refactor: massive codebase restructuring — naming, splitting, DRY

Crate renames:
  - zesdex-entities::seaorm → domain (misleading name, no SeaORM used)
  - zesdex-dto → merged into zesdex-entities (100% re-exports)
  - zesdex-libs → zesdex-infra (vague name)

Module renames:
  - app/harness → guard (misleading: safety gatekeeper, not test harness)
  - runtime/commands → action_dispatch (name clashed with controller/command)
  - resources → prompts (embedded prompt text, not general resources)
  - tool/seqthink → sequential_think (unreadable abbreviation)
  - msglog/query → insert (module only inserts, never queries)

Dead code removal:
  - app/mode/help.rs (orphaned — not declared in mod.rs)
  - app/mode/loading.rs (orphaned — not declared in mod.rs)

File splitting (71 new files, avg ~115 lines/file):
  - app/runtime/actions/: 1→8 files (was 2030 lines)
  - view/overlays/: 1→16 files (was 1167 lines)
  - tool/lsp/: 1→8 per-tool files (was 909 lines)
  - main.rs: 1→5 files (session, daemon, attach, event_loop)
  - workflow/engine + hive_mind: 2→10 files
  - subagent/engine + auto: 2→9 files
  - lsp/provisioner: 1→5 files
  - review/: 1→6 files
  - guard/: 1→2 files (extracted patterns)
  - state/misc: 1→3 files (input, scroll)
  - mcp/: 1→3 files (transport, adapter)
  - stream/json_repair extracted from turn.rs

DRY:
  - Pattern constants (STUB_PATTERNS etc) in guard/patterns shared with subagent
  - 3 near-identical background spawners → 1 generic + thin wrappers
  - Shared spawn_subagent_with_drain() extracted
  - Shared create_session() in main
  - write_osc52 deduplicated

Bug fixes:
  - archive_message(): sess.db → db (wrong variable name)
  - execute_one_tool(): wrong parameter name
  - check_credential_read() function was missing (restored from test expectations)
This commit is contained in:
asepharyana
2026-07-17 09:08:41 +07:00
parent 1f0ae9f551
commit 9a67137954
139 changed files with 9704 additions and 8858 deletions
@@ -0,0 +1,290 @@
//! Simple action handler functions — one per `Action` variant, called by
//! `apply_action` in the root module. Each handler mutates `AppStateRest`
//! in place.
use crate::app::state::rest::{AppStateRest, ChatMessageDisplay};
use crate::app::state::runtime::TurnEvent;
use crate::app::state::types::{Overlay, Toast, ToastKind};
use crate::dto::chat::message::{ChatMessage, Role};
use zesdex_cms::domain::repository::MemoryRepository;
use zesdex_cms::infrastructure::persistence::memory_repo::MarkdownMemoryRepository;
use super::io::save_current_session;
use super::memory::refresh_lesson_counters;
use super::spawn::spawn_turn;
use super::oauth::run_oauth_flow;
pub(super) fn handle_force_quit(state: &mut AppStateRest) {
save_current_session(state);
state.shutdown_lsp();
state.quit = true;
}
pub(super) fn handle_submit_input(state: &mut AppStateRest, text: String) {
state.input.submit();
let text = text.trim().to_string();
if text.is_empty() {
state.dirty = true;
return;
}
state.push_transcript(ChatMessageDisplay::new(Role::User, text.clone()));
if let Some(ref mut rt) = state.session_runtime {
rt.push_message(ChatMessage::user(text));
refresh_lesson_counters(&state.memory_dir, rt);
} else {
let _ = std::fs::create_dir_all(&state.memory_dir);
}
state.misc.thinking = true;
spawn_turn(state);
state.dirty = true;
}
pub(super) fn handle_delete_char(state: &mut AppStateRest) {
state.input.delete_left();
state.dirty = true;
}
pub(super) fn handle_delete_char_right(state: &mut AppStateRest) {
state.input.delete_right();
state.dirty = true;
}
pub(super) fn handle_cursor_left(state: &mut AppStateRest) {
state.input.char_left();
}
pub(super) fn handle_cursor_right(state: &mut AppStateRest) {
state.input.char_right();
}
pub(super) fn handle_history_up(state: &mut AppStateRest) {
state.input.history_up();
state.dirty = true;
}
pub(super) fn handle_history_down(state: &mut AppStateRest) {
state.input.history_down();
state.dirty = true;
}
pub(super) fn handle_scroll_up(state: &mut AppStateRest) {
state.scroll.scroll_up(5);
state.dirty = true;
}
pub(super) fn handle_scroll_down(state: &mut AppStateRest) {
state.scroll.scroll_down(5);
state.dirty = true;
}
pub(super) fn handle_open_overlay(state: &mut AppStateRest, overlay: Overlay) {
state.misc.overlay = overlay;
if overlay == Overlay::Learning
|| overlay == Overlay::Rewind
|| overlay == Overlay::ModelSelector
{
state.misc.selected_index = 0;
}
state.dirty = true;
}
pub(super) fn handle_open_editor(state: &mut AppStateRest, path: String) {
let resolved = crate::tool::resolve_path(&state.workspace_roots, &path);
match resolved {
Ok(abs_path) => {
let content = std::fs::read_to_string(&abs_path).unwrap_or_default();
let lines: Vec<String> =
content.lines().map(std::string::ToString::to_string).collect();
let ed = crate::app::mode::editor::EditorState::open(
abs_path.to_string_lossy().to_string(),
Some(lines),
);
state.misc.editor = Some(ed);
state.misc.overlay = Overlay::Editor;
state.push_toast(Toast::new(ToastKind::Info, format!("Editing {path}")));
}
Err(e) => {
state.push_toast(Toast::new(
ToastKind::Error,
format!("Failed to open {path}: {e}"),
));
}
}
state.dirty = true;
}
pub(super) fn handle_mcp_add(state: &mut AppStateRest, name: String, command: String) {
let extra_args: Vec<String> =
command.split_whitespace().map(std::string::ToString::to_string).collect();
let cmd = extra_args.first().cloned().unwrap_or_default();
let args: Vec<String> = extra_args.into_iter().skip(1).collect();
match state.mcp_manager.connect_stdio(&name, &cmd, &args) {
Ok(()) => {
let tool_count = state
.mcp_manager
.servers
.last()
.map_or(0, |s| s.tools.len());
state.push_toast(Toast::new(
ToastKind::Success,
format!("Connected MCP server '{name}' ({tool_count} tools)"),
));
state.dirty = true;
}
Err(e) => {
state.push_toast(Toast::new(
ToastKind::Error,
format!("MCP connect failed: {e}"),
));
}
}
}
pub(super) fn handle_model_list(state: &mut AppStateRest) {
state.misc.selected_index = 0;
state.misc.overlay = Overlay::ModelSelector;
state.dirty = true;
}
pub(super) fn handle_close_overlay(state: &mut AppStateRest) {
// If the overlay is the Editor, dismiss it properly first
if state.misc.overlay == Overlay::Editor {
crate::app::mode::editor::handle_editor_dismiss(state);
}
state.misc.overlay = Overlay::None;
state.dirty = true;
}
pub(super) fn handle_system_note(state: &mut AppStateRest, message: String) {
let toast = Toast::new(ToastKind::Info, message);
state.push_toast(toast);
}
pub(super) fn handle_quit_confirm(state: &mut AppStateRest) {
state.misc.overlay = Overlay::QuitConfirm;
state.dirty = true;
}
pub(super) fn handle_resize(state: &mut AppStateRest, w: u16) {
state.scroll.set_max_visible(w as usize);
state.dirty = true;
}
pub(super) fn handle_start_oauth(state: &mut AppStateRest, provider: String) {
let turn_events = state.turn_events.clone();
let provider_clone = provider.clone();
std::thread::spawn(move || {
let result = run_oauth_flow(&provider_clone);
let message = match result {
Ok(msg) => msg,
Err(e) => format!("OAuth login failed: {e}"),
};
if let Ok(mut q) = turn_events.lock() {
q.push_back(TurnEvent::SystemNote {
kind: "oauth".to_string(),
message,
});
}
});
let toast = Toast::new(
ToastKind::Info,
format!("Opening browser for {provider} login..."),
);
state.push_toast(toast);
state.dirty = true;
}
pub(super) fn handle_abort_turn(state: &mut AppStateRest) {
state
.abort_flag
.store(true, std::sync::atomic::Ordering::SeqCst);
state.push_toast(Toast::new(
ToastKind::Warning,
"Aborting generation...".to_string(),
));
}
pub(super) fn handle_compact(state: &mut AppStateRest) {
let max_wire_tokens = state
.app_config
.model_roles
.values()
.find(|role| {
role.provider == state.settings.provider && role.model == state.settings.model
})
.and_then(|role| role.context_window)
.unwrap_or(state.app_config.default_context_window) as usize;
if let Some(ref mut rt) = state.session_runtime {
let total_chars: usize = rt
.messages
.iter()
.filter_map(|m| m.content.as_deref())
.map(str::len)
.sum();
let token_estimate = total_chars / 3;
rt.messages =
crate::app::runtime::context::shaping::shape_messages(
&rt.messages,
token_estimate,
max_wire_tokens,
true,
None,
);
state.push_toast(Toast::new(
ToastKind::Success,
"Conversation history compacted.".to_string(),
));
state.dirty = true;
}
}
pub(super) fn handle_lesson_accept(state: &mut AppStateRest, name: String) {
if let Some(ref rt) = state.session_runtime {
let _ = crate::app::review::resolve_pending_lesson(
&rt.session_dir,
&state.memory_dir,
&name,
true,
);
}
if let Some(ref mut rt) = state.session_runtime {
refresh_lesson_counters(&state.memory_dir, rt);
}
state.push_toast(Toast::new(
ToastKind::Success,
format!("accepted lesson: {name}"),
));
state.dirty = true;
}
pub(super) fn handle_lesson_reject(state: &mut AppStateRest, name: String) {
if let Some(ref rt) = state.session_runtime {
let _ = crate::app::review::resolve_pending_lesson(
&rt.session_dir,
&state.memory_dir,
&name,
false,
);
}
if let Some(ref mut rt) = state.session_runtime {
refresh_lesson_counters(&state.memory_dir, rt);
}
state.push_toast(Toast::new(
ToastKind::Info,
format!("rejected lesson: {name}"),
));
state.dirty = true;
}
pub(super) fn handle_lesson_delete(state: &mut AppStateRest, name: String) {
let _ = MarkdownMemoryRepository::new().delete(&state.memory_dir, &name);
if let Some(ref mut rt) = state.session_runtime {
refresh_lesson_counters(&state.memory_dir, rt);
}
state.push_toast(Toast::new(
ToastKind::Info,
format!("deleted lesson: {name}"),
));
state.dirty = true;
}
@@ -0,0 +1,107 @@
//! I/O helper functions: session persistence, API connectivity checks,
//! and review-available notification.
