test: add 26 tests for multi-thread safety, db CRUD, concurrency, errors (#442)

* fix: use std::sync::RwLock in MessageTool to avoid runtime panic

The `requires_approval` method is synchronous but was using
`tokio::sync::RwLock` with `.await` which requires blocking the
runtime. This caused a panic:
"Cannot block the current thread from within a runtime"

Changes:
- Replace `tokio::sync::RwLock` with `std::sync::RwLock` for
  `default_channel` and `default_target` fields
- Use `unwrap_or_else(|e| e.into_inner())` to gracefully handle
  poisoned locks (recovers instead of panicking)
- Update all usages from `.read().await` to `.read().unwrap_or_else()`

The locks are short-held (just cloning strings), making std::sync::RwLock
appropriate for sync methods called from async contexts.

Fixes: "Cannot block the current thread from within a runtime" panic
when the LLM tries to send a message via the message tool.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* test: comprehensive testing improvements and fix MessageTool blocking_read panic

Fix tokio::sync::RwLock::blocking_read() panic in MessageTool::requires_approval()
under multi-threaded tokio runtimes by switching to std::sync::RwLock with poison
recovery. Add 26 new tests across 4 tiers:

Tier 1 - Multi-thread runtime safety:
- Fix MessageTool to use std::sync::RwLock instead of tokio::sync::RwLock
- 4 multi-thread tests for MessageTool::requires_approval() scenarios
- 1 multi-thread test for HttpTool credential-dependent approval
- 1 structural test exercising all core tool sync trait methods under multi-thread runtime

Tier 2 - Database CRUD coverage:
- Settings lifecycle (CRUD, bulk ops)
- Tool failure tracking (record, broken list, repair)
- Routine lifecycle (create, get, list, update, delete, runs)
- LLM call recording
- Sandbox job lifecycle (create, get, update, list, mode)
- Job events (save, list, limit)
- Estimation snapshot round-trip

Tier 3 - Concurrency:
- ToolRegistry concurrent register + read under 4-worker runtime

Tier 4 - Error coverage:
- Display tests for all 8 error variants
- From conversion tests for top-level Error enum

Supersedes the fix in PR #411 with the same bug fix plus comprehensive test coverage.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: remove trailing whitespace in registry.rs

