Files
boocode/apps/server/src/index.ts
indifferentketchup f8fc5db929 v1.13.5: opencode truncate.ts port — full tool output retrievable via opaque id
- New services/truncate.ts. Tmpfs storage at /tmp/boocode-truncations/
  (BOOCODE_TRUNCATION_DIR env var overrides for tests). 12-char base32
  opaque ids (~60 bits entropy, "tr_<id>"). Three exports: storeTruncation,
  readTruncation, truncateIfNeeded (wrap-or-passthrough helper).
  cleanupTruncations does TTL-pass (7 days) + orphan-reap (parts query on
  payload->'output'->>'outputPath') in one shot.
- Wired four tools through truncateIfNeeded: view_file (raw full file),
  list_dir (full filtered+secret-filtered entries serialized one-per-line),
  web_fetch (textRaw pre-slice), codecontext_client (body.result pre-slice).
  Each returns the existing sliced view plus an optional outputPath field
  when truncation fires.
- New view_truncated_output ToolDef. Resolves opaque id → on-disk content
  internally; model never sees the truncation dir. Same start_line /
  end_line slicing semantics as view_file. Registered in ALL_TOOLS (alpha
  sort places it after view_file automatically) and READ_ONLY_TOOL_NAMES.
- cleanupTruncations piggybacks on the v1.13.3 stuck-row sweeper's 60s
  setInterval. No-op when truncation dir is empty.

Not wired (TODO follow-up): grep and find_files. file_ops returns post-cap
results to the tool execute path, so the "full content" isn't recoverable
without a refactor of fileOps.grep / fileOps.findFiles to expose the
uncapped result. web_search is silent-slice (no truncated flag); outside
scope. Five sites of seven covered; the remaining two are the only ones
needing a file_ops change.

Tests: 7 new in truncate.test.ts (roundtrip, unknown id, malformed id,
truncateIfNeeded false/true/over-cap/storage-failure paths). 186 total
(was 179). cleanupTruncations file-system half implicitly via TTL pass;
orphan-reap branch covered by the live container smoke.

Smoke verified end-to-end against the live container:
- view_file with start_line=1, end_line=3 on CLAUDE.md → tool_result part
  carried outputPath "tr_cdpn1o04k6ma" + truncated=true.
- /tmp/boocode-truncations/tr_cdpn1o04k6ma exists, 15876 bytes, mode 0o600,
  parent dir mode 0o700.
- Follow-up view_truncated_output(id, start_line=50, end_line=55) returned
  the actual lines 50-55 of CLAUDE.md (the 808notes/BooCode bullets).
- ALL_TOOLS count=20 (was 19); alpha sort places view_truncated_output
  between view_file and watch_changes.

Closes a v1.12 catalog row that was scoped but deferred. The v1.13 parts
table made outputPath ride on the existing tool_result payload with no
schema change beyond the storage helper itself.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-22 07:55:55 +00:00

