Fix- Pass listen transcript to ask feature

[lawzcc]

Extended description:

• Before: live “Listen” transcript was never passed into askService, so queries only analyzed screen content.
• Now: askService merges the transcript with screen analysis when building the prompt.

---

name: Integrate Listen transcripts with Ask feature for contextual AI responses
about: Enable Ask feature to use recent audio transcripts from Listen sessions for more comprehensive analysis

Summary of Changes

This pull request integrates the Listen feature's audio transcripts with the Ask feature, allowing users to get AI responses based on both screen content and recent audio context. The Ask service now automatically retrieves and includes recent transcript data when processing user queries, providing more contextually relevant answers.

Related Issue

• Closes [BUG] Ask ignores Listen transcript #138

This change addresses the missing integration between the Listen and Ask features, where previously the Ask feature only analyzed screen content and ignored valuable audio transcript data from active Listen sessions.

Contributor's Self-Review Checklist

Please check the boxes that apply. This is a reminder of what we look for in a good pull request.

• I have read the CONTRIBUTING.md document.
• My code follows the project's coding style and architectural patterns as described in DESIGN_PATTERNS.md.
• I have added or updated relevant tests for my changes.
• I have updated the documentation to reflect my changes (if applicable).
• My changes have been tested locally and are working as expected.

Additional Context (Optional)

Add any other context or screenshots about the pull request here.