Files
platform/src/servers/api/chat/websocket.ts
T
pastilhasandClaude Opus 5 6b4339052a reattach a refreshed browser to a running turn
Refreshing mid-turn appeared to kill the agent's output. It never did: the
session survives a dropped socket, the agent keeps generating into it and keeps
committing durable events, and `close` only detaches the socket and arms an
hour-long idle timer. What broke was purely delivery — and the reconnect path
that would have fixed it could not fire, because the browser came back having
forgotten officer's session key. It lived in page state. The only id left was
Claude's transcript uuid in the URL, and nothing accepted that.

So accept it. `attach` carries the uuid, and the agent's on-disk session map —
the single record relating the two — turns it back into the key everything else
is written in terms of. The uuid now also goes out at `system.init` rather than
only at `result`, which is what makes the first turn recoverable at all: until
now a chat had no address until it had finished, and a long first turn is
exactly the one worth reconnecting to.

`sync:live` deliberately carries no messages. The harness writes its transcript
as it goes, so the HTTP load on landing already supplies the past; sending the
server's record of the same messages on top of it would duplicate them, and
there is no shared id to reconcile the two by. Attach hands over the rest of the
turn, the half-written paragraph the transcript cannot hold, and the session's
cursor head — that last one so a *later* drop replays from the head instead of
re-delivering the whole conversation from zero.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-07 17:59:26 +00:00

732 lines
27 KiB
TypeScript

import type { ServerWebSocket } from 'bun';
import { randomUUID } from 'crypto';
import type { ClientMessage, ServerMessage, Message, PromptImage, TurnMessage, UserSession } from './types';
import { sessionManager } from './session-manager';
import { sendClaudeCodeStreaming } from '@@/channels/send-claude-code';
import { sendOpenCodeStreaming } from '@@/channels/send-opencode';
import { ensureGeneralChatSessionsCwd } from './claude-sessions';
import * as sidecar from '@@/sidecar-registry';
import { join } from 'path';
import { getOwnerHomeDir, getEmailAccountsDir } from '../../../servers/data-path';
import { getUserSettings, getEmailAccounts, getChatEventsSince, getLastChatEventSeq, appendChatEvent } from 'officerdb';
import { mkdirSync } from 'node:fs';
import { logger } from './logger';
// Default model when no user preference is set
const DEFAULT_MODEL = 'claude-code';
// Harness selection: the `claude-code` provider runs through the Claude sidecar; every other provider
// (opencode/anthropic/openai/… — all `providerID/modelID` ids) runs through the OpenCode server.
const isClaudeModel = (model: string): boolean => model.startsWith('claude-code');
async function getUserDefaultModel(userId: number): Promise<string | null> {
try {
const settings = await getUserSettings(userId);
const chat = settings?.chat as Record<string, unknown> | undefined;
return (chat?.defaultModel as string) || null;
} catch (err) {
logger.error('Failed to read user settings for default model', { userId, error: String(err) });
}
return null;
}
type WSData = {
userId: number;
email: string;
username: string;
provider: string;
};
const IDLE_TIMEOUT_MS = 60 * 60 * 1000; // 1 hour
const resolveCwd = (email: string, cwd?: string) => {
const root = getOwnerHomeDir(email);
if (!cwd || cwd === '~') return root;
if (cwd.startsWith('~/')) return join(root, cwd.slice(2));
// The server owner is the only account — absolute paths are theirs to use.
if (cwd.startsWith('/')) return cwd;
return join(root, cwd);
};
export const resolveBaseCwd = (email: string, cwd?: string) => resolveCwd(email, cwd);
// The email chat runs from the selected account's storage dir:
// DATA_PATH/<owner>/email_accounts/<accountEmail>
// `accountEmail` will come from the account selector (msg.contextId) later; for now default to the
// owner's first enabled account. Falls back to the email_accounts root if there are no accounts.
