preserve the packaged runtime Rust toolchain

New config field `thinking` (OpenAI: reasoning_effort still wins): Anthropic adaptive thinking +
output_config.effort (thinking blocks kept and sent back), OpenAI reasoning.effort. A 400 that rejects
the effort is retried with the nearest accepted level (from the error's list, lower on a tie), logged,
never dropped to off.

PROTOCOL.md

@@ -231,9 +231,19 @@ folder again, as at start.
 {"type": "build", "source": "/actor/agent/public/drafts/notes"}
 ```
 
-The reply is `{"type": "built", "wasm": "/actor/cargo/public/builds/<n>/<name>.wasm", "built_by": "cargo", ...}`
-or `{"type": "build_failed", "errors": "..."}`. Pass `wasm`, `source`, and
-`built_by` on to `spawn` or `upgrade`.
+The build request may include `"skip_tests": true` to skip Rust unit tests.
+By default, `cargo` first runs `cargo test` for the host target (not WASI),
+so pure-logic unit tests in a `wasm32-wasip2` actor crate can run without a
+WASI test runner. If tests fail or cannot compile, the build fails before the
+WASI build. The reply carries `tests: {"passed": <count>, "failed": <count>,
+"output": "<cargo test stdout and stderr>"}`; counts sum Cargo's test-result
+summaries, and a test command/compilation failure without a summary counts as
+one failure. With `skip_tests: true`, counts are zero and output says tests
+were skipped.
+
+The reply is `{"type": "built", "wasm": "/actor/cargo/public/builds/<n>/<name>.wasm", "built_by": "cargo", "tests": {...}, ...}`
+or `{"type": "build_failed", "errors": "...", "tests": {...}}`. Pass
+`wasm`, `source`, and `built_by` on to `spawn` or `upgrade`.
 
 A Rust actor depends on the SDK with `sausage-actor = "0.1"`. `cargo` points
 that dependency at the SDK of the host, which it publishes at

agent/src/llm.rs

@@ -14,11 +14,49 @@ pub struct Config {
     pub base_url: String,
     pub model: String,
     pub token: String,
-    /// Optional reasoning effort for OpenAI models ("low", "medium", ...).
+    /// Optional reasoning effort for OpenAI models only (wins over `thinking` there).
     #[serde(default)]
     pub reasoning_effort: Option<String>,
     #[serde(default)]
     pub max_tokens: Option<u32>,
+    /// Thinking effort for both APIs: "low", "medium", "high", "xhigh", "max" (`LEVELS`), or "off"/unset for none.
+    /// Anthropic: adaptive thinking + output_config.effort; OpenAI: reasoning.effort. A level the model rejects is
+    /// replaced by the nearest accepted one (logged), never by "off".
+    #[serde(default)]
+    pub thinking: Option<String>,
+}
+
+/// Thinking levels, lowest first.
+pub const LEVELS: [&str; 5] = ["low", "medium", "high", "xhigh", "max"];
+
+/// The level nearest to `want` (lower on a tie) among those a 400 error lists in quotes (else all levels), not
+/// yet `tried`. None: nothing left, so the request goes out without an effort field (model default).
+fn fallback_effort(want: &str, error: &str, tried: &[String]) -> Option<String> {
+    let listed: Vec<&str> = error.split('\'').skip(1).step_by(2).filter(|w| LEVELS.contains(w)).collect();
+    let pool = if listed.iter().any(|l| *l != want) { listed } else { LEVELS.to_vec() };
+    let at = LEVELS.iter().position(|l| *l == want).unwrap_or(1) as i32;
+    pool.into_iter()
+        .filter(|l| *l != want && !tried.iter().any(|t| t == l))
+        .min_by_key(|l| {
+            let i = LEVELS.iter().position(|x| x == l).unwrap_or(1) as i32;
+            ((i - at).abs(), i > at)
+        })
+        .map(str::to_string)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::fallback_effort;
+
+    #[test]
+    fn nearest_accepted_level() {
+        let anthropic = "HTTP 400: output_config.effort: Input should be 'low', 'medium', 'high' or 'max'";
+        assert_eq!(fallback_effort("xhigh", anthropic, &["xhigh".into()]).as_deref(), Some("high"));
+        let openai = "HTTP 400: Invalid value: 'ultra'. Supported values are: 'none', 'minimal', 'low', 'medium', 'high', 'xhigh', and 'max'.";
+        assert_eq!(fallback_effort("ultra", openai, &["ultra".into()]).as_deref(), Some("medium"));
+        // No list in the error: step to the neighbour, never to off.
