zesdex/crates/zesdex-backend/src/app/runtime/actions/spawn.rs

//! 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 = crate::service::provider::resolve_api_key(
        &state.settings, &state.app_config,
    );
    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() {
        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;
        }
    });
}