async function resolveEmailCwd(userId: number, ownerEmail: string, accountEmail?: string): Promise<string> {
let account = accountEmail?.trim();
if (!account) {
try {
const accounts = await getEmailAccounts(userId);
account = (accounts.find((a) => a.enabled) ?? accounts[0])?.email;
} catch (err) {
logger.error('Failed to resolve email account for chat cwd', { userId, error: String(err) });
}
}
const dir = account ? join(getEmailAccountsDir(ownerEmail), account) : getEmailAccountsDir(ownerEmail);
mkdirSync(dir, { recursive: true });
return dir;
}
// The working directory a chat turn runs in, by context: email → the account dir; /chat → a chosen
// pwd or the default general_chat_sessions dir; everything else (browser/project/dashboard) → the given cwd.
async function resolveChatCwd(
msg: { context?: string; contextId?: string; cwd?: string },
email: string,
userId: number,
): Promise<string> {
if (msg.context === 'email') return resolveEmailCwd(userId, email, msg.contextId);
if (msg.context === 'chat') return msg.cwd?.trim() ? resolveCwd(email, msg.cwd) : ensureGeneralChatSessionsCwd(email);
return resolveCwd(email, msg.cwd);
}
const wsToSessionMap = new WeakMap<any, string>();
// Per-connection heartbeat. Bun closes a WS idle for `idleTimeout` (60s), and its timer only resets
// on frames *received* from the client — but during a chat turn the client only receives. So we ping
// each connection every 25s; the client auto-pongs at the protocol level, which resets Bun's timer
// (and keeps reverse proxies happy). Genuinely dead sockets still time out (no pong).
const pingTimers = new WeakMap<ServerWebSocket<WSData>, ReturnType<typeof setInterval>>();
const PING_INTERVAL_MS = 25_000;
function sendToClient(ws: ServerWebSocket<WSData> | null, msg: ServerMessage, seq?: number): void {
if (ws?.readyState === 1) {
ws.send(JSON.stringify(seq === undefined ? msg : { ...msg, seq }));
}
}
// Nothing in officer writes to chat_session_events any more. Both harnesses commit their own turn
// output in the sidecar that produced it (`sidecar/claude/session-log.ts`), which is the whole point:
// the durable record does not travel over the socket between the two processes, so officer can restart
// mid-turn without losing it. Officer reads the table on `resume` (getChatEventsSince) and relays what
// the sidecars send. The old `emitToSession` used to live here.
export async function open(ws: ServerWebSocket<WSData>): Promise<void> {
const timer = setInterval(() => {
try {
ws.ping(); // client auto-pongs → resets Bun's idleTimeout
} catch {
/* socket already gone */
}
}, PING_INTERVAL_MS);
pingTimers.set(ws, timer);
}
export function message(ws: ServerWebSocket<WSData>, raw: string | Buffer): void {
const data = typeof raw === 'string' ? raw : raw.toString();
(async () => {
try {
const clientMsg = JSON.parse(data) as ClientMessage;
if (clientMsg.type === 'chat') {
await handleChat(ws, clientMsg);
} else if (clientMsg.type === 'resume') {
await handleResume(ws, clientMsg);
} else if (clientMsg.type === 'stop') {
await handleStop(ws);
} else if (clientMsg.type === 'disconnect') {
await handleDisconnect(ws);
} else if (clientMsg.type === 'resume-cursor') {
await handleResumeCursor(ws, clientMsg);
} else if (clientMsg.type === 'attach') {
await handleAttach(ws, clientMsg);
}
} catch (err) {
logger.error('Error handling WebSocket message', { email: ws.data.email, error: String(err) });
sendToClient(ws, { type: 'error', message: 'Failed to process message' });
}
})();
}
export function close(ws: ServerWebSocket<WSData>): void {
const timer = pingTimers.get(ws);
if (timer) {
clearInterval(timer);
pingTimers.delete(ws);
}
const sessionId = wsToSessionMap.get(ws);
if (sessionId) {
sessionManager.detachWs(sessionId);
sessionManager.setIdleTimeout(sessionId, IDLE_TIMEOUT_MS);
}
}
// ── Claude Code: relay, don't rebuild ──
// The agent sidecar owns Claude's turn output end to end — it translates the parser stream, commits each
// message to chat_session_events and hands us a finished message plus its cursor id. Officer relays it.
