Benchmark run and artifact fix

.github/workflows/benchmarks.yaml

@@ -139,38 +139,24 @@ jobs:
 
     - name: Upload artifact
       id: upload-artifact
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
         name: benchmarks-debug
         path: ./benchmarks/benchmark-results
 
-    - name: Fetch Artifact ID
-      id: fetch-artifact-id
-      uses: actions/github-script@v6
-      with:
-        script: |
-          const run_id = ${{ github.run_id }};
-          const artifacts = await github.rest.actions.listWorkflowRunArtifacts({
-            owner: context.repo.owner,
-            repo: context.repo.repo,
-            run_id: run_id,
-          });
-          const artifact = artifacts.data.artifacts.find(artifact => artifact.name === 'benchmarks-debug');
-          return artifact.id;
-
     - name: Comment on PR with benchmark results and download link
       uses: actions/github-script@v6
       with:
         script: |
           const fs = require('fs');
           const summaryPath = './benchmarks/benchmark-results/summary.md';
           const contents = fs.readFileSync(summaryPath, 'utf8');
-          const artifactID = ${{ steps.fetch-artifact-id.outputs.result }};
+          const artifactID = ${{ steps.upload-artifact.outputs.artifact-id }};
           const downloadURL = `https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}/artifacts/${artifactID}`;
 
           github.rest.issues.updateComment({
             comment_id: ${{ env.BENCHMARKS_COMMENT_ID }},
             owner: context.repo.owner,
             repo: context.repo.repo,
-            body: '[Finished benchmarks](https://github.com/${{github.repository}}/actions/runs/${{github.run_id}})\n\n' + contents + '\n\n[Download Artifacts](' + downloadURL + ')'
+            body: '[Finished benchmarks](https://github.com/${{github.repository}}/actions/runs/${{github.run_id}})\n\n' + contents + '\n\n[Download artifacts](' + downloadURL + ')'
           })

benchmarks.json

@@ -13,8 +13,8 @@
         "autotx/tests/agents/token/research/test_research_and_swap.py::test_auto_tx_research_swap_and_send_governance_token": "70.00",
         "autotx/tests/agents/token/research/test_research.py::test_price_change_information": "90.00",
         "autotx/tests/agents/token/research/test_research.py::test_get_top_5_tokens_from_base": "90.00",
-        "autotx/tests/agents/token/test_swap.py::test_auto_tx_swap_multiple": "90.00",
-        "autotx/tests/agents/token/test_swap_and_send.py::test_auto_tx_swap_and_send_complex": "20.00",
+        "autotx/tests/agents/token/test_swap.py::test_auto_tx_swap_multiple": "100.00",
+        "autotx/tests/agents/token/test_swap_and_send.py::test_auto_tx_swap_and_send_complex": "100.00",
         "autotx/tests/agents/token/test_swap.py::test_auto_tx_swap_with_non_default_token": "100.00",
         "autotx/tests/agents/token/research/test_research.py::test_get_top_5_most_traded_tokens_from_l1": "70.00",
         "autotx/tests/agents/token/research/test_research.py::test_get_token_exchanges": "90.00",

benchmarks.py

@@ -67,6 +67,9 @@ def run_test(test_name, iterations, avg_time_across_tests, completed_tests, rema
 def print_summary_table(test_path: str, iterations: int, tests_results: dict, total_run_time: float, output_dir: str, total_benchmarks: dict):
     """Prints a summary table of all tests in markdown format to the console and a file, including total success percentage."""
 
+    # Sort test results
+    tests_results = sorted(tests_results, key=lambda x: x['name'])
+
     # Calculate total passes and fails
     total_passes = sum(result['passes'] for result in tests_results)
     total_fails = sum(result['fails'] for result in tests_results)