diff --git a/.github/ISSUE_TEMPLATE/bug_report.md b/.github/ISSUE_TEMPLATE/bug_report.md
deleted file mode 100644
index 00fa04a..0000000
--- a/.github/ISSUE_TEMPLATE/bug_report.md
+++ /dev/null
@@ -1,49 +0,0 @@
----
-name: Bug Report
-about: Create a report to help us improve
-title: "[BUG] "
-labels: bug
-assignees: ''
----
-
-## Describe the Bug
-A clear and concise description of what the bug is.
-
-## To Reproduce
-Steps to reproduce the behavior:
-1. Go to '...'
-2. Click on '....'
-3. Scroll down to '....'
-4. See error
-
-## Expected Behavior
-A clear and concise description of what you expected to happen.
-
-## Actual Behavior
-A clear and concise description of what actually happened.
-
-## Environment
-- OS: [e.g. macOS 13.0, Ubuntu 22.04]
-- Go version: [e.g. 1.21.0]
-- Fetch ML version: [e.g. v1.0.0]
-- Configuration: [e.g. file-based auth, database auth]
-
-## Configuration
-```yaml
-# Paste relevant configuration here
-auth:
-  enabled: true
-  # ...
-```
-
-## Logs
-```
-# Paste relevant logs here
-2024-01-01 12:00:00 ERROR: ...
-```
-
-## Additional Context
-Add any other context about the problem here.
-
-## Possible Solution
-If you have ideas on how to fix this, please describe them here.
diff --git a/.github/ISSUE_TEMPLATE/feature_request.md b/.github/ISSUE_TEMPLATE/feature_request.md
deleted file mode 100644
index e17975b..0000000
--- a/.github/ISSUE_TEMPLATE/feature_request.md
+++ /dev/null
@@ -1,34 +0,0 @@
----
-name: Feature Request
-about: Suggest an idea for this project
-title: "[FEATURE] "
-labels: enhancement
-assignees: ''
----
-
-## Feature Description
-A clear and concise description of what the feature is.
-
-## Problem Statement
-What problem does this feature solve? What pain point does it address?
-
-## Proposed Solution
-Describe the solution you'd like to see implemented.
-
-## Alternative Solutions
-Describe any alternative solutions or features you've considered.
-
-## Use Cases
-Describe specific use cases where this feature would be valuable.
-
-## Implementation Details
-If you have technical ideas on how this should be implemented, describe them here.
-
-## Mockups/UI (if applicable)
-If this involves UI changes, include mockups or screenshots.
-
-## Additional Context
-Add any other context, screenshots, or examples about the feature request here.
-
-## Questions
-Do you have any questions about how this feature might work?
diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
deleted file mode 100644
index 6bb2ed9..0000000
--- a/.github/PULL_REQUEST_TEMPLATE.md
+++ /dev/null
@@ -1,35 +0,0 @@
-## Description
-Brief description of what this PR changes.
-
-## Type of Change
-- [ ] Bug fix (non-breaking change that fixes an issue)
-- [ ] New feature (non-breaking change that adds functionality)
-- [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
-- [ ] Documentation update
-
-## Testing
-- [ ] Unit tests pass
-- [ ] Integration tests pass (if applicable)
-- [ ] Manual testing completed
-- [ ] Security audit passed
-
-## Checklist
-- [ ] Code follows the project's style guidelines
-- [ ] Self-review of the code completed
-- [ ] Documentation updated if necessary
-- [ ] Tests added for new functionality
-- [ ] No hardcoded secrets or credentials
-- [ ] Error handling implemented appropriately
-
-## Security Considerations
-- [ ] No sensitive data in logs
-- [ ] Proper input validation
-- [ ] Authentication/authorization properly implemented
-- [ ] No SQL injection vulnerabilities
-- [ ] No XSS vulnerabilities (if applicable)
-
-## Screenshots (if applicable)
-Add screenshots to help explain your changes.
-
-## Additional Context
-Add any other context about the pull request here.
diff --git a/.github/labeler.yml b/.github/labeler.yml
deleted file mode 100644
index 0a3e465..0000000
--- a/.github/labeler.yml
+++ /dev/null
@@ -1,82 +0,0 @@
-# Labeler configuration for automatic PR labeling
-
-# Bug reports
-bug:
-  - "[BUG]"
-  - "bug:"
-  - "fixes #"
-  - "closes #"
-
-# Feature requests
-enhancement:
-  - "[FEATURE]"
-  - "feat:"
-  - "feature:"
-  - "add "
-
-# Documentation
-documentation:
-  - "[DOCS]"
-  - "docs:"
-  - "README"
-  - "documentation"
-
-# Security
-security:
-  - "[SECURITY]"
-  - "security:"
-  - "auth"
-  - "authentication"
-  - "RBAC"
-  - "permissions"
-
-# Testing
-testing:
-  - "[TEST]"
-  - "test:"
-  - "tests"
-  - "unit test"
-  - "integration test"
-
-# CI/CD
-ci:
-  - "[CI]"
-  - "workflow"
-  - "github actions"
-  - "build"
-  - "deploy"
-
-# Configuration
-configuration:
-  - "[CONFIG]"
-  - "config"
-  - "yaml"
-  - "settings"
-
-# Dependencies
-dependencies:
-  - "[DEPS]"
-  - "go.mod"
-  - "dependency"
-  - "update"
-
-# Performance
-performance:
-  - "[PERF]"
-  - "performance"
-  - "optimize"
-  - "speed"
-
-# Breaking changes
-breaking-change:
-  - "[BREAKING]"
-  - "breaking"
-  - "deprecated"
-  - "remove"
-
-# TUI
-tui:
-  - "[TUI]"
-  - "cmd/tui"
-  - "terminal ui"
-  - "interface"
diff --git a/.github/rsync_manifest.json b/.github/rsync_manifest.json
deleted file mode 100644
index c79fdc8..0000000
--- a/.github/rsync_manifest.json
+++ /dev/null
@@ -1,21 +0,0 @@
-{
-  "version": "v3.2.7",
-  "base_url": "https://github.com/JMarvi3/rsync-static/releases/download",
-  "platforms": {
-    "linux-x86_64": {
-      "target": "x86_64-linux-musl",
-      "asset": "rsync-linux-x86_64",
-      "sha256": "0019dfc4b32d63c1392aa264aed2253c1e0c2fb09216f8e2cc269bbfb8bb49b5"
-    },
-    "macos-x86_64": {
-      "target": "x86_64-macos",
-      "asset": "rsync-macos-x86_64",
-      "sha256": "0019dfc4b32d63c1392aa264aed2253c1e0c2fb09216f8e2cc269bbfb8bb49b5"
-    },
-    "macos-arm64": {
-      "target": "aarch64-macos",
-      "asset": "rsync-macos-arm64",
-      "sha256": "0019dfc4b32d63c1392aa264aed2253c1e0c2fb09216f8e2cc269bbfb8bb49b5"
-    }
-  }
-}
diff --git a/.github/workflows/benchmark-metrics.yml b/.github/workflows/benchmark-metrics.yml
deleted file mode 100644
index bf5b1e3..0000000
--- a/.github/workflows/benchmark-metrics.yml
+++ /dev/null
@@ -1,87 +0,0 @@
-name: Benchmark Metrics
-
-on:
-  workflow_dispatch:
-
-jobs:
-  benchmark:
-    runs-on: ubuntu-latest
-    
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@v4
-    
-    - name: Setup Go
-      uses: actions/setup-go@v4
-      with:
-        go-version: '1.21'
-    
-    - name: Cache Go modules
-      uses: actions/cache@v3
-      with:
-        path: ~/go/pkg/mod
-        key: ${{ runner.os }}-go-${{ hashFiles('**/go.sum') }}
-    
-    - name: Run benchmarks
-      run: |
-        echo "Running performance benchmarks..."
-        go test -bench=. -benchmem ./tests/benchmarks/... > benchmark_results.txt 2>&1
-        
-        # Extract benchmark results
-        grep "Benchmark.*-[0-9].*" benchmark_results.txt > clean_benchmarks.txt || true
-    
-    - name: Convert to Prometheus metrics
-      run: |
-        # Create Prometheus metrics file
-        echo "# HELP benchmark_time_per_op Time per operation in nanoseconds" > prometheus_metrics.txt
-        echo "# TYPE benchmark_time_per_op gauge" >> prometheus_metrics.txt
-        echo "# HELP benchmark_memory_per_op Memory per operation in bytes" >> prometheus_metrics.txt
-        echo "# TYPE benchmark_memory_per_op gauge" >> prometheus_metrics.txt
-        echo "# HELP benchmark_allocs_per_op Allocations per operation" >> prometheus_metrics.txt
-        echo "# TYPE benchmark_allocs_per_op gauge" >> prometheus_metrics.txt
-        
-        # Parse benchmark results and convert to Prometheus format
-        while IFS= read -r line; do
-          if [[ -n "$line" ]]; then
-            BENCHMARK_NAME=$(echo "$line" | awk '{print $1}' | sed 's/-[0-9]*$//')
-            ITERATIONS=$(echo "$line" | awk '{print $2}')
-            TIME_PER_OP=$(echo "$line" | awk '{print $3}')
-            MEMORY_PER_OP=$(echo "$line" | awk '{print $4}')
-            ALLOCS_PER_OP=$(echo "$line" | awk '{print $5}')
-            
-            # Clean benchmark name for Prometheus
-            CLEAN_NAME=$(echo "$BENCHMARK_NAME" | sed 's/[^a-zA-Z0-9_]/_/g')
-            
-            echo "benchmark_time_per_op{benchmark=\"$CLEAN_NAME\"} ${TIME_PER_OP/ns/}" >> prometheus_metrics.txt
-            echo "benchmark_memory_per_op{benchmark=\"$CLEAN_NAME\"} ${MEMORY_PER_OP/B\/op/}" >> prometheus_metrics.txt
-            echo "benchmark_allocs_per_op{benchmark=\"$CLEAN_NAME\"} ${ALLOCS_PER_OP/allocs\/op/}" >> prometheus_metrics.txt
-          fi
-        done < clean_benchmarks.txt
-    
-    - name: Push to Prometheus Pushgateway
-      env:
-        PROMETHEUS_PUSHGATEWAY_URL: ${{ secrets['PROMETHEUS_PUSHGATEWAY_URL'] }}
-      run: |
-        # Push metrics to Prometheus Pushgateway (if configured)
-        if [ -n "$PROMETHEUS_PUSHGATEWAY_URL" ]; then
-          echo "Pushing metrics to Prometheus..."
-          curl --data-binary @prometheus_metrics.txt \
-            "$PROMETHEUS_PUSHGATEWAY_URL/metrics/job/benchmark/instance/${{ github.run_id }}"
-        else
-          echo "PROMETHEUS_PUSHGATEWAY_URL not configured, skipping push"
-        fi
-    
-    - name: Upload benchmark results
-      uses: actions/upload-artifact@v3
-      with:
-        name: benchmark-results-${{ github.run_id }}
-        path: |
-          benchmark_results.txt
-          clean_benchmarks.txt
-          prometheus_metrics.txt
-        retention-days: 30
-    
-    - name: Display results summary
-      run: |
-        echo "=== Benchmark Results Summary ==="
-        cat prometheus_metrics.txt | grep "benchmark_time_per_op" | head -10
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
deleted file mode 100644
index 3b85d89..0000000
--- a/.github/workflows/ci.yml
+++ /dev/null
@@ -1,276 +0,0 @@
-name: CI/CD Pipeline
-
-on:
-  workflow_dispatch:
-
-# Concurrency control to prevent multiple runs of the same workflow
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-# Workflow permissions
-permissions:
-  contents: read
-  security-events: write
-  actions: read
-  packages: write
-
-env:
-  GO_VERSION: '1.25.0'
-  ZIG_VERSION: '0.15.2'
-
-jobs:
-  test:
-    name: Test
-    runs-on: ubuntu-latest
-    timeout-minutes: 30
-    
-    services:
-      redis:
-        image: redis:7
-        ports:
-          - 6379:6379
-        options: >-
-          --health-cmd "redis-cli ping"
-          --health-interval 10s
-          --health-timeout 5s
-          --health-retries 5
-
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@v5
-
-    - name: Set up Go
-      uses: actions/setup-go@v5
-      with:
-        go-version: ${{ env.GO_VERSION }}
-
-    - name: Cache Go modules
-      uses: actions/cache@v4
-      with:
-        path: |
-          ~/.cache/go-build
-          ~/go/pkg/mod
-        key: ${{ runner.os }}-go-${{ hashFiles('**/go.sum', '**/go.mod') }}
-        restore-keys: |
-          ${{ runner.os }}-go-
-
-    - name: Set up Zig
-      uses: goto-bus-stop/setup-zig@v2
-      with:
-        version: ${{ env.ZIG_VERSION }}
-
-    - name: Cache Zig build
-      uses: actions/cache@v4
-      with:
-        path: |
-          ~/.cache/zig
-          cli/zig-cache
-          cli/zig-out
-        key: ${{ runner.os }}-zig-${{ hashFiles('cli/**') }}
-        restore-keys: |
-          ${{ runner.os }}-zig-
-
-    - name: Install dependencies
-      run: |
-        go mod download
-        sudo apt-get update
-        sudo apt-get install -y podman redis-tools
-
-    - name: Verify dependencies
-      run: go mod verify
-
-    - name: Run tests
-      run: make test
-
-    - name: Test internal/queue package
-      run: go test -v -race -coverprofile=queue-coverage.out ./internal/queue/...
-
-    - name: Run comprehensive tests
-      run: make test-all
-
-    - name: Run linters
-      run: make lint
-
-    - name: Generate coverage report
-      run: make coverage
-
-    - name: Upload coverage to Codecov
-      uses: codecov/codecov-action@v4
-      with:
-        file: ./coverage.out
-        flags: unittests
-        name: codecov-umbrella
-
-  dev-smoke:
-    name: Dev Compose Smoke Test
-    runs-on: ubuntu-latest
-    needs: test
-    timeout-minutes: 20
-
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@v5
-
-    - name: Run dev smoke test
-      run: make dev-smoke
-
-  build:
-    name: Build
-    runs-on: ubuntu-latest
-    needs: test
-    timeout-minutes: 15
-    
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@v5
-
-    - name: Set up Go
-      uses: actions/setup-go@v5
-      with:
-        go-version: ${{ env.GO_VERSION }}
-
-    - name: Set up Zig
-      uses: goto-bus-stop/setup-zig@v2
-      with:
-        version: ${{ env.ZIG_VERSION }}
-
-    - name: Cache Go modules
-      uses: actions/cache@v4
-      with:
-        path: |
-          ~/.cache/go-build
-          ~/go/pkg/mod
-        key: ${{ runner.os }}-go-${{ hashFiles('**/go.sum', '**/go.mod') }}
-        restore-keys: |
-          ${{ runner.os }}-go-
-
-    - name: Install build dependencies
-      run: |
-        sudo apt-get update
-        sudo apt-get install -y podman
-
-    - name: Build binaries
-      run: |
-        make build
-        make cli-build
-        # Build Zig CLI (dev and prod)
-        cd cli && zig build dev && zig build prod && cd ..
-        # Note: prod builds use rsync_placeholder wrapper
-        # For true embedded rsync, add static binary to cli/src/assets/rsync_release.bin
-
-    - name: Test binaries
-      run: |
-        ./bin/user_manager --help
-        ./bin/worker --help
-        ./bin/tui --help
-        ./bin/data_manager --help
-        # Test Zig CLI
-        ./cli/zig-out/prod/ml --help
-        # Verify binary size (should be small with placeholder rsync)
-        ls -lh ./cli/zig-out/prod/ml
-
-    - name: Upload build artifacts
-      uses: actions/upload-artifact@v4
-      with:
-        name: fetch_ml_binaries
-        path: |
-          bin/
-          cli/zig-out/
-          dist/
-        retention-days: 30
-
-  test-scripts:
-    name: Test Scripts
-    runs-on: ubuntu-latest
-    needs: test
-    timeout-minutes: 15
-    
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@v5
-
-    - name: Install dependencies
-      run: |
-        sudo apt-get update
-        sudo apt-get install -y podman redis-tools bats
-
-    - name: Test scripts
-      run: |
-        # Test script functionality
-        chmod +x scripts/*.sh
-        
-        # Test quick start script (dry run)
-        ./scripts/quick_start.sh --help || true
-        
-        # Test security monitor
-        ./scripts/security-monitor.sh help
-        
-        # Test auto setup
-        ./scripts/auto_setup.sh help
-        
-        # Test deployment scripts
-        ./scripts/deploy-secure.sh --help || true
-        ./scripts/deploy-prod.sh --help || true
-
-  security-scan:
-    name: Security Scan
-    runs-on: ubuntu-latest
-    timeout-minutes: 20
-    
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@v5
-
-    - name: Run Trivy vulnerability scanner
-      uses: aquasecurity/trivy-action@master
-      with:
-        scan-type: 'fs'
-        scan-ref: '.'
-        format: 'sarif'
-        output: 'trivy-results.sarif'
-
-    - name: Upload Trivy scan results to GitHub Security tab
-      uses: github/codeql-action/upload-sarif@v2
-      if: always()
-      with:
-        sarif_file: 'trivy-results.sarif'
-
-    - name: Gosec Security Scanner
-      run: |
-        go install github.com/securecodewarrior/gosec/v2/cmd/gosec@latest
-        gosec ./...
-
-  docker-build:
-    name: Docker Build
-    runs-on: ubuntu-latest
-    needs: [test, build, test-scripts]
-    if: github.event_name == 'push' && github.ref == 'refs/heads/main'
-    timeout-minutes: 30
-    
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@v5
-
-    - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v3
-
-    - name: Login to GitHub Container Registry
-      uses: docker/login-action@v3
-      with:
-        registry: ghcr.io
-        username: ${{ github.actor }}
-        password: ${{ secrets.GITHUB_TOKEN }}
-
-    - name: Build and push Docker image
-      uses: docker/build-push-action@v6
-      with:
-        context: .
-        platforms: linux/amd64,linux/arm64
-        push: true
-        tags: |
-          ghcr.io/${{ github.repository }}:latest
-          ghcr.io/${{ github.repository }}:${{ github.sha }}
-        cache-from: type=gha
-        cache-to: type=gha,mode=max
-
diff --git a/.github/workflows/docs.yml b/.github/workflows/docs.yml
deleted file mode 100644
index 792a430..0000000
--- a/.github/workflows/docs.yml
+++ /dev/null
@@ -1,58 +0,0 @@
-name: Documentation
-
-on:
-  workflow_dispatch:
-  push:
-    branches: [ main ]
-  pull_request:
-
-permissions:
-  contents: read
-  pages: write
-  id-token: write
-
-concurrency:
-  group: "pages"
-  cancel-in-progress: false
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    steps:
-    - name: Checkout
-      uses: actions/checkout@v4
-
-    - name: Setup Pages
-      id: pages
-      uses: actions/configure-pages@v3
-
-    - name: Set up Go (for Hugo Modules)
-      uses: actions/setup-go@v5
-      with:
-        go-version: '1.21'
-
-    - name: Setup Hugo
-      uses: peaceiris/actions-hugo@v3
-      with:
-        hugo-version: '0.125.7'
-        extended: true
-
-    - name: Build with Hugo
-      run: hugo --source docs --minify --baseURL "${{ steps.pages.outputs.base_url }}/"
-
-    - name: Upload artifact
-      uses: actions/upload-pages-artifact@v2
-      with:
-        path: docs/_site
-
-  deploy:
-    environment:
-      name: github-pages
-      url: ${{ steps.deployment.outputs.page_url }}
-    runs-on: ubuntu-latest
-    needs: build
-    if: github.ref == 'refs/heads/main'
-    steps:
-    - name: Deploy to GitHub Pages
-      id: deployment
-      uses: actions/deploy-pages@v2
diff --git a/.github/workflows/label.yml b/.github/workflows/label.yml
deleted file mode 100644
index 5603b88..0000000
--- a/.github/workflows/label.yml
+++ /dev/null
@@ -1,21 +0,0 @@
-name: Label Pull Request
-
-on:
-  workflow_dispatch:
-
-jobs:
-  label:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      pull-requests: write
-
-    steps:
-    - name: Checkout
-      uses: actions/checkout@v4
-
-    - name: Label PR
-      uses: actions/labeler@v4
-      with:
-        configuration-path: .github/labeler.yml
-        sync-labels: true
diff --git a/.github/workflows/license-check.yml b/.github/workflows/license-check.yml
deleted file mode 100644
index 24f4b85..0000000
--- a/.github/workflows/license-check.yml
+++ /dev/null
@@ -1,45 +0,0 @@
-name: License Check
-
-on:
-  push:
-    branches: [ main, develop ]
-  pull_request:
-    branches: [ main ]
-
-jobs:
-  license-check:
-    runs-on: ubuntu-latest
-    
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@v4
-    
-    - name: Check license headers
-      run: |
-        # Check if LICENSE file exists
-        if [ ! -f "LICENSE" ]; then
-          echo "LICENSE file is missing"
-          exit 1
-        fi
-
-        echo "License file OK"
-    
-    - name: Check Go files for license headers
-      run: |
-        # Check for license headers in Go files (optional but good practice)
-        missing_headers=0
-        
-        for file in $(find . -name "*.go" -not -path "./vendor/*" -not -path "./.git/*"); do
-          if ! head -10 "$file" | grep -q "Copyright"; then
-            echo "Missing license header in: $file"
-            missing_headers=$((missing_headers + 1))
-          fi
-        done
-        
-        if [ $missing_headers -gt 0 ]; then
-          echo "Found $missing_headers Go files without license headers"
-          echo "Consider adding license headers to Go files"
-          # Don't fail the build, just warn
-        else
-          echo "All Go files have license headers"
-        fi
diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
deleted file mode 100644
index 68ca145..0000000
--- a/.github/workflows/release.yml
+++ /dev/null
@@ -1,208 +0,0 @@
-name: Release
-
-on:
-  workflow_dispatch:
-
-permissions:
-  contents: write
-  packages: write
-  id-token: write
-
-env:
-  GO_VERSION: '1.25.0'
-  ZIG_VERSION: '0.15.2'
-
-jobs:
-  prepare_rsync:
-    name: Prepare rsync metadata
-    runs-on: ubuntu-latest
-    outputs:
-      matrix: ${{ steps.manifest.outputs.matrix }}
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v5
-
-      - name: Load rsync manifest
-        id: manifest
-        run: |
-          MANIFEST=.github/rsync_manifest.json
-          MATRIX=$(jq -c '
-            . as $cfg
-            | $cfg.platforms
-            | to_entries
-            | map({
-                platform: .key,
-                target: .value.target,
-                "rsync-url": ($cfg.base_url + "/" + $cfg.version + "/" + .value.asset),
-                "rsync-sha256": .value.sha256
-              })
-          ' "$MANIFEST")
-          printf 'matrix={"include":%s}\n' "$MATRIX" >> "$GITHUB_OUTPUT"
-
-  build-cli:
-    name: Build CLI - ${{ matrix.platform }}
-    needs: prepare_rsync
-    runs-on: ubuntu-latest
-    strategy:
-      matrix: ${{ fromJson(needs.prepare_rsync.outputs.matrix) }}
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v5
-
-      - name: Set up Zig
-        uses: goto-bus-stop/setup-zig@v2
-        with:
-          version: ${{ env.ZIG_VERSION }}
-
-      - name: Download static rsync
-        run: |
-          mkdir -p cli/src/assets
-          wget -O cli/src/assets/rsync_release.bin ${{ matrix.rsync-url }} || \
-            curl -L -o cli/src/assets/rsync_release.bin ${{ matrix.rsync-url }}
-          echo "${{ matrix.rsync-sha256 }}  cli/src/assets/rsync_release.bin" | sha256sum -c
-          chmod +x cli/src/assets/rsync_release.bin
-          ls -lh cli/src/assets/rsync_release.bin
-
-      - name: Build CLI
-        working-directory: cli
-        run: |
-          zig build-exe -OReleaseSmall -fstrip -target ${{ matrix.target }} \
-            -femit-bin=zig-out/bin/ml src/main.zig
-          ls -lh zig-out/bin/ml
-
-      - name: Strip binary (Linux only)
-        if: matrix.platform == 'linux-x86_64'
-        working-directory: cli
-        run: strip zig-out/bin/ml
-
-      - name: Package binary
-        run: |
-          mkdir -p dist
-          cp cli/zig-out/bin/ml dist/ml-${{ matrix.platform }}
-          cd dist
-          tar -czf ml-${{ matrix.platform }}.tar.gz ml-${{ matrix.platform }}
-          sha256sum ml-${{ matrix.platform }}.tar.gz > ml-${{ matrix.platform }}.tar.gz.sha256
-
-      - name: Upload build artifact
-        uses: actions/upload-artifact@v4
-        with:
-          name: ml-${{ matrix.platform }}
-          path: |
-            dist/ml-${{ matrix.platform }}.tar.gz
-            dist/ml-${{ matrix.platform }}.tar.gz.sha256
-
-  build-go-backends:
-    name: Build Go Backends
-    runs-on: ubuntu-latest
-    
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v5
-
-      - name: Set up Go
-        uses: actions/setup-go@v5
-        with:
-          go-version: ${{ env.GO_VERSION }}
-
-      - name: Build binaries
-        run: |
-          make cross-platform
-          ls -lh dist/
-
-      - name: Package binaries
-        run: |
-          cd dist
-          for binary in fetch_ml_*; do
-            if [[ -f "${binary}" ]]; then
-              tar -czf "${binary}.tar.gz" "${binary}"
-              sha256sum "${binary}.tar.gz" > "${binary}.tar.gz.sha256"
-            fi
-          done
-
-      - name: Upload build artifacts
-        uses: actions/upload-artifact@v4
-        with:
-          name: go-backends
-          path: |
-            dist/*.tar.gz
-            dist/*.sha256
-
-  create-release:
-    name: Create GitHub Release
-    needs: [build-cli, build-go-backends]
-    runs-on: ubuntu-latest
-    
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v5
-
-      - name: Download all artifacts
-        uses: actions/download-artifact@v4
-        with:
-          path: artifacts
-
-      - name: Prepare release assets
-        run: |
-          mkdir -p release
-          # Copy CLI binaries
-          cp artifacts/ml-*/ml-*.tar.gz* release/
-          # Copy Go binaries
-          cp artifacts/go-backends/*.tar.gz* release/
-          
-          # Generate combined checksums
-          cd release
-          sha256sum *.tar.gz > checksums.txt
-          ls -lh
-
-      - name: Install cosign
-        uses: sigstore/cosign-installer@v3
-
-      - name: Sign checksums.txt (keyless)
-        working-directory: release
-        env:
-          COSIGN_YES: "true"
-        run: |
-          cosign sign-blob \
-            --output-signature checksums.txt.sig \
-            --output-certificate checksums.txt.cert \
-            checksums.txt
-          ls -lh checksums.txt checksums.txt.sig checksums.txt.cert
-
-      - name: Create Release
-        uses: softprops/action-gh-release@v2
-        with:
-          files: release/*
-          body: |
-            ## 🚀 Release ${{ github.ref_name }}
-            
-            ### CLI Binaries (Zero Dependencies)
-            All CLI binaries include embedded static rsync for complete independence.
-            
-            - **`ml-linux-x86_64.tar.gz`** - Linux x86_64 (fully static, musl)
-            - **`ml-macos-x86_64.tar.gz`** - macOS Intel
-            - **`ml-macos-arm64.tar.gz`** - macOS Apple Silicon
-            
-            ### Go Backend Binaries
-            Included as per-platform tarballs named:
-            - `fetch_ml_<component>_<os>_<arch>[.exe].tar.gz`
-
-            ### Installation
-            ```bash
-            # Download and extract (example: CLI)
-            tar -xzf ml-<platform>.tar.gz
-            
-            # Make executable and move to PATH
-            chmod +x ml-<platform>
-            sudo mv ml-<platform> /usr/local/bin/ml
-            
-            # Verify installation
-            ml --help
-            ```
-            
-            ### Checksums
-            SHA256 checksums are provided in `checksums.txt` and individual `.sha256` files.
-          generate_release_notes: true
-          draft: false
-          prerelease: false
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
diff --git a/.github/workflows/stale.yml b/.github/workflows/stale.yml
deleted file mode 100644
index db6bd0f..0000000
--- a/.github/workflows/stale.yml
+++ /dev/null
@@ -1,33 +0,0 @@
-name: Mark Stale Issues and PRs
-
-on:
-  schedule:
-    - cron: "0 0 * * 1"  # Every Monday at midnight
-  workflow_dispatch:
-
-permissions:
-  issues: write
-  pull-requests: write
-
-jobs:
-  stale:
-    runs-on: ubuntu-latest
-    steps:
-    - name: Mark stale issues and PRs
-      uses: actions/stale@v8
-      with:
-        repo-token: ${{ secrets.GITHUB_TOKEN }}
-        days-before-stale: 30
-        days-before-close: 14
-        stale-issue-label: "stale"
-        stale-pr-label: "stale"
-        stale-issue-message: |
-          This issue has been automatically marked as stale because it has not had recent activity.
-          It will be closed if no further activity occurs within 14 days.
-          Thank you for your contributions!
-        stale-pr-message: |
-          This pull request has been automatically marked as stale because it has not had recent activity.
-          It will be closed if no further activity occurs within 14 days.
-          Thank you for your contributions!
-        exempt-issue-labels: "pinned,security,help wanted,good first issue"
-        exempt-pr-labels: "pinned,security,help wanted,good first issue"
diff --git a/.gitignore b/.gitignore
index 47bf62e..749b5a1 100644
--- a/.gitignore
+++ b/.gitignore
@@ -24,6 +24,10 @@ go.work
 *.swo
 *~
 