// That is what makes a restart survivable: the durable record no longer travels over the socket between
// the two processes, so if this one is down the output is already written and the client replays it.
//
// Officer keeps only the in-memory transcript, which exists to answer a `resume` with sync:messages —
// Claude's own transcript is the real record — so it is folded from the same messages, not rebuilt.
function foldIntoSession(session: UserSession, msg: TurnMessage, model: string): void {
switch (msg.type) {
case 'assistant:delta':
// A subagent's deltas are not the main agent typing; appending them here spliced its sentences into
// whatever the agent you are talking to was mid-way through saying.
if (!msg.parentToolUseId) session.streamBuffer += msg.text;
break;
case 'assistant:text':
session.messages.push({
id: randomUUID(),
timestamp: Date.now(),
role: 'assistant',
text: msg.text,
model,
parentToolUseId: msg.parentToolUseId,
});
session.meta.messageCount += 1;
// Only the main agent's own stream feeds the buffer a resume replays as `streamingText`.
if (!msg.parentToolUseId) session.streamBuffer = '';
break;
case 'tool:start':
session.messages.push({
id: randomUUID(),
timestamp: Date.now(),
role: 'tool',
toolCallId: msg.toolCallId,
toolName: msg.toolName,
toolInput: msg.toolInput,
parentToolUseId: msg.parentToolUseId,
});
session.meta.messageCount += 1;
break;
case 'tool:result':
for (let i = session.messages.length - 1; i >= 0; i--) {
const m = session.messages[i]!;
if (m.role === 'tool' && m.toolCallId === msg.toolCallId) {
m.output = msg.output;
m.isError = msg.isError;
break;
}
}
break;
case 'result': {
session.isGenerating = false;
session.meta.cost.inputTokens += msg.cost.inputTokens;
session.meta.cost.outputTokens += msg.cost.outputTokens;
session.meta.cost.totalUSD += msg.cost.totalUSD;
session.meta.updatedAt = Date.now();
// The turn's cost belongs to the assistant message it paid for (as it did when officer built these).
// The turn's cost is the main agent's, so skip past any subagent tail.
const last = [...session.messages].reverse().find((m) => !m.parentToolUseId);
if (last?.role === 'assistant' && !last.cost) last.cost = msg.cost;
break;
}
case 'error':
case 'stopped':
session.isGenerating = false;
break;
}
}
// Shared by both harnesses now: whichever sidecar ran the turn has already translated and committed it.
function createMessageHandler(sessionId: string, model: string) {
return (msg: TurnMessage, seq?: number): void => {
const session = sessionManager.getSession(sessionId);
if (!session) return;
foldIntoSession(session, msg, model);
sendToClient(session.ws as ServerWebSocket<WSData> | null, msg, seq);
};
}
async function handleChat(
ws: ServerWebSocket<WSData>,
msg: {
prompt: string;
displayText?: string;
sessionId?: string;
model?: string;
cwd?: string;
cwdRoot?: string;
groupSlug?: string;
attachmentIds?: string[];
images?: PromptImage[];
thinking?: string;
context?: string;
contextId?: string;
resumeSummary?: string;
resumeSessionId?: string;
},
): Promise<void> {
const { userId } = ws.data;
const sessionId = msg.sessionId || randomUUID();
// Prepend resume summary to the prompt if present
const prompt = msg.resumeSummary
? `Here is a summary of a previous conversation to continue from:\n\n${msg.resumeSummary}\n\n---\n\nUser's new message: ${msg.prompt}`
: msg.prompt;
// Use provided model, or fall back to user default, or the system default.
const model = msg.model || (await getUserDefaultModel(userId)) || DEFAULT_MODEL;
logger.info('Model selected for chat', { sessionId, model, clientModel: msg.model || null });
// Route by harness: claude-code → Claude sidecar; anything else → OpenCode server.
