name: PR Benchmark (SMG Components)

on:
  push:
    branches: [ main ]
    paths:
      - "sgl-model-gateway/**"
  pull_request:
    branches: [ main ]
    paths:
      - "sgl-model-gateway/**"
  workflow_dispatch:

concurrency:
  group: pr-benchmark-rust-${{ github.ref }}
  cancel-in-progress: true

env:
  RUSTC_WRAPPER: sccache
  SCCACHE_GHA_ENABLED: "true"

permissions:
  contents: read
  pull-requests: write
  issues: write

jobs:
  # Quick check job that always runs on PRs
  benchmark-compile-check:
    name: Benchmark Compilation Check
    runs-on: ubuntu-latest
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

      - name: Install dependencies
        run: |
          bash scripts/ci/ci_install_rust.sh

      - name: Configure sccache
        uses: mozilla-actions/sccache-action@v0.0.9
        with:
          version: "v0.12.0"

      - name: Rust cache
        uses: Swatinem/rust-cache@v2
        with:
          workspaces: sgl-model-gateway
          # Share cache across all benchmark jobs
          shared-key: "rust-cache"
          # Save cache even on failure
          save-if: true
          cache-all-crates: true
          cache-on-failure: true

      - name: Check benchmarks compile
        run: |
          source "$HOME/.cargo/env"
          cd sgl-model-gateway/
          cargo check --benches

      - name: Show sccache stats
        if: always()
        run: sccache --show-stats

  # Full benchmark jobs that only run with label or on main branch
  benchmark-request-processing:
    name: Request Processing Benchmark
    if: |
      github.repository == 'sgl-project/sglang' &&
      (github.event_name == 'push' ||
       github.event_name == 'workflow_dispatch' ||
       (contains(github.event.pull_request.labels.*.name, 'router-benchmark') &&
        contains(github.event.pull_request.labels.*.name, 'run-ci')))
    runs-on: ubuntu-latest
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
        with:
          # Fetch enough history for baseline comparison
          fetch-depth: 100

      - name: Install dependencies
        run: |
          bash scripts/ci/ci_install_rust.sh

      - name: Configure sccache
        uses: mozilla-actions/sccache-action@v0.0.9
        with:
          version: "v0.12.0"

      - name: Rust cache
        uses: Swatinem/rust-cache@v2
        with:
          workspaces: sgl-model-gateway
          # Share cache across all benchmark jobs
          shared-key: "rust-cache"
          cache-all-crates: true
          cache-on-failure: true
          # Save cache even on failure
          save-if: true

      - name: Run request processing benchmark
        timeout-minutes: 30
        run: |
          source "$HOME/.cargo/env"
          cd sgl-model-gateway/
          # Try to use sccache, but disable if it fails
          if command -v sccache &> /dev/null; then
            echo "Testing sccache availability..."
            # Try to start sccache and check if it works
            export RUSTC_WRAPPER=sccache
            export SCCACHE_GHA_ENABLED="true"
            if sccache --start-server 2>/dev/null && sccache --show-stats 2>/dev/null; then
              echo "sccache is working, using it for compilation"
            else
              echo "sccache failed to start, falling back to regular cargo"
              unset RUSTC_WRAPPER
              unset SCCACHE_GHA_ENABLED
            fi
          else
            echo "sccache not available, using regular cargo"
          fi
          # Run only the summary benchmark for quick validation in PRs
          # Capture output to file for CI summary
          cargo bench --bench request_processing -- benchmark_summary --exact 2>&1 | tee benchmark_output.txt

      - name: Upload benchmark results
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: request-processing-results-${{ github.sha }}
          path: |
            sgl-model-gateway/target/criterion/benchmark_summary/
            sgl-model-gateway/benchmark_output.txt
          retention-days: 30

      - name: Show sccache stats
        if: always()
        run: sccache --show-stats

  benchmark-tokenizer:
    name: Tokenizer Benchmark
    if: |
      github.repository == 'sgl-project/sglang' &&
      (github.event_name == 'push' ||
       github.event_name == 'workflow_dispatch' ||
       (contains(github.event.pull_request.labels.*.name, 'router-benchmark') &&
        contains(github.event.pull_request.labels.*.name, 'run-ci')))
    runs-on: ubuntu-latest
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
        with:
          fetch-depth: 100

