WIP refactor(model): unify config-driven retry across VLM and embedding

[qin-ctx]

Description

Unify retry handling for model calls by moving transient-error retry into shared utilities and config-driven defaults for both VLM and embedding providers.

Related Issue

Fixes #922

Type of Change

• Bug fix (non-breaking change that fixes an issue)
• New feature (non-breaking change that adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update
• Refactoring (no functional changes)
• Performance improvement
• Test update

Changes Made

• add a shared model retry helper and reuse its error classification in both VLM backends and the circuit breaker path
• make vlm.max_retries default to 3, add top-level embedding.max_retries, and wire embedding factories/providers to honor config-driven retry
• remove per-call async VLM retry overrides and update tests for new defaults, signatures, and retry behavior

Testing

• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• I have tested this on the following platforms:
  • Linux
  • macOS
  • Windows

Checklist

• My code follows the project's coding style
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• Any dependent changes have been merged and published

Screenshots (if applicable)

N/A

Additional Notes

Targeted verification completed with:

• python -m pytest --override-ini addopts='' tests/models/test_vlm_strip_think_tags.py tests/unit/test_vlm_response_formats.py tests/unit/test_extra_headers_vlm.py tests/unit/test_stream_config_vlm.py tests/unit/test_extra_headers_embedding.py tests/unit/test_jina_embedder.py tests/unit/test_voyage_embedder.py tests/unit/test_minimax_embedder_simple.py tests/unit/test_model_retry.py -q
• python -m compileall openviking openviking_cli tests/unit

I did not run the server test setup because local imports there require argon2, which is not installed in this environment. There is also an existing unrelated failure in tests/unit/test_openai_embedder.py that was not introduced by this change.

[github-actions]

Failed to generate code suggestions for PR