Fix missing error handling in LLM response stream iteration

[Copilot]

Addresses missing error handling in LLMSummarizer.Summarize() where the response stream from GenerateContent() was iterated without checking errors, causing silent failures.

Changes

• Error handling: Unpack both response and error from iter.Seq2[*model.LLMResponse, error] during iteration
• Type correction: Fixed Parts field type from []genai.Part back to []*genai.Part (compilation error from commit 0ff4ff5)

// Before
for resp := range responseStream {
    if resp == nil {
        continue
    }
    // ... process response
}

// After  
for resp, err := range responseStream {
    if err != nil {
        return nil, fmt.Errorf("LLM API call failed: %w", err)
    }
    if resp == nil {
        continue
    }
    // ... process response
}

API failures now surface immediately with context instead of returning nil content silently.

---

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.