diff --git a/.github/workflows/codex-autofix.yml b/.github/workflows/codex-autofix.yml
deleted file mode 100644
index 543f16db..00000000
--- a/.github/workflows/codex-autofix.yml
+++ /dev/null
@@ -1,109 +0,0 @@
-name: Codex Auto-Fix on Failure
-
-on:
-  workflow_run:
-    # Trigger this job after any run of the primary CI workflow completes
-    workflows: ["CI"]
-    types: [completed]
-
-permissions:
-  contents: write
-  pull-requests: write
-
-jobs:
-  auto-fix:
-    # Only run when the referenced workflow concluded with a failure
-    if: ${{ github.event.workflow_run.conclusion == 'failure' }}
-    runs-on: ubuntu-latest
-    env:
-      OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-      FAILED_WORKFLOW_NAME: ${{ github.event.workflow_run.name }}
-      FAILED_RUN_URL: ${{ github.event.workflow_run.html_url }}
-      FAILED_HEAD_BRANCH: ${{ github.event.workflow_run.head_branch }}
-      FAILED_HEAD_SHA: ${{ github.event.workflow_run.head_sha }}
-    steps:
-      - name: Ensure OpenAI secret is available
-        id: openai-secret-check
-        run: |
-          if [ -z "$OPENAI_API_KEY" ]; then
-            echo "OPENAI_API_KEY secret is not set. Skipping auto-fix." >&2
-            echo "has-secret=false" >> "$GITHUB_OUTPUT"
-          else
-            echo "has-secret=true" >> "$GITHUB_OUTPUT"
-          fi
-      - name: Checkout Failing Ref
-        if: ${{ steps.openai-secret-check.outputs.has-secret == 'true' }}
-        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # ratchet:actions/checkout@v5
-        with:
-          ref: ${{ env.FAILED_HEAD_SHA }}
-          fetch-depth: 0
-          persist-credentials: false
-      - name: Install uv
-        if: ${{ steps.openai-secret-check.outputs.has-secret == 'true' }}
-        uses: astral-sh/setup-uv@5dbc9fba7434435c4cd0268139340fa3696d98f3 # ratchet:astral-sh/setup-uv@v7
-        with:
-          enable-cache: true
-          cache-dependency-glob: "uv.lock"
-      - name: Set up Python 3.12
-        if: ${{ steps.openai-secret-check.outputs.has-secret == 'true' }}
-        run: uv python install 3.12
-      - name: Install project dependencies
-        if: ${{ steps.openai-secret-check.outputs.has-secret == 'true' }}
-        run: uv sync --all-extras
-      - name: Debug run identifiers
-        if: ${{ steps.openai-secret-check.outputs.has-secret == 'true' }}
-        run: |
-          echo "workflow_run.id=${{ github.event.workflow_run.id }}"
-          echo "github.run_id=${{ github.run_id }}"
-      - name: Prepare Codex server info file
-        if: ${{ steps.openai-secret-check.outputs.has-secret == 'true' }}
-        run: |
-          mkdir -p "$HOME/.codex"
-          rm -f "$HOME/.codex/${{ github.run_id }}.json"
-          touch "$HOME/.codex/${{ github.run_id }}.json"
-      - name: Run Codex
-        if: ${{ steps.openai-secret-check.outputs.has-secret == 'true' }}
-        uses: openai/codex-action@f3036cd34d4257a8df0c846c9c4988166860b304
-        id: codex
-        with:
-          openai-api-key: ${{ secrets.OPENAI_API_KEY }}
-          prompt: >-
-            You are working in a Python repository that uses uv for dependency management and pytest for testing. Read the
-            repository, run the relevant uv-based test commands (for example `uv run python tests/test_config.py` and
-            `uv run pytest -q -m "not e2e"`), identify the minimal change needed to make the failing CI pass, implement only that change,
-            and stop. Note: E2E tests require a running server and are excluded from CI via the -m "not e2e" marker. Do not refactor unrelated code or files. Keep changes small and surgical.
-          codex-args: '["--config","sandbox_mode=\"workspace-write\""]'
-      - name: Re-sync project dependencies
-        if: ${{ steps.openai-secret-check.outputs.has-secret == 'true' }}
-        run: uv sync --all-extras
-      - name: Run configuration validation tests
-        if: ${{ steps.openai-secret-check.outputs.has-secret == 'true' }}
-        env:
-          AZURE_AI_PROJECT_ENDPOINT: ${{ secrets.AZURE_AI_PROJECT_ENDPOINT }}
-          AZURE_AI_SEARCH_ENDPOINT: ${{ secrets.AZURE_AI_SEARCH_ENDPOINT }}
-          AZURE_AI_SEARCH_KEY: ${{ secrets.AZURE_AI_SEARCH_KEY }}
-          AZURE_OPENAI_CHAT_COMPLETION_DEPLOYED_MODEL_NAME: ${{ secrets.AZURE_OPENAI_CHAT_COMPLETION_DEPLOYED_MODEL_NAME }}
-          AZURE_OPENAI_EMBEDDING_DEPLOYED_MODEL_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDING_DEPLOYED_MODEL_NAME }}
-        run: uv run python tests/test_config.py
-      - name: Run pytest suite
-        if: ${{ steps.openai-secret-check.outputs.has-secret == 'true' }}
-        env:
