Files
searchi/crates/searchi-cli/tests/mcp.rs
T

359 lines
13 KiB
Rust
Raw Normal View History

//! Genuine executable MCP boundary: handshake, discovery, source scope and lifecycle.
use serde_json::{json, Value};
use std::{
io::{BufRead, BufReader, Write},
process::{Child, ChildStdin, Command, Stdio},
sync::mpsc,
time::Duration,
};
struct Server {
child: Child,
input: ChildStdin,
output: mpsc::Receiver<String>,
}
impl Drop for Server {
fn drop(&mut self) {
let _ = self.child.kill();
let _ = self.child.wait();
}
}
impl Server {
fn start(db: &std::path::Path) -> Self {
Self::start_with_assets(db, None)
}
fn start_with_assets(
db: &std::path::Path,
assets: Option<(&std::ffi::OsStr, &std::ffi::OsStr)>,
) -> Self {
let mut command = Command::new(env!("CARGO_BIN_EXE_searchi"));
command.args(["mcp", "--db"]).arg(db);
if let Some((model, worker)) = assets {
command
.arg("--model-dir")
.arg(model)
.arg("--embedding-worker")
.arg(worker);
}
let mut child = command
.env("SEARCHI_FORCE_CPU", "1")
.stdin(Stdio::piped())
.stdout(Stdio::piped())
.stderr(Stdio::null())
.spawn()
.unwrap();
let input = child.stdin.take().unwrap();
let stdout = child.stdout.take().unwrap();
let (tx, output) = mpsc::channel();
std::thread::spawn(move || {
for line in BufReader::new(stdout).lines() {
if tx.send(line.unwrap()).is_err() {
break;
}
}
});
Self {
child,
input,
output,
}
}
fn send(&mut self, value: Value) {
writeln!(self.input, "{value}").unwrap();
self.input.flush().unwrap();
}
fn request(&mut self, id: u32, method: &str, params: Value) -> Value {
self.send(json!({"jsonrpc":"2.0","id":id,"method":method,"params":params}));
loop {
let line = self
.output
.recv_timeout(Duration::from_secs(15))
.expect("MCP response deadline");
let value: Value =
serde_json::from_str(&line).expect("stdout contains non-JSONRPC logging");
assert_eq!(value["jsonrpc"], "2.0");
if value["id"] == id {
return value;
}
}
}
}
#[test]
fn actual_mcp_handshake_search_and_guarded_sources() {
let fixture = tempfile::tempdir().unwrap();
let folder = fixture.path().join("documents");
std::fs::create_dir(&folder).unwrap();
let file = folder.join("contract.txt");
std::fs::write(
&file,
"Termination clause: sixty days written notice to end the supplier partnership.",
)
.unwrap();
std::fs::write(
folder.join("retry.rs"),
"pub fn refreshAccessToken() { /* retry requests */ }",
)
.unwrap();
std::fs::write(
folder.join("symbol-note.txt"),
"refreshAccessToken retry requests",
)
.unwrap();
let db = fixture.path().join("index.sqlite");
let indexed = Command::new(env!("CARGO_BIN_EXE_searchi"))
.args(["index", "--db"])
.arg(&db)
.arg("--root")
.arg(&folder)
.output()
.unwrap();
assert!(indexed.status.success());
let mut server = Server::start(&db);
let hello=server.request(1,"initialize",json!({"protocolVersion":"2025-11-25","capabilities":{},"clientInfo":{"name":"searchi-test","version":"1"}}));
assert_eq!(hello["result"]["serverInfo"]["name"], "searchi");
server.send(json!({"jsonrpc":"2.0","method":"notifications/initialized"}));
let tools = server.request(2, "tools/list", json!({}));
let names: Vec<&str> = tools["result"]["tools"]
.as_array()
.unwrap()
.iter()
.map(|tool| {
assert_eq!(tool["annotations"]["readOnlyHint"], true);
tool["name"].as_str().unwrap()
})
.collect();
assert_eq!(names.len(), 3);
assert!(
names.contains(&"search") && names.contains(&"stats") && names.contains(&"read_source")
);
let found = server.request(
3,
"tools/call",
json!({"name":"search","arguments":{"query":"termination","limit":3,"extension":"txt"}}),
);
