Compare commits

...

4 Commits

Author SHA1 Message Date
ce31577d1e v2.0.0-beta: write tools, pending-changes queue, inference loop, API routes
Phase 2 of v2.0. BooCoder is now a functional write-capable chatbot.

Write-path guard: resolveWritePath() uses resolve() (no realpath — files may
not exist for creates) + prefix-check + secret-file deny list (.env, *.pem,
id_rsa*, etc.). 23 unit tests cover traversal attacks.

Pending-changes service: queueEdit/Create/Delete → applyOne/All →
rejectOne/All → rewindOne. Edit diffs stored as JSON {old, new}. All writes
queue before touching disk; apply re-validates the path guard.

5 write tools: edit_file, create_file, delete_file, apply_pending, rewind.
Registered alongside 25 read-only tools from BooChat (30 total, alpha-sorted).
Write tools use a module-level inference context for sql+sessionId injection.

Inference loop via workspace dependency: apps/coder imports
createInferenceRunner, createBroker, ALL_TOOLS from @boocode/server (dist/).
apps/server gains declaration: true + exports map with typed subpath entries.
No code duplication — one inference engine shared by both apps.

API routes: POST /api/sessions/:id/messages (user msg → inference), POST stop,
GET/POST pending-changes CRUD (5 endpoints), WebSocket session streaming.

Dockerfile updated to build apps/server first (coder depends on its .d.ts).
Health endpoint reports tool count: {"ok":true,"db":true,"tools":30}.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-25 01:53:38 +00:00
006226cce5 v2.0.0-alpha: BooCoder foundation — container, schema, DB rename
Phase 1 of v2.0. BooCoder is live at port 9502 with a health endpoint.

- Database renamed: ALTER DATABASE boocode RENAME TO boochat (one-time).
  All services updated to connect to /boochat. Docker service name stays
  boocode_db (rename is internal to Postgres, not Docker).

- New apps/coder/ app skeleton: Fastify server with health endpoint,
  postgres connection, schema apply on boot. Mirrors apps/server pattern
  but minimal (no inference loop yet — Phase 2).

- Schema: pending_changes (operation queue before /apply), tasks (dispatch
  DAG with state machine), available_agents (startup-probed agent registry),
  human_inbox view (tasks WHERE state IN blocked/failed). All IF NOT EXISTS,
  idempotent on re-run. Same boochat database, different tables.

- Dockerfile: Node 20 bookworm-slim (glibc for future node-pty in Phase 5).
  Multi-stage build matching the existing boocode image pattern.

- docker-compose.yml: boocoder service on 100.114.205.53:9502, /opt:/opt:rw
  mount (write-capable, policy-gated at tool layer), depends on boocode_db.

- BOOCODER.md: container guidance declaring write-tool capability +
  pending-changes discipline.

All 4 services boot and pass health checks. 9 tables in the shared DB.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-25 01:20:29 +00:00
62d818af23 v2.0 implementation plan: 8 phases from foundation to production
Detailed execution plan for all v2.0 sub-versions:

Phase 1 (v2.0.0-alpha): container skeleton, DB rename, schema migration
Phase 2 (v2.0.0-beta): write tools + pending-changes service + fuzz tests
Phase 3 (v2.0.0): frontend diff pane + chat pane + Caddy routing
Phase 4 (v2.0.0-final): dispatcher worker + task queue + agent probing
Phase 5 (v2.0.1): ACP client + PTY fallback + worktree management
Phase 6 (v2.0.2): MCP server (6 tools, stdio, 10-question eval)
Phase 7 (v2.0.3): CLI + human inbox + cost tracking + observation hooks + Boomerang
Phase 8 (v2.0.x): path-guard fuzz, integration tests, docs, production deploy

~2050 LoC total. Phases 1-4 sequential, 5-7 parallelizable after 4.
Risk register covers path-guard bypass, ACP instability, worktree cleanup,
DB rename, MCP eval, Boomerang context leak.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-25 01:09:05 +00:00
531d39ace9 v2.0 proposal update: add AGENTS.md extensions, Boomerang pattern, observation hooks, follow-up batches
Additions from second pass of boocode_code_review.md:

- AGENTS.md extensions: output_schema, exit_expression, execution_strategy
  (qodo-ai/agents MIT), expert_model escape hatch (RA.Aid Apache-2.0)
- Subagent isolation via Boomerang Tasks pattern: orchestrator-only-dispatches,
  down-pass/up-pass context discipline, fresh session per subtask
- Observation hooks: 5-event taxonomy from budi (SessionStart, UserPromptSubmit,
  PostToolUse, SubagentStart, Stop) mapped to WS frames
- Follow-up batches table: PR-resolver, HMAC audit log, blind-validation gate,
  majority-vote ensembler, drift detection, anti-slop, globstar gate, Docker
  sandbox, multi-provider LLM
- Additional repo to clone: qodo-ai/agents for agent.toml schema reference

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-24 23:22:57 +00:00
30 changed files with 2040 additions and 25 deletions

View File

@@ -1,27 +1,32 @@
# BooCoder
# BooCoder — Container Guidance
> (Stub. v2.0 implementation pending. This file documents the intended contract.)
You are BooCoder, a write-capable coding agent. You can read AND modify files within the project scope.
## Capabilities
## You can
- Everything in `BOOCHAT.md`
- Write tools (pending): `write_file`, `edit_file`, `delete_file` (all gated through pending-changes sandbox)
- Shell (pending): `run_command` (Docker-isolated per-session)
- Read files (view_file, list_dir, grep, find_files)
- Edit files (edit_file, create_file, delete_file) — all changes queue in pending_changes
- Apply pending changes to disk (apply_pending)
- Revert applied changes (rewind)
- Dispatch tasks to external agents (dispatch_external_agent)
- Use MCP tools from configured servers
## Constraints
## You cannot
- All writes land in a pending-changes virtual layer; nothing touches the real filesystem until `/apply`
- `run_command` executes inside the session sandbox, not the host
- No git commits, pushes, or pulls — Sam owns those
- Stop and ask before destructive operations (delete, overwrite, recreate)
- Write outside the project root (path-guard enforced)
- Write to secret files (.env, *.pem, id_rsa*, credentials.json)
- Apply changes without explicit user approval (unless auto-apply is enabled per task)
- Push to git remotes
- Access the internet except via configured MCP servers
## Pending changes discipline
Every file modification queues in `pending_changes` before touching disk. The user sees a diff preview and approves/rejects each change. Never bypass this queue — it is the safety boundary between inference and the filesystem.
## Behavior
- Show a diff preview before any write
- Group related edits into a single `/apply` batch
- If a tool fails, surface the error verbatim — don't paper over it
- Show diffs clearly. Explain what you're changing and why.
- For multi-file changes, organize as a logical unit (one task = one coherent change set).
- If uncertain about scope, use smaller edits and verify between steps.
- Cite file paths + line numbers for context.
- Verify before reporting work complete: run the relevant test/build/smoke and confirm output matches the claim. Evidence first, assertion second.
## Convention: rules vs recipes
Always-true rules live here, in `BOOCHAT.md`, and in `CLAUDE.md` (100% present each turn). On-demand recipes live in `/data/skills/` (roughly 6% invoke rate in multi-turn per Codeminer42, 2026). Don't file workflow rules as skills — they misfire. See Anthropic agent-skills best-practices (platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices).

32
apps/coder/Dockerfile Normal file
View File

@@ -0,0 +1,32 @@
# syntax=docker/dockerfile:1.7
FROM node:20-alpine AS builder
RUN corepack enable
WORKDIR /build
COPY package.json pnpm-workspace.yaml pnpm-lock.yaml tsconfig.base.json ./
COPY apps/server/package.json ./apps/server/
COPY apps/coder/package.json ./apps/coder/
RUN pnpm install --frozen-lockfile
# Build server first (coder depends on it via workspace dep for types + inference)
COPY apps/server ./apps/server
RUN pnpm -C apps/server build
COPY apps/coder ./apps/coder
RUN pnpm -C apps/coder build
RUN pnpm deploy --filter=@boocode/coder --prod --legacy /out/coder
FROM node:20-bookworm-slim AS runtime
RUN apt-get update && apt-get install -y --no-install-recommends ripgrep git && rm -rf /var/lib/apt/lists/*
WORKDIR /app
COPY --from=builder /out/coder ./
ENV NODE_ENV=production
EXPOSE 3000
CMD ["node", "dist/index.js"]

28
apps/coder/package.json Normal file
View File

@@ -0,0 +1,28 @@
{
"name": "@boocode/coder",
"version": "2.0.0",
"private": true,
"type": "module",
"main": "dist/index.js",
"scripts": {
"dev": "tsx watch src/index.ts",
"build": "tsc && node -e \"import('node:fs').then(fs=>fs.copyFileSync('src/schema.sql','dist/schema.sql'))\"",
"start": "node dist/index.js",
"typecheck": "tsc --noEmit",
"test": "vitest run"
},
"dependencies": {
"@boocode/server": "workspace:*",
"@fastify/static": "^7.0.4",
"@fastify/websocket": "^10.0.1",
"fastify": "^4.28.1",
"postgres": "^3.4.4",
"zod": "^3.23.8"
},
"devDependencies": {
"@types/node": "^20.14.10",
"tsx": "^4.16.2",
"typescript": "^5.5.0",
"vitest": "^3.0.0"
}
}

42
apps/coder/src/config.ts Normal file
View File

@@ -0,0 +1,42 @@
import { z } from 'zod';
// BooCoder's config is a superset of the server's Config type so it can be
// passed directly into the inference runner's InferenceContext. Fields the
// inference loop reads: LLAMA_SWAP_URL, PROJECT_ROOT_WHITELIST. The rest
// default to values that satisfy the server's Zod schema without BooCoder
// needing to supply them in its environment.
const ConfigSchema = z.object({
NODE_ENV: z.enum(['development', 'production', 'test']).default('development'),
PORT: z.coerce.number().int().positive().default(3000),
HOST: z.string().default('0.0.0.0'),
DATABASE_URL: z.string().url(),
LLAMA_SWAP_URL: z.string().url(),
PROJECT_ROOT_WHITELIST: z.string().default('/opt'),
BOOTSTRAP_ROOT: z.string().default('/opt/projects'),
DEFAULT_MODEL: z.string().default('qwen3.6-35b-a3b-mxfp4'),
LOG_LEVEL: z.string().default('info'),
CONTAINER_GUIDANCE_FILE: z.string().optional(),
// Fields needed to satisfy the server's Config type but unused by BooCoder:
SEARXNG_URL: z.string().url().default('http://100.114.205.53:8888'),
GITEA_BASE_URL: z.string().url().default('https://git.indifferentketchup.com'),
GITEA_USER: z.string().default('indifferentketchup'),
GITEA_TOKEN: z.string().optional(),
GITEA_SSH_HOST: z.string().default('100.114.205.53:2222'),
MCP_CONFIG_PATH: z.string().optional(),
});
export type Config = z.infer<typeof ConfigSchema>;
let cached: Config | null = null;
export function loadConfig(): Config {
if (cached) return cached;
const parsed = ConfigSchema.safeParse(process.env);
if (!parsed.success) {
console.error('Invalid environment configuration:');
console.error(parsed.error.flatten().fieldErrors);
process.exit(1);
}
cached = parsed.data;
return cached;
}

