Keep the body scrape for reserved message types and an empty receipt id marker

AGENTS.md

@@ -202,12 +202,13 @@ exactly 140.
   Message type `MC_DELIVERY_RECEIPT` (0x04) makes it a receipt whatever the body parses to, so a
   receipt in a format `dlrFromPdu()` cannot read reaches `dlr` with `smsId` undefined instead of
   arriving as an inbound SMS. Any other named type — delivery or user acknowledgement, conversation
-  abort, intermediate notification — is not a receipt and its body is not scraped. Message type 0
-  keeps the scrape: SMSCs that send text-only receipts leave `esm_class` at 0, and reading that as
-  the spec's "default message type" would lose every one of them. A `receipted_message_id` TLV marks
-  a receipt on the same footing where the message type is 0, since nothing but a receipt carries one.
-  What gets scraped is the decoded `short_message` with any UDH stripped, so a concatenated receipt
-  is read like any other.
+  abort, intermediate notification — is not a receipt and its body is not scraped. A message type of
+  0, or one of the ten the spec reserves, keeps the scrape: SMSCs that send text-only receipts leave
+  `esm_class` at 0, and reading that as the spec's "default message type" would lose every one of
+  them. A non-empty `receipted_message_id` TLV marks a receipt on the same footing there, since
+  nothing but a receipt carries one. What gets scraped is the decoded `short_message` with any UDH
+  stripped; receipts never reach the reassembler, so an SMSC that splits one across segments gets a
+  `dlr` per segment rather than one merged report.
   The `message_state` TLV is authoritative only where it names a state in the table — SMPP reserves
   0x80-0xFF for MC-vendor-specific values, so an unnameable one keeps its raw `statusId` and leaves
   `statusMsg` to the body.

src/defs/constants.ts

@@ -103,11 +103,11 @@ export const consts = {
 	},
 } as const;
 
-/** esm_class bits 5-2 name the message type; bit 6 is the UDH indicator. */
 export function hasUdh(esmClass: number): boolean {
 	return (esmClass & consts.ESM_CLASS.UDH_INDICATOR) === consts.ESM_CLASS.UDH_INDICATOR;
 }
 
+/** Bits 5-2 of esm_class; the rest carry the messaging mode and the GSM features. */
 export function messageTypeOf(esmClass: number): number {
 	return esmClass & 0x3c;
 }

src/dlr.ts

@@ -125,13 +125,25 @@ export function parseReceipt(message: string): Receipt {
 
 type MessageType = 'other' | 'receipt' | 'unmarked';
 
+/** The message types the spec names that are not receipts. It reserves the remaining ten. */
+const notReceiptTypes: number[] = [
+	consts.ESM_CLASS.CONVERSATION_ABORT,
+	consts.ESM_CLASS.DELIVERY_ACKNOWLEDGEMENT,
+	consts.ESM_CLASS.INTERMEDIATE_DELIVERY,
+	consts.ESM_CLASS.USER_ACKNOWLEDGEMENT,
+];
+
+function nonEmptyText(value: ParamValue | undefined): string | undefined {
+	return typeof value === 'string' && value !== '' ? value : undefined;
+}
+
 function messageType(pduObj: PduObject): MessageType {
 	const type = messageTypeOf(paramNumber(pduObj.params.esm_class, 0));
 
 	if (type === consts.ESM_CLASS.MC_DELIVERY_RECEIPT) return 'receipt';
-	if (type !== 0) return 'other';
+	if (notReceiptTypes.includes(type)) return 'other';
 
-	return pduObj.tlvs.receipted_message_id === undefined ? 'unmarked' : 'receipt';
+	return nonEmptyText(pduObj.tlvs.receipted_message_id?.tagValue) === undefined ? 'unmarked' : 'receipt';
 }
 
