feat(884): persistent perm_rx lock-holder for Matrix bot

Before: handle_message.rs acquired services.perm_rx only while processing
one chat message and dropped it on chat_fut completion. The moment the
bot wasn't actively responding, prompt_permission auto-denied any spawned
coder bash call as "no interactive session" — making unattended coder
work impossible.

Now: a permission_listener task is spawned at bot startup and holds
perm_rx for the bot's lifetime. Permission requests are forwarded to
the first configured Matrix room, replies resolved by the existing
on_room_message handler via pending_perm_replies. Per-message acquire is
gone from handle_message.rs (chat_fut just awaits cleanly).

- New module: chat/transport/matrix/bot/permission_listener.rs.
- Wired into run_bot before BotContext construction; bot_sent_event_ids
  is hoisted out so the listener and the rest of the bot share it.
- handle_message.rs no longer touches perm_rx.
- diagnostics/permission.rs comment updated to reflect the new reality.
- Regression test asserts the listener forwards a PermissionForward to
  the target room and records the pending reply key — exactly the path
  that was broken when no chat_fut was in flight.

Discord/Slack/WhatsApp transports still acquire perm_rx per message
(commands.rs:368 / commands/llm.rs:83 / commands/llm.rs:82). They are
not the active transport in this deployment so their per-message acquire
remains dormant; the same listener pattern should be applied to them as
follow-up work in 884 phase 2.
This commit is contained in:
dave
2026-04-30 13:53:46 +00:00
parent 0e4a970e3a
commit 7ac3fc2e3e
5 changed files with 267 additions and 68 deletions
@@ -2,13 +2,11 @@
//! streams the assistant reply back to the room.
use crate::chat::util::drain_complete_paragraphs;
use crate::http::context::PermissionDecision;
use crate::llm::providers::claude_code::{ClaudeCodeProvider, ClaudeCodeResult};
use crate::slog;
use matrix_sdk::ruma::OwnedRoomId;
use std::sync::Arc;
use std::sync::atomic::{AtomicBool, Ordering};
use std::time::Duration;
use tokio::sync::watch;
use super::super::context::BotContext;
@@ -113,64 +111,10 @@ pub(in crate::chat::transport::matrix::bot) async fn handle_message(
);
tokio::pin!(chat_fut);
// Lock the permission receiver for the duration of this chat session.
// Permission requests from the MCP `prompt_permission` tool arrive here.
let mut perm_rx_guard = ctx.services.perm_rx.lock().await;
let result = loop {
tokio::select! {
r = &mut chat_fut => break r,
Some(perm_fwd) = perm_rx_guard.recv() => {
// Post the permission prompt to the room via the transport.
let prompt_msg = format!(
"**Permission Request**\n\n\
Tool: `{}`\n```json\n{}\n```\n\n\
Reply **yes** to approve or **no** to deny.",
perm_fwd.tool_name,
serde_json::to_string_pretty(&perm_fwd.tool_input)
.unwrap_or_else(|_| perm_fwd.tool_input.to_string()),
);
let html = markdown_to_html(&prompt_msg);
if let Ok(msg_id) = ctx.transport.send_message(&room_id_str, &prompt_msg, &html).await
&& let Ok(event_id) = msg_id.parse()
{
sent_ids.lock().await.insert(event_id);
}
// Store the MCP oneshot sender so the event handler can
// resolve it when the user replies yes/no.
ctx.services.pending_perm_replies
.lock()
.await
.insert(room_id.to_string(), perm_fwd.response_tx);
// Spawn a timeout task: auto-deny if the user does not respond.
let pending = Arc::clone(&ctx.services.pending_perm_replies);
let timeout_room_id = room_id.to_string();
let timeout_transport = Arc::clone(&ctx.transport);
let timeout_room_id_str = room_id_str.clone();
let timeout_sent_ids = Arc::clone(&ctx.bot_sent_event_ids);
let timeout_secs = ctx.services.permission_timeout_secs;
tokio::spawn(async move {
tokio::time::sleep(Duration::from_secs(timeout_secs)).await;
if let Some(tx) = pending.lock().await.remove(&timeout_room_id) {
let _ = tx.send(PermissionDecision::Deny);
let msg = "Permission request timed out — denied (fail-closed).";
let html = markdown_to_html(msg);
if let Ok(msg_id) = timeout_transport
.send_message(&timeout_room_id_str, msg, &html)
.await
&& let Ok(event_id) = msg_id.parse()
{
timeout_sent_ids.lock().await.insert(event_id);
}
}
});
}
}
};
drop(perm_rx_guard);
// Permission requests are handled by the persistent permission_listener
// task spawned at bot startup (story 884) — they no longer route through
// per-message handlers. Just await chat_fut.
let result = (&mut chat_fut).await;
// Flush any remaining text that didn't end with a paragraph boundary.
let remaining = buffer.lock().unwrap().trim().to_string();