Compare commits
5 Commits
v1.16.0-co
...
v2.0.0-bet
| Author | SHA1 | Date | |
|---|---|---|---|
| ce31577d1e | |||
| 006226cce5 | |||
| 62d818af23 | |||
| 531d39ace9 | |||
| f2974d6887 |
41
BOOCODER.md
41
BOOCODER.md
@@ -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
32
apps/coder/Dockerfile
Normal 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
28
apps/coder/package.json
Normal 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
42
apps/coder/src/config.ts
Normal 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
45
apps/coder/src/db.ts
Normal 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
131
apps/coder/src/index.ts
Normal 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);
|
||||
});
|
||||
126
apps/coder/src/routes/messages.ts
Normal file
126
apps/coder/src/routes/messages.ts
Normal 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 };
|
||||
},
|
||||
);
|
||||
}
|
||||
121
apps/coder/src/routes/pending.ts
Normal file
121
apps/coder/src/routes/pending.ts
Normal 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;
|
||||
},
|
||||
);
|
||||
}
|
||||
51
apps/coder/src/routes/ws.ts
Normal file
51
apps/coder/src/routes/ws.ts
Normal 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
48
apps/coder/src/schema.sql
Normal 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');
|
||||
115
apps/coder/src/services/__tests__/write_guard.test.ts
Normal file
115
apps/coder/src/services/__tests__/write_guard.test.ts
Normal 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);
|
||||
});
|
||||
});
|
||||
224
apps/coder/src/services/pending_changes.ts
Normal file
224
apps/coder/src/services/pending_changes.ts
Normal 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
|
||||
`;
|
||||
}
|
||||
30
apps/coder/src/services/tools/adapter.ts
Normal file
30
apps/coder/src/services/tools/adapter.ts
Normal 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);
|
||||
},
|
||||
};
|
||||
}
|
||||
44
apps/coder/src/services/tools/apply_pending.ts
Normal file
44
apps/coder/src/services/tools/apply_pending.ts
Normal 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.` : ''}`,
|
||||
};
|
||||
},
|
||||
};
|
||||
51
apps/coder/src/services/tools/create_file.ts
Normal file
51
apps/coder/src/services/tools/create_file.ts
Normal 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.`,
|
||||
};
|
||||
},
|
||||
};
|
||||
48
apps/coder/src/services/tools/delete_file.ts
Normal file
48
apps/coder/src/services/tools/delete_file.ts
Normal 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.`,
|
||||
};
|
||||
},
|
||||
};
|
||||
54
apps/coder/src/services/tools/edit_file.ts
Normal file
54
apps/coder/src/services/tools/edit_file.ts
Normal 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.`,
|
||||
};
|
||||
},
|
||||
};
|
||||
26
apps/coder/src/services/tools/index.ts
Normal file
26
apps/coder/src/services/tools/index.ts
Normal 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 };
|
||||
36
apps/coder/src/services/tools/inference_context.ts
Normal file
36
apps/coder/src/services/tools/inference_context.ts
Normal 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;
|
||||
}
|
||||
71
apps/coder/src/services/tools/rewind.ts
Normal file
71
apps/coder/src/services/tools/rewind.ts
Normal 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.' };
|
||||
},
|
||||
};
|
||||
32
apps/coder/src/services/tools/types.ts
Normal file
32
apps/coder/src/services/tools/types.ts
Normal 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>;
|
||||
}
|
||||
73
apps/coder/src/services/write_guard.ts
Normal file
73
apps/coder/src/services/write_guard.ts
Normal 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
15
apps/coder/tsconfig.json
Normal 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"]
|
||||
}
|
||||
9
apps/coder/vitest.config.ts
Normal file
9
apps/coder/vitest.config.ts
Normal file
@@ -0,0 +1,9 @@
|
||||
import { defineConfig } from 'vitest/config';
|
||||
|
||||
export default defineConfig({
|
||||
test: {
|
||||
environment: 'node',
|
||||
globals: false,
|
||||
include: ['src/**/__tests__/**/*.test.ts'],
|
||||
},
|
||||
});
|
||||
@@ -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'))\"",
|
||||
|
||||
@@ -7,7 +7,7 @@
|
||||
"rootDir": "src",
|
||||
"lib": ["ES2022"],
|
||||
"types": ["node"],
|
||||
"declaration": false,
|
||||
"declaration": true,
|
||||
"sourceMap": true
|
||||
},
|
||||
"include": ["src/**/*"],
|
||||
|
||||
@@ -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:
|
||||
|
||||
413
openspec/changes/v2.0-boocoder/implementation-plan.md
Normal file
413
openspec/changes/v2.0-boocoder/implementation-plan.md
Normal 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. |
|
||||
346
openspec/changes/v2.0-boocoder/proposal.md
Normal file
346
openspec/changes/v2.0-boocoder/proposal.md
Normal file
@@ -0,0 +1,346 @@
|
||||
# v2.0 — BooCoder
|
||||
|
||||
Major version bump. New app `apps/coder/` inside the existing monorepo. Lands together with the `boocode_db` → `boochat_db` DB rename and the per-app subdomain split (`code.indifferentketchup.com` → BooChat, `coder.indifferentketchup.com` → BooCoder).
