The tasks build the inference path: emsha-backed SHA-256, inferproxy, config, a hand-written HTTP and SSE client, request building, delta assembly, the chat state machine, the thinking cap, the slot gate with retry, the startup self-test and on-device verification. Everything the tasks copy in was checked against a private reference implementation: the gate passes after each task in order, the timing tests pass repeatedly under CPU load, and the reference passes the self-test and all four device checks on straylight. Expected results for the recorded streams were derived by a separate script. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
234 lines
7.1 KiB
Rust
234 lines
7.1 KiB
Rust
//! Checks against the real server. Ignored unless run by `make verify-device`. Do not edit.
|
|
//!
|
|
//! They need two environment variables:
|
|
//! BOXMAKER_INFERPROXY path to the built `inferproxy` binary
|
|
//! BOXMAKER_UPSTREAM host:port of the llama-server router, for example straylight:11434
|
|
//! and, optionally, BOXMAKER_MODEL (default ornith-1.5-35b-a3b). They use slot 0.
|
|
//!
|
|
//! They never touch the real `llama-server` process. The "server dies" test kills and restarts
|
|
//! its own `inferproxy`.
|
|
|
|
use loopd::config::Config;
|
|
use loopd::llama::info::{CacheOutcome, cache_outcome};
|
|
use loopd::llama::{ChatEvent, ChatMessage, ChatRequest, Client};
|
|
use std::path::{Path, PathBuf};
|
|
use std::process::{Child, Command};
|
|
use std::sync::mpsc;
|
|
use std::thread;
|
|
use std::time::Duration;
|
|
|
|
struct Proxy {
|
|
child: Child,
|
|
socket: PathBuf,
|
|
}
|
|
|
|
impl Proxy {
|
|
fn start(socket: &Path) -> Proxy {
|
|
let binary = std::env::var("BOXMAKER_INFERPROXY").expect("BOXMAKER_INFERPROXY is not set");
|
|
let upstream = std::env::var("BOXMAKER_UPSTREAM").expect("BOXMAKER_UPSTREAM is not set");
|
|
let child = Command::new(binary)
|
|
.arg("--listen")
|
|
.arg(socket)
|
|
.arg("--upstream")
|
|
.arg(upstream)
|
|
.spawn()
|
|
.expect("cannot start inferproxy");
|
|
let mut proxy = Proxy {
|
|
child,
|
|
socket: socket.to_path_buf(),
|
|
};
|
|
for _ in 0..100 {
|
|
if socket.exists() {
|
|
return proxy;
|
|
}
|
|
thread::sleep(Duration::from_millis(20));
|
|
}
|
|
proxy.kill();
|
|
panic!("inferproxy did not create {}", socket.display());
|
|
}
|
|
|
|
fn kill(&mut self) {
|
|
let _ = self.child.kill();
|
|
let _ = self.child.wait();
|
|
}
|
|
}
|
|
|
|
impl Drop for Proxy {
|
|
fn drop(&mut self) {
|
|
self.kill();
|
|
}
|
|
}
|
|
|
|
fn socket_path(name: &str) -> PathBuf {
|
|
let dir = std::env::temp_dir().join(format!("loopd-device-{}-{name}", std::process::id()));
|
|
std::fs::create_dir_all(&dir).unwrap();
|
|
dir.join("infer.sock")
|
|
}
|
|
|
|
fn config(socket: &Path) -> Config {
|
|
let model =
|
|
std::env::var("BOXMAKER_MODEL").unwrap_or_else(|_| "ornith-1.5-35b-a3b".to_string());
|
|
let text = format!(
|
|
r#"
|
|
[infer]
|
|
socket = "{}"
|
|
model = "{model}"
|
|
[slots]
|
|
main = 0
|
|
background = 1
|
|
[expect]
|
|
template_sha256 = "f55f52930aa8bf44ab5cb85f99370fcc3c56e9a85640b812086d5330bce5d86b"
|
|
n_ctx = 131072
|
|
slots = 2
|
|
"#,
|
|
socket.display()
|
|
);
|
|
Config::parse(&text).unwrap()
|
|
}
|
|
|
|
fn user(text: &str) -> ChatMessage {
|
|
// A different prompt each run, so that an earlier run's cache cannot make a check pass.