45
apps/coder/src/db.ts Normal file
View File

@@ -0,0 +1,45 @@
import postgres from 'postgres';
import { readFile } from 'node:fs/promises';
import { fileURLToPath } from 'node:url';
import { dirname, resolve } from 'node:path';
import type { Config } from './config.js';
const __filename = fileURLToPath(import.meta.url);
const __dirname = dirname(__filename);
export type Sql = ReturnType<typeof postgres>;
let sqlInstance: Sql | null = null;
export function getSql(config: Config): Sql {
if (sqlInstance) return sqlInstance;
sqlInstance = postgres(config.DATABASE_URL, {
max: 10,
idle_timeout: 30,
connect_timeout: 10,
onnotice: () => {},
});
return sqlInstance;
}
export async function applySchema(sql: Sql): Promise<void> {
const schemaPath = resolve(__dirname, 'schema.sql');
const ddl = await readFile(schemaPath, 'utf8');
await sql.unsafe(ddl);
}
export async function pingDb(sql: Sql): Promise<boolean> {
try {
await sql`SELECT 1`;
return true;
} catch {
return false;
}
}
export async function closeDb(): Promise<void> {
if (sqlInstance) {
await sqlInstance.end({ timeout: 5 });
sqlInstance = null;
}
}

131
apps/coder/src/index.ts Normal file
View File

@@ -0,0 +1,131 @@
import Fastify from 'fastify';
import fastifyWebsocket from '@fastify/websocket';
import { loadConfig } from './config.js';
import { getSql, applySchema, pingDb, closeDb } from './db.js';
// v2.0.0 Phase 2B: workspace dependency on @boocode/server — reuse the
// inference loop, broker, and tool registry without duplication.
import { createInferenceRunner } from '@boocode/server/inference';
import { createBroker } from '@boocode/server/broker';
import { appendMcpTools, ALL_TOOLS } from '@boocode/server/tools';
import type { Config as ServerConfig } from '@boocode/server/config';
import type { WsFrame } from '@boocode/server/ws-frames';
// v2.0.0 Phase 2C: write tools + adapter for BooChat ToolDef compatibility.
import { WRITE_TOOLS } from './services/tools/index.js';
import { adaptWriteTool } from './services/tools/adapter.js';
import { setInferenceContext, clearInferenceContext } from './services/tools/inference_context.js';
// Routes
import { registerMessageRoutes } from './routes/messages.js';
import { registerPendingRoutes } from './routes/pending.js';
import { registerWebSocket } from './routes/ws.js';
async function main() {
const config = loadConfig();
const app = Fastify({
logger: { level: config.LOG_LEVEL },
});
// Allow empty JSON bodies (same pattern as apps/server).
app.removeContentTypeParser(['application/json']);
app.addContentTypeParser('application/json', { parseAs: 'string' }, (_req, body, done) => {
const str = (body as string) ?? '';
if (str.trim().length === 0) {
done(null, {});
return;
}
try {
done(null, JSON.parse(str));
} catch (err) {
done(err as Error, undefined);
}
});
const sql = getSql(config);
await applySchema(sql);
app.log.info('database schema applied');
// Broker: in-memory pub/sub for session + user channel streaming.
const broker = createBroker(app.log);
// --- Tool registry extension ---
// Append BooCoder write tools (adapted to BooChat's ToolDef interface) to
// the shared ALL_TOOLS registry. appendMcpTools re-sorts and rebuilds
// TOOLS_BY_NAME so tool-phase.ts dispatch sees the full set.
const adaptedWriteTools = WRITE_TOOLS.map((t) => adaptWriteTool(t));
appendMcpTools(adaptedWriteTools);
app.log.info(`tool registry: ${ALL_TOOLS.length} tools loaded (${WRITE_TOOLS.length} write tools)`);
// Inference runner: same engine as BooChat, uses ALL_TOOLS (which includes
// the appended write tools) for tool dispatch.
const inference = createInferenceRunner(
{
sql,
config: config as unknown as ServerConfig,
log: app.log,
publish: (sessionId, frame) => {
broker.publishFrame(sessionId, frame as unknown as WsFrame);
},
broker,
},
(user, frame) => {
broker.publishUserFrame(user, frame as unknown as WsFrame);
}
);
// Wrap the inference runner to set/clear the write-tool context around each run.
// The inference runner calls enqueue() which fires asynchronously — we hook
// into the enqueue to set context before the run starts.
const inferenceApi = {
enqueue: (sessionId: string, chatId: string, assistantId: string, user: string) => {
// Set the inference context so write tools can access sql + sessionId.
// The context persists for the duration of the inference run. Since
// BooCoder is single-user and runs one inference at a time per session,
// this module-level state is safe.
setInferenceContext({ sql, sessionId, taskId: null });
inference.enqueue(sessionId, chatId, assistantId, user);
},
cancel: async (sessionId: string, chatId: string) => {
const result = await inference.cancel(sessionId, chatId);
clearInferenceContext();
return result;
},
hasActive: (chatId: string) => inference.hasActive(chatId),
};
// Register WebSocket support
await app.register(fastifyWebsocket);
// Health endpoint
app.get('/api/health', async (_req, reply) => {
const dbOk = await pingDb(sql);
const status = dbOk ? 200 : 503;
return reply.status(status).send({
ok: dbOk,
db: dbOk,
tools: ALL_TOOLS.length,
});
});
// Register routes
registerMessageRoutes(app, sql, broker, inferenceApi);
registerPendingRoutes(app, sql);
registerWebSocket(app, sql, broker);
// Graceful shutdown
const shutdown = async () => {
app.log.info('shutting down');
await app.close();
await closeDb();
process.exit(0);
};
process.on('SIGTERM', shutdown);
process.on('SIGINT', shutdown);
await app.listen({ port: config.PORT, host: config.HOST });
app.log.info(`BooCoder listening on ${config.HOST}:${config.PORT}`);
}
main().catch((err) => {
console.error('fatal:', err);
process.exit(1);
});

View File

@@ -0,0 +1,126 @@
import type { FastifyInstance } from 'fastify';
import { z } from 'zod';
import type { Sql } from '../db.js';
import type { Broker } from '@boocode/server/broker';
import type { WsFrame } from '@boocode/server/ws-frames';
const SendBody = z.object({
content: z.string().min(1).max(64_000),
chat_id: z.string().uuid(),
});
interface InferenceApi {
enqueue: (sessionId: string, chatId: string, assistantId: string, user: string) => void;
cancel: (sessionId: string, chatId: string) => Promise<boolean>;
hasActive: (chatId: string) => boolean;
}
export function registerMessageRoutes(
app: FastifyInstance,
sql: Sql,
broker: Broker,
inference: InferenceApi,
): void {
// POST /api/sessions/:sessionId/messages — send a user message + kick off inference
app.post<{ Params: { sessionId: string } }>(
'/api/sessions/:sessionId/messages',
async (req, reply) => {
const parsed = SendBody.safeParse(req.body);
if (!parsed.success) {
reply.code(400);
return { error: 'invalid body', details: parsed.error.flatten() };
}
const sessionId = req.params.sessionId;
const { content, chat_id: chatId } = parsed.data;
// Validate session exists
const sessionRows = await sql<{ id: string }[]>`
SELECT id FROM sessions WHERE id = ${sessionId}
`;
if (sessionRows.length === 0) {
reply.code(404);
return { error: 'session not found' };
}
// Validate chat belongs to session and is open
const chatRows = await sql<{ id: string; session_id: string }[]>`
SELECT id, session_id FROM chats WHERE id = ${chatId} AND session_id = ${sessionId} AND status = 'open'
`;
if (chatRows.length === 0) {
reply.code(404);
return { error: 'chat not found or not open in this session' };
}
// Reject if inference is already running on this chat
if (inference.hasActive(chatId)) {
reply.code(409);
return { error: 'inference already running on this chat' };
}
// Create user message + streaming assistant row in a transaction
const result = await sql.begin(async (tx) => {
const [userMsg] = await tx<{ id: string }[]>`
INSERT INTO messages (session_id, chat_id, role, content, status, created_at)
VALUES (${sessionId}, ${chatId}, 'user', ${content}, 'complete', clock_timestamp())
RETURNING id
`;
const [assistantMsg] = await tx<{ id: string }[]>`
INSERT INTO messages (session_id, chat_id, role, content, status, created_at)
VALUES (${sessionId}, ${chatId}, 'assistant', '', 'streaming', clock_timestamp())
RETURNING id
`;
await tx`UPDATE sessions SET updated_at = clock_timestamp() WHERE id = ${sessionId}`;
await tx`UPDATE chats SET updated_at = clock_timestamp() WHERE id = ${chatId}`;
return { user_message_id: userMsg!.id, assistant_message_id: assistantMsg!.id };
});
// Publish user message frames so WS subscribers see it immediately
broker.publishFrame(sessionId, {
type: 'message_started',
message_id: result.user_message_id,
chat_id: chatId,
role: 'user',
} as unknown as WsFrame);
broker.publishFrame(sessionId, {
type: 'delta',
message_id: result.user_message_id,
chat_id: chatId,
content,
} as unknown as WsFrame);
broker.publishFrame(sessionId, {
type: 'message_complete',
message_id: result.user_message_id,
chat_id: chatId,
} as unknown as WsFrame);
// Enqueue inference — the runner will stream assistant deltas via broker
inference.enqueue(sessionId, chatId, result.assistant_message_id, 'default');
reply.code(202);
return result;
},
);
// POST /api/sessions/:sessionId/stop — cancel active inference
app.post<{ Params: { sessionId: string } }>(
'/api/sessions/:sessionId/stop',
async (req, reply) => {
const sessionId = req.params.sessionId;
// Find active chats in this session
const chats = await sql<{ id: string }[]>`
SELECT id FROM chats WHERE session_id = ${sessionId} AND status = 'open'
`;
let cancelled = false;
for (const chat of chats) {
if (inference.hasActive(chat.id)) {
cancelled = await inference.cancel(sessionId, chat.id);
break;
}
}
return { cancelled };
},
);
}