 /** A UDH-carrying short_message reaches here as a buffer, header and all. */
@@ -148,9 +160,7 @@ function receiptBody(pduObj: PduObject): string {
 }
 
 function receiptId(tlvId: ParamValue | undefined, receipt: Receipt | undefined): string | undefined {
-	if (typeof tlvId === 'string' && tlvId !== '') return tlvId;
-
-	return receipt?.id === '' ? undefined : receipt?.id;
+	return nonEmptyText(tlvId) ?? (receipt?.id === '' ? undefined : receipt?.id);
 }
 
 function isMessageState(name: string | undefined): name is MessageState {
@@ -173,12 +183,7 @@ function receiptStatus(
 	return { statusId: tlvState, statusMsg: isMessageState(named) ? named : scraped };
 }
 
-/**
- * Builds a delivery report from a deliver_sm, or nothing if the PDU carries a message rather than a
- * receipt. `esm_class` decides that where the peer names a message type and a receipted_message_id
- * TLV where it names none; failing both, the body is read for the standard receipt fields, which is
- * the only thing Kannel and several other SMSCs send.
- */
+/** The delivery report a deliver_sm carries, or nothing when it carries a message instead. */
 export function dlrFromPdu(pduObj: PduObject): Dlr | undefined {
 	const type = messageType(pduObj);
 

test/dlr.test.ts

@@ -119,6 +119,7 @@ describe('dlrFromPdu()', () => {
 
 	test('returns nothing when an unmarked deliver_sm identifies no message', () => {
 		assert.equal(dlrFromPdu(deliverSm('just a normal sms', undefined, 0)), undefined);
+		assert.equal(dlrFromPdu(deliverSm('id:0195f0c7 stat:WEIRDXX', undefined, 0)), undefined);
 	});
 
 	test('still reads the body when the peer marks no message type', () => {
@@ -171,6 +172,22 @@ describe('dlrFromPdu()', () => {
 		assert.ok(dlr);
 		assert.equal(dlr.smsId, 'from-the-tlv');
 		assert.equal(dlr.statusMsg, 'UNKNOWN');
+
+		const empty = dlrFromPdu(deliverSm('an ordinary inbound message', {
+			receipted_message_id: { tagValue: '' },
+		}, 0));
+
+		assert.equal(empty, undefined, 'an empty id marks nothing');
+	});
+
+	// The spec names six of the sixteen message types and reserves the rest, so a peer that types
+	// its receipts with one of the reserved bits keeps the body scrape rather than losing them.
+	test('keeps the body scrape for a message type the spec reserves', () => {
+		const dlr = dlrFromPdu(deliverSm(receiptText, undefined, 0x0c));
+
+		assert.ok(dlr);
+		assert.equal(dlr.smsId, '0195f0c7');
+		assert.equal(dlr.statusMsg, 'DELIVERED');
 	});
 
 	test('leaves a message the peer marked as another type to arrive as an SMS', () => {

todo.md

@@ -5,7 +5,7 @@ rules there constrain every item below.
 
 ## Status
 
-The rewrite is **feature complete and green**: 230 tests, lint and typecheck clean, verified on Node
+The rewrite is **feature complete and green**: 231 tests, lint and typecheck clean, verified on Node
 18, 20, 22 and 24. What is left is release work and a few things worth adding before or after 1.0.0.
 
 ```bash
@@ -147,6 +147,13 @@ session message is a change to every call site.
       `reassembly`, `dlr-merger`, `send-window`, `link-timers`, `reconnect-loop`, `pending-requests`
       and `send-sms`, so the directory would make that boundary visible. Do it on the next
       extraction out of `session.ts`, not as a move of its own.
+- [ ] **Does an intermediate delivery notification deserve to be a `dlr`?** `esm_class` message type
+      `INTERMEDIATE_DELIVERY` (0x20) is classified as a message today, so a peer that reports
+      non-final states with it hands the application a raw `id:… stat:ENROUTE` text as an inbound
+      SMS. Kannel treats 0x04, 0x08 and 0x20 alike as report-bearing. Against it: a non-final report
+      would take a segment's slot in `DlrMerger` and complete the group early. Raised by review,
+      2026-08-27; needs a decision.
+
 - [ ] **`submit_multi` and the broadcast commands** encode and decode, but nothing exercises them
       end to end. The interop suite is the natural place.
 - [ ] **Move to TypeScript 7** once `typescript-eslint` supports it; `renovate.json` pins TypeScript