Merge remote-tracking branch 'origin/staging' into v2-architecture

This commit is contained in:
2026-03-22 14:33:59 -07:00
96 changed files with 12606 additions and 1383 deletions
+87 -3
View File
@@ -162,7 +162,7 @@ pub struct AgentDeps {
/// HTTP interceptor for trace recording/replay.
pub http_interceptor: Option<Arc<dyn crate::llm::recording::HttpInterceptor>>,
/// Audio transcription middleware for voice messages.
pub transcription: Option<Arc<crate::transcription::TranscriptionMiddleware>>,
pub transcription: Option<Arc<crate::llm::transcription::TranscriptionMiddleware>>,
/// Document text extraction middleware for PDF, DOCX, PPTX, etc.
pub document_extraction: Option<Arc<crate::document_extraction::DocumentExtractionMiddleware>>,
/// Sandbox readiness state for full-job routine dispatch.
@@ -1160,8 +1160,92 @@ impl Agent {
// Process based on submission type
let result = match submission {
Submission::UserInput { content } => {
self.process_user_input(message, session, thread_id, &content)
.await
let mut result = self
.process_user_input(message, session.clone(), thread_id, &content)
.await;
// Drain any messages queued during processing.
// Messages are merged (newline-separated) so the LLM receives
// full context from rapid consecutive inputs instead of
// processing each as a separate turn with partial context (#259).
//
// Only `Response` continues the drain — the user got a normal
// reply and there may be more queued messages to process.
//
// Everything else stops the loop:
// - `NeedApproval`: thread is blocked on user approval
// - `Interrupted`: turn was cancelled
// - `Ok`: control-command acknowledgment (including the "queued"
// ack returned when a message arrives during Processing)
// - `Error`: soft error — draining more messages after an error
// would produce confusing interleaved output
// - `Err(_)`: hard error
while let Ok(SubmissionResult::Response { content: outgoing }) = &result {
let merged = {
let mut sess = session.lock().await;
sess.threads
.get_mut(&thread_id)
.and_then(|t| t.drain_pending_messages())
};
let Some(next_content) = merged else {
break;
};
tracing::debug!(
thread_id = %thread_id,
merged_len = next_content.len(),
"Drain loop: processing merged queued messages"
);
// Send the completed turn's response before starting the next.
//
// Known limitations:
// - One-shot channels (HttpChannel) consume the response
// sender on the first respond() call keyed by msg.id.
// Subsequent calls (including the outer handler's final
// respond) are silently dropped. For one-shot channels
// only this intermediate response is delivered.
// - All drain-loop responses are routed via the original
// `message`, so channels that key routing on message
// identity will attribute every response to the first
// message. This is acceptable for the current
// single-user-per-thread model.
if let Err(e) = self
.channels
.respond(message, OutgoingResponse::text(outgoing.clone()))
.await
{
tracing::warn!(
thread_id = %thread_id,
"Failed to send intermediate drain-loop response: {e}"
);
}
// Process merged queued messages as a single turn.
// Use a message clone with cleared attachments so
// augment_with_attachments doesn't re-apply the original
// message's attachments to unrelated queued text.
let mut queued_msg = message.clone();
queued_msg.attachments.clear();
result = self
.process_user_input(&queued_msg, session.clone(), thread_id, &next_content)
.await;
// If processing failed, re-queue the drained content so it
// isn't lost. It will be picked up on the next successful turn.
if !matches!(&result, Ok(SubmissionResult::Response { .. })) {
let mut sess = session.lock().await;
if let Some(thread) = sess.threads.get_mut(&thread_id) {
thread.requeue_drained(next_content);
tracing::debug!(
thread_id = %thread_id,
"Re-queued drained content after non-Response result"
);
}
}
}
result
}
Submission::SystemCommand { command, args } => {
tracing::debug!(
+16 -3
View File
@@ -6,6 +6,7 @@
//! via the `LoopDelegate` trait.