|
||||
|
||||
## What BooCoder is
|
||||
|
||||
A write-capable coding agent surface. Two execution paths, same UI:
|
||||
|
||||
- **Path A (native):** BooCode's own inference loop with write tools (`edit_file`, `create_file`, `delete_file`). Edits queue in `pending_changes` — nothing touches disk until user approves via `/apply`.
|
||||
- **Path B (dispatch):** Shells out to external CLI agents (`opencode`, `goose`, `claude`, `pi`) via ACP (preferred) or raw PTY (fallback). One git worktree per dispatch. Captures events into the same parts taxonomy.
|
||||
|
||||
Both paths feed the same task DAG, same project registry, same pending-changes queue, same UI.
|
||||
|
||||
## Why now
|
||||
|
||||
v1.x proved the read-only loop works end-to-end: inference, tool dispatch, streaming, compaction, MCP client, outer loop, step caps, artifact rendering. The infrastructure is stable. The jump from "read-only chat" to "write-capable agent orchestrator" is the remaining gap between BooCode and having a real development environment.
|
||||
|
||||
## Architecture
|
||||
|
||||
### Three protocol roles (locked 2026-05-22)
|
||||
|
||||
1. **MCP client (write-capable allowed).** Inherits v1.15 client. Write-capable MCP servers (e.g. `@modelcontextprotocol/server-filesystem`) route writes through `pending_changes`. Per-task allow/deny means dispatched tasks can have a different MCP roster.
|
||||
2. **MCP server (BooCoder's own primitives).** Exposes `boocoder.create_task`, `boocoder.list_pending_changes`, `boocoder.apply`, `boocoder.reject`, `boocoder.dispatch_external_agent`, `boocoder.list_worktrees` as MCP tools. Stdio transport for local consumers (Sam's `opencode` in Termius); HTTP deferred until OAuth + secret storage.
|
||||
3. **ACP client (host).** Spawns `opencode acp` and `goose acp` as JSON-RPC stdio subprocesses. Maps ACP events (file operations, tool calls, terminal output) to BooCode's parts taxonomy. MCP servers configured in BooCoder are auto-forwarded to the dispatched agent (per goose docs — `context_servers` is the field).
|
||||
|
||||
### Container layout (post-v2.0)
|
||||
|
||||
| Container | Port | Mount | Purpose |
|
||||
|---|---|---|---|
|
||||
| `boochat` (was `boocode`) | `100.114.205.53:9500` | `/opt:/opt:ro` | Read-only chat + MCP client |
|
||||
| `booterm` | `100.114.205.53:9501` | `/opt:/opt:rw` | PTY/tmux terminal |
|
||||
| `boocoder` | `100.114.205.53:9502` | `/opt:/opt:rw` (policy-gated) | Write tools + ACP host + MCP client + MCP server |
|
||||
| `boochat_db` (was `boocode_db`) | `127.0.0.1:5500` | `boocode_pgdata` | Shared Postgres 16 |
|
||||
| `codecontext` | internal `:8080` | `/opt:/opt:ro` | Analysis sidecar (shared) |
|
||||
|
||||
### Caddy routing
|
||||
|
||||
```
|
||||
code.indifferentketchup.com → boochat:9500
|
||||
coder.indifferentketchup.com → boocoder:9502
|
||||
term.indifferentketchup.com → booterm:9501 (or routed under code.*/term/)
|
||||
```
|
||||
|
||||
## Schema (new tables)
|
||||
|
||||
```sql
|
||||
-- Pending changes: queued writes before /apply
|
||||
CREATE TABLE IF NOT EXISTS pending_changes (
|
||||
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
|
||||
session_id UUID NOT NULL REFERENCES sessions(id),
|
||||
task_id UUID REFERENCES tasks(id),
|
||||
file_path TEXT NOT NULL,
|
||||
operation TEXT NOT NULL CHECK (operation IN ('create', 'edit', 'delete')),
|
||||
diff TEXT NOT NULL,
|
||||
status TEXT NOT NULL DEFAULT 'pending' CHECK (status IN ('pending', 'applied', 'rejected', 'reverted')),
|
||||
created_at TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp()
|
||||
);
|
||||
|
||||
-- Tasks: the dispatch DAG
