[mcp-server] Expose fuzzy file search in MCP (#2677)

## Summary
Expose a simple fuzzy file search implementation for mcp clients to work
with

## Testing
- [x] Tested locally
This commit is contained in:
Dylan
2025-09-29 12:19:09 -07:00
committed by GitHub
parent 04c1782e52
commit 197f45a3be
11 changed files with 313 additions and 3 deletions

View File

@@ -1,5 +1,6 @@
use crate::error_code::INTERNAL_ERROR_CODE;
use crate::error_code::INVALID_REQUEST_ERROR_CODE;
use crate::fuzzy_file_search::run_fuzzy_file_search;
use crate::json_to_toml::json_to_toml;
use crate::outgoing_message::OutgoingMessageSender;
use crate::outgoing_message::OutgoingNotification;
@@ -52,6 +53,8 @@ use codex_protocol::mcp_protocol::ExecArbitraryCommandResponse;
use codex_protocol::mcp_protocol::ExecCommandApprovalParams;
use codex_protocol::mcp_protocol::ExecCommandApprovalResponse;
use codex_protocol::mcp_protocol::ExecOneOffCommandParams;
use codex_protocol::mcp_protocol::FuzzyFileSearchParams;
use codex_protocol::mcp_protocol::FuzzyFileSearchResponse;
use codex_protocol::mcp_protocol::GetUserAgentResponse;
use codex_protocol::mcp_protocol::GetUserSavedConfigResponse;
use codex_protocol::mcp_protocol::GitDiffToRemoteResponse;
@@ -88,6 +91,8 @@ use std::collections::HashMap;
use std::ffi::OsStr;
use std::path::PathBuf;
use std::sync::Arc;
use std::sync::atomic::AtomicBool;
use std::sync::atomic::Ordering;
use std::time::Duration;
use tokio::select;
use tokio::sync::Mutex;
@@ -122,6 +127,7 @@ pub(crate) struct CodexMessageProcessor {
active_login: Arc<Mutex<Option<ActiveLogin>>>,
// Queue of pending interrupt requests per conversation. We reply when TurnAborted arrives.
pending_interrupts: Arc<Mutex<HashMap<ConversationId, Vec<RequestId>>>>,
pending_fuzzy_searches: Arc<Mutex<HashMap<String, Arc<AtomicBool>>>>,
}
impl CodexMessageProcessor {
@@ -141,6 +147,7 @@ impl CodexMessageProcessor {
conversation_listeners: HashMap::new(),
active_login: Arc::new(Mutex::new(None)),
pending_interrupts: Arc::new(Mutex::new(HashMap::new())),
pending_fuzzy_searches: Arc::new(Mutex::new(HashMap::new())),
}
}
@@ -206,6 +213,9 @@ impl CodexMessageProcessor {
ClientRequest::UserInfo { request_id } => {
self.get_user_info(request_id).await;
}
ClientRequest::FuzzyFileSearch { request_id, params } => {
self.fuzzy_file_search(request_id, params).await;
}
ClientRequest::ExecOneOffCommand { request_id, params } => {
self.exec_one_off_command(request_id, params).await;
}
@@ -1167,6 +1177,46 @@ impl CodexMessageProcessor {
}
}
}
async fn fuzzy_file_search(&mut self, request_id: RequestId, params: FuzzyFileSearchParams) {
let FuzzyFileSearchParams {
query,
roots,
cancellation_token,
} = params;
let cancel_flag = match cancellation_token.clone() {
Some(token) => {
let mut pending_fuzzy_searches = self.pending_fuzzy_searches.lock().await;
// if a cancellation_token is provided and a pending_request exists for
// that token, cancel it
if let Some(existing) = pending_fuzzy_searches.get(&token) {
existing.store(true, Ordering::Relaxed);
}
let flag = Arc::new(AtomicBool::new(false));
pending_fuzzy_searches.insert(token.clone(), flag.clone());
flag
}
None => Arc::new(AtomicBool::new(false)),
};
let results = match query.as_str() {
"" => vec![],
_ => run_fuzzy_file_search(query, roots, cancel_flag.clone()).await,
};
if let Some(token) = cancellation_token {
let mut pending_fuzzy_searches = self.pending_fuzzy_searches.lock().await;
if let Some(current_flag) = pending_fuzzy_searches.get(&token)
&& Arc::ptr_eq(current_flag, &cancel_flag)
{
pending_fuzzy_searches.remove(&token);
}
}
let response = FuzzyFileSearchResponse { files: results };
self.outgoing.send_response(request_id, response).await;
}
}
async fn apply_bespoke_event_handling(

View File

@@ -0,0 +1,84 @@
use std::num::NonZero;
use std::num::NonZeroUsize;
use std::path::PathBuf;
use std::sync::Arc;
use std::sync::atomic::AtomicBool;
use codex_file_search as file_search;
use codex_protocol::mcp_protocol::FuzzyFileSearchResult;
use tokio::task::JoinSet;
use tracing::warn;
const LIMIT_PER_ROOT: usize = 50;
const MAX_THREADS: usize = 12;
const COMPUTE_INDICES: bool = true;
pub(crate) async fn run_fuzzy_file_search(
query: String,
roots: Vec<String>,
cancellation_flag: Arc<AtomicBool>,
) -> Vec<FuzzyFileSearchResult> {
#[expect(clippy::expect_used)]
let limit_per_root =
NonZero::new(LIMIT_PER_ROOT).expect("LIMIT_PER_ROOT should be a valid non-zero usize");
let cores = std::thread::available_parallelism()
.map(std::num::NonZero::get)
.unwrap_or(1);
let threads = cores.min(MAX_THREADS);
let threads_per_root = (threads / roots.len()).max(1);
let threads = NonZero::new(threads_per_root).unwrap_or(NonZeroUsize::MIN);
let mut files: Vec<FuzzyFileSearchResult> = Vec::new();
let mut join_set = JoinSet::new();
for root in roots {
let search_dir = PathBuf::from(&root);
let query = query.clone();
let cancel_flag = cancellation_flag.clone();
join_set.spawn_blocking(move || {
match file_search::run(
query.as_str(),
limit_per_root,
&search_dir,
Vec::new(),
threads,
cancel_flag,
COMPUTE_INDICES,
) {
Ok(res) => Ok((root, res)),
Err(err) => Err((root, err)),
}
});
}
while let Some(res) = join_set.join_next().await {
match res {
Ok(Ok((root, res))) => {
for m in res.matches {
let result = FuzzyFileSearchResult {
root: root.clone(),
path: m.path,
score: m.score,
indices: m.indices,
};
files.push(result);
}
}
Ok(Err((root, err))) => {
warn!("fuzzy-file-search in dir '{root}' failed: {err}");
}
Err(err) => {
warn!("fuzzy-file-search join_next failed: {err}");
}
}
}
files.sort_by(file_search::cmp_by_score_desc_then_path_asc::<
FuzzyFileSearchResult,
_,
_,
>(|f| f.score, |f| f.path.as_str()));
files
}

View File

@@ -25,6 +25,7 @@ mod codex_tool_config;
mod codex_tool_runner;
mod error_code;
mod exec_approval;
mod fuzzy_file_search;
mod json_to_toml;
pub(crate) mod message_processor;
mod outgoing_message;