mirror of
https://github.com/Ark0N/Codeman.git
synced 2026-10-06 07:29:42 +02:00
COD-108 auto-reconnect remote tmux sessions on SSH drop
Continuous remote-only reconnect watcher closing the COD-104 durability arc: when a remote session's local ssh pane dies mid-run, re-establish it automatically instead of leaving a dead pane until the user pokes it. Design decisions (per cod108 design doc): - D1 event->owner: TmuxManager watcher DETECTS a dead remote pane and emits `remoteSessionDropped`; the session owner (server) reassembles the same RespawnPaneOptions and calls Session.reattachRemote() -> respawnPane, which re-runs the idempotent remote command (owned new-session -A / non-owned attach) and REJOINS the still-running durable remote tmux session. The watcher never reassembles options itself, and never routes through the Claude-idle respawn-controller. - D2 bounded backoff: per-session exponential backoff [5s,15s,45s,2m,5m,5m], reset on a successful reattach, `remoteReconnectExhausted` emitted once after the cap. Pure, unit-tested schedule + eligibility decision. - D3 always-on + kill-switch: `remoteAutoReconnect` app setting (default ON), read each tick; when false the watcher does nothing. Guards: killSession() (incl. the non-owned DETACH early-return) and shutdown add the session to an intentional-teardown guard set + clear its backoff BEFORE teardown, so a closed/killed tab is never auto-revived. Exactly one reconnect in flight per session (inFlight guard prevents stacked respawns). Per-session reconnect/guard state cleared on session removal. New: src/remote-reconnect.ts (pure backoff + decideReconnect), TmuxManager startRemoteReconnectWatcher/stop + runRemoteReconnectTick + noteRemoteReconnect + guardRemoteReconnect + clearRemoteReconnectState; Session.reattachRemote() (+ extracted _buildRespawnPaneOptions, shared with interactive start); server wiring + watcher start; 3 SSE events (sse-events.ts + constants.js in sync, broadcast + app.js exhausted "Reconnect" affordance); remoteAutoReconnect schema + settings-ui toggle. Tests: test/remote-auto-reconnect.test.ts (21) - pure schedule, eligibility (guarded never reconnects, non-remote/pane-alive/not-due skip, over-cap exhaust), and manager-level integration (dead remote pane -> dropped -> backoff -> exhausted; guarded emits nothing; reset-on-success; kill-switch off; state-cleared-on-remove). Verified real-remote against aa-desktop: drop local ssh pane -> watcher emitted -> respawnPane reattached the SAME remote session (remote pane_pid unchanged 3939->3939); test session cleaned up, the real host sessions left untouched. Checks: tsc, eslint, check:frontend-syntax, check:public-assets, prettier --check, build all green; tmux-manager/session-routes/session-manager/ sse-registry-parity suites pass. (cherry picked from commit d13d58b1994eb6594fd2eadea208104d36204f9d)
This commit is contained in:
+64
-17
@@ -1211,6 +1211,68 @@ export class Session extends EventEmitter {
|
||||
return { isRestored };
|
||||
}
|
||||
|
||||
/**
|
||||
* COD-108 — re-establish a dropped REMOTE session. Triggered by the
|
||||
* `TmuxManager` remote-reconnect watcher (via `remoteSessionDropped`): the
|
||||
* watcher detects a dead remote pane, the session owner reassembles the SAME
|
||||
* `RespawnPaneOptions` used for Claude-idle respawns and calls
|
||||
* `respawnPane()` directly. For a remote session that re-runs
|
||||
* `buildRemoteSessionCommand` (owned → `new-session -A`, non-owned →
|
||||
* `attach`), which idempotently REATTACHES the still-running durable remote
|
||||
* tmux session — scrollback + agent intact (proven COD-104/105).
|
||||
*
|
||||
* Deliberately does NOT route through the Claude-idle respawn-controller —
|
||||
* this is a transport re-establish, not a `/clear`/`/compact` cycle.
