Files
optimclaw/src/agent/routine_engine.rs
T
3f135bdde9 fix: persist turns after approval and add agent-level tests (#250)
* fix: persist turns after approval and add agent-level tests

Port relevant changes from PR #112 that were not carried over to #237:

- Add persist_turn calls in process_approval for the response, error,
  and auth-required paths. Previously, turns completed after tool
  approval were never persisted to DB — if the process crashed after
  approval the entire turn (user message + assistant response) was lost.

- Add agent-level unit tests: StaticLlmProvider mock, make_test_agent
  helper, tests for auto-approval logic, destructive shell command
  detection, and PendingApproval backward-compatible deserialization
  (without deferred_tool_calls field).

- Remove unused _thread_state binding in process_approval.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: address 14 audit findings in src/agent/

Audit of the agent module found 2 High, 7 Medium, 3 Low, and 2 Nit
severity issues. This commit fixes all of them:

High:
- Remove 4 `.expect()` calls in session.rs (entry API, match, direct
  indexing, if-let) to eliminate panic paths in production
- Add typed RoutineError enum replacing Result<_, String> across
  routine.rs, routine_engine.rs, and callers in history/store.rs and
  db/libsql/mod.rs

Medium:
- Sanitize routine names in path construction to prevent directory
  traversal (routine_engine.rs)
- Log warnings for 5 silently-swallowed errors in scheduler.rs,
  compaction.rs, and worker.rs
- Extract shared handle_auth_intercept helper to deduplicate auth
  interception in thread_ops.rs
- Add session count warning threshold in session_manager.rs
- Make FullJob stub degradation visible via warn-level log and
  prepended warning in output

Low:
- Restrict dead code visibility with #[cfg(test)] on 19 unused items
  in submission.rs, task.rs, and undo.rs
- Narrow pub to pub(crate) on self_repair.rs builder methods
- Remove TaskStatus from mod.rs re-exports (test-only type)

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: address PR review comments

- Reorder persist_turn before persist_response_chain so the
  conversation row exists before the metadata UPDATE runs
- Add persist_response_chain call to handle_auth_intercept so
  auth-required paths preserve the response chain
- Harden sanitize_routine_name to use allowlist (alphanumeric,
  dash, underscore) instead of denylist replacements
- Fix stale active_thread ID in get_or_create_thread: fall back
  to create_thread() when the stored ID is missing from the map
- Persist turn on approval rejection so user messages survive
  crashes after a tool is rejected