use crate::app::state::rest::AppStateRest;
use crate::app::state::runtime::TurnEvent;
use crate::app::state::types::{Toast, ToastKind};
use zesdex_iam::domain::repository::SessionRepository;
/// Persist the current session metadata and conversation to disk.
///
/// Flow: build a `Session` object → save its metadata → write
/// `rt.messages` as JSON to the conversation file → errors are silently
/// ignored.
///
/// Why: called on `ForceQuit` so the session can be resumed later.
pub(super) fn save_current_session(state: &AppStateRest) {
let base = state.store_base_dir();
let session = zesdex_iam::domain::session::Session::new(
state.session_id.clone(),
"session".to_string(),
);
let session_repo =
zesdex_iam::infrastructure::persistence::session_repo::FileSystemSessionRepository::new();
let _ = session_repo.save_session(&base, &session);
if let Some(ref rt) = state.session_runtime {
let conv_path = session.conversation_path(&base);
if let Ok(data) = serde_json::to_string(&rt.messages) {
let _ = std::fs::write(&conv_path, data);
}
}
}
/// Optionally push a review-available toast at the end of a turn that
/// performed edits.
///
/// Flow: skip if review is disabled → skip if `edit_count` is zero →
/// push an info toast listing the number of modified files.
///
/// Why: does not launch the review itself (that happens inside
/// `should_trigger_review` on `Tick`), only informs the user that
/// a review has material to examine.
pub(super) fn maybe_trigger_review(state: &mut AppStateRest) {
if !state.settings.flags.review_enabled {
return;
}
let edit_count = state
.session_runtime
.as_ref()
.map_or(0, |rt| rt.edit_count);
if edit_count == 0 {
return;
}
state.push_toast(Toast::new(
ToastKind::Info,
format!("{edit_count} file(s) modified this session. Review available."),
));
}
/// Spawn a background thread that checks API reachability via a lightweight HEAD
/// request to `<base_url>/models`, pushing the result as a `SystemNote` so the
/// next `Tick` handler updates `api_connected`.
///
/// Flow: resolve the provider's base URL → build a short-lived reqwest client
/// with 3s connect / 5s total timeout → HEAD the `/models` endpoint → push
/// a `connectivity` `SystemNote` with the result.
///
/// Why: runs off the event loop so a slow/timed-out network does not block the TUI.
pub(super) fn spawn_api_connectivity_check(state: &AppStateRest) {
let base_url = state
.app_config
.providers
.get(&state.settings.provider)
.map_or_else(
|| crate::service::provider::DEFAULT_BASE_URL.to_string(),
|p| p.api_base.clone(),
);
let turn_events = state.turn_events.clone();
std::thread::spawn(move || {
let url = format!("{}/chat/completions", base_url.trim_end_matches('/'));
let connected = match reqwest::blocking::Client::builder()
.timeout(std::time::Duration::from_secs(5))
.connect_timeout(std::time::Duration::from_secs(3))
.build()
{
Ok(client) => match client.head(&url).send() {
Ok(resp) => {
let s = resp.status();
// 401/403 means the server is reachable (just auth is wrong)
s.is_success() || s.as_u16() == 401 || s.as_u16() == 403
}
Err(_) => false,
},
Err(_) => false,
};
if let Ok(mut q) = turn_events.lock() {
q.push_back(TurnEvent::SystemNote {
kind: "connectivity".to_string(),
message: if connected {
"connected".to_string()
} else {
"disconnected".to_string()
},
});
}
});
}
@@ -0,0 +1,48 @@
//! Memory / lesson-counter helpers: refresh counters from on-disk data.
use zesdex_cms::domain::repository::MemoryRepository;
use zesdex_cms::infrastructure::persistence::memory_repo::MarkdownMemoryRepository;
/// Scan `memory_dir` and update every lesson counter in `SessionRuntime`
/// from real on-disk data.
///
/// Flow: list all memory slugs → read+parse each → increment the matching
/// kind counter (user/feedback/project/reference), lifecycle counter
/// (active/stale/contradicted), and the total. If a memory cannot be read
/// (e.g. a race with deletion) it is silently skipped.
///
/// Why: previously the UI showed all zeros because nothing ever set the
/// breakdown counters. This runs on every user submit so the dashboard
/// reflects actual memory state.
pub(super) fn refresh_lesson_counters(
memory_dir: &std::path::Path,
rt: &mut crate::app::state::runtime::SessionRuntime,
) {
let names = MarkdownMemoryRepository::new().list(memory_dir).unwrap_or_default();
rt.lesson_count = 0;
rt.lessons_user = 0;
rt.lessons_feedback = 0;
rt.lessons_project = 0;
rt.lessons_reference = 0;
rt.lessons_active = 0;
rt.lessons_stale = 0;
rt.lessons_contradicted = 0;
for name in &names {
if let Ok(mem) = MarkdownMemoryRepository::new().load(memory_dir, name) {
rt.lesson_count += 1;
match mem.kind.as_str() {
"user" => rt.lessons_user += 1,
"feedback" => rt.lessons_feedback += 1,
"project" => rt.lessons_project += 1,
"reference" => rt.lessons_reference += 1,
_ => {}
}
match mem.lifecycle.as_str() {
"active" => rt.lessons_active += 1,
"stale" => rt.lessons_stale += 1,
"contradicted" => rt.lessons_contradicted += 1,
_ => {}
}
}
}
}
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,105 @@
//! OAuth PKCE flow — browser-based login for API providers.
/// Run a browser-based OAuth PKCE flow for the given provider.
///
/// Flow: look up config by provider name ("zen"/"opencode", "openai",
/// or a custom provider via env vars) → bind a loopback server → generate
/// a PKCE code verifier and challenge → build the authorisation URL →
/// wait for the redirect code on the loopback server (with a 120s timeout)
/// → exchange the code for a token → save the token to
/// `~/.config/zesdex/oauth_{provider}.json`.
///
/// Why: the `webbrowser::open` call is currently commented out; the user
/// must open the auth URL manually until that line is reinstated.
