Merge pull request 'fix(ci): bounce task back to developer on red CI (capped retries)' (#18) from fix/ci-fail-retry-developer into main

src/webhooks/gitea.py

@@ -217,9 +217,30 @@ async def handle_ci_status(payload: dict):
             notify_qg_failure(task_id, current_stage, "check_ci_green", reason)
 
     elif state == "failure" and current_stage == "development":
-        # CI is now the authoritative gate for development -> review.
-        # A failing CI means the QG did not pass; notify (do not silently advance).
+        # CI is the authoritative gate for development -> review.
+        # On red CI: notify, then bounce the task back to the developer (capped retries),
+        # symmetric to the review REQUEST_CHANGES path.
         notify_qg_failure(task_id, current_stage, "check_ci_green", f"Gitea CI failed on branch '{branch}'")
+        conn = get_db()
+        retry_count = conn.execute(
+            "SELECT COUNT(*) as cnt FROM agent_runs WHERE task_id = ? AND agent = 'developer'",
+            (task_id,),
+        ).fetchone()["cnt"]
+        conn.close()
+        if retry_count < MAX_DEV_RETRIES:
+            # task already on 'development' — no stage change needed, just relaunch developer
+            try:
+                task_desc = (
+                    f"Work item: {work_item_id}\nRepo: {repo_name}\nBranch: {branch}\n"
+                    f"Stage: development\nNote: CI failed, fix and re-push (attempt {retry_count + 1}/{MAX_DEV_RETRIES})"
+                )
+                job_id = enqueue_job("developer", repo_name, task_desc, task_id=task_id)
+                logger.info(f"Task {task_id}: CI failed, enqueued developer (attempt {retry_count + 1}, job_id={job_id})")
+            except Exception as e:
+                notify_error(task_id, f"Failed to relaunch developer after CI failure: {e}")
+        else:
+            notify_error(task_id, f"Max developer retries ({MAX_DEV_RETRIES}) reached after CI failure, escalating")
+            logger.error(f"Task {task_id}: max retries reached after CI failure, needs manual intervention")
 
 
 async def handle_pr(payload: dict):

tests/test_webhooks.py

@@ -1,4 +1,5 @@
 import pytest
+import asyncio
 import os
 import tempfile
 from unittest.mock import patch, MagicMock, AsyncMock
@@ -341,3 +342,94 @@ def test_plane_webhook_event_logged():
     conn.close()
     assert event is not None
     assert event["source"] == "plane"
+
+
+# ---------------------------------------------------------------------------
+# BUG 7: red CI on development must bounce the task back to the developer
+# (capped retries, symmetric to review REQUEST_CHANGES). These are pure-logic
+# tests: they invoke handle_ci_status() directly with mocked helpers so they do
+# not pass through the TestClient HMAC barrier (baseline 401s are off-limits).
+# ---------------------------------------------------------------------------
+
+def _ci_failure_payload():
+    return {
+        "state": "failure",
+        "branches": [{"name": "feature/ET-011-test"}],
+        "repository": {"name": "enduro-trails"},
+    }
+
+
+def _mock_db_with_retry_count(count):
+    """Build a get_db() mock whose retry_count query returns `count`."""
+    conn = MagicMock()
+    conn.execute.return_value.fetchone.return_value = {"cnt": count}
+    return conn
+
+
+@patch("src.webhooks.gitea.notify_error")
+@patch("src.webhooks.gitea.notify_qg_failure")
+@patch("src.webhooks.gitea.enqueue_job")
+@patch("src.webhooks.gitea.update_task_stage")
+@patch("src.webhooks.gitea.get_db")
+@patch("src.webhooks.gitea.get_task_by_repo_branch")
+@patch("src.webhooks.gitea.get_project_by_repo")
+def test_ci_failure_development_retries_developer_under_limit(
+    mock_proj, mock_task, mock_get_db, mock_update_stage,
+    mock_enqueue, mock_qg, mock_err,
+):
+    """retry_count < MAX_DEV_RETRIES → relaunch developer, stage untouched."""
+    from src.webhooks.gitea import handle_ci_status
+
+    mock_proj.return_value = {"repo": "enduro-trails"}
+    mock_task.return_value = {
+        "id": 1, "stage": "development", "work_item_id": "ET-011",
+    }
+    mock_get_db.return_value = _mock_db_with_retry_count(0)
+    mock_enqueue.return_value = 42
+
+    asyncio.run(handle_ci_status(_ci_failure_payload()))
+
+    # QG failure was still reported (Slava sees both the failure and the retry).
+    assert mock_qg.called
+    # developer was re-enqueued.
+    assert mock_enqueue.called
+    assert mock_enqueue.call_args[0][0] == "developer"
+    # No escalation.
+    assert not mock_err.called
+    # Stage stays on development — no update_task_stage in the CI-failure path.
+    assert not mock_update_stage.called
+
+
+@patch("src.webhooks.gitea.notify_error")
+@patch("src.webhooks.gitea.notify_qg_failure")
+@patch("src.webhooks.gitea.enqueue_job")
+@patch("src.webhooks.gitea.update_task_stage")
+@patch("src.webhooks.gitea.get_db")
+@patch("src.webhooks.gitea.get_task_by_repo_branch")
+@patch("src.webhooks.gitea.get_project_by_repo")
+def test_ci_failure_development_escalates_at_limit(
+    mock_proj, mock_task, mock_get_db, mock_update_stage,
+    mock_enqueue, mock_qg, mock_err,
+):
+    """retry_count >= MAX_DEV_RETRIES → escalate via notify_error, no relaunch."""
+    from src.webhooks.gitea import handle_ci_status, MAX_DEV_RETRIES
+
+    mock_proj.return_value = {"repo": "enduro-trails"}
+    mock_task.return_value = {
+        "id": 1, "stage": "development", "work_item_id": "ET-011",
+    }
+    mock_get_db.return_value = _mock_db_with_retry_count(MAX_DEV_RETRIES)
+
+    asyncio.run(handle_ci_status(_ci_failure_payload()))
+
+    # QG failure still reported.
+    assert mock_qg.called
+    # developer NOT re-enqueued at the cap.
+    assert not mock_enqueue.called
+    # Escalation message mentions CI failure.
+    assert mock_err.called
+    err_msg = " ".join(str(a) for a in mock_err.call_args[0])
+    assert "Max developer retries" in err_msg
+    assert "after CI failure" in err_msg
+    # Stage untouched.
+    assert not mock_update_stage.called