fix(ci): bounce task back to developer on red CI (capped retries)

src/qg/checks.py

@@ -249,9 +249,17 @@ def check_reviewer_verdict(repo: str, work_item_id: str, branch: str | None = No
 
 def check_tests_local(repo: str, branch: str) -> tuple[bool, str]:
     """
+    DEPRECATED: replaced by check_ci_green on the development stage (CI is now
+    configured). Kept for backward-compat; not wired to any stage.
+
     S-1 fix: run the project test suite locally and judge by exit code, instead of
     depending on Gitea CI (which is not configured -> always false).
 
+    БАГ 5 fix: invoke pytest directly instead of make test. make is not installed
+    in the orchestrator container, so the previous ["make", "test"] call raised
+    FileNotFoundError. This reproduces the Makefile test target 1:1
+    (cd src/api && python -m pytest ../../tests/ -v).
+
     ORCH-2 / S-4: tests run inside the per-branch worktree (ensure_worktree), so this
     is safe for concurrent active tasks — no shared /repos checkout race.
     """
@@ -259,7 +267,8 @@ def check_tests_local(repo: str, branch: str) -> tuple[bool, str]:
     try:
         repo_path = ensure_worktree(repo, branch)
         r = subprocess.run(
-            ["make", "test"], cwd=repo_path,
+            ["python", "-m", "pytest", "../../tests/", "-v"],
+            cwd=os.path.join(repo_path, "src", "api"),
             capture_output=True, text=True, timeout=600,
         )
         if r.returncode == 0:

src/stages.py

@@ -13,7 +13,7 @@ STAGE_TRANSITIONS = {
     "created": {"next": "analysis", "agent": "analyst", "qg": None},
     "analysis": {"next": "architecture", "agent": "architect", "qg": "check_analysis_approved"},
     "architecture": {"next": "development", "agent": "developer", "qg": "check_architecture_done"},
-    "development": {"next": "review", "agent": "reviewer", "qg": "check_tests_local"},
+    "development": {"next": "review", "agent": "reviewer", "qg": "check_ci_green"},
     "review": {"next": "testing", "agent": "tester", "qg": "check_reviewer_verdict"},
     "testing": {"next": "deploy", "agent": "deployer", "qg": "check_tests_passed"},
     "deploy": {"next": "done", "agent": None, "qg": None},

src/webhooks/gitea.py

@@ -216,12 +216,31 @@ async def handle_ci_status(payload: dict):
         else:
             notify_qg_failure(task_id, current_stage, "check_ci_green", reason)
 
-    elif state == "failure":
-        # S-1: Gitea CI is NOT the authoritative gate anymore (the orchestrator runs
-        # tests locally via check_tests_local). Gitea CI is often unconfigured, so a
-        # "failure"/empty status here is not actionable. Log only, do not alert.
-        logger.debug(f"Task {task_id}: Gitea CI state='failure' on branch '{branch}' "
-                     f"(non-authoritative, suppressed — local tests are the gate)")
+    elif state == "failure" and current_stage == "development":
+        # 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_qg.py

@@ -17,7 +17,9 @@ from src.qg.checks import (
     check_ci_green,
     check_review_approved,
     check_tests_passed,
+    check_tests_local,
 )
+from src.stages import get_qg_for_stage
 