      - name: Install dependencies
        run: |
          bash scripts/ci/ci_install_rust.sh

      - name: Configure sccache
        uses: mozilla-actions/sccache-action@v0.0.9
        with:
          version: "v0.12.0"

      - name: Rust cache
        uses: Swatinem/rust-cache@v2
        with:
          workspaces: sgl-model-gateway
          # Share cache across all benchmark jobs
          shared-key: "rust-cache"
          cache-all-crates: true
          cache-on-failure: true
          # Save cache even on failure
          save-if: true

      - name: Run tokenizer benchmark
        timeout-minutes: 30
        run: |
          source "$HOME/.cargo/env"
          cd sgl-model-gateway/
          # Try to use sccache, but disable if it fails
          if command -v sccache &> /dev/null; then
            echo "Testing sccache availability..."
            # Try to start sccache and check if it works
            export RUSTC_WRAPPER=sccache
            export SCCACHE_GHA_ENABLED="true"
            if sccache --start-server 2>/dev/null && sccache --show-stats 2>/dev/null; then
              echo "sccache is working, using it for compilation"
            else
              echo "sccache failed to start, falling back to regular cargo"
              unset RUSTC_WRAPPER
              unset SCCACHE_GHA_ENABLED
            fi
          else
            echo "sccache not available, using regular cargo"
          fi
          # Capture output to file for CI summary
          cargo bench --bench tokenizer_benchmark 2>&1 | tee benchmark_output.txt

      - name: Upload benchmark results
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: tokenizer-results-${{ github.sha }}
          path: |
            sgl-model-gateway/target/criterion/tokenizer*/
            sgl-model-gateway/benchmark_output.txt
          retention-days: 30

  benchmark-tool-parser:
    name: Tool Parser Benchmark
    if: |
      github.repository == 'sgl-project/sglang' &&
      (github.event_name == 'push' ||
       github.event_name == 'workflow_dispatch' ||
       (contains(github.event.pull_request.labels.*.name, 'router-benchmark') &&
        contains(github.event.pull_request.labels.*.name, 'run-ci')))
    runs-on: ubuntu-latest
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
        with:
          fetch-depth: 100

      - name: Install dependencies
        run: |
          bash scripts/ci/ci_install_rust.sh

      - name: Configure sccache
        uses: mozilla-actions/sccache-action@v0.0.9
        with:
          version: "v0.12.0"

      - name: Rust cache
        uses: Swatinem/rust-cache@v2
        with:
          workspaces: sgl-model-gateway
          # Share cache across all benchmark jobs
          shared-key: "rust-cache"
          cache-all-crates: true
          cache-on-failure: true
          # Save cache even on failure
          save-if: true

      - name: Run tool parser benchmark
        timeout-minutes: 30
        run: |
          source "$HOME/.cargo/env"
          cd sgl-model-gateway/
          # Try to use sccache, but disable if it fails
          if command -v sccache &> /dev/null; then
            echo "Testing sccache availability..."
            # Try to start sccache and check if it works
            export RUSTC_WRAPPER=sccache
            export SCCACHE_GHA_ENABLED="true"
            if sccache --start-server 2>/dev/null && sccache --show-stats 2>/dev/null; then
              echo "sccache is working, using it for compilation"
            else
              echo "sccache failed to start, falling back to regular cargo"
              unset RUSTC_WRAPPER
              unset SCCACHE_GHA_ENABLED
            fi
          else
            echo "sccache not available, using regular cargo"
          fi
          # Capture output to file for CI summary
          cargo bench --bench tool_parser_benchmark 2>&1 | tee benchmark_output.txt

      - name: Upload benchmark results
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: tool-parser-results-${{ github.sha }}
          path: |
            sgl-model-gateway/target/criterion/tool_parser*/
            sgl-model-gateway/benchmark_output.txt
          retention-days: 30