+        assert_eq!(fallback_effort("max", "HTTP 400: effort max not supported", &["max".into()]).as_deref(), Some("xhigh"));
+    }
 }
 
 #[derive(Serialize, Deserialize, Clone, Debug)]
@@ -32,7 +70,7 @@ pub enum Entry {
     },
     ToolCall { id: String, name: String, arguments: String },
     ToolResult { id: String, output: String },
-    /// A provider item that only this API shape understands (OpenAI reasoning).
+    /// A provider item that only this API shape understands (OpenAI reasoning, Anthropic thinking).
     Opaque { api: String, item: Value },
 }
 
@@ -43,10 +81,28 @@ pub struct Tool {
 }
 
 pub async fn complete(cfg: &Config, system: &str, tools: &[Tool], history: &[Entry]) -> Result<Vec<Entry>, String> {
-    match cfg.api.as_str() {
-        "openai-responses" => openai(cfg, system, tools, history).await,
-        "anthropic-messages" => anthropic(cfg, system, tools, history).await,
-        other => Err(format!("unknown API shape {other:?}")),
+    let want = match cfg.api.as_str() {
+        "openai-responses" => cfg.reasoning_effort.clone().or_else(|| cfg.thinking.clone()),
+        _ => cfg.thinking.clone(),
+    }
+    .filter(|t| t != "off");
+    let mut effort = want.clone();
+    let mut tried = Vec::new();
+    loop {
+        let result = match cfg.api.as_str() {
+            "openai-responses" => openai(cfg, system, tools, history, effort.as_deref()).await,
+            "anthropic-messages" => anthropic(cfg, system, tools, history, want.is_some(), effort.as_deref()).await,
+            other => return Err(format!("unknown API shape {other:?}")),
+        };
+        match (result, effort.clone()) {
+            // The model rejected the effort level: retry with the nearest accepted one (thinking stays on).
+            (Err(e), Some(current)) if e.starts_with("HTTP 400") && e.contains("effort") => {
+                tried.push(current.clone());
+                effort = fallback_effort(want.as_deref().unwrap_or(""), &e, &tried);
+                eprintln!("agent: {} rejected thinking effort {current:?}; retrying with {effort:?}: {e}", cfg.model);
+            }
+            (result, _) => return result,
+        }
     }
 }
 
@@ -67,7 +123,7 @@ async fn post(url: &str, headers: &[(&str, String)], body: &Value) -> Result<Val
     serde_json::from_str(&text).map_err(|e| format!("invalid JSON in response: {e}"))
 }
 
-async fn openai(cfg: &Config, system: &str, tools: &[Tool], history: &[Entry]) -> Result<Vec<Entry>, String> {
+async fn openai(cfg: &Config, system: &str, tools: &[Tool], history: &[Entry], effort: Option<&str>) -> Result<Vec<Entry>, String> {
     let mut input = Vec::new();
     for e in history {
         match e {
@@ -104,7 +160,7 @@ async fn openai(cfg: &Config, system: &str, tools: &[Tool], history: &[Entry]) -
     if let Some(max_tokens) = cfg.max_tokens {
         body["max_output_tokens"] = json!(max_tokens);
     }
-    if let Some(effort) = &cfg.reasoning_effort {
+    if let Some(effort) = effort {
         body["reasoning"] = json!({"effort": effort});
     }
     let url = format!("{}/v1/responses", cfg.base_url);
@@ -143,7 +199,14 @@ async fn openai(cfg: &Config, system: &str, tools: &[Tool], history: &[Entry]) -
     Ok(out)
 }
 
-async fn anthropic(cfg: &Config, system: &str, tools: &[Tool], history: &[Entry]) -> Result<Vec<Entry>, String> {
+async fn anthropic(
+    cfg: &Config,
+    system: &str,
+    tools: &[Tool],
+    history: &[Entry],
+    thinking: bool,
+    effort: Option<&str>,
+) -> Result<Vec<Entry>, String> {
     // Merge consecutive blocks of the same role into one message.