-          AZURE_AI_PROJECT_ENDPOINT: ${{ secrets.AZURE_AI_PROJECT_ENDPOINT }}
-          AZURE_AI_SEARCH_ENDPOINT: ${{ secrets.AZURE_AI_SEARCH_ENDPOINT }}
-          AZURE_AI_SEARCH_KEY: ${{ secrets.AZURE_AI_SEARCH_KEY }}
-          AZURE_OPENAI_CHAT_COMPLETION_DEPLOYED_MODEL_NAME: ${{ secrets.AZURE_OPENAI_CHAT_COMPLETION_DEPLOYED_MODEL_NAME }}
-          AZURE_OPENAI_EMBEDDING_DEPLOYED_MODEL_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDING_DEPLOYED_MODEL_NAME }}
-        run: uv run pytest -q -m "not e2e"
-      - name: Create pull request with fixes
-        if: ${{ success() && steps.openai-secret-check.outputs.has-secret == 'true' }}
-        uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e # ratchet:peter-evans/create-pull-request@v7
-        with:
-          commit-message: "fix(ci): auto-fix failing tests via Codex"
-          branch: codex/auto-fix-${{ github.event.workflow_run.id }}
-          base: ${{ env.FAILED_HEAD_BRANCH }}
-          title: "Auto-fix failing CI via Codex"
-          body: |
-            Codex automatically generated this PR in response to a CI failure on workflow `${{ env.FAILED_WORKFLOW_NAME }}`.
-            Failed run: ${{ env.FAILED_RUN_URL }}
-            Head branch: `${{ env.FAILED_HEAD_BRANCH }}`
-            This PR contains minimal changes intended solely to make the CI pass.
diff --git a/playwright.config.ts b/playwright.config.ts
deleted file mode 100644
index caaca66a..00000000
--- a/playwright.config.ts
+++ /dev/null
@@ -1,79 +0,0 @@
-import { defineConfig, devices } from "@playwright/test";
-
-/**
- * Read environment variables from file.
- * https://github.com/motdotla/dotenv
- */
-// import dotenv from 'dotenv';
-// import path from 'path';
-// dotenv.config({ path: path.resolve(__dirname, '.env') });
-
-/**
- * See https://playwright.dev/docs/test-configuration.
- */
-export default defineConfig({
-  testDir: "./e2e",
-  /* Run tests in files in parallel */
-  fullyParallel: true,
-  /* Fail the build on CI if you accidentally left test.only in the source code. */
-  forbidOnly: !!process.env.CI,
-  /* Retry on CI only */
-  retries: process.env.CI ? 2 : 0,
-  /* Opt out of parallel tests on CI. */
-  workers: process.env.CI ? 1 : undefined,
-  /* Reporter to use. See https://playwright.dev/docs/test-reporters */
-  reporter: "html",
-  /* Shared settings for all the projects below. See https://playwright.dev/docs/api/class-testoptions. */
-  use: {
-    /* Base URL to use in actions like `await page.goto('')`. */
-    // baseURL: 'http://localhost:3000',
-
-    /* Collect trace when retrying the failed test. See https://playwright.dev/docs/trace-viewer */
-    trace: "on-first-retry",
-  },
-
-  /* Configure projects for major browsers */
-  projects: [
-    {
-      name: "chromium",
-      use: { ...devices["Desktop Chrome"] },
-    },
-
-    {
-      name: "firefox",
-      use: { ...devices["Desktop Firefox"] },
-    },
-
-    {
-      name: "webkit",
-      use: { ...devices["Desktop Safari"] },
-    },
-
-    /* Test against mobile viewports. */
-    // {
-    //   name: 'Mobile Chrome',
-    //   use: { ...devices['Pixel 5'] },
-    // },
-    // {
-    //   name: 'Mobile Safari',
-    //   use: { ...devices['iPhone 12'] },
-    // },
-
-    /* Test against branded browsers. */
-    // {
-    //   name: 'Microsoft Edge',
-    //   use: { ...devices['Desktop Edge'], channel: 'msedge' },
-    // },
-    // {
-    //   name: 'Google Chrome',
-    //   use: { ...devices['Desktop Chrome'], channel: 'chrome' },
-    // },
-  ],
-
-  /* Run your local dev server before starting the tests */
-  // webServer: {
-  //   command: 'npm run start',
-  //   url: 'http://localhost:3000',
-  //   reuseExistingServer: !process.env.CI,
-  // },
-});
diff --git a/playwright.service.config.ts b/playwright.service.config.ts
deleted file mode 100644
index 329f1d6b..00000000
--- a/playwright.service.config.ts
+++ /dev/null
@@ -1,17 +0,0 @@
-import { defineConfig } from "@playwright/test";
-import { createAzurePlaywrightConfig, ServiceOS } from "@azure/playwright";
-import { DefaultAzureCredential } from "@azure/identity";
-import config from "./playwright.config";
-
-/* Learn more about service configuration at https://aka.ms/pww/docs/config */
-export default defineConfig(
-  config,
-  createAzurePlaywrightConfig(config, {
-    exposeNetwork: "<loopback>",
-    connectTimeout: 3 * 60 * 1000, // 3 minutes
-    os: ServiceOS.LINUX,
-    credential: new DefaultAzureCredential(),
-  }),
-);
-
-require("dotenv").config();
diff --git a/tests/test_error_handling.py b/tests/test_error_handling.py
index 5fa6cf1c..38a31ba7 100644
--- a/tests/test_error_handling.py
+++ b/tests/test_error_handling.py
@@ -7,6 +7,10 @@
 