Co-Authored-By: Claude Opus 4.6 <[email protected]>

---------

Co-authored-by: Jerome Revillard <[email protected]>
Co-authored-by: Claude Opus 4.6 <[email protected]>
Co-authored-by: Illia Polosukhin <[email protected]>
This commit is contained in:
Zaki Manian
2026-03-06 04:39:04 +00:00
committed by GitHub
co-authored by Jerome Revillard Claude Opus 4.6 Illia Polosukhin
parent 04c5c3fe9f
commit 06c84a5c77
6 changed files with 863 additions and 24 deletions
+40
View File
@@ -998,4 +998,44 @@ mod tests {
let params = serde_json::json!({"method": "GET"});
assert_eq!(extract_host_from_params(&params), None);
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn requires_approval_multi_thread_no_panic() {
use crate::secrets::CredentialMapping;
use crate::tools::wasm::SharedCredentialRegistry;
// Test with credential registry (uses std::sync::RwLock - should be safe)
let registry = Arc::new(SharedCredentialRegistry::new());
registry.add_mappings(vec![CredentialMapping::bearer("test_key", "api.test.com")]);
let tool = HttpTool::new().with_credentials(
registry,
Arc::new(crate::secrets::InMemorySecretsStore::new(Arc::new(
crate::secrets::SecretsCrypto::new(secrecy::SecretString::from(
"0123456789abcdef0123456789abcdef".to_string(),
))
.unwrap(),
))),
);
// These calls should not panic in multi-thread runtime
let params_no_auth = serde_json::json!({
"method": "GET",
"url": "https://api.example.com/data"
});
let _ = tool.requires_approval(&params_no_auth);
let params_with_cred = serde_json::json!({
"method": "GET",
"url": "https://api.test.com/v1/models"
});
let _ = tool.requires_approval(&params_with_cred);
let params_with_auth = serde_json::json!({
"method": "GET",
"url": "https://api.example.com",
"headers": {"Authorization": "Bearer token"}
});
let _ = tool.requires_approval(&params_with_auth);
}
}
+36 -24
View File
@@ -533,41 +533,53 @@ mod tests {
);
}
/// Regression test: requires_approval() is a sync method called from async context.
/// With tokio::sync::RwLock, this would panic with:
/// "Cannot block the current thread from within a runtime"
/// because blocking_read() cannot be called inside an async runtime.
/// With std::sync::RwLock, it works correctly since std locks are safe
/// for short-held locks in sync methods called from async contexts.
#[tokio::test]
async fn requires_approval_works_from_async_context() {
let tool = MessageTool::new(Arc::new(ChannelManager::new()));
// ── Multi-thread runtime safety tests ─────────────────────────────
// Set context asynchronously (simulating real usage pattern)
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn requires_approval_no_channel_multi_thread() {
let tool = MessageTool::new(Arc::new(ChannelManager::new()));
// No channel set, no channel param - should not panic in multi-thread runtime
let result = tool.requires_approval(&serde_json::json!({"content": "hello"}));
assert_eq!(result, ApprovalRequirement::UnlessAutoApproved);
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn requires_approval_with_context_multi_thread() {
let tool = MessageTool::new(Arc::new(ChannelManager::new()));
tool.set_context(Some("signal".to_string()), Some("+1234567890".to_string()))
.await;
// Call requires_approval (sync method) from async context.
// This is the critical test: with tokio::sync::RwLock::blocking_read(),
// this would panic. With std::sync::RwLock::read(), it works.
let approval = tool.requires_approval(&serde_json::json!({
// No channel param - uses default, less risky
let result = tool.requires_approval(&serde_json::json!({"content": "hello"}));
assert_eq!(result, ApprovalRequirement::UnlessAutoApproved);
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn requires_approval_cross_channel_multi_thread() {
let tool = MessageTool::new(Arc::new(ChannelManager::new()));
tool.set_context(Some("signal".to_string()), Some("+1234567890".to_string()))
.await;
// Different channel than default requires approval
let result = tool.requires_approval(&serde_json::json!({
"content": "hello",
"channel": "telegram"
}));
// Different channel from default -> Always
assert!(matches!(approval, ApprovalRequirement::Always));
assert_eq!(result, ApprovalRequirement::Always);
}
// No channel specified (uses default) -> UnlessAutoApproved
let approval = tool.requires_approval(&serde_json::json!({
"content": "hello"
}));
assert!(matches!(approval, ApprovalRequirement::UnlessAutoApproved));
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn requires_approval_same_channel_explicit_multi_thread() {
let tool = MessageTool::new(Arc::new(ChannelManager::new()));
tool.set_context(Some("signal".to_string()), Some("+1234567890".to_string()))
.await;
// Explicit channel (even if same as default) -> Always
let approval = tool.requires_approval(&serde_json::json!({
// Explicit channel that matches default still returns Always
// (existing behavior: any explicit channel param triggers Always)
let result = tool.requires_approval(&serde_json::json!({
"content": "hello",
"channel": "signal"
}));
assert!(matches!(approval, ApprovalRequirement::Always));
assert_eq!(result, ApprovalRequirement::Always);
}
}
+38
View File
@@ -765,6 +765,44 @@ mod tests {
assert_ne!(desc, "EVIL SHADOW");
}
#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
async fn concurrent_register_and_read_no_panic() {
use std::sync::Arc as StdArc;
let registry = StdArc::new(ToolRegistry::new());
registry.register_builtin_tools();
// Spawn concurrent readers and check they don't panic
let mut handles = Vec::new();
// Readers
for _ in 0..10 {
let reg = StdArc::clone(&registry);
handles.push(tokio::spawn(async move {
let tools = reg.all().await;
assert!(!tools.is_empty());
let names = reg.list().await;
assert!(!names.is_empty());
let _ = reg.get("echo").await;
let _ = reg.has("echo").await;
let _ = reg.tool_definitions().await;
}));
}
// Concurrent register attempts (will be rejected as shadowing)
for _ in 0..5 {
let reg = StdArc::clone(&registry);
handles.push(tokio::spawn(async move {
// This will be rejected (echo is protected) but should not panic
reg.register(Arc::new(EchoTool)).await;
}));
}
for handle in handles {
handle.await.expect("task should not panic");
}
}
#[tokio::test]
async fn test_tool_definitions_sorted_alphabetically() {
// Create tools with names that would NOT be alphabetical if inserted in this order.