277 lines
9.7 KiB
TypeScript

import Fastify from 'fastify';
import fastifyStatic from '@fastify/static';
import fastifyWebsocket from '@fastify/websocket';
import { existsSync } from 'node:fs';
import { resolve } from 'node:path';
import { loadConfig } from './config.js';
import { getSql, applySchema, pingDb, closeDb } from './db.js';
import { registerProjectRoutes } from './routes/projects.js';
import { registerSessionRoutes } from './routes/sessions.js';
import { registerSettingsRoutes } from './routes/settings.js';
import { registerMessageRoutes } from './routes/messages.js';
import { registerChatRoutes } from './routes/chats.js';
import { registerSidebarRoutes } from './routes/sidebar.js';
import { registerWebSocket } from './routes/ws.js';
import { registerModelRoutes } from './routes/models.js';
import { registerAgentRoutes } from './routes/agents.js';
import { registerSkillsRoutes } from './routes/skills.js';
import { createInferenceRunner } from './services/inference/index.js';
import { createBroker } from './services/broker.js';
import { listSkills } from './services/skills.js';
import * as compaction from './services/compaction.js';
import { configureModelContext } from './services/model-context.js';
import { cleanupTruncations } from './services/truncate.js';
async function main() {
const config = loadConfig();
const app = Fastify({
logger: { level: config.LOG_LEVEL },
});
// Allow empty JSON bodies on POSTs that don't take a body (archive, unarchive, stop, etc.).
// Default Fastify parser throws FST_ERR_CTP_EMPTY_JSON_BODY on empty string.
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');
const swept = await sql<{ count: string }[]>`
WITH swept AS (
UPDATE messages SET status = 'failed'
WHERE status = 'streaming' AND created_at < NOW() - INTERVAL '5 minutes'
RETURNING id
) SELECT count(*)::text AS count FROM swept
`;
const sweptCount = Number(swept[0]?.count ?? 0);
if (sweptCount > 0) {
app.log.info({ sweptCount }, 'swept stale streaming messages to failed');
}
// v1.11.3: tell the model-context cache where llama-swap lives. Cache
// lookups go to ${LLAMA_SWAP_URL}/upstream/<model>/props to read
// default_generation_settings.n_ctx — the value persisted as messages.ctx_max.
configureModelContext({ llamaSwapUrl: config.LLAMA_SWAP_URL });
await app.register(fastifyWebsocket);
app.get('/api/health', async () => {
const dbOk = await pingDb(sql);
return { status: dbOk ? 'ok' : 'degraded', db: dbOk };
});
const broker = createBroker();
registerProjectRoutes(app, sql, config, broker);
registerSessionRoutes(app, sql, config, broker);
registerSettingsRoutes(app, sql);
registerModelRoutes(app, config);
registerAgentRoutes(app, sql);
registerSidebarRoutes(app, sql);
registerChatRoutes(app, sql, broker);
// Batch 9.6: warm the skills cache at boot and surface the count. Empty or
// missing /data/skills is non-fatal — the skill tools just return empty.
try {
const skills = await listSkills();
app.log.info(`skills loaded: ${skills.length}`);
} catch (err) {
app.log.warn({ err }, 'skills boot walk failed');
}
const inference = createInferenceRunner(
{
sql,
config,
log: app.log,
publish: (sessionId, frame) => {
broker.publish(sessionId, frame as unknown as Record<string, unknown> & { type: string });
},
// v1.11: broker handle for compaction.process to publish 'compacted'
// frames on the per-session channel. Inference's regular publish path
// is bound to (sessionId, InferenceFrame); compaction publishes a
// different frame shape, so it goes through the raw broker.
broker,
},
(user, frame) => {
broker.publishUser(user, frame as unknown as Record<string, unknown> & { type: string });
}
);
registerMessageRoutes(app, sql, {
enqueueInference: (sessionId, chatId, assistantId, user) => {
inference.enqueue(sessionId, chatId, assistantId, user);
},
// v1.11: synchronous compaction. Awaits the LLM call inside the route's
// request lifecycle; the new summary row arrives via the WS 'compacted'
// frame published from inside compaction.process. We let the error
// bubble up so the route can reply 500 — manual /compact failures
// should be loud (the user just clicked a button).
runCompaction: (chatId) =>
compaction.process({ sql, config, log: app.log, broker, chatId }),