use async_trait::async_trait;
use std::borrow::Cow;
use crate::agent::session::PendingApproval;
use crate::error::Error;
@@ -235,12 +236,12 @@ pub async fn run_agentic_loop(
///
/// `max` is a byte budget. The result is truncated at the last valid char
/// boundary at or before `max` bytes, so it is always valid UTF-8.
pub fn truncate_for_preview(s: &str, max: usize) -> String {
pub fn truncate_for_preview(s: &str, max: usize) -> Cow<'_, str> {
if s.len() <= max {
s.to_string()
Cow::Borrowed(s)
} else {
let end = crate::util::floor_char_boundary(s, max);
format!("{}...", &s[..end])
Cow::Owned(format!("{}...", &s[..end]))
}
}
@@ -597,12 +598,24 @@ mod tests {
assert_eq!(truncate_for_preview("hello", 10), "hello");
}
#[test]
fn test_truncate_short_string_borrows() {
let result = truncate_for_preview("hello", 10);
assert!(matches!(result, Cow::Borrowed("hello")));
}
#[test]
fn test_truncate_long_string_adds_ellipsis() {
let result = truncate_for_preview("hello world", 5);
assert_eq!(result, "hello...");
}
#[test]
fn test_truncate_long_string_owns() {
let result = truncate_for_preview("hello world", 5);
assert!(matches!(result, Cow::Owned(_)));
}
#[test]
fn test_truncate_multibyte_safe() {
let result = truncate_for_preview("café", 4);
+37 -20
View File
@@ -317,7 +317,7 @@ impl<'a> LoopDelegate for ChatDelegate<'a> {
.channels
.send_status(
&self.message.channel,
StatusUpdate::Thinking("Calling LLM...".into()),
StatusUpdate::Thinking(format!("Thinking (step {iteration})...")),
&self.message.metadata,
)
.await;
@@ -435,7 +435,7 @@ impl<'a> LoopDelegate for ChatDelegate<'a> {
.channels
.send_status(
&self.message.channel,
StatusUpdate::Thinking(format!("Executing {} tool(s)...", tool_calls.len())),
StatusUpdate::Thinking(contextual_tool_message(&tool_calls)),
&self.message.metadata,
)
.await;
@@ -845,11 +845,9 @@ impl<'a> LoopDelegate for ChatDelegate<'a> {
Ok(output) => {
let sanitized =
self.agent.safety().sanitize_tool_output(&tc.name, &output);
self.agent.safety().wrap_for_llm(
&tc.name,
&sanitized.content,
sanitized.was_modified,
)
self.agent
.safety()
.wrap_for_llm(&tc.name, &sanitized.content)
}
Err(e) => format!("Tool '{}' failed: {}", tc.name, e),
};
@@ -971,6 +969,30 @@ pub(super) fn check_auth_required(
Some((name, instructions))
}
/// Build a contextual thinking message based on tool names.
///
/// Instead of a generic "Executing 2 tool(s)..." this returns messages like
/// "Running command..." or "Fetching page..." for single-tool calls, falling
/// back to "Executing N tool(s)..." for multi-tool calls.
fn contextual_tool_message(tool_calls: &[crate::llm::ToolCall]) -> String {
if tool_calls.len() == 1 {
match tool_calls[0].name.as_str() {
"shell" => "Running command...".into(),
"web_fetch" => "Fetching page...".into(),
"memory_search" => "Searching memory...".into(),
"memory_write" => "Writing to memory...".into(),
"memory_read" => "Reading memory...".into(),
"http_request" => "Making HTTP request...".into(),
"file_read" => "Reading file...".into(),
"file_write" => "Writing file...".into(),
"json_transform" => "Transforming data...".into(),
name => format!("Running {name}..."),
}
} else {
format!("Executing {} tool(s)...", tool_calls.len())
}
}
/// Compact messages for retry after a context-length-exceeded error.