     let mut messages: Vec<(String, Vec<Value>)> = Vec::new();
     let mut push = |role: &str, block: Value| match messages.last_mut() {
@@ -163,6 +226,8 @@ async fn anthropic(cfg: &Config, system: &str, tools: &[Tool], history: &[Entry]
             Entry::ToolResult { id, output } => {
                 push("user", json!({"type": "tool_result", "tool_use_id": id, "content": output}))
             }
+            // Thinking blocks go back unchanged (with their signature): required next to tool use.
+            Entry::Opaque { api, item } if api == "anthropic-messages" && thinking => push("assistant", item.clone()),
             Entry::Opaque { .. } => {}
         }
     }
@@ -171,13 +236,19 @@ async fn anthropic(cfg: &Config, system: &str, tools: &[Tool], history: &[Entry]
         .iter()
         .map(|t| json!({"name": t.name, "description": t.description, "input_schema": t.parameters}))
         .collect();
-    let body = json!({
+    let mut body = json!({
         "model": cfg.model,
         "system": system,
         "messages": messages,
         "tools": tools,
         "max_tokens": cfg.max_tokens.unwrap_or(32000),
     });
+    if thinking {
+        body["thinking"] = json!({"type": "adaptive"});
+        if let Some(effort) = effort {
+            body["output_config"] = json!({"effort": effort});
+        }
+    }
     let url = format!("{}/v1/messages", cfg.base_url);
     let resp = post(
         &url,
@@ -199,6 +270,9 @@ async fn anthropic(cfg: &Config, system: &str, tools: &[Tool], history: &[Entry]
                 name: block["name"].as_str().unwrap_or_default().to_string(),
                 arguments: block["input"].to_string(),
             }),
+            Some("thinking") | Some("redacted_thinking") => {
+                out.push(Entry::Opaque { api: "anthropic-messages".into(), item: block })
+            }
             _ => {}
         }
     }

cli/src/cargo_actor.rs

@@ -1,8 +1,9 @@
 //! The native `cargo` actor: builds Rust source folders into `.wasm` files.
 //!
 //! Request:  `{"type": "build", "source": "/actor/<id>/public/<folder>"}`
-//! Replies:  `{"type": "built", "wasm": "/actor/cargo/public/builds/<n>/<name>.wasm", ...}`
-//!           `{"type": "build_failed", "errors": "..."}`
+//!           optional `"skip_tests": true` skips native `cargo test` (tests run by default).
+//! Replies:  `{"type": "built", "wasm": "/actor/cargo/public/builds/<n>/<name>.wasm", "tests": {"passed": 1, "failed": 0, "output": "..."}, ...}`
+//!           `{"type": "build_failed", "errors": "...", "tests": {"passed": 0, "failed": 1, "output": "..."}}`
 //!
 //! The broker knows nothing about Rust. This actor is one way to get a
 //! `.wasm` file. Other actors can add other languages.
@@ -32,11 +33,49 @@ pub const TARGET: &str = "wasm32-wasip2";
 /// The source of the `sausage-actor` SDK.
 static SDK: Dir<'_> = include_dir!("$CARGO_MANIFEST_DIR/../sdk");
 
+#[derive(Clone, Default, Debug)]
+pub struct TestResults {
+    pub passed: u64,
+    pub failed: u64,
+    pub output: String,
+}
+
+impl TestResults {
+    fn value(&self) -> Value {
+        json!({"passed": self.passed, "failed": self.failed, "output": self.output})
+    }
+}
+
 pub struct BuildOutput {
     /// Host path of the published `.wasm` file.
     pub wasm: PathBuf,
     pub seconds: f64,
     pub warnings: String,
+    pub tests: TestResults,
+}
+
+#[derive(Debug)]
+pub struct BuildFailure {
+    pub reason: String,
+    pub tests: TestResults,
+}
+
+impl std::fmt::Display for BuildFailure {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        if self.tests.failed > 0 && !self.tests.output.is_empty() {
+            write!(f, "{}:\n{}", self.reason, self.tests.output)
+        } else {
+            f.write_str(&self.reason)
+        }
+    }
+}
+
+impl std::error::Error for BuildFailure {}
+
+impl From<anyhow::Error> for BuildFailure {
+    fn from(error: anyhow::Error) -> Self {
+        Self { reason: format!("{error:#}"), tests: TestResults::default() }
+    }
 }
 
 /// All builds share one target folder, so they run one at a time.
