mirror of
https://github.com/outbackdingo/optimclaw.git
synced 2026-08-25 14:53:34 +00:00
* perf: build system prompt once per turn, skip tools on force-text, fix nudge role (#565) Three fixes to agentic loop prompt handling: 1. Build system prompt once per turn instead of every tool iteration. `build_system_prompt_with_tools` is now pub; callers pass the result via `ReasoningContext::system_prompt` to avoid rebuilding ~1,500 tokens per iteration. 2. Skip `## Available Tools` section when `force_text = true`. The dispatcher passes a no-tools prompt variant on the final iteration, saving ~460 tokens and removing misleading instructions. 3. Change nudge message from `Role::System` to `Role::User`. A second system message mid-conversation is unsupported by most providers. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: revert nudge role change to keep ChatMessage::system Copilot review correctly identified that using Role::User for the nudge breaks compact_messages_for_retry, which uses rposition for Role::User to find the last real user message. Role::Assistant would cause back-to-back assistant messages. Since no production issues were reported with the original system role, revert to ChatMessage::system. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address PR review — omit tool guidance when tools empty, rename shadowed var - Conditionalize "Call tools…" guidelines and "## Tool Call Style" section in the system prompt so they are only included when tools are non-empty. Previously the force-text (no-tools) prompt still contained misleading tool-calling instructions. (Copilot review comment) - Rename `system_prompt` → `cached_prompt` in dispatcher to avoid shadowing the earlier workspace identity `system_prompt` variable. (Copilot review) - Add regression tests: `test_system_prompt_with_tools_contains_tool_guidance` and extended assertions in `test_system_prompt_without_tools_omits_tools_section`. Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> Co-authored-by: [email protected] <[email protected]>
124 lines
4.2 KiB
Rust
124 lines
4.2 KiB
Rust
#![cfg(feature = "postgres")]
|
|
//! Heartbeat integration test.
|
|
//!
|
|
//! Exercises the heartbeat system in isolation: connects to the real
|
|
//! database, reads the real HEARTBEAT.md, calls the real LLM, and prints
|
|
//! every step so you can see exactly where it breaks.
|
|
//!
|
|
//! Usage:
|
|
//! cargo test --test heartbeat_integration -- --ignored --nocapture
|
|
|
|
use std::sync::Arc;
|
|
|
|
use ironclaw::{
|
|
agent::HeartbeatRunner,
|
|
config::Config,
|
|
history::Store,
|
|
llm::{create_llm_provider, create_session_manager},
|
|
safety::SafetyLayer,
|
|
workspace::Workspace,
|
|
};
|
|
|
|
#[tokio::test]
|
|
#[ignore] // Requires running database and LLM credentials
|
|
async fn test_heartbeat_end_to_end() {
|
|
// Load .env and set up logging
|
|
let _ = dotenvy::dotenv();
|
|
let _ = tracing_subscriber::fmt()
|
|
.with_env_filter("ironclaw=debug")
|
|
.try_init();
|
|
|
|
println!("=== Heartbeat Integration Test ===\n");
|
|
|
|
// 1. Load config
|
|
let config = Config::from_env().await.expect("Failed to load config");
|
|
println!("[1/6] Config loaded");
|
|
println!(" heartbeat.enabled = {}", config.heartbeat.enabled);
|
|
println!(
|
|
" heartbeat.interval_secs = {}",
|
|
config.heartbeat.interval_secs
|
|
);
|
|
println!(
|
|
" heartbeat.notify_channel = {:?}",
|
|
config.heartbeat.notify_channel
|
|
);
|
|
println!(
|
|
" heartbeat.notify_user = {:?}",
|
|
config.heartbeat.notify_user
|
|
);
|
|
|
|
// 2. Connect to database
|
|
let store = Store::new(&config.database)
|
|
.await
|
|
.expect("Failed to connect to database");
|
|
store
|
|
.run_migrations()
|
|
.await
|
|
.expect("Failed to run migrations");
|
|
println!("[2/6] Database connected");
|
|
|
|
// 3. Create workspace
|
|
let workspace = Arc::new(Workspace::new("default", store.pool()));
|
|
println!("[3/6] Workspace created");
|
|
|
|
// 4. Read HEARTBEAT.md
|
|
let checklist = workspace.heartbeat_checklist().await;
|
|
match &checklist {
|
|
Ok(Some(content)) => {
|
|
let preview: String = content.chars().take(200).collect();
|
|
println!("[4/6] HEARTBEAT.md found ({} chars)", content.len());
|
|
println!(" Preview: {}...", preview);
|
|
}
|
|
Ok(None) => {
|
|
println!("[4/6] HEARTBEAT.md is None (no file, no seed fallback)");
|
|
println!(" Heartbeat will return Skipped.");
|
|
}
|
|
Err(e) => {
|
|
println!("[4/6] HEARTBEAT.md read error: {}", e);
|
|
}
|
|
}
|
|
|
|
// Check if the checklist would be considered "effectively empty"
|
|
if let Ok(Some(_)) = checklist {
|
|
println!(" (Will verify via runner below)");
|
|
}
|
|
|
|
// 5. Create LLM provider
|
|
let session = create_session_manager(config.llm.session.clone()).await;
|
|
let llm = create_llm_provider(&config.llm, session).expect("Failed to create LLM provider");
|
|
println!("[5/6] LLM provider created (model: {})", llm.model_name());
|
|
|
|
// 6. Run heartbeat check
|
|
println!("[6/6] Running check_heartbeat()...\n");
|
|
|
|
let hb_config = ironclaw::agent::HeartbeatConfig::default();
|
|
let hygiene_config = ironclaw::workspace::hygiene::HygieneConfig::default();
|
|
let safety = Arc::new(SafetyLayer::new(&config.safety));
|
|
let runner = HeartbeatRunner::new(hb_config, hygiene_config, workspace, llm, safety);
|
|
|
|
let result = runner.check_heartbeat().await;
|
|
|
|
println!("=== Result ===\n");
|
|
match &result {
|
|
ironclaw::agent::HeartbeatResult::Ok => {
|
|
println!("HeartbeatResult::Ok");
|
|
println!(" LLM responded HEARTBEAT_OK, nothing needs attention.");
|
|
}
|
|
ironclaw::agent::HeartbeatResult::NeedsAttention(msg) => {
|
|
println!("HeartbeatResult::NeedsAttention");
|
|
println!(" Message:\n{}", msg);
|
|
}
|
|
ironclaw::agent::HeartbeatResult::Skipped => {
|
|
println!("HeartbeatResult::Skipped");
|
|
println!(" No checklist found, or checklist was effectively empty.");
|
|
println!(" This means the HEARTBEAT.md either:");
|
|
println!(" - Does not exist in the workspace database");
|
|
println!(" - Contains only headers, comments, and empty checkboxes");
|
|
}
|
|
ironclaw::agent::HeartbeatResult::Failed(err) => {
|
|
println!("HeartbeatResult::Failed");
|
|
println!(" Error: {}", err);
|
|
}
|
|
}
|
|
}
|