From b1c0265e8cdf9278664e64f77fbde4ec8c22fcfd Mon Sep 17 00:00:00 2001
From: asepharyana <superaseph@gmail.com>
Date: Tue, 14 Jul 2026 09:30:35 +0700
Subject: [PATCH] fix(hive-mind): tambah timeout per-node dan jamin dokumentasi
 convergence tetap tertulis saat sintesis gagal

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
---
 src/app/workflow/hive_mind.rs | 57 +++++++++++++++++++++++++++++------
 1 file changed, 47 insertions(+), 10 deletions(-)

diff --git a/src/app/workflow/hive_mind.rs b/src/app/workflow/hive_mind.rs
index 25ac5dd..5814bf3 100644
--- a/src/app/workflow/hive_mind.rs
+++ b/src/app/workflow/hive_mind.rs
@@ -105,10 +105,19 @@ fn build_live(
 /// directive is to reconcile the complete collective state into a single
 /// consensus, not list what each node said.
 ///
-/// Return: `(consensus, all_node_reports)`. `consensus` is the synthesis
-/// node's reconciled output — what the Core Intelligence actually
-/// receives. `all_node_reports` is the complete per-node record,
-/// persisted verbatim to `docs/runs/*.md`.
+/// Concurrency per cycle and the per-node timeout both come from
+/// `Settings::load()` (`workflow_max_concurrency`, `hive_mind_node_timeout_ms`)
+/// rather than a hardcoded cap/no-timeout — a stuck node can no longer hang
+/// the whole convergence forever.
+///
+/// Return: `(consensus, all_node_reports)` on success. `consensus` is the
+/// synthesis node's reconciled output — what the Core Intelligence
+/// actually receives. `all_node_reports` is the complete per-node record.
+///
+/// The convergence doc under `docs/runs/*.md` is written unconditionally
+/// before this function returns — even when synthesis itself fails — so a
+/// synthesis-node error never discards the work already done by cycle
+/// nodes. Callers must not write their own copy of this doc.
 pub fn run_hive_mind(
     user_request: &str,
     plan: &CognitiveCyclePlan,
@@ -121,6 +130,10 @@ pub fn run_hive_mind(
         anyhow::bail!("cognitive cycle plan has no cycles");
     }
 
+    let settings = crate::model::settings::Settings::load();
+    let node_timeout_ms = Some(settings.hive_mind_node_timeout_ms);
+    let max_cycle_concurrency = settings.workflow_max_concurrency.max(1);
+
     let live = build_live(turn_events);
     let collective_state: Arc<Mutex<Vec<String>>> = Arc::new(Mutex::new(Vec::new()));
     let args: HashMap<String, String> = HashMap::new();
@@ -162,14 +175,14 @@ pub fn run_hive_mind(
         let results = execute_primitive(
             &cycle_primitive,
             &args,
-            directives.len().clamp(1, 10),
+            directives.len().clamp(1, max_cycle_concurrency),
             true,
             &abort_owned,
             live.as_ref(),
             session_dir,
             workspaces,
             &collective_state,
-            None,
+            node_timeout_ms,
         )?;
 
         // engine::execute_primitive's ScopedAgent arm already merged each
@@ -185,9 +198,29 @@ pub fn run_hive_mind(
         }
     }
 
-    let consensus = synthesize_consensus(
-        user_request, session_dir, workspaces, &collective_state, live.as_ref(), abort_flag,
-    )?;
+    let consensus_result = synthesize_consensus(
+        user_request, session_dir, workspaces, &collective_state, live.as_ref(), abort_flag, node_timeout_ms,
+    );
+
+    // Guaranteed documentation: write the convergence doc for whatever
+    // reports/consensus we actually have, whether synthesis succeeded or
+    // failed. A synthesis-node failure must not silently discard every
+    // completed cycle node's work — this is the durable audit trail
+    // CLAUDE.md promises for every convergence.
+    let doc_consensus = match &consensus_result {
+        Ok(c) => c.clone(),
+        Err(e) => format!(
+            "Synthesis failed: {e}. See individual node reports above for partial results.",
+        ),
+    };
+    if let Some(workspace_root) = workspaces.first() {
+        match crate::app::workflow::docs::write_hive_mind_convergence(workspace_root, user_request, &reports, &doc_consensus) {
+            Ok(path) => tracing::info!("[hive-mind] convergence documented at {}", path.display()),
+            Err(e) => tracing::warn!("[hive-mind] failed to write docs/runs report: {e}"),
+        }
+    }
+
+    let consensus = consensus_result?;
     Ok((consensus, reports))
 }
 
@@ -200,6 +233,9 @@ pub fn run_hive_mind(
 /// reasoning can reconcile that into a coherent answer; deterministic
 /// formatting can only concatenate, not resolve conflicts.
 ///
+/// `node_timeout_ms` is forwarded from `run_hive_mind`'s `Settings::load()`
+/// read so the synthesis node is bound by the same deadline as cycle nodes.
+///
 /// Return: the synthesis node's reconciled consensus text.
 fn synthesize_consensus(
     user_request: &str,
@@ -208,6 +244,7 @@ fn synthesize_consensus(
     collective_state: &Arc<Mutex<Vec<String>>>,
     live: Option<&LiveStateFn>,
     abort_flag: Option<&Arc<AtomicBool>>,
+    node_timeout_ms: Option<u64>,
 ) -> anyhow::Result<String> {
     let synthesis = ScriptPrimitive::ScopedAgent {
         prompt: format!(
@@ -227,7 +264,7 @@ fn synthesize_consensus(
     let args: HashMap<String, String> = HashMap::new();
     let abort_owned: Option<Arc<AtomicBool>> = abort_flag.cloned();
     let results = execute_primitive(
-        &synthesis, &args, 1, false, &abort_owned, live, session_dir, workspaces, collective_state, None,
+        &synthesis, &args, 1, false, &abort_owned, live, session_dir, workspaces, collective_state, node_timeout_ms,
     )?;
     Ok(results.into_iter().next().unwrap_or_default())
 }