+# Allow committing VS Code settings
+!.vscode/settings.json
+!cli/.vscode/settings.json
+
 # OS generated files
 .DS_Store
 .DS_Store?
@@ -80,7 +84,7 @@ share/python-wheels/
 *.egg-info/
 .installed.cfg
 *.egg
-MANIFEST
+# MANIFEST
 
 # PyInstaller
 *.manifest
@@ -212,6 +216,8 @@ coverage.html
 queue-coverage.out
 coverage/
 
+test_results/
+
 # documents
 docs/_site/**
 
@@ -232,6 +238,7 @@ db/*.db
 *.pem
 secrets/
 cli/src/assets/rsync_release.bin
+cli/src/assets/rsync_release_*.bin
 
 # Local artifacts (e.g. test run outputs)
 .local-artifacts/
@@ -265,6 +272,3 @@ db/*.db
 ssl/
 *.pem
 *.key
-
-# Windsurf AI
-.windsurf/
diff --git a/.local-artifacts/run_20251204_230712/benchmark_results.txt b/.local-artifacts/run_20251204_230712/benchmark_results.txt
deleted file mode 100644
index 259711e..0000000
--- a/.local-artifacts/run_20251204_230712/benchmark_results.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-goos: darwin
-goarch: arm64
-pkg: github.com/jfraeys/fetch_ml/tests/benchmarks
-cpu: Apple M2 Ultra
-BenchmarkAPIServerCreateJobSimple-24    	   25867	     44784 ns/op	   13520 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	58569440	        19.87 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    104650 ns/op	   26708 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	    8703	    553714 ns/op	   18123 B/op	     131 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     918	   1357144 ns/op	    6088 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     908	   1351232 ns/op	    6466 B/op	      73 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     909	   1338756 ns/op	    6719 B/op	      74 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      42	  26589647 ns/op	  657022 B/op	   12350 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	      94	  12482363 ns/op	  794538 B/op	    6254 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     358	   3631202 ns/op	 1129266 B/op	    1376 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      34	  35603358 ns/op	 1111297 B/op	   12625 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      55	  27881781 ns/op	  615782 B/op	   17884 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   12116	     98516 ns/op	    2933 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	23803464	        49.69 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   18534	     65030 ns/op	    1285 B/op	      36 allocs/op
-PASS
-ok  	github.com/jfraeys/fetch_ml/tests/benchmarks	28.082s
diff --git a/.local-artifacts/run_20251204_230712/clean_benchmarks.txt b/.local-artifacts/run_20251204_230712/clean_benchmarks.txt
deleted file mode 100644
index 81009dd..0000000
--- a/.local-artifacts/run_20251204_230712/clean_benchmarks.txt
+++ /dev/null
@@ -1,15 +0,0 @@
-BenchmarkAPIServerCreateJobSimple-24    	   25867	     44784 ns/op	   13520 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	58569440	        19.87 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    104650 ns/op	   26708 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	    8703	    553714 ns/op	   18123 B/op	     131 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     918	   1357144 ns/op	    6088 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     908	   1351232 ns/op	    6466 B/op	      73 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     909	   1338756 ns/op	    6719 B/op	      74 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      42	  26589647 ns/op	  657022 B/op	   12350 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	      94	  12482363 ns/op	  794538 B/op	    6254 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     358	   3631202 ns/op	 1129266 B/op	    1376 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      34	  35603358 ns/op	 1111297 B/op	   12625 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      55	  27881781 ns/op	  615782 B/op	   17884 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   12116	     98516 ns/op	    2933 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	23803464	        49.69 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   18534	     65030 ns/op	    1285 B/op	      36 allocs/op
diff --git a/.local-artifacts/run_20251204_230712/prometheus_metrics.txt b/.local-artifacts/run_20251204_230712/prometheus_metrics.txt
deleted file mode 100644
index 3b01f0c..0000000
--- a/.local-artifacts/run_20251204_230712/prometheus_metrics.txt
+++ /dev/null
@@ -1,51 +0,0 @@
-# HELP benchmark_time_per_op Time per operation in nanoseconds
-# TYPE benchmark_time_per_op gauge
-# HELP benchmark_memory_per_op Memory per operation in bytes
-# TYPE benchmark_memory_per_op gauge
-# HELP benchmark_allocs_per_op Allocations per operation
-# TYPE benchmark_allocs_per_op gauge
-benchmark_time_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} 44784
-benchmark_memory_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} 13520
-benchmark_time_per_op{benchmark="BenchmarkMetricsCollection"} 19.87
-benchmark_memory_per_op{benchmark="BenchmarkMetricsCollection"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMetricsCollection"} 0
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} 104650
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} 26708
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} 553714
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} 18123
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} 1357144
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} 6088
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} 1351232
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} 6466
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} 1338756
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} 6719
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} 26589647
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} 657022
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} 12482363
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} 794538
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} 3631202
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} 1129266
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} 35603358
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} 1111297
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} 27881781
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} 615782
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} 98516
-benchmark_memory_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} 2933
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} 49.69
-benchmark_memory_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} 16
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} 65030
-benchmark_memory_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} 1285
diff --git a/.local-artifacts/run_20251204_230712/report.html b/.local-artifacts/run_20251204_230712/report.html
deleted file mode 100644
index 1e73592..0000000
--- a/.local-artifacts/run_20251204_230712/report.html
+++ /dev/null
@@ -1,141 +0,0 @@
-<!DOCTYPE html>
-<html>
-<head>
-    <title>Benchmark Report - 20251204_230712</title>
-    <style>
-        body { font-family: Arial, sans-serif; margin: 20px; }
-        table { border-collapse: collapse; width: 100%; }
-        th, td { border: 1px solid #ddd; padding: 8px; text-align: left; }
-        th { background-color: #f2f2f2; }
-        .metric { font-family: monospace; }
-    </style>
-</head>
-<body>
-    <h1>Benchmark Report</h1>
-    <p><strong>Run ID:</strong> 20251204_230712</p>
-    <p><strong>Date:</strong> Thu Dec  4 18:07:41 EST 2025</p>
-    
-    <h2>Results</h2>
-    <table>
-        <tr>
-            <th>Benchmark</th>
-            <th>Time (ns/op)</th>
-            <th>Memory (B/op)</th>
-            <th>Allocs (allocs/op)</th>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkAPIServerCreateJobSimple-24</td>
-            <td>44784</td>
-            <td>ns/op</td>
-            <td>13520</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMetricsCollection-24</td>
-            <td>19.87</td>
-            <td>ns/op</td>
-            <td>0</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-1-24</td>
-            <td>104650</td>
-            <td>ns/op</td>
-            <td>26708</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-5-24</td>
-            <td>553714</td>
-            <td>ns/op</td>
-            <td>18123</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-10-24</td>
-            <td>1357144</td>
-            <td>ns/op</td>
-            <td>6088</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-25-24</td>
-            <td>1351232</td>
-            <td>ns/op</td>
-            <td>6466</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-50-24</td>
-            <td>1338756</td>
-            <td>ns/op</td>
-            <td>6719</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/SmallExperiment-24</td>
-            <td>26589647</td>
-            <td>ns/op</td>
-            <td>657022</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/MediumExperiment-24</td>
-            <td>12482363</td>
-            <td>ns/op</td>
-            <td>794538</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/LargeExperiment-24</td>
-            <td>3631202</td>
-            <td>ns/op</td>
-            <td>1129266</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/ConcurrentExperiments-24</td>
-            <td>35603358</td>
-            <td>ns/op</td>
-            <td>1111297</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/ExperimentMetrics-24</td>
-            <td>27881781</td>
-            <td>ns/op</td>
-            <td>615782</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetCreation-24</td>
-            <td>98516</td>
-            <td>ns/op</td>
-            <td>2933</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetRetrieval-24</td>
-            <td>49.69</td>
-            <td>ns/op</td>
-            <td>16</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetUpdate-24</td>
-            <td>65030</td>
-            <td>ns/op</td>
-            <td>1285</td>
-        </tr>
-    </table>
-    
-    <h2>Raw Output</h2>
-    <pre>goos: darwin
-goarch: arm64
-pkg: github.com/jfraeys/fetch_ml/tests/benchmarks
-cpu: Apple M2 Ultra
-BenchmarkAPIServerCreateJobSimple-24    	   25867	     44784 ns/op	   13520 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	58569440	        19.87 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    104650 ns/op	   26708 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	    8703	    553714 ns/op	   18123 B/op	     131 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     918	   1357144 ns/op	    6088 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     908	   1351232 ns/op	    6466 B/op	      73 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     909	   1338756 ns/op	    6719 B/op	      74 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      42	  26589647 ns/op	  657022 B/op	   12350 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	      94	  12482363 ns/op	  794538 B/op	    6254 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     358	   3631202 ns/op	 1129266 B/op	    1376 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      34	  35603358 ns/op	 1111297 B/op	   12625 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      55	  27881781 ns/op	  615782 B/op	   17884 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   12116	     98516 ns/op	    2933 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	23803464	        49.69 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   18534	     65030 ns/op	    1285 B/op	      36 allocs/op
-PASS
-ok  	github.com/jfraeys/fetch_ml/tests/benchmarks	28.082s</pre>
-</body>
-</html>
diff --git a/.local-artifacts/run_20251204_231218/benchmark_results.txt b/.local-artifacts/run_20251204_231218/benchmark_results.txt
deleted file mode 100644
index 610cfbe..0000000
--- a/.local-artifacts/run_20251204_231218/benchmark_results.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-goos: darwin
-goarch: arm64
-pkg: github.com/jfraeys/fetch_ml/tests/benchmarks
-cpu: Apple M2 Ultra
-BenchmarkAPIServerCreateJobSimple-24    	   28656	     43062 ns/op	   13518 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	59213934	        19.29 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    108510 ns/op	   26825 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	    9895	    657334 ns/op	   16807 B/op	     124 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     914	   1346314 ns/op	    6032 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     885	   1350853 ns/op	    6289 B/op	      73 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     853	   1346826 ns/op	    6431 B/op	      75 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      43	  26357159 ns/op	  657854 B/op	   12354 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	      92	  12494936 ns/op	  794812 B/op	    6254 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     348	   3659886 ns/op	 1129733 B/op	    1376 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      40	  32637755 ns/op	 1114183 B/op	   12636 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      56	  27153394 ns/op	  615897 B/op	   17885 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   10000	    102638 ns/op	    2921 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	20641564	        50.73 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   20919	     65724 ns/op	    1285 B/op	      36 allocs/op
-PASS
-ok  	github.com/jfraeys/fetch_ml/tests/benchmarks	26.755s
diff --git a/.local-artifacts/run_20251204_231218/clean_benchmarks.txt b/.local-artifacts/run_20251204_231218/clean_benchmarks.txt
deleted file mode 100644
index 84112e7..0000000
--- a/.local-artifacts/run_20251204_231218/clean_benchmarks.txt
+++ /dev/null
@@ -1,15 +0,0 @@
-BenchmarkAPIServerCreateJobSimple-24    	   28656	     43062 ns/op	   13518 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	59213934	        19.29 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    108510 ns/op	   26825 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	    9895	    657334 ns/op	   16807 B/op	     124 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     914	   1346314 ns/op	    6032 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     885	   1350853 ns/op	    6289 B/op	      73 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     853	   1346826 ns/op	    6431 B/op	      75 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      43	  26357159 ns/op	  657854 B/op	   12354 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	      92	  12494936 ns/op	  794812 B/op	    6254 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     348	   3659886 ns/op	 1129733 B/op	    1376 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      40	  32637755 ns/op	 1114183 B/op	   12636 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      56	  27153394 ns/op	  615897 B/op	   17885 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   10000	    102638 ns/op	    2921 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	20641564	        50.73 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   20919	     65724 ns/op	    1285 B/op	      36 allocs/op
diff --git a/.local-artifacts/run_20251204_231218/prometheus_metrics.txt b/.local-artifacts/run_20251204_231218/prometheus_metrics.txt
deleted file mode 100644
index 72d240d..0000000
--- a/.local-artifacts/run_20251204_231218/prometheus_metrics.txt
+++ /dev/null
@@ -1,51 +0,0 @@
-# HELP benchmark_time_per_op Time per operation in nanoseconds
-# TYPE benchmark_time_per_op gauge
-# HELP benchmark_memory_per_op Memory per operation in bytes
-# TYPE benchmark_memory_per_op gauge
-# HELP benchmark_allocs_per_op Allocations per operation
-# TYPE benchmark_allocs_per_op gauge
-benchmark_time_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} 43062
-benchmark_memory_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} 13518
-benchmark_time_per_op{benchmark="BenchmarkMetricsCollection"} 19.29
-benchmark_memory_per_op{benchmark="BenchmarkMetricsCollection"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMetricsCollection"} 0
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} 108510
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} 26825
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} 657334
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} 16807
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} 1346314
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} 6032
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} 1350853
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} 6289
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} 1346826
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} 6431
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} 26357159
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} 657854
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} 12494936
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} 794812
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} 3659886
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} 1129733
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} 32637755
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} 1114183
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} 27153394
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} 615897
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} 102638
-benchmark_memory_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} 2921
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} 50.73
-benchmark_memory_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} 16
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} 65724
-benchmark_memory_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} 1285
diff --git a/.local-artifacts/run_20251204_231218/report.html b/.local-artifacts/run_20251204_231218/report.html
deleted file mode 100644
index 44afaa6..0000000
--- a/.local-artifacts/run_20251204_231218/report.html
+++ /dev/null
@@ -1,141 +0,0 @@
-<!DOCTYPE html>
-<html>
-<head>
-    <title>Benchmark Report - 20251204_231218</title>
-    <style>
-        body { font-family: Arial, sans-serif; margin: 20px; }
-        table { border-collapse: collapse; width: 100%; }
-        th, td { border: 1px solid #ddd; padding: 8px; text-align: left; }
-        th { background-color: #f2f2f2; }
-        .metric { font-family: monospace; }
-    </style>
-</head>
-<body>
-    <h1>Benchmark Report</h1>
-    <p><strong>Run ID:</strong> 20251204_231218</p>
-    <p><strong>Date:</strong> Thu Dec  4 18:12:46 EST 2025</p>
-    
-    <h2>Results</h2>
-    <table>
-        <tr>
-            <th>Benchmark</th>
-            <th>Time (ns/op)</th>
-            <th>Memory (B/op)</th>
-            <th>Allocs (allocs/op)</th>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkAPIServerCreateJobSimple-24</td>
-            <td>43062</td>
-            <td>ns/op</td>
-            <td>13518</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMetricsCollection-24</td>
-            <td>19.29</td>
-            <td>ns/op</td>
-            <td>0</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-1-24</td>
-            <td>108510</td>
-            <td>ns/op</td>
-            <td>26825</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-5-24</td>
-            <td>657334</td>
-            <td>ns/op</td>
-            <td>16807</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-10-24</td>
-            <td>1346314</td>
-            <td>ns/op</td>
-            <td>6032</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-25-24</td>
-            <td>1350853</td>
-            <td>ns/op</td>
-            <td>6289</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-50-24</td>
-            <td>1346826</td>
-            <td>ns/op</td>
-            <td>6431</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/SmallExperiment-24</td>
-            <td>26357159</td>
-            <td>ns/op</td>
-            <td>657854</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/MediumExperiment-24</td>
-            <td>12494936</td>
-            <td>ns/op</td>
-            <td>794812</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/LargeExperiment-24</td>
-            <td>3659886</td>
-            <td>ns/op</td>
-            <td>1129733</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/ConcurrentExperiments-24</td>
-            <td>32637755</td>
-            <td>ns/op</td>
-            <td>1114183</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/ExperimentMetrics-24</td>
-            <td>27153394</td>
-            <td>ns/op</td>
-            <td>615897</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetCreation-24</td>
-            <td>102638</td>