return isClaudeModel(model)
? handleClaudeCodeChat(ws, sessionId, model, msg, prompt)
: handleOpenCodeChat(ws, sessionId, model, msg, prompt);
}
async function handleClaudeCodeChat(
ws: ServerWebSocket<WSData>,
sessionId: string,
model: string,
msg: {
prompt: string;
displayText?: string;
groupSlug?: string;
context?: string;
contextId?: string;
cwd?: string;
cwdRoot?: string;
images?: PromptImage[];
resumeSessionId?: string;
},
effectivePrompt: string,
): Promise<void> {
const { email, username, userId } = ws.data;
const cwd = await resolveChatCwd(msg, email, userId);
const groupSlug = msg.groupSlug || null;
const session = sessionManager.getOrCreate(sessionId, email, cwd, model, groupSlug, msg.context, msg.contextId);
session.userId = userId;
sessionManager.attachWs(sessionId, ws);
wsToSessionMap.set(ws as any, sessionId);
sendToClient(ws, {
type: 'session:init',
sessionId,
model,
cwd,
context: session.meta.context,
contextId: session.meta.contextId,
});
// Add user message to session
const userMsg: Message = {
id: randomUUID(),
timestamp: Date.now(),
role: 'user',
text: msg.prompt,
};
session.messages.push(userMsg);
session.meta.messageCount += 1;
session.meta.updatedAt = Date.now();
if (!session.meta.title) {
session.meta.title = (msg.displayText ?? msg.prompt).slice(0, 100);
}
session.isGenerating = true;
const onMessage = createMessageHandler(sessionId, model);
try {
if (!session._claudeKill) {
// First turn of this session: open the persistent session + a SESSION-scoped event subscription
// (survives turn-end so background task:notifications keep flowing). handle.kill tears both down.
const handle = await sendClaudeCodeStreaming({
userId,
email,
username,
prompt: effectivePrompt,
images: msg.images,
sessionKey: sessionId,
cwd,
model,
resumeSessionId: msg.resumeSessionId,
onMessage,
});
session.piProcess = sessionId as any;
session._claudeKill = handle.kill;
} else {
// Session already live: push this turn onto the existing persistent session (no new subscription).
await sidecar.spawnClaudeStreaming({
userId,
email,
username,
prompt: effectivePrompt,
images: msg.images,
sessionKey: sessionId,
cwd,
model,
resumeSessionId: msg.resumeSessionId,
});
}
} catch (err) {
logger.error('Failed to start Claude Code streaming', { sessionId, error: String(err) });
sendToClient(ws, { type: 'error', message: 'Failed to start Claude Code' });
session.isGenerating = false;
}
}
async function handleOpenCodeChat(
ws: ServerWebSocket<WSData>,
sessionId: string,
model: string,
msg: {
prompt: string;
displayText?: string;
groupSlug?: string;
context?: string;
contextId?: string;
cwd?: string;
cwdRoot?: string;
resumeSessionId?: string;
},
effectivePrompt: string,
): Promise<void> {
const { email, username, userId } = ws.data;
const cwd = await resolveChatCwd(msg, email, userId);
const groupSlug = msg.groupSlug || null;
const session = sessionManager.getOrCreate(sessionId, email, cwd, model, groupSlug, msg.context, msg.contextId);
session.userId = userId;
sessionManager.attachWs(sessionId, ws);
wsToSessionMap.set(ws as any, sessionId);
sendToClient(ws, {
type: 'session:init',
sessionId,
model,
cwd,
context: session.meta.context,
contextId: session.meta.contextId,
});
const userMsg: Message = {
id: randomUUID(),
timestamp: Date.now(),
role: 'user',
text: msg.prompt,
};
session.messages.push(userMsg);
session.meta.messageCount += 1;
session.meta.updatedAt = Date.now();
if (!session.meta.title) {
session.meta.title = (msg.displayText ?? msg.prompt).slice(0, 100);
}
session.isGenerating = true;
const onMessage = createMessageHandler(sessionId, model);
try {
const handle = await sendOpenCodeStreaming({
userId,
email,
username,
prompt: effectivePrompt,
sessionKey: sessionId,
cwd,
model,
resumeSessionId: msg.resumeSessionId,
onMessage,
});
// Store the abort handle so handleStop can end the turn (OpenCode is aborted via this handle).
