test(sdk, api): fix finish reason, chat, audio and completion tests

[justinthelaw]

Description

Creates and enables vLLM E2E tests that touch each SDK gRPC endpoint at least once with a "happy path" test. Standardizes the new Completions test from vLLM's E2E tests to the LLaMA-CPP-Python E2E tests. Fixes the FinishReason enum typing issues across Completions and ChatCompletions.

BREAKING CHANGES

• fixes FinishReason to be an enum in both Completions and ChatCompletions protobufs
  • modifies API gRPC handler, typing utils, and helper utils to use a Enum class to define and transform the stub responses
• fixes object and created field for Completions, using Literal text_completion as defined in the OpenAI API specification

CHANGES

• adds and enables simple ("happy path") E2E vLLM testing for local environments only (GPU runner is broken, see commit history)
• adds Completions E2E test to llama-cpp-python and vLLM to catch more potential issues, like FinishReason being the wrong type
• adds Audio and Completions unit testing
• condenses tests into a single test file with an ENV parser (default, warning and helper text included) for model name
• adds more comprehensive Make target for test and typing artifact clean-up
• improves testing documentation and Makefile targets

Related Issue

Fixes #1037

Relates to #854

Checklist before merging

• Tests, documentation, ADR added or updated as needed
• Followed the Contributor Guide Steps

[netlify]

✅ Deploy Preview for leapfrogai-docs canceled.

Name	Link
🔨 Latest commit	cac0fdb
🔍 Latest deploy log	https://app.netlify.com/sites/leapfrogai-docs/deploys/66eca5b299eeee000876a768

[justinthelaw]

There seems to be an issue with our GPU runner configurations that is blocking the vLLM E2E tests from running: https://github.com/defenseunicorns/leapfrogai/actions/runs/10894219888/job/30230952202

The upstream UDS Common action is unable to install UDS CLI into the bin directory. It seems like it needs sudo or higher permissions, even though that is not usually required in our CPU (large or regular) runners. As a side note, the vLLM E2E tests run locally.