Compare commits

...
Author SHA1 Message Date
ZakiandClaude Opus 4.6 9cb64dd8a7 fix: clarify test comment and use exact assertions
Address Gemini review feedback:
- Fix misleading comment: \u{00e9} is precomposed e-acute, not combining accent
- Replace weak assertions (ends_with/is_empty) with exact assert_eq!

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
2026-03-26 16:56:56 -07:00
ZakiandClaude Opus 4.6 6198c98673 fix: prevent UTF-8 panics in byte-index string truncation
Replace unsafe `&s[..n]` patterns with `floor_char_boundary(s, n)` at 3
production code sites where the truncation index could land mid-multibyte
character, panicking on non-ASCII input:

- src/llm/nearai_chat.rs: API response truncation in error message
- src/cli/memory.rs: memory content display truncation
- src/cli/config.rs: config value display truncation

All 3 sites operate on external or user-supplied strings that may contain
non-ASCII characters. The existing `crate::util::floor_char_boundary`
utility (used at 18 other call sites) walks back to the nearest char
boundary, preventing the panic.

Adds regression test with multi-byte characters (combining accents and
4-byte emoji) for truncate_content.

[skip-regression-check]

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
2026-03-26 16:34:14 -07:00
dd0a0e10ab fix(routines): recover delete name after failed update fallback (#1108)
Co-authored-by: [email protected] <[email protected]>
Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>
2026-03-26 16:20:01 -07:00
1d5777824c fix(mcp): handle 202 Accepted and wire session manager for Streamable HTTP (#1437)
* fix(mcp): handle 202 Accepted for Streamable HTTP notifications

The MCP Streamable HTTP spec requires servers to respond with
202 Accepted (empty body) for JSON-RPC notifications like
`notifications/initialized`. The HTTP transport tried to parse
this empty body as JSON, which failed and broke the session
handshake — subsequent requests like `tools/list` were rejected
because the server considered the session uninitialized.

Add an early return for 202 responses that produces an empty
McpResponse without attempting body parsing.

Fixes #1436

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* fix(mcp): wire session manager into transport for non-OAuth HTTP clients

The factory used McpClient::new_with_config().with_session_manager()
which only set the session manager on the client, not on the
HttpMcpTransport. The transport never captured Mcp-Session-Id from
responses, so subsequent requests lacked the header and the server
rejected them as uninitialized.

Fix by constructing the HttpMcpTransport with the session manager
before wrapping it in Arc, matching the pattern already used by
new_authenticated().

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* refactor(mcp): deduplicate factory HTTP path, gate dead-code methods as test-only