-            <td>ns/op</td>
-            <td>2921</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetRetrieval-24</td>
-            <td>50.73</td>
-            <td>ns/op</td>
-            <td>16</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetUpdate-24</td>
-            <td>65724</td>
-            <td>ns/op</td>
-            <td>1285</td>
-        </tr>
-    </table>
-    
-    <h2>Raw Output</h2>
-    <pre>goos: darwin
-goarch: arm64
-pkg: github.com/jfraeys/fetch_ml/tests/benchmarks
-cpu: Apple M2 Ultra
-BenchmarkAPIServerCreateJobSimple-24    	   28656	     43062 ns/op	   13518 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	59213934	        19.29 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    108510 ns/op	   26825 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	    9895	    657334 ns/op	   16807 B/op	     124 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     914	   1346314 ns/op	    6032 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     885	   1350853 ns/op	    6289 B/op	      73 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     853	   1346826 ns/op	    6431 B/op	      75 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      43	  26357159 ns/op	  657854 B/op	   12354 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	      92	  12494936 ns/op	  794812 B/op	    6254 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     348	   3659886 ns/op	 1129733 B/op	    1376 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      40	  32637755 ns/op	 1114183 B/op	   12636 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      56	  27153394 ns/op	  615897 B/op	   17885 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   10000	    102638 ns/op	    2921 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	20641564	        50.73 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   20919	     65724 ns/op	    1285 B/op	      36 allocs/op
-PASS
-ok  	github.com/jfraeys/fetch_ml/tests/benchmarks	26.755s</pre>
-</body>
-</html>
diff --git a/.local-artifacts/run_20251204_231255/benchmark_results.txt b/.local-artifacts/run_20251204_231255/benchmark_results.txt
deleted file mode 100644
index 11a27d1..0000000
--- a/.local-artifacts/run_20251204_231255/benchmark_results.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-goos: darwin
-goarch: arm64
-pkg: github.com/jfraeys/fetch_ml/tests/benchmarks
-cpu: Apple M2 Ultra
-BenchmarkAPIServerCreateJobSimple-24    	   28408	     45304 ns/op	   13517 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	60437035	        19.88 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    106089 ns/op	   26846 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	    9220	    579691 ns/op	   17615 B/op	     128 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     925	   1348616 ns/op	    6050 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     927	   1340898 ns/op	    6529 B/op	      73 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     916	   1333626 ns/op	    6694 B/op	      74 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      43	  26542657 ns/op	  656983 B/op	   12350 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	     100	  12121203 ns/op	  794420 B/op	    6253 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     358	   3704013 ns/op	 1128981 B/op	    1374 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      34	  32337061 ns/op	 1113039 B/op	   12630 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      52	  26482224 ns/op	  615734 B/op	   17883 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   12356	    101514 ns/op	    2934 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	24143787	        49.80 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   18423	     65515 ns/op	    1285 B/op	      36 allocs/op
-PASS
-ok  	github.com/jfraeys/fetch_ml/tests/benchmarks	28.641s
diff --git a/.local-artifacts/run_20251204_231255/clean_benchmarks.txt b/.local-artifacts/run_20251204_231255/clean_benchmarks.txt
deleted file mode 100644
index b87bdc2..0000000
--- a/.local-artifacts/run_20251204_231255/clean_benchmarks.txt
+++ /dev/null
@@ -1,15 +0,0 @@
-BenchmarkAPIServerCreateJobSimple-24    	   28408	     45304 ns/op	   13517 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	60437035	        19.88 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    106089 ns/op	   26846 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	    9220	    579691 ns/op	   17615 B/op	     128 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     925	   1348616 ns/op	    6050 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     927	   1340898 ns/op	    6529 B/op	      73 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     916	   1333626 ns/op	    6694 B/op	      74 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      43	  26542657 ns/op	  656983 B/op	   12350 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	     100	  12121203 ns/op	  794420 B/op	    6253 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     358	   3704013 ns/op	 1128981 B/op	    1374 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      34	  32337061 ns/op	 1113039 B/op	   12630 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      52	  26482224 ns/op	  615734 B/op	   17883 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   12356	    101514 ns/op	    2934 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	24143787	        49.80 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   18423	     65515 ns/op	    1285 B/op	      36 allocs/op
diff --git a/.local-artifacts/run_20251204_231255/prometheus_metrics.txt b/.local-artifacts/run_20251204_231255/prometheus_metrics.txt
deleted file mode 100644
index 3828ea0..0000000
--- a/.local-artifacts/run_20251204_231255/prometheus_metrics.txt
+++ /dev/null
@@ -1,51 +0,0 @@
-# HELP benchmark_time_per_op Time per operation in nanoseconds
-# TYPE benchmark_time_per_op gauge
-# HELP benchmark_memory_per_op Memory per operation in bytes
-# TYPE benchmark_memory_per_op gauge
-# HELP benchmark_allocs_per_op Allocations per operation
-# TYPE benchmark_allocs_per_op gauge
-benchmark_time_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} 45304
-benchmark_memory_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} 13517
-benchmark_time_per_op{benchmark="BenchmarkMetricsCollection"} 19.88
-benchmark_memory_per_op{benchmark="BenchmarkMetricsCollection"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMetricsCollection"} 0
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} 106089
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} 26846
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} 579691
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} 17615
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} 1348616
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} 6050
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} 1340898
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} 6529
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} 1333626
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} 6694
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} 26542657
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} 656983
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} 12121203
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} 794420
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} 3704013
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} 1128981
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} 32337061
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} 1113039
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} 26482224
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} 615734
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} 101514
-benchmark_memory_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} 2934
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} 49.80
-benchmark_memory_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} 16
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} 65515
-benchmark_memory_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} 1285
diff --git a/.local-artifacts/run_20251204_231255/report.html b/.local-artifacts/run_20251204_231255/report.html
deleted file mode 100644
index a060891..0000000
--- a/.local-artifacts/run_20251204_231255/report.html
+++ /dev/null
@@ -1,141 +0,0 @@
-<!DOCTYPE html>
-<html>
-<head>
-    <title>Benchmark Report - 20251204_231255</title>
-    <style>
-        body { font-family: Arial, sans-serif; margin: 20px; }
-        table { border-collapse: collapse; width: 100%; }
-        th, td { border: 1px solid #ddd; padding: 8px; text-align: left; }
-        th { background-color: #f2f2f2; }
-        .metric { font-family: monospace; }
-    </style>
-</head>
-<body>
-    <h1>Benchmark Report</h1>
-    <p><strong>Run ID:</strong> 20251204_231255</p>
-    <p><strong>Date:</strong> Thu Dec  4 18:13:24 EST 2025</p>
-    
-    <h2>Results</h2>
-    <table>
-        <tr>
-            <th>Benchmark</th>
-            <th>Time (ns/op)</th>
-            <th>Memory (B/op)</th>
-            <th>Allocs (allocs/op)</th>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkAPIServerCreateJobSimple-24</td>
-            <td>45304</td>
-            <td>ns/op</td>
-            <td>13517</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMetricsCollection-24</td>
-            <td>19.88</td>
-            <td>ns/op</td>
-            <td>0</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-1-24</td>
-            <td>106089</td>
-            <td>ns/op</td>
-            <td>26846</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-5-24</td>
-            <td>579691</td>
-            <td>ns/op</td>
-            <td>17615</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-10-24</td>
-            <td>1348616</td>
-            <td>ns/op</td>
-            <td>6050</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-25-24</td>
-            <td>1340898</td>
-            <td>ns/op</td>
-            <td>6529</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-50-24</td>
-            <td>1333626</td>
-            <td>ns/op</td>
-            <td>6694</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/SmallExperiment-24</td>
-            <td>26542657</td>
-            <td>ns/op</td>
-            <td>656983</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/MediumExperiment-24</td>
-            <td>12121203</td>
-            <td>ns/op</td>
-            <td>794420</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/LargeExperiment-24</td>
-            <td>3704013</td>
-            <td>ns/op</td>
-            <td>1128981</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/ConcurrentExperiments-24</td>
-            <td>32337061</td>
-            <td>ns/op</td>
-            <td>1113039</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/ExperimentMetrics-24</td>
-            <td>26482224</td>
-            <td>ns/op</td>
-            <td>615734</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetCreation-24</td>
-            <td>101514</td>
-            <td>ns/op</td>
-            <td>2934</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetRetrieval-24</td>
-            <td>49.80</td>
-            <td>ns/op</td>
-            <td>16</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetUpdate-24</td>
-            <td>65515</td>
-            <td>ns/op</td>
-            <td>1285</td>
-        </tr>
-    </table>
-    
-    <h2>Raw Output</h2>
-    <pre>goos: darwin
-goarch: arm64
-pkg: github.com/jfraeys/fetch_ml/tests/benchmarks
-cpu: Apple M2 Ultra
-BenchmarkAPIServerCreateJobSimple-24    	   28408	     45304 ns/op	   13517 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	60437035	        19.88 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    106089 ns/op	   26846 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	    9220	    579691 ns/op	   17615 B/op	     128 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     925	   1348616 ns/op	    6050 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     927	   1340898 ns/op	    6529 B/op	      73 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     916	   1333626 ns/op	    6694 B/op	      74 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      43	  26542657 ns/op	  656983 B/op	   12350 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	     100	  12121203 ns/op	  794420 B/op	    6253 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     358	   3704013 ns/op	 1128981 B/op	    1374 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      34	  32337061 ns/op	 1113039 B/op	   12630 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      52	  26482224 ns/op	  615734 B/op	   17883 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   12356	    101514 ns/op	    2934 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	24143787	        49.80 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   18423	     65515 ns/op	    1285 B/op	      36 allocs/op
-PASS
-ok  	github.com/jfraeys/fetch_ml/tests/benchmarks	28.641s</pre>
-</body>
-</html>
diff --git a/.local-artifacts/run_20251204_231459/benchmark_results.txt b/.local-artifacts/run_20251204_231459/benchmark_results.txt
deleted file mode 100644
index 3d855ec..0000000
--- a/.local-artifacts/run_20251204_231459/benchmark_results.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-goos: darwin
-goarch: arm64
-pkg: github.com/jfraeys/fetch_ml/tests/benchmarks
-cpu: Apple M2 Ultra
-BenchmarkAPIServerCreateJobSimple-24    	   28129	     45677 ns/op	   13532 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	59903404	        19.48 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    105817 ns/op	   26610 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	    8654	    545199 ns/op	   18285 B/op	     132 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     904	   1350040 ns/op	    6043 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     924	   1332526 ns/op	    6228 B/op	      72 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     952	   1339113 ns/op	    6724 B/op	      75 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      45	  26355390 ns/op	  657327 B/op	   12351 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	      92	  12034762 ns/op	  794688 B/op	    6254 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     351	   3763459 ns/op	 1129490 B/op	    1375 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      37	  30668937 ns/op	 1112708 B/op	   12626 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      56	  26930825 ns/op	  615839 B/op	   17885 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   12364	    102242 ns/op	    2935 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	23809105	        50.50 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   18494	     65564 ns/op	    1285 B/op	      36 allocs/op
-PASS
-ok  	github.com/jfraeys/fetch_ml/tests/benchmarks	27.143s
diff --git a/.local-artifacts/run_20251204_231459/clean_benchmarks.txt b/.local-artifacts/run_20251204_231459/clean_benchmarks.txt
deleted file mode 100644
index 0e12017..0000000
--- a/.local-artifacts/run_20251204_231459/clean_benchmarks.txt
+++ /dev/null
@@ -1,15 +0,0 @@
-BenchmarkAPIServerCreateJobSimple-24    	   28129	     45677 ns/op	   13532 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	59903404	        19.48 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    105817 ns/op	   26610 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	    8654	    545199 ns/op	   18285 B/op	     132 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     904	   1350040 ns/op	    6043 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     924	   1332526 ns/op	    6228 B/op	      72 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     952	   1339113 ns/op	    6724 B/op	      75 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      45	  26355390 ns/op	  657327 B/op	   12351 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	      92	  12034762 ns/op	  794688 B/op	    6254 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     351	   3763459 ns/op	 1129490 B/op	    1375 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      37	  30668937 ns/op	 1112708 B/op	   12626 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      56	  26930825 ns/op	  615839 B/op	   17885 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   12364	    102242 ns/op	    2935 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	23809105	        50.50 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   18494	     65564 ns/op	    1285 B/op	      36 allocs/op
diff --git a/.local-artifacts/run_20251204_231459/prometheus_metrics.txt b/.local-artifacts/run_20251204_231459/prometheus_metrics.txt
deleted file mode 100644
index e91b32d..0000000
--- a/.local-artifacts/run_20251204_231459/prometheus_metrics.txt
+++ /dev/null
@@ -1,51 +0,0 @@
-# HELP benchmark_time_per_op Time per operation in nanoseconds
-# TYPE benchmark_time_per_op gauge
-# HELP benchmark_memory_per_op Memory per operation in bytes
-# TYPE benchmark_memory_per_op gauge
-# HELP benchmark_allocs_per_op Allocations per operation
-# TYPE benchmark_allocs_per_op gauge
-benchmark_time_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} 45677
-benchmark_memory_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} 13532
-benchmark_time_per_op{benchmark="BenchmarkMetricsCollection"} 19.48
-benchmark_memory_per_op{benchmark="BenchmarkMetricsCollection"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMetricsCollection"} 0
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} 105817
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} 26610
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} 545199
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} 18285
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} 1350040
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} 6043
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} 1332526
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} 6228
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} 1339113
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} 6724
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} 26355390
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} 657327
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} 12034762
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} 794688
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} 3763459
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} 1129490
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} 30668937
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} 1112708
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} 26930825
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} 615839
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} 102242
-benchmark_memory_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} 2935
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} 50.50
-benchmark_memory_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} 16
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} 65564
-benchmark_memory_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} 1285
diff --git a/.local-artifacts/run_20251204_231459/report.html b/.local-artifacts/run_20251204_231459/report.html
deleted file mode 100644
index 9801c8d..0000000
--- a/.local-artifacts/run_20251204_231459/report.html
+++ /dev/null
@@ -1,141 +0,0 @@
-<!DOCTYPE html>
-<html>
-<head>
-    <title>Benchmark Report - 20251204_231459</title>
-    <style>
-        body { font-family: Arial, sans-serif; margin: 20px; }
-        table { border-collapse: collapse; width: 100%; }
-        th, td { border: 1px solid #ddd; padding: 8px; text-align: left; }
-        th { background-color: #f2f2f2; }
-        .metric { font-family: monospace; }
-    </style>
-</head>
-<body>
-    <h1>Benchmark Report</h1>
-    <p><strong>Run ID:</strong> 20251204_231459</p>
-    <p><strong>Date:</strong> Thu Dec  4 18:15:28 EST 2025</p>
-    
-    <h2>Results</h2>
-    <table>
-        <tr>
-            <th>Benchmark</th>
-            <th>Time (ns/op)</th>
-            <th>Memory (B/op)</th>
-            <th>Allocs (allocs/op)</th>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkAPIServerCreateJobSimple-24</td>
-            <td>45677</td>
-            <td>ns/op</td>
-            <td>13532</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMetricsCollection-24</td>
-            <td>19.48</td>
-            <td>ns/op</td>
-            <td>0</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-1-24</td>
-            <td>105817</td>
-            <td>ns/op</td>
-            <td>26610</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-5-24</td>
-            <td>545199</td>
-            <td>ns/op</td>
