feat: surface assembled prompt byte metrics during spawn (#2822)

[ApexYash11]

Fixes

Closes #2822

Summary

This PR addresses Issue #2822 by surfacing informational prompt size metrics during session spawn.

After the final prompt and system prompt are assembled, AO now measures their byte lengths using len() and exposes them through the spawn response and CLI output. This gives users visibility into the size of the prompt AO assembles without introducing any provider- or model-specific assumptions.

Changes

• Measure assembled prompt and system prompt byte sizes in Manager.Spawn()
• Thread the values through the spawn flow using Go multi-return values
• Expose promptBytes and systemPromptBytes in the spawn response
• Display prompt metrics in ao spawn output when non-zero
• Regenerate the OpenAPI specification and frontend API schema

Design

This implementation is intentionally informational only.

It does not:

• estimate tokens
• enforce prompt limits
• introduce provider-specific logic
• modify prompt assembly
• modify prompt delivery
• introduce new abstractions or agent interfaces

The metrics are computed during spawn and are not persisted.

Testing

Verified with:

• gofmt
• go vet ./...
• go build ./...
• Relevant unit tests
• Integration tests
• OpenAPI/spec generation
• Frontend schema generation

[somewherelostt]

Thanks for contributing to Agent Orchestrator.

This PR is being picked up by the current external contributor on-call pair:

• @neversettle17-101
• @somewherelostt

If someone is already working on this, please continue as usual.
The on-call pair is added for visibility, tracking, and support, not to take over the work.
If you need help with review, direction, reproduction, or next steps, please tag @neversettle17-101 and @somewherelostt here.

For faster context or live questions, you can also join the AO Discord.

Join the session here:
https://discord.gg/H6ZDcUXmq

Come by if you want to see what is being built, ask questions, or just hang around with the community.