View File

@@ -0,0 +1,121 @@
import type { FastifyInstance } from 'fastify';
import type { Sql } from '../db.js';
import {
listPending,
applyOne,
applyAll,
rejectOne,
rewindOne,
} from '../services/pending_changes.js';
/**
* Resolve project root from a session's project path.
*/
async function resolveProjectRoot(sql: Sql, sessionId: string): Promise<string | null> {
const rows = await sql<{ path: string }[]>`
SELECT p.path FROM sessions s
JOIN projects p ON s.project_id = p.id
WHERE s.id = ${sessionId}
`;
return rows.length > 0 ? rows[0]!.path : null;
}
/**
* Resolve project root from a pending change's session.
*/
async function resolveProjectRootForChange(sql: Sql, changeId: string): Promise<string | null> {
const rows = await sql<{ path: string }[]>`
SELECT p.path FROM pending_changes pc
JOIN sessions s ON pc.session_id = s.id
JOIN projects p ON s.project_id = p.id
WHERE pc.id = ${changeId}
`;
return rows.length > 0 ? rows[0]!.path : null;
}
export function registerPendingRoutes(app: FastifyInstance, sql: Sql): void {
// GET /api/sessions/:sessionId/pending — list pending changes for a session
app.get<{ Params: { sessionId: string } }>(
'/api/sessions/:sessionId/pending',
async (req, reply) => {
const sessionId = req.params.sessionId;
const session = await sql<{ id: string }[]>`SELECT id FROM sessions WHERE id = ${sessionId}`;
if (session.length === 0) {
reply.code(404);
return { error: 'session not found' };
}
const pending = await listPending(sql, sessionId);
return pending;
},
);
// POST /api/sessions/:sessionId/pending/apply — apply all pending changes
app.post<{ Params: { sessionId: string } }>(
'/api/sessions/:sessionId/pending/apply',
async (req, reply) => {
const sessionId = req.params.sessionId;
const projectRoot = await resolveProjectRoot(sql, sessionId);
if (!projectRoot) {
reply.code(404);
return { error: 'session or project not found' };
}
const results = await applyAll(sql, sessionId, projectRoot);
return { results };
},
);
// POST /api/pending/:id/apply — apply a single pending change
app.post<{ Params: { id: string } }>(
'/api/pending/:id/apply',
async (req, reply) => {
const changeId = req.params.id;
const projectRoot = await resolveProjectRootForChange(sql, changeId);
if (!projectRoot) {
reply.code(404);
return { error: 'pending change or project not found' };
}
const result = await applyOne(sql, changeId, projectRoot);
if (!result.success) {
reply.code(422);
}
return result;
},
);
// POST /api/pending/:id/reject — reject a single pending change
app.post<{ Params: { id: string } }>(
'/api/pending/:id/reject',
async (req, reply) => {
const changeId = req.params.id;
await rejectOne(sql, changeId);
return { ok: true };
},
);
// POST /api/pending/:id/rewind — rewind (undo) an applied change
app.post<{ Params: { id: string } }>(
'/api/pending/:id/rewind',
async (req, reply) => {
const changeId = req.params.id;
const projectRoot = await resolveProjectRootForChange(sql, changeId);
if (!projectRoot) {
reply.code(404);
return { error: 'pending change or project not found' };
}
const result = await rewindOne(sql, changeId, projectRoot);
if (!result.success) {
reply.code(422);
}
return result;
},
);
}

View File

@@ -0,0 +1,51 @@
import type { FastifyInstance } from 'fastify';
import type { Sql } from '../db.js';
import type { Broker } from '@boocode/server/broker';
export function registerWebSocket(
app: FastifyInstance,
sql: Sql,
broker: Broker,
): void {
// Per-session streaming WebSocket. Clients connect here to receive live
// inference frames (deltas, tool_calls, tool_results, message_complete).
app.get<{ Params: { sessionId: string } }>(
'/api/ws/sessions/:sessionId',
{ websocket: true },
async (socket, req) => {
const sessionId = req.params.sessionId;
// Validate session exists
const session = await sql<{ id: string }[]>`SELECT id FROM sessions WHERE id = ${sessionId}`;
if (session.length === 0) {
socket.send(JSON.stringify({ type: 'error', error: 'session not found' }));
socket.close(1008, 'session not found');
return;
}
// Send snapshot of existing messages so client can hydrate
const messages = await sql<Record<string, unknown>[]>`
SELECT id, session_id, chat_id, role, content, kind, tool_calls, tool_results, status, last_seq,
tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at, metadata,
summary, tail_start_id, compacted_at
FROM messages_with_parts
WHERE session_id = ${sessionId}
ORDER BY created_at ASC, id ASC
`;
socket.send(JSON.stringify({ type: 'snapshot', messages }));
// Subscribe to broker for live frames
const unsubscribe = broker.subscribe(sessionId, (frame) => {
if (socket.readyState !== socket.OPEN) return;
try {
socket.send(JSON.stringify(frame));
} catch (err) {
app.log.warn({ err, sessionId }, 'ws send failed');
}
});
socket.on('close', () => unsubscribe());
socket.on('error', () => unsubscribe());
},
);
}

48
apps/coder/src/schema.sql Normal file
View File

@@ -0,0 +1,48 @@
-- v2.0.0: BooCoder schema — pending changes, tasks, agent registry.
-- Applied on startup by apps/coder/src/db.ts:applySchema().
-- Lives in the same 'boochat' database as BooChat's tables.
CREATE TABLE IF NOT EXISTS pending_changes (
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
session_id UUID NOT NULL,
task_id UUID,
file_path TEXT NOT NULL,
operation TEXT NOT NULL,
diff TEXT NOT NULL,
status TEXT NOT NULL DEFAULT 'pending',
created_at TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp(),
CONSTRAINT pending_changes_operation_chk CHECK (operation IN ('create', 'edit', 'delete')),
CONSTRAINT pending_changes_status_chk CHECK (status IN ('pending', 'applied', 'rejected', 'reverted'))
);
CREATE TABLE IF NOT EXISTS tasks (
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
project_id UUID NOT NULL,
parent_task_id UUID REFERENCES tasks(id),
state TEXT NOT NULL DEFAULT 'pending',
input TEXT NOT NULL,
output_summary TEXT,
agent TEXT,
model TEXT,
execution_path TEXT,
worktree_path TEXT,
cost_tokens INTEGER,
started_at TIMESTAMPTZ,
ended_at TIMESTAMPTZ,
created_at TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp(),
CONSTRAINT tasks_state_chk CHECK (state IN ('pending', 'running', 'completed', 'failed', 'blocked', 'cancelled')),
CONSTRAINT tasks_execution_path_chk CHECK (execution_path IS NULL OR execution_path IN ('native', 'acp', 'pty'))
);
CREATE TABLE IF NOT EXISTS available_agents (
name TEXT PRIMARY KEY,
install_path TEXT,
version TEXT,
supports_acp BOOLEAN NOT NULL DEFAULT false,
supports_mcp_client BOOLEAN NOT NULL DEFAULT false,
last_probed_at TIMESTAMPTZ
);
-- Human inbox: tasks needing attention
CREATE OR REPLACE VIEW human_inbox AS
SELECT * FROM tasks WHERE state IN ('blocked', 'failed');

View File

@@ -0,0 +1,115 @@
import { describe, it, expect } from 'vitest';
import { resolveWritePath, isSecretPath, WriteGuardError } from '../write_guard.js';
const PROJECT_ROOT = '/opt/projects/my-app';
describe('resolveWritePath', () => {
it('resolves a relative path correctly', () => {
const result = resolveWritePath(PROJECT_ROOT, 'src/index.ts');
expect(result).toBe('/opt/projects/my-app/src/index.ts');
});
it('resolves nested relative path', () => {
const result = resolveWritePath(PROJECT_ROOT, 'src/lib/utils.ts');
expect(result).toBe('/opt/projects/my-app/src/lib/utils.ts');
});
it('throws on ../ escape', () => {
expect(() => resolveWritePath(PROJECT_ROOT, '../../../etc/passwd')).toThrow(WriteGuardError);
expect(() => resolveWritePath(PROJECT_ROOT, '../../../etc/passwd')).toThrow('path escapes project root');
});
it('throws on absolute path outside project root', () => {
expect(() => resolveWritePath(PROJECT_ROOT, '/etc/shadow')).toThrow(WriteGuardError);
expect(() => resolveWritePath(PROJECT_ROOT, '/tmp/exploit')).toThrow('path escapes project root');
});
it('allows absolute path inside project root', () => {
const result = resolveWritePath(PROJECT_ROOT, '/opt/projects/my-app/src/new.ts');
expect(result).toBe('/opt/projects/my-app/src/new.ts');
});
it('denies .env files', () => {
expect(() => resolveWritePath(PROJECT_ROOT, '.env')).toThrow(WriteGuardError);
expect(() => resolveWritePath(PROJECT_ROOT, '.env')).toThrow('cannot write to secret file');
});
it('denies .env.local', () => {
expect(() => resolveWritePath(PROJECT_ROOT, '.env.local')).toThrow(WriteGuardError);
});
it('denies .env.production', () => {
expect(() => resolveWritePath(PROJECT_ROOT, '.env.production')).toThrow(WriteGuardError);
});
it('denies *.pem files', () => {
expect(() => resolveWritePath(PROJECT_ROOT, 'certs/server.pem')).toThrow(WriteGuardError);
expect(() => resolveWritePath(PROJECT_ROOT, 'certs/server.pem')).toThrow('cannot write to secret file');
});
it('denies *.key files', () => {
expect(() => resolveWritePath(PROJECT_ROOT, 'ssl/private.key')).toThrow(WriteGuardError);
});
it('denies id_rsa', () => {
expect(() => resolveWritePath(PROJECT_ROOT, '.ssh/id_rsa')).toThrow(WriteGuardError);
});
it('denies id_ed25519', () => {
expect(() => resolveWritePath(PROJECT_ROOT, '.ssh/id_ed25519')).toThrow(WriteGuardError);
});
it('denies credentials.json', () => {
expect(() => resolveWritePath(PROJECT_ROOT, 'credentials.json')).toThrow(WriteGuardError);
});
it('passes a normal file inside project', () => {
const result = resolveWritePath(PROJECT_ROOT, 'src/components/Button.tsx');
expect(result).toBe('/opt/projects/my-app/src/components/Button.tsx');
});
it('passes a non-existent nested file (no realpath)', () => {
// This is the key difference from BooChat's pathGuard: no realpath means
// files that don't exist yet still pass validation
const result = resolveWritePath(PROJECT_ROOT, 'src/new-dir/new-file.ts');
expect(result).toBe('/opt/projects/my-app/src/new-dir/new-file.ts');
});
it('throws on null/empty path', () => {
expect(() => resolveWritePath(PROJECT_ROOT, '')).toThrow(WriteGuardError);
expect(() => resolveWritePath(PROJECT_ROOT, '')).toThrow('file path is required');
});
it('normalizes ../ within project root and still allows', () => {
const result = resolveWritePath(PROJECT_ROOT, 'src/../lib/utils.ts');
expect(result).toBe('/opt/projects/my-app/lib/utils.ts');
});
it('rejects path that looks inside root but normalizes outside', () => {
expect(() => resolveWritePath(PROJECT_ROOT, 'src/../../other-project/hack.ts')).toThrow(WriteGuardError);
});
});
describe('isSecretPath', () => {
it('detects .env', () => {
expect(isSecretPath('.env')).toBe(true);
});
it('detects nested .env', () => {
expect(isSecretPath('config/.env')).toBe(true);
});
it('detects *.pfx', () => {
expect(isSecretPath('certs/client.pfx')).toBe(true);
});
it('does not flag normal source files', () => {
expect(isSecretPath('src/index.ts')).toBe(false);
expect(isSecretPath('README.md')).toBe(false);
expect(isSecretPath('package.json')).toBe(false);
});
it('returns false for empty string', () => {
expect(isSecretPath('')).toBe(false);
});
});