@@ -51,19 +90,44 @@ impl Cargo {
         Ok(Self { world })
     }
 
-    /// Build the crate in `source` (a host path) and publish the `.wasm` file
-    /// under `/actor/cargo/public/builds/<n>/`.
-    pub async fn build(&self, source: &Path) -> Result<BuildOutput> {
+    /// Run native `cargo test` unless opted out, then build and publish the
+    /// crate's `wasm32-wasip2` binary under `/actor/cargo/public/builds/<n>/`.
+    pub async fn build(&self, source: &Path, skip_tests: bool) -> std::result::Result<BuildOutput, BuildFailure> {
         if !source.join("Cargo.toml").is_file() {
-            bail!("{} has no Cargo.toml", source.display());
+            return Err(BuildFailure {
+                reason: format!("{} has no Cargo.toml", source.display()),
+                tests: TestResults::default(),
+            });
         }
         let started = Instant::now();
         let data = self.world.data_dir(ID);
         let build_dir = data.join("work");
         world::replace_source(source, &build_dir)?;
         let manifest = build_dir.join("Cargo.toml");
-        std::fs::write(&manifest, prepare_manifest(&std::fs::read_to_string(&manifest)?, Some(&self.world.public_dir(ID).join("sdk")))?)?;
+        let original = std::fs::read_to_string(&manifest).context("read build manifest")?;
+        let prepared = prepare_manifest(&original, Some(&self.world.public_dir(ID).join("sdk")))?;
+        std::fs::write(&manifest, prepared).context("write prepared manifest")?;
 
+        let target_dir = data.join("target");
+        let tests = if skip_tests {
+            TestResults { output: "skipped (skip_tests=true)".into(), ..TestResults::default() }
+        } else {
+            match run_tests(&build_dir, &target_dir).await {
+                Ok(tests) => tests,
+                Err(error) => {
+                    let output = format!("cannot run cargo tests: {error:#}");
+                    return Err(BuildFailure {
+                        reason: output.clone(),
+                        tests: TestResults { failed: 1, output, ..TestResults::default() },
+                    });
+                }
+            }
+        };
+        if tests.failed > 0 {
+            return Err(BuildFailure { reason: "unit tests failed".into(), tests });
+        }
+
+        let build_result: Result<BuildOutput> = async {
             let mut cmd = Command::new("cargo");
             cmd.arg("build")
                 .arg("--release")
@@ -71,7 +135,7 @@ impl Cargo {
                 .arg(TARGET)
                 .arg("--message-format=json-render-diagnostics")
                 .arg("--target-dir")
-            .arg(data.join("target"))
+                .arg(&target_dir)
                 .current_dir(&build_dir)
                 .kill_on_drop(true);
             let out = cmd.output().await.context("cannot run cargo (is it on PATH, with the wasm32-wasip2 target?)")?;
@@ -95,7 +159,15 @@ impl Cargo {
             let name = artifact.file_name().context("artifact has no file name")?;
             let dest = dest_dir.join(name);
             world::write_atomic(&dest, &std::fs::read(&artifact)?)?;
-        Ok(BuildOutput { wasm: dest, seconds: started.elapsed().as_secs_f64(), warnings: strip_progress(&stderr) })
+            Ok(BuildOutput {
+                wasm: dest,
+                seconds: started.elapsed().as_secs_f64(),
+                warnings: strip_progress(&stderr),
+                tests: tests.clone(),
+            })
+        }
+        .await;
+        build_result.map_err(|error| BuildFailure { reason: format!("{error:#}"), tests })
     }
 
     /// The native `cargo` actor. Builds run one at a time, in order.