- Collapse the two identical non-OAuth HTTP branches in
  `create_client_from_config()` into one (early-return for the
  authenticated path, fall through for the common case).
- Gate `McpClient::new_with_config()` and `McpClient::with_session_manager()`
  as `#[cfg(test)]` — the factory was their only production caller and no
  longer uses them. Both methods silently skip wiring the session manager
  into the transport, which was the root cause of #1436.
- Add doc warnings on both methods explaining the footgun.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>
Co-authored-by: [email protected] <[email protected]>
2026-03-26 14:47:31 -07:00
10 changed files with 314 additions and 26 deletions
+2 -1
View File
@@ -127,7 +127,8 @@ async fn list_settings(
}
let display_value = if value.len() > 60 {
format!("{}...", &value[..57])
let end = crate::util::floor_char_boundary(&value, 57);
format!("{}...", &value[..end])
} else {
value
};
+15 -1
View File
@@ -256,7 +256,8 @@ fn truncate_content(s: &str, max_len: usize) -> String {
if s.len() <= max_len {
s.to_string()
} else {
format!("{}...", &s[..max_len])
let end = crate::util::floor_char_boundary(s, max_len);
format!("{}...", &s[..end])
}
}
@@ -292,4 +293,17 @@ mod tests {
assert_eq!(truncate_content("hello", 10), "hello");
assert_eq!(truncate_content("hello world", 5), "hello...");
}
#[test]
fn test_truncate_content_multibyte_does_not_panic() {
// \u{00e9} is precomposed 'é' (2 bytes in UTF-8)
let s = "caf\u{00e9} au lait"; // "café au lait", é starts at byte 3
let result = truncate_content(s, 4); // byte 4 is inside 2-byte é
assert_eq!(result, "caf...");
// 4-byte emoji: slicing mid-emoji must not panic
let emoji = "Hi \u{1F600} there"; // 😀 is 4 bytes, starts at byte 3
let result = truncate_content(emoji, 4); // byte 4 is inside 😀
assert_eq!(result, "Hi ...");
}
}
+3
View File
@@ -192,6 +192,9 @@ pub struct JobContext {
/// but subsequent tools (e.g., `json`) may need the full output. This
/// stash stores the complete, unsanitized output so tools can reference
/// previous results by ID via `$tool_call_id` parameter syntax.
///
/// Also used for cross-tool implicit state (keys prefixed with `__`) such
/// as `__routine_last_name` for fallback recovery in routine tool chains.
#[serde(skip)]
pub tool_output_stash: Arc<tokio::sync::RwLock<HashMap<String, String>>>,
/// User's preferred timezone (IANA name, e.g. "America/New_York"). Defaults to "UTC".
+1 -1
View File
@@ -451,7 +451,7 @@ impl NearAiChatProvider {
provider: "nearai_chat".to_string(),
reason: format!(
"No model names found in response: {}",
&response_text[..response_text.len().min(300)]
&response_text[..crate::util::floor_char_boundary(&response_text, 300)]
),
})
}
+35 -3
View File
@@ -650,6 +650,23 @@ pub(crate) fn routine_update_parameters_schema() -> Value {
})
}
const ROUTINE_LAST_NAME_STASH_KEY: &str = "__routine_last_name";
async fn stash_last_routine_name(ctx: &JobContext, name: &str) {
ctx.tool_output_stash
.write()
.await
.insert(ROUTINE_LAST_NAME_STASH_KEY.to_string(), name.to_string());
}
async fn restore_last_routine_name(ctx: &JobContext) -> Option<String> {
ctx.tool_output_stash
.read()
.await
.get(ROUTINE_LAST_NAME_STASH_KEY)
.cloned()
}
fn nested_object<'a>(params: &'a Value, field: &str) -> Option<&'a Map<String, Value>> {
params.get(field).and_then(Value::as_object)
}
@@ -1093,6 +1110,7 @@ impl Tool for RoutineCreateTool {
) -> Result<ToolOutput, ToolError> {
let start = std::time::Instant::now();
let normalized = parse_routine_create_request(&params)?;
stash_last_routine_name(ctx, &normalized.name).await;
let trigger = build_routine_trigger(&normalized.trigger);
let action =
build_routine_action(&normalized.name, &normalized.prompt, &normalized.execution);
@@ -1274,6 +1292,7 @@ impl Tool for RoutineUpdateTool {
let start = std::time::Instant::now();
let name = require_str(&params, "name")?;
stash_last_routine_name(ctx, name).await;
let mut routine = self
.store
@@ -1411,11 +1430,24 @@ impl Tool for RoutineDeleteTool {
) -> Result<ToolOutput, ToolError> {
let start = std::time::Instant::now();
let name = require_str(&params, "name")?;
let name = if let Some(name) = params.get("name").and_then(|v| v.as_str()) {
if name.trim().is_empty() {
return Err(ToolError::InvalidParameters(
"'name' parameter cannot be empty".to_string(),
));
}
name.to_string()
} else {
restore_last_routine_name(ctx).await.ok_or_else(|| {
ToolError::InvalidParameters(
"missing 'name' parameter and no previous routine target to infer".to_string(),
)
})?
};
let routine = self
.store
.get_routine_by_name(&ctx.user_id, name)
.get_routine_by_name(&ctx.user_id, &name)
.await
.map_err(|e| ToolError::ExecutionFailed(format!("DB error: {e}")))?
.ok_or_else(|| ToolError::ExecutionFailed(format!("routine '{}' not found", name)))?;
@@ -1430,7 +1462,7 @@ impl Tool for RoutineDeleteTool {
self.engine.refresh_event_cache().await;
let result = serde_json::json!({
"name": name,
"name": &name,
"deleted": deleted,
});
+19 -1
View File
@@ -117,6 +117,11 @@ impl McpClient {
