Merge remote-tracking branch 'origin/main' into feat/lancedb-backend

FEATURE_PARITY.md

@@ -39,7 +39,7 @@ This document tracks feature parity between IronClaw (Rust implementation) and O
 | Network modes (loopback/LAN/remote) | ✅ | 🚧 | HTTP only |
 | OpenAI-compatible HTTP API | ✅ | ✅ | /v1/chat/completions, per-request `model` override |
 | Canvas hosting | ✅ | ❌ | Agent-driven UI |
-| Gateway lock (PID-based) | ✅ | ❌ | |
+| Gateway lock (PID-based) | ✅ | ✅ | `fs4` flock-based, acquired in `main.rs` before agent startup |
 | launchd/systemd integration | ✅ | ❌ | |
 | Bonjour/mDNS discovery | ✅ | ❌ | |
 | Tailscale integration | ✅ | ❌ | |

docker-compose.yml

@@ -3,7 +3,7 @@ services:
   postgres:
     image: pgvector/pgvector:pg16
     ports:
-      - "5432:5432"
+      - "127.0.0.1:5432:5432"
     environment:
       POSTGRES_DB: ironclaw
       POSTGRES_USER: ironclaw

src/app.rs

@@ -255,15 +255,18 @@ impl AppBuilder {
                     self.libsql_db.take();
                 }
 
-                // Re-resolve config with OS credentials
-                if let Some(ref db) = self.db {
-                    let toml_path = self.toml_path.as_deref();
-                    if let Ok(refreshed) =
-                        Config::from_db_with_toml(db.as_ref(), "default", toml_path).await
-                    {
-                        self.config = refreshed;
-                        tracing::debug!("LlmConfig re-resolved after OS credential injection");
-                    }
+                // Re-resolve only the LLM config with OS credentials.
+                let store: Option<&(dyn crate::db::SettingsStore + Sync)> =
+                    self.db.as_ref().map(|db| db.as_ref() as _);
+                let toml_path = self.toml_path.as_deref();
+                if let Err(e) = self
+                    .config
+                    .re_resolve_llm(store, "default", toml_path)
+                    .await
+                {
+                    tracing::warn!(
+                        "Failed to re-resolve LLM config after OS credential injection: {e}"
+                    );
                 }
 
                 return Ok(());
@@ -308,18 +311,16 @@ impl AppBuilder {
             // Inject LLM API keys from encrypted storage
             crate::config::inject_llm_keys_from_secrets(secrets.as_ref(), "default").await;
 
-            // Re-resolve config with newly available keys
-            if let Some(ref db) = self.db {
-                let toml_path = self.toml_path.as_deref();
-                match Config::from_db_with_toml(db.as_ref(), "default", toml_path).await {
-                    Ok(refreshed) => {
-                        self.config = refreshed;
-                        tracing::debug!("LlmConfig re-resolved after secret injection");
-                    }
-                    Err(e) => {
-                        tracing::warn!("Failed to re-resolve config after secret injection: {}", e);
-                    }
-                }
+            // Re-resolve only the LLM config with newly available keys.
+            let store: Option<&(dyn crate::db::SettingsStore + Sync)> =
+                self.db.as_ref().map(|db| db.as_ref() as _);
+            let toml_path = self.toml_path.as_deref();
+            if let Err(e) = self
+                .config
+                .re_resolve_llm(store, "default", toml_path)
+                .await
+            {
+                tracing::warn!("Failed to re-resolve LLM config after secret injection: {e}");
             }
         }
 