|
||||
*
|
||||
* @returns true if the pane was respawned (reattach issued), false otherwise.
|
||||
*/
|
||||
async reattachRemote(): Promise<boolean> {
|
||||
if (!this._remote) return false; // not a remote session
|
||||
if (!this._useMux || !this._mux || !this._muxSession) return false;
|
||||
const mux = this._mux;
|
||||
|
||||
// If tmux lost the whole session (not just a dead pane), there is nothing to
|
||||
// respawn into — a genuine death, leave it for normal recovery/reconcile.
|
||||
if (!mux.muxSessionExists(this._muxSession.muxName)) {
|
||||
console.log('[Session] reattachRemote: mux session gone, skipping:', this._muxSession.muxName);
|
||||
return false;
|
||||
}
|
||||
|
||||
const newPid = await mux.respawnPane(this._buildRespawnPaneOptions());
|
||||
if (!newPid) {
|
||||
console.error('[Session] reattachRemote: respawnPane failed for', this._muxSession.muxName);
|
||||
return false;
|
||||
}
|
||||
console.log('[Session] reattachRemote: reattached remote session', this._muxSession.muxName, 'pid', newPid);
|
||||
return true;
|
||||
}
|
||||
|
||||
/**
|
||||
* Assemble the {@link RespawnPaneOptions} for this session. Single source of
|
||||
* truth shared by interactive start, shell start (via their inline copies),
|
||||
* and {@link reattachRemote} so the remote reattach path can never drift from
|
||||
* the spawn path.
|
||||
*/
|
||||
private _buildRespawnPaneOptions(): import('./mux-interface.js').RespawnPaneOptions {
|
||||
return {
|
||||
sessionId: this.id,
|
||||
workingDir: this.workingDir,
|
||||
mode: this.mode,
|
||||
niceConfig: this._niceConfig,
|
||||
model: this._model,
|
||||
claudeMode: this._claudeMode,
|
||||
allowedTools: this._allowedTools,
|
||||
openCodeConfig: this._openCodeConfig,
|
||||
codexConfig: this._codexConfig,
|
||||
geminiConfig: this._geminiConfig,
|
||||
resumeSessionId: this._resumeSessionId,
|
||||
envOverrides: this._envOverrides,
|
||||
effort: this._effort,
|
||||
historyLimit: this._tmuxHistoryLimit,
|
||||
remote: this._remote,
|
||||
};
|
||||
}
|
||||
|
||||
private _handleTerminalOutput(data: string): void {
|
||||
// Codex AND Claude Code emit sequences that wipe xterm.js scrollback, plus
|
||||
// mouse-tracking enables that hijack the scroll wheel so the user can't reach
|
||||
@@ -1334,23 +1396,8 @@ export class Session extends EventEmitter {
|
||||
if (this._useMux && this._mux) {
|
||||
try {
|
||||
const { isRestored } = await this._setupOrAttachMuxSession({
|
||||
respawnPaneOptions: {
|
||||
sessionId: this.id,
|
||||
workingDir: this.workingDir,
|
||||
mode: this.mode,
|
||||
niceConfig: this._niceConfig,
|
||||
model: this._model,
|
||||
claudeMode: this._claudeMode,
|
||||
allowedTools: this._allowedTools,
|
||||
openCodeConfig: this._openCodeConfig,
|
||||
codexConfig: this._codexConfig,
|
||||
geminiConfig: this._geminiConfig,
|
||||
resumeSessionId: this._resumeSessionId,
|
||||
envOverrides: this._envOverrides,
|
||||
effort: this._effort,
|
||||
historyLimit: this._tmuxHistoryLimit,
|
||||
remote: this._remote,
|
||||
},
|
||||
// Single source of truth shared with reattachRemote() (COD-108).
|
||||
respawnPaneOptions: this._buildRespawnPaneOptions(),
|
||||
createSessionOptions: {
|
||||
sessionId: this.id,
|
||||
workingDir: this.workingDir,
|
||||
|
||||
Reference in New Issue
Block a user