/// The config must use HTTP transport (the default); for stdio/UDS use `new_with_transport`.
///
/// Returns an error if the config uses a non-HTTP transport.
///
/// **Note:** The session manager is NOT wired into the transport. For
/// production use, prefer `create_client_from_config()` which constructs
/// the transport with session tracking.
#[cfg(test)]
pub fn new_with_config(config: McpServerConfig) -> Result<Self, ToolError> {
if !matches!(
config.effective_transport(),
@@ -214,7 +219,14 @@ impl McpClient {
}
}
/// Attach a session manager for Streamable HTTP session tracking.
/// Attach a session manager to the **client** only.
///
/// **Warning:** This does NOT wire the session manager into the underlying
/// `HttpMcpTransport`, so the transport will not capture `Mcp-Session-Id`
/// from responses. For production use, construct the transport with
/// `HttpMcpTransport::with_session_manager()` and pass it to
/// `new_with_transport()` instead. See `create_client_from_config()`.
#[cfg(test)]
pub fn with_session_manager(mut self, session_manager: Arc<McpSessionManager>) -> Self {
self.session_manager = Some(session_manager);
self
@@ -235,6 +247,12 @@ impl McpClient {
self.session_manager.is_some()
}
/// Get the underlying transport (test-only).
#[cfg(test)]
pub(crate) fn transport(&self) -> &Arc<dyn McpTransport> {
&self.transport
}
/// Get the next request ID.
fn next_request_id(&self) -> u64 {
self.next_id.fetch_add(1, Ordering::SeqCst)
+101 -16
View File
@@ -7,6 +7,7 @@ use std::sync::Arc;
use crate::secrets::SecretsStore;
use crate::tools::mcp::config::{EffectiveTransport, McpServerConfig};
use crate::tools::mcp::http_transport::HttpMcpTransport;
use crate::tools::mcp::{McpClient, McpProcessManager, McpSessionManager, McpTransport};
/// Error returned when MCP client creation fails.
@@ -78,33 +79,37 @@ pub async fn create_client_from_config(
Err(McpFactoryError::UnixNotSupported { name: server_name })
}
EffectiveTransport::Http => {
// Authenticated (OAuth) path: tokens exist or server requires auth.
if let Some(ref secrets) = secrets {
let has_tokens =
crate::tools::mcp::is_authenticated(&server, secrets, user_id).await;
if has_tokens || server.requires_auth() {
Ok(McpClient::new_authenticated(
return Ok(McpClient::new_authenticated(
server,
Arc::clone(session_manager),
Arc::clone(secrets),
user_id,
))
} else {
Ok(McpClient::new_with_config(server)
.map_err(|e| McpFactoryError::InvalidConfig {
name: server_name.clone(),
reason: e.to_string(),
})?
.with_session_manager(Arc::clone(session_manager)))
));
}
} else {
Ok(McpClient::new_with_config(server)
.map_err(|e| McpFactoryError::InvalidConfig {
name: server_name,
reason: e.to_string(),
})?
.with_session_manager(Arc::clone(session_manager)))
}
// Non-OAuth HTTP: wire the session manager into the *transport* so
// it captures `Mcp-Session-Id` from responses. Passing it only to
// the client (via `with_session_manager`) is not enough — the
// transport must know about it to read/write the header.
let transport = Arc::new(
HttpMcpTransport::new(server.url.clone(), server.name.clone())
.with_session_manager(Arc::clone(session_manager)),
);
Ok(McpClient::new_with_transport(
server.name.clone(),
transport,
Some(Arc::clone(session_manager)),
secrets,
user_id,
Some(server),
))
}
}
}
@@ -134,4 +139,84 @@ mod tests {
"non-OAuth HTTP clients must carry a session manager"
);
}
/// Regression test: the factory must wire the session manager into the
/// *transport*, not just the client. Otherwise the transport never
/// captures `Mcp-Session-Id` from responses and subsequent requests
/// lack the header, causing the server to reject them.
#[tokio::test]
async fn test_factory_non_oauth_http_transport_captures_session_id() {
use axum::http::header::HeaderName;
use axum::{Router, http::StatusCode, response::IntoResponse, routing::post};
use tokio::net::TcpListener;
const SESSION_ID: &str = "test-session-abc123";
async fn session_echo() -> impl IntoResponse {
let body = serde_json::json!({
"jsonrpc": "2.0",
"id": 1,
"result": {}
})
.to_string();
(
StatusCode::OK,
[(
HeaderName::from_static("mcp-session-id"),
SESSION_ID.to_string(),
)],
body,
)
}
let app = Router::new().route("/", post(session_echo));
let listener = TcpListener::bind("127.0.0.1:0").await.unwrap();
let addr = listener.local_addr().unwrap();
let url = format!("http://127.0.0.1:{}", addr.port());
tokio::spawn(async move {
axum::serve(listener, app).await.unwrap();
});
let server = McpServerConfig::new("session-test", &url);
let session_manager = Arc::new(McpSessionManager::new());
let process_manager = Arc::new(McpProcessManager::new());
let client = create_client_from_config(
server,
&session_manager,
&process_manager,
None,
"test-user",
)
.await
.expect("factory should succeed for HTTP config");
// Pre-create a session entry so that update_session_id has something to update.
// In production, the MCP initialize handshake calls get_or_create before responses arrive.
session_manager.get_or_create("session-test", &url).await;