///
/// Keeps all `System` messages (which carry the system prompt and instructions),
@@ -1246,9 +1268,10 @@ mod tests {
#[test]
fn test_shell_destructive_command_requires_explicit_approval() {
// requires_explicit_approval() detects destructive commands that
// should return ApprovalRequirement::Always from ShellTool.
use crate::tools::builtin::shell::requires_explicit_approval;
// classify_command_risk() classifies destructive commands as High, which
// maps to ApprovalRequirement::Always in ShellTool::requires_approval().
use crate::tools::RiskLevel;
use crate::tools::builtin::shell::classify_command_risk;
let destructive_cmds = [
"rm -rf /tmp/test",
@@ -1256,20 +1279,14 @@ mod tests {
"git reset --hard HEAD~5",
];
for cmd in &destructive_cmds {
assert!(
requires_explicit_approval(cmd),
"'{}' should require explicit approval",
cmd
);
let r = classify_command_risk(cmd);
assert_eq!(r, RiskLevel::High, "'{}'", cmd); // safety: test code
}
let safe_cmds = ["git status", "cargo build", "ls -la"];
for cmd in &safe_cmds {
assert!(
!requires_explicit_approval(cmd),
"'{}' should not require explicit approval",
cmd
);
let r = classify_command_risk(cmd);
assert_ne!(r, RiskLevel::High, "'{}'", cmd); // safety: test code
}
}
+2 -2
View File
@@ -529,8 +529,8 @@ pub fn normalize_cron_expression(schedule: &str) -> String {
let trimmed = schedule.trim();
let fields: Vec<&str> = trimmed.split_whitespace().collect();
match fields.len() {
5 => format!("0 {} *", trimmed),
6 => format!("{} *", trimmed),
5 => format!("0 {} *", fields.join(" ")),
6 => format!("{} *", fields.join(" ")),
_ => trimmed.to_string(),
}
}
+2 -10
View File
@@ -1557,20 +1557,12 @@ async fn execute_lightweight_with_tools(
let result_content = match result {
Ok(output) => {
let sanitized = ctx.safety.sanitize_tool_output(&tc.name, &output);
ctx.safety.wrap_for_llm(
&tc.name,
&sanitized.content,
sanitized.was_modified,
)
ctx.safety.wrap_for_llm(&tc.name, &sanitized.content)
}
Err(e) => {
let error_msg = format!("Tool '{}' failed: {}", tc.name, e);
let sanitized = ctx.safety.sanitize_tool_output(&tc.name, &error_msg);
ctx.safety.wrap_for_llm(
&tc.name,
&sanitized.content,
sanitized.was_modified,
)
ctx.safety.wrap_for_llm(&tc.name, &sanitized.content)
}
};
+216 -2
View File
@@ -10,7 +10,7 @@
//! - Compaction: Summarize old turns to save context
//! - Resume: Continue from a saved checkpoint
use std::collections::{HashMap, HashSet};
use std::collections::{HashMap, HashSet, VecDeque};
use chrono::{DateTime, TimeDelta, Utc};
use serde::{Deserialize, Serialize};
@@ -222,8 +222,17 @@ pub struct Thread {
/// Pending auth token request (thread is in auth mode).
#[serde(default)]
pub pending_auth: Option<PendingAuth>,
/// Messages queued while the thread was processing a turn.
#[serde(default, skip_serializing_if = "VecDeque::is_empty")]
pub pending_messages: VecDeque<String>,
}
/// Maximum number of messages that can be queued while a thread is processing.
/// 10 merged messages can produce a large combined input for the LLM, but this
/// is acceptable for the personal assistant use case where a single user sends
/// rapid follow-ups. The drain loop processes them as one newline-delimited turn.
pub const MAX_PENDING_MESSAGES: usize = 10;
impl Thread {
/// Create a new thread.
pub fn new(session_id: Uuid) -> Self {
@@ -238,6 +247,7 @@ impl Thread {
metadata: serde_json::Value::Null,
pending_approval: None,
pending_auth: None,
pending_messages: VecDeque::new(),
}
}
@@ -254,6 +264,7 @@ impl Thread {
metadata: serde_json::Value::Null,
pending_approval: None,
pending_auth: None,
pending_messages: VecDeque::new(),
}
}
@@ -272,6 +283,47 @@ impl Thread {
self.turns.last_mut()
}
/// Queue a message for processing after the current turn completes.