src/bootstrap.rs

@@ -414,10 +414,103 @@ pub enum MigrationError {
     Io(String),
 }
 
+// ── PID Lock ──────────────────────────────────────────────────────────────
+
+/// Path to the PID lock file: `~/.ironclaw/ironclaw.pid`.
+pub fn pid_lock_path() -> PathBuf {
+    ironclaw_base_dir().join("ironclaw.pid")
+}
+
+/// A PID-based lock that prevents multiple IronClaw instances from running
+/// simultaneously.
+///
+/// Uses `fs4::try_lock_exclusive()` for atomic locking (no TOCTOU race),
+/// then writes the current PID into the locked file for diagnostics.
+/// The OS-level lock is held for the lifetime of this struct and
+/// automatically released on drop (along with the PID file cleanup).
+#[derive(Debug)]
+pub struct PidLock {
+    path: PathBuf,
+    /// Held open to maintain the OS-level exclusive lock.
+    _file: std::fs::File,
+}
+
+/// Errors from PID lock acquisition.
+#[derive(Debug, thiserror::Error)]
+pub enum PidLockError {
+    #[error("Another IronClaw instance is already running (PID {pid})")]
+    AlreadyRunning { pid: u32 },
+    #[error("Failed to acquire PID lock: {0}")]
+    Io(#[from] std::io::Error),
+}
+
+impl PidLock {
+    /// Try to acquire the PID lock.
+    ///
+    /// Uses an exclusive file lock (`flock`/`LockFileEx`) so that two
+    /// concurrent processes cannot both acquire the lock — no TOCTOU race.
+    /// If the lock file exists but the holding process is gone (stale),
+    /// the lock is reclaimed automatically by the OS.
+    pub fn acquire() -> Result<Self, PidLockError> {
+        Self::acquire_at(pid_lock_path())
+    }
+
+    /// Acquire at a specific path (for testing).
+    fn acquire_at(path: PathBuf) -> Result<Self, PidLockError> {
+        use fs4::FileExt;
+        use std::fs::OpenOptions;
+        use std::io::Write;
+
+        // Ensure parent directory exists
+        if let Some(parent) = path.parent() {
+            std::fs::create_dir_all(parent)?;
+        }
+
+        // Open (or create) the lock file
+        let mut file = OpenOptions::new()
+            .read(true)
+            .write(true)
+            .create(true)
+            .truncate(false)
+            .open(&path)?;
+
+        // Try non-blocking exclusive lock — if another process holds it,
+        // this fails immediately instead of blocking.
+        if let Err(e) = file.try_lock_exclusive() {
+            if e.kind() == std::io::ErrorKind::WouldBlock {
+                // Lock held by another process — read its PID for the error message
+                let pid = std::fs::read_to_string(&path)
+                    .ok()
+                    .and_then(|s| s.trim().parse::<u32>().ok())
+                    .unwrap_or(0);
+                return Err(PidLockError::AlreadyRunning { pid });
+            }
+            // Other errors (permissions, unsupported filesystem, etc.)
+            return Err(PidLockError::Io(e));
+        }
+
+        // We hold the exclusive lock — write our PID
+        file.set_len(0)?; // truncate
+        write!(file, "{}", std::process::id())?;
+
+        Ok(PidLock { path, _file: file })
+    }
+}
+
+impl Drop for PidLock {
+    fn drop(&mut self) {
+        // Remove the PID file; the OS-level lock is released when _file is dropped.
+        let _ = std::fs::remove_file(&self.path);
+    }
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
+    use std::process::Command;
     use std::sync::Mutex;
+    use std::thread;
+    use std::time::{Duration, Instant};
     use tempfile::tempdir;
 