// Send a request through the client's transport to trigger session capture.
use crate::tools::mcp::protocol::McpRequest;
let request = McpRequest {
jsonrpc: "2.0".to_string(),
id: Some(1),
method: "test".to_string(),
params: Some(serde_json::json!({})),
};
let headers = std::collections::HashMap::new();
client
.transport()
.send(&request, &headers)
.await
.expect("request should succeed");
// Verify the session manager captured the session ID from the response.
let captured = session_manager.get_session_id("session-test").await;
assert_eq!(
captured.as_deref(),
Some(SESSION_ID),
"transport must capture Mcp-Session-Id into session manager"
);
}
}
+28
View File
@@ -494,6 +494,34 @@ mod tests {
assert_eq!(echoed["authorization"], "Bearer oauth-token");
}
/// Regression test for #1436: 202 Accepted responses for notifications
/// were parsed as JSON, causing "Failed to parse MCP response" errors
/// that broke the MCP session handshake.
#[tokio::test]
async fn test_wire_202_accepted_for_notification() {
use axum::{Router, http::StatusCode, routing::post};
use tokio::net::TcpListener;
async fn accept_notification() -> StatusCode {
StatusCode::ACCEPTED
}
let app = Router::new().route("/", post(accept_notification));
let listener = TcpListener::bind("127.0.0.1:0").await.unwrap();
let addr = listener.local_addr().unwrap();
let url = format!("http://127.0.0.1:{}", addr.port());
tokio::spawn(async move {
axum::serve(listener, app).await.unwrap();
});
let transport = HttpMcpTransport::new(&url, "test-202");
let request = McpRequest::initialized_notification();
let response = transport.send(&request, &HashMap::new()).await.unwrap();
assert!(response.result.is_none());
assert!(response.error.is_none());
}
#[tokio::test]
async fn test_wire_custom_auth_preserved_when_no_per_request_auth() {
let (url, _handle) = spawn_echo_server().await;
+40 -3
View File
@@ -205,7 +205,44 @@ mod tests {
}
// -----------------------------------------------------------------------
// Test 5: routine_manual_create_defaults_to_tools_enabled
// Test 5: routine_update_fail_delete_fallback
// -----------------------------------------------------------------------
#[tokio::test]
async fn routine_update_fail_delete_fallback() {
let trace = LlmTrace::from_file(concat!(
env!("CARGO_MANIFEST_DIR"),
"/tests/fixtures/llm_traces/tools/routine_update_fail_delete_fallback.json"
))
.expect("failed to load routine_update_fail_delete_fallback.json");
let rig = TestRigBuilder::new()
.with_trace(trace.clone())
.with_auto_approve_tools(true)
.build()
.await;
rig.send_message("Try converting a routine trigger, then recover by deleting it")
.await;
let responses = rig.wait_for_responses(1, Duration::from_secs(15)).await;
rig.verify_trace_expects(&trace, &responses);
let completed = rig.tool_calls_completed();
assert!(
completed.iter().any(|(n, ok)| n == "routine_update" && !ok),
"routine_update should fail in this regression path: {completed:?}"
);
assert!(
completed.iter().any(|(n, ok)| n == "routine_delete" && *ok),
"routine_delete should recover successfully via preserved routine identity: {completed:?}"
);
rig.shutdown();
}
// -----------------------------------------------------------------------
// Test 6: routine_manual_create_defaults_to_tools_enabled
// -----------------------------------------------------------------------
#[tokio::test]
@@ -246,7 +283,7 @@ mod tests {
}
// -----------------------------------------------------------------------
// Test 6: routine_manual_create_explicit_no_tools
// Test 7: routine_manual_create_explicit_no_tools
// -----------------------------------------------------------------------
#[tokio::test]
@@ -287,7 +324,7 @@ mod tests {
}
// -----------------------------------------------------------------------
// Test 7: routine_history
// Test 8: routine_history
// -----------------------------------------------------------------------
#[tokio::test]
@@ -0,0 +1,70 @@
{
"model_name": "test-routine-update-fail-delete-fallback",
"expects": {
"tools_used": ["routine_create", "routine_update", "routine_delete"],
"tool_results_contain": {
"routine_update": "Cannot update schedule or timezone on a non-cron routine.",
"routine_delete": "temp-routine"
},
"min_responses": 1
},
"steps": [
{
"response": {
"type": "tool_calls",
"tool_calls": [
{
"id": "call_rc_fallback",
"name": "routine_create",
"arguments": {
"name": "temp-routine",
"trigger_type": "manual",
"prompt": "Temporary routine for fallback test."
}
}
],
"input_tokens": 120,
"output_tokens": 40
}
},
{
"response": {
"type": "tool_calls",
"tool_calls": [
{
"id": "call_ru_fallback",
"name": "routine_update",
"arguments": {
"name": "temp-routine",
"schedule": "0 */10 * * * *"
}
}
],
"input_tokens": 200,
"output_tokens": 30
}
},
{
"response": {
"type": "tool_calls",
"tool_calls": [
{
"id": "call_rd_fallback",
"name": "routine_delete",
"arguments": {}
}
],
"input_tokens": 300,
"output_tokens": 20
}
},
{
"response": {
"type": "text",
"content": "I recovered from the failed update and cleaned up the original routine.",
"input_tokens": 380,
"output_tokens": 25
}
}
]
}