Compare commits

...

6 Commits

Author SHA1 Message Date
Jochen
bbeaaea2e3 temporarily disable codebase_fast_start
it seems the llm gets "lazy" and assumes all the tool
calls meant it's done most of the work.
I need to revise this approach.
2025-11-27 16:36:40 +11:00
Jochen
7e1ce36a4b Merge pull request #35 from dhanji/jochen_write_existing_file
remove check for whether a file exists in the workspace
2025-11-27 13:44:45 +11:00
Jochen
9f6592efc2 remove redundant 'if' 2025-11-27 13:34:54 +11:00
Jochen
99125fc39e completely remove the skipping first player logic 2025-11-27 13:21:40 +11:00
Jochen
a2a82a2526 Merge pull request #36 from dhanji/jochen_fix_cache_control_if
add cache_control to user messages
2025-11-27 13:13:54 +11:00
Jochen
c58aa80932 explain what file was found in workspace 2025-11-26 21:43:59 +11:00
2 changed files with 186 additions and 236 deletions

View File

@@ -183,6 +183,7 @@ use rustyline::error::ReadlineError;
use rustyline::DefaultEditor;
use std::path::Path;
use std::path::PathBuf;
use std::process::exit;
use sha2::{Digest, Sha256};
use tokio_util::sync::CancellationToken;
use tracing::{error, info};
@@ -298,6 +299,10 @@ pub async fn run() -> Result<()> {
return run_flock_mode(project_dir.clone(), flock_workspace.clone(), num_segments, cli.flock_max_turns).await;
}
if cli.codebase_fast_start.is_some() {
print!("codebase_fast_start is temporarily disabled.");
exit(1);
}
// Otherwise, continue with normal mode
// Only initialize logging if not in retro mode
@@ -1761,16 +1766,6 @@ async fn run_autonomous(
let loop_start = Instant::now();
output.print("🔄 Starting coach-player feedback loop...");
// Check if implementation files already exist
let skip_first_player = project.has_implementation_files();
if skip_first_player {
output.print("📂 Detected existing implementation files in workspace");
output.print("⏭️ Skipping first player turn - proceeding directly to coach review");
} else {
output.print("📂 No existing implementation files detected");
output.print("🎯 Starting with player implementation");
}
// Load fast-discovery messages before the loop starts (if enabled)
let (discovery_messages, discovery_working_dir): (Vec<g3_providers::Message>, Option<String>) =
if let Some(ref codebase_path) = codebase_fast_start {
@@ -1811,203 +1806,201 @@ async fn run_autonomous(
loop {
let turn_start_time = Instant::now();
let turn_start_tokens = agent.get_context_window().used_tokens;
// Skip player turn if it's the first turn and implementation files exist
if !(turn == 1 && skip_first_player) {
output.print(&format!(
"\n=== TURN {}/{} - PLAYER MODE ===",
turn, max_turns
));
// Surface provider info for player agent
agent.print_provider_banner("Player");
output.print(&format!(
"\n=== TURN {}/{} - PLAYER MODE ===",
turn, max_turns
));
// Player mode: implement requirements (with coach feedback if available)
let player_prompt = if coach_feedback.is_empty() {
format!(
"You are G3 in implementation mode. Read and implement the following requirements:\n\n{}\n\nRequirements SHA256: {}\n\nImplement this step by step, creating all necessary files and code.",
requirements, requirements_sha
)
} else {
format!(
"You are G3 in implementation mode. Address the following specific feedback from the coach:\n\n{}\n\nContext: You are improving an implementation based on these requirements:\n{}\n\nFocus on fixing the issues mentioned in the coach feedback above.",
coach_feedback, requirements
)
};
// Surface provider info for player agent
agent.print_provider_banner("Player");
output.print(&format!("🎯 Starting player implementation... (elapsed: {})", format_elapsed_time(loop_start.elapsed())));
// Player mode: implement requirements (with coach feedback if available)
let player_prompt = if coach_feedback.is_empty() {
format!(
"You are G3 in implementation mode. Read and implement the following requirements:\n\n{}\n\nRequirements SHA256: {}\n\nImplement this step by step, creating all necessary files and code.",
requirements, requirements_sha
)
} else {
format!(
"You are G3 in implementation mode. Address the following specific feedback from the coach:\n\n{}\n\nContext: You are improving an implementation based on these requirements:\n{}\n\nFocus on fixing the issues mentioned in the coach feedback above.",
coach_feedback, requirements
)
};
// Display what feedback the player is receiving
// If there's no coach feedback on subsequent turns, this is an error
if coach_feedback.is_empty() {
if turn > 1 {
return Err(anyhow::anyhow!(