cancelInference: async (sessionId, chatId) => {
return inference.cancel(sessionId, chatId);
},
hasActiveInference: (chatId) => inference.hasActive(chatId),
publishUserMessage: (sessionId, chatId, userMessageId, content) => {
broker.publish(sessionId, {
type: 'message_started',
message_id: userMessageId,
chat_id: chatId,
role: 'user',
});
broker.publish(sessionId, {
type: 'delta',
message_id: userMessageId,
chat_id: chatId,
content,
});
broker.publish(sessionId, {
type: 'message_complete',
message_id: userMessageId,
chat_id: chatId,
});
},
publishMessagesDeleted: (sessionId, chatId, messageIds) => {
broker.publish(sessionId, {
type: 'messages_deleted',
message_ids: messageIds,
chat_id: chatId,
});
},
publishSessionFrame: (sessionId, frame) => {
broker.publish(sessionId, frame);
},
});
registerSkillsRoutes(app, sql, {
enqueueInference: (sessionId, chatId, assistantId, user) => {
inference.enqueue(sessionId, chatId, assistantId, user);
},
publishUserMessage: (sessionId, chatId, userMessageId, content) => {
broker.publish(sessionId, {
type: 'message_started',
message_id: userMessageId,
chat_id: chatId,
role: 'user',
});
broker.publish(sessionId, {
type: 'delta',
message_id: userMessageId,
chat_id: chatId,
content,
});
broker.publish(sessionId, {
type: 'message_complete',
message_id: userMessageId,
chat_id: chatId,
});
},
publishSessionFrame: (sessionId, frame) => {
broker.publish(sessionId, frame);
},
});
registerWebSocket(app, sql, broker);
const webDist = process.env.WEB_DIST_PATH ?? resolve(process.cwd(), '../web/dist');
if (existsSync(webDist)) {
await app.register(fastifyStatic, {
root: webDist,
prefix: '/',
wildcard: false,
});
app.setNotFoundHandler((req, reply) => {
if (req.url.startsWith('/api')) {
reply.code(404).send({ error: 'not found' });
return;
}
reply.sendFile('index.html');
});
app.log.info(`serving static frontend from ${webDist}`);
}
// v1.13.3: periodic in-process sweeper for streaming rows orphaned by a
// mid-session crash. The boot sweep (above) only fires once at startup;
// this loop catches the in-flight case. 60s cadence + 5-min threshold
// matches the boot sweep so behavior is consistent. Publishes
// chat_status='idle' on the user channel so the UI dot drops without a
// refresh — same pattern as handleAbortOrError.
const SWEEP_INTERVAL_MS = 60_000;
const sweepStaleStreaming = async (): Promise<void> => {
try {
const rows = await sql<{ id: string; chat_id: string }[]>`
UPDATE messages
SET status = 'failed', finished_at = clock_timestamp()
WHERE status = 'streaming'
AND created_at < NOW() - INTERVAL '5 minutes'
RETURNING id, chat_id
`;
if (rows.length === 0) return;
app.log.warn(
{ swept: rows.length, ids: rows.map((r) => r.id) },
'swept stale streaming rows',
);
const seenChats = new Set<string>();
const now = new Date().toISOString();
for (const row of rows) {
if (seenChats.has(row.chat_id)) continue;
seenChats.add(row.chat_id);
broker.publishUser('default', {
type: 'chat_status',
chat_id: row.chat_id,
status: 'idle',
at: now,
});
}
} catch (err) {
app.log.error({ err }, 'stuck-row sweeper failed');
}
};
// v1.13.5: truncation cleanup rides the same cadence — 60s tick reaps
// tmpfs files past the 7-day TTL plus any orphans whose owning part has
// been pruned (v1.13.4) or deleted. No-op when the dir is empty.
const sweepTimer = setInterval(() => {
void sweepStaleStreaming();
void cleanupTruncations({ sql, log: app.log });
}, SWEEP_INTERVAL_MS);
app.addHook('onClose', async () => { clearInterval(sweepTimer); });
const shutdown = async (signal: string) => {
app.log.info(`received ${signal}, shutting down`);
try {
await app.close();
await closeDb();
process.exit(0);
} catch (err) {
app.log.error(err);
process.exit(1);
}
};
process.on('SIGINT', () => void shutdown('SIGINT'));
process.on('SIGTERM', () => void shutdown('SIGTERM'));
// Bound to 0.0.0.0 intentionally. Public access goes through Caddy → Authelia.
// Direct Tailscale access (100.114.205.53:9500) is unauthenticated by design;
// the threat model treats Tailnet membership as the trust boundary.
await app.listen({ port: config.PORT, host: config.HOST });
app.log.info(`boocode server listening on http://${config.HOST}:${config.PORT}`);
}
main().catch((err) => {
console.error('Fatal startup error:', err);
process.exit(1);
});