@@ -106,7 +178,7 @@ impl Cargo {
                 continue;
             }
             let body = self.handle(&broker, &env).await.unwrap_or_else(|e| {
-                json!({"type": "build_failed", "source": env.body.get("source"), "errors": format!("{e:#}")})
+                json!({"type": "build_failed", "source": env.body.get("source"), "errors": format!("{e:#}"), "tests": TestResults::default().value()})
             });
             broker.send(ID, Some(&env.from), None, Some(&env.id), body);
         }
@@ -117,7 +189,9 @@ impl Cargo {
             Some("build") => {
                 let source_s = env.body.get("source").and_then(Value::as_str).ok_or_else(|| anyhow!("missing \"source\""))?;
                 let source = broker.world.resolve(&env.from, source_s)?;
-                let out = self.build(&source).await?;
+                let skip_tests = env.body.get("skip_tests").and_then(Value::as_bool).unwrap_or(false);
+                match self.build(&source, skip_tests).await {
+                    Ok(out) => {
                         let wasm = self.world.global_path(&out.wasm).unwrap_or_else(|| out.wasm.display().to_string());
                         Ok(json!({
                             "type": "built",
@@ -126,13 +200,65 @@ impl Cargo {
                             "built_by": ID,
                             "seconds": (out.seconds * 10.0).round() / 10.0,
                             "warnings": out.warnings,
+                            "tests": out.tests.value(),
                         }))
                     }
+                    Err(failure) => Ok(json!({
+                        "type": "build_failed",
+                        "source": source_s,
+                        "errors": failure.reason,
+                        "tests": failure.tests.value(),
+                    })),
+                }
+            }
             other => bail!("unknown request {other:?}. Known: build"),
         }
     }
 }
 
+/// Run tests for the host triple: WASI crates' pure-logic tests can use the
+/// normal Rust test harness without needing a WASI test runner.
+async fn run_tests(build_dir: &Path, target_dir: &Path) -> Result<TestResults> {
+    let mut cmd = Command::new("cargo");
+    cmd.arg("test")
+        .arg("--target-dir")
+        .arg(target_dir)
+        .current_dir(build_dir)
+        .kill_on_drop(true);
+    let out = cmd.output().await.context("cannot run cargo test")?;
+    let stdout = String::from_utf8_lossy(&out.stdout).to_string();
+    let stderr = String::from_utf8_lossy(&out.stderr).to_string();
+    let combined = match (stdout.is_empty(), stderr.is_empty()) {
+        (true, true) => String::new(),
+        (false, true) => stdout,
+        (true, false) => stderr,
+        (false, false) => format!("{stdout}\n{stderr}"),
+    };
+    let output = strip_progress(&combined);
+    let passed = test_count(&output, "passed");
+    let mut failed = test_count(&output, "failed");
+    // Compilation failures and runner errors have no `test result` summary,
+    // but still make the default test phase fail.
+    if !out.status.success() && failed == 0 {
+        failed = 1;
+    }
+    Ok(TestResults { passed, failed, output })
+}
+
+/// Count the `passed` or `failed` totals in cargo's per-target test summaries.
+fn test_count(output: &str, field: &str) -> u64 {
+    output
+        .lines()
+        .filter_map(|line| line.split_once("test result:").map(|(_, rest)| rest))
+        .flat_map(|summary| summary.split(';'))
+        .filter_map(|part| {
+            let words: Vec<_> = part.split_whitespace().collect();
+            let index = words.iter().position(|word| *word == field)?;
+            words.get(index.checked_sub(1)?)?.parse::<u64>().ok()
+        })
+        .sum()
+}
+
 /// Point a `sausage-actor` dependency at `sdk` (keeping its features), and
 /// add an empty `[workspace]`, so the crate never joins a parent workspace.