|
||||
CREATE TABLE IF NOT EXISTS tasks (
|
||||
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
|
||||
project_id UUID NOT NULL REFERENCES projects(id),
|
||||
parent_task_id UUID REFERENCES tasks(id),
|
||||
state TEXT NOT NULL DEFAULT 'pending'
|
||||
CHECK (state IN ('pending', 'running', 'completed', 'failed', 'blocked', 'cancelled')),
|
||||
input TEXT NOT NULL,
|
||||
output_summary TEXT,
|
||||
agent TEXT,
|
||||
model TEXT,
|
||||
execution_path TEXT CHECK (execution_path IN ('native', 'acp', 'pty')),
|
||||
worktree_path TEXT,
|
||||
cost_tokens INTEGER,
|
||||
started_at TIMESTAMPTZ,
|
||||
ended_at TIMESTAMPTZ,
|
||||
created_at TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp()
|
||||
);
|
||||
|
||||
-- Available agents: probed at startup
|
||||
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 VIEW human_inbox AS
|
||||
SELECT * FROM tasks WHERE state IN ('blocked', 'failed');
|
||||
```
|
||||
|
||||
`task_templates` and `pipelines` deferred to v2.1 — overhead for single-user. The core is `tasks` + `pending_changes` + `available_agents`.
|
||||
|
||||
## Path A — Native write tools
|
||||
|
||||
### Tools
|
||||
|
||||
| Tool | Description |
|
||||
|---|---|
|
||||
| `edit_file` | Apply a diff to an existing file. Input: `{file_path, old_string, new_string}`. Queues in `pending_changes` with `operation='edit'`. |
|
||||
| `create_file` | Create a new file. Input: `{file_path, content}`. Queues as `operation='create'`. |
|
||||
| `delete_file` | Delete a file. Input: `{file_path}`. Queues as `operation='delete'`. |
|
||||
| `apply_pending` | Flush all pending changes for the current session to disk. Path-guarded. |
|
||||
| `rewind` | Revert a specific applied change or all changes since a checkpoint. |
|
||||
|
||||
### Path guard for writes
|
||||
|
||||
Same `pathGuard()` function from BooChat, but with a write-path variant:
|
||||
- `resolveWritePath(projectRoot, requested)` — uses `resolve()` (not `realpath()`, since the file may not exist yet for creates), then verifies the result starts with `projectRoot + sep`.
|
||||
- Deny list: everything in `secret_guard.ts` (`.env`, `*.pem`, etc.) — can't write to those either.
|
||||
- Defense-in-depth: the `pending_changes` queue means even a path-guard bypass only queues; it doesn't hit disk until `/apply` (which re-validates).
|
||||
|
||||
### Diff format
|
||||
|
||||
Standard unified diff (what `git diff` produces). The `edit_file` tool takes `old_string` / `new_string` (same as Claude Code's edit tool — the model is trained on this shape). Server computes the unified diff for storage in `pending_changes.diff`.
|
||||
|
||||
### UI: per-pane diff viewer
|
||||
|
||||
Frontend pane type `pending_changes` in BooCoder's workspace. Shows:
|
||||
- List of queued changes with file path + operation
|
||||
- Per-change diff view (syntax-highlighted, side-by-side or unified)
|
||||
- Approve / Reject per change, or Approve All / Reject All
|
||||
|
||||
## Path B — External agent dispatch
|
||||
|
||||
### dispatch_external_agent tool
|
||||
|
||||
```typescript
|
||||
{
|
||||
agent: 'opencode' | 'claude' | 'goose' | 'pi',
|
||||
model: string, // e.g. 'claude-opus-4-7'
|
||||
task: string, // natural-language task description
|
||||
worktree?: string, // optional — auto-creates if not specified
|
||||
}
|
||||
```
|
||||
|
||||
### Transport selection
|
||||
|
||||
Dispatcher checks `available_agents.supports_acp` at runtime:
|
||||
- **ACP** (preferred): `opencode acp`, `goose acp` — JSON-RPC stdio. Native session lifecycle, file-operation events, terminal events, permission prompts.