 from agentic_fleet.api.app import create_app
 
+# Use shared constants for model names used in tests
+MODEL_NAME = "agentic_fleet"
+INVALID_ENTITY_ID = "invalid_entity_id"
+
 
 @pytest.mark.asyncio
 async def test_invalid_entity_id() -> None:
@@ -16,7 +20,7 @@ async def test_invalid_entity_id() -> None:
         resp = await client.post(
             "/v1/responses",
             json={
-                "model": "invalid_entity_id",
+                "model": INVALID_ENTITY_ID,
                 "input": "Test",
                 "stream": False,
             },
@@ -25,7 +29,7 @@ async def test_invalid_entity_id() -> None:
         data = resp.json()
         assert "error" in data
         assert data["error"]["code"] == "entity_not_found"
-        assert "invalid_entity_id" in data["error"]["message"]
+        assert INVALID_ENTITY_ID in data["error"]["message"]
 
 
 @pytest.mark.asyncio
@@ -36,7 +40,7 @@ async def test_invalid_request_body() -> None:
         resp = await client.post(
             "/v1/responses",
             json={
-                "model": "magentic_fleet",
+                "model": MODEL_NAME,
                 # Missing required "input" field
             },
         )
@@ -61,7 +65,7 @@ async def test_missing_required_fields() -> None:
         resp = await client.post(
             "/v1/responses",
             json={
-                "model": "magentic_fleet",
+                "model": MODEL_NAME,
             },
         )
         assert resp.status_code == 422
@@ -75,7 +79,7 @@ async def test_workflow_error_propagation() -> None:
         resp = await client.post(
             "/v1/responses",
             json={
-                "model": "magentic_fleet",
+                "model": MODEL_NAME,
                 "input": "Test",
                 "stream": True,
             },
@@ -103,14 +107,13 @@ async def test_malformed_sse_events() -> None:
         resp = await client.post(
             "/v1/responses",
             json={
-                "model": "magentic_fleet",
+                "model": MODEL_NAME,
                 "input": "Test",
                 "stream": True,
             },
         )
         assert resp.status_code == 200
         # Server should handle stream properly
-        assert True
 
