Add the startup self-test and the loopd selftest command
Implemented-By: OpenCode session (model recorded in docs/implementer-log.md)
This commit is contained in:
@@ -0,0 +1,169 @@
|
||||
//! Tests for the startup self-test, against the fake server. Do not edit.
|
||||
|
||||
mod support;
|
||||
|
||||
use loopd::llama::Client;
|
||||
use loopd::selftest::{SelfTestError, run};
|
||||
use support::{FakeServer, Reply};
|
||||
|
||||
const CHAT: &str = "/v1/chat/completions";
|
||||
|
||||
/// A change to the config before the self-test runs.
|
||||
type Edit = fn(&mut loopd::config::Config);
|
||||
|
||||
/// A server that passes: the recorded props, then the three recorded completions in order.
|
||||
fn healthy() -> FakeServer {
|
||||
let server = FakeServer::start();
|
||||
server.route("/props", vec![Reply::fixture("props")]);
|
||||
server.route(
|
||||
CHAT,
|
||||
vec![
|
||||
Reply::fixture("tool_call"),
|
||||
Reply::fixture("turn1"),
|
||||
Reply::fixture("turn2"),
|
||||
],
|
||||
);
|
||||
server
|
||||
}
|
||||
|
||||
fn run_with(
|
||||
server: &FakeServer,
|
||||
edit: impl FnOnce(&mut loopd::config::Config),
|
||||
) -> (Result<(), SelfTestError>, Vec<String>) {
|
||||
let mut cfg = support::test_config(&server.socket);
|
||||
edit(&mut cfg);
|
||||
let mut steps = Vec::new();
|
||||
let result = run(&Client::new(cfg), &mut |s| steps.push(s.to_string()));
|
||||
(result, steps)
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_healthy_server_passes_all_three_checks_in_order() {
|
||||
let server = healthy();
|
||||
let (result, steps) = run_with(&server, |_| {});
|
||||
assert!(result.is_ok(), "{result:?}");
|
||||
assert_eq!(
|
||||
steps,
|
||||
[
|
||||
"server matches config",
|
||||
"tool call round trip",
|
||||
"turn 2 cache hit"
|
||||
]
|
||||
);
|
||||
|
||||
let chats = server.requests_to(CHAT);
|
||||
assert_eq!(chats.len(), 3);
|
||||
// The tool-call check offers exactly one tool; the cache check offers none.
|
||||
assert_eq!(chats[0].json()["tools"].as_array().map(Vec::len), Some(1));
|
||||
assert!(chats[1].json().get("tools").is_none());
|
||||
// All three run on the main slot.
|
||||
assert!(chats.iter().all(|c| c.json()["id_slot"] == 0));
|
||||
// Turn 2 is turn 1 plus the assistant's answer plus a new question: a strict extension.
|
||||
let turn1 = chats[1].json()["messages"].as_array().unwrap().clone();
|
||||
let turn2 = chats[2].json()["messages"].as_array().unwrap().clone();
|
||||
assert_eq!(turn2.len(), turn1.len() + 2);
|
||||
assert_eq!(turn2[..turn1.len()], turn1[..]);
|
||||
assert_eq!(
|
||||
turn2[turn1.len()],
|
||||
serde_json::json!({"role": "assistant", "content": "Blue"})
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn the_main_slot_comes_from_the_config() {
|
||||
let server = healthy();
|
||||
let (result, _) = run_with(&server, |c| c.slots.main = 1);
|
||||
assert!(result.is_ok(), "{result:?}");
|
||||
assert!(
|
||||
server
|
||||
.requests_to(CHAT)
|
||||
.iter()
|
||||
.all(|c| c.json()["id_slot"] == 1)
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn each_expected_value_is_checked() {
|
||||
let zero = proto::Hash32::ZERO;
|
||||
let cases: [(&str, Edit); 3] = [
|
||||
("chat template sha256", |c| {
|
||||
c.expect.template_sha256 = proto::Hash32::ZERO
|
||||
}),
|
||||
("context per slot", |c| c.expect.n_ctx = 4096),
|
||||
("slot count", |c| c.expect.slots = 3),
|
||||
];
|
||||
for (want_what, edit) in cases {
|
||||
let server = healthy();
|
||||
let (result, steps) = run_with(&server, edit);
|
||||
match result {
|
||||
Err(SelfTestError::Mismatch {
|
||||
what,
|
||||
expected,
|
||||
got,
|
||||
}) => {
|
||||
assert_eq!(what, want_what);
|
||||
assert_ne!(expected, got);
|
||||
if what == "chat template sha256" {
|
||||
assert_eq!(expected, zero.to_hex());
|
||||
}
|
||||
}
|
||||
other => panic!("{want_what}: {other:?}"),
|
||||
}
|
||||
assert_eq!(
|
||||
steps.len(),
|
||||
1,
|
||||
"a server that is not the expected one is not sent any prompt"
|
||||
);
|
||||
assert!(server.requests_to(CHAT).is_empty());
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_completion_without_the_tool_call_fails_the_second_check() {
|
||||
let server = FakeServer::start();
|
||||
server.route("/props", vec![Reply::fixture("props")]);
|
||||
server.route(CHAT, vec![Reply::fixture("plain")]);
|
||||
let (result, steps) = run_with(&server, |_| {});
|
||||
assert!(
|
||||
matches!(result, Err(SelfTestError::ToolCall(_))),
|
||||
"{result:?}"
|
||||
);
|
||||
assert_eq!(steps.len(), 2);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_cold_second_turn_fails_the_third_check() {
|
||||
// turn1 twice: the "second turn" reuses 15 tokens where 46 were left.
|
||||
let server = FakeServer::start();
|
||||
server.route("/props", vec![Reply::fixture("props")]);
|
||||
server.route(
|
||||
CHAT,
|
||||
vec![
|
||||
Reply::fixture("tool_call"),
|
||||
Reply::fixture("progress"),
|
||||
Reply::fixture("turn1"),
|
||||
],
|
||||
);
|
||||
let (result, steps) = run_with(&server, |_| {});
|
||||
match result {
|
||||
Err(SelfTestError::CacheMiss { expected, got }) => assert_eq!((expected, got), (7052, 15)),
|
||||
other => panic!("{other:?}"),
|
||||
}
|
||||
assert_eq!(steps.len(), 3);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_server_that_is_down_is_an_inference_error_after_retries() {
|
||||
let server = FakeServer::start();
|
||||
server.route("/props", vec![Reply::fixture("props")]);
|
||||
server.route(CHAT, vec![Reply::fixture("tool_call").cut_after(500)]);
|
||||
let (result, _) = run_with(&server, |c| c.limits.retry_attempts = 2);
|
||||
assert!(matches!(result, Err(SelfTestError::Infer(_))), "{result:?}");
|
||||
assert_eq!(
|
||||
server.requests_to(CHAT).len(),
|
||||
2,
|
||||
"the self-test retries like everything else"
|
||||
);
|
||||
let e: Box<dyn std::error::Error> = Box::new(result.unwrap_err());
|
||||
assert!(!e.to_string().is_empty());
|
||||
}
|
||||
Reference in New Issue
Block a user