feat(ai): add PixelRAG VLM generate preflight

tests/test_pixelrag_vlm_replay_worker_service.py

@@ -257,6 +257,83 @@ def test_pixelrag_vlm_replay_worker_auto_selects_installed_candidate(tmp_path, m
     assert payload["summary"]["executed_ok_count"] == 1
 
 
+def test_pixelrag_vlm_replay_worker_generate_probe_blocks_tile_generate(tmp_path, monkeypatch):
+    from services import pixelrag_vlm_replay_worker_service as service
+
+    _write_receipt(
+        tmp_path,
+        platform="shopee_tw",
+        manifest_id="shopee-ok",
+        title="Shopee 防曬乳",
+        url="https://shopee.tw/search?keyword=sunscreen",
+    )
+
+    monkeypatch.setattr(
+        service,
+        "build_pixelrag_vlm_route_readiness",
+        lambda **kwargs: {
+            "policy": "read_only_pixelrag_vlm_route_readiness_v1",
+            "status": "critical",
+            "summary": {
+                "configured_model": "minicpm-v:latest",
+                "candidate_model": "gemma3:4b",
+                "candidate_host": "http://34.21.145.224:11434",
+                "tag_model_route_ready": True,
+                "model_route_ready": False,
+                "generate_probe_performed": True,
+                "generate_probe_ok_count": 0,
+                "generate_route_ready": False,
+                "generate_ready_model": "",
+                "generate_ready_host": "",
+                "generate_ready_provider": "",
+                "model_call_performed": True,
+            },
+            "controlled_apply": {"model_call": True},
+            "next_machine_action": "repair_ollama_vlm_generate_runtime_or_proxy_timeout",
+        },
+    )
+
+    class FakeOllama:
+        def __init__(self, model):
+            self.model = model
+
+        def generate(self, *args, **kwargs):
+            raise AssertionError("tile VLM generate should not be called")
+
+    monkeypatch.setattr(service, "OllamaService", FakeOllama)
+    payload = service.run_pixelrag_ollama_vlm_replay_worker(
+        artifact_root=tmp_path,
+        output_root=tmp_path / "receipts",
+        platform="shopee_tw",
+        model="minicpm-v:latest",
+        execute=True,
+        write_receipt=True,
+        tile_limit=1,
+        auto_select_model=True,
+        probe_generate_before_execute=True,
+    )
+
+    assert payload["status"] == "critical"
+    assert payload["model"] == "gemma3:4b"
+    assert payload["summary"]["model_route_not_ready_count"] == 1
+    assert payload["summary"]["route_model_call_performed"] is True
+    assert payload["summary"]["tile_model_call_performed"] is False
+    assert payload["summary"]["model_call_performed"] is True
+    assert payload["controlled_apply"]["model_call"] is True
+    assert payload["next_machine_action"] == "repair_ollama_vlm_generate_runtime_or_proxy_timeout"
+    item = payload["worker_items"][0]
+    assert item["worker_status"] == "model_route_not_ready"
+    assert item["generate_probe_performed"] is True
+    assert item["generate_route_ready"] is False
+    assert item["model_call_performed"] is False
+    receipt_path = tmp_path / "receipts" / "shopee_tw" / "shopee-ok" / "vlm_replay_receipt.json"
+    assert receipt_path.exists()
+    receipt = json.loads(receipt_path.read_text(encoding="utf-8"))
+    assert receipt["worker_status"] == "model_route_not_ready"
+    assert receipt["artifact_write_performed"] is True
+    assert receipt["generate_route_ready"] is False
+
+
 def test_pixelrag_vlm_replay_worker_cli_outputs_machine_readable_json(tmp_path):
     _write_receipt(
         tmp_path,

tests/test_pixelrag_vlm_route_readiness_service.py

@@ -67,6 +67,70 @@ def test_pixelrag_vlm_route_readiness_critical_when_no_candidate(monkeypatch):
     assert payload["next_machine_action"] == "install_or_configure_pixelrag_vlm_model_on_approved_ollama_host"
 
 
+def test_pixelrag_vlm_route_readiness_generate_probe_success(monkeypatch):
+    from services import pixelrag_vlm_route_readiness_service as service
+
+    monkeypatch.setattr(service, "_approved_hosts", lambda: ["http://secondary:11434"])
+    monkeypatch.setattr(
+        service.requests,
+        "get",
+        lambda url, timeout: FakeResponse(payload={"models": [{"name": "gemma3:4b"}]}),
+    )
+    monkeypatch.setattr(
+        service.requests,
+        "post",
+        lambda url, json, timeout: FakeResponse(payload={"response": "OK", "done": True}),
+    )
+
+    payload = service.build_pixelrag_vlm_route_readiness(
+        model="minicpm-v:latest",
+        probe_generate=True,
+        probe_timeout_seconds=1,
+    )
+
+    assert payload["status"] == "warning"
+    assert payload["summary"]["candidate_model"] == "gemma3:4b"
+    assert payload["summary"]["tag_model_route_ready"] is True
+    assert payload["summary"]["model_route_ready"] is True
+    assert payload["summary"]["generate_probe_performed"] is True
+    assert payload["summary"]["generate_probe_ok_count"] == 1
+    assert payload["summary"]["generate_route_ready"] is True
+    assert payload["summary"]["generate_ready_host"] == "http://secondary:11434"
+    assert payload["controlled_apply"]["model_call"] is True
+
+
+def test_pixelrag_vlm_route_readiness_generate_probe_failure_blocks_route(monkeypatch):
+    from services import pixelrag_vlm_route_readiness_service as service
+
+    monkeypatch.setattr(service, "_approved_hosts", lambda: ["http://secondary:11434"])
+    monkeypatch.setattr(
+        service.requests,
+        "get",
+        lambda url, timeout: FakeResponse(payload={"models": [{"name": "gemma3:4b"}]}),
+    )
+
+    def fake_post(url, json, timeout):
+        raise TimeoutError("generate timeout")
+
+    monkeypatch.setattr(service.requests, "post", fake_post)
+
+    payload = service.build_pixelrag_vlm_route_readiness(
+        model="minicpm-v:latest",
+        probe_generate=True,
+        probe_timeout_seconds=1,
+    )
+
+    assert payload["status"] == "critical"
+    assert payload["success"] is False
+    assert payload["summary"]["candidate_model"] == "gemma3:4b"
+    assert payload["summary"]["tag_model_route_ready"] is True
+    assert payload["summary"]["model_route_ready"] is False
+    assert payload["summary"]["generate_probe_performed"] is True
+    assert payload["summary"]["generate_probe_ok_count"] == 0
+    assert payload["summary"]["generate_route_ready"] is False
+    assert payload["next_machine_action"] == "repair_ollama_vlm_generate_runtime_or_proxy_timeout"
+
+
 def test_pixelrag_vlm_route_readiness_route_returns_readback(monkeypatch):
     from flask import Flask
     from routes import system_public_routes as routes
@@ -87,6 +151,7 @@ def test_pixelrag_vlm_route_readiness_route_returns_readback(monkeypatch):
     app = Flask(__name__)
     with app.test_request_context(
         "/api/ai-automation/pixelrag-vlm-route-readiness?model=minicpm-v:latest"
+        "&probe_generate=true&probe_timeout=4"
     ):
         response = routes.ai_automation_pixelrag_vlm_route_readiness_api.__wrapped__()
     payload = response.get_json()