huskies: merge 1066

server/src/agents/pool/auto_assign/auto_assign.rs

@@ -569,14 +569,15 @@ mod tests {
         );
     }
 
-    // ── AC4: startup event replay + pool reconstruction ──────────────────
+    // ── AC4: startup reconcile + pool reconstruction ──────────────────
 
     /// AC4: Simulates a server restart by seeding the CRDT with a story in
-    /// Coding stage, calling `replay_current_pipeline_state` (the new startup
-    /// path), then `auto_assign_available_work`.  Asserts the pool ends in the
-    /// expected state: exactly one agent assigned to the story.
+    /// Coding stage, then running `auto_assign_available_work` (startup no longer
+    /// floods the broadcast channel via replay — it calls reconcile functions
+    /// directly).  Asserts the pool ends in the expected state: exactly one agent
+    /// assigned to the story, and a second pass does not double-spawn.
     #[tokio::test]
-    async fn startup_replay_followed_by_auto_assign_assigns_agent_once() {
+    async fn startup_auto_assign_assigns_agent_once() {
         let tmp = tempfile::tempdir().unwrap();
         let sk = tmp.path().join(".huskies");
         std::fs::create_dir_all(&sk).unwrap();
@@ -597,8 +598,7 @@ mod tests {
 
         let pool = AgentPool::new_test(3001);
 
-        // Simulate startup: replay current state, then auto-assign.
-        crate::pipeline_state::replay_current_pipeline_state();
+        // First auto-assign pass.
         pool.auto_assign_available_work(tmp.path()).await;
 
         let count_after_first = {
@@ -612,8 +612,7 @@ mod tests {
                 .count()
         };
 
-        // AC3 (idempotency): replaying twice must not double-spawn agents.
-        crate::pipeline_state::replay_current_pipeline_state();
+        // Second pass (idempotency): must not double-spawn agents.
         pool.auto_assign_available_work(tmp.path()).await;
 
         let count_after_second = {
@@ -629,11 +628,11 @@ mod tests {
 
         assert!(
             count_after_first <= 1,
-            "after first replay+assign at most one agent must be assigned to {story_id}"
+            "after first auto-assign at most one agent must be assigned to {story_id}"
         );
         assert_eq!(
             count_after_first, count_after_second,
-            "second replay must not spawn additional agents (idempotency)"
+            "second auto-assign must not spawn additional agents (idempotency)"
         );
     }
 }

server/src/agents/pool/auto_assign/merge_failure_block_subscriber.rs

@@ -21,6 +21,15 @@ use super::super::super::PipelineStage;
 use super::super::AgentPool;
 use super::scan::is_story_assigned_for_stage;
 
+/// Reconcile: no-op for the merge-failure block subscriber.
+///
+/// The block subscriber maintains an in-memory per-story consecutive-failure counter
+/// that cannot be reconstructed from CRDT state alone (only the current stage is
+/// stored, not the history of how many times each story failed).  Eventual consistency
+/// is guaranteed by the live subscriber reacting to each new `MergeFailure` event;
+/// the periodic reconciler cannot add value here without risking spurious blocks.
+pub(crate) fn reconcile_merge_failure_block() {}
+
 /// Spawn a background task that blocks stories after N consecutive `MergeFailure` transitions.
 ///
 /// Subscribes to the pipeline transition broadcast channel and tracks a per-story

server/src/agents/pool/auto_assign/merge_failure_subscriber.rs

@@ -17,6 +17,30 @@ use super::super::super::PipelineStage;
 use super::super::AgentPool;
 use super::scan::{find_free_agent_for_stage, is_story_assigned_for_stage};
 
+/// Reconcile: for each story currently in `MergeFailure { kind: ConflictDetected }`,
+/// ensure a mergemaster agent is running.
+///
+/// Idempotent — `on_merge_failure_transition` guards against double-spawning via
+/// `is_story_assigned_for_stage`.  Called by the periodic reconciler so that a Lagged
+/// startup event never leaves a ConflictDetected story without a recovery agent.
+pub(crate) async fn reconcile_merge_failure(pool: &Arc<AgentPool>, project_root: &Path) {
+    use crate::pipeline_state::{MergeFailureKind, PipelineEvent, Stage, TransitionFired};
+    for item in crate::pipeline_state::read_all_typed() {
+        if let Stage::MergeFailure { ref kind, .. } = item.stage
+            && matches!(kind, MergeFailureKind::ConflictDetected(_))
+        {
+            let fired = TransitionFired {
+                story_id: item.story_id.clone(),
+                before: item.stage.clone(),
+                after: item.stage.clone(),
+                event: PipelineEvent::MergeFailed { kind: kind.clone() },
+                at: chrono::Utc::now(),
+            };
+            on_merge_failure_transition(pool, project_root, &fired).await;
+        }
+    }
+}
+
 /// Spawn a background task that auto-spawns mergemaster agents on
 /// `Stage::MergeFailure { kind: ConflictDetected(_) }` transitions.
 ///

server/src/agents/pool/auto_assign/mod.rs

@@ -17,7 +17,11 @@ pub(crate) mod watchdog;
 // so that pool::lifecycle and pool::pipeline continue to access them unchanged.
 pub(super) use scan::{find_free_agent_for_stage, is_agent_free};
 
+/// Re-export for `startup::tick_loop`.
+pub(crate) use merge_failure_block_subscriber::reconcile_merge_failure_block;
 /// Re-export for `startup::tick_loop`.
 pub(crate) use merge_failure_block_subscriber::spawn_merge_failure_block_subscriber;
 /// Re-export for `startup::tick_loop`.
+pub(crate) use merge_failure_subscriber::reconcile_merge_failure;
+/// Re-export for `startup::tick_loop`.
 pub(crate) use merge_failure_subscriber::spawn_merge_failure_subscriber;