-            <td>18285</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-10-24</td>
-            <td>1350040</td>
-            <td>ns/op</td>
-            <td>6043</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-25-24</td>
-            <td>1332526</td>
-            <td>ns/op</td>
-            <td>6228</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-50-24</td>
-            <td>1339113</td>
-            <td>ns/op</td>
-            <td>6724</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/SmallExperiment-24</td>
-            <td>26355390</td>
-            <td>ns/op</td>
-            <td>657327</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/MediumExperiment-24</td>
-            <td>12034762</td>
-            <td>ns/op</td>
-            <td>794688</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/LargeExperiment-24</td>
-            <td>3763459</td>
-            <td>ns/op</td>
-            <td>1129490</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/ConcurrentExperiments-24</td>
-            <td>30668937</td>
-            <td>ns/op</td>
-            <td>1112708</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/ExperimentMetrics-24</td>
-            <td>26930825</td>
-            <td>ns/op</td>
-            <td>615839</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetCreation-24</td>
-            <td>102242</td>
-            <td>ns/op</td>
-            <td>2935</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetRetrieval-24</td>
-            <td>50.50</td>
-            <td>ns/op</td>
-            <td>16</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetUpdate-24</td>
-            <td>65564</td>
-            <td>ns/op</td>
-            <td>1285</td>
-        </tr>
-    </table>
-    
-    <h2>Raw Output</h2>
-    <pre>goos: darwin
-goarch: arm64
-pkg: github.com/jfraeys/fetch_ml/tests/benchmarks
-cpu: Apple M2 Ultra
-BenchmarkAPIServerCreateJobSimple-24    	   28129	     45677 ns/op	   13532 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	59903404	        19.48 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    105817 ns/op	   26610 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	    8654	    545199 ns/op	   18285 B/op	     132 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     904	   1350040 ns/op	    6043 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     924	   1332526 ns/op	    6228 B/op	      72 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     952	   1339113 ns/op	    6724 B/op	      75 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      45	  26355390 ns/op	  657327 B/op	   12351 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	      92	  12034762 ns/op	  794688 B/op	    6254 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     351	   3763459 ns/op	 1129490 B/op	    1375 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      37	  30668937 ns/op	 1112708 B/op	   12626 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      56	  26930825 ns/op	  615839 B/op	   17885 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   12364	    102242 ns/op	    2935 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	23809105	        50.50 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   18494	     65564 ns/op	    1285 B/op	      36 allocs/op
-PASS
-ok  	github.com/jfraeys/fetch_ml/tests/benchmarks	27.143s</pre>
-</body>
-</html>
diff --git a/.local-artifacts/run_20251204_231634/benchmark_results.txt b/.local-artifacts/run_20251204_231634/benchmark_results.txt
deleted file mode 100644
index 32fe643..0000000
--- a/.local-artifacts/run_20251204_231634/benchmark_results.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-goos: darwin
-goarch: arm64
-pkg: github.com/jfraeys/fetch_ml/tests/benchmarks
-cpu: Apple M2 Ultra
-BenchmarkAPIServerCreateJobSimple-24    	   26200	     44608 ns/op	   13514 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	58956229	        19.88 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    108040 ns/op	   26965 B/op	     163 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	   10000	    657977 ns/op	   16658 B/op	     123 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     843	   1342869 ns/op	    6078 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     902	   1356405 ns/op	    6555 B/op	      73 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     907	   1341416 ns/op	    6429 B/op	      74 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      39	  26197300 ns/op	  657330 B/op	   12352 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	     100	  12172133 ns/op	  794610 B/op	    6253 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     348	   3686597 ns/op	 1129573 B/op	    1375 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      33	  33467878 ns/op	 1111544 B/op	   12626 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      57	  27330560 ns/op	  615815 B/op	   17885 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   12249	     97669 ns/op	    2934 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	24545986	        50.01 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   18687	     65891 ns/op	    1285 B/op	      36 allocs/op
-PASS
-ok  	github.com/jfraeys/fetch_ml/tests/benchmarks	28.732s
diff --git a/.local-artifacts/run_20251204_231634/clean_benchmarks.txt b/.local-artifacts/run_20251204_231634/clean_benchmarks.txt
deleted file mode 100644
index 0cabf2d..0000000
--- a/.local-artifacts/run_20251204_231634/clean_benchmarks.txt
+++ /dev/null
@@ -1,15 +0,0 @@
-BenchmarkAPIServerCreateJobSimple-24    	   26200	     44608 ns/op	   13514 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	58956229	        19.88 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    108040 ns/op	   26965 B/op	     163 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	   10000	    657977 ns/op	   16658 B/op	     123 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     843	   1342869 ns/op	    6078 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     902	   1356405 ns/op	    6555 B/op	      73 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     907	   1341416 ns/op	    6429 B/op	      74 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      39	  26197300 ns/op	  657330 B/op	   12352 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	     100	  12172133 ns/op	  794610 B/op	    6253 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     348	   3686597 ns/op	 1129573 B/op	    1375 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      33	  33467878 ns/op	 1111544 B/op	   12626 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      57	  27330560 ns/op	  615815 B/op	   17885 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   12249	     97669 ns/op	    2934 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	24545986	        50.01 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   18687	     65891 ns/op	    1285 B/op	      36 allocs/op
diff --git a/.local-artifacts/run_20251204_231634/prometheus_metrics.txt b/.local-artifacts/run_20251204_231634/prometheus_metrics.txt
deleted file mode 100644
index 061c879..0000000
--- a/.local-artifacts/run_20251204_231634/prometheus_metrics.txt
+++ /dev/null
@@ -1,51 +0,0 @@
-# HELP benchmark_time_per_op Time per operation in nanoseconds
-# TYPE benchmark_time_per_op gauge
-# HELP benchmark_memory_per_op Memory per operation in bytes
-# TYPE benchmark_memory_per_op gauge
-# HELP benchmark_allocs_per_op Allocations per operation
-# TYPE benchmark_allocs_per_op gauge
-benchmark_time_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} 44608
-benchmark_memory_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} 13514
-benchmark_time_per_op{benchmark="BenchmarkMetricsCollection"} 19.88
-benchmark_memory_per_op{benchmark="BenchmarkMetricsCollection"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMetricsCollection"} 0
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} 108040
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} 26965
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} 657977
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} 16658
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} 1342869
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} 6078
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} 1356405
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} 6555
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} 1341416
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} 6429
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} 26197300
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} 657330
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} 12172133
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} 794610
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} 3686597
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} 1129573
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} 33467878
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} 1111544
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} 27330560
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} 615815
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} 97669
-benchmark_memory_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} 2934
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} 50.01
-benchmark_memory_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} 16
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} 65891
-benchmark_memory_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} 1285
diff --git a/.local-artifacts/run_20251204_231712/benchmark_results.txt b/.local-artifacts/run_20251204_231712/benchmark_results.txt
deleted file mode 100644
index 0759753..0000000
--- a/.local-artifacts/run_20251204_231712/benchmark_results.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-goos: darwin
-goarch: arm64
-pkg: github.com/jfraeys/fetch_ml/tests/benchmarks
-cpu: Apple M2 Ultra
-BenchmarkAPIServerCreateJobSimple-24    	   27906	     45877 ns/op	   13520 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	59125434	        19.91 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    106563 ns/op	   26651 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	    9916	    580762 ns/op	   16774 B/op	     124 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     902	   1361628 ns/op	    6050 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     913	   1341660 ns/op	    6645 B/op	      73 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     902	   1339436 ns/op	    6130 B/op	      73 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      42	  26144707 ns/op	  657412 B/op	   12352 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	      99	  12045172 ns/op	  794945 B/op	    6255 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     350	   3655986 ns/op	 1129633 B/op	    1375 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      30	  37392029 ns/op	 1111096 B/op	   12623 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      52	  26943573 ns/op	  615802 B/op	   17883 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   12285	    101658 ns/op	    2934 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	24175867	        50.53 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   18481	     65640 ns/op	    1285 B/op	      36 allocs/op
-PASS
-ok  	github.com/jfraeys/fetch_ml/tests/benchmarks	29.026s
diff --git a/.local-artifacts/run_20251204_231712/clean_benchmarks.txt b/.local-artifacts/run_20251204_231712/clean_benchmarks.txt
deleted file mode 100644
index 7d0839d..0000000
--- a/.local-artifacts/run_20251204_231712/clean_benchmarks.txt
+++ /dev/null
@@ -1,15 +0,0 @@
-BenchmarkAPIServerCreateJobSimple-24    	   27906	     45877 ns/op	   13520 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	59125434	        19.91 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    106563 ns/op	   26651 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	    9916	    580762 ns/op	   16774 B/op	     124 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     902	   1361628 ns/op	    6050 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     913	   1341660 ns/op	    6645 B/op	      73 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     902	   1339436 ns/op	    6130 B/op	      73 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      42	  26144707 ns/op	  657412 B/op	   12352 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	      99	  12045172 ns/op	  794945 B/op	    6255 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     350	   3655986 ns/op	 1129633 B/op	    1375 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      30	  37392029 ns/op	 1111096 B/op	   12623 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      52	  26943573 ns/op	  615802 B/op	   17883 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   12285	    101658 ns/op	    2934 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	24175867	        50.53 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   18481	     65640 ns/op	    1285 B/op	      36 allocs/op
diff --git a/.local-artifacts/run_20251204_231712/prometheus_metrics.txt b/.local-artifacts/run_20251204_231712/prometheus_metrics.txt
deleted file mode 100644
index c140131..0000000
--- a/.local-artifacts/run_20251204_231712/prometheus_metrics.txt
+++ /dev/null
@@ -1,51 +0,0 @@
-# HELP benchmark_time_per_op Time per operation in nanoseconds
-# TYPE benchmark_time_per_op gauge
-# HELP benchmark_memory_per_op Memory per operation in bytes
-# TYPE benchmark_memory_per_op gauge
-# HELP benchmark_allocs_per_op Allocations per operation
-# TYPE benchmark_allocs_per_op gauge
-benchmark_time_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} 45877
-benchmark_memory_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} 13520
-benchmark_time_per_op{benchmark="BenchmarkMetricsCollection"} 19.91
-benchmark_memory_per_op{benchmark="BenchmarkMetricsCollection"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMetricsCollection"} 0
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} 106563
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} 26651
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} 580762
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} 16774
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} 1361628
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} 6050
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} 1341660
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} 6645
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} 1339436
-benchmark_memory_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} 6130
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} 26144707
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} 657412
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} 12045172
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} 794945
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} 3655986
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} 1129633
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} 37392029
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} 1111096
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} 26943573
-benchmark_memory_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} 615802
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} 101658
-benchmark_memory_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} 2934
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} 50.53
-benchmark_memory_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} 16
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} 65640
-benchmark_memory_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} ns/op
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} 1285
diff --git a/.local-artifacts/run_20251204_231712/report.html b/.local-artifacts/run_20251204_231712/report.html
deleted file mode 100644
index a2a0363..0000000
--- a/.local-artifacts/run_20251204_231712/report.html
+++ /dev/null
@@ -1,141 +0,0 @@
-<!DOCTYPE html>
-<html>
-<head>
-    <title>Benchmark Report - 20251204_231712</title>
-    <style>
-        body { font-family: Arial, sans-serif; margin: 20px; }
-        table { border-collapse: collapse; width: 100%; }
-        th, td { border: 1px solid #ddd; padding: 8px; text-align: left; }
-        th { background-color: #f2f2f2; }
-        .metric { font-family: monospace; }
-    </style>
-</head>
-<body>
-    <h1>Benchmark Report</h1>
-    <p><strong>Run ID:</strong> 20251204_231712</p>
-    <p><strong>Date:</strong> Thu Dec  4 18:17:42 EST 2025</p>
-    
-    <h2>Results</h2>
-    <table>
-        <tr>
-            <th>Benchmark</th>
-            <th>Time (ns/op)</th>
-            <th>Memory (B/op)</th>
-            <th>Allocs (allocs/op)</th>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkAPIServerCreateJobSimple-24</td>
-            <td>45877</td>
-            <td>ns/op</td>
-            <td>13520</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMetricsCollection-24</td>
-            <td>19.91</td>
-            <td>ns/op</td>
-            <td>0</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-1-24</td>
-            <td>106563</td>
-            <td>ns/op</td>
-            <td>26651</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-5-24</td>
-            <td>580762</td>
-            <td>ns/op</td>
-            <td>16774</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-10-24</td>
-            <td>1361628</td>
-            <td>ns/op</td>
-            <td>6050</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-25-24</td>
-            <td>1341660</td>
-            <td>ns/op</td>
-            <td>6645</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-50-24</td>
-            <td>1339436</td>
-            <td>ns/op</td>
-            <td>6130</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/SmallExperiment-24</td>
-            <td>26144707</td>
-            <td>ns/op</td>
-            <td>657412</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/MediumExperiment-24</td>
-            <td>12045172</td>
-            <td>ns/op</td>
-            <td>794945</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/LargeExperiment-24</td>
-            <td>3655986</td>
-            <td>ns/op</td>
-            <td>1129633</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/ConcurrentExperiments-24</td>
-            <td>37392029</td>
-            <td>ns/op</td>
-            <td>1111096</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/ExperimentMetrics-24</td>
-            <td>26943573</td>
-            <td>ns/op</td>
-            <td>615802</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetCreation-24</td>
-            <td>101658</td>
-            <td>ns/op</td>
-            <td>2934</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetRetrieval-24</td>
-            <td>50.53</td>
-            <td>ns/op</td>
-            <td>16</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetUpdate-24</td>
-            <td>65640</td>
-            <td>ns/op</td>
-            <td>1285</td>
-        </tr>
-    </table>
-    
-    <h2>Raw Output</h2>
-    <pre>goos: darwin
-goarch: arm64
-pkg: github.com/jfraeys/fetch_ml/tests/benchmarks
-cpu: Apple M2 Ultra
-BenchmarkAPIServerCreateJobSimple-24    	   27906	     45877 ns/op	   13520 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	59125434	        19.91 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    106563 ns/op	   26651 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	    9916	    580762 ns/op	   16774 B/op	     124 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     902	   1361628 ns/op	    6050 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     913	   1341660 ns/op	    6645 B/op	      73 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     902	   1339436 ns/op	    6130 B/op	      73 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      42	  26144707 ns/op	  657412 B/op	   12352 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	      99	  12045172 ns/op	  794945 B/op	    6255 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     350	   3655986 ns/op	 1129633 B/op	    1375 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      30	  37392029 ns/op	 1111096 B/op	   12623 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      52	  26943573 ns/op	  615802 B/op	   17883 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   12285	    101658 ns/op	    2934 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	24175867	        50.53 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   18481	     65640 ns/op	    1285 B/op	      36 allocs/op
-PASS
-ok  	github.com/jfraeys/fetch_ml/tests/benchmarks	29.026s</pre>
-</body>
-</html>
diff --git a/.local-artifacts/run_20251204_231833/benchmark_results.txt b/.local-artifacts/run_20251204_231833/benchmark_results.txt