Co-Authored-By: Claude Opus 4.6 <[email protected]>

---------

Co-authored-by: Claude Opus 4.6 <[email protected]>
2026-02-20 02:28:15 +00:00

635 lines
20 KiB
Rust

//! Routine execution engine.
//!
//! Handles loading routines, checking triggers, enforcing guardrails,
//! and executing both lightweight (single LLM call) and full-job routines.
//!
//! The engine runs two independent loops:
//! - A **cron ticker** that polls the DB every N seconds for due cron routines
//! - An **event matcher** called synchronously from the agent main loop
//!
//! Lightweight routines execute inline (single LLM call, no scheduler slot).
//! Full-job routines are delegated to the existing `Scheduler`.
use std::sync::Arc;
use std::sync::atomic::{AtomicUsize, Ordering};
use std::time::Duration;
use chrono::Utc;
use regex::Regex;
use tokio::sync::{RwLock, mpsc};
use uuid::Uuid;
use crate::agent::routine::{
NotifyConfig, Routine, RoutineAction, RoutineRun, RunStatus, Trigger, next_cron_fire,
};
use crate::channels::{IncomingMessage, OutgoingResponse};
use crate::config::RoutineConfig;
use crate::db::Database;
use crate::error::RoutineError;
use crate::llm::{ChatMessage, CompletionRequest, FinishReason, LlmProvider};
use crate::workspace::Workspace;
/// The routine execution engine.
pub struct RoutineEngine {
config: RoutineConfig,
store: Arc<dyn Database>,
llm: Arc<dyn LlmProvider>,
workspace: Arc<Workspace>,
/// Sender for notifications (routed to channel manager).
notify_tx: mpsc::Sender<OutgoingResponse>,
/// Currently running routine count (across all routines).
running_count: Arc<AtomicUsize>,
/// Compiled event regex cache: routine_id -> compiled regex.
event_cache: Arc<RwLock<Vec<(Uuid, Routine, Regex)>>>,
}
impl RoutineEngine {
pub fn new(
config: RoutineConfig,
store: Arc<dyn Database>,
llm: Arc<dyn LlmProvider>,
workspace: Arc<Workspace>,
notify_tx: mpsc::Sender<OutgoingResponse>,
) -> Self {
Self {
config,
store,
llm,
workspace,
notify_tx,
running_count: Arc::new(AtomicUsize::new(0)),
event_cache: Arc::new(RwLock::new(Vec::new())),
}
}
/// Refresh the in-memory event trigger cache from DB.
pub async fn refresh_event_cache(&self) {
match self.store.list_event_routines().await {
Ok(routines) => {
let mut cache = Vec::new();
for routine in routines {
if let Trigger::Event { ref pattern, .. } = routine.trigger {
match Regex::new(pattern) {
Ok(re) => cache.push((routine.id, routine.clone(), re)),
Err(e) => {
tracing::warn!(
routine = %routine.name,
"Invalid event regex '{}': {}",
pattern, e
);
}
}
}
}
let count = cache.len();
*self.event_cache.write().await = cache;
tracing::debug!("Refreshed event cache: {} routines", count);
}
Err(e) => {
tracing::error!("Failed to refresh event cache: {}", e);
}
}
}
/// Check incoming message against event triggers. Returns number of routines fired.
///
/// Called synchronously from the main loop after handle_message(). The actual
/// execution is spawned async so this returns quickly.
pub async fn check_event_triggers(&self, message: &IncomingMessage) -> usize {
let cache = self.event_cache.read().await;
let mut fired = 0;
for (_, routine, re) in cache.iter() {
// Channel filter
if let Trigger::Event {
channel: Some(ch), ..
} = &routine.trigger
&& ch != &message.channel
{
continue;
}
// Regex match
if !re.is_match(&message.content) {
continue;
}
// Cooldown check
if !self.check_cooldown(routine) {
tracing::debug!(routine = %routine.name, "Skipped: cooldown active");
continue;
}
// Concurrent run check
if !self.check_concurrent(routine).await {
tracing::debug!(routine = %routine.name, "Skipped: max concurrent reached");
continue;
}
// Global capacity check
if self.running_count.load(Ordering::Relaxed) >= self.config.max_concurrent_routines {
tracing::warn!(routine = %routine.name, "Skipped: global max concurrent reached");
continue;
}
let detail = truncate(&message.content, 200);
self.spawn_fire(routine.clone(), "event", Some(detail));
