feat(local-agent-v2): step 4 — journey produces structured AgentConfig JSON

Replace freeform prompt_template output with validated AgentConfig JSON:
- agent_setup.py: new system prompt (journey_system_v2), AGENT_CONFIG_START/END
  markers, _extract_agent_config() with Pydantic validation, updated handlers
  returning agent_config key; import AgentConfig from schemas
- tests/test_journey_v2.py: 6 unit tests + 5 parametrized LLM eval cases
  following test_agent_runner_v2.py pattern; _run_journey uses
  set_client_executor/clear_client_executor mirroring device_ws
- tests/fixtures/journey_v2/: cases.yaml + email_action.html + email_info.html
- tests/conftest.py: add --journey-dir CLI option; remove S3/plugin fixtures
  (cleanup from microservices migration, already present in working tree)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

tests/conftest.py

@@ -6,26 +6,21 @@ a per-test session, and a FastAPI ``TestClient`` wired to use it.
 
 from __future__ import annotations
 
-import json
-import os
 import time
 import uuid
 from collections.abc import AsyncGenerator, Generator
-from unittest.mock import patch
 
-import boto3
 import pytest
 import pytest_asyncio
 from fastapi.testclient import TestClient
 from jose import jwt
-from moto import mock_aws
 from sqlalchemy import StaticPool, event
 from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
 
 from app.config.settings import settings
 from app.db import Base, get_session
 from app.main import app
-from app.models import Plugin, Subscription, User
+from app.models import Subscription, User
 
 # ── Fixed test user IDs (one per tier) ───────────────────────────────
 
@@ -109,79 +104,6 @@ def client(db_session: AsyncSession) -> Generator[TestClient, None, None]:   # n
     app.dependency_overrides.pop(get_session, None)
 
 
-# ── Seed data helpers ────────────────────────────────────────────────
-
-_SEED_PLUGINS = [
-    Plugin(
-        id="plugin-github-sync",
-        name="GitHub Sync",
-        description="Sync tasks with GitHub Issues and pull requests.",
-        version="1.0.0",
-        author_name="Adiuva",
-        category="productivity",
-        price_cents=0,
-        permissions=json.dumps(["read:tasks", "write:tasks"]),
-        status="approved",
-        s3_package_key="plugins/plugin-github-sync/1.0.0/package.zip",
-        install_count=0,
-        avg_rating=0.0,
-    ),
-    Plugin(
-        id="plugin-slack-notify",
-        name="Slack Notifier",
-        description="Post task and timeline updates to Slack channels.",
-        version="1.2.0",
-        author_name="Adiuva",
-        category="communication",
-        price_cents=499,
-        permissions=json.dumps(["read:tasks", "read:timelines"]),
-        status="approved",
-        s3_package_key="plugins/plugin-slack-notify/1.2.0/package.zip",
-        install_count=0,
-        avg_rating=0.0,
-    ),
-    Plugin(
-        id="plugin-time-tracker",
-        name="Time Tracker",
-        description="Track time spent on tasks with automatic reporting.",
-        version="0.9.1",
-        author_name="Third Party",
-        category="productivity",
-        price_cents=999,
-        permissions=json.dumps(["read:tasks", "write:tasks"]),
-        status="approved",
-        s3_package_key="plugins/plugin-time-tracker/0.9.1/package.zip",
-        install_count=0,
-        avg_rating=0.0,
-    ),
-]
-
-
-@pytest_asyncio.fixture
-async def seed_plugins(db_session: AsyncSession) -> list[Plugin]:
-    """Insert the 3 default approved plugins and return them."""
-    plugins = []
-    for template in _SEED_PLUGINS:
-        p = Plugin(
-            id=template.id,
-            name=template.name,
-            description=template.description,
-            version=template.version,
-            author_name=template.author_name,
-            category=template.category,
-            price_cents=template.price_cents,
-            permissions=template.permissions,
-            status=template.status,
-            s3_package_key=template.s3_package_key,
-            install_count=template.install_count,
-            avg_rating=template.avg_rating,
-        )
-        db_session.add(p)
-        plugins.append(p)
-    await db_session.commit()
-    return plugins
-
-
 # ── JWT helpers ──────────────────────────────────────────────────────
 
 
@@ -212,29 +134,6 @@ def auth_header(tier: str = "power", user_id: str | None = None) -> dict[str, st
     return {"Authorization": f"Bearer {make_jwt(tier, user_id)}"}
 
 
-# ── S3 mock fixture ──────────────────────────────────────────────────
-
-S3_TEST_BUCKET = "test-bucket"
-S3_TEST_REGION = "us-east-1"
-
-
-@pytest.fixture
-def s3_bucket():
-    """Create a mocked S3 bucket via moto and patch BlobStore settings."""
-    with mock_aws():
-        os.environ.setdefault("AWS_ACCESS_KEY_ID", "testing")
-        os.environ.setdefault("AWS_SECRET_ACCESS_KEY", "testing")
-        os.environ.setdefault("AWS_DEFAULT_REGION", S3_TEST_REGION)
-        client = boto3.client("s3", region_name=S3_TEST_REGION)
-        client.create_bucket(Bucket=S3_TEST_BUCKET)
-        with patch("app.storage.blob_store.settings") as mock_settings:
-            mock_settings.S3_BUCKET = S3_TEST_BUCKET
-            mock_settings.S3_REGION = S3_TEST_REGION
-            mock_settings.AWS_ACCESS_KEY_ID = "testing"
-            mock_settings.AWS_SECRET_ACCESS_KEY = "testing"
-            yield S3_TEST_BUCKET
-
-
 # ── CLI options ───────────────────────────────────────────────────────
 
 def pytest_addoption(parser):
@@ -243,3 +142,13 @@ def pytest_addoption(parser):
         default=None,
         help="Override fixture folder for preprocessor tests (must contain cases.yaml + data/)",
     )
+    parser.addoption(
+        "--runner-dir",
+        default=None,
+        help="Override fixture folder for agent_runner_v2 eval tests (must contain cases.yaml + data/)",
+    )
+    parser.addoption(
+        "--journey-dir",
+        default=None,
+        help="Override fixture folder for journey_v2 eval tests (must contain cases.yaml + data/)",
+    )