deleted file mode 100644
index cb79385..0000000
--- a/.local-artifacts/run_20251204_231833/benchmark_results.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-goos: darwin
-goarch: arm64
-pkg: github.com/jfraeys/fetch_ml/tests/benchmarks
-cpu: Apple M2 Ultra
-BenchmarkAPIServerCreateJobSimple-24    	   27950	     44615 ns/op	   13510 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	61569640	        19.81 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    104975 ns/op	   26775 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	    9744	    616978 ns/op	   16959 B/op	     125 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     921	   1342897 ns/op	    6123 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     916	   1355236 ns/op	    6286 B/op	      73 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     930	   1326230 ns/op	    6997 B/op	      76 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      44	  26734717 ns/op	  657047 B/op	   12351 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	      93	  12165317 ns/op	  794462 B/op	    6254 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     364	   3637957 ns/op	 1128897 B/op	    1374 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      33	  31061085 ns/op	 1114816 B/op	   12631 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      54	  26862161 ns/op	  615718 B/op	   17884 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   12193	    102081 ns/op	    2933 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	19180039	        52.64 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   18472	     65401 ns/op	    1285 B/op	      36 allocs/op
-PASS
-ok  	github.com/jfraeys/fetch_ml/tests/benchmarks	27.261s
diff --git a/.local-artifacts/run_20251204_231833/clean_benchmarks.txt b/.local-artifacts/run_20251204_231833/clean_benchmarks.txt
deleted file mode 100644
index 5f4e611..0000000
--- a/.local-artifacts/run_20251204_231833/clean_benchmarks.txt
+++ /dev/null
@@ -1,15 +0,0 @@
-BenchmarkAPIServerCreateJobSimple-24    	   27950	     44615 ns/op	   13510 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	61569640	        19.81 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    104975 ns/op	   26775 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	    9744	    616978 ns/op	   16959 B/op	     125 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     921	   1342897 ns/op	    6123 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     916	   1355236 ns/op	    6286 B/op	      73 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     930	   1326230 ns/op	    6997 B/op	      76 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      44	  26734717 ns/op	  657047 B/op	   12351 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	      93	  12165317 ns/op	  794462 B/op	    6254 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     364	   3637957 ns/op	 1128897 B/op	    1374 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      33	  31061085 ns/op	 1114816 B/op	   12631 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      54	  26862161 ns/op	  615718 B/op	   17884 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   12193	    102081 ns/op	    2933 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	19180039	        52.64 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   18472	     65401 ns/op	    1285 B/op	      36 allocs/op
diff --git a/.local-artifacts/run_20251204_231833/prometheus_metrics.txt b/.local-artifacts/run_20251204_231833/prometheus_metrics.txt
deleted file mode 100644
index 49516e7..0000000
--- a/.local-artifacts/run_20251204_231833/prometheus_metrics.txt
+++ /dev/null
@@ -1,36 +0,0 @@
-# HELP benchmark_time_per_op Time per operation in nanoseconds
-# TYPE benchmark_time_per_op gauge
-# HELP benchmark_memory_per_op Memory per operation in bytes
-# TYPE benchmark_memory_per_op gauge
-# HELP benchmark_allocs_per_op Allocations per operation
-# TYPE benchmark_allocs_per_op gauge
-benchmark_time_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} 44615
-benchmark_allocs_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} 13510
-benchmark_time_per_op{benchmark="BenchmarkMetricsCollection"} 19.81
-benchmark_allocs_per_op{benchmark="BenchmarkMetricsCollection"} 0
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} 104975
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} 26775
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} 616978
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} 16959
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} 1342897
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} 6123
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} 1355236
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} 6286
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} 1326230
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} 6997
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} 26734717
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} 657047
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} 12165317
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} 794462
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} 3637957
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} 1128897
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} 31061085
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} 1114816
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} 26862161
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} 615718
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} 102081
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} 2933
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} 52.64
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} 16
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} 65401
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} 1285
diff --git a/.local-artifacts/run_20251204_231833/report.html b/.local-artifacts/run_20251204_231833/report.html
deleted file mode 100644
index 1376941..0000000
--- a/.local-artifacts/run_20251204_231833/report.html
+++ /dev/null
@@ -1,141 +0,0 @@
-<!DOCTYPE html>
-<html>
-<head>
-    <title>Benchmark Report - 20251204_231833</title>
-    <style>
-        body { font-family: Arial, sans-serif; margin: 20px; }
-        table { border-collapse: collapse; width: 100%; }
-        th, td { border: 1px solid #ddd; padding: 8px; text-align: left; }
-        th { background-color: #f2f2f2; }
-        .metric { font-family: monospace; }
-    </style>
-</head>
-<body>
-    <h1>Benchmark Report</h1>
-    <p><strong>Run ID:</strong> 20251204_231833</p>
-    <p><strong>Date:</strong> Thu Dec  4 18:19:01 EST 2025</p>
-    
-    <h2>Results</h2>
-    <table>
-        <tr>
-            <th>Benchmark</th>
-            <th>Time (ns/op)</th>
-            <th>Memory (B/op)</th>
-            <th>Allocs (allocs/op)</th>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkAPIServerCreateJobSimple-24</td>
-            <td>44615</td>
-            <td>ns/op</td>
-            <td>13510</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMetricsCollection-24</td>
-            <td>19.81</td>
-            <td>ns/op</td>
-            <td>0</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-1-24</td>
-            <td>104975</td>
-            <td>ns/op</td>
-            <td>26775</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-5-24</td>
-            <td>616978</td>
-            <td>ns/op</td>
-            <td>16959</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-10-24</td>
-            <td>1342897</td>
-            <td>ns/op</td>
-            <td>6123</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-25-24</td>
-            <td>1355236</td>
-            <td>ns/op</td>
-            <td>6286</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-50-24</td>
-            <td>1326230</td>
-            <td>ns/op</td>
-            <td>6997</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/SmallExperiment-24</td>
-            <td>26734717</td>
-            <td>ns/op</td>
-            <td>657047</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/MediumExperiment-24</td>
-            <td>12165317</td>
-            <td>ns/op</td>
-            <td>794462</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/LargeExperiment-24</td>
-            <td>3637957</td>
-            <td>ns/op</td>
-            <td>1128897</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/ConcurrentExperiments-24</td>
-            <td>31061085</td>
-            <td>ns/op</td>
-            <td>1114816</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/ExperimentMetrics-24</td>
-            <td>26862161</td>
-            <td>ns/op</td>
-            <td>615718</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetCreation-24</td>
-            <td>102081</td>
-            <td>ns/op</td>
-            <td>2933</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetRetrieval-24</td>
-            <td>52.64</td>
-            <td>ns/op</td>
-            <td>16</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetUpdate-24</td>
-            <td>65401</td>
-            <td>ns/op</td>
-            <td>1285</td>
-        </tr>
-    </table>
-    
-    <h2>Raw Output</h2>
-    <pre>goos: darwin
-goarch: arm64
-pkg: github.com/jfraeys/fetch_ml/tests/benchmarks
-cpu: Apple M2 Ultra
-BenchmarkAPIServerCreateJobSimple-24    	   27950	     44615 ns/op	   13510 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	61569640	        19.81 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    104975 ns/op	   26775 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	    9744	    616978 ns/op	   16959 B/op	     125 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     921	   1342897 ns/op	    6123 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     916	   1355236 ns/op	    6286 B/op	      73 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     930	   1326230 ns/op	    6997 B/op	      76 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      44	  26734717 ns/op	  657047 B/op	   12351 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	      93	  12165317 ns/op	  794462 B/op	    6254 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     364	   3637957 ns/op	 1128897 B/op	    1374 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      33	  31061085 ns/op	 1114816 B/op	   12631 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      54	  26862161 ns/op	  615718 B/op	   17884 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   12193	    102081 ns/op	    2933 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	19180039	        52.64 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   18472	     65401 ns/op	    1285 B/op	      36 allocs/op
-PASS
-ok  	github.com/jfraeys/fetch_ml/tests/benchmarks	27.261s</pre>
-</body>
-</html>
diff --git a/.local-artifacts/run_20251204_232656/benchmark_results.txt b/.local-artifacts/run_20251204_232656/benchmark_results.txt
deleted file mode 100644
index 805d2cb..0000000
--- a/.local-artifacts/run_20251204_232656/benchmark_results.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-goos: darwin
-goarch: arm64
-pkg: github.com/jfraeys/fetch_ml/tests/benchmarks
-cpu: Apple M2 Ultra
-BenchmarkAPIServerCreateJobSimple-24    	   27296	     43913 ns/op	   13526 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	61271120	        19.34 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    105096 ns/op	   26660 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	   10000	    646391 ns/op	   16738 B/op	     124 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     872	   1369525 ns/op	    6036 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     904	   1394439 ns/op	    6546 B/op	      73 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     889	   1373567 ns/op	    6347 B/op	      74 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      40	  26726470 ns/op	  657367 B/op	   12352 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	      97	  12430890 ns/op	  794823 B/op	    6254 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     346	   3863256 ns/op	 1129599 B/op	    1375 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      36	  32534372 ns/op	 1115220 B/op	   12637 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      52	  26962389 ns/op	  615818 B/op	   17884 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   12075	    100813 ns/op	    2933 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	23898721	        50.28 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   18692	     63463 ns/op	    1285 B/op	      36 allocs/op
-PASS
-ok  	github.com/jfraeys/fetch_ml/tests/benchmarks	28.692s
diff --git a/.local-artifacts/run_20251204_232656/clean_benchmarks.txt b/.local-artifacts/run_20251204_232656/clean_benchmarks.txt
deleted file mode 100644
index 0be38d4..0000000
--- a/.local-artifacts/run_20251204_232656/clean_benchmarks.txt
+++ /dev/null
@@ -1,15 +0,0 @@
-BenchmarkAPIServerCreateJobSimple-24    	   27296	     43913 ns/op	   13526 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	61271120	        19.34 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    105096 ns/op	   26660 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	   10000	    646391 ns/op	   16738 B/op	     124 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     872	   1369525 ns/op	    6036 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     904	   1394439 ns/op	    6546 B/op	      73 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     889	   1373567 ns/op	    6347 B/op	      74 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      40	  26726470 ns/op	  657367 B/op	   12352 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	      97	  12430890 ns/op	  794823 B/op	    6254 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     346	   3863256 ns/op	 1129599 B/op	    1375 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      36	  32534372 ns/op	 1115220 B/op	   12637 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      52	  26962389 ns/op	  615818 B/op	   17884 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   12075	    100813 ns/op	    2933 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	23898721	        50.28 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   18692	     63463 ns/op	    1285 B/op	      36 allocs/op
diff --git a/.local-artifacts/run_20251204_232656/prometheus_metrics.txt b/.local-artifacts/run_20251204_232656/prometheus_metrics.txt
deleted file mode 100644
index 45e7b2c..0000000
--- a/.local-artifacts/run_20251204_232656/prometheus_metrics.txt
+++ /dev/null
@@ -1,36 +0,0 @@
-# HELP benchmark_time_per_op Time per operation in nanoseconds
-# TYPE benchmark_time_per_op gauge
-# HELP benchmark_memory_per_op Memory per operation in bytes
-# TYPE benchmark_memory_per_op gauge
-# HELP benchmark_allocs_per_op Allocations per operation
-# TYPE benchmark_allocs_per_op gauge
-benchmark_time_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} 43913
-benchmark_allocs_per_op{benchmark="BenchmarkAPIServerCreateJobSimple"} 13526
-benchmark_time_per_op{benchmark="BenchmarkMetricsCollection"} 19.34
-benchmark_allocs_per_op{benchmark="BenchmarkMetricsCollection"} 0
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} 105096
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_1"} 26660
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} 646391
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_5"} 16738
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} 1369525
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_10"} 6036
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} 1394439
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_25"} 6546
-benchmark_time_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} 1373567
-benchmark_allocs_per_op{benchmark="BenchmarkConcurrentRequests_Concurrency_50"} 6347
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} 26726470
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_SmallExperiment"} 657367
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} 12430890
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_MediumExperiment"} 794823
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} 3863256
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_LargeExperiment"} 1129599
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} 32534372
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_ConcurrentExperiments"} 1115220
-benchmark_time_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} 26962389
-benchmark_allocs_per_op{benchmark="BenchmarkMLExperimentExecution_ExperimentMetrics"} 615818
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} 100813
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetCreation"} 2933
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} 50.28
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetRetrieval"} 16
-benchmark_time_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} 63463
-benchmark_allocs_per_op{benchmark="BenchmarkDatasetOperations_DatasetUpdate"} 1285
diff --git a/.local-artifacts/run_20251204_232656/report.html b/.local-artifacts/run_20251204_232656/report.html
deleted file mode 100644
index 4a8fd49..0000000
--- a/.local-artifacts/run_20251204_232656/report.html
+++ /dev/null
@@ -1,141 +0,0 @@
-<!DOCTYPE html>
-<html>
-<head>
-    <title>Benchmark Report - 20251204_232656</title>
-    <style>
-        body { font-family: Arial, sans-serif; margin: 20px; }
-        table { border-collapse: collapse; width: 100%; }
-        th, td { border: 1px solid #ddd; padding: 8px; text-align: left; }
-        th { background-color: #f2f2f2; }
-        .metric { font-family: monospace; }
-    </style>
-</head>
-<body>
-    <h1>Benchmark Report</h1>
-    <p><strong>Run ID:</strong> 20251204_232656</p>
-    <p><strong>Date:</strong> Thu Dec  4 18:27:25 EST 2025</p>
-    
-    <h2>Results</h2>
-    <table>
-        <tr>
-            <th>Benchmark</th>
-            <th>Time (ns/op)</th>
-            <th>Memory (B/op)</th>
-            <th>Allocs (allocs/op)</th>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkAPIServerCreateJobSimple-24</td>
-            <td>43913</td>
-            <td>ns/op</td>
-            <td>13526</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMetricsCollection-24</td>
-            <td>19.34</td>
-            <td>ns/op</td>
-            <td>0</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-1-24</td>
-            <td>105096</td>
-            <td>ns/op</td>
-            <td>26660</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-5-24</td>
-            <td>646391</td>
-            <td>ns/op</td>
-            <td>16738</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-10-24</td>
-            <td>1369525</td>
-            <td>ns/op</td>
-            <td>6036</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-25-24</td>
-            <td>1394439</td>
-            <td>ns/op</td>
-            <td>6546</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkConcurrentRequests/Concurrency-50-24</td>
-            <td>1373567</td>
-            <td>ns/op</td>
-            <td>6347</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/SmallExperiment-24</td>
-            <td>26726470</td>
-            <td>ns/op</td>
-            <td>657367</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/MediumExperiment-24</td>
-            <td>12430890</td>
-            <td>ns/op</td>
-            <td>794823</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/LargeExperiment-24</td>
-            <td>3863256</td>
-            <td>ns/op</td>
-            <td>1129599</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/ConcurrentExperiments-24</td>
-            <td>32534372</td>
-            <td>ns/op</td>
-            <td>1115220</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkMLExperimentExecution/ExperimentMetrics-24</td>
-            <td>26962389</td>
-            <td>ns/op</td>
-            <td>615818</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetCreation-24</td>
-            <td>100813</td>
-            <td>ns/op</td>
-            <td>2933</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetRetrieval-24</td>
-            <td>50.28</td>
-            <td>ns/op</td>
-            <td>16</td>
-        </tr>
-        <tr>
-            <td class="metric">BenchmarkDatasetOperations/DatasetUpdate-24</td>
-            <td>63463</td>
-            <td>ns/op</td>
-            <td>1285</td>
-        </tr>
-    </table>
-    
-    <h2>Raw Output</h2>
-    <pre>goos: darwin
-goarch: arm64
-pkg: github.com/jfraeys/fetch_ml/tests/benchmarks
-cpu: Apple M2 Ultra
-BenchmarkAPIServerCreateJobSimple-24    	   27296	     43913 ns/op	   13526 B/op	      98 allocs/op
