feat(embedding): add Gemini embedding provider support across runtime

[srinivasrk]

Description

Add Gemini embedding support end-to-end in runtime config and setup flow.

• Register Gemini as a first-class embedding provider in embedding runtime metadata with:
  • default endpoint (https://generativelanguage.googleapis.com/v1beta/openai/embeddings)
  • env key fallback (GEMINI_API_KEY)
  • default model/dimension (gemini-embedding-001, 3072)
• Expose Gemini in scripts/start_tour.py embedding setup:
  • add provider option in embedding provider selection
  • add default model suggestion for Gemini
• Update embedding endpoint normalization/validation mappings so Gemini is treated as its own provider (instead of aliasing to OpenAI).
• Update .env.example with Gemini embedding endpoint example and GEMINI_API_KEY fallback entry.
• Add regression tests for:
  • embedding runtime resolution for Gemini binding/defaults/env fallback
  • setup tour provider/model suggestion exposure for Gemini

Related Issues

• Closes #...
• Related to #...

Module(s) Affected

• agents
• api
• config
• core
• knowledge
• logging
• services
• tools
• utils
• web (Frontend)
• docs (Documentation)
• scripts
• tests
• Other: ...

Checklist

• I have read and followed the contribution guidelines.
• My code follows the project's coding standards.
• I have run pre-commit run --all-files and fixed any issues.
• I have added relevant tests for my changes.
• I have updated the documentation (if necessary).
• My changes do not introduce any new security vulnerabilities.

Additional Notes

• Targeted tests and syntax/lint checks were run locally for touched files.
• Full pre-commit run --all-files was not executed in this session.