llms/ollama: Add generation duration metrics to GenerateContent response

[andrewyang17]

PR Checklist

• Read the Contributing documentation.
• Read the Code of conduct documentation.
• Name your Pull Request title clearly, concisely, and prefixed with the name of the primarily affected package you changed according to Good commit messages (such as memory: add interfaces for X, Y or util: add whizzbang helpers).
• Check that there isn't already a PR that solves the problem the same way to avoid creating a duplicate.
• Provide a description in this PR that addresses what the PR is solving, or reference the issue that it solves (e.g. Fixes #123).
• Describes the source of new concepts.
• References existing implementations as appropriate.
• Contains test coverage for new functions.
• Passes all golangci-lint checks.

Problem

• Duration metrics (PromptEvalDuration, EvalDuration, LoadDuration, TotalDuration) were available from the ollamaclient.ChatResponse.
• These values were missing from the genInfo map, so they could not be accessed downstream for analysis or monitoring.

Solution

• Added the missing duration metrics into the genInfo variable within GenerateContent:
  • PromptEvalDuration – time spent evaluating the prompt.
  • EvalDuration – time spent generating tokens.
  • LoadDuration – time spent loading the model/resources.
  • TotalDuration – total request duration.
• Ensures duration metrics are included in the response for observability and performance insights.