|
|
let nonce = std::time::SystemTime::now()
|
|
.duration_since(std::time::UNIX_EPOCH)
|
|
.unwrap()
|
|
.as_nanos();
|
|
ChatMessage::User {
|
|
content: format!("{text} (run {nonce})"),
|
|
}
|
|
}
|
|
|
|
#[test]
|
|
#[ignore = "needs the real server; run with make verify-device"]
|
|
fn the_startup_self_test_passes() {
|
|
let socket = socket_path("selftest");
|
|
let _proxy = Proxy::start(&socket);
|
|
let client = Client::new(config(&socket));
|
|
loopd::selftest::run(&client, &mut |step| eprintln!("selftest: {step}")).unwrap();
|
|
}
|
|
|
|
#[test]
|
|
#[ignore = "needs the real server; run with make verify-device"]
|
|
fn a_capped_thinking_block_ends_and_the_answer_arrives() {
|
|
let socket = socket_path("cap");
|
|
let _proxy = Proxy::start(&socket);
|
|
let mut cfg = config(&socket);
|
|
cfg.limits.thinking_cap = 60;
|
|
let client = Client::new(cfg);
|
|
let ask = "Think at great length about how many ways 8 rooks fit on a chessboard without attacking \
|
|
each other and with none on the main diagonal. Then answer in one sentence.";
|
|
let req = ChatRequest {
|
|
slot: 0,
|
|
messages: vec![user(ask)],
|
|
tools: vec![],
|
|
thinking: true,
|
|
};
|
|
let mut capped = Vec::new();
|
|
let done = client
|
|
.chat_with_retry(&req, &mut |e| {
|
|
if let ChatEvent::ThinkingCapped { tokens } = e {
|
|
capped.push(*tokens);
|
|
}
|
|
})
|
|
.unwrap();
|
|
assert!(done.thinking_capped);
|
|
assert_eq!(capped.len(), 1);
|
|
assert!(capped[0] >= 60 && capped[0] < 70, "capped at {capped:?}");
|
|
assert!(
|
|
done.reasoning_tokens < 60 + 256,
|
|
"thinking went on to {}",
|
|
done.reasoning_tokens
|
|
);
|
|
assert!(
|
|
done.content.is_some_and(|c| !c.trim().is_empty()),
|
|
"an answer followed the forced end"
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
#[ignore = "needs the real server; run with make verify-device"]
|
|
fn a_request_survives_its_proxy_being_killed_and_restarted() {
|
|
let socket = socket_path("restart");
|
|
let mut proxy = Proxy::start(&socket);
|
|
let mut cfg = config(&socket);
|
|
cfg.limits.retry_backoff_ms = vec![1_500];
|
|
let client = Client::new(cfg);
|
|
let ask = "Write about 300 words on the history of cork.";
|
|
let req = ChatRequest {
|
|
slot: 0,
|
|
messages: vec![user(ask)],
|
|
tools: vec![],
|
|
thinking: false,
|
|
};
|
|
|
|
let (tx, rx) = mpsc::channel();
|
|
let worker = thread::spawn(move || {
|
|
let mut retries = 0;
|
|
let mut told = false;
|
|
let result = client.chat_with_retry(&req, &mut |e| match e {
|
|
ChatEvent::Content(_) if !told => {
|
|
told = true;
|
|
let _ = tx.send(());
|
|
}
|
|
ChatEvent::Retrying { .. } => retries += 1,
|
|
_ => {}
|
|
});
|
|
(result, retries)
|
|
});
|
|
|
|
rx.recv_timeout(Duration::from_secs(120))
|
|
.expect("no content arrived");
|
|
proxy.kill(); // the stream dies in the middle of the answer
|
|
thread::sleep(Duration::from_millis(300));
|
|
let _proxy = Proxy::start(&proxy.socket);
|
|
|
|
let (result, retries) = worker.join().unwrap();
|
|
let done = result.expect("the retry should have succeeded");
|
|
assert!(retries >= 1, "the request was retried");
|
|
assert!(
|
|
done.content
|
|
.is_some_and(|c| c.split_whitespace().count() > 100)
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
#[ignore = "needs the real server; run with make verify-device"]
|
|
fn a_second_turn_reuses_the_first_turns_cache() {
|
|
let socket = socket_path("cache");
|
|
let _proxy = Proxy::start(&socket);
|
|
let client = Client::new(config(&socket));
|
|
let mut messages = vec![user(
|
|
"What is 17 * 23? Think briefly, then answer in one short sentence.",
|
|
)];
|
|
let req = ChatRequest {
|
|
slot: 0,
|
|
messages: messages.clone(),
|
|
tools: vec![],
|
|
thinking: true,
|
|
};
|
|
let turn1 = client.chat_with_retry(&req, &mut |_| {}).unwrap();
|
|
assert!(
|
|
turn1.reasoning_content.is_some(),
|
|
"this check is about replaying a thinking block"
|
|
);
|
|
messages.push(ChatMessage::Assistant {
|
|
content: turn1.content.clone(),
|
|
reasoning_content: turn1.reasoning_content.clone(),
|
|
tool_calls: turn1.tool_calls.clone(),
|
|
});
|
|
messages.push(user("And 17 * 24?"));
|
|
let req = ChatRequest {
|
|
slot: 0,
|
|
messages,
|
|
tools: vec![],
|
|
thinking: true,
|
|
};
|
|
let turn2 = client.chat_with_retry(&req, &mut |_| {}).unwrap();
|
|
assert_eq!(
|
|
cache_outcome(&turn1.timings, &turn2.timings),
|
|
CacheOutcome::Hit,
|
|
"{:?} then {:?}",
|
|
turn1.timings,
|
|
turn2.timings
|
|
);
|
|
}
|