      - name: Show sccache stats
        if: always()
        run: sccache --show-stats

  benchmark-tree:
    name: Tree Benchmark
    if: |
      github.repository == 'sgl-project/sglang' &&
      (github.event_name == 'push' ||
       github.event_name == 'workflow_dispatch' ||
       (contains(github.event.pull_request.labels.*.name, 'router-benchmark') &&
        contains(github.event.pull_request.labels.*.name, 'run-ci')))
    # Use 4-core runner for concurrent benchmarks that spawn multiple threads
    runs-on: 4-gpu-a10
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
        with:
          fetch-depth: 100

      - name: Install dependencies
        run: |
          bash scripts/ci/ci_install_rust.sh

      - name: Configure sccache
        uses: mozilla-actions/sccache-action@v0.0.9
        with:
          version: "v0.10.0"

      - name: Rust cache
        uses: Swatinem/rust-cache@v2
        with:
          workspaces: sgl-model-gateway
          # Share cache across all benchmark jobs
          shared-key: "rust-cache"
          cache-all-crates: true
          cache-on-failure: true
          # Save cache even on failure
          save-if: true

      - name: Run tree benchmark
        timeout-minutes: 30
        run: |
          source "$HOME/.cargo/env"
          cd sgl-model-gateway/
          # Try to use sccache, but disable if it fails
          if command -v sccache &> /dev/null; then
            echo "Testing sccache availability..."
            # Try to start sccache and check if it works
            export RUSTC_WRAPPER=sccache
            export SCCACHE_GHA_ENABLED="true"
            if sccache --start-server 2>/dev/null && sccache --show-stats 2>/dev/null; then
              echo "sccache is working, using it for compilation"
            else
              echo "sccache failed to start, falling back to regular cargo"
              unset RUSTC_WRAPPER
              unset SCCACHE_GHA_ENABLED
            fi
          else
            echo "sccache not available, using regular cargo"
          fi
          # Run summary benchmark for quick validation in CI
          # Note: Don't use --exact because benchmark names are prefixed (benchmark_summary/insert_realistic)
          # Capture output to file for CI summary
          cargo bench --bench tree_benchmark -- benchmark_summary 2>&1 | tee benchmark_output.txt

      - name: Upload benchmark results
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: tree-results-${{ github.sha }}
          path: |
            sgl-model-gateway/target/criterion/benchmark_summary*/
            sgl-model-gateway/benchmark_output.txt
          retention-days: 30

      - name: Show sccache stats
        if: always()
        run: sccache --show-stats

  benchmark-summary:
    name: Benchmark Summary
    needs: [benchmark-request-processing, benchmark-tokenizer, benchmark-tool-parser, benchmark-tree]
    if: always() && (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request')
    runs-on: ubuntu-latest
    steps:
      - name: Download all benchmark results
        uses: actions/download-artifact@v4
        with:
          pattern: '*-results-${{ github.sha }}'
          path: benchmark-results

      - name: Generate summary
        run: |
          echo "## 🚀 Benchmark Results Summary" > summary.md
          echo "" >> summary.md

          # Request Processing Benchmark
          echo "### Request Processing" >> summary.md
          REQ_DIR="benchmark-results/request-processing-results-${{ github.sha }}"
          if [ -d "$REQ_DIR" ]; then
            echo "✅ **Completed**" >> summary.md
            if [ -f "$REQ_DIR/benchmark_output.txt" ]; then
              echo "" >> summary.md
              echo "<details>" >> summary.md
              echo "<summary>View Results</summary>" >> summary.md
              echo "" >> summary.md
              echo '```' >> summary.md
              # Extract the summary section (starts with "SGLang Model Gateway" or performance data)
              grep -A 100 "SGLang Model Gateway\|Quick Performance\|Performance Insights" "$REQ_DIR/benchmark_output.txt" | head -50 >> summary.md || cat "$REQ_DIR/benchmark_output.txt" | tail -60 >> summary.md
              echo '```' >> summary.md
              echo "</details>" >> summary.md
            fi
          else
            echo "❌ Failed or skipped" >> summary.md
          fi
          echo "" >> summary.md