"Player mode error: No coach feedback received on turn {}",
turn
));
}
output.print("📋 Player starting initial implementation (no prior coach feedback)");
} else {
output.print(&format!(
"📋 Player received coach feedback ({} chars):",
coach_feedback.len()
));
output.print(&coach_feedback.to_string());
}
output.print(""); // Empty line for readability
output.print(&format!("🎯 Starting player implementation... (elapsed: {})", format_elapsed_time(loop_start.elapsed())));
// Execute player task with retry on error
let mut _player_retry_count = 0;
const MAX_PLAYER_RETRIES: u32 = 3;
let mut player_failed = false;
loop {
match agent
.execute_task_with_timing(
&player_prompt,
None,
false,
show_prompt,
show_code,
true,
if has_discovery {
Some(DiscoveryOptions {
messages: &discovery_messages,
fast_start_path: discovery_working_dir.as_deref(),
})
} else { None },
)
.await
{
Ok(result) => {
// Display player's implementation result
output.print("📝 Player implementation completed:");
output.print_smart(&result.response);
break;
}
Err(e) => {
// Check if this is a context length exceeded error
use g3_core::error_handling::{classify_error, ErrorType, RecoverableError};
let error_type = classify_error(&e);
if matches!(error_type, ErrorType::Recoverable(RecoverableError::ContextLengthExceeded)) {
output.print(&format!("⚠️ Context length exceeded in player turn: {}", e));
output.print("📝 Logging error to session and ending current turn...");
// Build forensic context
let forensic_context = format!(
"Turn: {}\n\
Role: Player\n\
Context tokens: {}\n\
Total available: {}\n\
Percentage used: {:.1}%\n\
Prompt length: {} chars\n\
Error occurred at: {}",
turn,
agent.get_context_window().used_tokens,
agent.get_context_window().total_tokens,
agent.get_context_window().percentage_used(),
player_prompt.len(),
chrono::Utc::now().to_rfc3339()
);
// Log to session JSON
agent.log_error_to_session(&e, "assistant", Some(forensic_context));
// Mark turn as failed and continue to next turn
player_failed = true;
break;
} else if e.to_string().contains("panic") {
output.print(&format!("💥 Player panic detected: {}", e));
// Generate final report even for panic
let elapsed = start_time.elapsed();
let context_window = agent.get_context_window();
output.print(&format!("\n{}", "=".repeat(60)));
output.print("📊 AUTONOMOUS MODE SESSION REPORT");
output.print(&"=".repeat(60));
output.print(&format!(
"⏱️ Total Duration: {:.2}s",
elapsed.as_secs_f64()
));
output.print(&format!("🔄 Turns Taken: {}/{}", turn, max_turns));
output.print("📝 Final Status: 💥 PLAYER PANIC");
output.print("\n📈 Token Usage Statistics:");
output.print(&format!(
" • Used Tokens: {}",
context_window.used_tokens
));
output.print(&format!(
" • Total Available: {}",
context_window.total_tokens
));
output.print(&format!(
" • Cumulative Tokens: {}",
context_window.cumulative_tokens
));
output.print(&format!(
" • Usage Percentage: {:.1}%",
context_window.percentage_used()
));
// Add per-turn histogram
output.print(&generate_turn_histogram(&turn_metrics));
output.print(&"=".repeat(60));
return Err(e);
}
_player_retry_count += 1;
output.print(&format!(
"⚠️ Player error (attempt {}/{}): {}",
_player_retry_count, MAX_PLAYER_RETRIES, e
));
if _player_retry_count >= MAX_PLAYER_RETRIES {
output.print(
"🔄 Max retries reached for player, marking turn as failed...",
);
player_failed = true;
break; // Exit retry loop
}
output.print("🔄 Retrying player implementation...");
}
}
}
// If player failed after max retries, increment turn and continue
if player_failed {
output.print(&format!(
"⚠️ Player turn {} failed after max retries. Moving to next turn.",
// Display what feedback the player is receiving
// If there's no coach feedback on subsequent turns, this is an error
if coach_feedback.is_empty() {
if turn > 1 {
return Err(anyhow::anyhow!(
"Player mode error: No coach feedback received on turn {}",
turn
));
// Record turn metrics before incrementing
let turn_duration = turn_start_time.elapsed();
let turn_tokens = agent.get_context_window().used_tokens.saturating_sub(turn_start_tokens);
turn_metrics.push(TurnMetrics {
turn_number: turn,
tokens_used: turn_tokens,
wall_clock_time: turn_duration,
});
turn += 1;
}
output.print("📋 Player starting initial implementation (no prior coach feedback)");
} else {
output.print(&format!(
"📋 Player received coach feedback ({} chars):",
coach_feedback.len()
));
output.print(&coach_feedback.to_string());
}
output.print(""); // Empty line for readability