 fn prepare_manifest(text: &str, sdk: Option<&Path>) -> Result<String> {

cli/src/main.rs

@@ -85,7 +85,7 @@ async fn init(dir: PathBuf) -> Result<()> {
     std::fs::create_dir_all(&source)?;
     AGENT_SOURCE.extract(&source).context("extract agent source")?;
     println!("Building the agent actor (the first build takes a few minutes) …");
-    let out = cargo_actor::Cargo::new(world.clone())?.build(&source).await.context("build agent")?;
+    let out = cargo_actor::Cargo::new(world.clone())?.build(&source, false).await.context("build agent")?;
     std::fs::copy(&out.wasm, world.wasm_path("agent"))?;
     println!("Built in {:.1} s. Start the world with: sausage run {}", out.seconds, dir.display());
     Ok(())

cli/tests/crates/cargo-test-fail/Cargo.toml

@@ -0,0 +1,6 @@
+[package]
+name = "cargo-test-fail"
+version = "0.1.0"
+edition = "2024"
+
+[workspace]

cli/tests/crates/cargo-test-fail/src/main.rs

@@ -0,0 +1,9 @@
+fn main() {}
+
+#[cfg(test)]
+mod tests {
+    #[test]
+    fn deliberate_unit_test_failure() {
+        assert_eq!(2 + 2, 5);
+    }
+}

cli/tests/crates/cargo-valid/src/main.rs

@@ -1 +1,9 @@
 fn main() {}
+
+#[cfg(test)]
+mod tests {
+    #[test]
+    fn unit_tests_run_on_the_host_target() {
+        assert_eq!(2 + 2, 4);
+    }
+}

cli/tests/host.rs

@@ -619,9 +619,10 @@ async fn unknown_broker_request_lists_the_known_ones() {
 }
 
 #[tokio::test]
-async fn cargo_actor_builds_valid_crates_and_reports_compiler_errors() {
+async fn cargo_actor_runs_unit_tests_by_default_and_can_skip_them() {
     let world = create_world("cargo-actor");
     let (host, mut mailbox) = start(&world).await;
+
     let valid_source = cargo_source("cargo-valid");
     let valid_id = host.broker.send(
         "console",
@@ -630,12 +631,42 @@ async fn cargo_actor_builds_valid_crates_and_reports_compiler_errors() {
         None,
         json!({"type": "build", "source": valid_source.display().to_string()}),
     );
-    let built = receive_reply(&mut mailbox, &valid_id, Duration::from_secs(120)).await;
-    assert_eq!(built.body["type"], "built");
+    let built = receive_reply(&mut mailbox, &valid_id, Duration::from_secs(180)).await;
+    assert_eq!(built.body["type"], "built", "{built:?}");
+    assert_eq!(built.body["tests"]["passed"], 1);
+    assert_eq!(built.body["tests"]["failed"], 0);
+    assert!(built.body["tests"]["output"].as_str().unwrap().contains("unit_tests_run_on_the_host_target"));
     let wasm = built.body["wasm"].as_str().unwrap();
     assert!(wasm.ends_with(".wasm"));
     assert!(host.world.resolve("console", wasm).unwrap().is_file());
 
+    let failing_test_source = cargo_source("cargo-test-fail");
+    let failed_test_id = host.broker.send(
+        "console",
+        Some("cargo"),
+        None,
+        None,
+        json!({"type": "build", "source": failing_test_source.display().to_string()}),
+    );
+    let failed_test = receive_reply(&mut mailbox, &failed_test_id, Duration::from_secs(120)).await;
+    assert_eq!(failed_test.body["type"], "build_failed", "{failed_test:?}");
+    assert_eq!(failed_test.body["tests"]["passed"], 0);
+    assert_eq!(failed_test.body["tests"]["failed"], 1);
+    assert!(failed_test.body["tests"]["output"].as_str().unwrap().contains("deliberate_unit_test_failure"));
+
+    let skipped_id = host.broker.send(
+        "console",
+        Some("cargo"),
+        None,
+        None,
+        json!({"type": "build", "source": failing_test_source.display().to_string(), "skip_tests": true}),
+    );
+    let skipped = receive_reply(&mut mailbox, &skipped_id, Duration::from_secs(120)).await;
+    assert_eq!(skipped.body["type"], "built", "{skipped:?}");
+    assert_eq!(skipped.body["tests"]["passed"], 0);
+    assert_eq!(skipped.body["tests"]["failed"], 0);
+    assert_eq!(skipped.body["tests"]["output"], "skipped (skip_tests=true)");
+
     let invalid_source = cargo_source("cargo-fail");
     let invalid_id = host.broker.send(
         "console",
