refactor: improve conversation metadata generation logic

[chenyme]

Summary

Fix automatic conversation title and label generation after failed first turns.

Conversation metadata generation no longer depends on message_count == 0. If a failed first turn already created server-side messages, later successful turns can still generate metadata as long as the title is still a placeholder or labels are empty. Existing manual titles are preserved, existing labels are not overwritten, and the existing 5000-token metadata prompt limit remains unchanged.

Change type

• Bug fix
• Feature
• Documentation
• Refactor
• Configuration / deployment
• Security hardening
• Other

Affected areas

• Frontend / UI
• Backend / API
• Authentication / authorization
• Conversations / streaming
• Files / RAG / extraction
• Model routing / providers
• MCP / tools
• Billing / payments
• Admin console
• Deployment / Docker / configuration
• Documentation

Verification

• cd backend && go test ./internal/application/conversation/...
• git diff --check

Screenshots, API examples, or logs

No screenshots. Backend conversation metadata behavior fix.

Configuration, migration, and compatibility notes

No configuration, database migration, environment variable, Docker, or API contract changes.

The existing metadata prompt truncation limit remains unchanged at 5000 estimated tokens.

Documentation

• Documentation is not needed for this change.
• Documentation was updated.
• Documentation still needs to be updated.

Security and privacy

• No secrets, tokens, credentials, local config, or personal data are included.
• User data access remains scoped by authenticated user context unless an admin-only path explicitly requires broader access.
• Security-sensitive behavior was reviewed, including authentication, authorization, provider routing, file processing, billing, and admin APIs where relevant.

Checklist

• I searched existing issues and pull requests.
• Changes are focused and do not include unrelated refactors.
• Tests or static verification were run where practical.
• User-facing behavior, deployment steps, API contracts, or configuration changes are documented.
• Generated artifacts are included only when this project explicitly requires them.
• Caches, build output, .pyc files, .env files, and local storage data are not committed.