session.piProcess = sessionId as any;
session._claudeKill = handle.kill;
} catch (err) {
logger.error('Failed to start OpenCode streaming', { sessionId, error: String(err) });
sendToClient(ws, { type: 'error', message: 'Failed to start OpenCode' });
session.isGenerating = false;
}
}
async function handleResume(
ws: ServerWebSocket<WSData>,
msg: { sessionId: string; cwd?: string; cwdRoot?: string },
): Promise<void> {
const { sessionId } = msg;
try {
const session = sessionManager.getSession(sessionId);
if (!session) {
// Sessions live in memory for the connection's lifetime; there's no disk store to reload from.
sendToClient(ws, { type: 'error', message: 'Session not found', errorCode: 'SESSION_NOT_FOUND' });
return;
}
sessionManager.attachWs(sessionId, ws);
wsToSessionMap.set(ws as any, sessionId);
sendToClient(ws, {
type: 'session:init',
sessionId,
model: session.model,
cwd: session.cwd,
context: session.meta.context,
contextId: session.meta.contextId,
});
// Claude resumes lazily: the next chat prompt re-attaches via `--resume <sessionKey>`, so there's
// no long-lived process to spawn here — just replay the stored transcript to the client.
sendToClient(ws, {
type: 'sync:messages',
sessionId,
messages: session.messages,
isGenerating: session.isGenerating,
streamingText: session.streamBuffer,
});
logger.info('Session resumed successfully', { sessionId, messageCount: session.messages.length });
} catch (err) {
logger.error('Unexpected error in handleResume', { sessionId, error: String(err) });
sendToClient(ws, { type: 'error', message: 'Failed to resume session' });
}
}
async function handleStop(ws: ServerWebSocket<WSData>): Promise<void> {
const sessionId = wsToSessionMap.get(ws);
if (sessionId) {
const session = sessionManager.getSession(sessionId);
if (session?.piProcess) {
try {
if (isClaudeModel(session.model)) {
// Interrupt the current turn but KEEP the persistent session alive (background tasks + the
// warm worker survive). Full teardown is 'disconnect' → deleteSession → _claudeKill.
void sidecar.interruptClaude(sessionId);
logger.info('Interrupted Claude Code turn via sidecar (session stays warm)', { sessionId });
} else {
session._claudeKill?.(); // OpenCode: abort the turn via the stored handle
logger.info('Aborted OpenCode turn', { sessionId });
}
session.isGenerating = false;
} catch (err) {
logger.error('Failed to stop process', { sessionId, error: String(err) });
}
}
}
sendToClient(ws, { type: 'stopped' });
}
// Tear down the whole session (not just the current turn): deleteSession fires _claudeKill (kills any
// in-flight Claude/OpenCode turn) + _sidecarUnsub, clears the idle timer, and drops the session from the
// manager's maps. The WS stays open so the client can immediately start a fresh session.
async function handleDisconnect(ws: ServerWebSocket<WSData>): Promise<void> {
const sessionId = wsToSessionMap.get(ws);
if (sessionId) {
try {
sessionManager.deleteSession(sessionId);
wsToSessionMap.delete(ws as any);
logger.info('Disconnected chat session', { sessionId });
} catch (err) {
logger.error('Failed to disconnect session', { sessionId, error: String(err) });
}
}
sendToClient(ws, { type: 'disconnected' });
}
/**
* Re-adopt a session whose in-memory record died with the process that held it.