let data = &found["result"]["structuredContent"];
assert_eq!(data["mode"], "lexical_only");
assert_eq!(data["main_result_count"], 1);
assert_eq!(data["related_result_count"], 0);
assert_eq!(data["match_assessment"], "main_matches");
assert_eq!(data["results"][0]["evidence"], "main_match");
assert_eq!(data["results"][0]["filename"], "contract.txt");
assert!(data["results"][0]["snippet"]
.as_str()
.unwrap()
.contains("sixty"));
let handle = data["results"][0]["source_handle"]
.as_str()
.unwrap()
.to_owned();
let source = server.request(
4,
"tools/call",
json!({"name":"read_source","arguments":{"handle":handle}}),
);
assert!(source["result"]["structuredContent"]["text"]
.as_str()
.unwrap()
.contains("sixty"));
let invented = server.request(
5,
"tools/call",
json!({"name":"read_source","arguments":{"handle":"invented"}}),
);
assert_eq!(invented["result"]["isError"], true);
let invalid = server.request(
6,
"tools/call",
json!({"name":"search","arguments":{"query":"termination","limit":101}}),
);
assert_eq!(invalid["result"]["isError"], true);
for (offset, folder) in [r"\\host\share", r"\\?\UNC\host\share", "//host/share"]
.iter()
.enumerate()
{
let rejected = server.request(
20 + offset as u32,
"tools/call",
json!({"name":"search","arguments":{"query":"termination","folder":folder}}),
);
assert_eq!(rejected["result"]["isError"], true);
assert!(rejected["result"]["structuredContent"]["error"]
.as_str()
.unwrap()
.contains("local path"));
}
let code = server.request(
40,
"tools/call",
json!({"name":"search","arguments":{"query":"refreshAccessToken","code_only":true}}),
);
let code_results = code["result"]["structuredContent"]["results"]
.as_array()
.unwrap();
assert_eq!(code_results.len(), 1);
assert_eq!(code_results[0]["filename"], "retry.rs");
assert_eq!(code_results[0]["source"]["kind"], "line");
assert!(code_results[0]["snippet"]
.as_str()
.unwrap()
.contains("refreshAccessToken"));
let mutation = server.request(7, "tools/call", json!({"name":"index","arguments":{}}));
assert!(mutation["error"].is_object());
std::fs::write(
&file,
"The source changed and its previous clause is stale.",
)
.unwrap();
let stale = server.request(
8,
"tools/call",
json!({"name":"read_source","arguments":{"handle":handle}}),
);
assert_eq!(stale["result"]["isError"], true);
let reindexed = Command::new(env!("CARGO_BIN_EXE_searchi"))
.args(["index", "--db"])
.arg(&db)
.arg("--root")
.arg(&folder)
.output()
.unwrap();
assert!(reindexed.status.success());
let replaced = server.request(
30,
"tools/call",
json!({"name":"read_source","arguments":{"handle":handle}}),
);
assert_eq!(replaced["result"]["isError"], true);
assert!(replaced["result"]["structuredContent"]["error"]
.as_str()
.unwrap()
.contains("version changed"));
std::fs::remove_file(&file).unwrap();
let deleted = server.request(
9,
"tools/call",
json!({"name":"read_source","arguments":{"handle":handle}}),
);
assert_eq!(deleted["result"]["isError"], true);
let stats = server.request(10, "tools/call", json!({"name":"stats","arguments":{}}));
assert_eq!(stats["result"]["structuredContent"]["mode"], "lexical_only");
}
#[test]
fn missing_database_never_creates_file_or_protocol_noise() {
let temp = tempfile::tempdir().unwrap();
let db = temp.path().join("missing.sqlite");
let output = Command::new(env!("CARGO_BIN_EXE_searchi"))
.args(["mcp", "--db"])
.arg(&db)
.output()
.unwrap();
assert!(!output.status.success());
assert!(output.stdout.is_empty());
assert!(!db.exists());
}
#[test]
#[ignore = "Requires verified Google model and current CPU-capable native worker"]