fired += 1;
}
fired
}
/// Check all due cron routines and fire them. Called by the cron ticker.
pub async fn check_cron_triggers(&self) {
let routines = match self.store.list_due_cron_routines().await {
Ok(r) => r,
Err(e) => {
tracing::error!("Failed to load due cron routines: {}", e);
return;
}
};
for routine in routines {
if self.running_count.load(Ordering::Relaxed) >= self.config.max_concurrent_routines {
tracing::warn!("Global max concurrent routines reached, skipping remaining");
break;
}
if !self.check_cooldown(&routine) {
continue;
}
if !self.check_concurrent(&routine).await {
continue;
}
let detail = if let Trigger::Cron { ref schedule } = routine.trigger {
Some(schedule.clone())
} else {
None
};
self.spawn_fire(routine, "cron", detail);
}
}
/// Fire a routine manually (from tool call or CLI).
pub async fn fire_manual(&self, routine_id: Uuid) -> Result<Uuid, RoutineError> {
let routine = self
.store
.get_routine(routine_id)
.await
.map_err(|e| RoutineError::Database {
reason: e.to_string(),
})?
.ok_or(RoutineError::NotFound { id: routine_id })?;
if !routine.enabled {
return Err(RoutineError::Disabled {
name: routine.name.clone(),
});
}
if !self.check_concurrent(&routine).await {
return Err(RoutineError::MaxConcurrent {
name: routine.name.clone(),
});
}
let run_id = Uuid::new_v4();
let run = RoutineRun {
id: run_id,
routine_id: routine.id,
trigger_type: "manual".to_string(),
trigger_detail: None,
started_at: Utc::now(),
completed_at: None,
status: RunStatus::Running,
result_summary: None,
tokens_used: None,
job_id: None,
created_at: Utc::now(),
};
if let Err(e) = self.store.create_routine_run(&run).await {
return Err(RoutineError::Database {
reason: format!("failed to create run record: {e}"),
});
}
// Execute inline for manual triggers (caller wants to wait)
let engine = EngineContext {
store: self.store.clone(),
llm: self.llm.clone(),
workspace: self.workspace.clone(),
notify_tx: self.notify_tx.clone(),
running_count: self.running_count.clone(),
max_lightweight_tokens: self.config.max_lightweight_tokens,
};
tokio::spawn(async move {
execute_routine(engine, routine, run).await;
});
Ok(run_id)
}
/// Spawn a fire in a background task.
fn spawn_fire(&self, routine: Routine, trigger_type: &str, trigger_detail: Option<String>) {
let run = RoutineRun {
id: Uuid::new_v4(),
routine_id: routine.id,
trigger_type: trigger_type.to_string(),
trigger_detail,
started_at: Utc::now(),
completed_at: None,
status: RunStatus::Running,
result_summary: None,
tokens_used: None,
job_id: None,
created_at: Utc::now(),
};
let engine = EngineContext {
store: self.store.clone(),
llm: self.llm.clone(),
workspace: self.workspace.clone(),
notify_tx: self.notify_tx.clone(),
running_count: self.running_count.clone(),
max_lightweight_tokens: self.config.max_lightweight_tokens,
};
// Record the run in DB, then spawn execution
let store = self.store.clone();
tokio::spawn(async move {
if let Err(e) = store.create_routine_run(&run).await {
tracing::error!(routine = %routine.name, "Failed to record run: {}", e);
return;
}
execute_routine(engine, routine, run).await;
});
}
fn check_cooldown(&self, routine: &Routine) -> bool {
if let Some(last_run) = routine.last_run_at {
let elapsed = Utc::now().signed_duration_since(last_run);
let cooldown = chrono::Duration::from_std(routine.guardrails.cooldown)
.unwrap_or(chrono::Duration::seconds(300));
if elapsed < cooldown {
return false;
}
}
true
}
async fn check_concurrent(&self, routine: &Routine) -> bool {
match self.store.count_running_routine_runs(routine.id).await {
Ok(count) => count < routine.guardrails.max_concurrent as i64,
Err(e) => {
tracing::error!(
routine = %routine.name,
"Failed to check concurrent runs: {}", e
);
false
}
}
}
}
/// Shared context passed to the execution function.
struct EngineContext {
store: Arc<dyn Database>,
llm: Arc<dyn LlmProvider>,
workspace: Arc<Workspace>,