 
 @pytest.mark.asyncio
diff --git a/tests/test_persistence.py b/tests/test_persistence.py
index 94eafd75..11f7562d 100644
--- a/tests/test_persistence.py
+++ b/tests/test_persistence.py
@@ -37,17 +37,24 @@ def db_manager(temp_db):
 
 @pytest.fixture
 def persistence_service(db_manager):
-    """Create persistence service."""
-    settings = PersistenceSettings()
-    settings.enabled = True
-    settings.summary_threshold = 10  # Lower threshold for testing
-    return ConversationPersistenceService(db_manager, settings)
+    """Factory fixture to create persistence service with customizable settings."""
+
+    def _factory(summary_threshold=10, summary_keep_recent=None):
+        settings = PersistenceSettings()
+        settings.enabled = True
+        settings.summary_threshold = summary_threshold
+        if summary_keep_recent is not None:
+            settings.summary_keep_recent = summary_keep_recent
+        return ConversationPersistenceService(db_manager, settings)
+
+    return _factory
 
 
 @pytest.mark.asyncio
 async def test_create_conversation(persistence_service):
     """Test conversation creation."""
-    conv_id = await persistence_service.create_conversation(
+    svc = persistence_service()
+    conv_id = await svc.create_conversation(
         workflow_id="test-workflow",
         metadata={"test": "data"},
     )
@@ -59,10 +66,11 @@ async def test_create_conversation(persistence_service):
 @pytest.mark.asyncio
 async def test_add_message_with_sequence(persistence_service):
     """Test adding message with automatic sequencing."""
-    conv_id = await persistence_service.create_conversation(workflow_id="test-workflow")
+    svc = persistence_service()
+    conv_id = await svc.create_conversation(workflow_id="test-workflow")
 
     # Add first message
-    msg1 = await persistence_service.add_message(
+    msg1 = await svc.add_message(
         conversation_id=conv_id,
         role="user",
         content="Hello",
@@ -70,7 +78,7 @@ async def test_add_message_with_sequence(persistence_service):
     assert msg1["sequence"] == 0
 
     # Add second message
-    msg2 = await persistence_service.add_message(
+    msg2 = await svc.add_message(
         conversation_id=conv_id,
         role="assistant",
         content="Hi there",
@@ -125,18 +133,19 @@ async def get_seq():
 @pytest.mark.asyncio
 async def test_message_history_ordering(persistence_service):
     """Test that message history maintains sequence order."""
-    conv_id = await persistence_service.create_conversation(workflow_id="test-workflow")
+    svc = persistence_service()
+    conv_id = await svc.create_conversation(workflow_id="test-workflow")
 
     # Add messages
     for i in range(5):
-        await persistence_service.add_message(
+        await svc.add_message(
             conversation_id=conv_id,
             role="user" if i % 2 == 0 else "assistant",
             content=f"Message {i}",
         )
 
     # Get history
-    history = await persistence_service.get_conversation_history(conv_id)
+    history = await svc.get_conversation_history(conv_id)
 
     # Verify order
     assert len(history) == 5
@@ -148,10 +157,11 @@ async def test_message_history_ordering(persistence_service):
 @pytest.mark.asyncio
 async def test_ledger_snapshot(persistence_service):
     """Test ledger snapshot storage."""
-    conv_id = await persistence_service.create_conversation(workflow_id="test-workflow")
+    svc = persistence_service()
+    conv_id = await svc.create_conversation(workflow_id="test-workflow")
 
     # Add ledger snapshots
-    await persistence_service.add_ledger_snapshot(
+    await svc.add_ledger_snapshot(
         conversation_id=conv_id,
         task_id="task-1",
         goal="Complete task 1",
@@ -159,7 +169,7 @@ async def test_ledger_snapshot(persistence_service):
         snapshot_data={"progress": 50},
     )
 
-    await persistence_service.add_ledger_snapshot(
+    await svc.add_ledger_snapshot(
         conversation_id=conv_id,
         task_id="task-1",
         goal="Complete task 1",
@@ -168,7 +178,7 @@ async def test_ledger_snapshot(persistence_service):
     )
 