     static ENV_MUTEX: Mutex<()> = Mutex::new(());
@@ -986,4 +1079,162 @@ INJECTED="pwned"#;
             unsafe { std::env::remove_var("IRONCLAW_BASE_DIR") };
         }
     }
+
+    // ── PID Lock tests ───────────────────────────────────────────────
+
+    #[test]
+    fn test_pid_lock_acquire_and_drop() {
+        let dir = tempdir().unwrap();
+        let pid_path = dir.path().join("ironclaw.pid");
+
+        // Acquire lock
+        let lock = PidLock::acquire_at(pid_path.clone()).unwrap();
+        assert!(pid_path.exists());
+
+        // PID file should contain our PID
+        let contents = std::fs::read_to_string(&pid_path).unwrap();
+        assert_eq!(contents.trim().parse::<u32>().unwrap(), std::process::id());
+
+        // Drop should remove the file
+        drop(lock);
+        assert!(!pid_path.exists());
+    }
+
+    #[test]
+    fn test_pid_lock_rejects_second_acquire() {
+        let dir = tempdir().unwrap();
+        let pid_path = dir.path().join("ironclaw.pid");
+
+        // First lock succeeds
+        let _lock1 = PidLock::acquire_at(pid_path.clone()).unwrap();
+
+        // Second acquire on same file must fail (exclusive flock held)
+        let result = PidLock::acquire_at(pid_path.clone());
+        assert!(result.is_err());
+        match result.unwrap_err() {
+            PidLockError::AlreadyRunning { pid } => {
+                assert_eq!(pid, std::process::id());
+            }
+            other => panic!("expected AlreadyRunning, got: {}", other),
+        }
+    }
+
+    #[test]
+    fn test_pid_lock_reclaims_after_drop() {
+        let dir = tempdir().unwrap();
+        let pid_path = dir.path().join("ironclaw.pid");
+
+        // Acquire and release
+        let lock = PidLock::acquire_at(pid_path.clone()).unwrap();
+        drop(lock);
+
+        // Should succeed — OS lock was released on drop
+        let lock2 = PidLock::acquire_at(pid_path).unwrap();
+        drop(lock2);
+    }
+
+    #[test]
+    fn test_pid_lock_reclaims_stale_file_without_flock() {
+        let dir = tempdir().unwrap();
+        let pid_path = dir.path().join("ironclaw.pid");
+
+        // Write a stale PID file manually (no flock held)
+        std::fs::write(&pid_path, "4294967294").unwrap();
+
+        // Should succeed because no OS lock is held on the file
+        let lock = PidLock::acquire_at(pid_path.clone()).unwrap();
+        let contents = std::fs::read_to_string(&pid_path).unwrap();
+        assert_eq!(contents.trim().parse::<u32>().unwrap(), std::process::id());
+        drop(lock);
+    }
+
+    #[test]
+    fn test_pid_lock_handles_corrupt_pid_file() {
+        let dir = tempdir().unwrap();
+        let pid_path = dir.path().join("ironclaw.pid");
+
+        // Write garbage (no flock held)
+        std::fs::write(&pid_path, "not-a-number").unwrap();
+
+        // Should succeed — no OS lock held, file is reclaimed
+        let lock = PidLock::acquire_at(pid_path).unwrap();
+        drop(lock);
+    }
+
+    #[test]
+    fn test_pid_lock_creates_parent_dirs() {
+        let dir = tempdir().unwrap();
+        let pid_path = dir.path().join("nested").join("deep").join("ironclaw.pid");
+
+        let lock = PidLock::acquire_at(pid_path.clone()).unwrap();
+        assert!(pid_path.exists());
+        drop(lock);
+    }
+
+    #[test]
+    fn test_pid_lock_child_helper_holds_lock() {
+        if std::env::var("IRONCLAW_PID_LOCK_CHILD").ok().as_deref() != Some("1") {
+            return;
+        }
+
+        let pid_path = PathBuf::from(
+            std::env::var("IRONCLAW_PID_LOCK_PATH").expect("IRONCLAW_PID_LOCK_PATH missing"),
+        );
+        let hold_ms = std::env::var("IRONCLAW_PID_LOCK_HOLD_MS")
+            .ok()
+            .and_then(|s| s.parse::<u64>().ok())
+            .unwrap_or(3000);
+
+        let _lock = PidLock::acquire_at(pid_path).expect("child failed to acquire pid lock");
+        thread::sleep(Duration::from_millis(hold_ms));
+    }
+
+    #[test]
+    fn test_pid_lock_rejects_lock_held_by_other_process() {
+        let dir = tempdir().unwrap();
+        let pid_path = dir.path().join("ironclaw.pid");
+
+        let current_exe = std::env::current_exe().unwrap();
+        let mut child = Command::new(current_exe)
+            .args([
+                "--exact",
+                "bootstrap::tests::test_pid_lock_child_helper_holds_lock",
+                "--nocapture",
+                "--test-threads=1",
+            ])
+            .env("IRONCLAW_PID_LOCK_CHILD", "1")
+            .env("IRONCLAW_PID_LOCK_PATH", pid_path.display().to_string())
+            .env("IRONCLAW_PID_LOCK_HOLD_MS", "3000")
+            .spawn()
+            .unwrap();
+
+        let started = Instant::now();
+        while started.elapsed() < Duration::from_secs(2) {
+            if pid_path.exists() {
+                break;
+            }
+            if let Some(status) = child.try_wait().unwrap() {
+                panic!("child exited before acquiring lock: {}", status);
+            }
+            thread::sleep(Duration::from_millis(20));
+        }
+        assert!(
+            pid_path.exists(),
+            "child did not create lock file in time: {}",
+            pid_path.display()
+        );
+
+        let result = PidLock::acquire_at(pid_path.clone());
+        match result.unwrap_err() {
+            PidLockError::AlreadyRunning { .. } => {}
+            other => panic!("expected AlreadyRunning, got: {}", other),
+        }
+
+        let status = child.wait().unwrap();
+        assert!(status.success(), "child process failed: {}", status);
+
+        // After the child exits, lock should be released and reacquirable.
+        let lock = PidLock::acquire_at(pid_path).unwrap();
+        drop(lock);
+    }
 }

