loopd: the self-test checks the model's tags against the tokenizer

Co-Authored-By: ornith-1.5-35b-a3b <agent@wntrmute.dev>

crates/loopd/tests/selftest.rs

@@ -4,17 +4,26 @@ mod support;
 
 use loopd::llama::Client;
 use loopd::selftest::{SelfTestError, run};
-use support::{FakeServer, Reply};
+use support::{FakeServer, Reply, tokenizer};
 
 const CHAT: &str = "/v1/chat/completions";
+const TOKENIZE: &str = "/tokenize";
 
 /// 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 {
+/// The recorded props and the fake tokenizer, and no completion yet.
+fn props_and_tags() -> FakeServer {
     let server = FakeServer::start();
     server.route("/props", vec![Reply::fixture("props")]);
+    server.respond(TOKENIZE, tokenizer);
+    server
+}
+
+/// A server that passes: the recorded props, the fake tokenizer, then the three recorded
+/// completions in order.
+fn healthy() -> FakeServer {
+    let server = props_and_tags();
     server.route(
         CHAT,
         vec![
@@ -38,7 +47,7 @@ fn run_with(
 }
 
 #[test]
-fn a_healthy_server_passes_all_three_checks_in_order() {
+fn a_healthy_server_passes_all_four_checks_in_order() {
     let server = healthy();
     let (result, steps) = run_with(&server, |_| {});
     assert!(result.is_ok(), "{result:?}");
@@ -46,6 +55,7 @@ fn a_healthy_server_passes_all_three_checks_in_order() {
         steps,
         [
             "server matches config",
+            "tags tokenize as recorded",
             "tool call round trip",
             "turn 2 cache hit"
         ]
@@ -115,27 +125,26 @@ fn each_expected_value_is_checked() {
             "a server that is not the expected one is not sent any prompt"
         );
         assert!(server.requests_to(CHAT).is_empty());
+        assert!(server.requests_to(TOKENIZE).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")]);
+fn a_completion_without_the_tool_call_fails_the_tool_call_check() {
+    let server = props_and_tags();
     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);
+    assert_eq!(steps.len(), 3);
 }
 
 #[test]
-fn a_cold_second_turn_fails_the_third_check() {
+fn a_cold_second_turn_fails_the_cache_check() {
     // turn1 twice: the "second turn" reuses 15 tokens where 46 were left.
-    let server = FakeServer::start();
-    server.route("/props", vec![Reply::fixture("props")]);
+    let server = props_and_tags();
     server.route(
         CHAT,
         vec![
@@ -149,13 +158,12 @@ fn a_cold_second_turn_fails_the_third_check() {
         Err(SelfTestError::CacheMiss { expected, got }) => assert_eq!((expected, got), (7052, 15)),
         other => panic!("{other:?}"),
     }
-    assert_eq!(steps.len(), 3);
+    assert_eq!(steps.len(), 4);
 }
 
 #[test]
 fn a_server_that_is_down_is_an_inference_error_after_retries() {
-    let server = FakeServer::start();
-    server.route("/props", vec![Reply::fixture("props")]);
+    let server = props_and_tags();
     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:?}");