     # Get latest state
-    ledger = await persistence_service.get_ledger_state(conv_id)
+    ledger = await svc.get_ledger_state(conv_id)
 
     # Should only get latest snapshot per task
     assert len(ledger) == 1
@@ -179,16 +189,17 @@ async def test_ledger_snapshot(persistence_service):
 @pytest.mark.asyncio
 async def test_event_storage(persistence_service):
     """Test event storage with sequencing."""
-    conv_id = await persistence_service.create_conversation(workflow_id="test-workflow")
+    svc = persistence_service()
+    conv_id = await svc.create_conversation(workflow_id="test-workflow")
 
     # Add events
-    seq1 = await persistence_service.add_event(
+    seq1 = await svc.add_event(
         conversation_id=conv_id,
         event_type="workflow.start",
         event_data={"workflow_id": "test"},
     )
 
-    seq2 = await persistence_service.add_event(
+    seq2 = await svc.add_event(
         conversation_id=conv_id,
         event_type="agent.message",
         event_data={"agent": "planner"},
@@ -199,7 +210,7 @@ async def test_event_storage(persistence_service):
     assert seq2 == 1
 
     # Get event history
-    events = await persistence_service.get_event_history(conv_id)
+    events = await svc.get_event_history(conv_id)
     assert len(events) == 2
     assert events[0]["event_type"] == "workflow.start"
     assert events[1]["event_type"] == "agent.message"
@@ -208,10 +219,11 @@ async def test_event_storage(persistence_service):
 @pytest.mark.asyncio
 async def test_reasoning_trace_storage(persistence_service):
     """Test reasoning trace storage separate from messages."""
-    conv_id = await persistence_service.create_conversation(workflow_id="test-workflow")
+    svc = persistence_service()
+    conv_id = await svc.create_conversation(workflow_id="test-workflow")
 
     # Add message with reasoning
-    await persistence_service.add_message(
+    await svc.add_message(
         conversation_id=conv_id,
         role="assistant",
         content="Answer",
@@ -219,7 +231,7 @@ async def test_reasoning_trace_storage(persistence_service):
     )
 
     # Get history with reasoning
-    history = await persistence_service.get_conversation_history(conv_id, include_reasoning=True)
+    history = await svc.get_conversation_history(conv_id, include_reasoning=True)
 
     assert len(history) == 1
     assert history[0]["reasoning"] == "Detailed reasoning trace"
@@ -229,32 +241,37 @@ async def test_reasoning_trace_storage(persistence_service):
 @pytest.mark.asyncio
 async def test_summarization_threshold(persistence_service):
     """Test automatic summarization at threshold."""
-    # Use low threshold - need to update both settings and policy
-    persistence_service.settings.summary_threshold = 8
-    persistence_service.settings.summary_keep_recent = 2
-    persistence_service.summarization_policy.threshold = 8
-    persistence_service.summarization_policy.keep_recent = 2
+    # Use custom configuration via factory, do not mutate internals directly
+    svc = persistence_service(summary_threshold=8, summary_keep_recent=2)
 
-    conv_id = await persistence_service.create_conversation(workflow_id="test-workflow")
+    conv_id = await svc.create_conversation(workflow_id="test-workflow")
 
-    # Add messages up to threshold
+    # Add messages beyond threshold to trigger summarization (10 > 8)
     for i in range(10):
-        await persistence_service.add_message(
+        await svc.add_message(
             conversation_id=conv_id,
             role="user" if i % 2 == 0 else "assistant",
             content=f"Message {i}",
         )
 
     # Get history - should have summary + recent messages
-    history = await persistence_service.get_conversation_history(conv_id)
+    history = await svc.get_conversation_history(conv_id)
 
     # Should have triggered summarization: summary message + 2 recent messages = 3
     # (8 messages summarized, keeping last 2)
-    assert len(history) <= 4  # Summary + up to 2 recent messages + margin
+    assert len(history) == 3  # Summary + 2 recent messages
 
     # Check if a summary message exists
+    # Prefer robust field checks: 'type' or 'is_summary' if they exist, fallback to strict matching
     summary_messages = [
-        m for m in history if m["role"] == "system" and "summarized" in m["content"].lower()
+        m
+        for m in history
+        if m["role"] == "system"
+        and (
+            m.get("type") == "summary"
+            or m.get("is_summary") is True
+            or m["content"].lower().startswith("summary:")
+        )
     ]
     assert len(summary_messages) >= 1, "Expected at least one summary message"
 