-BenchmarkMetricsCollection-24           	61271120	        19.34 ns/op	       0 B/op	       0 allocs/op
-BenchmarkConcurrentRequests/Concurrency-1-24         	   10000	    105096 ns/op	   26660 B/op	     162 allocs/op
-BenchmarkConcurrentRequests/Concurrency-5-24         	   10000	    646391 ns/op	   16738 B/op	     124 allocs/op
-BenchmarkConcurrentRequests/Concurrency-10-24        	     872	   1369525 ns/op	    6036 B/op	      71 allocs/op
-BenchmarkConcurrentRequests/Concurrency-25-24        	     904	   1394439 ns/op	    6546 B/op	      73 allocs/op
-BenchmarkConcurrentRequests/Concurrency-50-24        	     889	   1373567 ns/op	    6347 B/op	      74 allocs/op
-BenchmarkMLExperimentExecution/SmallExperiment-24    	      40	  26726470 ns/op	  657367 B/op	   12352 allocs/op
-BenchmarkMLExperimentExecution/MediumExperiment-24   	      97	  12430890 ns/op	  794823 B/op	    6254 allocs/op
-BenchmarkMLExperimentExecution/LargeExperiment-24    	     346	   3863256 ns/op	 1129599 B/op	    1375 allocs/op
-BenchmarkMLExperimentExecution/ConcurrentExperiments-24         	      36	  32534372 ns/op	 1115220 B/op	   12637 allocs/op
-BenchmarkMLExperimentExecution/ExperimentMetrics-24             	      52	  26962389 ns/op	  615818 B/op	   17884 allocs/op
-BenchmarkDatasetOperations/DatasetCreation-24                   	   12075	    100813 ns/op	    2933 B/op	      75 allocs/op
-BenchmarkDatasetOperations/DatasetRetrieval-24                  	23898721	        50.28 ns/op	      16 B/op	       1 allocs/op
-BenchmarkDatasetOperations/DatasetUpdate-24                     	   18692	     63463 ns/op	    1285 B/op	      36 allocs/op
-PASS
-ok  	github.com/jfraeys/fetch_ml/tests/benchmarks	28.692s</pre>
-</body>
-</html>
diff --git a/.pylintrc b/.pylintrc
deleted file mode 100644
index dd3574c..0000000
--- a/.pylintrc
+++ /dev/null
@@ -1,307 +0,0 @@
-[MASTER]
-# Google Python Style Guide Configuration
-# Based on https://google.github.io/styleguide/pyguide.html
-
-# Files or directories to be skipped over when performing analysis.
-ignore=
-    .git,
-    __pycache__,
-    *.pyc,
-    .pytest_cache,
-    .mypy_cache,
-    .venv,
-    venv,
-    # ML experiment code - exclude from style checks
-    podman/workspace,
-    workspace,
-    tests/fixtures/examples,
-    tests/fixtures/podman,
-    results,
-    data,
-    logs,
-    secrets,
-    .agent
-
-# Regular expression matching files that should be skipped entirely.
-ignore-patterns=
-    ^\.#,
-    ^setup\.py$,
-    ^conftest\.py$
-
-# Add files or directories matching the regex patterns to the ignore list.
-ignore-paths=
-
-# Files or directories to be added to the list of ignored regular expressions.
-ignore-paths=
-
-# Pickle collected data for later comparisons.
-persistent=yes
-
-# Use multiple processes to speed up Pylint.
-jobs=1
-
-# List of plugins (as comma separated values of python module names) to load,
-# usually to register additional checkers.
-load-plugins=
-
-# Load all enabled extensions.
-load-all-plugins=no
-
-# Control the amount of potential astroid warnings (0, 1 or 2).
-unsafe-load-any-extension=no
-
-# A comma-separated list of package or module names from where C extensions may
-# be loaded. Extensions are loading into the active Python interpreter and may
-# run arbitrary code.
-extension-pkg-whitelist=
-
-[MESSAGES CONTROL]
-# Only show warnings with the listed confidence levels.
-confidence=
-
-# Disable the message, report, category or checker with the given id(s).
-disable=
-    # Google Style Guide allows some of these
-    missing-module-docstring,
-    missing-function-docstring,
-    too-many-locals,
-    too-many-arguments,
-    too-many-instance-attributes,
-    too-many-public-methods,
-    too-few-public-methods,
-    too-many-lines,
-    too-many-statements,
-    too-many-branches,
-    too-many-nested-blocks,
-    # Not relevant for ML projects
-    invalid-name,
-    C0114,  # missing-module-docstring
-    C0115,  # missing-class-docstring
-    C0116,  # missing-function-docstring
-    R0903,  # too-few-public-methods
-    R0902,  # too-many-instance-attributes
-    R0913,  # too-many-arguments
-    R0914,  # too-many-locals
-    R0915,  # too-many-statements
-    R0912,  # too-many-branches
-    R0911,  # too-many-return-statements
-    W0613,  # unused-argument (common in callbacks)
-
-# Enable the message, report, category or checker with the given id(s).
-enable=
-
-[REPORTS]
-# Set the output format.
-output-format=text
-
-# Tells whether to display a full report or only the messages.
-reports=no
-
-# Python expression which determines if a message should not be displayed.
-evaluation=
-
-# Template used to display messages.
-msg-template=
-
-[BASIC]
-# Good variable names which should always be accepted, separated by a comma.
-good-names=
-    i,j,k,ex,Run,_
-
-# Bad variable names which should always be refused.
-bad-names=
-    foo,bar,baz,toto,tutu,tata
-
-# List of builtins function names that should not be used.
-bad-functions=
-
-# Regular expression for correct variable names.
-variable-rgx=^[a-z_][a-z0-9_]{2,30}$
-
-# Regular expression for correct constant names.
-const-rgx=^(_?[A-Z][A-Z0-9_]{2,30}|__.*__)$
-
-# Regular expression for correct function names.
-function-rgx=^(?:(?P<camel_case>_?[A-Z][a-zA-Z0-9]{2,30})|(?P<snake_case>_?[a-z][a-z0-9_]{2,30}))$
-
-# Regular expression for correct class names.
-class-rgx=^_?[A-Z][a-zA-Z0-9]{2,30}$
-
-# Regular expression for correct attribute names.
-attr-rgx=^_{0,2}[a-z][a-z0-9_]{2,30}$
-
-# Regular expression for correct argument names.
-argument-rgx=^[a-z][a-z0-9_]{2,30}$
-
-# Regular expression for correct method resolution order names.
-method-rgx=^_{0,2}[a-z][a-z0-9_]{2,30}$
-
-# Regular expression which should only match function or class names that do
-# not require a docstring.
-no-docstring-rgx=^_
-
-# Minimum line length for functions/classes that require docstrings.
-docstring-min-length=-1
-
-[TYPECHECK]
-# List of decorators that produce context managers.
-contextmanager-decorators=contextlib.contextmanager
-
-# List of member names which should be excluded from the access member check.
-exclude-members=
-
-# List of qualified names (objects) which require a disable protection.
-generated-members=
-
-[MISCELLANEOUS]
-# List of note tags to take in consideration.
-notes=
-
-[VARIABLES]
-# Tells whether we should check for unused imports.
-init-import=no
-
-# A regular expression matching the name of dummy variables.
-dummy-variable-rgx=^_|dummy
-
-# List of variable names that should not be used.
-additional-builtins=
-
-# List of variables which are ignored for the undefined-variable check.
-ignored-classes=
-
-# List of members which are skipped from the member access check.
-ignored-modules=
-
-# List of deprecated symbols which should not be used.
-deprecated-modules=
-
-# List of symbols that can be safely accessed.
-allowed-redefined-builtins=
-
-[FORMAT]
-# Maximum number of characters on a single line.
-max-line-length=80
-
-# Regexp for a line that is allowed to be longer than the limit.
-long-line-regexp=^[\t ]*(# )?<?https?://\S+>?$
-
-# Allow the body of an if to be on the same line as the test.
-single-line-if-stmt=no
-
-# List of optional parameters for which we don't want to call a linting
-# function.
-single-line-class-stmt=no
-
-# Maximum number of characters on a single line, when there are no multiline
-# strings.
-max-line-length-sigil-fallback=80
-
-[SIMILARITIES]
-# Minimum lines number of a similarity.
-min-similarity-lines=4
-
-# Ignore comments when computing similarities.
-ignore-comments=yes
-
-# Ignore docstrings when computing similarities.
-ignore-docstrings=yes
-
-# Ignore imports when computing similarities.
-ignore-imports=no
-
-[LOGGING]
-# Logging modules to check that the string formatting arguments are in
-# logging function parameter format.
-logging-modules=logging
-
-[DESIGN]
-# Maximum number of arguments for function / method.
-max-args=5
-
-# Argument names that match this regular expression are ignored.
-ignored-argument-names=
-
-# Maximum number of locals for function / method body.
-max-locals=15
-
-# Maximum number of return statements for function / method body.
-max-returns=6
-
-# Maximum number of branch for function / method body.
-max-branches=12
-
-# Maximum number of statements in function / method body.
-max-statements=50
-
-# Maximum number of parents for a class.
-max-parents=7
-
-# Maximum number of attributes for a class.
-max-attributes=7
-
-# Minimum number of public methods for a class.
-min-public-methods=2
-
-# Maximum number of public methods for a class.
-max-public-methods=20
-
-# Maximum number of boolean expressions in a if statement.
-max-bool-expr=5
-
-[CLASSES]
-# List of method names used to declare (i.e. assign) instance attributes.
-defining-attr-methods=__init__,__new__,setUp
-
-# List of valid names for the first argument in a class method.
-valid-classmethod-first-arg=cls
-
-# List of valid names for the first argument in a metaclass class method.
-valid-metaclass-classmethod-first-arg=mcls
-
-# List of member names which should be excluded from the access member check.
-exclude-protected=_asdict,_fields,_replace,_source,_make
-
-[IMPORTS]
-# Deprecated modules which should not be used.
-deprecated-modules=
-
-# Create a graph of every module's dependencies.
-import-graph=
-
-# Create a graph of every (i.e. internal and external) dependencies in the
-# current file.
-ext-import-graph=
-
-# Create a graph of external dependencies in the current file.
-int-import-graph=
-
-# Force import order to match a specific order.
-import-order-style=google
-
-# Add files or directories to the blacklist.
-ignore-on-import-order=no
-
-# List of modules that can be imported at any level from the specified
-# application modules.
-known-third-party=
-
-# Analyse import fallback blocks.
-analyse-fallback-blocks=no
-
-[EXCEPTIONS]
-# Exceptions that will emit a warning when being caught.
-overgeneral-exceptions=Exception,BaseException
-
-# Exceptions that will emit a warning when being returned.
-return-exceptions=no
-
-# Exceptions that will emit a warning when being instantiated.
-nonstandard-exceptions=no
-
-[REFACTORING]
-# Maximum number of nested blocks.
-max-nested-blocks=5
-
-# Complete name of the function that returns the YAPF version.
-yapf-version=
diff --git a/.windsurf/rules/test-new-features.md b/.windsurf/rules/test-new-features.md
new file mode 100644
index 0000000..cac25e9
--- /dev/null
+++ b/.windsurf/rules/test-new-features.md
@@ -0,0 +1,90 @@
+---
+trigger: model_decision
+description: When a new feature is added, this prompt needs to be run
+---
+
+# Development Guidelines
+
+## Code Quality Standards
+
+### Testing Requirements
+- MANDATORY: Every new feature MUST include corresponding tests
+- Write tests BEFORE implementing complex features (TDD approach)
+- Test coverage for new code should be >80%
+- Include both unit tests and integration tests where applicable
+- Test edge cases, error paths, and boundary conditions
+
+### Documentation Standards
+- Update relevant documentation IN THE SAME COMMIT as code changes
+- Documentation locations:
+  - README.md: User-facing features, installation, quick start
+  - CHANGELOG.md: All changes, following Keep a Changelog format
+  - Code comments: Complex logic, non-obvious decisions, API contracts
+  - Function/struct docs: Public APIs must have doc comments
+- Use concrete examples in documentation
+- Keep docs concise but complete
+
+### Code Organization
+- CRITICAL: Clean up as you go - no orphaned files or dead code
+- Remove commented-out code blocks (use git history instead)
+- Delete unused imports, functions, and variables immediately
+- Consolidate duplicate code into reusable functions
+- Move TODO items from loose files into:
+  - Code comments with `// TODO(context):` for implementation tasks
+  - GitHub Issues for larger features
+  - NEVER create standalone .md files for tracking
+
+### When Making Changes
+For EVERY significant change, complete ALL of these:
+
+1. Write/update tests
+2. Update documentation (README, CHANGELOG, code comments)
+3. Update build scripts if dependencies/build process changed
+4. Remove any temporary/debug code added during development
+5. Delete unused files created during exploration
+6. Verify no dead code remains (unused functions, imports, variables)
+
+### Cleanup Checklist (Run BEFORE committing)
+- [ ] Removed all debug print statements
+- [ ] Deleted temporary test files
+- [ ] Removed commented-out code
+- [ ] Cleaned up unused imports
+- [ ] Deleted exploratory/spike code
+- [ ] Consolidated duplicate logic
+- [ ] Removed obsolete scripts/configs
+
+### Communication Style
+- Report what you've done: "Added feature X with tests in test/x_test.go"
+- Highlight what needs attention: "WARNING: Manual testing needed for edge case Y"
+- Ask questions directly: "Should we support Z? Trade-offs are..."
+- NEVER say "I'll track this in a markdown file" - use code comments or tell me directly
+
+### Script/Build System Updates
+- Update Makefile/build.zig when adding new targets or commands
+- Modify CI/CD configs (.github/workflows) if build/test process changes
+- Update package.json/Cargo.toml/go.mod when dependencies change
+- Document new scripts in README under "Development" section
+
+## Anti-Patterns to AVOID
+- Creating notes.md, todo.md, tasks.md, ideas.md files
+- Leaving commented-out code "for reference"
+- Keeping old implementation files with .old or .backup suffixes
+- Adding features without tests
+- Updating code without updating docs
+- Leaving TODO comments without context or assignee
+
+## Preferred Patterns
+- Inline TODO comments: `// TODO(user): Add caching layer for better performance`
+- Self-documenting code with clear names
+- Tests that serve as usage examples
+- Incremental, complete commits (code + tests + docs)
+- Direct communication about tasks and priorities
+
+## Definition of Done
+A task is complete ONLY when:
+1. Code is written and working
+2. Tests are written and passing
+3. Documentation is updated
+4. All temporary/dead code is removed
+5. Build scripts are updated if needed
+6. Changes are committed with clear message
\ No newline at end of file
diff --git a/AGENTS.md b/AGENTS.md
new file mode 100644
index 0000000..35f186e
--- /dev/null
+++ b/AGENTS.md
@@ -0,0 +1,238 @@
+# AGENTS.md - Coding Agent Guidelines
+
+This document provides essential information for agentic coding assistants working with the FetchML codebase.
+
+## Build Commands
+
+### Go Components
+```bash
+# Build all Go components
+make build
+
+# Build for development (faster compilation)
+make dev
+
+# Build for production (optimized)
+make prod
+
+# Cross-platform build for Linux/macOS/Windows
+make cross-platform
+```
+
+### Zig CLI
+```bash
+# Build CLI with release-small optimization
+cd cli && make all
+
+# Build for development
+cd cli && make dev
+
+# Build for production
+cd cli && make prod
+
+# Alternative using zig build system
+cd cli && zig build
+```
+
+## Test Commands
+
+### Running Tests
+```bash
+# Run all tests
+make test
+
+# Run unit tests only
+make test-unit
+
+# Run integration tests only
+make test-integration
+
+# Run end-to-end tests only
+make test-e2e
+
+# Run with coverage report
+make test-coverage
+
+# Run a single test
+go test -v ./path/to/package -run TestName
+
+# Run tests with race detector
+go test -race ./path/to/package/...
+```
+
+### Performance Testing
+```bash
+# Run performance benchmarks
+make benchmark
+
+# Run load testing suite
+make load-test
+
+# Run chaos engineering tests
+make chaos-test
+
+# Run complete technical excellence suite
+make tech-excellence
+```
+
+## Lint Commands
+
+```bash
+# Run all linters and formatters
+make lint
+
+# Run Go linters
+golangci-lint run
+
+# Run Go formatters
+gofmt -w ./cmd ./internal ./tests
+
+# Run Go vet
+go vet ./...
+
+# Format Zig code
+cd cli && zig fmt .
+
+# Validate YAML configs against schema
+make configlint
+make worker-configlint
+```
+
+## Code Style Guidelines
+
+### Go Code Style
+
+1. **Formatting**:
+   - Use `gofmt` for formatting
+   - Line length: 100 characters (configured in .golangci.yml)
+   - Use `goimports` for import organization
+
+2. **Naming Conventions**:
+   - Use camelCase for variables and functions
+   - Use PascalCase for exported identifiers
+   - Use clear, descriptive names
+   - Acronyms should be all caps (e.g., HTTP, URL)
+
+3. **Imports**:
+   - Group imports in order: standard library, third-party, internal
+   - Use meaningful import aliases when needed
+   - Remove unused imports
+
+4. **Error Handling**:
+   - Always handle errors explicitly
+   - Use `errors.Is` and `errors.As` for error checking
+   - Wrap errors with context using `fmt.Errorf("context: %w", err)`
+
+5. **Documentation**:
+   - All exported functions, types, and variables must have doc comments
+   - Comments should explain "why" not just "what"
+   - Use godoc formatting conventions
+
+### Zig Code Style
+
+1. **Formatting**:
+   - Use built-in Zig formatter (`zig fmt`)
+   - Consistent indentation with 4 spaces
+
+2. **Naming Conventions**:
+   - Use camelCase for variables and functions
+   - Use PascalCase for types
+   - Use snake_case for file names
+
+3. **Error Handling**:
+   - Use Zig's error union types (`!T`)
+   - Handle errors with `try`, `catch`, or `if` expressions
+   - Return errors early when appropriate
+
+### Python Code Style
+
+1. **Formatting**:
+   - Use Black formatter with 80 character line limit
+   - Use isort for import organization (Google style)
+
+2. **Type Checking**:
+   - Use mypy with strict settings
+   - All functions should have type annotations
+
+3. **Testing**:
+   - Use pytest framework
+   - Follow naming conventions: `test_*` for functions, `*_test.py` for files
+
+### YAML/Configuration Style
+
+1. **Formatting**:
+   - Use yamllint for validation
+   - Consistent indentation with 2 spaces
+   - No trailing whitespace
+
+2. **Validation**:
+   - All configs must pass schema validation
+   - Use `make configlint` and `make worker-configlint`
+
+## Development Guidelines
+
+### Testing Requirements (from .windsurf/rules/test-new-features.md)
+- Every new feature MUST include corresponding tests
+- Test coverage for new code should be >80%
+- Include both unit tests and integration tests where applicable
+- Test edge cases, error paths, and boundary conditions
+
+### Code Organization
+- Clean up as you go - no orphaned files or dead code
+- Remove commented-out code blocks
+- Delete unused imports, functions, and variables immediately
+- Consolidate duplicate code into reusable functions
+
+### Documentation Standards
+- Update relevant documentation IN THE SAME COMMIT as code changes
+- Documentation locations:
+  - README.md: User-facing features, installation, quick start
+  - CHANGELOG.md: All changes, following Keep a Changelog format
+  - Code comments: Complex logic, non-obvious decisions, API contracts
+  - Function/struct docs: Public APIs must have doc comments
+
+### Commit Message Convention
+Use conventional commits:
+- `feat:` for new features
+- `fix:` for bug fixes
+- `docs:` for documentation changes
+- `style:` for formatting changes
+- `refactor:` for code refactoring
+- `test:` for adding/updating tests
+- `chore:` for maintenance tasks
+
+## Project Structure
+
+- `cmd/` - Main applications
+- `internal/` - Internal packages
+- `cli/` - Zig command-line interface
+- `tests/` - Test files organized by type
+- `configs/` - Configuration files and schemas
+- `docs/` - Documentation
+- `scripts/` - Utility scripts
+
+## Dependencies
+
+- Go 1.25+
+- Zig 0.15+
+- Python 3.11+ (for some tools)
+- Redis (for integration tests)
+- Docker/Podman (for container-based tests)
+
+## Useful Make Targets
+
+```bash
+# Development workflow
+make dev-start     # Start development environment
+make test          # Run all tests
+make lint          # Run linters
+make ci-local      # Run local CI dry-run
+
+# Documentation
+make docs          # Start documentation server
+make docs-build    # Build static documentation
+
+# Cleanup
+make clean         # Remove build artifacts
+make clean-docs    # Remove documentation artifacts
+```
\ No newline at end of file
diff --git a/cpu.prof b/cpu.prof
new file mode 100644
index 0000000..0fa19f8
Binary files /dev/null and b/cpu.prof differ
diff --git a/mem.prof b/mem.prof
new file mode 100644
index 0000000..51a2e6c
Binary files /dev/null and b/mem.prof differ
diff --git a/tests/benchmarks/api_benchmark_test.go b/tests/benchmarks/api_benchmark_test.go
index 1243ecf..08fb8bb 100644
--- a/tests/benchmarks/api_benchmark_test.go
+++ b/tests/benchmarks/api_benchmark_test.go
@@ -5,6 +5,8 @@ import (
 	"context"
 	"encoding/json"
 	"fmt"
+	"io"
+	"net"
 	"net/http"
 	"net/http/httptest"
 	"strings"
@@ -15,11 +17,32 @@ import (
 	"github.com/prometheus/client_golang/prometheus"
 )
 