src/channels/repl.rs

@@ -18,7 +18,7 @@
 //! - `Esc` - Interrupt current operation
 
 use std::borrow::Cow;
-use std::io::{self, Write};
+use std::io::{self, IsTerminal, Write};
 use std::sync::Arc;
 use std::sync::atomic::{AtomicBool, Ordering};
 
@@ -303,6 +303,9 @@ impl Channel for ReplChannel {
             if let Some(msg) = single_message {
                 let incoming = IncomingMessage::new("repl", "default", &msg).with_timezone(&sys_tz);
                 let _ = tx.blocking_send(incoming);
+                // Ensure the agent exits after handling exactly one turn in -m mode,
+                // even when other channels (gateway/http) are enabled.
+                let _ = tx.blocking_send(IncomingMessage::new("repl", "default", "/quit"));
                 return;
             }
 
@@ -408,10 +411,15 @@ impl Channel for ReplChannel {
                         }
                     }
                     Err(ReadlineError::Eof) => {
-                        // Ctrl+D: send /quit so the agent loop runs graceful shutdown
-                        let msg =
-                            IncomingMessage::new("repl", "default", "/quit").with_timezone(&sys_tz);
-                        let _ = tx.blocking_send(msg);
+                        // Ctrl+D in interactive mode: graceful shutdown.
+                        // In daemon mode (stdin = /dev/null, no TTY), EOF arrives
+                        // immediately — just drop the REPL thread silently so other
+                        // channels (gateway, telegram, …) keep running.
+                        if std::io::stdin().is_terminal() {
+                            let msg = IncomingMessage::new("repl", "default", "/quit")
+                                .with_timezone(&sys_tz);
+                            let _ = tx.blocking_send(msg);
+                        }
                         break;
                     }
                     Err(e) => {
@@ -621,3 +629,29 @@ impl Channel for ReplChannel {
         Ok(())
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use futures::StreamExt;
+
+    use super::*;
+
+    #[tokio::test]
+    async fn single_message_mode_sends_message_then_quit() {
+        let repl = ReplChannel::with_message("hi".to_string());
+        let mut stream = repl.start().await.expect("repl start should succeed");
+
+        let first = stream.next().await.expect("first message missing");
+        assert_eq!(first.channel, "repl");
+        assert_eq!(first.content, "hi");
+
+        let second = stream.next().await.expect("quit message missing");
+        assert_eq!(second.channel, "repl");
+        assert_eq!(second.content, "/quit");
+
+        assert!(
+            stream.next().await.is_none(),
+            "stream should end after /quit"
+        );
+    }
+}

src/channels/web/static/app.js

@@ -1481,7 +1481,7 @@ chatInput.addEventListener('keydown', (e) => {
     }
   }
 
-  if (e.key === 'Enter' && !e.shiftKey) {
+  if (e.key === 'Enter' && !e.shiftKey && !e.isComposing) {
     e.preventDefault();
     hideSlashAutocomplete();
     sendMessage();

src/cli/status.rs

@@ -8,9 +8,35 @@ use std::path::PathBuf;
 use crate::bootstrap::ironclaw_base_dir;
 use crate::settings::Settings;
 
+/// Load settings from JSON and TOML config files, matching the runtime
+/// priority: TOML overlay > settings.json > defaults.
+///
+/// This mirrors the loading chain in `Config::from_env_with_toml()` but
+/// without resolving the full `Config` (which requires async + secrets).
+fn load_settings() -> Settings {
+    load_settings_from(&Settings::default_path(), &Settings::default_toml_path())
+}
+
+/// Inner implementation with injectable paths (testable).
+fn load_settings_from(json_path: &std::path::Path, toml_path: &std::path::Path) -> Settings {
+    let mut settings = Settings::load_from(json_path);
+
+    match Settings::load_toml(toml_path) {
+        Ok(Some(toml_settings)) => {
+            settings.merge_from(&toml_settings);
+        }
+        Ok(None) => {} // File not found — fine for default path
+        Err(e) => {
+            eprintln!("Warning: failed to parse {}: {}", toml_path.display(), e);
+        }
+    }
+
+    settings
+}
+
 /// Run the status command, printing system health info.
 pub async fn run_status_command() -> anyhow::Result<()> {
-    let settings = Settings::default();
+    let settings = load_settings();
 