fn actual_google_cli_and_mcp_use_query_role_with_cited_results() {
let models = std::env::var_os("SEARCHI_GEMMA_MODEL_DIR").expect("Set models");
let worker = std::env::var_os("SEARCHI_GEMMA_WORKER").expect("Set worker");
let fixture = tempfile::tempdir().unwrap();
let folder = fixture.path().join("documents");
std::fs::create_dir(&folder).unwrap();
std::fs::write(
folder.join("supplier.txt"),
"The supplier agreement may be terminated with sixty days written notice.",
)
.unwrap();
std::fs::write(
folder.join("garden.txt"),
"Vegetable beds and rainwater collection in the garden.",
)
.unwrap();
std::fs::write(
folder.join("retry.rs"),
"pub fn retry_backoff(attempt: u32) -> u64 {\n 100 * 2_u64.pow(attempt)\n}\n",
)
.unwrap();
let db = fixture.path().join("index.sqlite");
searchi_core::SearchIndex::open(&db)
.unwrap()
.index_folder(&folder)
.unwrap();
let indexer = searchi_service::HybridSearch::open(&db, &models, &worker, 1).unwrap();
assert_eq!(indexer.worker_info().unwrap().role, "indexing");
drop(indexer);
let embedded = Command::new(env!("CARGO_BIN_EXE_searchi"))
.args(["embed", "--db"])
.arg(&db)
.arg("--model-dir")
.arg(&models)
.arg("--embedding-worker")
.arg(&worker)
.arg("--text-only")
.env("SEARCHI_FORCE_CPU", "1")
.output()
.unwrap();
assert!(
embedded.status.success(),
"{}",
String::from_utf8_lossy(&embedded.stderr)
);
let output = Command::new(env!("CARGO_BIN_EXE_searchi"))
.args(["search", "--db"])
.arg(&db)
.args(["cancel the supplier partnership", "--json"])
.arg("--model-dir")
.arg(&models)
.arg("--embedding-worker")
.arg(&worker)
.env("SEARCHI_FORCE_CPU", "1")
.output()
.unwrap();
assert!(
output.status.success(),
"{}",
String::from_utf8_lossy(&output.stderr)
);
let cli: Value = serde_json::from_slice(&output.stdout).unwrap();
assert_eq!(cli[0]["filename"], "supplier.txt");
let mut server = Server::start_with_assets(&db, Some((&models, &worker)));
server.request(1,"initialize",json!({"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"query-role-regression","version":"1"}}));
server.send(json!({"jsonrpc":"2.0","method":"notifications/initialized"}));
let stats = server.request(2, "tools/call", json!({"name":"stats","arguments":{}}));
let status = &stats["result"]["structuredContent"];
assert_eq!(status["worker"]["role"], "query");
assert_eq!(status["worker"]["context_tokens"], 512);
assert_eq!(status["worker"]["device"], "cpu");
assert_eq!(status["worker"]["media_supported"], true);
let found = server.request(
3,
"tools/call",
json!({"name":"search","arguments":{"query":"cancel the supplier partnership","limit":2}}),
);
let first = &found["result"]["structuredContent"]["results"][0];
assert_eq!(first["filename"], "supplier.txt");
let handle = first["source_handle"].as_str().unwrap();
let source = server.request(
4,
"tools/call",
json!({"name":"read_source","arguments":{"handle":handle}}),
);
assert!(source["result"]["structuredContent"]["text"]
.as_str()
.unwrap()
.contains("sixty days"));
let code=server.request(5,"tools/call",json!({"name":"search","arguments":{"query":"retry failed requests with exponential backoff","code_only":true}}));
let first = &code["result"]["structuredContent"]["results"][0];
assert_eq!(first["filename"], "retry.rs");
assert_eq!(first["source"]["kind"], "line");
let handle = first["source_handle"].as_str().unwrap();
let source = server.request(
6,
"tools/call",
json!({"name":"read_source","arguments":{"handle":handle}}),
);
assert!(source["result"]["structuredContent"]["text"]
.as_str()
.unwrap()
.contains("2_u64.pow"));
}