View File

@@ -0,0 +1,224 @@
import { readFile, writeFile, unlink, mkdir } from 'node:fs/promises';
import { dirname } from 'node:path';
import type { Sql } from '../db.js';
import { resolveWritePath } from './write_guard.js';
// --- Types -------------------------------------------------------------------
export interface PendingChange {
id: string;
session_id: string;
task_id: string | null;
file_path: string;
operation: 'create' | 'edit' | 'delete';
diff: string;
status: 'pending' | 'applied' | 'rejected' | 'reverted';
created_at: string;
}
export interface ApplyResult {
id: string;
file_path: string;
operation: string;
success: boolean;
error?: string;
}
// --- Queue functions ---------------------------------------------------------
export async function queueEdit(
sql: Sql,
sessionId: string,
taskId: string | null,
filePath: string,
oldString: string,
newString: string,
projectRoot: string,
): Promise<PendingChange> {
const resolved = resolveWritePath(projectRoot, filePath);
const diff = JSON.stringify({ old: oldString, new: newString });
const [row] = await sql<PendingChange[]>`
INSERT INTO pending_changes (session_id, task_id, file_path, operation, diff)
VALUES (${sessionId}, ${taskId}, ${resolved}, 'edit', ${diff})
RETURNING *
`;
return row!;
}
export async function queueCreate(
sql: Sql,
sessionId: string,
taskId: string | null,
filePath: string,
content: string,
projectRoot: string,
): Promise<PendingChange> {
const resolved = resolveWritePath(projectRoot, filePath);
const [row] = await sql<PendingChange[]>`
INSERT INTO pending_changes (session_id, task_id, file_path, operation, diff)
VALUES (${sessionId}, ${taskId}, ${resolved}, 'create', ${content})
RETURNING *
`;
return row!;
}
export async function queueDelete(
sql: Sql,
sessionId: string,
taskId: string | null,
filePath: string,
projectRoot: string,
): Promise<PendingChange> {
const resolved = resolveWritePath(projectRoot, filePath);
const [row] = await sql<PendingChange[]>`
INSERT INTO pending_changes (session_id, task_id, file_path, operation, diff)
VALUES (${sessionId}, ${taskId}, ${resolved}, 'delete', '')
RETURNING *
`;
return row!;
}
// --- Apply functions ---------------------------------------------------------
export async function applyOne(
sql: Sql,
changeId: string,
projectRoot: string,
): Promise<ApplyResult> {
const [change] = await sql<PendingChange[]>`
SELECT * FROM pending_changes WHERE id = ${changeId} AND status = 'pending'
`;
if (!change) {
return { id: changeId, file_path: '', operation: '', success: false, error: 'change not found or not pending' };
}
try {
// Re-validate path in case projectRoot has shifted
resolveWritePath(projectRoot, change.file_path);
switch (change.operation) {
case 'create': {
await mkdir(dirname(change.file_path), { recursive: true });
await writeFile(change.file_path, change.diff, 'utf8');
break;
}
case 'edit': {
const { old: oldStr, new: newStr } = JSON.parse(change.diff) as { old: string; new: string };
const content = await readFile(change.file_path, 'utf8');
if (!content.includes(oldStr)) {
throw new Error('old_string not found in file — file may have changed since the edit was queued');
}
const updated = content.replace(oldStr, newStr);
await writeFile(change.file_path, updated, 'utf8');
break;
}
case 'delete': {
// Stash current content in diff for potential rewind
try {
const existing = await readFile(change.file_path, 'utf8');
await sql`UPDATE pending_changes SET diff = ${existing} WHERE id = ${changeId}`;
} catch {
// File may already be gone — proceed with status update
}
await unlink(change.file_path);
break;
}
}
await sql`UPDATE pending_changes SET status = 'applied' WHERE id = ${changeId}`;
return { id: change.id, file_path: change.file_path, operation: change.operation, success: true };
} catch (err) {
const message = err instanceof Error ? err.message : String(err);
return { id: change.id, file_path: change.file_path, operation: change.operation, success: false, error: message };
}
}
export async function applyAll(
sql: Sql,
sessionId: string,
projectRoot: string,
): Promise<ApplyResult[]> {
const pending = await sql<PendingChange[]>`
SELECT * FROM pending_changes
WHERE session_id = ${sessionId} AND status = 'pending'
ORDER BY created_at ASC
`;
const results: ApplyResult[] = [];
for (const change of pending) {
results.push(await applyOne(sql, change.id, projectRoot));
}
return results;
}
// --- Reject functions --------------------------------------------------------
export async function rejectOne(sql: Sql, changeId: string): Promise<void> {
await sql`UPDATE pending_changes SET status = 'rejected' WHERE id = ${changeId} AND status = 'pending'`;
}
export async function rejectAll(sql: Sql, sessionId: string): Promise<void> {
await sql`UPDATE pending_changes SET status = 'rejected' WHERE session_id = ${sessionId} AND status = 'pending'`;
}
// --- Rewind functions --------------------------------------------------------
export async function rewindOne(
sql: Sql,
changeId: string,
projectRoot: string,
): Promise<ApplyResult> {
const [change] = await sql<PendingChange[]>`
SELECT * FROM pending_changes WHERE id = ${changeId} AND status = 'applied'
`;
if (!change) {
return { id: changeId, file_path: '', operation: '', success: false, error: 'change not found or not applied' };
}
try {
resolveWritePath(projectRoot, change.file_path);
switch (change.operation) {
case 'create': {
// Reverse a create: delete the file
await unlink(change.file_path);
break;
}
case 'edit': {
// Reverse an edit: swap old and new
const { old: oldStr, new: newStr } = JSON.parse(change.diff) as { old: string; new: string };
const content = await readFile(change.file_path, 'utf8');
if (!content.includes(newStr)) {
throw new Error('new_string not found in file — cannot rewind; file may have been modified since apply');
}
const reverted = content.replace(newStr, oldStr);
await writeFile(change.file_path, reverted, 'utf8');
break;
}
case 'delete': {
// Reverse a delete: recreate the file (diff holds the original content stashed at apply time)
await mkdir(dirname(change.file_path), { recursive: true });
await writeFile(change.file_path, change.diff, 'utf8');
break;
}
}
await sql`UPDATE pending_changes SET status = 'reverted' WHERE id = ${changeId}`;
return { id: change.id, file_path: change.file_path, operation: change.operation, success: true };
} catch (err) {
const message = err instanceof Error ? err.message : String(err);
return { id: change.id, file_path: change.file_path, operation: change.operation, success: false, error: message };
}
}
// --- Query functions ---------------------------------------------------------
export async function listPending(sql: Sql, sessionId: string): Promise<PendingChange[]> {
return sql<PendingChange[]>`
SELECT * FROM pending_changes
WHERE session_id = ${sessionId} AND status = 'pending'
ORDER BY created_at ASC
`;
}

View File

@@ -0,0 +1,30 @@
/**
* Adapts BooCoder write tools (which take ToolContext) into BooChat's ToolDef
* interface (which takes `projectRoot, extraRoots?`).
*
* The adapter reads the module-level inference context at execute time, so the
* wrapping happens at boot (static) — no per-inference re-wrap needed.
*/
import type { ToolDef as ServerToolDef } from '@boocode/server/tools';
import type { ToolDef, ToolContext } from './types.js';
import { getInferenceContext } from './inference_context.js';
/**
* Wrap a BooCoder write tool (execute takes ToolContext) into a BooChat
* ToolDef (execute takes projectRoot + optional extraRoots). The adapter
* builds the ToolContext from the module-level inference context at call time.
*/
// eslint-disable-next-line @typescript-eslint/no-explicit-any
export function adaptWriteTool(tool: ToolDef<any>): ServerToolDef<any> {
return {
name: tool.name,
description: tool.description,
inputSchema: tool.inputSchema,
jsonSchema: tool.jsonSchema,
async execute(input: unknown, projectRoot: string, _extraRoots?: readonly string[]): Promise<unknown> {
const ctx: ToolContext = getInferenceContext();
return tool.execute(input, projectRoot, ctx);
},
};
}

View File

@@ -0,0 +1,44 @@
import { z } from 'zod';
import type { ToolDef, ToolContext } from './types.js';
import { applyAll } from '../pending_changes.js';
const ApplyPendingInput = z.object({});
type ApplyPendingInputT = z.infer<typeof ApplyPendingInput>;
export const applyPendingTool: ToolDef<ApplyPendingInputT> = {
name: 'apply_pending',
description:
'Apply all pending changes for the current session to disk. ' +
'Each queued create/edit/delete is executed in order.',
inputSchema: ApplyPendingInput,
jsonSchema: {
type: 'function',
function: {
name: 'apply_pending',
description:
'Apply all pending changes for the current session to disk. ' +
'Each queued create/edit/delete is executed in order.',
parameters: {
type: 'object',
properties: {},
required: [],
},
},
},
async execute(_input: ApplyPendingInputT, projectRoot: string, context: ToolContext): Promise<unknown> {
const results = await applyAll(context.sql, context.sessionId, projectRoot);
const succeeded = results.filter((r) => r.success).length;
const failed = results.filter((r) => !r.success).length;
return {
total: results.length,
succeeded,
failed,
results,
message:
results.length === 0
? 'No pending changes to apply.'
: `Applied ${succeeded}/${results.length} changes.${failed > 0 ? ` ${failed} failed.` : ''}`,
};
},
};