|
||||
- **PTY** (fallback): `claude`, `pi`, `smallcode` — raw terminal capture via `node-pty`. Captures stdout/stderr/exit-code into PostgreSQL. Less structured than ACP.
|
||||
|
||||
### Worktree management
|
||||
|
||||
Each dispatched task gets its own git worktree:
|
||||
```bash
|
||||
git worktree add /tmp/booworktrees/<task-id> -b task-<task-id> HEAD
|
||||
```
|
||||
|
||||
On completion: diff the worktree against HEAD, queue the diff into `pending_changes` for the same task, clean up the worktree. User approves/rejects the diff the same way as Path A.
|
||||
|
||||
### ACP event mapping
|
||||
|
||||
ACP events → BooCode parts taxonomy:
|
||||
- `file_operation` → `tool_call` part (name: `acp_edit_file`) + `tool_result` part
|
||||
- `tool_call` → `tool_call` part (preserves name)
|
||||
- `terminal_output` → routes into BooTerm pane
|
||||
- `permission_request` → pause inference (same mechanism as `ask_user_input`)
|
||||
- `session_end` → task state → `completed` or `failed`
|
||||
|
||||
### MCP server auto-forward
|
||||
|
||||
Per goose docs, `context_servers` field in the ACP session config auto-forwards BooCoder's configured MCP servers to the dispatched agent. One MCP config drives every agent.
|
||||
|
||||
## Dispatcher worker
|
||||
|
||||
Background process (or in-process `setInterval` for v2.0 simplicity) that:
|
||||
1. Queries `tasks` WHERE `state = 'pending'` ORDER BY `created_at`
|
||||
2. For each ready task (no unmet dependencies):
|
||||
- Mark `state = 'running'`
|
||||
- Resolve execution path (Path A if no agent specified, Path B if agent specified)
|
||||
- Path A: run the inference loop with write tools enabled
|
||||
- Path B: spawn ACP/PTY subprocess, stream events into parts
|
||||
- On completion: mark `state = 'completed'` or `'failed'`
|
||||
- Queue output diff into `pending_changes`
|
||||
3. On failure: mark `state = 'failed'`, surface in `human_inbox` view
|
||||
|
||||
## BooCoder MCP server
|
||||
|
||||
Exposes BooCoder's primitives as MCP tools so external agents (Sam's opencode in Termius) can drive the task queue:
|
||||
|
||||
| MCP Tool | Description |
|
||||
|---|---|
|
||||
| `boocoder.create_task` | Create a new task in the queue |
|
||||
| `boocoder.list_pending_changes` | List queued changes awaiting approval |
|
||||
| `boocoder.apply` | Apply a specific pending change |
|
||||
| `boocoder.reject` | Reject a pending change |
|
||||
| `boocoder.dispatch_external_agent` | Dispatch a task to an external agent |
|
||||
| `boocoder.list_worktrees` | List active git worktrees |
|
||||
|
||||
Stdio transport for local consumers. HTTP transport deferred until OAuth + secret storage.
|
||||
|
||||
**Eval requirement:** run through `anthropics/skills mcp-builder` 10-question evaluation framework before shipping.
|
||||
|
||||
## Code lifts
|
||||
|
||||
### Primary architectural template
|
||||
|
||||
**`Dominic789654/agent-hub`** (Apache-2.0) — task DAG schema, dispatcher worker, project registry, human inbox. Three-process model (board server + dispatcher + assistant terminal). BooCode adapts this into a single-process Fastify app (v2.0.0) with the dispatcher as an in-process worker.
|
||||
|
||||
### Pending-changes UX
|
||||
|
||||
**`plandex-ai/plandex`** (MIT) — diff/apply/rewind vocabulary. The `pending_changes` queue concept, per-file diff view, approve/reject UI pattern. No code lifted — schema and UX design only.
|
||||
|
||||
### ACP client
|
||||
|
||||
**`agentclientprotocol.com` spec + `@zed-industries/agent-client-protocol` SDK** (Apache-2.0) — local-subprocess ACP via stdio JSON-RPC. The SDK handles framing; BooCode maps events to its parts taxonomy.