/// Returns `false` if the queue is at capacity ([`MAX_PENDING_MESSAGES`]).
pub fn queue_message(&mut self, content: String) -> bool {
if self.pending_messages.len() >= MAX_PENDING_MESSAGES {
return false;
}
self.pending_messages.push_back(content);
self.updated_at = Utc::now();
true
}
/// Take the next pending message from the queue.
pub fn take_pending_message(&mut self) -> Option<String> {
self.pending_messages.pop_front()
}
/// Drain all pending messages from the queue.
/// Multiple messages are joined with newlines so the LLM receives
/// full context from rapid consecutive inputs (#259).
pub fn drain_pending_messages(&mut self) -> Option<String> {
if self.pending_messages.is_empty() {
return None;
}
let parts: Vec<String> = self.pending_messages.drain(..).collect();
self.updated_at = Utc::now();
Some(parts.join("\n"))
}
/// Re-queue previously drained content at the front of the queue.
/// Used to preserve user input when the drain loop fails to process
/// merged messages (soft error, hard error, interrupt).
///
/// This intentionally bypasses [`MAX_PENDING_MESSAGES`] — the content
/// was already counted against the cap before draining. The overshoot
/// is bounded to 1 entry (the re-queued merged string) plus any new
/// messages that arrived during the failed attempt.
pub fn requeue_drained(&mut self, content: String) {
self.pending_messages.push_front(content);
self.updated_at = Utc::now();
}
/// Start a new turn with user input.
pub fn start_turn(&mut self, user_input: impl Into<String>) -> &mut Turn {
let turn_number = self.turns.len();
@@ -335,11 +387,12 @@ impl Thread {
self.pending_auth.take()
}
/// Interrupt the current turn.
/// Interrupt the current turn and discard any queued messages.
pub fn interrupt(&mut self) {
if let Some(turn) = self.turns.last_mut() {
turn.interrupt();
}
self.pending_messages.clear();
self.state = ThreadState::Interrupted;
self.updated_at = Utc::now();
}
@@ -1392,4 +1445,165 @@ mod tests {
);
assert!(tool_result_content.ends_with("..."));
}
#[test]
fn test_thread_message_queue() {
let mut thread = Thread::new(Uuid::new_v4());
// Queue is initially empty
assert!(thread.pending_messages.is_empty());
assert!(thread.take_pending_message().is_none());
// Queue messages and verify FIFO ordering
assert!(thread.queue_message("first".to_string()));
assert!(thread.queue_message("second".to_string()));
assert!(thread.queue_message("third".to_string()));
assert_eq!(thread.pending_messages.len(), 3);
assert_eq!(thread.take_pending_message(), Some("first".to_string()));
assert_eq!(thread.take_pending_message(), Some("second".to_string()));
assert_eq!(thread.take_pending_message(), Some("third".to_string()));
assert!(thread.take_pending_message().is_none());
// Fill to capacity — all 10 should succeed
for i in 0..MAX_PENDING_MESSAGES {
assert!(thread.queue_message(format!("msg-{}", i)));
}
assert_eq!(thread.pending_messages.len(), MAX_PENDING_MESSAGES);
// 11th message rejected by queue_message itself
assert!(!thread.queue_message("overflow".to_string()));
assert_eq!(thread.pending_messages.len(), MAX_PENDING_MESSAGES);
// Drain and verify order
for i in 0..MAX_PENDING_MESSAGES {
assert_eq!(thread.take_pending_message(), Some(format!("msg-{}", i)));
}
assert!(thread.take_pending_message().is_none());
}
#[test]
fn test_thread_message_queue_serialization() {
let mut thread = Thread::new(Uuid::new_v4());
// Empty queue should not appear in serialization (skip_serializing_if)
let json = serde_json::to_string(&thread).unwrap();
assert!(!json.contains("pending_messages"));
// Non-empty queue should serialize and deserialize
thread.queue_message("queued msg".to_string());
let json = serde_json::to_string(&thread).unwrap();
assert!(json.contains("pending_messages"));
assert!(json.contains("queued msg"));
let restored: Thread = serde_json::from_str(&json).unwrap();
assert_eq!(restored.pending_messages.len(), 1);
assert_eq!(restored.pending_messages[0], "queued msg");
}
#[test]
fn test_thread_message_queue_default_on_old_data() {
// Deserialization of old data without pending_messages should default to empty
let thread = Thread::new(Uuid::new_v4());
let json = serde_json::to_string(&thread).unwrap();
// The field is absent (skip_serializing_if), simulating old data