notify_tx: mpsc::Sender<OutgoingResponse>,
running_count: Arc<AtomicUsize>,
max_lightweight_tokens: u32,
}
/// Execute a routine run. Handles both lightweight and full_job modes.
async fn execute_routine(ctx: EngineContext, routine: Routine, run: RoutineRun) {
// Increment running count (atomic: survives panics in the execution below)
ctx.running_count.fetch_add(1, Ordering::Relaxed);
let result = match &routine.action {
RoutineAction::Lightweight {
prompt,
context_paths,
max_tokens,
} => execute_lightweight(&ctx, &routine, prompt, context_paths, *max_tokens).await,
RoutineAction::FullJob { description, .. } => {
// Full job mode: scheduler integration not yet implemented.
// Execute as lightweight and prepend a warning to the summary.
tracing::warn!(
routine = %routine.name,
"FullJob mode not yet implemented; falling back to lightweight execution"
);
match execute_lightweight(&ctx, &routine, description, &[], ctx.max_lightweight_tokens)
.await
{
Ok((status, summary, tokens)) => {
let warning = "[Note: FullJob mode is not yet implemented. This routine ran as \
a single LLM call without tool access. Configure as 'lightweight' \
or wait for full scheduler integration.]";
let summary = match summary {
Some(s) => Some(format!("{warning}\n\n{s}")),
None => Some(warning.to_string()),
};
Ok((status, summary, tokens))
}
Err(e) => Err(e),
}
}
};
// Decrement running count
ctx.running_count.fetch_sub(1, Ordering::Relaxed);
// Process result
let (status, summary, tokens) = match result {
Ok(execution) => execution,
Err(e) => {
tracing::error!(routine = %routine.name, "Execution failed: {}", e);
(RunStatus::Failed, Some(e.to_string()), None)
}
};
// Complete the run record
if let Err(e) = ctx
.store
.complete_routine_run(run.id, status, summary.as_deref(), tokens)
.await
{
tracing::error!(routine = %routine.name, "Failed to complete run record: {}", e);
}
// Update routine runtime state
let now = Utc::now();
let next_fire = if let Trigger::Cron { ref schedule } = routine.trigger {
next_cron_fire(schedule).unwrap_or(None)
} else {
None
};
let new_failures = if status == RunStatus::Failed {
routine.consecutive_failures + 1
} else {
0
};
if let Err(e) = ctx
.store
.update_routine_runtime(
routine.id,
now,
next_fire,
routine.run_count + 1,
new_failures,
&routine.state,
)
.await
{
tracing::error!(routine = %routine.name, "Failed to update runtime state: {}", e);
}
// Send notifications based on config
send_notification(
&ctx.notify_tx,
&routine.notify,
&routine.name,
status,
summary.as_deref(),
)
.await;
}
/// Sanitize a routine name for use in workspace paths.
/// Only keeps alphanumeric, dash, and underscore characters; replaces everything else.
fn sanitize_routine_name(name: &str) -> String {
name.chars()
.map(|c| {
if c.is_ascii_alphanumeric() || c == '-' || c == '_' {
c
} else {
'_'
}
})
.collect()
}
/// Execute a lightweight routine (single LLM call).
async fn execute_lightweight(
ctx: &EngineContext,
routine: &Routine,
prompt: &str,
context_paths: &[String],
max_tokens: u32,
) -> Result<(RunStatus, Option<String>, Option<i32>), RoutineError> {
// Load context from workspace
let mut context_parts = Vec::new();
for path in context_paths {
match ctx.workspace.read(path).await {
Ok(doc) => {
context_parts.push(format!("## {}\n\n{}", path, doc.content));
}
Err(e) => {
tracing::debug!(
routine = %routine.name,
"Failed to read context path {}: {}", path, e
);
}
}
}
// Load routine state from workspace (name sanitized to prevent path traversal)
let safe_name = sanitize_routine_name(&routine.name);
let state_path = format!("routines/{safe_name}/state.md");
let state_content = match ctx.workspace.read(&state_path).await {
Ok(doc) => Some(doc.content),
Err(_) => None,
};
// Build the prompt
let mut full_prompt = String::new();
full_prompt.push_str(prompt);
if !context_parts.is_empty() {
full_prompt.push_str("\n\n---\n\n# Context\n\n");
full_prompt.push_str(&context_parts.join("\n\n"));