|
||||
|
||||
**`goose` docs** (`goose-docs.ai/docs/guides/acp-clients/`) — `context_servers` auto-forward pattern. Critical: one MCP config drives every dispatched agent.
|
||||
|
||||
### MCP server
|
||||
|
||||
**`anthropics/skills/mcp-builder`** (MIT) — 4-phase build workflow + 10-question evaluation framework for validating the MCP server before shipping.
|
||||
|
||||
### Dispatcher pattern
|
||||
|
||||
**Paseo (`getpaseo/paseo`)** — AGPL-3.0, **design only, no code lift**. Daemon+clients architecture, `--worktree` flag, CLI verb shape (`run/ls/attach/send`). BooCode reproduces the architecture using only license-clean patterns.
|
||||
|
||||
**Roo Code Boomerang Tasks** — orchestrator with intentional capability restriction. Down-pass/up-pass context discipline (`new_task` message, `attempt_completion` result, no implicit inheritance). Explicit precedence override clause.
|
||||
|
||||
### Write-tool security
|
||||
|
||||
**opencode `permission/evaluate.ts`** — wildcard permission ruleset (already lifted in v1.15). Extended in v2.0 to gate write tools.
|
||||
|
||||
**`covibes/zeroshot`** — blind-validation invariant. Verify gate runs in a separate agent context that only sees the diff and acceptance criteria, not the producing conversation. v2.0+ optional batch.
|
||||
|
||||
## Sub-versions
|
||||
|
||||
| Version | Scope |
|
||||
|---|---|
|
||||
| **v2.0.0** | Schema + Path A (native write tools + pending-changes queue + diff UI) + basic dispatcher |
|
||||
| **v2.0.1** | Path B (ACP client for opencode/goose + PTY fallback for claude/pi + worktree management) |
|
||||
| **v2.0.2** | BooCoder MCP server (stdio transport, `boocoder.*` tools, eval framework) |
|
||||
| **v2.0.3** | Polish: `boocode` CLI (`run/ls/attach/send`), human_inbox UI, cost tracking |
|
||||
|
||||
## Dependencies
|
||||
|
||||
- v1.13 ✅ (parts table — the event taxonomy for everything)
|
||||
- v1.14 ✅ (outer loop + step boundaries for future revert snapshots)
|
||||
- v1.14.x-mcp ✅ (MCP client PoC — proves the protocol)
|
||||
- v1.15 ✅ (full MCP client + tool globs — write-capable MCP servers route through pending_changes)
|
||||
- v1.16 ✅ (codesight merge — codecontext now has blast-radius for impact analysis)
|
||||
|
||||
All dependencies shipped. v2.0 is unblocked.
|
||||
|
||||
## Estimate
|
||||
|
||||
- v2.0.0: ~800 LoC (schema + write tools + pending-changes service + diff pane + dispatcher skeleton)
|
||||
- v2.0.1: ~600 LoC (ACP client + PTY dispatch + worktree management + event mapping)
|
||||
- v2.0.2: ~400 LoC (MCP server + 6 tool handlers + stdio transport + eval)
|
||||
- v2.0.3: ~400 LoC (CLI client + inbox UI + cost aggregation)
|
||||
- **Total: ~2200 LoC** across 4 sub-versions
|
||||
|
||||
## Hard rules
|
||||
|
||||
- BooChat stays read-only. BooCoder is the only surface with write tools.
|
||||
- Path-guard correctness is the #1 test target. Fuzz against every traversal pattern.
|
||||
- Pending-changes queue gates ALL writes (native + MCP). Nothing touches disk without user approval (or explicit auto-apply flag per task).
|
||||
- One shared database. Cross-surface joins are valuable (task → chat → terminal debugging session).
|
||||
- External CLI agents on the host, not in containers. BooCoder shells out via local-exec.
|
||||
- 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 + 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 reference
|
||||
git clone https://github.com/qodo-ai/agents.git # MIT, agent.toml schema (output_schema, exit_expression, execution_strategy)
|
||||
```
|
||||
|
||||
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.