 
 @pytest.fixture(autouse=True)
@@ -186,3 +188,57 @@ class TestCheckTestsPassed:
         passed, reason = check_tests_passed("enduro-trails", "ET-001")
         assert passed is False
         assert "not found" in reason.lower()
+
+
+class TestDevelopmentStageQG:
+    """BUG 6: development stage QG is now check_ci_green (CI is the authoritative
+    gate), not the deprecated check_tests_local."""
+
+    def test_development_qg_is_check_ci_green(self):
+        assert get_qg_for_stage("development") == "check_ci_green"
+
+    def test_check_tests_local_is_deprecated_and_unwired(self):
+        # Kept in the registry for backward-compat, but not wired to any stage.
+        from src.qg.checks import QG_CHECKS
+        from src.stages import STAGE_TRANSITIONS
+        assert "check_tests_local" in QG_CHECKS
+        wired = {t.get("qg") for t in STAGE_TRANSITIONS.values()}
+        assert "check_tests_local" not in wired
+
+
+class TestCheckTestsLocal:
+    """BUG 5: check_tests_local must run pytest directly (not make, which is
+    not installed in the orchestrator container)."""
+
+    @patch("src.qg.checks.ensure_worktree")
+    @patch("subprocess.run")
+    def test_passes_on_returncode_zero(self, mock_run, mock_wt, tmp_path):
+        mock_wt.return_value = str(tmp_path)
+        mock_run.return_value = MagicMock(returncode=0, stdout="ok", stderr="")
+        passed, reason = check_tests_local("enduro-trails", "feature/ET-001-x")
+        assert passed is True
+        assert reason == "Local tests passed"
+
+    @patch("src.qg.checks.ensure_worktree")
+    @patch("subprocess.run")
+    def test_fails_on_nonzero_returncode(self, mock_run, mock_wt, tmp_path):
+        mock_wt.return_value = str(tmp_path)
+        mock_run.return_value = MagicMock(returncode=1, stdout="boom", stderr="trace")
+        passed, reason = check_tests_local("enduro-trails", "feature/ET-001-x")
+        assert passed is False
+        assert "Local tests failed" in reason
+
+    @patch("src.qg.checks.ensure_worktree")
+    @patch("subprocess.run")
+    def test_invokes_pytest_not_make(self, mock_run, mock_wt, tmp_path):
+        """The subprocess call must be pytest, from src/api, against ../../tests/."""
+        mock_wt.return_value = str(tmp_path)
+        mock_run.return_value = MagicMock(returncode=0, stdout="", stderr="")
+        check_tests_local("enduro-trails", "feature/ET-001-x")
+        args, kwargs = mock_run.call_args
+        cmd = args[0]
+        assert "make" not in cmd
+        assert cmd[:3] == ["python", "-m", "pytest"]
+        assert "../../tests/" in cmd
+        assert kwargs["cwd"] == os.path.join(str(tmp_path), "src", "api")
+

tests/test_stage_engine.py

@@ -203,10 +203,13 @@ class TestQgFailureDoesNotAdvance:
         assert _jobs() == []
 
     def test_webhook_path_emits_qg_failure_notification(self, monkeypatch):
-        """finished_agent=None -> generic QG-failure notification fires (plane parity)."""
+        """finished_agent=None -> generic QG-failure notification fires (plane parity).
+
+        development stage QG is now check_ci_green (was check_tests_local).
+        """
         monkeypatch.setattr(
             stage_engine, "QG_CHECKS",
-            {**stage_engine.QG_CHECKS, "check_tests_local": _fail("ci red")},
+            {**stage_engine.QG_CHECKS, "check_ci_green": _fail("ci red")},
         )
         task_id = _make_task("development")
         advance_stage(task_id, "development", "enduro-trails", "ET-001",

tests/test_webhooks.py

@@ -1,4 +1,5 @@
 import pytest
+import asyncio
 import os
 import tempfile
 from unittest.mock import patch, MagicMock, AsyncMock
@@ -272,6 +273,46 @@ def test_gitea_ci_success_advances_to_review(mock_launcher, mock_ci):
     assert task["stage"] == "review"
 
 
+@patch("src.webhooks.gitea.notify_qg_failure")
+@patch("src.webhooks.gitea.launcher")
+def test_gitea_ci_failure_on_development_notifies_qg_failure(mock_launcher, mock_notify):
+    """BUG 6: CI failure at development is now the authoritative QG gate failing.
+
+    It must notify QG failure (not silently suppress) and must NOT advance the stage.
+    """
+    conn = get_db()
+    conn.execute(
+        "INSERT INTO tasks (plane_id, work_item_id, repo, branch, stage) VALUES (?, ?, ?, ?, ?)",
+        ("ci-fail-001", "ET-011", "enduro-trails", "feature/ET-011-test", "development"),
+    )
+    conn.commit()
+    conn.close()
+
+    resp = client.post(
+        "/webhook/gitea",
+        json={
+            "state": "failure",
+            "branches": [{"name": "feature/ET-011-test"}],
+            "repository": {"name": "enduro-trails"},
+        },
+        headers={"X-Gitea-Event": "status"},
+    )
+    assert resp.status_code == 200
+
+    # QG failure was reported for the development stage with check_ci_green.
+    assert mock_notify.called
+    args, kwargs = mock_notify.call_args
+    call = list(args) + list(kwargs.values())
+    assert "development" in call
+    assert "check_ci_green" in call
+
+    # Stage did NOT advance.
+    conn = get_db()
+    task = conn.execute("SELECT * FROM tasks WHERE plane_id = 'ci-fail-001'").fetchone()
+    conn.close()
+    assert task["stage"] == "development"
+
+
 def test_gitea_webhook_pr():
     """PR event is accepted."""
     resp = client.post(
@@ -301,3 +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