}
if let Some(state) = &state_content {
full_prompt.push_str("\n\n---\n\n# Previous State\n\n");
full_prompt.push_str(state);
}
full_prompt.push_str(
"\n\n---\n\nIf nothing needs attention, reply EXACTLY with: ROUTINE_OK\n\
If something needs attention, provide a concise summary.",
);
// Get system prompt
let system_prompt = match ctx.workspace.system_prompt().await {
Ok(p) => p,
Err(e) => {
tracing::warn!(routine = %routine.name, "Failed to get system prompt: {}", e);
String::new()
}
};
let messages = if system_prompt.is_empty() {
vec![ChatMessage::user(&full_prompt)]
} else {
vec![
ChatMessage::system(&system_prompt),
ChatMessage::user(&full_prompt),
]
};
// Determine max_tokens from model metadata with fallback
let effective_max_tokens = match ctx.llm.model_metadata().await {
Ok(meta) => {
let from_api = meta.context_length.map(|ctx| ctx / 2).unwrap_or(max_tokens);
from_api.max(max_tokens)
}
Err(_) => max_tokens,
};
let request = CompletionRequest::new(messages)
.with_max_tokens(effective_max_tokens)
.with_temperature(0.3);
let response = ctx
.llm
.complete(request)
.await
.map_err(|e| RoutineError::LlmFailed {
reason: e.to_string(),
})?;
let content = response.content.trim();
let tokens_used = Some((response.input_tokens + response.output_tokens) as i32);
// Empty content guard (same as heartbeat)
if content.is_empty() {
return if response.finish_reason == FinishReason::Length {
Err(RoutineError::TruncatedResponse)
} else {
Err(RoutineError::EmptyResponse)
};
}
// Check for the "nothing to do" sentinel
if content == "ROUTINE_OK" || content.contains("ROUTINE_OK") {
return Ok((RunStatus::Ok, None, tokens_used));
}
Ok((RunStatus::Attention, Some(content.to_string()), tokens_used))
}
/// Send a notification based on the routine's notify config and run status.
async fn send_notification(
tx: &mpsc::Sender<OutgoingResponse>,
notify: &NotifyConfig,
routine_name: &str,
status: RunStatus,
summary: Option<&str>,
) {
let should_notify = match status {
RunStatus::Ok => notify.on_success,
RunStatus::Attention => notify.on_attention,
RunStatus::Failed => notify.on_failure,
RunStatus::Running => false,
};
if !should_notify {
return;
}
let icon = match status {
RunStatus::Ok => "✅",
RunStatus::Attention => "🔔",
RunStatus::Failed => "❌",
RunStatus::Running => "⏳",
};
let message = match summary {
Some(s) => format!("{} *Routine '{}'*: {}\n\n{}", icon, routine_name, status, s),
None => format!("{} *Routine '{}'*: {}", icon, routine_name, status),
};
let response = OutgoingResponse {
content: message,
thread_id: None,
metadata: serde_json::json!({
"source": "routine",
"routine_name": routine_name,
"status": status.to_string(),
}),
};
if let Err(e) = tx.send(response).await {
tracing::error!(routine = %routine_name, "Failed to send notification: {}", e);
}
}
/// Spawn the cron ticker background task.
pub fn spawn_cron_ticker(
engine: Arc<RoutineEngine>,
interval: Duration,
) -> tokio::task::JoinHandle<()> {
tokio::spawn(async move {
let mut ticker = tokio::time::interval(interval);
// Skip immediate first tick
ticker.tick().await;
loop {
ticker.tick().await;
engine.check_cron_triggers().await;
}
})
}
fn truncate(s: &str, max: usize) -> String {
if s.len() <= max {
s.to_string()
} else {
let end = crate::util::floor_char_boundary(s, max);
format!("{}...", &s[..end])
}
}
#[cfg(test)]
mod tests {
use crate::agent::routine::{NotifyConfig, RunStatus};
#[test]
fn test_notification_gating() {
let config = NotifyConfig {
on_success: false,
on_failure: true,
on_attention: true,
..Default::default()
};
// on_success = false means Ok status should not notify
assert!(!config.on_success);
assert!(config.on_failure);
assert!(config.on_attention);
}
#[test]
fn test_run_status_icons() {
// Just verify the mapping doesn't panic
for status in [
RunStatus::Ok,
RunStatus::Attention,
RunStatus::Failed,
RunStatus::Running,
] {
let _ = status.to_string();
}
}
}