assert!(!json.contains("pending_messages"));
let restored: Thread = serde_json::from_str(&json).unwrap();
assert!(restored.pending_messages.is_empty());
}
#[test]
fn test_interrupt_clears_pending_messages() {
let mut thread = Thread::new(Uuid::new_v4());
// Start a turn so there's something to interrupt
thread.start_turn("initial input");
// Queue several messages while "processing"
thread.queue_message("queued-1".to_string());
thread.queue_message("queued-2".to_string());
thread.queue_message("queued-3".to_string());
assert_eq!(thread.pending_messages.len(), 3);
// Interrupt should clear the queue
thread.interrupt();
assert!(thread.pending_messages.is_empty());
assert_eq!(thread.state, ThreadState::Interrupted);
}
#[test]
fn test_thread_state_idle_after_full_drain() {
let mut thread = Thread::new(Uuid::new_v4());
// Simulate a full drain cycle: start turn, queue messages, complete turn,
// then drain all queued messages as a single merged turn (#259).
thread.start_turn("turn 1");
assert_eq!(thread.state, ThreadState::Processing);
thread.queue_message("queued-a".to_string());
thread.queue_message("queued-b".to_string());
// Complete the turn (simulates process_user_input finishing)
thread.complete_turn("response 1");
assert_eq!(thread.state, ThreadState::Idle);
// Drain: merge all queued messages and process as a single turn
let merged = thread.drain_pending_messages().unwrap();
assert_eq!(merged, "queued-a\nqueued-b");
thread.start_turn(&merged);
thread.complete_turn("response for merged");
// Queue is fully drained, thread is idle
assert!(thread.drain_pending_messages().is_none());
assert!(thread.pending_messages.is_empty());
assert_eq!(thread.state, ThreadState::Idle);
}
#[test]
fn test_drain_pending_messages_merges_with_newlines() {
let mut thread = Thread::new(Uuid::new_v4());
// Empty queue returns None
assert!(thread.drain_pending_messages().is_none());
// Single message returned as-is (no trailing newline)
thread.queue_message("only one".to_string());
assert_eq!(
thread.drain_pending_messages(),
Some("only one".to_string()),
);
assert!(thread.pending_messages.is_empty());
// Multiple messages joined with newlines
thread.queue_message("hey".to_string());
thread.queue_message("can you check the server".to_string());
thread.queue_message("it started 10 min ago".to_string());
assert_eq!(
thread.drain_pending_messages(),
Some("hey\ncan you check the server\nit started 10 min ago".to_string()),
);
assert!(thread.pending_messages.is_empty());
// Queue is empty after drain
assert!(thread.drain_pending_messages().is_none());
}
#[test]
fn test_requeue_drained_preserves_content_at_front() {
let mut thread = Thread::new(Uuid::new_v4());
// Re-queue into empty queue
thread.requeue_drained("failed batch".to_string());
assert_eq!(thread.pending_messages.len(), 1);
assert_eq!(thread.pending_messages[0], "failed batch");
// New messages go behind the re-queued content
thread.queue_message("new msg".to_string());
assert_eq!(thread.pending_messages.len(), 2);
// Drain should return re-queued content first (front of queue)
let merged = thread.drain_pending_messages().unwrap();
assert_eq!(merged, "failed batch\nnew msg");
}
}
+201 -9
View File
@@ -14,7 +14,7 @@ use crate::agent::compaction::ContextCompactor;
use crate::agent::dispatcher::{
AgenticLoopResult, check_auth_required, execute_chat_tool_standalone, parse_auth_result,
};
use crate::agent::session::{PendingApproval, Session, ThreadState};
use crate::agent::session::{MAX_PENDING_MESSAGES, PendingApproval, Session, ThreadState};
use crate::agent::submission::SubmissionResult;
use crate::channels::web::util::truncate_preview;
use crate::channels::{IncomingMessage, StatusUpdate};
@@ -211,14 +211,72 @@ impl Agent {
// Check thread state
match thread_state {
ThreadState::Processing => {
tracing::warn!(
message_id = %message.id,
thread_id = %thread_id,
"Thread is processing, rejecting new input"
);
return Ok(SubmissionResult::error(
"Turn in progress. Use /interrupt to cancel.",
));
let mut sess = session.lock().await;
if let Some(thread) = sess.threads.get_mut(&thread_id) {
// Re-check state under lock — the turn may have completed
// between the snapshot read and this mutable lock acquisition.