+func newBenchmarkHTTPClient() *http.Client {
+	transport := &http.Transport{
+		Proxy: http.ProxyFromEnvironment,
+		DialContext: (&net.Dialer{
+			Timeout:   30 * time.Second,
+			KeepAlive: 30 * time.Second,
+		}).DialContext,
+		ForceAttemptHTTP2:     true,
+		MaxIdleConns:          256,
+		MaxIdleConnsPerHost:   256,
+		IdleConnTimeout:       90 * time.Second,
+		TLSHandshakeTimeout:   10 * time.Second,
+		ExpectContinueTimeout: 1 * time.Second,
+	}
+
+	return &http.Client{
+		Timeout:   30 * time.Second,
+		Transport: transport,
+	}
+}
+
 // BenchmarkAPIServerCreateJob tests job creation performance
 func BenchmarkAPIServerCreateJob(b *testing.B) {
 	server := setupTestAPIServer(b)
 	defer server.Close()
-	client := &http.Client{Timeout: 30 * time.Second}
+	client := newBenchmarkHTTPClient()
 	b.ResetTimer()
 	b.ReportAllocs()
 	benchmarkCreateJob(b, server.URL, client)
@@ -80,6 +103,7 @@ func BenchmarkAPIServerCreateJobSimple(b *testing.B) {
 			// Skip this iteration if server isn't ready
 			continue
 		}
+		_, _ = io.Copy(io.Discard, resp.Body)
 		_ = resp.Body.Close()
 	}
 