// Check if we've reached max turns
if turn > max_turns {
output.print("\n=== SESSION COMPLETED - MAX TURNS REACHED ===");
output.print(&format!("⏰ Maximum turns ({}) reached", max_turns));
// Execute player task with retry on error
let mut _player_retry_count = 0;
const MAX_PLAYER_RETRIES: u32 = 3;
let mut player_failed = false;
loop {
match agent
.execute_task_with_timing(
&player_prompt,
None,
false,
show_prompt,
show_code,
true,
if has_discovery {
Some(DiscoveryOptions {
messages: &discovery_messages,
fast_start_path: discovery_working_dir.as_deref(),
})
} else { None },
)
.await
{
Ok(result) => {
// Display player's implementation result
output.print("📝 Player implementation completed:");
output.print_smart(&result.response);
break;
}
Err(e) => {
// Check if this is a context length exceeded error
use g3_core::error_handling::{classify_error, ErrorType, RecoverableError};
let error_type = classify_error(&e);
// Continue to next iteration with empty feedback (restart from scratch)
coach_feedback = String::new();
continue;
if matches!(error_type, ErrorType::Recoverable(RecoverableError::ContextLengthExceeded)) {
output.print(&format!("⚠️ Context length exceeded in player turn: {}", e));
output.print("📝 Logging error to session and ending current turn...");
// Build forensic context
let forensic_context = format!(
"Turn: {}\n\
Role: Player\n\
Context tokens: {}\n\
Total available: {}\n\
Percentage used: {:.1}%\n\
Prompt length: {} chars\n\
Error occurred at: {}",
turn,
agent.get_context_window().used_tokens,
agent.get_context_window().total_tokens,
agent.get_context_window().percentage_used(),
player_prompt.len(),
chrono::Utc::now().to_rfc3339()
);
// Log to session JSON
agent.log_error_to_session(&e, "assistant", Some(forensic_context));
// Mark turn as failed and continue to next turn
player_failed = true;
break;
} else if e.to_string().contains("panic") {
output.print(&format!("💥 Player panic detected: {}", e));
// Generate final report even for panic
let elapsed = start_time.elapsed();
let context_window = agent.get_context_window();
output.print(&format!("\n{}", "=".repeat(60)));
output.print("📊 AUTONOMOUS MODE SESSION REPORT");
output.print(&"=".repeat(60));
output.print(&format!(
"⏱️ Total Duration: {:.2}s",
elapsed.as_secs_f64()
));
output.print(&format!("🔄 Turns Taken: {}/{}", turn, max_turns));
output.print("📝 Final Status: 💥 PLAYER PANIC");
output.print("\n📈 Token Usage Statistics:");
output.print(&format!(
" • Used Tokens: {}",
context_window.used_tokens
));
output.print(&format!(
" • Total Available: {}",
context_window.total_tokens
));
output.print(&format!(
" • Cumulative Tokens: {}",
context_window.cumulative_tokens
));
output.print(&format!(
" • Usage Percentage: {:.1}%",
context_window.percentage_used()
));
// Add per-turn histogram
output.print(&generate_turn_histogram(&turn_metrics));
output.print(&"=".repeat(60));
return Err(e);
}
_player_retry_count += 1;
output.print(&format!(
"⚠️ Player error (attempt {}/{}): {}",
_player_retry_count, MAX_PLAYER_RETRIES, e
));
if _player_retry_count >= MAX_PLAYER_RETRIES {
output.print(
"🔄 Max retries reached for player, marking turn as failed...",
);
player_failed = true;
break; // Exit retry loop
}
output.print("🔄 Retrying player implementation...");
}
}
}
// If player failed after max retries, increment turn and continue
if player_failed {
output.print(&format!(
"⚠️ Player turn {} failed after max retries. Moving to next turn.",
turn
));
// Record turn metrics before incrementing
let turn_duration = turn_start_time.elapsed();
let turn_tokens = agent.get_context_window().used_tokens.saturating_sub(turn_start_tokens);
turn_metrics.push(TurnMetrics {
turn_number: turn,
tokens_used: turn_tokens,
wall_clock_time: turn_duration,
});
turn += 1;
// Check if we've reached max turns
if turn > max_turns {
output.print("\n=== SESSION COMPLETED - MAX TURNS REACHED ===");
output.print(&format!("⏰ Maximum turns ({}) reached", max_turns));
break;
}
// Give some time for file operations to complete
tokio::time::sleep(tokio::time::Duration::from_millis(500)).await;
// Continue to next iteration with empty feedback (restart from scratch)
coach_feedback = String::new();
continue;
}
// Give some time for file operations to complete
tokio::time::sleep(tokio::time::Duration::from_millis(500)).await;
// Create a new agent instance for coach mode to ensure fresh context
// Use the same config with overrides that was passed to the player agent
let base_config = agent.get_config().clone();

