Fix misleading comment on counterparty_commitment_txn_on_chain insert

[joostjager]

The comment claimed this insert "isn't useful yet" and was only a safety measure for a watchtower race. In practice it is also used critically by provide_payment_preimage to look up the commitment number when a preimage arrives after the counterparty commitment tx is confirmed.

[ldk-reviews-bot]

👋 Thanks for assigning @TheBlueMatt as a reviewer!
I'll wait for their review and will help manage the review process.
Once they submit their review, I'll check if a second reviewer would be helpful.

[ldk-claude-review-bot]

I've now reviewed the full context. The PR is a comment-only change. Let me verify the new comment's claims are accurate:

1. provide_payment_preimage uses counterparty_commitment_txn_on_chain: Confirmed at lines 3806 and 3817 — provide_payment_preimage calls self.counterparty_commitment_txn_on_chain.get(&txid) to look up the commitment number.

2. The watchtower race scenario: This was already documented in the old comment and remains in the new one.

3. "the above conditional": The new comment refers to counterparty_commitment_txn_on_chain entry not being generated by the above conditional — this refers to line 4850 where the insert happens inside the revoked commitment branch. This is accurate.

The new comment is factually correct and more informative than the old one. This is a clean, comment-only change with no code modifications.

No issues found.