     println!("IronClaw Status");
     println!("===============\n");
@@ -209,3 +235,99 @@ fn default_tools_dir() -> PathBuf {
 fn default_channels_dir() -> PathBuf {
     ironclaw_base_dir().join("channels")
 }
+
+#[cfg(test)]
+mod tests {
+    use super::load_settings_from;
+
+    /// Regression test for #354: load_settings_from must read config.toml.
+    #[test]
+    fn reads_toml_heartbeat_enabled() {
+        let dir = tempfile::tempdir().expect("tempdir");
+        let json_path = dir.path().join("settings.json");
+        let toml_path = dir.path().join("config.toml");
+
+        // No JSON file — only TOML
+        std::fs::write(
+            &toml_path,
+            "[heartbeat]\nenabled = true\ninterval_secs = 600",
+        )
+        .expect("write toml");
+
+        let settings = load_settings_from(&json_path, &toml_path);
+        assert!(settings.heartbeat.enabled);
+        assert_eq!(settings.heartbeat.interval_secs, 600);
+    }
+
+    /// Without any config files, defaults are returned.
+    #[test]
+    fn defaults_without_config_files() {
+        let dir = tempfile::tempdir().expect("tempdir");
+        let settings = load_settings_from(
+            &dir.path().join("nonexistent.json"),
+            &dir.path().join("nonexistent.toml"),
+        );
+        assert!(!settings.heartbeat.enabled);
+    }
+
+    /// settings.json is respected.
+    #[test]
+    fn reads_json_heartbeat_enabled() {
+        let dir = tempfile::tempdir().expect("tempdir");
+        let json_path = dir.path().join("settings.json");
+        let toml_path = dir.path().join("nonexistent.toml");
+
+        std::fs::write(
+            &json_path,
+            r#"{"heartbeat":{"enabled":true,"interval_secs":900}}"#,
+        )
+        .expect("write json");
+
+        let settings = load_settings_from(&json_path, &toml_path);
+        assert!(settings.heartbeat.enabled);
+        assert_eq!(settings.heartbeat.interval_secs, 900);
+    }
+
+    /// TOML overlay wins over JSON settings.
+    #[test]
+    fn toml_overlay_wins_over_json() {
+        let dir = tempfile::tempdir().expect("tempdir");
+        let json_path = dir.path().join("settings.json");
+        let toml_path = dir.path().join("config.toml");
+
+        std::fs::write(
+            &json_path,
+            r#"{"heartbeat":{"enabled":false,"interval_secs":100}}"#,
+        )
+        .expect("write json");
+        std::fs::write(
+            &toml_path,
+            "[heartbeat]\nenabled = true\ninterval_secs = 200",
+        )
+        .expect("write toml");
+
+        let settings = load_settings_from(&json_path, &toml_path);
+        assert!(settings.heartbeat.enabled);
+        assert_eq!(settings.heartbeat.interval_secs, 200);
+    }
+
+    /// Invalid TOML is warned but doesn't crash; falls back to JSON/defaults.
+    #[test]
+    fn invalid_toml_falls_back_gracefully() {
+        let dir = tempfile::tempdir().expect("tempdir");
+        let json_path = dir.path().join("settings.json");
+        let toml_path = dir.path().join("config.toml");
+
+        std::fs::write(
+            &json_path,
+            r#"{"heartbeat":{"enabled":true,"interval_secs":500}}"#,
+        )
+        .expect("write json");
+        std::fs::write(&toml_path, "this is not valid toml [[[").expect("write bad toml");
+
+        let settings = load_settings_from(&json_path, &toml_path);
+        // Should fall back to JSON values, not crash
+        assert!(settings.heartbeat.enabled);
+        assert_eq!(settings.heartbeat.interval_secs, 500);
+    }
+}