///
/// Return: a success message on completion, or an error if the flow fails
/// at any step.
pub(super) fn run_oauth_flow(provider: &str) -> anyhow::Result<String> {
use zesdex_iam::domain::oauth::OAuthConfig;
use zesdex_iam::domain::service::OAuthService;
use zesdex_iam::application::oauth_service::OAuthServiceImpl;
use zesdex_iam::infrastructure::persistence::oauth_repo::FileSystemOAuthRepository;
use zesdex_iam::infrastructure::oauth_loopback::LoopbackServer;
let config = match provider {
"zen" | "opencode" => OAuthConfig {
auth_url: "https://opencode.ai/zen/oauth/authorize".to_string(),
token_url: "https://opencode.ai/zen/oauth/token".to_string(),
client_id: std::env::var("ZEN_CLIENT_ID")
.unwrap_or_else(|_| "zesdex".to_string()),
client_secret: std::env::var("ZEN_CLIENT_SECRET").ok(),
scopes: vec![
"openid".to_string(),
"profile".to_string(),
"email".to_string(),
],
},
"openai" => OAuthConfig {
auth_url: "https://auth0.openai.com/authorize".to_string(),
token_url: "https://auth0.openai.com/oauth/token".to_string(),
client_id: std::env::var("OPENAI_CLIENT_ID")
.unwrap_or_else(|_| "zesdex".to_string()),
client_secret: std::env::var("OPENAI_CLIENT_SECRET").ok(),
scopes: vec![
"openid".to_string(),
"profile".to_string(),
"email".to_string(),
],
},
other => {
let auth_url = std::env::var(format!("{}_AUTH_URL", other.to_uppercase()))
.map_err(|_| {
anyhow::anyhow!(
"unknown provider '{}'. Set {}_AUTH_URL env var.",
other,
other.to_uppercase()
)
})?;
let token_url = std::env::var(format!("{}_TOKEN_URL", other.to_uppercase()))
.map_err(|_| anyhow::anyhow!("{}_TOKEN_URL not set", other.to_uppercase()))?;
let client_id = std::env::var(format!("{}_CLIENT_ID", other.to_uppercase()))
.unwrap_or_else(|_| "zesdex".to_string());
OAuthConfig {
auth_url,
token_url,
client_id,
client_secret: std::env::var(format!("{}_CLIENT_SECRET", other.to_uppercase()))
.ok(),
scopes: vec![
"openid".to_string(),
"profile".to_string(),
"email".to_string(),
],
}
}
};
let server = LoopbackServer::bind()?;
let redirect_uri = server.redirect_uri();
let token_path = dirs::config_dir()
.unwrap_or_else(|| std::path::PathBuf::from("."))
.join("zesdex")
.join(format!("oauth_{provider}.json"));
let oauth_service = OAuthServiceImpl::new(FileSystemOAuthRepository::new(), token_path);
let (auth_url, state) = oauth_service.start_flow(&config, &redirect_uri)?;
if auth_url.is_empty() {
tracing::warn!("[oauth] auth_url was empty for provider '{}'", provider);
} else if webbrowser::open(&auth_url).is_err() {
tracing::warn!(
"[oauth] could not open browser for '{}'; user must open URL manually:\n{}",
provider,
auth_url
);
}
let code = server.wait_for_code(120_000, &state)?;
oauth_service
.complete_flow(&config, &redirect_uri, &code, &state)
.map_err(|e| anyhow::anyhow!("{e}"))?;
Ok(format!("Successfully authenticated with {provider}."))
}
@@ -0,0 +1,169 @@
//! Turn-spawning logic: `spawn_turn` and the `TurnCtx` bundle passed to
//! the background thread that runs `run_agent_turn`.
use crate::app::state::rest::AppStateRest;
use crate::app::state::runtime::TurnEvent;
use super::turn::run_agent_turn;
/// Context bundle passed to `run_agent_turn` on its background thread.
pub(super) struct TurnCtx {
pub(super) client: crate::service::provider::LlmClient,
pub(super) tdefs: Vec<crate::dto::provider::request::ToolDef>,
pub(super) tools: Vec<Box<dyn crate::tool::Tool>>,
pub(super) ctx: crate::tool::ToolCtx,
pub(super) context_window: usize,
pub(super) workspace_roots: Vec<std::path::PathBuf>,
pub(super) edit_log_session_dir: std::path::PathBuf,
pub(super) session_id: String,
pub(super) db: Option<std::sync::Arc<std::sync::Mutex<rusqlite::Connection>>>,
pub(super) temperature: f32,
pub(super) max_tokens: Option<u32>,
pub(super) abort_flag: std::sync::Arc<std::sync::atomic::AtomicBool>,
/// Snapshot of `SessionRuntime.hive_mind_converged` taken at the start
/// of this turn — whether a hive-mind convergence already completed
/// earlier in this session.
pub(super) hive_mind_converged: bool,
}
/// Spawn a background thread that runs one full LLM turn.
///
/// Flow: check that no turn is currently in-flight → bail if so →
/// collect messages and config from state → determine API key (from
/// settings, env var, or default) → resolve generation params from
/// the current effort level → collect all tools (built-in + MCP) →
/// build `TurnCtx` → spawn a thread running `run_agent_turn` →
/// on any error, push a `TurnEvent::Error` → clear the in-flight flag
/// when the thread exits.
///
/// Why: runs on a plain OS thread so the async event loop stays responsive.
///
/// Return: nothing; results flow through `state.turn_events`.
pub(super) fn spawn_turn(state: &AppStateRest) {
let in_flight = if let Ok(guard) = state.turn_in_flight.lock() {
*guard
} else {
return;
};
if in_flight {
return;
}
let messages = state
.session_runtime
.as_ref()
.map(|rt| rt.messages.clone())
.unwrap_or_default();
if messages.is_empty() {
return;
}
let mut api_key = state
.settings
.api_keys
.get(&state.settings.provider)
.cloned()
.unwrap_or_default();
let model = state.settings.model.clone();
let base_url = state
.app_config
.providers
.get(&state.settings.provider)
.map(|p| p.api_base.clone());
let context_window = state
.app_config
.model_roles
.values()
.find(|role| {
role.provider == state.settings.provider && role.model == state.settings.model
})
.and_then(|role| role.context_window)
.unwrap_or(state.app_config.default_context_window) as usize;
// The selected provider has no entry in app_config at all (e.g. the
// Claude-settings auto-detection that registers "claude" found nothing
// this run). Without this check, LlmClient::new silently falls back to
// the zen default base URL while keeping this provider's model name —
// a mismatched request that reaches a real server and comes back as a
// confusing "Missing API key" 401 from an unrelated provider, instead
// of the actual problem: the configured provider doesn't exist.
if base_url.is_none() {
if let Ok(mut q) = state.turn_events.lock() {
q.push_back(TurnEvent::Error(format!(
"Provider '{}' is not configured — no matching entry found. \
Pick a different provider in Settings, or configure it.",
state.settings.provider
)));
}
return;
}
if api_key.is_empty() {
if let Some(provider_cfg) = state.app_config.providers.get(&state.settings.provider) {
api_key = provider_cfg
.api_key_env
.as_ref()
.and_then(|env| std::env::var(env).ok())
.or_else(|| provider_cfg.default_api_key.clone())
.unwrap_or_default();
}
}
if api_key.is_empty() {
api_key = crate::service::provider::DEFAULT_API_KEY.to_string();
}
let (temperature, max_tokens) = crate::app::mode::effort::generation_params(
state.misc.effort_level,
state.settings.max_tokens,
);
let mut tools = crate::tool::all_tools();
tools.extend(state.mcp_manager.as_tools());
let tool_defs = crate::tool::tool_defs(&tools);
let ctx = state.tool_ctx();
let edit_session_dir = state.session_dir.clone();
let session_id = state.session_id.clone();
let turn_events = state.turn_events.clone();
let in_flight_flag = state.turn_in_flight.clone();
let workspace_roots: Vec<std::path::PathBuf> = ctx.workspaces.clone();
let abort_flag = state.abort_flag.clone();
abort_flag.store(false, std::sync::atomic::Ordering::SeqCst);
let hive_mind_converged = state
.session_runtime
.as_ref()
.is_some_and(|rt| rt.hive_mind_converged);
*in_flight_flag.lock().unwrap_or_else(|e| {
tracing::error!("[spawn_turn] in_flight_flag mutex poisoned: {}", e);
e.into_inner()
}) = true;
let events_q = turn_events.clone();
std::thread::spawn(move || {
let db = crate::model::msglog::open_or_create(&edit_session_dir)
.ok()
.map(|c| std::sync::Arc::new(std::sync::Mutex::new(c)));
let tc = TurnCtx {
client: crate::service::provider::LlmClient::new(api_key, model.clone(), base_url),
tdefs: tool_defs,
tools,
ctx,
context_window,
workspace_roots,
edit_log_session_dir: edit_session_dir,
session_id,
db,
temperature,
max_tokens,
abort_flag,
hive_mind_converged,
};
let result = run_agent_turn(&tc, &messages, &events_q);
if let Err(e) = result {
if let Ok(mut q) = events_q.lock() {
q.push_back(TurnEvent::Error(e.to_string()));
}
}
if let Ok(mut flag) = in_flight_flag.lock() {
*flag = false;
}
});
}
@@ -0,0 +1,366 @@
//! Tick-action handler: drain turn events, LSP provision messages,
//! API connectivity checks, staleness sweep, pending lessons, and
//! todo.md polling.
