mirror of
https://github.com/KeygraphHQ/shannon.git
synced 2026-10-04 15:26:55 +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.
117 lines
4.1 KiB
TypeScript
117 lines
4.1 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.
|
|
|
|
/**
|
|
* Per-session custom tools registered for every agent: `todo_write` and `glob`.
|
|
*
|
|
* These replace harness built-ins that pi does not ship. `todo_write` is a
|
|
* full-state-replace planning scratchpad mirrored to the workflow log; `glob` is
|
|
* fast-glob file matching (pi has no `Glob` built-in).
|
|
*/
|
|
|
|
import { defineTool, type ToolDefinition } from '@earendil-works/pi-coding-agent';
|
|
import { Type } from 'typebox';
|
|
import { fs, glob, path } from 'zx';
|
|
|
|
import type { AuditLogger } from '../audit-logger.js';
|
|
|
|
export interface TodoItem {
|
|
content: string;
|
|
status: 'pending' | 'in_progress' | 'completed';
|
|
activeForm: string;
|
|
}
|
|
|
|
function renderTodos(todos: readonly TodoItem[]): string {
|
|
const mark = (status: TodoItem['status']): string => {
|
|
if (status === 'completed') return 'x';
|
|
if (status === 'in_progress') return '~';
|
|
return ' ';
|
|
};
|
|
return todos.map((todo) => `[${mark(todo.status)}] ${todo.content}`).join(' ');
|
|
}
|
|
|
|
export function createTodoWriteTool(auditLogger: AuditLogger): ToolDefinition {
|
|
let current: TodoItem[] = [];
|
|
|
|
return defineTool({
|
|
name: 'todo_write',
|
|
label: 'Todo Write',
|
|
description:
|
|
'Use this tool to create and manage a structured task list for your current session. ' +
|
|
'Pass the complete todo list on every call; it replaces the stored list entirely. Each ' +
|
|
'todo has a status of pending, in_progress, or completed.',
|
|
promptSnippet: 'todo_write: create and manage a structured task list',
|
|
parameters: Type.Object({
|
|
todos: Type.Array(
|
|
Type.Object({
|
|
content: Type.String({ description: 'Imperative task description, e.g. "Map SSRF sinks".' }),
|
|
status: Type.Union([Type.Literal('pending'), Type.Literal('in_progress'), Type.Literal('completed')]),
|
|
activeForm: Type.String({ description: 'Present-continuous form, e.g. "Mapping SSRF sinks".' }),
|
|
}),
|
|
),
|
|
}),
|
|
async execute(_toolCallId, params) {
|
|
current = params.todos as TodoItem[];
|
|
const completed = current.filter((todo) => todo.status === 'completed').length;
|
|
await auditLogger.logNote('todo', renderTodos(current));
|
|
return {
|
|
content: [
|
|
{
|
|
type: 'text' as const,
|
|
text: `Todos updated (${current.length} items, ${completed} completed).`,
|
|
},
|
|
],
|
|
details: undefined,
|
|
};
|
|
},
|
|
});
|
|
}
|
|
|
|
export function createGlobTool(cwd: string): ToolDefinition {
|
|
return defineTool({
|
|
name: 'glob',
|
|
label: 'Glob',
|
|
description:
|
|
'Fast file pattern matching. Supports glob patterns like "**/*.ts" or "src/**/*.{js,ts}". ' +
|
|
'Returns matching file paths sorted by modification time, most recent first.',
|
|
promptSnippet: 'glob: find files by name pattern',
|
|
parameters: Type.Object({
|
|
pattern: Type.String({ description: 'The glob pattern to match files against.' }),
|
|
path: Type.Optional(Type.String({ description: 'Directory to search in. Omit for the repository root.' })),
|
|
}),
|
|
async execute(_toolCallId, params) {
|
|
const searchRoot = params.path ? path.resolve(cwd, params.path) : cwd;
|
|
const matches = await glob.globby(params.pattern, {
|
|
cwd: searchRoot,
|
|
absolute: true,
|
|
dot: true,
|
|
onlyFiles: true,
|
|
followSymbolicLinks: false,
|
|
});
|
|
|
|
if (matches.length === 0) {
|
|
return { content: [{ type: 'text' as const, text: 'No files found' }], details: undefined };
|
|
}
|
|
|
|
const withMtime = await Promise.all(
|
|
matches.map(async (file) => {
|
|
try {
|
|
return { file, mtime: (await fs.stat(file)).mtimeMs };
|
|
} catch {
|
|
return { file, mtime: 0 };
|
|
}
|
|
}),
|
|
);
|
|
withMtime.sort((a, b) => b.mtime - a.mtime);
|
|
|
|
return {
|
|
content: [{ type: 'text' as const, text: withMtime.map((match) => match.file).join('\n') }],
|
|
details: undefined,
|
|
};
|
|
},
|
|
});
|
|
}
|