src/config/mod.rs

@@ -262,6 +262,32 @@ impl Config {
         Ok(())
     }
 
+    /// Re-resolve only the LLM config after credential injection.
+    ///
+    /// Called by `AppBuilder::init_secrets()` after injecting API keys into
+    /// the env overlay. Only rebuilds `self.llm` — all other config fields
+    /// are unaffected, preserving values from the initial config load (or
+    /// from `Config::for_testing()` in test mode).
+    pub async fn re_resolve_llm(
+        &mut self,
+        store: Option<&(dyn crate::db::SettingsStore + Sync)>,
+        user_id: &str,
+        toml_path: Option<&std::path::Path>,
+    ) -> Result<(), ConfigError> {
+        let settings = if let Some(store) = store {
+            let mut s = match store.get_all_settings(user_id).await {
+                Ok(map) => Settings::from_db_map(&map),
+                Err(_) => Settings::default(),
+            };
+            Self::apply_toml_overlay(&mut s, toml_path)?;
+            s
+        } else {
+            Settings::default()
+        };
+        self.llm = LlmConfig::resolve(&settings)?;
+        Ok(())
+    }
+
     /// Build config from settings (shared by from_env and from_db).
     async fn build(settings: &Settings) -> Result<Self, ConfigError> {
         Ok(Self {

src/main.rs

@@ -145,6 +145,24 @@ async fn async_main() -> anyhow::Result<()> {
         }
     }
 
+    // ── PID lock (prevent multiple instances) ────────────────────────
+    let _pid_lock = match ironclaw::bootstrap::PidLock::acquire() {
+        Ok(lock) => Some(lock),
+        Err(ironclaw::bootstrap::PidLockError::AlreadyRunning { pid }) => {
+            anyhow::bail!(
+                "Another IronClaw instance is already running (PID {}). \
+                 If this is incorrect, remove the stale PID file: {}",
+                pid,
+                ironclaw::bootstrap::pid_lock_path().display()
+            );
+        }
+        Err(e) => {
+            eprintln!("Warning: Could not acquire PID lock: {}", e);
+            eprintln!("Continuing without PID lock protection.");
+            None
+        }
+    };
+
     // ── Agent startup ──────────────────────────────────────────────────
 
     // Enhanced first-run detection
@@ -166,13 +184,12 @@ async fn async_main() -> anyhow::Result<()> {
     let config = match Config::from_env_with_toml(toml_path).await {
         Ok(c) => c,
         Err(ironclaw::error::ConfigError::MissingRequired { key, hint }) => {
-            eprintln!("Configuration error: Missing required setting '{}'", key);
-            eprintln!("  {}", hint);
-            eprintln!();
-            eprintln!(
-                "Run 'ironclaw onboard' to configure, or set the required environment variables."
+            anyhow::bail!(
+                "Configuration error: Missing required setting '{}'. {}. \
+                 Run 'ironclaw onboard' to configure, or set the required environment variables.",
+                key,
+                hint
             );
-            std::process::exit(1);
         }
         Err(e) => return Err(e.into()),
     };

tests/e2e_builtin_tool_coverage.rs

@@ -242,6 +242,16 @@ mod tests {
             "create_job should return a job_id: {:?}",
             create_result.1
         );
+        assert!(
+            create_result.1.contains("in_progress"),
+            "create_job should dispatch through the scheduler, not stay pending: {:?}",
+            create_result.1
+        );
+        assert!(
+            !create_result.1.contains("scheduler unavailable"),
+            "create_job should not fall back to the unscheduled path: {:?}",
+            create_result.1
+        );
         let status_result = results
             .iter()
             .find(|(n, _)| n == "job_status")

tests/support/test_rig.rs

@@ -545,16 +545,14 @@ impl TestRigBuilder {
             .await
             .expect("AppBuilder::build_all() failed in test rig");
 
+        let scheduler_slot: ironclaw::tools::builtin::SchedulerSlot =
+            Arc::new(tokio::sync::RwLock::new(None));
+
         // 6. Register job tools, routine tools, and extra tools.
         {
-            use ironclaw::context::ContextManager;
-
-            let ctx_mgr = Arc::new(ContextManager::new(
-                components.config.agent.max_parallel_jobs,
-            ));
             components.tools.register_job_tools(
-                ctx_mgr,
-                None,
+                Arc::clone(&components.context_manager),
+                Some(scheduler_slot.clone()),
                 None,
                 components.db.clone(),
                 None,
@@ -657,10 +655,13 @@ impl TestRigBuilder {
             None, // heartbeat_config
             None, // hygiene_config
             routine_config,
-            None, // context_manager
+            Some(Arc::clone(&components.context_manager)),
             None, // session_manager
         );
 