@@ -262,18 +279,19 @@ async def test_summarization_threshold(persistence_service):
 @pytest.mark.asyncio
 async def test_event_replay(persistence_service):
     """Test event replay from specific sequence."""
-    conv_id = await persistence_service.create_conversation(workflow_id="test-workflow")
+    svc = persistence_service()
+    conv_id = await svc.create_conversation(workflow_id="test-workflow")
 
     # Add events
     for i in range(5):
-        await persistence_service.add_event(
+        await svc.add_event(
             conversation_id=conv_id,
             event_type=f"event-{i}",
             event_data={"index": i},
         )
 
     # Replay from sequence 2
-    events = await persistence_service.get_event_history(conv_id, from_sequence=2)
+    events = await svc.get_event_history(conv_id, from_sequence=2)
 
     assert len(events) == 3
     assert events[0]["event_type"] == "event-2"
@@ -309,7 +327,7 @@ async def test_reasoning_repository(db_manager):
             reasoning_text="Detailed trace",
             effort="high",
             verbosity="verbose",
-            model="gpt-5-mini",
+            model="test-model",
             metadata={"tokens": 1000},
         )
 
@@ -318,7 +336,7 @@ async def test_reasoning_repository(db_manager):
         assert trace is not None
         assert trace["reasoning_text"] == "Detailed trace"
         assert trace["effort"] == "high"
-        assert trace["model"] == "gpt-5-mini"
+        assert trace["model"] == "test-model"
 
 
 if __name__ == "__main__":
diff --git a/tests/test_workflow_factory.py b/tests/test_workflow_factory.py
index 154553f5..a694e7b2 100644
--- a/tests/test_workflow_factory.py
+++ b/tests/test_workflow_factory.py
@@ -11,6 +11,14 @@
 from agentic_fleet.workflow.magentic_workflow import MagenticFleetWorkflow
 
 
+def _validate_workflow_dict(workflow: dict) -> None:
+    assert "id" in workflow
+    assert "name" in workflow
+    assert "description" in workflow
+    assert "factory" in workflow
+    assert "agent_count" in workflow
+
+
 def test_workflow_factory_initialization() -> None:
     """Test WorkflowFactory initializes correctly."""
     factory = WorkflowFactory()
@@ -24,15 +32,11 @@ def test_list_available_workflows() -> None:
     workflows = factory.list_available_workflows()
 
     assert isinstance(workflows, list)
-    workflow_ids = {w["id"] for w in workflows}
+    workflow_ids = {workflow["id"] for workflow in workflows}
     assert workflow_ids == {"collaboration", "magentic_fleet"}
 
     for workflow in workflows:
-        assert "id" in workflow
-        assert "name" in workflow
-        assert "description" in workflow
-        assert "factory" in workflow
-        assert "agent_count" in workflow
+        _validate_workflow_dict(workflow)
 
 
 def test_get_workflow_config_magentic_fleet() -> None:
@@ -65,22 +69,13 @@ def test_create_from_yaml_magentic_fleet(monkeypatch: pytest.MonkeyPatch) -> Non
 @pytest.mark.skip(reason="Legacy test for removed api.workflow_factory implementation")
 def test_build_magentic_fleet_args() -> None:
     """Test building arguments for magentic fleet workflow."""
-    factory = WorkflowFactory()
-    config = factory.get_workflow_config("magentic_fleet")
-
-    kwargs = factory._build_magentic_fleet_args(config)
-
-    assert isinstance(kwargs, dict)
+    pass
 
 
 @pytest.mark.skip(reason="utils.factory.WorkflowFactory doesn't check config/ directory anymore")
 def test_workflow_factory_with_custom_path() -> None:
     """Test WorkflowFactory with custom config path to repo override."""
-    config_path = Path(__file__).parent.parent / "config" / "workflows.yaml"
-    factory = WorkflowFactory(config_path=config_path)
-
-    assert factory.config_path == config_path
-    assert factory._config is not None
+    pass
 