*
* The sidecars are PM2 peers, so `pm2 restart officer` does not touch a running turn: the agent keeps
* generating and keeps committing to chat_session_events. What the restart destroys is purely this
* process's binding to it — the session record and, critically, the session-scoped subscription that
* relays the sidecar's events to the browser. Re-creating the record is not enough on its own; without
* the subscription the client reconnects, receives its replay, and then goes silent for the rest of the
* turn, which is indistinguishable from the agent having died.
*
* Nothing is spawned here. The subscription is a local event-bus filter, so adopting a session that is
* NOT in fact still live upstream costs a listener that never fires and a record the idle GC collects.
*/
function adoptOrphanedSession(ws: ServerWebSocket<WSData>, sessionId: string, model: string, cwd: string): UserSession {
const { email, userId } = ws.data;
const session = sessionManager.getOrCreate(sessionId, email, cwd, model, null);
session.userId = userId;
session.piProcess = sessionId as any;
const onMessage = createMessageHandler(sessionId, model);
const unsubClaude = sidecar.onClaudeMessage((key, msg, seq) => {
if (key === sessionId) onMessage(msg, seq);
});
const unsubOpenCode = sidecar.onOpenCodeMessage((key, msg, seq) => {
if (key === sessionId) onMessage(msg, seq);
});
const unsub = () => {
unsubClaude();
unsubOpenCode();
};
// Must be set, and not only for teardown: handleChat treats an absent `_claudeKill` as "first turn of
// this session" and opens a *second* subscription, which would then deliver every message twice.
session._claudeKill = () => {
if (isClaudeModel(model)) sidecar.killClaude(sessionId);
else sidecar.killOpenCode(sessionId);
unsub();
};
logger.info('Adopted orphaned chat session after restart', { sessionId, model });
return session;
}
// Reconnect: re-bind this socket to the (possibly still-live) session and replay every durable event
// queued since the client's cursor — so a brief disconnect never loses turn output or a background
// task:notification. attachWs cancels the pending idle-GC.
async function handleResumeCursor(
ws: ServerWebSocket<WSData>,
msg: { sessionId: string; cursor: number; model?: string; cwd?: string; generating?: boolean },
): Promise<void> {
const { sessionId, cursor } = msg;
const model = msg.model || DEFAULT_MODEL;
if (!sessionManager.getSession(sessionId)) {
adoptOrphanedSession(ws, sessionId, model, msg.cwd ?? '');
}
sessionManager.attachWs(sessionId, ws);
wsToSessionMap.set(ws as any, sessionId);
try {
const events = await getChatEventsSince(sessionId, cursor ?? 0);
for (const { id, event } of events) {
sendToClient(ws, event as ServerMessage, id);
}
} catch (err) {
logger.error('Failed to replay chat events on resume-cursor', { sessionId, error: String(err) });
}
if (msg.generating) await endTurnIfAgentIsGone(ws, sessionId, model);
}
/**
* Re-bind a socket that knows only Claude's transcript uuid.
*
* This is the refresh case, and until now it was the hole in an otherwise complete reconnect path. Every
* piece of the machinery already existed — the session survives a dropped socket, the agent keeps
* generating into it, `close` only detaches and arms an hour-long idle timer — but the browser came back
* having forgotten officer's session id, so `resume-cursor` could never fire and the output simply stopped
* arriving. The uuid in the URL is the one identifier a refresh cannot destroy; the agent's on-disk map
* turns it back into the key everything else here is written in terms of.
*
* Deliberately hands over only the live turn, never the transcript — see `sync:live`.