+        // Match main.rs: fill the scheduler slot once Agent::new has created it.
+        *scheduler_slot.write().await = Some(agent.scheduler());
+
         // 9. Spawn agent in background task.
         let agent_handle = tokio::spawn(async move {
             if let Err(e) = agent.run().await {

tests/support/trace_llm.rs

@@ -513,32 +513,41 @@ impl LlmProvider for TraceLlm {
     }
 
     async fn complete(&self, request: CompletionRequest) -> Result<CompletionResponse, LlmError> {
-        let step = self.next_step(&request.messages)?;
-        match step.response {
-            TraceResponse::Text {
-                content,
-                input_tokens,
-                output_tokens,
-            } => Ok(CompletionResponse {
-                content,
-                input_tokens,
-                output_tokens,
-                finish_reason: FinishReason::Stop,
-                cache_read_input_tokens: 0,
-                cache_creation_input_tokens: 0,
-            }),
-            TraceResponse::ToolCalls { .. } => Err(LlmError::RequestFailed {
-                provider: self.model_name.clone(),
-                reason: "TraceLlm::complete() called but current step is a tool_calls response; \
-                         use complete_with_tools() instead"
-                    .to_string(),
-            }),
-            TraceResponse::UserInput { .. } => Err(LlmError::RequestFailed {
-                provider: self.model_name.clone(),
-                reason: "TraceLlm::complete() encountered a user_input step; \
-                         these should have been filtered out during construction"
-                    .to_string(),
-            }),
+        // complete() is called when Reasoning has force_text=true (no tools
+        // available). Skip any remaining ToolCalls steps in the trace and
+        // return the next Text step, since in real usage the LLM would
+        // produce text when no tools are offered.
+        loop {
+            let step = self.next_step(&request.messages)?;
+            match step.response {
+                TraceResponse::Text {
+                    content,
+                    input_tokens,
+                    output_tokens,
+                } => {
+                    return Ok(CompletionResponse {
+                        content,
+                        input_tokens,
+                        output_tokens,
+                        finish_reason: FinishReason::Stop,
+                        cache_read_input_tokens: 0,
+                        cache_creation_input_tokens: 0,
+                    });
+                }
+                TraceResponse::ToolCalls { .. } => {
+                    // Skip tool_calls steps — complete() is called in
+                    // force_text mode so the LLM can't use tools anyway.
+                    continue;
+                }
+                TraceResponse::UserInput { .. } => {
+                    return Err(LlmError::RequestFailed {
+                        provider: self.model_name.clone(),
+                        reason: "TraceLlm::complete() encountered a user_input step; \
+                                 these should have been filtered out during construction"
+                            .to_string(),
+                    });
+                }
+            }
         }
     }
 

tests/support_unit_tests.rs

@@ -571,22 +571,29 @@ mod trace_llm_tests {
     }
 
     #[tokio::test]
-    async fn complete_errors_on_tool_calls_step() {
+    async fn complete_skips_tool_calls_step() {
+        // complete() is called in force_text mode where tools aren't available.
+        // When the trace has a ToolCalls step followed by a Text step, complete()
+        // should skip the ToolCalls and return the Text response.
         let trace = LlmTrace::single_turn(
             "test-model",
             "hi",
-            vec![tool_calls_step(vec![simple_tool_call("echo")], 10, 5)],
+            vec![
+                tool_calls_step(vec![simple_tool_call("echo")], 10, 5),
+                text_step("skipped past tools", 20, 8),
+            ],
         );
         let llm = TraceLlm::from_trace(trace);
 
-        let result = llm.complete(make_completion_request("hi")).await;
+        let resp = llm
+            .complete(make_completion_request("hi"))
+            .await
+            .expect("complete() should skip ToolCalls and return the Text step");
 
-        assert!(result.is_err());
-        let err_msg = result.unwrap_err().to_string();
-        assert!(
-            err_msg.contains("tool_calls"),
-            "Expected 'tool_calls' in error: {err_msg}"
-        );
+        assert_eq!(resp.content, "skipped past tools");
+        assert_eq!(resp.input_tokens, 20);
+        assert_eq!(resp.output_tokens, 8);
+        assert_eq!(resp.finish_reason, FinishReason::Stop);
     }
 
     #[tokio::test]