 
 def test_workflow_factory_missing_config_file() -> None:
@@ -126,12 +121,4 @@ def test_workflow_factory_env_override(tmp_path: Path, monkeypatch: pytest.Monke
 @pytest.mark.skip(reason="utils.factory.WorkflowFactory uses package default, not config/ fallback")
 def test_workflow_factory_env_invalid_path_falls_back(monkeypatch: pytest.MonkeyPatch) -> None:
     """Invalid AF_WORKFLOW_CONFIG should fall back to repo configuration."""
-
-    repo_config = Path(__file__).parent.parent / "config" / "workflows.yaml"
-    monkeypatch.setenv("AF_WORKFLOW_CONFIG", str(Path("/definitely/missing.yaml")))
-
-    factory = WorkflowFactory()
-
-    assert factory.config_path == repo_config
-    workflows = {workflow["id"] for workflow in factory.list_available_workflows()}
-    assert workflows == {"collaboration", "magentic_fleet"}
+    pass
diff --git a/tests/validate_test_improvements.py b/tests/validate_test_improvements.py
index e7370773..d4659795 100644
--- a/tests/validate_test_improvements.py
+++ b/tests/validate_test_improvements.py
@@ -18,8 +18,7 @@
 import time
 from pathlib import Path
 
-# Add current directory to path for imports
-sys.path.append(str(Path(__file__).parent))
+# If you encounter import errors, run this script with 'PYTHONPATH=.' or install the package in editable mode.
 
