tweak docs

Author: jonathanalgar

README.md

@@ -13,11 +13,11 @@
 
 ## Overview
 
-The BSD-3 licensed [`CustomCode-Analyzer`](https://github.com/jonathanalgar/CustomCode-Analyzer) component was released to give you real-time feedback your C# code as you build an External Library in your IDE of choice. But more generally `CustomCode-Analyzer` can be thought of as a way of locally validating an External Library at the point of build. This makes it a powerful component in an end-to-end Large Language Model (LLM) pipeline for generating an ODC External Library:
+The BSD-3 licensed [`CustomCode-Analyzer`](https://github.com/jonathanalgar/CustomCode-Analyzer) component was released to give you real-time feedback your C# code as you build an external library in your IDE of choice. But more generally `CustomCode-Analyzer` can be thought of as a way of locally validating an external library at the point of build. This makes it a powerful component in an end-to-end Large Language Model (LLM) pipeline for generating an ODC external library:
 
 ![](./README_resources/diagram.png)
 
-The `CustomCode-Analyzer-Generator` is an orchestrator  around the `CustomCode-Analyzer` and other local components and external APIs. As seen in the above diagram the `CustomCode-Analyzer-Generator` takes user input for an External Library functionality and:
+The `CustomCode-Analyzer-Generator` is an orchestrator  around the `CustomCode-Analyzer` and other local components and external APIs. As seen in the above diagram the `CustomCode-Analyzer-Generator` takes user input for an external library functionality and:
 
 * Calls the NuGet API and LLMs to generate the candidate implementation and unit test code.
 * Creates implementation and unit test C# projects, installs packages and incorporates candidate code.
@@ -59,7 +59,7 @@ _(Quick start script for Mac coming soon)._
 
 ##  Technical notes on evaluation
 
-To validate that the LLM pipeline works effectively and generates external libraries aligned with user intent there is a supplementary evaluation pipeline complete with [eight diverse test cases](./agents/evaluation/ground_truth/).
+To validate that the LLM pipeline works effectively and generates external libraries aligned with user intent there is a supplementary evaluation pipeline complete with [eight diverse test cases](./agents/evaluation/ground_truth/). The objective is [to add more](https://github.com/jonathanalgar/CustomCode-Analyzer-Generator/issues/6).
 
 This means a range of models and prompts can be programatically benchmarked. The central piece of pipeline is the Roslyn-based [`CCGATestGenerator`](./agents/evaluation/CCAGTestGenerator/), which—given the LLM-generated implementation code and human created ground truth file—will deterministically create a unit test.
 
@@ -76,6 +76,9 @@ You can replicate a run using:
 ```
 docker compose -f run_full_benchmark.yml up --abort-on-container-exit
 ```
+
+> :bulb: API access to o3-mini is [still in preview](https://help.openai.com/en/articles/10362446-api-access-to-o1-and-o3-mini).
+
 _(More documentation and analysis coming soon.)_
 
 ## TODO

windows_setup.ps1

@@ -16,43 +16,6 @@ try {
     exit
 }
 
-# Perform Docker cleanup to prevent accumulation of old containers and images
-Write-Host "`nCleaning up old containers and images..."
-try {
-    # Stop and remove only containers related to this specific image
-    $containers = docker ps -a --filter "ancestor=ghcr.io/jonathanalgar/customcode-analyzer-generator" --format "{{.ID}}"
-    if ($containers) {
-        Write-Host "Removing old containers from customcode-analyzer-generator..."
-        docker rm -f $containers
-    } else {
-        Write-Host "No old containers from customcode-analyzer-generator found."
-    }
-    
-    # Remove only dangling images related to this specific repository
-    # This is much safer than a broad prune
-    $danglingImages = docker images --filter "dangling=true" --filter "reference=ghcr.io/jonathanalgar/customcode-analyzer-generator*" --format "{{.ID}}"
-    if ($danglingImages) {
-        Write-Host "Removing dangling images from customcode-analyzer-generator..."
-        docker rmi $danglingImages
-    } else {
-        Write-Host "No dangling images from customcode-analyzer-generator found."
-    }
-    
-    # Remove old versions of the image (keep the latest)
-    $images = docker images "ghcr.io/jonathanalgar/customcode-analyzer-generator" --format "{{.ID}}" | Select-Object -Skip 1
-    if ($images) {
-        Write-Host "Removing old image versions of customcode-analyzer-generator..."
-        docker rmi $images
-    } else {
-        Write-Host "No old image versions of customcode-analyzer-generator found."
-    }
-    
-    Write-Host "Cleanup completed successfully" -ForegroundColor Green
-} catch {
-    Write-Host "Warning: Cleanup encountered an issue. Continuing with installation..." -ForegroundColor Yellow
-    Write-Host $_.Exception.Message
-}
-
 # Get the current username
 $username = $env:USERNAME
 
@@ -111,6 +74,42 @@ try {
     exit
 }
 
+# Perform Docker cleanup to prevent accumulation of old containers and images
+Write-Host "`nCleaning up old containers and images..."
+try {
+    # Stop and remove only containers related to this specific image
+    $containers = docker ps -a --filter "ancestor=ghcr.io/jonathanalgar/customcode-analyzer-generator" --format "{{.ID}}"
+    if ($containers) {
+        Write-Host "Removing old containers from customcode-analyzer-generator..."
+        docker rm -f $containers
+    } else {
+        Write-Host "No old containers from customcode-analyzer-generator found."
+    }
+    
+    # Remove only dangling images related to this specific repository
+    $danglingImages = docker images --filter "dangling=true" --filter "reference=ghcr.io/jonathanalgar/customcode-analyzer-generator*" --format "{{.ID}}"
+    if ($danglingImages) {
+        Write-Host "Removing dangling images from customcode-analyzer-generator..."
+        docker rmi $danglingImages
+    } else {
+        Write-Host "No dangling images from customcode-analyzer-generator found."
+    }
+    
+    # Remove old versions of the image (keep the latest)
+    $images = docker images "ghcr.io/jonathanalgar/customcode-analyzer-generator" --format "{{.ID}}" | Select-Object -Skip 1
+    if ($images) {
+        Write-Host "Removing old image versions of customcode-analyzer-generator..."
+        docker rmi $images
+    } else {
+        Write-Host "No old image versions of customcode-analyzer-generator found."
+    }
+    
+    Write-Host "Cleanup completed successfully" -ForegroundColor Green
+} catch {
+    Write-Host "Warning: Cleanup encountered an issue. Continuing..." -ForegroundColor Yellow
+    Write-Host $_.Exception.Message
+}
+
 $scriptPath = Split-Path -Parent -Path $MyInvocation.MyCommand.Definition
 Set-Location -Path $scriptPath