_ML_REGION, and GOOGLE_APPLICATION_CREDENTIALS environment variables, along with the use_vertex, vertex_project, and cloud_ml_region config.toml keys, are removed. Vertex users must switch to Anthropic, AWS Bedrock, or a custom Anthropic-compatible base URL. The CLAUDE_CODE_MAX_OUTPUT_TOKENS environment variable and the max_output_tokens config.toml key are also removed.
59 lines
2.4 KiB
TypeScript
59 lines
2.4 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.
|
|
|
|
/**
|
|
* Exploitation Checker Service
|
|
*
|
|
* Pure domain logic for determining whether exploitation should run.
|
|
* Reads queue file, parses JSON, returns decision.
|
|
*
|
|
* No Temporal dependencies - this is pure business logic.
|
|
*/
|
|
|
|
import type { ActivityLogger } from '../types/activity-logger.js';
|
|
import { isOk } from '../types/result.js';
|
|
import { type ExploitationDecision, type VulnType, validateQueueSafe } from './queue-validation.js';
|
|
|
|
/**
|
|
* Service for checking exploitation queue decisions.
|
|
*
|
|
* Determines whether an exploit agent should run based on
|
|
* the vulnerability analysis deliverables and queue files.
|
|
*/
|
|
export class ExploitationCheckerService {
|
|
/**
|
|
* Check if exploitation should run for a given vulnerability type.
|
|
*
|
|
* Reads the vulnerability queue file and returns the decision.
|
|
* This is pure domain logic - reads queue file, parses JSON, returns decision.
|
|
*
|
|
* @param vulnType - Type of vulnerability (injection, xss, auth, ssrf, authz)
|
|
* @param repoPath - Path to the repository containing deliverables
|
|
* @param logger - ActivityLogger for structured logging
|
|
* @returns ExploitationDecision indicating whether to exploit
|
|
* @throws PentestError if queue validation fails (retryable or not)
|
|
*/
|
|
async checkQueue(vulnType: VulnType, repoPath: string, logger: ActivityLogger): Promise<ExploitationDecision> {
|
|
const result = await validateQueueSafe(vulnType, repoPath);
|
|
|
|
if (isOk(result)) {
|
|
const decision = result.value;
|
|
logger.info(
|
|
`${vulnType}: ${decision.shouldExploit ? `${decision.vulnerabilityCount} vulnerabilities found` : 'no vulnerabilities, skipping exploitation'}`,
|
|
);
|
|
return decision;
|
|
}
|
|
|
|
// Validation failed. Throw in every case so the error reaches the workflow's
|
|
// per-class handler. Laundering a failure into a "no vulnerabilities" decision
|
|
// would render an un-assessed class as clean. Retryable vs non-retryable is
|
|
// decided downstream at the activity boundary.
|
|
const error = result.error;
|
|
logger.warn(`${vulnType}: ${error.message}${error.retryable ? ' (retryable)' : ' (non-retryable, failing class)'}`);
|
|
throw error;
|
|
}
|
|
}
|