|
||||
130
openspec/changes/v2.0-boocoder/tasks.md
Normal file
130
openspec/changes/v2.0-boocoder/tasks.md
Normal file
@@ -0,0 +1,130 @@
|
||||
# v2.0 — BooCoder task breakdown
|
||||
|
||||
## Phase 0 — Prep (before any code)
|
||||
|
||||
- [ ] Clone lift sources: `agent-hub`, `plandex`, `opencode` to `/opt/forks/`
|
||||
- [ ] Read agent-hub's schema + dispatcher pattern (Apache-2.0)
|
||||
- [ ] Read plandex's pending-changes + diff/apply/rewind flow (MIT)
|
||||
- [ ] Read opencode's `permission/evaluate.ts` for write-gate patterns (MIT)
|
||||
- [ ] Install ACP SDK: `pnpm add @zed-industries/agent-client-protocol`
|
||||
- [ ] Verify `opencode acp` and `goose acp` are available on the host
|
||||
- [ ] Write `openspec/changes/v2.0-boocoder/design.md` with finalized decisions
|
||||
|
||||
## v2.0.0 — Schema + Path A (native write tools + pending-changes + diff UI)
|
||||
|
||||
### Infra
|
||||
|
||||
- [ ] Create `apps/coder/` directory skeleton (Fastify server, mirroring `apps/server/` structure)
|
||||
- [ ] Create `apps/coder/Dockerfile` (Node 20 bookworm-slim, `/opt:/opt:rw` mount)
|
||||
- [ ] Add `boocoder` service to `docker-compose.yml` (port 9502, boocode_net)
|
||||
- [ ] Add Caddy route: `coder.indifferentketchup.com` → boocoder:9502
|
||||
- [ ] DB rename: `boocode_db` → `boochat_db` (one-time ALTER DATABASE + docker-compose volume rename)
|
||||
- [ ] Schema migration: CREATE TABLE `pending_changes`, `tasks`, `available_agents`; CREATE VIEW `human_inbox`
|
||||
- [ ] Container guidance: `BOOCODER.md` (bind-mounted at `/app/BOOCODER.md`)
|
||||
|
||||
### Write tools
|
||||
|
||||
- [ ] `apps/coder/src/services/write_guard.ts` — `resolveWritePath(projectRoot, filePath)` (resolve + prefix-check, no realpath since file may not exist)
|
||||
- [ ] `apps/coder/src/services/pending_changes.ts` — queue, apply, reject, revert operations
|
||||
- [ ] Tool: `edit_file` — takes `{file_path, old_string, new_string}`, computes unified diff, queues in `pending_changes`
|
||||
- [ ] Tool: `create_file` — takes `{file_path, content}`, queues as `operation='create'`
|
||||
- [ ] Tool: `delete_file` — takes `{file_path}`, queues as `operation='delete'`
|
||||
- [ ] Tool: `apply_pending` — flushes pending changes to disk (re-validates write_guard before each write)
|
||||
- [ ] Tool: `rewind` — reverts applied changes by inverse-diff
|
||||
|
||||
### Inference loop
|
||||
|
||||
- [ ] Port the v1.14 outer loop from `apps/server/` into `apps/coder/` (or share via workspace package)
|
||||
- [ ] Register write tools in the coder's tool registry (alongside all read tools from BooChat)
|
||||
- [ ] Permission gate: write tools require `pending_changes` queue (can't bypass to direct disk write)
|
||||
|
||||
### Frontend (diff pane)
|
||||
|
||||
- [ ] Create `apps/coder/web/` SPA (React + Vite, same stack as BooChat's `apps/web/`)
|
||||
- [ ] Diff pane component: shows pending changes with syntax-highlighted diffs
|
||||
- [ ] Approve / Reject per change, Approve All / Reject All buttons
|
||||
- [ ] Workspace splitter integration (chat pane + diff pane side by side)
|
||||
|
||||
### Verification
|
||||
|
||||
- [ ] `pnpm -C apps/coder build` clean
|
||||
- [ ] Write path-guard fuzz tests (traversal patterns, symlinks, non-existent paths, `.env` deny)
|
||||
- [ ] `docker compose up --build -d` — boocoder container starts, healthcheck passes
|
||||
- [ ] Smoke: send a chat requesting a file edit → see it queued in diff pane → approve → file written
|
||||
|
||||
## v2.0.1 — Path B (ACP dispatch + PTY fallback + worktrees)
|
||||
|
||||
### ACP client
|
||||
|
||||
- [ ] `apps/coder/src/services/acp-client.ts` — spawn `opencode acp` / `goose acp` via `@zed-industries/agent-client-protocol` StdioTransport