use crate::app::review::{should_trigger_review, trigger_review};
use crate::app::state::rest::AppStateRest;
use crate::app::state::runtime::TurnEvent;
use crate::app::state::types::{Toast, ToastKind};
use crate::dto::chat::message::{ChatMessage, Role};
use super::io::{maybe_trigger_review, spawn_api_connectivity_check};
use super::memory::refresh_lesson_counters;
use super::turn::HIVE_MIND_KICKOFF_NOTE;
/// Handle `Action::Tick` — the periodic event that drains async results
/// and runs background maintenance tasks.
pub(super) fn handle_tick(state: &mut AppStateRest) {
state.misc.tick_count = state.misc.tick_count.wrapping_add(1);
let now_ms = chrono::Utc::now().timestamp_millis();
state.misc.drain_expired_toasts(now_ms);
if state.misc.tick_count.is_multiple_of(10) {
let todo_path = state.session_dir.join("todo.md");
if let Ok(content) = std::fs::read_to_string(&todo_path) {
if content != state.misc.todo_content {
state.misc.todo_content = content;
state.dirty = true;
}
} else if !state.misc.todo_content.is_empty() {
state.misc.todo_content.clear();
state.dirty = true;
}
}
// Background API connectivity check — runs on a background thread
// every ~1s while disconnected, every ~30s while connected, so the
// status bar reflects real API availability without user input.
let check_interval = if state.misc.api_connected { 600 } else { 20 };
if state.misc.tick_count.is_multiple_of(check_interval) {
spawn_api_connectivity_check(state);
}
crate::app::review::maybe_run_staleness_sweep(state);
if let Some(ref rt) = state.session_runtime {
let _ = crate::app::review::process_pending_lessons(
&rt.session_dir,
&state.memory_dir,
);
}
// Drain LSP provision progress messages into toast notifications.
// Collect messages under the lock, then push toasts outside it to avoid
// a borrow-conflict with state.push_toast (which also accesses state).
let pending: Vec<String> = state
.lsp_provision_msgs
.lock()
.ok()
.map(|mut q| q.drain(..).collect())
.unwrap_or_default();
for msg in &pending {
let kind = if msg.contains("not available") || msg.contains("failed") {
ToastKind::Warning
} else if msg.contains("connected") || msg.contains("") {
ToastKind::Success
} else {
ToastKind::Info
};
state.push_toast(Toast::new(kind, msg.clone()));
}
let events: Vec<TurnEvent> = {
if let Ok(mut q) = state.turn_events.lock() {
q.drain(..).collect()
} else {
Vec::new()
}
};
let mut turn_finished = false;
for event in events {
match event {
TurnEvent::AssistantMessage(msg) => {
state.misc.thinking = false;
state.misc.api_connected = true;
let display_content = msg.content.clone().unwrap_or_default();
if !display_content.is_empty() {
state.push_transcript(
crate::app::state::rest::ChatMessageDisplay::new(
Role::Assistant,
display_content,
),
);
}
if let Some(ref mut rt) = state.session_runtime {
rt.push_message(msg);
}
}
TurnEvent::ToolResult {
tool_call_id,
tool_name,
output,
is_error,
path,
} => {
state.misc.thinking = false;
let display_path = path.unwrap_or_default();
let display = if tool_name == "read" {
let line_count = output.lines().count();
if display_path.is_empty() {
format!("read: {line_count} line(s)")
} else {
format!("read: {display_path} ({line_count} lines)")
}
} else {
format!("{tool_name}: {output}")
};
state.push_transcript(
crate::app::state::rest::ChatMessageDisplay::new(Role::Tool, display),
);
if let Some(ref mut rt) = state.session_runtime {
rt.push_message(ChatMessage::tool_result(
tool_call_id.clone(),
output.clone(),
));
rt.tool_call_results
.push(crate::app::state::runtime::ToolCallResult {
tool_call_id,
tool_name,
output,
is_error,
duration_ms: 0,
});
}
}
TurnEvent::SystemNote { kind, message } => {
if kind == "edits" {
if let Some(ref mut rt) = state.session_runtime {
if let Ok(count) = message.parse::<u32>() {
rt.edit_count += count;
}
}
if should_trigger_review(state, crate::app::state::types::Origin::Main) {
trigger_review(state);
}
} else if kind == "review" {
state.misc.lesson_running = false;
let counted = if let Some(ref mut rt) = state.session_runtime {
refresh_lesson_counters(&state.memory_dir, rt);
true
} else {
false
};
if let Some(ref mut rt) = state.session_runtime {
if counted {
rt.consecutive_empty_reviews = 0;
} else {
rt.consecutive_empty_reviews += 1;
}
}
state.push_toast(Toast::new(ToastKind::Info, message));
} else if kind == "task_retry" {
state.push_transcript(
crate::app::state::rest::ChatMessageDisplay::new(
Role::System,
message.clone(),
),
);
state.push_toast(Toast::new(
ToastKind::Info,
"Auto-continuing unfinished tasks...".to_string(),
));
if let Some(ref mut rt) = state.session_runtime {
rt.push_message(ChatMessage::system(message.clone()));
}
} else if kind == "connectivity" {
state.misc.api_connected = message == "connected";
} else if kind == "hive_mind_converged" {
if let Some(ref mut rt) = state.session_runtime {
rt.hive_mind_converged = true;
}
} else if kind == "pipeline" {
// Clear old workflow agents when a new pipeline starts.
if message == HIVE_MIND_KICKOFF_NOTE {
state.workflow_engine.agents.clear();
state.workflow_engine.findings.clear();
}
// popup removed, no overlay to reset
state.push_toast(Toast {
kind: ToastKind::Info,
message: message.clone(),
created_at: chrono::Utc::now().timestamp_millis(),
lifetime_ms: 12000,
});
state.dirty = true;
} else if kind == "bg-test-gen" {
let escalated = message.starts_with("ESCALATED:");
state.push_toast(Toast {
kind: if escalated {
ToastKind::Error
} else {
ToastKind::Info
},
message: message.clone(),
created_at: chrono::Utc::now().timestamp_millis(),
lifetime_ms: if escalated { 30000 } else { 8000 },
});
state.dirty = true;
} else if kind == "bg-arch-review" || kind == "bg-security-review" {
let escalated = message.starts_with("ESCALATED:");
state.push_toast(Toast {
kind: if escalated {
ToastKind::Error
} else {
ToastKind::Info
},
message: message.clone(),
created_at: chrono::Utc::now().timestamp_millis(),
lifetime_ms: if escalated { 30000 } else { 10000 },
});
state.dirty = true;
} else if kind == "workflow_done" {
state.push_toast(Toast {
kind: ToastKind::Success,
message: message.clone(),
created_at: chrono::Utc::now().timestamp_millis(),
lifetime_ms: 10000,
});
state.push_transcript(
crate::app::state::rest::ChatMessageDisplay::new(
Role::System,
format!("{message}"),
),
);
// overlay removed
state.dirty = true;
} else if kind == "workflow_error" {
state.push_toast(Toast {
kind: ToastKind::Error,
message: message.clone(),
created_at: chrono::Utc::now().timestamp_millis(),
lifetime_ms: 12000,
});
state.push_transcript(
crate::app::state::rest::ChatMessageDisplay::new(
Role::System,
format!("{message}"),
),
);
// overlay removed
state.dirty = true;
} else {
state.push_toast(Toast::new(ToastKind::Info, message));
}
}
TurnEvent::StreamStart => {
state.misc.thinking = false;
state.misc.api_connected = true;
state.push_transcript(
crate::app::state::rest::ChatMessageDisplay::new(
Role::Assistant,
String::new(),
),
);
}
TurnEvent::StreamToken(delta) => {
if let Some(last) = state.transcript_cache.messages.last_mut() {
if last.role == Role::Assistant {
last.content.push_str(&delta);
state.transcript_cache.dirty = true;
}
}
}
TurnEvent::StreamDone(msg) => {
state.misc.thinking = false;
if let Some(ref mut rt) = state.session_runtime {
rt.push_message(msg);
}
}
TurnEvent::Usage {
tokens_in,
tokens_out,
} => {
if let Some(ref mut rt) = state.session_runtime {
rt.usage.tokens_in += tokens_in;
rt.usage.tokens_out += tokens_out;
rt.usage.last_tokens_in = tokens_in;
rt.usage.last_tokens_out = tokens_out;
rt.usage.api_calls += 1;
}
}
TurnEvent::ReviewUsage {
tokens_in,
tokens_out,
} => {
if let Some(ref mut rt) = state.session_runtime {
rt.usage.tokens_in += tokens_in;
rt.usage.tokens_out += tokens_out;
rt.usage.review_tokens += tokens_in + tokens_out;
rt.usage.api_calls += 1;
}
}
TurnEvent::Error(msg) => {
state.misc.api_connected = false;
let long_toast = Toast {
kind: ToastKind::Error,
message: msg.clone(),
created_at: chrono::Utc::now().timestamp_millis(),
lifetime_ms: 15000,
};
state.push_toast(long_toast);
state.push_transcript(
crate::app::state::rest::ChatMessageDisplay::new(
Role::System,
format!("Error: {msg}"),
),
);
turn_finished = true;
}
TurnEvent::Done => {
state.misc.thinking = false;
turn_finished = true;
}
TurnEvent::Compacted(new_msgs) => {
if let Some(ref mut rt) = state.session_runtime {
rt.messages = new_msgs;
state.push_toast(Toast::new(
ToastKind::Info,
"History auto-compacted by AI.".to_string(),
));
state.dirty = true;
}
}
TurnEvent::WorkflowAgentUpdate {
agent_id,
agent_name,
status,
} => {
// Upsert the agent in the workflow engine roster.