@@ -644,14 +675,10 @@ async fn cargo_actor_builds_valid_crates_and_reports_compiler_errors() {
         None,
         json!({"type": "build", "source": invalid_source.display().to_string()}),
     );
-    let failed = receive_reply(&mut mailbox, &invalid_id, Duration::from_secs(120)).await;
-    assert_eq!(failed.body["type"], "build_failed");
-    assert!(
-        failed.body["errors"]
-            .as_str()
-            .unwrap()
-            .contains("missing_function")
-    );
+    let invalid = receive_reply(&mut mailbox, &invalid_id, Duration::from_secs(120)).await;
+    assert_eq!(invalid.body["type"], "build_failed", "{invalid:?}");
+    assert_eq!(invalid.body["tests"]["failed"], 1);
+    assert!(invalid.body["tests"]["output"].as_str().unwrap().contains("missing_function"));
 
     host.stop().await;
 }

flake.lock

@@ -1,5 +1,20 @@
 {
   "nodes": {
+    "crane": {
+      "locked": {
+        "lastModified": 1791754810,
+        "narHash": "sha256-cN0Mgk+sQtCJcGWs9H4M0CnLRAuC4I8aCwiBTcBJs6E=",
+        "owner": "ipetkov",
+        "repo": "crane",
+        "rev": "bd63bf1d0a0f6dcacd7549c714a671ee63b0db6a",
+        "type": "github"
+      },
+      "original": {
+        "owner": "ipetkov",
+        "repo": "crane",
+        "type": "github"
+      }
+    },
     "flake-utils": {
       "inputs": {
         "systems": "systems"
@@ -36,6 +51,7 @@
     },
     "root": {
       "inputs": {
+        "crane": "crane",
         "flake-utils": "flake-utils",
         "nixpkgs": "nixpkgs",
         "rust-overlay": "rust-overlay"

flake.nix

@@ -6,9 +6,10 @@
     flake-utils.url = "github:numtide/flake-utils";
     rust-overlay.url = "github:oxalica/rust-overlay";
     rust-overlay.inputs.nixpkgs.follows = "nixpkgs";
+    crane.url = "github:ipetkov/crane";
   };
 
-  outputs = { nixpkgs, flake-utils, rust-overlay, ... }:
+  outputs = { nixpkgs, flake-utils, rust-overlay, crane, ... }:
     flake-utils.lib.eachSystem flake-utils.lib.allSystems (system:
       let
         pkgs = import nixpkgs {
@@ -20,21 +21,39 @@
           targets = [ "wasm32-wasip2" ];
           extensions = [ "rust-src" ];
         };
-        rustPlatform = pkgs.makeRustPlatform { cargo = rust; rustc = rust; };
-        sausage = rustPlatform.buildRustPackage {
+        # The runtime cargo actor needs Cargo, rustc (with wasm32-wasip2), and
+        # the native linker, even when the host itself is started with a bare
+        # PATH. Keep this same runtime path in the packaged host and exercise
+        # the installed binary below with PATH deliberately empty.
+        runtimePath = pkgs.lib.makeBinPath [ rust pkgs.stdenv.cc ];
+        craneLib = (crane.mkLib pkgs).overrideToolchain rust;
+        common = {
           pname = "sausage";
           version = "0.1.0";
           src = ./.;
-          cargoLock.lockFile = ./Cargo.lock;
-          cargoBuildFlags = [ "-p" "sausage" ];
+        };
+        # The test packages for `checks.tests`.
+        testPackages = "-p sausage -p sausage-actor -p agent";
+        cargoArtifacts = craneLib.buildDepsOnly (common // {
+          doCheck = false;
+          # The dependencies of the host binary and of the tests.
+          buildPhaseCargoCommand = ''
+            cargoWithProfile build --locked -p sausage
+            cargoWithProfile test --locked --no-run ${testPackages}
+          '';
+        });
+        sausage = craneLib.buildPackage (common // {
+          inherit cargoArtifacts;
+          doNotRemoveReferencesToRustToolchain = true;
+          cargoExtraArgs = "--locked -p sausage";
           doCheck = false;
           nativeBuildInputs = [ pkgs.makeWrapper ];
           # The `cargo` actor runs cargo at runtime. Build scripts need a C linker.
           postInstall = ''
-            wrapProgram $out/bin/sausage --prefix PATH : ${pkgs.lib.makeBinPath [ rust pkgs.stdenv.cc ]}
+            wrapProgram $out/bin/sausage --prefix PATH : ${runtimePath}
           '';
           meta.mainProgram = "sausage";
-        };
+        });
