docs(configuration): document HINDSIGHT_API_RETAIN_CHUNK_BATCH_SIZE

The retain_chunk_batch_size hierarchical config field and its
ENV_RETAIN_CHUNK_BATCH_SIZE loader have existed in HindsightConfig
since the retain streaming batch landed, but the Retain section of
the configuration reference never got a row for them — users who
want to cap chunk-batch size on large document ingestion had to
discover the env var by grepping the source.

Add a row to the Retain table next to the other chunk/batch knobs,
with the same format as surrounding entries and an explicit note
that the field is configurable per bank via the bank config API.

Author: mrkhachaturov

hindsight-docs/docs/developer/configuration.md

@@ -721,6 +721,7 @@ Controls the retain (memory ingestion) pipeline.
 | `HINDSIGHT_API_RETAIN_BATCH_ENABLED` | Use LLM Batch API for fact extraction (50% cost savings, only with async operations) | `false` |
 | `HINDSIGHT_API_RETAIN_MAX_CONCURRENT` | Max concurrent retain DB phases (HNSW reads + writes). Limits I/O contention during high-concurrency ingestion. | `4` |
 | `HINDSIGHT_API_RETAIN_BATCH_TOKENS` | Max characters per sub-batch for async retain auto-splitting | `10000` |
+| `HINDSIGHT_API_RETAIN_CHUNK_BATCH_SIZE` | Max chunks per streaming batch when retain ingests long documents. Each chunk produces roughly 17 facts, so the default 100 chunks ≈ 1700 facts per batch. Lower to cap memory/LLM pressure on large documents; raise for smaller chunks. Configurable per bank. | `100` |
 | `HINDSIGHT_API_RETAIN_ENTITY_LOOKUP` | Entity lookup method during retain: `full` (exact match) or `trigram` (fuzzy trigram matching) | `trigram` |
 | `HINDSIGHT_API_RETAIN_DEFAULT_STRATEGY` | Default retain strategy name. When set, all retain calls without an explicit `strategy` parameter use this strategy. | - |
 | `HINDSIGHT_API_RETAIN_BATCH_POLL_INTERVAL_SECONDS` | Batch API polling interval in seconds | `60` |