Add a modelName option to the command line runners

[digitalWestie]

I found that running from the command line resulted in the following error:

Attempt 1 failed: ClientError: [VertexAI.ClientError]: got status: 404 Not Found. {"error":{"code":404,"message":"Publisher Model `projects/sensemaker-466109/locations/global/publishers/google/models/gemini-2.5-pro-preview-06-05` was not found or your project does not have access to it. Please ensure you are using a valid model version. For more information, see: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions","status":"NOT_FOUND"}}

Since the code is fixed to this model, I have added an option so that we can specify the model from the command line, for example:

npx ts-node ./library/runner-cli/categorization_runner.ts --vertexProject "sensemaker-466109" --outputFile glasgow-categorized.csv --inputFile ./in.csv --additionalContext "Comments about Glasgow's historical connections to slavery and how the city should address this legacy" --modelName "gemini-2.5-flash-lite"

Without the option it still defaults back to gemini-2.5-pro-preview-06-05 - which for whatever reason doesn't work for me. Perhaps others can comment on that?

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

[digitalWestie]

In my fork I have both PRs merged together, I can make a PR with both changes if that makes things easier.

#36
#37