Updated README

Author: cyberphor

.github/workflows/integrate.yaml

@@ -13,9 +13,6 @@ jobs:
         id: trufflehog
         uses: trufflesecurity/trufflehog@main
         continue-on-error: false
-        with:
-          head: HEAD
-          extra_args: --debug
   qa:
     name: Quality Assurance
     runs-on: ubuntu-latest
@@ -28,7 +25,7 @@ jobs:
           python-version: 3.12
       - name: Install Python dependencies
         run: python -m pip install black
-      - name: Run Python black
+      - name: Check code formatting
         run: black --diff --color --check .
   sca:
     name: Software Composition Analysis
@@ -56,5 +53,5 @@ jobs:
     steps:
       - name: Clone the repository
         uses: actions/checkout@v4
-      - name: Do a SAST scan
+      - name: Perform a SAST scan
         run: semgrep scan --config auto

.github/workflows/publish.yaml

@@ -7,11 +7,10 @@ jobs:
   pypi:
     name: Publish to PyPI
     runs-on: ubuntu-latest
-    environment:
-      name: pypi
-      url: https://pypi.org/p/pySunshower
     permissions:
       id-token: write
+      actions: read
+      contents: write
     steps:
       - uses: actions/checkout@v4
       - name: Install Python

README.md

@@ -10,7 +10,7 @@
 ## Overview
 Not all AI agents are created equal. In the design phase of system development, choosing the right harness and model is critical. `pySunshower` automates this decision-making process by running trials in parallel and using an LLM to score the results.  
 
-![diagram](diagram.png)
+![diagram](./diagram.png)
 
 ## Features
 * **Declarative**: Define your entire experiment (teams, models, harnesses, and metrics) in YAML

pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "pySunshower"
-version = "0.0.2"
-description = "pySunshower is a Python library for evaluating AI agents in a declarative way."
+version = "0.0.3"
+description = "Declarative and Distributed Benchmarking for AI Agents."
 readme = "README.md"
 requires-python = ">=3.12"