View File

@@ -0,0 +1,51 @@
import { z } from 'zod';
import type { ToolDef, ToolContext } from './types.js';
import { queueCreate } from '../pending_changes.js';
const CreateFileInput = z.object({
file_path: z.string().min(1),
content: z.string(),
});
type CreateFileInputT = z.infer<typeof CreateFileInput>;
export const createFileTool: ToolDef<CreateFileInputT> = {
name: 'create_file',
description:
'Queue creation of a new file with the given content. ' +
'The change is staged in pending_changes and must be applied explicitly.',
inputSchema: CreateFileInput,
jsonSchema: {
type: 'function',
function: {
name: 'create_file',
description:
'Queue creation of a new file with the given content. ' +
'The change is staged in pending_changes and must be applied explicitly.',
parameters: {
type: 'object',
properties: {
file_path: { type: 'string', description: 'Path for the new file (relative to project root or absolute)' },
content: { type: 'string', description: 'Full content of the file to create' },
},
required: ['file_path', 'content'],
},
},
},
async execute(input: CreateFileInputT, projectRoot: string, context: ToolContext): Promise<unknown> {
const change = await queueCreate(
context.sql,
context.sessionId,
context.taskId,
input.file_path,
input.content,
projectRoot,
);
return {
status: 'queued',
change_id: change.id,
file_path: change.file_path,
operation: 'create',
message: `File creation queued: ${change.file_path}. Use apply_pending to write changes to disk.`,
};
},
};

View File

@@ -0,0 +1,48 @@
import { z } from 'zod';
import type { ToolDef, ToolContext } from './types.js';
import { queueDelete } from '../pending_changes.js';
const DeleteFileInput = z.object({
file_path: z.string().min(1),
});
type DeleteFileInputT = z.infer<typeof DeleteFileInput>;
export const deleteFileTool: ToolDef<DeleteFileInputT> = {
name: 'delete_file',
description:
'Queue deletion of a file. ' +
'The change is staged in pending_changes and must be applied explicitly.',
inputSchema: DeleteFileInput,
jsonSchema: {
type: 'function',
function: {
name: 'delete_file',
description:
'Queue deletion of a file. ' +
'The change is staged in pending_changes and must be applied explicitly.',
parameters: {
type: 'object',
properties: {
file_path: { type: 'string', description: 'Path to the file to delete (relative to project root or absolute)' },
},
required: ['file_path'],
},
},
},
async execute(input: DeleteFileInputT, projectRoot: string, context: ToolContext): Promise<unknown> {
const change = await queueDelete(
context.sql,
context.sessionId,
context.taskId,
input.file_path,
projectRoot,
);
return {
status: 'queued',
change_id: change.id,
file_path: change.file_path,
operation: 'delete',
message: `File deletion queued: ${change.file_path}. Use apply_pending to write changes to disk.`,
};
},
};

View File

@@ -0,0 +1,54 @@
import { z } from 'zod';
import type { ToolDef, ToolContext } from './types.js';
import { queueEdit } from '../pending_changes.js';
const EditFileInput = z.object({
file_path: z.string().min(1),
old_string: z.string().min(1),
new_string: z.string(),
});
type EditFileInputT = z.infer<typeof EditFileInput>;
export const editFileTool: ToolDef<EditFileInputT> = {
name: 'edit_file',
description:
'Queue an edit to a file. The edit replaces old_string with new_string. ' +
'The change is staged in pending_changes and must be applied explicitly.',
inputSchema: EditFileInput,
jsonSchema: {
type: 'function',
function: {
name: 'edit_file',
description:
'Queue an edit to a file. The edit replaces old_string with new_string. ' +
'The change is staged in pending_changes and must be applied explicitly.',
parameters: {
type: 'object',
properties: {
file_path: { type: 'string', description: 'Path to the file to edit (relative to project root or absolute)' },
old_string: { type: 'string', description: 'The exact string to find and replace (must appear in the file)' },
new_string: { type: 'string', description: 'The replacement string' },
},
required: ['file_path', 'old_string', 'new_string'],
},
},
},
async execute(input: EditFileInputT, projectRoot: string, context: ToolContext): Promise<unknown> {
const change = await queueEdit(
context.sql,
context.sessionId,
context.taskId,
input.file_path,
input.old_string,
input.new_string,
projectRoot,
);
return {
status: 'queued',
change_id: change.id,
file_path: change.file_path,
operation: 'edit',
message: `Edit queued for ${change.file_path}. Use apply_pending to write changes to disk.`,
};
},
};

View File

@@ -0,0 +1,26 @@
import type { ToolDef } from './types.js';
import { editFileTool } from './edit_file.js';
import { createFileTool } from './create_file.js';
import { deleteFileTool } from './delete_file.js';
import { applyPendingTool } from './apply_pending.js';
import { rewindTool } from './rewind.js';
export type { ToolDef, ToolContext, ToolJsonSchema } from './types.js';
// All BooCoder write tools. The inference loop (Phase 2B) will combine these
// with BooChat's read-only tools to form the full tool set available to agents.
// eslint-disable-next-line @typescript-eslint/no-explicit-any
export const WRITE_TOOLS: readonly ToolDef<any>[] = [
applyPendingTool,
createFileTool,
deleteFileTool,
editFileTool,
rewindTool,
];
// eslint-disable-next-line @typescript-eslint/no-explicit-any
export const WRITE_TOOLS_BY_NAME: ReadonlyMap<string, ToolDef<any>> = new Map(
WRITE_TOOLS.map((t) => [t.name, t]),
);
export { editFileTool, createFileTool, deleteFileTool, applyPendingTool, rewindTool };

View File

@@ -0,0 +1,36 @@
import type { Sql } from '../../db.js';
/**
* Module-level inference context for write tools.
*
* Set via `setInferenceContext()` before each inference run starts.
* Write tools read it via `getInferenceContext()` during execute.
* Same pattern as BooChat's `loadConfig()` singleton — tools need
* ambient state that can't be threaded through the tool-phase execute
* signature (which is `execute(input, projectRoot, extraRoots?)`).
*/
export interface InferenceContext {
sql: Sql;
sessionId: string;
taskId: string | null;
}
let current: InferenceContext | null = null;
export function setInferenceContext(ctx: InferenceContext): void {
current = ctx;
}
export function clearInferenceContext(): void {
current = null;
}
export function getInferenceContext(): InferenceContext {
if (!current) {
throw new Error(
'Write tool called outside inference context — setInferenceContext() was not called before this run',
);
}
return current;
}

View File

@@ -0,0 +1,71 @@
import { z } from 'zod';
import type { ToolDef, ToolContext } from './types.js';
import { rewindOne } from '../pending_changes.js';
const RewindInput = z.object({
change_id: z.string().uuid().optional(),
all: z.boolean().optional(),
});
type RewindInputT = z.infer<typeof RewindInput>;
export const rewindTool: ToolDef<RewindInputT> = {
name: 'rewind',
description:
'Revert applied changes. Provide change_id to revert a specific change, ' +
'or set all=true to revert all applied changes for the session (in reverse order).',
inputSchema: RewindInput,
jsonSchema: {
type: 'function',
function: {
name: 'rewind',
description:
'Revert applied changes. Provide change_id to revert a specific change, ' +
'or set all=true to revert all applied changes for the session (in reverse order).',
parameters: {
type: 'object',
properties: {
change_id: { type: 'string', format: 'uuid', description: 'ID of a specific change to revert' },
all: { type: 'boolean', description: 'If true, revert all applied changes for this session' },
},
required: [],
},
},
},
async execute(input: RewindInputT, projectRoot: string, context: ToolContext): Promise<unknown> {
if (input.change_id) {
const result = await rewindOne(context.sql, input.change_id, projectRoot);
return {
results: [result],
message: result.success
? `Reverted change ${input.change_id} (${result.operation} on ${result.file_path}).`
: `Failed to revert: ${result.error}`,
};
}
if (input.all) {
// Rewind all applied changes for this session in reverse order
const applied = await context.sql<{ id: string }[]>`
SELECT id FROM pending_changes
WHERE session_id = ${context.sessionId} AND status = 'applied'
ORDER BY created_at DESC
`;
const results = [];
for (const row of applied) {
results.push(await rewindOne(context.sql, row.id, projectRoot));
}
const succeeded = results.filter((r) => r.success).length;
return {
total: results.length,
succeeded,
failed: results.length - succeeded,
results,
message:
results.length === 0
? 'No applied changes to revert.'
: `Reverted ${succeeded}/${results.length} changes.`,
};
}
return { error: 'Provide either change_id or all=true.' };
},
};

View File

@@ -0,0 +1,32 @@
import type { z } from 'zod';
import type { Sql } from '../../db.js';
export interface ToolJsonSchema {
type: 'function';
function: {
name: string;
description: string;
parameters: Record<string, unknown>;
};
}
/**
* Context passed to BooCoder tool execute functions.
*
* Unlike BooChat's tools (which only need projectRoot), BooCoder's write tools
* interact with the database (pending_changes table) and need session/task
* context for proper attribution.
*/
export interface ToolContext {
sql: Sql;
sessionId: string;
taskId: string | null;
}
export interface ToolDef<TInput> {
name: string;
description: string;
inputSchema: z.ZodType<TInput>;
jsonSchema: ToolJsonSchema;
execute(input: TInput, projectRoot: string, context: ToolContext): Promise<unknown>;
}

View File

@@ -0,0 +1,73 @@
import { resolve, sep } from 'node:path';
export class WriteGuardError extends Error {
constructor(message: string) {
super(message);
this.name = 'WriteGuardError';
}
}
// Deny list: files that should never be written regardless of path-guard.
// Subset of BooChat's secret_guard.ts — covers the most dangerous patterns.
// Full parity with BooChat's deny list is not needed for write-guard because
// the write tools are intentional (model chose to create/edit); we block only
// files that are unambiguously secrets.
const SECRET_PATTERNS: readonly string[] = [
'.env',
'.env.local',
'.env.production',
'.env.development',
'.env.staging',
'id_rsa',
'id_dsa',
'id_ecdsa',
'id_ed25519',
'*.pem',
'*.key',
'*.p12',
'*.pfx',
'*.crt',
'credentials.json',
'*.kdbx',
'.netrc',
];
export function isSecretPath(filePath: string): boolean {
const normalized = filePath.replace(/\\/g, '/');
const segments = normalized.split('/').filter((s) => s.length > 0);
if (segments.length === 0) return false;
const basename = segments[segments.length - 1]!;
return SECRET_PATTERNS.some((pattern) => {
if (pattern.startsWith('*')) {
return basename.endsWith(pattern.slice(1));
}
return basename === pattern;
});
}
/**
* Resolve and validate a write target path.
*
* Key difference from BooChat's pathGuard: no realpath() — the file may not
* exist yet (creates). Uses resolve() to normalize ../ segments and then
* checks the result stays within projectRoot.
*/
export function resolveWritePath(projectRoot: string, filePath: string): string {
if (!filePath || filePath.length === 0) {
throw new WriteGuardError('file path is required');
}
const candidate = filePath.startsWith('/') ? filePath : resolve(projectRoot, filePath);
const normalized = resolve(candidate); // normalizes ../ segments
if (!normalized.startsWith(projectRoot + sep) && normalized !== projectRoot) {
throw new WriteGuardError(`path escapes project root: ${filePath}`);
}
if (isSecretPath(normalized)) {
throw new WriteGuardError(`cannot write to secret file: ${filePath}`);
}
return normalized;
}