if thread.state == ThreadState::Processing {
// Reject messages with attachments — the queue stores
// text only, so attachments would be silently dropped.
if !message.attachments.is_empty() {
return Ok(SubmissionResult::error(
"Cannot queue messages with attachments while a turn is processing. \
Please resend after the current turn completes.",
));
}
// Run the same safety checks that the normal path applies
// (validation, policy, secret scan) so that blocked content
// is never stored in pending_messages or serialized.
let validation = self.safety().validate_input(content);
if !validation.is_valid {
let details = validation
.errors
.iter()
.map(|e| format!("{}: {}", e.field, e.message))
.collect::<Vec<_>>()
.join("; ");
return Ok(SubmissionResult::error(format!(
"Input rejected by safety validation: {details}",
)));
}
let violations = self.safety().check_policy(content);
if violations
.iter()
.any(|rule| rule.action == crate::safety::PolicyAction::Block)
{
return Ok(SubmissionResult::error("Input rejected by safety policy."));
}
if let Some(warning) = self.safety().scan_inbound_for_secrets(content) {
tracing::warn!(
user = %message.user_id,
channel = %message.channel,
"Queued message blocked: contains leaked secret"
);
return Ok(SubmissionResult::error(warning));
}
if !thread.queue_message(content.to_string()) {
return Ok(SubmissionResult::error(format!(
"Message queue full ({MAX_PENDING_MESSAGES}). Wait for the current turn to complete.",
)));
}
// Return `Ok` (not `Response`) so the drain loop in
// agent_loop.rs breaks — `Ok` signals a control
// acknowledgment, not a completed LLM turn.
return Ok(SubmissionResult::Ok {
message: Some(
"Message queued — will be processed after the current turn.".into(),
),
});
}
// State changed (turn completed) — fall through to process normally.
// NOTE: `sess` (the Mutex guard) is dropped at the end of
// this `Processing` match arm, releasing the session lock
// before the rest of process_user_input runs. No deadlock.
} else {
return Ok(SubmissionResult::error("Thread no longer exists."));
}
}
ThreadState::AwaitingApproval => {
tracing::warn!(
@@ -498,6 +556,33 @@ impl Agent {
.await;
}
// Emit per-turn cost summary
{
let usage = self.cost_guard().model_usage().await;
let (total_in, total_out, total_cost) =
usage
.values()
.fold((0u64, 0u64, rust_decimal::Decimal::ZERO), |acc, m| {
(
acc.0 + m.input_tokens,
acc.1 + m.output_tokens,
acc.2 + m.cost,
)
});
let _ = self
.channels
.send_status(
&message.channel,
StatusUpdate::TurnCost {
input_tokens: total_in,
output_tokens: total_out,
cost_usd: format!("${:.4}", total_cost),
},
&message.metadata,
)
.await;
}
Ok(SubmissionResult::response(response))
}
Ok(AgenticLoopResult::NeedApproval { pending }) => {
@@ -849,6 +934,7 @@ impl Agent {
.get_mut(&thread_id)
.ok_or_else(|| Error::from(crate::error::JobError::NotFound { id: thread_id }))?;
thread.turns.clear();
thread.pending_messages.clear();
thread.state = ThreadState::Idle;
// Clear undo history too
@@ -2012,6 +2098,112 @@ mod tests {
}
}
#[test]
fn test_queue_cap_rejects_at_capacity() {
use crate::agent::session::{MAX_PENDING_MESSAGES, Thread, ThreadState};
use uuid::Uuid;
let mut thread = Thread::new(Uuid::new_v4());
thread.start_turn("processing something");
assert_eq!(thread.state, ThreadState::Processing);
// Fill the queue to the cap
for i in 0..MAX_PENDING_MESSAGES {
assert!(thread.queue_message(format!("msg-{}", i)));