|
||||
- [ ] Event mapping: ACP `file_operation` → `tool_call` part, `terminal_output` → BooTerm route, `permission_request` → pause
|
||||
- [ ] Session lifecycle: start, mid-session model switch, end
|
||||
- [ ] MCP auto-forward: pass BooCoder's `context_servers` config to the ACP session
|
||||
|
||||
### PTY fallback
|
||||
|
||||
- [ ] `apps/coder/src/services/pty-dispatch.ts` — spawn `claude` / `pi` / `smallcode` via `node-pty`
|
||||
- [ ] Capture stdout/stderr/exit-code into parts (less structured than ACP)
|
||||
- [ ] Worktree setup: `git worktree add /tmp/booworktrees/<task-id> -b task-<task-id> HEAD`
|
||||
- [ ] On completion: diff worktree vs HEAD → queue into `pending_changes`
|
||||
|
||||
### Dispatcher
|
||||
|
||||
- [ ] `apps/coder/src/services/dispatcher.ts` — polls `tasks` WHERE `state='pending'`, picks by priority + creation order
|
||||
- [ ] Transport selection: check `available_agents.supports_acp` at dispatch time
|
||||
- [ ] On failure: mark `state='failed'`, surface in `human_inbox`
|
||||
- [ ] On completion: mark `state='completed'`, queue diff if Path B
|
||||
|
||||
### Agent probing
|
||||
|
||||
- [ ] Startup probe: `which opencode && opencode --version`, `which goose`, `which claude`, `which pi`
|
||||
- [ ] Populate `available_agents` table with version + ACP support
|
||||
|
||||
### Verification
|
||||
|
||||
- [ ] Smoke: dispatch a task to `opencode` via ACP → task completes → diff queued
|
||||
- [ ] Smoke: dispatch to `claude` via PTY fallback → captures output → diff from worktree
|
||||
- [ ] Worktree cleanup after task completion
|
||||
|
||||
## v2.0.2 — BooCoder MCP server
|
||||
|
||||
### Implementation
|
||||
|
||||
- [ ] `apps/coder/src/services/mcp-server.ts` — register 6 tools as MCP tool handlers
|
||||
- [ ] Stdio transport (use `@modelcontextprotocol/sdk` server-side, same SDK as client)
|
||||
- [ ] Tools: `boocoder.create_task`, `boocoder.list_pending_changes`, `boocoder.apply`, `boocoder.reject`, `boocoder.dispatch_external_agent`, `boocoder.list_worktrees`
|
||||
- [ ] Each tool maps to a DB operation or service call
|
||||
|
||||
### Eval
|
||||
|
||||
- [ ] Write 10-question eval per `anthropics/skills/mcp-builder` framework
|
||||
- [ ] Run eval against the MCP server — all 10 must pass before shipping
|
||||
- [ ] Document eval results in openspec
|
||||
|
||||
### Verification
|
||||
|
||||
- [ ] From a terminal: `echo '{"jsonrpc":"2.0","method":"tools/list","id":1}' | boocoder --mcp` → returns 6 tools
|
||||
- [ ] From opencode: configure BooCoder as an MCP server in `~/.opencode/config.json`, verify tool calls work
|
||||
|
||||
## v2.0.3 — Polish
|
||||
|
||||
### CLI client
|
||||
|
||||
- [ ] `apps/coder/src/cli.ts` — thin WebSocket/HTTP client against BooCoder API
|
||||
- [ ] Verbs: `boocode run <task>`, `boocode ls`, `boocode attach <id>`, `boocode send <id> <message>`
|
||||
- [ ] Mirrors Paseo's UX, license-clean implementation
|
||||
|
||||
### Human inbox UI
|
||||
|
||||
- [ ] Frontend route showing tasks in `blocked`/`failed` state
|
||||
- [ ] Per-task: view output, retry, cancel, reassign to different agent
|
||||
|
||||
### Cost tracking
|
||||
|
||||
- [ ] `tasks.cost_tokens` populated from inference usage
|
||||
- [ ] Summary view: per-project, per-agent, per-day token spend
|
||||
|
||||
### Verification
|
||||
|
||||
- [ ] `boocode run "add a health endpoint"` from terminal → task appears in UI → completes → diff in pane
|
||||
- [ ] `boocode ls` shows running/completed/failed tasks
|
||||
34
pnpm-lock.yaml
generated
34
pnpm-lock.yaml
generated
@@ -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':
|
||||
|
||||
Reference in New Issue
Block a user