*/
async function handleAttach(ws: ServerWebSocket<WSData>, msg: { claudeSessionId: string }): Promise<void> {
const { claudeSessionId } = msg;
if (!claudeSessionId) return;
const sessionId = await sidecar.findClaudeSessionKey(claudeSessionId);
if (!sessionId) {
// No agent, or a transcript it has never run. Nothing is wrong: an ordinary finished conversation
// opened from history lands here every time. Stay silent and leave the socket as it was — the next
// `chat` mints a session in the usual way.
logger.info('Attach found no live session for transcript', { claudeSessionId });
return;
}
// An officer restart takes the in-memory session with it while the agent carries on, so the key can
// resolve to a session this process has never heard of. Adopting re-subscribes it to the sidecar's bus,
// which is what makes the rest of the turn arrive.
const existing = sessionManager.getSession(sessionId);
const session = existing ?? adoptOrphanedSession(ws, sessionId, DEFAULT_MODEL, '');
sessionManager.attachWs(sessionId, ws);
wsToSessionMap.set(ws as any, sessionId);
// The client learns officer's key here, so any *later* drop of this socket goes down the existing
// cursor-replay path instead of coming back through attach.
sendToClient(ws, {
type: 'session:init',
sessionId,
model: session.model,
cwd: session.cwd,
context: session.meta.context,
contextId: session.meta.contextId,
});
// `isGenerating` is officer's own belief and is only as good as this process's memory of the turn. For
// an adopted session it is a fresh record's default, so ask the agent — the same question, and for the
// same reason, as `endTurnIfAgentIsGone`.
const isGenerating = existing ? session.isGenerating : await sidecar.isClaudeGenerating(sessionId);
session.isGenerating = isGenerating;
let cursor = 0;
try {
cursor = (await getLastChatEventSeq(sessionId)) ?? 0;
} catch (err) {
logger.error('Failed to read chat event head on attach', { sessionId, error: String(err) });
}
sendToClient(ws, {
type: 'sync:live',
sessionId,
isGenerating,
cursor,
// Whatever the agent had typed but not yet finished as a message. The transcript on disk cannot
// supply it — the harness writes an assistant message only once it is complete — so this is the one
// piece of the turn a refresh would otherwise genuinely lose.
streamingText: session.streamBuffer,
});
logger.info('Attached socket to live session by transcript id', { sessionId, claudeSessionId, isGenerating });
}
/**
* The client came back still believing a turn is running. Check whether it is, and if it isn't, say so.
*
* A restart of the agent sidecar takes its persistent sessions with it, and nothing downstream notices:
* the turn simply stops emitting. The browser's socket is fine, the conversation looks alive, and the
* spinner runs forever — a refresh doesn't help either, because there is no ending in the transcript to
* read. This is the one moment we can catch it, so the answer is written durably: a reload after this
* shows the same explanation rather than a conversation that trails off mid-tool-call.
*
* Only the claude harness is asked. OpenCode runs a turn per invocation and has no equivalent question,
* so its sessions are left alone rather than guessed at.
*/
async function endTurnIfAgentIsGone(
ws: ServerWebSocket<WSData> | null,
sessionId: string,
model: string,
): Promise<void> {
if (!isClaudeModel(model)) return;
if (await sidecar.isClaudeGenerating(sessionId)) return;
const session = sessionManager.getSession(sessionId);
if (session) session.isGenerating = false;
const event: ServerMessage = { type: 'cut-off' };
try {
const seq = await appendChatEvent(sessionId, event);
sendToClient(ws, event, seq);
} catch (err) {
// Still tell this client — an un-replayable explanation beats a spinner that never stops.
logger.error('Failed to persist cut-off notice', { sessionId, error: String(err) });
sendToClient(ws, event);
}
logger.info('Ended a turn whose agent had gone', { sessionId });
}
// The other half of the same problem: the agent restarts while the browser sits there with a healthy
// socket, so nothing ever reconnects and nothing ever asks. A fresh agent process means every turn we
// still believe is running belongs to a process that no longer exists. On a fresh officer this loop is
// empty — it has no sessions yet — which is exactly right, because that case is the reconnect's to catch.
sidecar.onClaudeSidecarStarted(() => {
for (const session of sessionManager.getAllSessions()) {
if (!session.isGenerating) continue;
void endTurnIfAgentIsGone(session.ws as ServerWebSocket<WSData> | null, session.sessionId, session.model);
}
});
export const chatWebsocket = {
open,
message,
close,
drain() {},
};