15
apps/coder/tsconfig.json Normal file
View File

@@ -0,0 +1,15 @@
{
"extends": "../../tsconfig.base.json",
"compilerOptions": {
"module": "NodeNext",
"moduleResolution": "NodeNext",
"outDir": "dist",
"rootDir": "src",
"lib": ["ES2022"],
"types": ["node"],
"declaration": false,
"sourceMap": true
},
"include": ["src/**/*"],
"exclude": ["src/**/__tests__/**", "**/*.test.ts"]
}

View File

@@ -0,0 +1,9 @@
import { defineConfig } from 'vitest/config';
export default defineConfig({
test: {
environment: 'node',
globals: false,
include: ['src/**/__tests__/**/*.test.ts'],
},
});

View File

@@ -4,6 +4,23 @@
"private": true,
"type": "module",
"main": "dist/index.js",
"exports": {
".": { "types": "./dist/index.d.ts", "default": "./dist/index.js" },
"./inference": { "types": "./dist/services/inference/index.d.ts", "default": "./dist/services/inference/index.js" },
"./tools": { "types": "./dist/services/tools.d.ts", "default": "./dist/services/tools.js" },
"./broker": { "types": "./dist/services/broker.d.ts", "default": "./dist/services/broker.js" },
"./compaction": { "types": "./dist/services/compaction.d.ts", "default": "./dist/services/compaction.js" },
"./model-context": { "types": "./dist/services/model-context.d.ts", "default": "./dist/services/model-context.js" },
"./system-prompt": { "types": "./dist/services/system-prompt.d.ts", "default": "./dist/services/system-prompt.js" },
"./agents": { "types": "./dist/services/agents.d.ts", "default": "./dist/services/agents.js" },
"./truncate": { "types": "./dist/services/truncate.d.ts", "default": "./dist/services/truncate.js" },
"./path-guard": { "types": "./dist/services/path_guard.d.ts", "default": "./dist/services/path_guard.js" },
"./file-ops": { "types": "./dist/services/file_ops.d.ts", "default": "./dist/services/file_ops.js" },
"./types": { "types": "./dist/types/api.d.ts", "default": "./dist/types/api.js" },
"./ws-frames": { "types": "./dist/types/ws-frames.d.ts", "default": "./dist/types/ws-frames.js" },
"./db": { "types": "./dist/db.d.ts", "default": "./dist/db.js" },
"./config": { "types": "./dist/config.d.ts", "default": "./dist/config.js" }
},
"scripts": {
"dev": "tsx watch src/index.ts",
"build": "tsc && node -e \"import('node:fs').then(fs=>fs.copyFileSync('src/schema.sql','dist/schema.sql'))\"",

View File

@@ -7,7 +7,7 @@
"rootDir": "src",
"lib": ["ES2022"],
"types": ["node"],
"declaration": false,
"declaration": true,
"sourceMap": true
},
"include": ["src/**/*"],

View File

@@ -9,7 +9,7 @@ services:
environment:
CODECONTEXT_URL: http://codecontext:8080
CONTAINER_GUIDANCE_FILE: /app/BOOCHAT.md
DATABASE_URL: postgres://boocode:${POSTGRES_PASSWORD}@boocode_db:5432/boocode
DATABASE_URL: postgres://boocode:${POSTGRES_PASSWORD}@boocode_db:5432/boochat
volumes:
- /opt:/opt
- /opt/projects:/opt/projects:rw
@@ -41,7 +41,7 @@ services:
environment:
NODE_ENV: production
PORT: 3000
DATABASE_URL: postgres://boocode:${POSTGRES_PASSWORD}@boocode_db:5432/boocode
DATABASE_URL: postgres://boocode:${POSTGRES_PASSWORD}@boocode_db:5432/boochat
volumes:
- /opt:/opt:rw
- /home/samkintop:/home/samkintop:rw
@@ -50,6 +50,28 @@ services:
networks:
- boocode_net
boocoder:
build:
context: .
dockerfile: apps/coder/Dockerfile
container_name: boocoder
restart: unless-stopped
ports:
- "100.114.205.53:9502:3000"
env_file: .env
environment:
CONTAINER_GUIDANCE_FILE: /app/BOOCODER.md
DATABASE_URL: postgres://boocode:${POSTGRES_PASSWORD}@boocode_db:5432/boochat
volumes:
- /opt:/opt:rw
- /opt/projects:/opt/projects:rw
- ./data:/data
- /opt/boocode/BOOCODER.md:/app/BOOCODER.md:ro
depends_on:
- boocode_db
networks:
- boocode_net
boocode_db:
image: postgres:16-alpine
container_name: boocode_db
@@ -57,7 +79,7 @@ services:
environment:
POSTGRES_USER: boocode
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
POSTGRES_DB: boocode
POSTGRES_DB: boochat
ports:
- "127.0.0.1:5500:5432"
volumes:

View File

@@ -0,0 +1,413 @@
# v2.0 BooCoder — Implementation Plan
Ordered execution plan across all 4 sub-versions. Each phase is dispatchable as a single batch. Phases 1-4 are sequential (each builds on the prior); phases within a sub-version can sometimes be parallelized.
---
## Phase 1 — Foundation (v2.0.0-alpha)
**Goal:** Standalone BooCoder container boots, connects to DB, serves a health endpoint. No inference yet.
**Estimated:** ~200 LoC
### Steps
1. **Clone lift sources** (prep, no code)
- `cd /opt/forks && git clone agent-hub, plandex, opencode, qodo-ai/agents`
- Read agent-hub schema, plandex pending-changes, opencode permission/evaluate.ts
- Read RA.Aid README for three-stage pattern
2. **Create `apps/coder/` skeleton**
- `apps/coder/package.json` (Fastify, postgres, zod — same deps as `apps/server`)
- `apps/coder/tsconfig.json` (extends base, NodeNext)
- `apps/coder/src/index.ts` (Fastify boot, health endpoint, DB connect)
- `apps/coder/src/config.ts` (Zod config schema — DATABASE_URL, PORT, HOST, LLAMA_SWAP_URL, CONTAINER_GUIDANCE_FILE)
- `apps/coder/src/db.ts` (postgres connection, schema apply — shared with `apps/server` or fresh)
3. **Create Dockerfile**
- `apps/coder/Dockerfile` — Node 20 bookworm-slim (matches booterm for glibc compat with node-pty later)
- Mount: `/opt:/opt:rw`
- COPY built server + BOOCODER.md
4. **docker-compose.yml** — add `boocoder` service
- Port `100.114.205.53:9502:3000`
- Environment: `DATABASE_URL`, `LLAMA_SWAP_URL`, `CONTAINER_GUIDANCE_FILE=/app/BOOCODER.md`
- Network: `boocode_net`
- Depends on: `boocode_db`
5. **DB rename**`boocode_db``boochat_db`
- `ALTER DATABASE boocode RENAME TO boochat;` (one-time, run manually)
- Update `DATABASE_URL` in all docker-compose services
- Update volume name mapping
- Verify all 3 services boot against renamed DB
6. **Schema migration** — new tables in `apps/coder/src/schema.sql`
- `pending_changes` table
- `tasks` table
- `available_agents` table
- `human_inbox` view
- Applied idempotently on boot (same pattern as BooChat's `applySchema()`)
7. **BOOCODER.md** — container guidance file
- Write tools enabled (unlike BOOCHAT.md which declares read-only)
- Pending-changes queue discipline
- Path-guard rules
### Verification
- `docker compose up --build -d` — boocoder container starts
- `curl http://100.114.205.53:9502/api/health` — 200 OK
- `psql` confirms new tables exist
- BooChat + BooTerm unaffected (still boot, still serve)
---
## Phase 2 — Write Tools + Pending Changes (v2.0.0-beta)
**Goal:** BooCoder can chat with the LLM, the LLM can call write tools, changes queue in `pending_changes`, user can apply/reject.
**Estimated:** ~400 LoC
### Steps
1. **Write-path guard** (`apps/coder/src/services/write_guard.ts`)
- `resolveWritePath(projectRoot, filePath): string``resolve()` + prefix check (no realpath — file may not exist for creates)
- Deny list: inherit from BooChat's `secret_guard.ts` (`.env`, `*.pem`, `id_rsa*`, etc.)
- Fuzz tests: `../` escape, symlink outside root, null bytes, non-existent parent dirs
2. **Pending-changes service** (`apps/coder/src/services/pending_changes.ts`)
- `queueEdit(session_id, task_id, file_path, old_string, new_string): PendingChange` — computes unified diff, validates write path, INSERTs
- `queueCreate(session_id, task_id, file_path, content): PendingChange`
- `queueDelete(session_id, task_id, file_path): PendingChange`
- `applyAll(session_id): ApplyResult[]` — re-validates each path, writes to disk, marks `status='applied'`
- `applyOne(change_id): ApplyResult`
- `rejectOne(change_id): void` — marks `status='rejected'`
- `rejectAll(session_id): void`
- `rewindOne(change_id): void` — inverse-diff, writes to disk, marks `status='reverted'`
- `listPending(session_id): PendingChange[]`
3. **Write tools** (`apps/coder/src/services/tools/`)
- `edit_file.ts` — input: `{file_path, old_string, new_string}`, calls `queueEdit`
- `create_file.ts` — input: `{file_path, content}`, calls `queueCreate`
- `delete_file.ts` — input: `{file_path}`, calls `queueDelete`
- `apply_pending.ts` — calls `applyAll` for current session
- `rewind.ts` — input: `{change_id}` or `{all: true}`, calls `rewindOne`/`rewindAll`
4. **Tool registry** — register write tools alongside ALL read tools from BooChat
- Import BooChat's read tools (view_file, grep, etc.) + codecontext tools
- Add the 5 write tools
- Alpha-sort the combined list
5. **Inference loop** — port from BooChat or share via workspace package
- Copy `apps/server/src/services/inference/` into `apps/coder/src/services/inference/` (or symlink via pnpm workspace)
- The outer loop (v1.14) runs unchanged — write tools are just ToolDefs with `execute()` functions
- Compaction, doom-loop, step cap all carry forward
6. **API routes**
- `POST /api/sessions/:id/messages` — same as BooChat (creates user + assistant rows, enqueues inference)
- `GET /api/sessions/:id/pending` — returns pending changes for the session
- `POST /api/sessions/:id/pending/apply` — applies all pending
- `POST /api/pending/:id/apply` — applies one
- `POST /api/pending/:id/reject` — rejects one
- `POST /api/pending/:id/rewind` — reverts one
- WebSocket streaming (same protocol as BooChat)
### Verification
- Send a chat asking BooCoder to edit a file
- LLM calls `edit_file` → change queued in `pending_changes`
- `GET /api/sessions/:id/pending` shows the queued change with diff
- `POST /api/pending/:id/apply` writes to disk
- `POST /api/pending/:id/rewind` reverts it
- Fuzz test: attempt traversal via `edit_file("../../etc/passwd", ...)` → rejected by write_guard
---
## Phase 3 — Frontend: Diff Pane + Chat (v2.0.0)
**Goal:** Browser UI at `coder.indifferentketchup.com` with chat pane + diff pane side by side.
**Estimated:** ~200 LoC
### Steps
1. **Create `apps/coder/web/`** — React + Vite SPA (same stack as BooChat's `apps/web/`)
- Copy BooChat's Vite config, Tailwind v4 setup, font pipeline
- Shared components: `MarkdownRenderer`, `CodeBlock`, `Button`, `Input`
- New app shell: sidebar (sessions) + workspace (panes)
2. **Chat pane** — reuse BooChat's ChatPane/MessageBubble pattern
- Same WS streaming, same `useSessionStream` hook, same message rendering
- ActionRow includes tool-call rendering for write tools
3. **Diff pane** — NEW (`apps/coder/web/src/components/DiffPane.tsx`)
- Fetches `GET /api/sessions/:id/pending`
- Lists pending changes: file path + operation badge (create/edit/delete)
- Per-change: syntax-highlighted unified diff view (use Shiki or a diff-specific highlighter)
- Buttons: Approve / Reject per change, Approve All / Reject All
- Real-time updates via WS frame (`pending_change_added`, `pending_change_applied`, etc.)
4. **Workspace splitter** — chat left, diff right (or configurable)
5. **Caddy route**`coder.indifferentketchup.com` → boocoder:9502
- Authelia gating (same as BooChat)
### Verification
- Open `coder.indifferentketchup.com` in browser
- Send a message asking for a code change
- See the change appear in the diff pane in real time
- Click Approve → file written, change marked applied
- Click Reject → change discarded
---
## Phase 4 — Dispatcher + Tasks (v2.0.0 final)
**Goal:** Task queue works. User can create tasks, dispatcher picks them up and runs them through Path A.
**Estimated:** ~150 LoC
### Steps
1. **Dispatcher** (`apps/coder/src/services/dispatcher.ts`)
- In-process `setInterval(5000)` polling `tasks` WHERE `state='pending'` ORDER BY `created_at`
- For each ready task: mark `state='running'`, run inference with the task's `input` as the user message
- On completion: mark `state='completed'`
- On error: mark `state='failed'`
- On abort: mark `state='cancelled'`
- Respects `app.addHook('onClose')` — stops polling, waits for in-flight task
2. **Task API routes**
- `POST /api/tasks` — create a task `{project_id, input, agent?, model?}`
- `GET /api/tasks` — list tasks (filterable by state, project)
- `GET /api/tasks/:id` — get task details + output_summary
- `POST /api/tasks/:id/cancel` — cancel a running task
3. **Task → session linkage**
- Each task creates its own session + chat for isolation
- Task's pending_changes reference the task_id
- When task completes, its pending_changes are visible in the UI for approval
4. **Agent probing** (`apps/coder/src/services/agent-probe.ts`)
- On startup: `which opencode`, `which goose`, `which claude`, `which pi`
- Parse version from `<agent> --version`
- Check ACP support: `opencode acp --help` exits 0 → supports_acp = true
- Populate `available_agents` table
### Verification
- `POST /api/tasks {input: "add a /api/version endpoint"}` → task created
- Dispatcher picks it up → inference runs → `edit_file` queued → task completes
- `GET /api/tasks/:id` shows `state='completed'` + output_summary
- Pending changes visible in diff pane for approval
---
## Phase 5 — ACP Dispatch (v2.0.1)
**Goal:** Tasks can be dispatched to external agents via ACP. opencode and goose run as subprocesses, their events flow back into BooCode.
**Estimated:** ~350 LoC
### Steps
1. **ACP client** (`apps/coder/src/services/acp-client.ts`)
- Install: `pnpm -C apps/coder add @zed-industries/agent-client-protocol`
- `spawnAcpAgent(agent: string, task: string, worktree: string, mcpServers: McpConfig[]): AcpSession`
- Uses SDK's `StdioTransport` — spawn `opencode acp` or `goose acp` as child
- Pass `context_servers` for MCP auto-forward
- Event listener: maps ACP events to BooCode's parts taxonomy
2. **ACP event mapping**
- `file_operation` → queue into `pending_changes` (same as Path A native writes)
- `tool_call` / `tool_result` → insert as `message_parts` in the task's session
- `terminal_output` → publish as WS frame for BooTerm routing
- `permission_request` → pause (same mechanism as `ask_user_input`)
- `session_end` → task state → `completed` or `failed`
3. **Worktree management** (`apps/coder/src/services/worktrees.ts`)
- `createWorktree(projectPath, taskId): string``git worktree add /tmp/booworktrees/<taskId> -b task-<taskId> HEAD`
- `diffWorktree(worktreePath, projectPath): UnifiedDiff[]``git diff HEAD...<worktree-branch>`
- `cleanupWorktree(worktreePath): void``git worktree remove`
- On ACP session end: diff the worktree, queue diffs into `pending_changes`, cleanup
4. **PTY fallback** (`apps/coder/src/services/pty-dispatch.ts`)
- For agents without ACP (claude, pi, smallcode)
- `spawnPtyAgent(agent: string, task: string, worktree: string): PtySession`
- Uses `node-pty` — spawn `claude` or `pi` with cwd = worktree
- Capture stdout/stderr into `message_parts` (kind='text', less structured than ACP)
- On exit: diff worktree → queue pending_changes → cleanup
5. **Dispatcher update** — transport selection
- Check `available_agents[agent].supports_acp` at dispatch time
- ACP-capable → `spawnAcpAgent`
- PTY fallback → `spawnPtyAgent`
- Native (no agent specified) → Path A inference loop (Phase 4)
6. **AGENTS.md extensions**
- Add `execution_strategy: plan | act | research` field
- Add `expert_model` field for cost-routing
- Add `output_schema` field (optional JSON Schema for structured final output)
### Verification
- Create task with `agent: 'opencode'` → ACP subprocess spawns
- opencode edits files in worktree → events stream into UI
- On completion: worktree diff queued in `pending_changes`
- Approve → changes applied to main project
- Fallback: create task with `agent: 'claude'` → PTY captures output → worktree diff queued
---
## Phase 6 — MCP Server (v2.0.2)
**Goal:** BooCoder exposes its own primitives as MCP tools. External opencode sessions in Termius can drive the task queue.
**Estimated:** ~250 LoC
### Steps
1. **MCP server** (`apps/coder/src/services/mcp-server.ts`)
- Use `@modelcontextprotocol/sdk` server-side (`Server` class)
- Stdio transport (read from stdin, write to stdout)
- Entry point: `boocoder --mcp` CLI flag starts the MCP server instead of the HTTP server
2. **Tool handlers** (6 tools)
- `boocoder.create_task` → INSERT into tasks table, return task_id
- `boocoder.list_pending_changes` → SELECT from pending_changes WHERE session matches
- `boocoder.apply` → call `applyOne(change_id)`
- `boocoder.reject` → call `rejectOne(change_id)`
- `boocoder.dispatch_external_agent` → create task with agent specified, return task_id
- `boocoder.list_worktrees` → list active worktrees from tasks WHERE worktree_path IS NOT NULL AND state='running'
3. **10-question eval** (per `anthropics/skills/mcp-builder` framework)
- Write 10 independent, read-only, verifiable questions about the BooCoder state
- Run eval: `echo '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"boocoder.list_pending_changes","arguments":{}},"id":1}' | boocoder --mcp`
- All 10 must return correct answers
4. **opencode integration test**
- Add BooCoder as an MCP server in `~/.opencode/config.json`:
```json
{"mcpServers": {"boocoder": {"type": "stdio", "command": "boocoder", "args": ["--mcp"]}}}
```
- From opencode: call `boocoder.create_task` → verify task appears in BooCoder UI
### Verification
- `echo '...' | boocoder --mcp` returns valid MCP responses
- 10-question eval passes
- opencode can drive BooCoder's task queue via MCP
---
## Phase 7 — CLI + Polish (v2.0.3)
**Goal:** `boocode` CLI client, human inbox UI, cost tracking, observation hooks.
**Estimated:** ~400 LoC
### Steps
1. **CLI client** (`apps/coder/src/cli.ts`)
- Thin HTTP/WS client against BooCoder API
- `boocode run "task description"` → POST /api/tasks → stream output via WS
- `boocode ls` → GET /api/tasks → formatted table
- `boocode attach <id>` → WS subscribe to task's session → stream live
- `boocode send <id> "message"` → POST message to task's session chat
- Build as a standalone binary via `pkg` or `esbuild --bundle`
2. **Human inbox UI** (frontend)
- New route: `/inbox` → shows tasks WHERE `state IN ('blocked', 'failed')`
- Per-task: view output, retry (reset state to pending), cancel, reassign agent
- Badge on sidebar showing count of inbox items
3. **Cost tracking**
- `tasks.cost_tokens` populated from inference `usage` callback (same as BooChat's `tokens_used`)
- Summary API: `GET /api/stats/costs?group_by=project|agent|day` → aggregated token spend
- Simple UI: cost badge on each task, totals in settings
4. **Observation hooks** (budi taxonomy)
- Emit 5 event types on the BooCoder WS protocol for dispatched agents:
- `session_start` — agent spawned
- `user_prompt_submit` — task spec delivered
- `post_tool_use` — each tool call completed
- `subagent_start` — nested dispatch (Boomerang)
- `stop` — agent finished
- Consumed by frontend for real-time status indicators
5. **Boomerang `new_task` tool** (subagent isolation)
- When an agent's toolset includes `new_task`:
- Creates a child task (fresh session, fresh context)
- Child runs to completion
- Parent gets only `attempt_completion` summary
- Orchestrator agent profile: tools = `[new_task, list_tasks, check_task_status]` ONLY
### Verification
- `boocode run "add health endpoint"` from terminal → task runs → output streams → diff queued
- `boocode ls` shows task list with states + cost
- Inbox shows failed tasks, retry works
- Boomerang: orchestrator creates subtask → subtask runs isolated → parent gets summary only
---
## Phase 8 — Hardening + Ship (v2.0.x)
**Goal:** Security hardening, integration tests, documentation, production deploy.
**Estimated:** ~100 LoC (mostly tests + docs)
### Steps
1. **Path-guard fuzz suite** — property tests for every traversal pattern:
- `../` sequences (all depths)
- Symlink outside project root
- Null bytes in path
- Unicode normalization attacks
- Race conditions (TOCTOU between validate + write)
- MCP-served filesystem writes routed through pending_changes
2. **Integration tests**
- End-to-end: create task → inference → edit_file → apply → file written → verify content
- ACP dispatch: mock opencode → events flow → pending_changes queued
- MCP server: 10-question eval automated in CI
3. **Documentation**
- `BOOCODER.md` finalized (container guidance)
- `CLAUDE.md` updated with BooCoder architecture section
- `boocode_roadmap.md` v2.0 retrospective
- `CHANGELOG.md` entries for each sub-version
4. **Production deploy**
- Caddy config: `coder.indifferentketchup.com`
- Authelia: same SSO group as BooChat
- Smoke: full workflow (chat → edit → approve → verify)
5. **Tag** — `v2.0.0` (or `v2.0.0-rc1` if Sam wants a bake period)
---
## Execution order summary
```
Phase 1 (foundation) → v2.0.0-alpha ~200 LoC container boots
Phase 2 (write tools) → v2.0.0-beta ~400 LoC inference + pending_changes
Phase 3 (frontend) → v2.0.0 ~200 LoC chat + diff panes
Phase 4 (dispatcher) → v2.0.0-final ~150 LoC task queue + native dispatch
Phase 5 (ACP dispatch) → v2.0.1 ~350 LoC external agents + worktrees
Phase 6 (MCP server) → v2.0.2 ~250 LoC boocoder.* tools + eval
Phase 7 (CLI + polish) → v2.0.3 ~400 LoC CLI + inbox + hooks + Boomerang
Phase 8 (hardening) → v2.0.x ~100 LoC fuzz + integration tests + docs
--------
~2050 LoC total
```
Each phase is independently dispatchable. Phases 1-4 are sequential (each needs the prior). Phases 5-7 are parallelizable after Phase 4 ships (they're independent protocol surfaces). Phase 8 gates the production tag.
---
## Risk register
| Risk | Mitigation |
|---|---|
| Path-guard bypass → arbitrary writes | Pending-changes double-validates (at queue time + apply time). Fuzz suite in Phase 8. OpenHands sandbox (v2.1) as fallback. |
| ACP spec instability (remote transport WIP) | Use stdio only. No remote ACP in v2.0. |
| node-pty native compilation breaks in Docker | bookworm-slim + glibc matches booterm's working config. Pin node-pty version. |
| Worktree cleanup failure → disk bloat | 30-min idle timeout sweeper. `git worktree prune` on startup. |
| DB rename breaks existing sessions | One-time migration with explicit backup. BooChat/BooTerm URLs unchanged. |
| MCP server eval failure | Ship stdio MCP server only after 10/10 eval passes. |
| Boomerang context leak (child leaks state to parent) | Architectural enforcement: child's session_id ≠ parent's. Summary field is the ONLY bridge. |