          # Tokenizer Benchmark
          echo "### Tokenizer" >> summary.md
          TOK_DIR="benchmark-results/tokenizer-results-${{ github.sha }}"
          if [ -d "$TOK_DIR" ]; then
            echo "✅ **Completed**" >> summary.md
            if [ -f "$TOK_DIR/benchmark_output.txt" ]; then
              echo "" >> summary.md
              echo "<details>" >> summary.md
              echo "<summary>View Results</summary>" >> summary.md
              echo "" >> summary.md
              echo '```' >> summary.md
              # Extract the summary table section
              grep -A 200 "TOKENIZER BENCHMARK SUMMARY\|ENCODING THROUGHPUT" "$TOK_DIR/benchmark_output.txt" | head -100 >> summary.md || cat "$TOK_DIR/benchmark_output.txt" | tail -100 >> summary.md
              echo '```' >> summary.md
              echo "</details>" >> summary.md
            fi
          else
            echo "❌ Failed or skipped" >> summary.md
          fi
          echo "" >> summary.md

          # Tool Parser Benchmark
          echo "### Tool Parser" >> summary.md
          TOOL_DIR="benchmark-results/tool-parser-results-${{ github.sha }}"
          if [ -d "$TOOL_DIR" ]; then
            echo "✅ **Completed**" >> summary.md
            if [ -f "$TOOL_DIR/benchmark_output.txt" ]; then
              echo "" >> summary.md
              echo "<details>" >> summary.md
              echo "<summary>View Results</summary>" >> summary.md
              echo "" >> summary.md
              echo '```' >> summary.md
              # Extract the summary table section
              grep -A 200 "TOOL PARSER BENCHMARK SUMMARY\|REGISTRY OPERATIONS\|COMPLETE PARSING" "$TOOL_DIR/benchmark_output.txt" | head -100 >> summary.md || cat "$TOOL_DIR/benchmark_output.txt" | tail -100 >> summary.md
              echo '```' >> summary.md
              echo "</details>" >> summary.md
            fi
          else
            echo "❌ Failed or skipped" >> summary.md
          fi
          echo "" >> summary.md

          # Tree Benchmark
          echo "### Radix Tree (Cache-Aware Routing)" >> summary.md
          TREE_DIR="benchmark-results/tree-results-${{ github.sha }}"
          if [ -d "$TREE_DIR" ]; then
            echo "✅ **Completed**" >> summary.md
            if [ -f "$TREE_DIR/benchmark_output.txt" ]; then
              echo "" >> summary.md
              echo "<details>" >> summary.md
              echo "<summary>View Results</summary>" >> summary.md
              echo "" >> summary.md
              echo '```' >> summary.md
              # Extract benchmark results (printed incrementally during run)
              echo "=== Summary Results ===" >> summary.md
              grep "\[BENCH_RESULT\] summary" "$TREE_DIR/benchmark_output.txt" | sed 's/\[BENCH_RESULT\] //' >> summary.md || true
              echo "" >> summary.md
              # Also show the full summary table if available
              grep -A 100 "RADIX TREE BENCHMARK SUMMARY\|CI SUMMARY" "$TREE_DIR/benchmark_output.txt" | head -60 >> summary.md || cat "$TREE_DIR/benchmark_output.txt" | tail -60 >> summary.md
              echo '```' >> summary.md
              echo "</details>" >> summary.md
            fi
          else
            echo "❌ Failed or skipped" >> summary.md
          fi

          echo "" >> summary.md
          echo "---" >> summary.md
          echo "_Generated at $(date -u '+%Y-%m-%d %H:%M:%S UTC')_" >> summary.md

          # Display summary in logs
          cat summary.md

          # Write to GitHub Step Summary for visibility in the Actions UI
          cat summary.md >> $GITHUB_STEP_SUMMARY

      - name: Upload summary
        uses: actions/upload-artifact@v4
        with:
          name: benchmark-summary-${{ github.sha }}
          path: summary.md
          retention-days: 30