Function embed_passages_parallel_with_embedding_choice 

pub fn embed_passages_parallel_with_embedding_choice(
    models_dir: &Path,
    texts: &[String],
    parallelism: usize,
    batch_size: usize,
    embedding_backend: EmbeddingBackendChoice,
    llm_backend: LlmBackendChoice,
) -> Result<Vec<Vec<f32>>, AppError>

v1.0.93 (GAP-OR-INGEST): embeds multiple passages with EmbeddingBackendChoice awareness. When the resolved chain starts with OpenRouter and the client is initialised, uses the HTTP batch API (embed_batch) instead of subprocess fan-out — no LLM slot consumed, ~200ms per batch vs ~15s per subprocess cold-start. Falls back to embed_passages_parallel_local for LLM backends.