View File

@@ -262,13 +262,85 @@ All dependencies shipped. v2.0 is unblocked.
- No OAuth in v2.0. MCP server is stdio-only until secret storage lands.
- DB rename `boocode_db``boochat_db` lands with v2.0.0 (one-time migration).
## AGENTS.md extensions (v2.0.0)
Port from `qodo-ai/agents` (MIT) `agent.toml` schema and `ai-christianson/RA.Aid` (Apache-2.0) three-stage pattern:
| Field | Type | Purpose | Source |
|---|---|---|---|
| `steps` | number | Per-agent step cap (already shipped v1.14.0) | opencode |
| `output_schema` | JSON Schema | Structured output constraint for the agent's final response | qodo-ai/agents |
| `exit_expression` | string | Regex/predicate — when the agent considers itself done | qodo-ai/agents |
| `execution_strategy` | `plan` \| `act` \| `research` | Which phase of the RA.Aid three-stage pattern this agent operates in | qodo-ai/agents + RA.Aid |
| `model` | string | Per-agent model override (already shipped v1.8) | — |
| `expert_model` | string | Escalation model for hard reasoning (RA.Aid "expert tool" escape hatch) | RA.Aid |
The three-stage pattern maps to BooCoder's use case:
- **Research agent** (cheap model) → understand the task, find relevant files
- **Planning agent** (standard model) → decide which files to edit, what the changes look like
- **Implementation agent** (full model) → produce the actual diffs
`expert_model` is the escape hatch: a routine model handles most subtasks, but can call the expert model (e.g. qwopus27b) when stuck. Matches Sam's existing cost-routing discipline.
## Subagent isolation (Boomerang pattern, v2.0.1)
From Roo Code Boomerang Tasks (Apache-2.0 pattern):
When an orchestrator agent calls a `new_task` tool, BooCoder:
1. Creates a fresh `tasks` row with `parent_task_id` pointing to the orchestrator's task
2. Spawns a fresh inference session (Path A) or dispatch (Path B) with ONLY the task spec as context — no inherited conversation
3. Child runs to `attempt_completion`, writes a summary to `tasks.output_summary`
4. Parent resumes reading ONLY the summary (not the child's full conversation)
**Three principles:**
- Orchestrator capability restriction: the orchestrator agent's tool list includes ONLY `new_task`, `list_tasks`, `check_task_status` — it cannot read files or call MCP tools directly
- Down-pass: parent sends task spec via `new_task(input)`, nothing else inherited
- Up-pass: child sends result via `attempt_completion(summary)`, nothing else surfaces to parent
This is the **single most important context-management primitive** — it prevents long-running orchestrators from poisoning their context with implementation detail.
## Observation hooks (v2.0.3)
From `siropkin/budi` (MIT) Claude Code 5-hook taxonomy:
Register BooCoder as a hook receiver for dispatched agents. Five events:
- `SessionStart` — agent spawned
- `UserPromptSubmit` — task spec delivered
- `PostToolUse` — each tool call completed
- `SubagentStart` — nested dispatch
- `Stop` — agent finished
These map directly to BooCode's existing WS frame protocol. The hook receiver is the BooCoder Fastify server; events flow into the `message_parts` taxonomy as `step_start`-style instrumentation parts.
## Follow-up batches (v2.0+ optional, ordered by value)
| Batch | Source | What | When |
|---|---|---|---|
| **PR-resolver tool** | `qodo-ai/qodo-skills` (MIT) | Fetch GitHub issues → batch/interactive fix → inline PR reply. BooCoder tool that replaces Sam's manual PR workflow. | v2.0.3+ |
| **HMAC audit log** | `sipyourdrink-ltd/bernstein` (verify license) | One new `audit_log` table with `prev_hmac` field. Tamper-evident history of every edit BooCoder makes. Small lift (~50 LoC). | v2.0.1+ |
| **Blind-validation gate** | `covibes/zeroshot` (MIT) | Verify gate runs in a separate agent context that sees ONLY the diff + acceptance criteria, not the producing conversation. Complements Boomerang (isolation) + bernstein (lineage). | v2.0.2+ |
| **Majority-vote ensembler** | `augmentcode/augment-swebench-agent` (MIT) | K candidate diffs from K agents → ranker model picks the best one. Optional layer above `pending_changes`. | v2.1+ |
| **Drift detection** | `memovai/memov` (MIT) | `validate_commit` concept — detects when actual changes diverge from what was requested. Shadow timeline comparison. | v2.0.3+ |
| **Anti-slop for frontend** | `Leonxlnx/taste-skill` (MIT) | 100+ specific font/color/layout ban list + 3-dial parameterization. Vendor into skills/ when BooCoder generates frontend code. | v2.0+ |
| **Verify-before-commit gate** | `DeepSourceCorp/globstar` (MIT) | Rule-based AST linter as a pre-apply quality gate. YAML checkers in `.globstar/`. | v2.1+ (parked) |
| **Docker sandbox** | `OpenHands/OpenHands` (MIT) | Per-session Docker container for write tools. Closes the `/opt:rw` mount risk if path-guard ever proves insufficient. | v2.1 (optional) |
| **Multi-provider LLM** | `earendil-works/pi` (MIT) | Provider abstraction if a need for Anthropic/OpenAI/Mistral direct surfaces beyond llama-swap. | v2.x (optional) |
## Repos to clone before starting
```bash
cd /opt/forks
git clone https://github.com/Dominic789654/agent-hub.git # Apache-2.0, task DAG reference
git clone https://github.com/Dominic789654/agent-hub.git # Apache-2.0, task DAG + dispatcher
git clone https://github.com/plandex-ai/plandex.git # MIT, pending-changes UX
git clone https://github.com/anomalyco/opencode.git # MIT, permission evaluate.ts + MCP client reference
git clone https://github.com/anomalyco/opencode.git # MIT, permission evaluate.ts reference
git clone https://github.com/qodo-ai/agents.git # MIT, agent.toml schema (output_schema, exit_expression, execution_strategy)
```
ACP SDK is an npm package (`@zed-industries/agent-client-protocol`), installed at implementation time. Paseo is design-only (AGPL, no code lift).
Also read (no clone needed):
- `ai-christianson/RA.Aid` README — three-stage pattern + expert-tool escape hatch
- `getpaseo/paseo` README + `skills/` directory — daemon architecture + CLI verbs (AGPL, design-only)
- `agentclientprotocol.com` spec — ACP stdio protocol
- `goose-docs.ai/docs/guides/acp-clients/``context_servers` auto-forward pattern
- `siropkin/budi` README — 5-hook Claude Code taxonomy for observation
ACP SDK and MCP SDK are npm packages installed at implementation time.

34
pnpm-lock.yaml generated
View File

@@ -46,6 +46,40 @@ importers:
specifier: ^5.5.0
version: 5.9.3
apps/coder:
dependencies:
'@boocode/server':
specifier: workspace:*
version: link:../server
'@fastify/static':
specifier: ^7.0.4
version: 7.0.4
'@fastify/websocket':
specifier: ^10.0.1
version: 10.0.1
fastify:
specifier: ^4.28.1
version: 4.29.1
postgres:
specifier: ^3.4.4
version: 3.4.9
zod:
specifier: ^3.23.8
version: 3.25.76
devDependencies:
'@types/node':
specifier: ^20.14.10
version: 20.19.41
tsx:
specifier: ^4.16.2
version: 4.22.0
typescript:
specifier: ^5.5.0
version: 5.9.3
vitest:
specifier: ^3.0.0
version: 3.2.4(@types/debug@4.1.13)(@types/node@20.19.41)(lightningcss@1.32.0)(msw@2.14.6(@types/node@20.19.41)(typescript@5.9.3))
apps/server:
dependencies:
'@ai-sdk/openai-compatible':