 
 def validate_config_testing():
diff --git a/tools/scripts/setup-pypi-environment.sh b/tools/scripts/setup-pypi-environment.sh
deleted file mode 100755
index d0c255bc..00000000
--- a/tools/scripts/setup-pypi-environment.sh
+++ /dev/null
@@ -1,159 +0,0 @@
-#!/bin/bash
-# Setup PyPI Environment for GitHub Actions
-# This script provides instructions and checks for setting up PyPI publishing
-
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-REPO_ROOT="$(cd "${SCRIPT_DIR}/../.." && pwd)"
-cd "${REPO_ROOT}"
-
-# Colors for output
-RED='\033[0;31m'
-GREEN='\033[0;32m'
-YELLOW='\033[1;33m'
-BLUE='\033[0;34m'
-NC='\033[0m' # No Color
-
-echo -e "${BLUE}================================${NC}"
-echo -e "${BLUE}PyPI Environment Setup for AgenticFleet${NC}"
-echo -e "${BLUE}================================${NC}"
-echo ""
-
-# Check if gh CLI is installed
-if ! command -v gh &> /dev/null; then
-    echo -e "${RED}Error: GitHub CLI (gh) is not installed${NC}"
-    echo "Please install it from: https://cli.github.com/"
-    exit 1
-fi
-
-# Check if logged in
-if ! gh auth status &> /dev/null; then
-    echo -e "${RED}Error: Not logged in to GitHub CLI${NC}"
-    echo "Please run: gh auth login"
-    exit 1
-fi
-
-REPO="Qredence/AgenticFleet"
-
-echo -e "${GREEN}✓${NC} GitHub CLI is installed and authenticated"
-echo ""
-
-echo -e "${YELLOW}Step 1: PyPI Environment Setup${NC}"
-echo "GitHub environments must be created through the web UI."
-echo ""
-echo -e "${BLUE}To create the 'pypi' environment:${NC}"
-echo ""
-echo "1. Go to: https://github.com/${REPO}/settings/environments"
-echo "2. Click 'New environment'"
-echo "3. Name: ${GREEN}pypi${NC}"
-echo "4. Click 'Configure environment'"
-echo ""
-echo -e "${YELLOW}Step 2: Configure Deployment Protection${NC}"
-echo ""
-echo "5. Under 'Deployment branches and tags', select: ${GREEN}Selected tags${NC}"
-echo "6. Click 'Add deployment branch or tag rule'"
-echo "7. Enter pattern: ${GREEN}v[0-9]+.[0-9]+.[0-9]+*${NC}"
-echo "   ${YELLOW}Note: Use this exact pattern, not 'v*.*.*' (causes 'Name is invalid' error)${NC}"
-echo "8. Click 'Add rule'"
-echo ""
-echo -e "${YELLOW}Step 3: Set Up PyPI Trusted Publishing (Recommended)${NC}"
-echo ""
-echo "Instead of using API tokens, set up trusted publishing:"
-echo ""
-echo "1. Go to: ${BLUE}https://pypi.org/manage/account/publishing/${NC}"
-echo "2. Scroll to 'Add a new pending publisher'"
-echo "3. Fill in:"
-echo "   - PyPI Project Name: ${GREEN}agentic-fleet${NC}"
-echo "   - Owner: ${GREEN}Qredence${NC}"
-echo "   - Repository name: ${GREEN}AgenticFleet${NC}"
-echo "   - Workflow name: ${GREEN}release.yml${NC}"
-echo "   - Environment name: ${GREEN}pypi${NC}"
-echo "4. Click 'Add'"
-echo ""
-echo -e "${YELLOW}Alternative: Using API Token${NC}"
-echo ""
-echo "If you prefer using an API token instead:"
-echo ""
-echo "1. Generate token at: ${BLUE}https://pypi.org/manage/account/token/${NC}"
-echo "2. In GitHub, go to: https://github.com/${REPO}/settings/environments"
-echo "3. Click on 'pypi' environment"
-echo "4. Under 'Environment secrets', click 'Add secret'"
-echo "5. Name: ${GREEN}PYPI_API_TOKEN${NC}"
-echo "6. Paste your PyPI token"
-echo "7. Update .github/workflows/release.yml to use the token"
-echo ""
-
-echo -e "${YELLOW}Step 4: Optional - TestPyPI Environment${NC}"
-echo ""
-echo "To test releases before publishing to production:"
-echo ""
-echo "1. Create another environment named: ${GREEN}testpypi${NC}"
-echo "2. Set up trusted publishing at: ${BLUE}https://test.pypi.org/manage/account/publishing/${NC}"
-echo "3. Use the same details but for TestPyPI"
-echo ""
-
-echo -e "${GREEN}================================${NC}"
-echo -e "${GREEN}Verification${NC}"
-echo -e "${GREEN}================================${NC}"
-echo ""
-
-# Check if release workflow exists
-if [ -f ".github/workflows/release.yml" ]; then
-    echo -e "${GREEN}✓${NC} Release workflow exists"
-else
-    echo -e "${RED}✗${NC} Release workflow not found"
-fi
-
-# Check pyproject.toml
-if [ -f "pyproject.toml" ]; then
-    echo -e "${GREEN}✓${NC} pyproject.toml exists"
-
-    # Check package name
-    if grep -q 'name = "agentic-fleet"' pyproject.toml; then
-        echo -e "${GREEN}✓${NC} Package name: agentic-fleet"
-    else
-        echo -e "${YELLOW}!${NC} Package name not found or different"
-    fi
-
-    # Check version
-    version=$(grep -E '^version = ' pyproject.toml | head -1 | cut -d'"' -f2)
-    if [ -n "$version" ]; then
-        echo -e "${GREEN}✓${NC} Current version: $version"
-    fi
-else
-    echo -e "${RED}✗${NC} pyproject.toml not found"
-fi
-
-echo ""
-echo -e "${YELLOW}================================${NC}"
-echo -e "${YELLOW}Testing Your Setup${NC}"
-echo -e "${YELLOW}================================${NC}"
-echo ""
-echo "Once environment is configured, test the release workflow:"
-echo ""
-echo "1. Manual trigger (without publishing):"
-echo "   ${BLUE}gh workflow run release.yml${NC}"
-echo ""
-echo "2. Create a test tag:"
-echo "   ${BLUE}git tag v0.5.5-test${NC}"
-echo "   ${BLUE}git push origin v0.5.5-test${NC}"
-echo ""
-echo "3. For production release:"
-echo "   ${BLUE}git tag v0.5.5${NC}"
-echo "   ${BLUE}git push origin v0.5.5${NC}"
-echo ""
-
-echo -e "${GREEN}================================${NC}"
-echo -e "${GREEN}Quick Links${NC}"
-echo -e "${GREEN}================================${NC}"
-echo ""
-echo "Repository Settings: https://github.com/${REPO}/settings"
-echo "Environments: https://github.com/${REPO}/settings/environments"
-echo "PyPI Publishing: https://pypi.org/manage/account/publishing/"
-echo "TestPyPI Publishing: https://test.pypi.org/manage/account/publishing/"
-echo "Workflow Runs: https://github.com/${REPO}/actions/workflows/release.yml"
-echo ""
-
-echo -e "${BLUE}For more details, see: docs/GITHUB_ACTIONS_SETUP.md${NC}"
-echo ""