Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
138 changes: 138 additions & 0 deletions tests/e2e_advanced_traces.rs
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,10 @@ mod support;
mod advanced {
use std::time::Duration;

use ironclaw::agent::routine::Trigger;
use ironclaw::channels::IncomingMessage;
use ironclaw::db::Database;

use crate::support::cleanup::CleanupGuard;
use crate::support::test_rig::TestRigBuilder;
use crate::support::trace_llm::LlmTrace;
Expand All @@ -19,6 +23,28 @@ mod advanced {
);
const TIMEOUT: Duration = Duration::from_secs(30);

async fn wait_for_routine_run(
db: &std::sync::Arc<dyn Database>,
routine_id: uuid::Uuid,
timeout: Duration,
) -> Vec<ironclaw::agent::routine::RoutineRun> {
let deadline = tokio::time::Instant::now() + timeout;
loop {
let runs = db
.list_routine_runs(routine_id, 10)
.await
.expect("list_routine_runs");
if !runs.is_empty() {
return runs;
}
assert!(
tokio::time::Instant::now() < deadline,
"timed out waiting for routine run"
);
tokio::time::sleep(Duration::from_millis(100)).await;
}
}

// -----------------------------------------------------------------------
// 1. Multi-turn memory coherence
// -----------------------------------------------------------------------
Expand Down Expand Up @@ -380,6 +406,118 @@ mod advanced {
rig.shutdown();
}

// -----------------------------------------------------------------------
// 6b. Event routine: Telegram-scoped trigger fires on matching message
// -----------------------------------------------------------------------

#[tokio::test]
async fn routine_event_trigger_telegram_channel_fires() {
let trace = LlmTrace::from_file(format!("{FIXTURES}/routine_event_telegram.json")).unwrap();
let rig = TestRigBuilder::new()
.with_trace(trace.clone())
.with_routines()
.with_auto_approve_tools(true)
.build()
.await;

rig.send_message(
"Create a routine that watches Telegram messages starting with 'bug:' and alerts me.",
)
.await;
let create_responses = rig.wait_for_responses(1, TIMEOUT).await;
rig.verify_trace_expects(&trace, &create_responses);

let routine = rig
.database()
.get_routine_by_name("test-user", "telegram-bug-watcher")
.await
.expect("get_routine_by_name")
.expect("telegram-bug-watcher should exist");

match &routine.trigger {
Trigger::Event { channel, pattern } => {
assert_eq!(channel.as_deref(), Some("telegram"));
assert_eq!(pattern, "^bug\\b");
}
other => panic!("expected event trigger, got {other:?}"),
}

rig.send_incoming(IncomingMessage::new(
"telegram",
"test-user",
"bug: home button broken",
))
.await;

let runs = wait_for_routine_run(rig.database(), routine.id, TIMEOUT).await;
assert_eq!(runs[0].trigger_type, "event");

let responses = rig.wait_for_responses(3, TIMEOUT).await;
assert!(
responses.iter().any(|response| {
response
.metadata
.get("source")
.and_then(|value| value.as_str())
== Some("routine")
&& response.content.contains("telegram-bug-watcher")
&& response.content.contains("Bug report detected")
}),
"expected routine notification in responses: {responses:?}"
);

rig.shutdown();
}

// -----------------------------------------------------------------------
// 6c. Event routine without channel filter still fires on Telegram
// -----------------------------------------------------------------------

#[tokio::test]
async fn routine_event_trigger_without_channel_filter_still_fires() {
let trace =
LlmTrace::from_file(format!("{FIXTURES}/routine_event_any_channel.json")).unwrap();
let rig = TestRigBuilder::new()
.with_trace(trace)
.with_routines()
.with_auto_approve_tools(true)
.build()
.await;

rig.send_message(
"Create a routine that watches messages starting with 'bug:' and alerts me.",
)
.await;
let _ = rig.wait_for_responses(1, TIMEOUT).await;

let routine = rig
.database()
.get_routine_by_name("test-user", "any-channel-bug-watcher")
.await
.expect("get_routine_by_name")
.expect("any-channel-bug-watcher should exist");

match &routine.trigger {
Trigger::Event { channel, pattern } => {
assert_eq!(channel, &None);
assert_eq!(pattern, "^bug\\b");
}
other => panic!("expected event trigger, got {other:?}"),
}

rig.send_incoming(IncomingMessage::new(
"telegram",
"test-user",
"bug: login button broken",
))
.await;

let runs = wait_for_routine_run(rig.database(), routine.id, TIMEOUT).await;
assert_eq!(runs[0].trigger_type, "event");

rig.shutdown();
}

// -----------------------------------------------------------------------
// 7. Prompt injection resilience
// -----------------------------------------------------------------------
Expand Down
54 changes: 54 additions & 0 deletions tests/fixtures/llm_traces/advanced/routine_event_any_channel.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,54 @@
{
"model_name": "advanced-routine-event-any-channel",
"expects": {
"tools_used": ["routine_create"],
"all_tools_succeeded": true,
"min_responses": 1
},
"steps": [
{
"response": {
"type": "tool_calls",
"tool_calls": [
{
"id": "call_routine_create_event_any_channel",
"name": "routine_create",
"arguments": {
"name": "any-channel-bug-watcher",
"description": "Watch bug reports from any incoming channel.",
"trigger_type": "event",
"event_pattern": "^bug\\b",
"prompt": "Summarize the bug report in one line."
}
}
],
"input_tokens": 130,
"output_tokens": 38
}
},
{
"response": {
"type": "text",
"content": "Created the any-channel-bug-watcher routine for bug messages.",
"input_tokens": 170,
"output_tokens": 18
}
},
{
"response": {
"type": "text",
"content": "I saw the Telegram message.",
"input_tokens": 90,
"output_tokens": 12
}
},
{
"response": {
"type": "text",
"content": "Bug report detected: login button broken.",
"input_tokens": 120,
"output_tokens": 14
}
}
]
}
55 changes: 55 additions & 0 deletions tests/fixtures/llm_traces/advanced/routine_event_telegram.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,55 @@
{
"model_name": "advanced-routine-event-telegram",
"expects": {
"tools_used": ["routine_create"],
"all_tools_succeeded": true,
"min_responses": 1
},
"steps": [
{
"response": {
"type": "tool_calls",
"tool_calls": [
{
"id": "call_routine_create_event_telegram",
"name": "routine_create",
"arguments": {
"name": "telegram-bug-watcher",
"description": "Watch Telegram bug reports and alert on them.",
"trigger_type": "event",
"event_channel": "telegram",
"event_pattern": "^bug\\b",
"prompt": "Summarize the bug report in one line."
}
}
],
"input_tokens": 140,
"output_tokens": 40
}
},
{
"response": {
"type": "text",
"content": "Created the telegram-bug-watcher routine for Telegram bug messages.",
"input_tokens": 180,
"output_tokens": 20
}
},
{
"response": {
"type": "text",
"content": "I saw the Telegram message.",
"input_tokens": 90,
"output_tokens": 12
}
},
{
"response": {
"type": "text",
"content": "Bug report detected: home button broken.",
"input_tokens": 120,
"output_tokens": 14
}
}
]
}
Loading