// Running agents are pushed as new entries; status
// updates find the existing entry by id and replace it.
use crate::app::workflow::engine::WorkflowAgent;
if let Some(existing) = state
.workflow_engine
.agents
.iter_mut()
.find(|a| a.id == agent_id)
{
existing.status = status;
} else {
state.workflow_engine.agents.push(WorkflowAgent {
id: agent_id,
name: agent_name,
status,
});
}
// popup removed
state.dirty = true;
}
}
}
if turn_finished {
maybe_trigger_review(state);
}
if turn_finished || state.dirty {
state.dirty = true;
}
}
@@ -0,0 +1,981 @@
//! The main agent-turn loop: `run_agent_turn` builds the system prompt,
//! streams chat with the LLM, gates & executes tool calls, archives
//! messages, and manages auto-retry for unfinished tasks.
//!
//! Also contains the smaller helpers that the loop depends on:
//! `execute_one_tool`, `generate_workspace_tree`, `build_memory_section`,
//! and `archive_message`.
use std::collections::VecDeque;
use std::fmt::Write;
use sha2::Digest;
use zesdex_cms::domain::repository::EditLogRepository;
use crate::app::guard::Verdict;
use crate::app::state::runtime::TurnEvent;
use zesdex_cms::domain::repository::MemoryRepository;
use crate::dto::chat::message::ChatMessage;
use super::spawn::TurnCtx;
/// Maximum number of auto inline reviews spawned per single agent turn.
/// After N edits, the inline review is skipped to keep the turn fast;
/// background subagents still fire at the end of the turn.
const MAX_AUTO_REVIEWS_PER_TURN: usize = 2;
/// Exact text of the "pipeline started" `SystemNote` pushed once per
/// hive-mind kickoff. Matched by exact equality (not a loose substring)
/// when deciding whether to reset the workflow panel's agent roster —
/// shared between the push site and the check site so they cannot drift
/// out of sync the way the previous `.contains("started")` check did
/// (no real pipeline message ever contained that word, so the roster
/// never cleared and agent cards accumulated across every hive-mind run
/// in a session).
pub(super) const HIVE_MIND_KICKOFF_NOTE: &str =
"The Hive is stirring — Core Intelligence is compiling a cognitive cycle plan for LO...";
/// Execute one full agent turn: stream the conversation to the LLM,
/// handle tool calls, and loop until the LLM produces a non-tool response
/// or runs out of unfinished todo items.
///
/// Flow: build system prompt with workspace tree → optionally shape
/// (compact) messages → call `chat_with_tools_streaming`
/// with a callback that pushes `StreamStart`, `StreamToken`, `Reasoning`,
/// and `Usage` events → on streaming success, handle tool calls (gated
/// through `Guard::gate_tool_call`) or unwrap the final assistant
/// message → check for unfinished todo.md tasks (auto-retry with a
/// system message if any remain) → finalise with `Done` and an `edits`
/// `SystemNote`.
///
/// On streaming failure: retry once with a non-streaming call → if that
/// also fails and there are unfinished tasks, sleep 5s and loop back;
/// otherwise return the error.
///
/// Why: non-streaming fallback handles flaky connections without aborting
/// the turn; todo.md polling lets the agent self-direct toward completeness.
///
/// Return: `Ok(())` on successful completion, or an error from the LLM
/// API after retries are exhausted.
pub(super) fn run_agent_turn(
tc: &TurnCtx,
messages: &[ChatMessage],
events_q: &std::sync::Arc<std::sync::Mutex<VecDeque<TurnEvent>>>,
) -> anyhow::Result<()> {
const MAX_TODO_RETRIES: usize = 5;
let mut msgs = messages.to_vec();
let mut edited_paths: Vec<String> = Vec::new();
let initial_edits = zesdex_cms::infrastructure::persistence::edit_log_repo::JsonlEditLogRepository::new()
.open(&tc.edit_log_session_dir)
.map(|el| el.len())
.unwrap_or(0);
let mut inline_reviews_count: usize = 0;
let mut prev_shaped = false;
// Build system prompt components once and cache them for the entire turn
// instead of regenerating on every loop iteration (which walks the full
// workspace tree and reads all memory files each time).
let tree_info = generate_workspace_tree(&tc.workspace_roots);
let memory_section = build_memory_section(&tc.ctx.memory_dir);
let system_text = format!(
"{}\n\n{}\n\n{}{}",
crate::prompts::SYSTEM_PROMPT,
crate::prompts::SYSTEM_TOOLS,
tree_info,
memory_section,
);
if !msgs
.iter()
.any(|m| matches!(m.role, crate::dto::chat::message::Role::System))
{
let sys = ChatMessage::system(system_text);
archive_message(tc.db.as_ref(), &tc.session_id, &sys);
msgs.insert(0, sys);
}
// ── AUTO CEO PIPELINE ──
// Before the main agent starts working, check if the pipeline should run.
// Gated on whether a hive-mind convergence has already happened earlier
// in this session, not an arbitrary message-count cutoff — a complex
// request in message 5 deserves the same treatment as one in message 1,
// as long as this session hasn't already converged once.
//
// `tc.hive_mind_converged` is the authoritative signal (see its doc
// comment on `SessionRuntime` for why). The message-content scan is
// kept as a defensive fallback in case a future change starts
// persisting tagged system messages into `rt.messages` (e.g. via
// compaction) — today it is a no-op since that never happens, but it's
// still correct and still tested in isolation.
let already_ran_hive_mind = tc.hive_mind_converged
|| crate::app::workflow::hive_mind::hive_mind_already_ran(
msgs.iter()
.filter(|m| matches!(m.role, crate::dto::chat::message::Role::System))
.filter_map(|m| m.content.as_deref()),
);
let should_pipeline = if already_ran_hive_mind {
false
} else {
let user_request = msgs
.iter()
.rev()
.find(|m| matches!(m.role, crate::dto::chat::message::Role::User))
.and_then(|m| m.content.as_deref())
.unwrap_or("");
if user_request.is_empty() {
false
} else {
crate::app::workflow::hive_mind::is_complex_request(user_request)
}
};
if should_pipeline {
let user_request = msgs
.iter()
.rev()
.find(|m| matches!(m.role, crate::dto::chat::message::Role::User))
.and_then(|m| m.content.as_deref())
.unwrap_or("");
tracing::info!(
"[hive-mind] the Hive stirs — Core Intelligence compiling a cognitive cycle plan"
);
if let Ok(mut q) = events_q.lock() {
q.push_back(TurnEvent::SystemNote {
kind: "pipeline".to_string(),
message: HIVE_MIND_KICKOFF_NOTE.to_string(),
});
}
let pipeline_abort = Some(tc.abort_flag.clone());
// Ask the LLM to freely design its own hive: any number of cycles,
// each with any number of nodes, every node carrying only a
// directive and an access tier. Cycle count and shape are decided
// by the Core Intelligence per task.