}
assert_eq!(thread.pending_messages.len(), MAX_PENDING_MESSAGES);
// The next message should be rejected by queue_message
assert!(!thread.queue_message("overflow".to_string()));
assert_eq!(thread.pending_messages.len(), MAX_PENDING_MESSAGES);
// Verify all drain in FIFO order
for i in 0..MAX_PENDING_MESSAGES {
assert_eq!(thread.take_pending_message(), Some(format!("msg-{}", i)));
}
assert!(thread.take_pending_message().is_none());
}
#[test]
fn test_clear_clears_pending_messages() {
use crate::agent::session::{Thread, ThreadState};
use uuid::Uuid;
let mut thread = Thread::new(Uuid::new_v4());
thread.start_turn("processing");
thread.queue_message("pending-1".to_string());
thread.queue_message("pending-2".to_string());
assert_eq!(thread.pending_messages.len(), 2);
// Simulate what process_clear does: clear turns and pending_messages
thread.turns.clear();
thread.pending_messages.clear();
thread.state = ThreadState::Idle;
assert!(thread.pending_messages.is_empty());
assert!(thread.turns.is_empty());
assert_eq!(thread.state, ThreadState::Idle);
}
#[test]
fn test_processing_arm_thread_gone_returns_error() {
// Regression: if the thread disappears between the state snapshot and the
// mutable lock, the Processing arm must return an error — not a false
// "queued" acknowledgment.
//
// Exercises the exact branch at the `else` of
// `if let Some(thread) = sess.threads.get_mut(&thread_id)`.
use crate::agent::session::{Session, Thread, ThreadState};
use uuid::Uuid;
let thread_id = Uuid::new_v4();
let session_id = Uuid::new_v4();
let mut thread = Thread::with_id(thread_id, session_id);
thread.start_turn("working");
assert_eq!(thread.state, ThreadState::Processing);
let mut session = Session::new("test-user");
session.threads.insert(thread_id, thread);
// Simulate the thread disappearing (e.g., /clear racing with queue)
session.threads.remove(&thread_id);
// The Processing arm re-locks and calls get_mut — must get None.
assert!(session.threads.get_mut(&thread_id).is_none());
// Nothing was queued anywhere — the removed thread's queue is gone.
}
#[test]
fn test_processing_arm_state_changed_does_not_queue() {
// Regression: if the thread transitions from Processing to Idle between
// the state snapshot and the mutable lock, the message must NOT be queued.
// Instead the Processing arm falls through to normal processing.
//
// Exercises the `if thread.state == ThreadState::Processing` re-check.
use crate::agent::session::{Session, Thread, ThreadState};
use uuid::Uuid;
let thread_id = Uuid::new_v4();
let session_id = Uuid::new_v4();
let mut thread = Thread::with_id(thread_id, session_id);
thread.start_turn("working");
assert_eq!(thread.state, ThreadState::Processing);
// Simulate the turn completing between snapshot and re-lock
thread.complete_turn("done");
assert_eq!(thread.state, ThreadState::Idle);
let mut session = Session::new("test-user");
session.threads.insert(thread_id, thread);
// Re-check under lock: state is Idle, so queue_message must NOT be called.
let t = session.threads.get_mut(&thread_id).unwrap();
assert_ne!(t.state, ThreadState::Processing);
// Verify nothing was queued — the fall-through path doesn't touch the queue.
assert!(t.pending_messages.is_empty());
}
// Helper function to extract the approval message without needing a full Agent instance
fn extract_approval_message(
session: &crate::agent::session::Session,