@@ -126,7 +150,7 @@ func BenchmarkConcurrentRequests(b *testing.B) {
 	server := setupTestAPIServer(b)
 	defer server.Close()
 
-	client := &http.Client{Timeout: 30 * time.Second}
+	client := newBenchmarkHTTPClient()
 
 	b.ResetTimer()
 
@@ -148,6 +172,7 @@ func benchmarkConcurrentRequests(b *testing.B, baseURL string, client *http.Clie
 
 			resp, err := client.Do(req)
 			if err == nil && resp != nil {
+				_, _ = io.Copy(io.Discard, resp.Body)
 				_ = resp.Body.Close()
 			}
 			i++
@@ -212,6 +237,7 @@ func benchmarkCreateJob(b *testing.B, baseURL string, client *http.Client) {
 		if err != nil {
 			b.Fatalf("Request failed: %v", err)
 		}
+		_, _ = io.Copy(io.Discard, resp.Body)
 		_ = resp.Body.Close()
 	}
 }
@@ -229,6 +255,7 @@ func benchmarkListJobs(b *testing.B, baseURL string, client *http.Client) {
 		if err != nil {
 			b.Fatalf("Request failed: %v", err)
 		}
+		_, _ = io.Copy(io.Discard, resp.Body)
 		_ = resp.Body.Close()
 	}
 }
@@ -237,7 +264,7 @@ func benchmarkListJobs(b *testing.B, baseURL string, client *http.Client) {
 func BenchmarkAPIServerListJobs(b *testing.B) {
 	server := setupTestAPIServer(b)
 	defer server.Close()
-	client := &http.Client{Timeout: 30 * time.Second}
+	client := newBenchmarkHTTPClient()
 	b.ResetTimer()
 	b.ReportAllocs()
 	benchmarkListJobs(b, server.URL, client)
diff --git a/tests/load/load_test.go b/tests/load/load_test.go
index 2df3c56..d045bcf 100644
--- a/tests/load/load_test.go
+++ b/tests/load/load_test.go
@@ -332,6 +332,22 @@ func runLoadTestScenario(t *testing.T, baseURL, scenarioName string, config Load
 	runner := NewLoadTestRunner(baseURL, config)
 	results := runner.Run()
 
+	if minThroughput, maxErrorRate, maxP99Latency, ok := loadTestCriteria(scenarioName); ok {
+		t.Logf("Load test criteria for %s:", scenarioName)
+		t.Logf("  Min throughput: %.2f RPS", minThroughput)
+		t.Logf("  Max error rate: %.2f%%", maxErrorRate)
+		t.Logf("  Max P99 latency: %.0fms", maxP99Latency)
+	}
+
+	t.Logf("Load test config for %s:", scenarioName)
+	t.Logf("  Concurrency: %d", config.Concurrency)
+	t.Logf("  Duration: %v", config.Duration)
+	t.Logf("  Ramp up: %v", config.RampUpTime)
+	t.Logf("  Target RPS: %d", config.RequestsPerSec)
+	t.Logf("  Payload size: %d", config.PayloadSize)
+	t.Logf("  Method: %s", config.Method)
+	t.Logf("  Endpoint: %s", config.Endpoint)
+
 	t.Logf("Load test results for %s:", scenarioName)
 	t.Logf("  Total requests: %d", results.TotalRequests)
 	t.Logf("  Successful: %d", results.SuccessfulReqs)
@@ -348,6 +364,19 @@ func runLoadTestScenario(t *testing.T, baseURL, scenarioName string, config Load
 	validateLoadTestResults(t, scenarioName, results)
 }
 
+func loadTestCriteria(scenarioName string) (minThroughput, maxErrorRate, maxP99Latency float64, ok bool) {
+	switch scenarioName {
+	case "LightLoad":
+		return 40.0, 1.0, 100.0, true
+	case "MediumLoad":
+		return 180.0, 2.0, 200.0, true
+	case "HeavyLoad":
+		return 450.0, 5.0, 500.0, true
+	default:
+		return 0, 0, 0, false
+	}
+}
+
 // Run executes the load test
 func (ltr *LoadTestRunner) Run() *LoadTestResults {
 	start := time.Now()
@@ -684,24 +713,8 @@ func runStressTest(t *testing.T, baseURL string) {
 
 // validateLoadTestResults checks if results meet performance criteria
 func validateLoadTestResults(t *testing.T, scenarioName string, results *LoadTestResults) {
-	// Define performance thresholds based on scenario type
-	var maxErrorRate, maxP99Latency float64
-	var minThroughput float64
-
-	switch scenarioName {
-	case "LightLoad":
-		maxErrorRate = 1.0
-		maxP99Latency = 100.0 // 100ms
-		minThroughput = 40.0
-	case "MediumLoad":
-		maxErrorRate = 2.0
-		maxP99Latency = 200.0 // 200ms
-		minThroughput = 180.0
-	case "HeavyLoad":
-		maxErrorRate = 5.0
-		maxP99Latency = 500.0 // 500ms
-		minThroughput = 450.0
-	default:
+	minThroughput, maxErrorRate, maxP99Latency, ok := loadTestCriteria(scenarioName)
+	if !ok {
 		return
 	}
 
diff --git a/tests/unit/worker/jupyter_task_test.go b/tests/unit/worker/jupyter_task_test.go
index 971ada3..eeb7d13 100644
--- a/tests/unit/worker/jupyter_task_test.go
+++ b/tests/unit/worker/jupyter_task_test.go
@@ -12,11 +12,12 @@ import (
 )
 
 type fakeJupyterManager struct {
-	startFn   func(ctx context.Context, req *jupyter.StartRequest) (*jupyter.JupyterService, error)
-	stopFn    func(ctx context.Context, serviceID string) error
-	removeFn  func(ctx context.Context, serviceID string, purge bool) error
-	restoreFn func(ctx context.Context, name string) (string, error)
-	listFn    func() []*jupyter.JupyterService
+	startFn    func(ctx context.Context, req *jupyter.StartRequest) (*jupyter.JupyterService, error)
+	stopFn     func(ctx context.Context, serviceID string) error
+	removeFn   func(ctx context.Context, serviceID string, purge bool) error
+	restoreFn  func(ctx context.Context, name string) (string, error)
+	listFn     func() []*jupyter.JupyterService
+	listPkgsFn func(ctx context.Context, serviceName string) ([]jupyter.InstalledPackage, error)
 }
 
 func (f *fakeJupyterManager) StartService(ctx context.Context, req *jupyter.StartRequest) (*jupyter.JupyterService, error) {
@@ -39,6 +40,13 @@ func (f *fakeJupyterManager) ListServices() []*jupyter.JupyterService {
 	return f.listFn()
 }
 
+func (f *fakeJupyterManager) ListInstalledPackages(ctx context.Context, serviceName string) ([]jupyter.InstalledPackage, error) {
+	if f.listPkgsFn == nil {
+		return nil, nil
+	}
+	return f.listPkgsFn(ctx, serviceName)
+}
+
 type jupyterOutput struct {
 	Type    string `json:"type"`
 	Service *struct {
@@ -47,6 +55,15 @@ type jupyterOutput struct {
 	} `json:"service"`
 }
 
+type jupyterPackagesOutput struct {
+	Type     string `json:"type"`
+	Packages []struct {
+		Name    string `json:"name"`
+		Version string `json:"version"`
+		Source  string `json:"source"`
+	} `json:"packages"`
+}
+
 func TestRunJupyterTaskStartSuccess(t *testing.T) {
 	w := worker.NewTestWorkerWithJupyter(&worker.Config{}, nil, &fakeJupyterManager{
 		startFn: func(_ context.Context, req *jupyter.StartRequest) (*jupyter.JupyterService, error) {
@@ -55,10 +72,11 @@ func TestRunJupyterTaskStartSuccess(t *testing.T) {
 			}
 			return &jupyter.JupyterService{Name: req.Name, URL: "http://127.0.0.1:8888"}, nil
 		},
-		stopFn:    func(context.Context, string) error { return nil },
-		removeFn:  func(context.Context, string, bool) error { return nil },
-		restoreFn: func(context.Context, string) (string, error) { return "", nil },
-		listFn:    func() []*jupyter.JupyterService { return nil },
+		stopFn:     func(context.Context, string) error { return nil },
+		removeFn:   func(context.Context, string, bool) error { return nil },
+		restoreFn:  func(context.Context, string) (string, error) { return "", nil },
+		listFn:     func() []*jupyter.JupyterService { return nil },
+		listPkgsFn: func(context.Context, string) ([]jupyter.InstalledPackage, error) { return nil, nil },
 	})
 
 	task := &queue.Task{JobName: "jupyter-my-workspace", Metadata: map[string]string{
@@ -85,11 +103,12 @@ func TestRunJupyterTaskStartSuccess(t *testing.T) {
 
 func TestRunJupyterTaskStopFailure(t *testing.T) {
 	w := worker.NewTestWorkerWithJupyter(&worker.Config{}, nil, &fakeJupyterManager{
-		startFn:   func(context.Context, *jupyter.StartRequest) (*jupyter.JupyterService, error) { return nil, nil },
-		stopFn:    func(context.Context, string) error { return errors.New("stop failed") },
-		removeFn:  func(context.Context, string, bool) error { return nil },
-		restoreFn: func(context.Context, string) (string, error) { return "", nil },
-		listFn:    func() []*jupyter.JupyterService { return nil },
+		startFn:    func(context.Context, *jupyter.StartRequest) (*jupyter.JupyterService, error) { return nil, nil },
+		stopFn:     func(context.Context, string) error { return errors.New("stop failed") },
+		removeFn:   func(context.Context, string, bool) error { return nil },
+		restoreFn:  func(context.Context, string) (string, error) { return "", nil },
+		listFn:     func() []*jupyter.JupyterService { return nil },
+		listPkgsFn: func(context.Context, string) ([]jupyter.InstalledPackage, error) { return nil, nil },
 	})
 
 	task := &queue.Task{JobName: "jupyter-my-workspace", Metadata: map[string]string{
@@ -102,3 +121,41 @@ func TestRunJupyterTaskStopFailure(t *testing.T) {
 		t.Fatalf("expected error")
 	}
 }
+
+func TestRunJupyterTaskListPackagesSuccess(t *testing.T) {
+	w := worker.NewTestWorkerWithJupyter(&worker.Config{}, nil, &fakeJupyterManager{
+		startFn:   func(context.Context, *jupyter.StartRequest) (*jupyter.JupyterService, error) { return nil, nil },
+		stopFn:    func(context.Context, string) error { return nil },
+		removeFn:  func(context.Context, string, bool) error { return nil },
+		restoreFn: func(context.Context, string) (string, error) { return "", nil },
+		listFn:    func() []*jupyter.JupyterService { return nil },
+		listPkgsFn: func(_ context.Context, serviceName string) ([]jupyter.InstalledPackage, error) {
+			if serviceName != "my-workspace" {
+				return nil, errors.New("bad service")
+			}
+			return []jupyter.InstalledPackage{
+				{Name: "numpy", Version: "1.26.0", Source: "pip"},
+				{Name: "pandas", Version: "2.1.0", Source: "conda"},
+			}, nil
+		},
+	})
+
+	task := &queue.Task{JobName: "jupyter-packages-my-workspace", Metadata: map[string]string{
+		"task_type":      "jupyter",
+		"jupyter_action": "list_packages",
+		"jupyter_name":   "my-workspace",
+	}}
+
+	out, err := w.RunJupyterTask(context.Background(), task)
+	if err != nil {
+		t.Fatalf("expected nil error, got %v", err)
+	}
+
+	var decoded jupyterPackagesOutput
+	if err := json.Unmarshal(out, &decoded); err != nil {
+		t.Fatalf("expected valid JSON, got %v", err)
+	}
+	if len(decoded.Packages) != 2 {
+		t.Fatalf("expected 2 packages, got %d", len(decoded.Packages))
+	}
+}