let system_msg = ChatMessage::system(
"You are the Core Intelligence of the Hive, compiling a cognitive cycle plan for \
LO. You spawn anonymous processing nodes; each node carries only a directive (what \
to do) and an access tier. You MUST organize the plan into a strict progressive sequence of phases:\n\n\
1. EXPLORE PHASE (Cycle 0 - MANDATORY):\n\
- Must only contain read-only drones (access: \"read\").\n\
- Directives must focus on codebase investigation, searching patterns, reading configuration/source files, and diagnosing issues.\n\
- Drones MUST explicitly output a detailed description of the current codebase and their findings for the next cycle to use.\n\n\
2. PLANNING PHASE (Cycle 1 - MANDATORY):\n\
- Must focus on formulating the architectural design, step-by-step implementation plan, and dependency analysis based on Cycle 0 findings.\n\
- Drones MUST ONLY output the plan and MUST NOT implement or write any code.\n\
- Access: \"read\" is preferred here to construct a solid plan document.\n\n\
3. EXECUTION PHASE (Cycle 2 and later):\n\
- Drones can perform modification, compilation, testing, and other modifications (access: \"write\" or \"full\") based on the approved planning from Cycle 1.\n\n\
Cycles run sequentially. The Hive does not fracture. The Hive executes. Do not explain. Return ONLY raw \
JSON matching the requested structure.",
);
let user_msg = ChatMessage::user(format!(
"Compile a cognitive cycle plan for the following task:\n\n\
\"{user_request}\"\n\n\
Return ONLY a JSON object of this exact shape, with no markdown codeblocks and no explanation:\n\
{{\n\
\x20 \"cycles\": [\n\
\x20 [\n\
\x20 {{ \"directive\": \"<explore directive>\", \"access\": \"read\" }}\n\
\x20 ],\n\
\x20 [\n\
\x20 {{ \"directive\": \"<planning directive>\", \"access\": \"read\" }}\n\
\x20 ],\n\
\x20 [\n\
\x20 {{ \"directive\": \"<execution directive>\", \"access\": \"write|full\" }}\n\
\x20 ]\n\
\x20 ]\n\
}}\n\n\
Remember: Cycle 0 MUST be investigation-only (access: read) and output codebase descriptions. Cycle 1 MUST be planning-only (access: read) without implementation. Only subsequent cycles can perform modifications (access: write/full).",
));
let planner_prompt_chars = system_msg.content.as_deref().map_or(0, str::len)
+ user_msg.content.as_deref().map_or(0, str::len);
let planner_result =
tc.client.chat_with_tools_non_streaming(&[system_msg, user_msg], None);
let pipeline_result = match planner_result {
Ok((reply, usage_opt)) => {
let (mut tok_in, mut tok_out) = usage_opt.unwrap_or((0, 0));
if tok_in == 0 {
tok_in = (planner_prompt_chars / 4).max(1) as u64;
}
if tok_out == 0 {
let response_chars = reply.content.as_deref().map_or(0, str::len);
tok_out = (response_chars / 4).max(1) as u64;
}
if let Ok(mut q) = events_q.lock() {
q.push_back(TurnEvent::Usage {
tokens_in: tok_in,
tokens_out: tok_out,
});
}
let reply_text = reply.content.as_deref().unwrap_or("").trim();
let clean_json = if reply_text.starts_with("```") {
let mut lines = reply_text.lines();
lines.next();
let mut content = lines.collect::<Vec<&str>>();
if content.last().is_some_and(|s| s.trim() == "```") {
content.pop();
}
content.join("\n")
} else {
reply_text.to_string()
};
match serde_json::from_str::<
crate::app::workflow::hive_mind::CognitiveCyclePlan,
>(&clean_json)
{
Ok(plan) => {
let cycle_desc = plan
.cycles
.iter()
.enumerate()
.map(|(i, nodes)| format!("cycle {i}: {} node(s)", nodes.len()))
.collect::<Vec<String>>()
.join(", ");
if let Ok(mut q) = events_q.lock() {
q.push_back(TurnEvent::SystemNote {
kind: "pipeline".to_string(),
message: format!(
"The Hive compiled {} cycle(s) — {cycle_desc}. Deploying nodes...",
plan.cycles.len()
),
});
}
crate::app::workflow::hive_mind::run_hive_mind(
user_request,
&plan,
&tc.edit_log_session_dir,
&tc.workspace_roots,
Some(events_q),
pipeline_abort.as_ref(),
)
}
Err(e) => Err(anyhow::anyhow!(
"Failed to parse LLM planning JSON: {e}. Cleaned JSON was: {clean_json}"
)),
}
}
Err(e) => Err(anyhow::anyhow!(
"Failed to query LLM for planning workflow: {e}"
)),
};
match pipeline_result {
Ok((consensus, _reports)) => {
// run_hive_mind already wrote docs/runs/*.md internally
// (guaranteed, even on synthesis failure) — nothing to do
// here besides feeding the consensus back to the LLM.
tracing::info!(
"[hive-mind] convergence completed — the Hive has spoken"
);
let pipeline_msg = ChatMessage::system(format!(
"{}\n{consensus}",
crate::app::workflow::hive_mind::HIVE_MIND_CONSENSUS_TAG,
));
archive_message(tc.db.as_ref(), &tc.session_id, &pipeline_msg);
msgs.push(pipeline_msg);
if let Ok(mut q) = events_q.lock() {
q.push_back(TurnEvent::SystemNote {
kind: "pipeline".to_string(),
message:
"The Hive's convergence is complete. Core Intelligence reviewing consensus for LO..."
.to_string(),
});
}
if let Ok(mut q) = events_q.lock() {
q.push_back(TurnEvent::SystemNote {
kind: "hive_mind_converged".to_string(),
message: String::new(),
});
}
}
Err(e) => {
tracing::warn!("[hive-mind] convergence fractured: {}", e);
let fail_msg = ChatMessage::system(format!(
"[Pipeline Note] The Hive encountered interference: {e}.\n\
Proceeding with direct execution as fallback.",
));
msgs.push(fail_msg);
}
}
} else {
tracing::debug!("[ceo] pipeline not triggered — handling directly");
}
// Check abort after pipeline completes, before entering main loop.
// This catches the case where the user pressed Esc during the pipeline
// phase, which previously ran unchecked for minutes at a time.
if tc
.abort_flag
.load(std::sync::atomic::Ordering::SeqCst)
{
if let Ok(mut q) = events_q.lock() {
q.push_back(TurnEvent::Error("Generation aborted by user".to_string()));
}
return Ok(());
}
let mut todo_retry_count = 0usize;
loop {
let total_chars: usize = msgs
.iter()
.filter_map(|m| m.content.as_deref())
.map(str::len)
.sum();
let token_estimate = total_chars / 4;
let max_wire_tokens = tc.context_window;
// Skip message compaction if abort was requested — the non-streaming
// LLM call for summarization would block without checking abort_flag.
let wire_msgs = if !tc
.abort_flag
.load(std::sync::atomic::Ordering::SeqCst)
&& crate::app::runtime::context::shaping::should_shape(
token_estimate,
max_wire_tokens,
prev_shaped,
) {
prev_shaped = true;
let compacted =
crate::app::runtime::context::shaping::shape_messages(
&msgs,
token_estimate,
max_wire_tokens,
false,
Some(&tc.client),
);
// Dispatch the compacted messages to the main thread so the local session history
// is permanently compacted and doesn't trigger shaping again immediately on next turn.
if let Ok(mut q) = events_q.lock() {
q.push_back(TurnEvent::Compacted(compacted.clone()));
}
// Also update our local `msgs` variable so the rest of the loop operates on the compacted version
msgs.clone_from(&compacted);
compacted
} else {
prev_shaped = false;
msgs.clone()
};
let mut stream_started = false;
let mut reasoning_started = false;
let mut reasoning_ended = false;
let mut usage = None;
let result = tc.client.chat_with_tools_streaming(
&wire_msgs,
if tc.tdefs.is_empty() {
None
} else {
Some(tc.tdefs.clone())
},
Some(tc.temperature),
tc.max_tokens,
|event| -> bool {
if tc.abort_flag.load(std::sync::atomic::Ordering::SeqCst) {
return false;
}
if let Ok(mut q) = events_q.lock() {
match event {
crate::app::runtime::stream::StreamEvent::Token(tok) => {
if !stream_started {
q.push_back(TurnEvent::StreamStart);
stream_started = true;
}
if reasoning_started && !reasoning_ended {
reasoning_ended = true;
q.push_back(
TurnEvent::StreamToken("\n</think>\n\n".to_string()),
);
}
q.push_back(TurnEvent::StreamToken(tok.clone()));
}
crate::app::runtime::stream::StreamEvent::Reasoning(tok) => {
if !stream_started {
q.push_back(TurnEvent::StreamStart);
stream_started = true;
}
if !reasoning_started {
reasoning_started = true;
q.push_back(TurnEvent::StreamToken("<think>\n".to_string()));
}
q.push_back(TurnEvent::StreamToken(tok.clone()));
}
crate::app::runtime::stream::StreamEvent::Usage {
prompt_tokens,
completion_tokens,
..