View File

@@ -98,49 +98,6 @@ impl Project {
self.requirements_text.is_some() || self.requirements_path.is_some()
}
/// Check if implementation files exist in the workspace
pub fn has_implementation_files(&self) -> bool {
self.check_dir_for_implementation_files(&self.workspace_dir)
}
/// Recursively check a directory for implementation files
#[allow(clippy::only_used_in_recursion)]
fn check_dir_for_implementation_files(&self, dir: &Path) -> bool {
// Common source file extensions
let extensions = vec![
"swift", "rs", "py", "js", "ts", "java", "cpp", "c",
"go", "rb", "php", "cs", "kt", "scala", "m", "h"
];
if let Ok(entries) = std::fs::read_dir(dir) {
for entry in entries.flatten() {
let path = entry.path();
if path.is_file() {
// Check if it's a source file
if let Some(ext) = path.extension() {
if let Some(ext_str) = ext.to_str() {
if extensions.contains(&ext_str) {
return true;
}
}
}
} else if path.is_dir() {
// Skip hidden directories and common non-source directories
if let Some(name) = path.file_name().and_then(|n| n.to_str()) {
if !name.starts_with('.') && name != "logs" && name != "target" && name != "node_modules" {
// Recursively check subdirectories
if self.check_dir_for_implementation_files(&path) {
return true;
}
}
}
}
}
}
false
}
/// Read the requirements file content
pub fn read_requirements(&self) -> Result<Option<String>> {
// Prioritize requirements text override
@@ -181,4 +138,4 @@ impl Project {
}
Ok(())
}
}
}