Files
zesdex/apps/infrastructure/src/workflow/hive_mind/cycle.rs
T
asepharyana 6a98d52d54 perf(agent): stabilkan async & parallel — satu runtime, bounded concurrency, isolasi error
Seperti Claude Code: satu runtime shared, concurrency dibatasi, error
subagent terisolasi (satu node gagal tidak menggagalkan cycle).

- feat(runtime): global tokio runtime via OnceLock — ganti 9+ titik
  Runtime::new() per tool call (spawn, parallel_delegate, workflow,
  explore, dir_cache, daemon handler). Hemat resource, hilangkan panic
  path Runtime::new().expect() di daemon compaction.
- fix(workflow): execute_cycle ganti try_join_all (fail-fast) →
  buffer_unordered(8) + isolasi error per node; node gagal di-log dan
  diganti [ERROR], hasil node lain tetap dipakai (Claude Code-style).
- fix(parallel_delegate): spawn subagent dibatasi per batch max_parallel
  (tidak unbounded threads).
- perf(subagent): run_agent adaptif max_tokens (800/1600/4096), temp 0.2,
  truncate tool output 12k, error-recovery note utk tool error berulang.
- test: runtime singleton + block_on (2 test).
2026-08-27 23:25:44 +07:00

120 lines
4.5 KiB
Rust

//! Hive-mind cycle execution — run one cycle of parallel nodes.
//!
//! Flow: load settings → resolve LLM credentials → run all directives in the
//! cycle concurrently via a BOUNDED buffer (`buffer_unordered(MAX)`) → collect
//! `Vec<NodeOutput>`. Unlike `try_join_all`, a single failing node does NOT
//! fail the whole cycle — failed nodes are logged and replaced with an
//! `[ERROR]` output so the remaining results are preserved (like Claude
//! Code's isolated subagents).
use anyhow::Result;
use futures_util::stream::StreamExt;
use tracing::{info, warn};
use zesdex_domain::cms::{AppConfigRepository, SettingsRepository};
use zesdex_domain::core::Store;
use crate::persistence::{JsonAppConfigRepository, JsonSettingsRepository};
use crate::subagent::context::SubagentContext;
use crate::subagent::division::AccessTier;
use crate::subagent::engine::run_agent;
use crate::tools::ToolCtx;
use zesdex_domain::workflow::{CognitiveCycle, NodeDirective, NodeOutput};
/// Maximum number of hive-mind nodes running concurrently per cycle.
/// Keeps thread/runtime pressure bounded (Claude Code-style).
const MAX_CONCURRENT_NODES: usize = 8;
/// Execute one cycle: run each node directive and collect outputs.
///
/// Flow:
/// 1. Load `Settings` and `AppConfig` from the store directory.
/// 2. Resolve provider, model, base_url, and api_key.
/// 3. Spawn directives with bounded concurrency — each builds a
/// `SubagentContext` and calls `run_agent`.
/// 4. Collect `NodeOutput`s; failed nodes are logged and replaced with an
/// `[ERROR]` placeholder so the cycle still completes.
pub async fn execute_cycle(cycle: &CognitiveCycle, tool_ctx: &ToolCtx) -> Result<Vec<NodeOutput>> {
info!(
"Executing cycle {} with {} directives",
cycle.index,
cycle.directives.len()
);
let store = Store::new();
let settings = JsonSettingsRepository::new()
.load(&store.base_dir)
.unwrap_or_default();
let app_config = JsonAppConfigRepository::new()
.load(&store.base_dir)
.unwrap_or_default();
let (provider, model) =
crate::subagent::provider::resolve_subagent_provider(&settings, &app_config);
let base_url = app_config
.providers
.get(&provider)
.map(|p| p.api_base.clone())
.unwrap_or_else(|| zesdex_domain::agent::defaults::DEFAULT_API_BASE.to_string());
let api_key = crate::llm::provider::resolve_api_key(&settings, &app_config);
let cycle_index = cycle.index;
// Run all directives with bounded concurrency. Each node is its own
// future; failures are collected, not propagated (isolated errors).
let tasks: Vec<_> = cycle
.directives
.iter()
.enumerate()
.map(|(i, node_dir): (usize, &NodeDirective)| {
let dir = node_dir.directive.clone();
let access_tier = node_dir.access_tier.clone();
let ctx = SubagentContext::new(
dir.clone(),
tool_ctx.clone(),
access_tier.clone(),
base_url.clone(),
api_key.clone(),
model.clone(),
);
let tc = tool_ctx.clone();
let access = match access_tier.as_str() {
"write" => AccessTier::Write,
"full" => AccessTier::Full,
_ => AccessTier::Read,
};
let node_id = format!("Node-{}-{}", cycle_index, i);
async move {
match run_agent(ctx, &dir, access, tc).await {
Ok(output) => Ok::<NodeOutput, anyhow::Error>(NodeOutput {
id: node_id.clone(),
directive: dir,
output,
}),
Err(e) => {
warn!(node = %node_id, error = %e, "hive-mind node failed (isolated)");
Ok::<NodeOutput, anyhow::Error>(NodeOutput {
id: node_id,
directive: dir,
output: format!("[ERROR] {e}"),
})
}
}
}
})
.collect();
// Bounded concurrency: run at most MAX_CONCURRENT_NODES futures at once.
let mut stream = futures_util::stream::iter(tasks).buffer_unordered(MAX_CONCURRENT_NODES);
let mut results = Vec::with_capacity(cycle.directives.len());
while let Some(node) = stream.next().await {
results.push(node?);
}
Ok(results)
}