fix(qg): use check_ci_green instead of local tests on development stage

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/stage_engine.py

@@ -189,36 +189,48 @@ def advance_stage(
 
         # --- Quality gate ----------------------------------------------------
         if qg_name and qg_name in QG_CHECKS:
-            # Human-approval gate: special analyst approved-flow (launcher only).
+            # Human-approval gate: split by path.
             if qg_name == "check_analysis_approved":
-                _handle_analysis_approved_flow(
-                    task_id, current_stage, repo, work_item_id, branch, agent, result
-                )
-                return result
+                # Launcher path (analyst just finished): set In Review + ask for
+                # the Approved status. This gate never advances on its own -- a
+                # human Approved verdict does that.
+                if agent == "analyst":
+                    _handle_analysis_approved_flow(
+                        task_id, current_stage, repo, work_item_id, branch, agent, result
+                    )
+                    return result
+                # Webhook Approved-verdict path (agent is None): the human flipped
+                # the Plane status to Approved, which IS the approval. The gate is
+                # satisfied -- do NOT re-run check_analysis_approved (it looks for
+                # an :approved: *comment* and would block on a status-only
+                # approval). Mark it passed and fall through to the Advance block.
+                result.qg_name = qg_name
+                result.qg_passed = True
+                result.qg_reason = "approved-via-status"
+            else:
+                passed, reason = _run_qg(qg_name, repo, work_item_id, branch)
+                result.qg_passed = passed
+                result.qg_reason = reason
 
-            passed, reason = _run_qg(qg_name, repo, work_item_id, branch)
-            result.qg_passed = passed
-            result.qg_reason = reason
+                if not passed:
+                    logger.info(
+                        f"Task {task_id}: QG '{qg_name}' not passed after {agent}: {reason}"
+                    )
+                    # Behaviour parity:
+                    #  - webhook path (finished_agent is None): emit the generic
+                    #    QG-failure notification, exactly like the old plane handler.
+                    #  - launcher path (finished_agent set): NO generic notification;
+                    #    the rollback branches below own their own messaging, exactly
+                    #    like the old launcher handler.
+                    if agent is None:
+                        notify_qg_failure(task_id, current_stage, qg_name, reason)
+                        plane_notify_qg(work_item_id, current_stage, qg_name, reason)
 
-            if not passed:
-                logger.info(
-                    f"Task {task_id}: QG '{qg_name}' not passed after {agent}: {reason}"
-                )
-                # Behaviour parity:
-                #  - webhook path (finished_agent is None): emit the generic
-                #    QG-failure notification, exactly like the old plane handler.
-                #  - launcher path (finished_agent set): NO generic notification;
-                #    the rollback branches below own their own messaging, exactly
-                #    like the old launcher handler.
-                if agent is None:
-                    notify_qg_failure(task_id, current_stage, qg_name, reason)
-                    plane_notify_qg(work_item_id, current_stage, qg_name, reason)
-
-                _handle_qg_failure_rollbacks(
-                    task_id, current_stage, repo, work_item_id, branch,
-                    agent, qg_name, reason, result,
-                )
-                return result
+                    _handle_qg_failure_rollbacks(
+                        task_id, current_stage, repo, work_item_id, branch,
+                        agent, qg_name, reason, result,
+                    )
+                    return result
 
         elif qg_name:
             # QG name set but not registered — do not advance (launcher behavior).

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 +216,10 @@ 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 now the authoritative gate for development -> review.
+        # A failing CI means the QG did not pass; notify (do not silently advance).
+        notify_qg_failure(task_id, current_stage, "check_ci_green", f"Gitea CI failed on branch '{branch}'")
 
 
 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",
@@ -358,6 +361,63 @@ class TestAnalysisApprovedFlow:
         assert stage_engine.notify_approve_requested.called
         assert _jobs() == []
 
+    def test_approved_verdict_advances_analysis_to_architecture(self, monkeypatch):
+        """BUG 4: a human Approved STATUS (webhook path, finished_agent=None)
+        must satisfy the analysis gate and advance analysis -> architecture,
+        enqueuing the architect. The status-only approval must NOT re-run
+        check_analysis_approved (which looks for an :approved: COMMENT and would
+        otherwise wrongly block the advance).
+        """
+        # Make check_analysis_approved FAIL if it is ever called: the webhook
+        # path must bypass it entirely (status == approval). If the engine were
+        # to re-run the gate, this would block the advance and fail the test.
+        monkeypatch.setattr(
+            stage_engine, "QG_CHECKS",
+            {
+                **stage_engine.QG_CHECKS,
+                "check_analysis_approved": _fail("no :approved: comment"),
+            },
+        )
+        # Guard: the approval-flow (launcher-only) must NOT be invoked here.
+        flow = MagicMock()
+        monkeypatch.setattr(stage_engine, "_handle_analysis_approved_flow", flow)
+
+        task_id = _make_task("analysis")
+        res = advance_stage(
+            task_id, "analysis", "enduro-trails", "ET-001",
+            "feature/ET-001-x", finished_agent=None,
+        )
+
+        assert res.advanced is True
+        assert res.to_stage == "architecture"
+        assert _stage(task_id) == "architecture"
+        assert res.enqueued_agent == "architect"
+        # Sanity: agent for analysis is architect, never analyst (no re-run loop).
+        assert get_agent_for_stage("analysis") == "architect"
+        jobs = _jobs()
+        assert len(jobs) == 1
+        assert jobs[0]["agent"] == "architect"
+        # The launcher-only approval-flow was NOT called on the webhook path.
+        flow.assert_not_called()
+
+    def test_launcher_path_does_not_advance_and_calls_flow(self, monkeypatch):
+        """Regression: the launcher path (finished_agent='analyst') still routes
+        into _handle_analysis_approved_flow and does NOT advance.
+        """
+        flow = MagicMock()
+        monkeypatch.setattr(stage_engine, "_handle_analysis_approved_flow", flow)
+
+        task_id = _make_task("analysis")
+        res = advance_stage(
+            task_id, "analysis", "enduro-trails", "ET-001",
+            "feature/ET-001-x", finished_agent="analyst",
+        )
+
+        assert res.advanced is not True
+        assert _stage(task_id) == "analysis"
+        assert _jobs() == []
+        flow.assert_called_once()
+
 
 # ---------------------------------------------------------------------------
 # launcher + plane both delegate to the engine

tests/test_webhooks.py

@@ -272,6 +272,46 @@ 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(