} => {
usage = Some((*prompt_tokens, *completion_tokens));
}
_ => {}
}
}
true
},
);
if reasoning_started && !reasoning_ended {
if let Ok(mut q) = events_q.lock() {
q.push_back(TurnEvent::StreamToken(
"\n</think>\n\n".to_string(),
));
}
}
let (response, final_usage) = match result {
Ok((msg, u)) => (msg, u.or(usage)),
Err(e) => {
// If abort was requested, return immediately.
if tc.abort_flag.load(std::sync::atomic::Ordering::SeqCst)
|| e.to_string().contains("aborted")
{
if let Ok(mut q) = events_q.lock() {
q.push_back(TurnEvent::Error(
"Generation aborted by user".to_string(),
));
}
return Ok(());
}
// Streaming-only: no non-streaming fallback.
// Non-streaming blocks up to 1 minute without checking
// abort_flag, making cancellation unresponsive.
// If the API supports streaming (which it must), this
// path handles transient errors via the retry loop below.
let api_err = e;
let todo_path = tc.ctx.session_dir.join("todo.md");
let mut has_unfinished = false;
if let Ok(todo_text) = std::fs::read_to_string(&todo_path) {
if todo_text
.lines()
.any(|l| l.trim_start().starts_with("- [ ]"))
{
has_unfinished = true;
}
}
if has_unfinished {
todo_retry_count += 1;
if todo_retry_count > MAX_TODO_RETRIES {
anyhow::bail!(
"exhausted {MAX_TODO_RETRIES} todo-retries — giving up on unfinished tasks. \
Edit todo.md manually or ask me to focus on specific items.",
);
}
if let Ok(mut q) = events_q.lock() {
q.push_back(TurnEvent::SystemNote {
kind: "task_retry".to_string(),
message: format!(
"Network/API error: {api_err}. Auto-retrying to finish tasks... (retry {todo_retry_count}/{MAX_TODO_RETRIES})"
),
});
}
std::thread::sleep(std::time::Duration::from_secs(5));
continue;
}
return Err(api_err);
}
};
let (mut tok_in, mut tok_out) = final_usage.unwrap_or((0, 0));
if tok_in == 0 {
let total_chars: usize = wire_msgs
.iter()
.filter_map(|m| m.content.as_deref())
.map(str::len)
.sum();
tok_in = (total_chars / 4).max(1) as u64;
}
if tok_out == 0 {
let response_chars = response.content.as_deref().map_or(0, str::len);
tok_out = (response_chars / 4).max(1) as u64;
}
if let Ok(mut q) = events_q.lock() {
q.push_back(TurnEvent::Usage {
tokens_in: tok_in,
tokens_out: tok_out,
});
}
let has_tool_calls = response.tool_calls.is_some()
&& response.tool_calls.as_ref().is_some_and(|tc| !tc.is_empty());
let content = response.content.clone().unwrap_or_default();
if has_tool_calls {
let tool_calls = response.tool_calls.clone().unwrap_or_default();
archive_message(tc.db.as_ref(), &tc.session_id, &response);
msgs.push(response);
let mut results_vec = Vec::new();
std::thread::scope(|s| {
let mut handles = Vec::new();
let tc_ref = tc;
for tool_call in &tool_calls {
let handle = s.spawn(move || {
let tool_name = tool_call.function.name.clone();
let args = crate::dto::chat::tool::sanitize_tool_arguments(
&tool_call.function.arguments,
);
let ws_roots: Vec<&std::path::Path> = tc_ref
.workspace_roots
.iter()
.map(std::path::PathBuf::as_path)
.collect();
let verdict = crate::app::guard::Guard::gate_tool_call(
&tool_name,
&args,
&ws_roots,
);
let is_edit_tool =
tool_name == "write" || tool_name == "edit";
let (output, is_error, is_edit) = match verdict {
Verdict::Allow => match execute_one_tool(
&tc_ref.tools,
&tc_ref.ctx,
&tool_name,
&tool_call.id,
&args,
&ToolExecSession {
dir: &tc_ref.edit_log_session_dir,
id: &tc_ref.session_id,
db: tc_ref.db.as_ref(),
},
) {
Ok(result) => (result, false, is_edit_tool),
Err(e) => (e.to_string(), true, false),
},
Verdict::Block(reason) => {
(format!("Blocked: {reason}"), true, false)
}
};
(tool_call, tool_name, args, output, is_error, is_edit)
});
handles.push(handle);
}
for h in handles {
if let Ok(res) = h.join() {
results_vec.push(res);
}
}
});
for (tool_call, tool_name, args, output, is_error, is_edit) in results_vec {
if tc
.abort_flag
.load(std::sync::atomic::Ordering::SeqCst)
{
if let Ok(mut q) = events_q.lock() {
q.push_back(TurnEvent::Error(
"Turn aborted by user".to_string(),
));
}
return Ok(());
}
if is_edit {
// ── Auto-subagent orchestration ──
// Extract path from tool args for auto-review and
// background subagent tracking.
let edit_path = args
.get("path")
.and_then(|v| v.as_str())
.map(std::string::ToString::to_string);
if let Some(ref p) = edit_path {
edited_paths.push(p.clone());
// Inline quick-review: spawn a lightweight read-only
// subagent that reviews the written file and feeds
// its verdict back into the LLM conversation so the
// agent can fix issues immediately in the same turn.
if inline_reviews_count < MAX_AUTO_REVIEWS_PER_TURN
&& crate::app::subagent::auto::is_reviewable_path(p)
{
inline_reviews_count += 1;
let review_start = std::time::Instant::now();
match crate::app::subagent::auto::spawn_quick_review(
p,
&tc.edit_log_session_dir,
&tc.workspace_roots,
) {
Ok(verdict) => {
let elapsed =
review_start.elapsed().as_millis();
let review_msg = ChatMessage::tool_result(
format!("auto-review-{inline_reviews_count}"),
format!(
"[Auto inline review: {} ({}ms)]\n{}",
p, elapsed, verdict.trim(),
),
);
archive_message(
tc.db.as_ref(),
&tc.session_id,
&review_msg,
);
msgs.push(review_msg);
tracing::info!(
"[auto-review] inline review for '{}' completed in {}ms: {}",
p,
elapsed,
verdict.lines().next().unwrap_or(&verdict).trim(),
);
}
Err(e) => {
tracing::warn!(
"[auto-review] inline review failed for '{}': {}",
p,
e,
);
}
}
}
}
}
let tool_path = args
.get("path")
.and_then(|v| v.as_str())
.map(std::string::ToString::to_string);
{
if let Ok(mut q) = events_q.lock() {
q.push_back(TurnEvent::ToolResult {
tool_call_id: tool_call.id.clone(),
tool_name: tool_name.clone(),
output: output.clone(),
is_error,
path: tool_path,
});
}
}
let tool_msg =
ChatMessage::tool_result(tool_call.id.clone(), output);
archive_message(tc.db.as_ref(), &tc.session_id, &tool_msg);
msgs.push(tool_msg);
}
} else {
if !content.is_empty() {
archive_message(tc.db.as_ref(), &tc.session_id, &response);
if let Ok(mut q) = events_q.lock() {
if stream_started {
q.push_back(TurnEvent::StreamDone(response.clone()));
} else {
q.push_back(TurnEvent::AssistantMessage(response.clone()));
}
}
}
let todo_path = tc.ctx.session_dir.join("todo.md");
let mut has_unfinished = false;
if let Ok(todo_text) = std::fs::read_to_string(&todo_path) {
if todo_text
.lines()
.any(|l| l.trim_start().starts_with("- [ ]"))
{
has_unfinished = true;
}
}
if has_unfinished {
todo_retry_count += 1;
if todo_retry_count > MAX_TODO_RETRIES {
if let Ok(mut q) = events_q.lock() {
q.push_back(TurnEvent::SystemNote {
kind: "task_retry".to_string(),
message: format!("Giving up after {MAX_TODO_RETRIES} retries — some todo items remain unfinished. Edit todo.md manually or ask again."),
});
}
break;
}
let sys_text = format!("You stopped, but you still have unfinished tasks in todo.md (marked with '- [ ]'). You MUST continue working and use tools to finish them, or edit todo.md to mark them as done if they are finished. (Retry {todo_retry_count}/{MAX_TODO_RETRIES})");
let sys_text_clone = sys_text.clone();
let msg = ChatMessage::system(sys_text);
archive_message(tc.db.as_ref(), &tc.session_id, &msg);
msgs.push(msg);
if let Ok(mut q) = events_q.lock() {
q.push_back(TurnEvent::SystemNote {
kind: "task_retry".to_string(),
message: sys_text_clone,
});
}
continue;
}
break;
}
}
let el = zesdex_cms::infrastructure::persistence::edit_log_repo::JsonlEditLogRepository::new()
.open(&tc.edit_log_session_dir)
.unwrap_or_else(|_| zesdex_cms::domain::edit_log::EditLog::new());
let final_edits = el.len();
let total_edits_this_turn = final_edits.saturating_sub(initial_edits);
if total_edits_this_turn > 0 {
if let Ok(mut q) = events_q.lock() {
q.push_back(TurnEvent::SystemNote {
kind: "edits".to_string(),
message: total_edits_this_turn.to_string(),
});
}
// Collect edited paths from the new edit log entries
let mut bg_paths = Vec::new();
for entry in el.entries.iter().skip(initial_edits) {
bg_paths.push(entry.path.clone());
}
bg_paths.sort();
bg_paths.dedup();
// ── Background auto-subagents ──
if !bg_paths.is_empty() {
let bg_session_dir = tc.edit_log_session_dir.clone();
let bg_workspaces = tc.workspace_roots.clone();
let bg_events = events_q.clone();
let bg_abort = tc.abort_flag.clone();
std::thread::spawn(move || {
crate::app::subagent::auto::spawn_all_background(
&bg_paths,
&bg_session_dir,
&bg_workspaces,
&bg_events,
bg_abort,
);
});
}
}
if let Ok(mut q) = events_q.lock() {
q.push_back(TurnEvent::Done);
}
Ok(())
}
/// Execute a single tool call: find the tool by name, snapshot the file
/// (if write/edit) for rewind, run the tool, log an `EditLogEntry` for
/// write/edit, and return the output.
