M5b plan: task 08, the self-test checks the tags against the tokenizer
loopd's self-test gains a check, run second (after "server matches config", before any prompt): each tag in bxcore::sanitize::TAGS must be one token from /tokenize, its recorded id, and its neutralised form more than one. A failure names the tag by its id, never its text, and points at a new runbook entry, loopd-tags-unexpected, given as a fragment; SelfTestError::pointer picks the entry per failure. One request per text (66): /tokenize has no batch form. The fake server gains respond and a fake tokenizer; selftest.rs, serve.rs, pointers.rs and support/mod.rs get M5b copies. Checks, on a reference at ref 08 (titan, rustc 1.98.1, own target/): - /tokenize fields from llama.cpp tools/server/README.md at b10964 (b29c606) and its handler; on straylight all 33 tags gave their ids and every neutralised form 7 to 11 tokens, 66 requests in ~0.3 s - given tests before the change: 4 fail as the task lists, selftest_tags does not compile (7 E0599); pointers passes - make gate: gate: ok, 1050 tests (1042 + 8); /tmp and $TMPDIR unchanged around it; the four suites 25 runs under load, no failure - 20 mutations, each caught: id not compared; neutralised check dropped; > 1 as >= 1, as == 1 missing 0, as > 2; first or last tag skipped; tag asked twice; pointer dropped or wrong (all or Tokenize); check skipped in serve; check run last; parse_special false; add_special left out; id missing from the message; the tag's text in the message; tokenize error as Infer; wrong count; wrong other id - the task's edits applied to a fresh ref-07 copy give files byte-identical to the reference; every before block found once - no chat-template tag whole in the task or given files; task lines within 100 characters except tables and verbatim lines; given files under 500 lines Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,128 @@
|
||||
//! Tests for the `loopd serve` command. Do not edit.
|
||||
|
||||
mod support;
|
||||
|
||||
use std::os::unix::fs::PermissionsExt;
|
||||
use std::process::{Command, Stdio};
|
||||
use std::time::Duration;
|
||||
use support::{FakeServer, Home, Reply, tokenizer};
|
||||
|
||||
fn config_file(home: &Home, server: &FakeServer, expect_slots: u32) -> std::path::PathBuf {
|
||||
let text = format!(
|
||||
r#"
|
||||
[infer]
|
||||
socket = "{}"
|
||||
model = "test-model"
|
||||
[slots]
|
||||
main = 0
|
||||
background = 1
|
||||
[expect]
|
||||
template_sha256 = "f55f52930aa8bf44ab5cb85f99370fcc3c56e9a85640b812086d5330bce5d86b"
|
||||
n_ctx = 131072
|
||||
slots = {expect_slots}
|
||||
[limits]
|
||||
poll_ms = 40
|
||||
liveness_ms = 500
|
||||
retry_backoff_ms = [10]
|
||||
[paths]
|
||||
home = "{}"
|
||||
"#,
|
||||
server.socket.display(),
|
||||
home.dir.display()
|
||||
);
|
||||
let path = home.dir.join("config.toml");
|
||||
std::fs::write(&path, text).unwrap();
|
||||
path
|
||||
}
|
||||
|
||||
fn healthy_routes(server: &FakeServer) {
|
||||
server.route("/props", vec![Reply::fixture("props")]);
|
||||
server.respond("/tokenize", tokenizer);
|
||||
server.route(
|
||||
"/v1/chat/completions",
|
||||
vec![
|
||||
Reply::fixture("tool_call"),
|
||||
Reply::fixture("turn1"),
|
||||
Reply::fixture("turn2"),
|
||||
Reply::fixture("plain"),
|
||||
],
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn serve_runs_the_self_test_then_binds_the_socket_with_mode_0600() {
|
||||
let home = Home::new();
|
||||
let server = FakeServer::start();
|
||||
healthy_routes(&server);
|
||||
let config = config_file(&home, &server, 2);
|
||||
let socket = home.dir.join("run").join("loop").join("loop.sock");
|
||||
let mut child = Command::new(env!("CARGO_BIN_EXE_loopd"))
|
||||
.args(["serve", "--config"])
|
||||
.arg(&config)
|
||||
.stderr(Stdio::piped())
|
||||
.spawn()
|
||||
.unwrap();
|
||||
let mut up = false;
|
||||
for _ in 0..200 {
|
||||
if socket.exists() {
|
||||
up = true;
|
||||
break;
|
||||
}
|
||||
std::thread::sleep(Duration::from_millis(50));
|
||||
}
|
||||
let mode = std::fs::metadata(&socket).map(|m| m.permissions().mode() & 0o777);
|
||||
let _ = child.kill();
|
||||
let output = child.wait_with_output().unwrap();
|
||||
let stderr = String::from_utf8_lossy(&output.stderr);
|
||||
assert!(up, "the socket never appeared; stderr: {stderr}");
|
||||
assert_eq!(mode.unwrap(), 0o600, "{stderr}");
|
||||
assert!(stderr.contains("selftest: ok"), "{stderr}");
|
||||
assert!(stderr.contains("serving on"), "{stderr}");
|
||||
assert_eq!(
|
||||
server.requests_to("/v1/chat/completions").len(),
|
||||
3,
|
||||
"the three self-test completions ran"
|
||||
);
|
||||
assert_eq!(
|
||||
server.requests_to("/tokenize").len(),
|
||||
2 * bxcore::sanitize::TAGS.len(),
|
||||
"the tag check ran: each tag and its neutralised form"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn serve_refuses_to_start_when_the_self_test_fails() {
|
||||
let home = Home::new();
|
||||
let server = FakeServer::start();
|
||||
healthy_routes(&server);
|
||||
let config = config_file(&home, &server, 3); // the fixture reports 2 slots
|
||||
let output = Command::new(env!("CARGO_BIN_EXE_loopd"))
|
||||
.args(["serve", "--config"])
|
||||
.arg(&config)
|
||||
.output()
|
||||
.unwrap();
|
||||
let stderr = String::from_utf8_lossy(&output.stderr);
|
||||
assert_eq!(output.status.code(), Some(1), "{stderr}");
|
||||
assert!(stderr.contains("selftest: FAILED"), "{stderr}");
|
||||
assert!(stderr.contains("slot count"), "{stderr}");
|
||||
assert!(
|
||||
!home.dir.join("run").join("loop").join("loop.sock").exists(),
|
||||
"no socket was left behind"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn usage_and_a_bad_config_are_reported() {
|
||||
let output = Command::new(env!("CARGO_BIN_EXE_loopd"))
|
||||
.arg("dance")
|
||||
.output()
|
||||
.unwrap();
|
||||
assert_eq!(output.status.code(), Some(2));
|
||||
assert!(String::from_utf8_lossy(&output.stderr).contains("usage"));
|
||||
let output = Command::new(env!("CARGO_BIN_EXE_loopd"))
|
||||
.args(["serve", "--config", "/nonexistent/config.toml"])
|
||||
.output()
|
||||
.unwrap();
|
||||
assert_eq!(output.status.code(), Some(1));
|
||||
assert!(String::from_utf8_lossy(&output.stderr).contains("config.toml"));
|
||||
}
|
||||
Reference in New Issue
Block a user