         # `nix run .#loop -- <world>` runs the newest `sausage run <world>`
         # (without a folder: bare `sausage`, i.e. ./world, created if needed)
         # from the public repo, again and again: after a crash or a broker
@@ -62,15 +81,82 @@
         # `nix flake check` runs every test of the host, the SDK, and the
         # agent. The tests build WASM actors with cargo, offline, from the
         # vendored crates of Cargo.lock.
-        checks.tests = sausage.overrideAttrs (old: {
-          pname = "sausage-tests";
-          doCheck = true;
-          cargoTestFlags = [ "-p" "sausage" "-p" "sausage-actor" "-p" "agent" ];
+        # The binary the host loop runs (`nix run`), built from the same
+        # cached dependencies as the tests.
+        checks.package = sausage;
+        checks.tests = craneLib.cargoTest (common // {
+          inherit cargoArtifacts;
+          cargoExtraArgs = "--locked ${testPackages}";
+          # Nothing builds on the test run's target folder: don't store it.
+          doInstallCargoArtifacts = false;
           preCheck = ''
             # Its own lock file pins crates that the vendored set may lack.
             rm -f cli/tests/actors/toolbox/Cargo.lock
           '';
         });
+        # Exercise the installed host exactly as the loop launches it: the
+        # caller has no Cargo on PATH, so only the packaged runtime toolchain
+        # can run the native tests and the wasm32-wasip2 build.
+        checks.runtime-toolchain = pkgs.runCommand "sausage-runtime-toolchain" { } ''
+          set -eu
+          root="$TMPDIR/runtime-toolchain"
+          world="$root/world"
+          emptyPath="$root/empty-bin"
+          mkdir -p "$emptyPath" "$root/home" "$root/cargo-home"
+          for actor in broker console cargo fs; do
+            mkdir -p "$world/actor/$actor/public" "$world/actor/$actor/data"
+          done
+          source="$world/actor/console/public/probe"
+          mkdir -p "$source/src" "$source/tests"
+          cat > "$source/Cargo.toml" <<'TOML'
+          [package]
+          name = "runtime-probe"
+          version = "0.1.0"
+          edition = "2024"
+          TOML
+          printf 'fn main() {}\n' > "$source/src/main.rs"
+          cat > "$source/tests/probe.rs" <<'RUST'
+          #[test]
+          fn native_test_harness_runs() {
+              assert_eq!(2 + 2, 4);
+          }
+          RUST
+          echo "runtime-check: run packaged host with an empty PATH"
+          coproc host {
+            ${pkgs.coreutils}/bin/env -i PATH="$emptyPath" HOME="$root/home" TMPDIR="$root" \
+              CARGO_HOME="$root/cargo-home" ${sausage}/bin/sausage run "$world"
+          }
+          hostInput=''${host[1]}
+          hostOutput=''${host[0]}
+          hostPid=$host_PID
+          trap 'kill "$hostPid" 2>/dev/null || true' EXIT
+          printf '%s\n' '@cargo {"type":"build","source":"/actor/console/public/probe"}' >&"$hostInput"
+          built=0
+          while IFS= read -r -t 300 line <&"$hostOutput"; do
+            echo "$line"
+            case "$line" in
+              *'"type":"build_failed"'*)
+                echo "packaged cargo actor build failed with an empty caller PATH" >&2
+                exit 1
+                ;;
+              *'"type":"built"'*)
+                case "$line" in
+                  *'"passed":1'*) built=1 ;;
+                  *) echo "native test did not pass" >&2; exit 1 ;;
+                esac
+                break
+                ;;
+            esac
+          done
+          if [ "$built" -ne 1 ]; then
+            echo "packaged host did not build the probe" >&2
+            exit 1
+          fi
+          printf '%s\n' '/quit' >&"$hostInput"
+          wait "$hostPid"
+          mkdir -p "$out"
+          touch "$out/passed"
+        '';
 
         apps.default = { type = "app"; program = "${sausage}/bin/sausage"; };
         apps.loop = { type = "app"; program = "${loop}/bin/sausage-loop"; };