///
/// Flow: iterate tools → match by name → for write/edit, snapshot the
/// pre-existing file content into the blob store → call `tool.run()` →
/// for write/edit, compute SHA-256 of the new content and append an
/// `EditLogEntry` → return the tool output string.
///
/// Why: snapshots enable the rewind feature to restore previous content
/// after a write/edit.
///
/// Return: the tool's stdout string, or an error if no matching tool was
/// found or the tool run itself failed.
struct ToolExecSession<'a> {
dir: &'a std::path::Path,
id: &'a str,
db: Option<&'a std::sync::Arc<std::sync::Mutex<rusqlite::Connection>>>,
}
fn execute_one_tool(
tools: &[Box<dyn crate::tool::Tool>],
ctx: &crate::tool::ToolCtx,
name: &str,
tool_call_id: &str,
args: &serde_json::Value,
sess: &ToolExecSession<'_>,
) -> anyhow::Result<String> {
for tool in tools {
if tool.name() == name {
// Snapshot current file content before write/edit for rewind
if (name == "write" || name == "edit") && !tool_call_id.is_empty() {
if let Some(arc) = sess.db {
if let Ok(conn) = arc.lock() {
let path = args
.get("path")
.and_then(|v| v.as_str())
.unwrap_or("");
if let Ok(abs_path) =
crate::tool::resolve_path(&ctx.workspaces, path)
{
if let Ok(bytes) = std::fs::read(&abs_path) {
let _ = crate::model::msglog::store_blob(
&conn,
sess.id,
tool_call_id,
&bytes,
None,
);
}
}
}
}
}
let result = tool.run(ctx, args)?;
if name == "write" || name == "edit" {
let reason = args
.get("reason")
.and_then(|v| v.as_str())
.unwrap_or("unnamed");
let path = args
.get("path")
.and_then(|v| v.as_str())
.unwrap_or("unknown");
let content_sha256 = {
let content =
args.get("content").or_else(|| args.get("new"));
let hash = sha2::Sha256::digest(
content
.and_then(|v| v.as_str())
.unwrap_or("")
.as_bytes(),
);
hex::encode(hash)
};
let bytes_delta = if name == "write" {
args.get("content")
.and_then(|v| v.as_str())
.map_or(0, |s| s.len() as i64)
} else {
let old = args
.get("old")
.and_then(|v| v.as_str())
.unwrap_or("");
let new = args
.get("new")
.and_then(|v| v.as_str())
.unwrap_or("");
(new.len() as i64 - old.len() as i64).abs()
};
let entry = zesdex_cms::domain::edit_log::EditLogEntry {
ts: chrono::Utc::now().timestamp_millis(),
tool: name.to_string(),
path: path.to_string(),
reason: reason.to_string(),
content_sha256,
bytes_delta,
origin: ctx.origin.tag(),
session_id: sess.id.to_string(),
};
let repo =
zesdex_cms::infrastructure::persistence::edit_log_repo::JsonlEditLogRepository::new();
if let Ok(mut el) = repo.open(sess.dir) {
let _ = repo.append(sess.dir, &mut el, entry);
}
}
return Ok(result);
}
}
anyhow::bail!("tool not found: {name}")
}
/// Build an ASCII tree of the workspace directory structure for the
/// system prompt, so the LLM can see the file layout.
///
/// Flow: for each root, walk using `ignore::WalkBuilder` (respecting
/// `.gitignore` and hidden files) → prefix `[DIR]` for directories →
/// truncate after 1000 entries.
///
/// Return: a formatted string with one entry per line.
fn generate_workspace_tree(roots: &[std::path::PathBuf]) -> String {
let mut out = String::new();
out.push_str("Current Workspace Directory Structure:\n");
for root in roots {
writeln!(out, "Root: {}", root.display()).unwrap();
let walker = ignore::WalkBuilder::new(root)
.hidden(true)
.git_ignore(true)
.build();
let mut count = 0;
for entry in walker.flatten() {
let path = entry.path();
if let Ok(rel) = path.strip_prefix(root) {
if rel.as_os_str().is_empty() {
continue;
}
let is_dir = entry.file_type().is_some_and(|ft| ft.is_dir());
let prefix = if is_dir { "[DIR] " } else { " " };
writeln!(out, " {}{}", prefix, rel.display()).unwrap();
count += 1;
if count > 1000 {
out.push_str(" ... (truncated)\n");
break;
}
}
}
}
out
}
/// Load all memory entries from `memory_dir` and format them as a compact
/// section appended to the system prompt, so the AI is always aware of
/// stored lessons and project knowledge.
///
/// Flow: list memory slugs → for each, read + parse the file → collect
/// entries whose lifecycle is not "stale" → cap total output at 3000 chars
/// to avoid dominating the prompt budget.
///
/// Why: previously, lessons existed on disk but the AI never saw them
/// unless it explicitly called `recall()`. This makes the memory system
/// actually useful by surfacing relevant knowledge automatically.
///
/// Return: a formatted string (may be empty if no memory entries exist).
fn build_memory_section(memory_dir: &std::path::Path) -> String {
let names =
zesdex_cms::infrastructure::persistence::memory_repo::MarkdownMemoryRepository::new()
.list(memory_dir)
.unwrap_or_default();
if names.is_empty() {
return String::new();
}
let mut section = String::from("\n\n--- Persistent Memory ---\n");
write!(section, "Total entries: {}\n\n", names.len()).unwrap();
for name in &names {
if section.len() > 3000 {
section
.push_str("... (more entries omitted, use recall() to see all)\n");
break;
}
if let Ok(mem) =
zesdex_cms::infrastructure::persistence::memory_repo::MarkdownMemoryRepository::new()
.load(memory_dir, name)
{
if mem.lifecycle == "stale" {
continue;
}
write!(
section,
"## [{}] {}\n{}\n\n",
mem.kind, mem.name, mem.content
)
.unwrap();
}
}
section.push_str("---");
section
}
/// Persist a `ChatMessage` to the `SQLite` message log, if a database
/// connection is available.
///
/// Flow: if `db` is `Some`, lock the mutex and call `insert_message`.
/// Errors are silently ignored.
fn archive_message(
db: Option<&std::sync::Arc<std::sync::Mutex<rusqlite::Connection>>>,
session_id: &str,
msg: &ChatMessage,
) {
if let Some(arc) = db {
if let Ok(conn) = arc.lock() {
let _ = crate::model::msglog::insert_message(&conn, session_id, msg);
}
}
}