feat: route embedding input types by usage

[RerankerGuo]

Summary

• Fixes Support input_type for asymmetric embeddings in built-in memorySearch #1421.
• Add optional inputType, queryInputType, and documentInputType embedding config fields.
• Route document embeddings through documentInputType and query embeddings through queryInputType, falling back to inputType when a specific value is absent.
• Forward input_type to OpenAI-compatible and OpenClaw host embedding requests when configured.
• Retry the viewer embedding model probe once with input_type: "query" when a provider explicitly reports that input_type is required.

Validation

• static embedding input_type checks passed
• npm test -- --run tests/embedding-input-type.test.ts (blocked: vitest: not found)
• npm run build (blocked: tsc: not found)
• npm run lint (blocked: eslint: not found)
• make format (blocked: poetry: Command not found)

[Memtensor-AI]

Automated Test Results: PASSED

Cloud test-engine full-audit rerun against dev-v2.0.22 completed successfully after clearing the cloud workspace disk.

• Run: tr-678431ce-070 on cloud test-engine 10011
• memos_local_openclaw/unit: 12 passed, 0 failed, 0 skipped

Manual code review is still required before merge.