From 1e35761dbbfc65b8a2369fe3ebc5a25a82b127ab Mon Sep 17 00:00:00 2001
From: Boden <halomastar@gmail.com>
Date: Fri, 29 May 2026 16:33:00 -0500
Subject: [PATCH] test(scrape): lock mixed-length snowflake cursor selection

Add cursor-mixed-length smoke where string max_by would pick the wrong
--after value; padded sort_by in last_message_id already picks the max.
---
 ...-29-034-fix-snowflake-cursor-smoke-plan.md | 27 ++++++++++++++++++
 scripts/tests/run-discord-scrape-smoke.sh     | 15 ++++++++++
 .../append-after-mixed-length.json            | 23 +++++++++++++++
 .../append-mixed-length-cursor.json           | 28 +++++++++++++++++++
 4 files changed, 93 insertions(+)
 create mode 100644 docs/plans/2026-05-29-034-fix-snowflake-cursor-smoke-plan.md
 create mode 100644 scripts/tests/test-fixtures/append-after-mixed-length.json
 create mode 100644 scripts/tests/test-fixtures/append-mixed-length-cursor.json

diff --git a/docs/plans/2026-05-29-034-fix-snowflake-cursor-smoke-plan.md b/docs/plans/2026-05-29-034-fix-snowflake-cursor-smoke-plan.md
new file mode 100644
index 00000000..a179adda
--- /dev/null
+++ b/docs/plans/2026-05-29-034-fix-snowflake-cursor-smoke-plan.md
@@ -0,0 +1,27 @@
+---
+title: fix: Mixed-length snowflake cursor smoke
+type: fix
+status: complete
+date: 2026-05-29
+origin: /lfg — close residual review P2 on last_message_id; lock padded sort behavior
+---
+
+# fix: Mixed-length snowflake cursor smoke
+
+## Summary
+
+`last_message_id` already uses zero-padded `sort_by` (not string `max_by`). Add a smoke fixture where an 18-digit ID lexicographically beats a 19-digit ID but is numerically smaller, and assert `--after` uses the true maximum.
+
+## Requirements
+
+| ID | Requirement |
+|----|-------------|
+| R1 | Fixture archive with IDs `999999999999999999` and `1000000000000000000` (unordered) |
+| R2 | Smoke expects `--after` = `1000000000000000000` |
+| R3 | `DCE_MIN_FREE_MB=0 ./scripts/run-all-smokes.sh` passes |
+| R4 | PR #1538 notes residual P2 addressed |
+
+## Verification
+
+- `./scripts/tests/run-discord-scrape-smoke.sh`
+- `DCE_MIN_FREE_MB=0 ./scripts/run-all-smokes.sh`
diff --git a/scripts/tests/run-discord-scrape-smoke.sh b/scripts/tests/run-discord-scrape-smoke.sh
index 3762e2c8..2ba560a5 100755
--- a/scripts/tests/run-discord-scrape-smoke.sh
+++ b/scripts/tests/run-discord-scrape-smoke.sh
@@ -103,6 +103,14 @@ cat >"$CONFIG_PATH" <<JSON
       "guild_ids": [],
       "guild_name_patterns": []
     },
+    {
+      "name": "cursor-mixed-length",
+      "kind": "guild",
+      "output_dir": "$ARCHIVE_ROOT/cursor-mixed-length",
+      "channel_ids": ["111"],
+      "guild_ids": [],
+      "guild_name_patterns": []
+    },
     {
       "name": "bootstrap-map",
       "kind": "guild",
@@ -173,6 +181,7 @@ case "$subcommand" in
       initial) cp "$fixture_dir/append-existing.json" "$output" ;;
       append) cp "$fixture_dir/append-incremental.json" "$output" ;;
       append-after-high-id) cp "$fixture_dir/append-after-high-id.json" "$output" ;;
+      append-after-mixed-length) cp "$fixture_dir/append-after-mixed-length.json" "$output" ;;
       partial-write) cp "$fixture_dir/append-partial-write.json" "$output" ;;
       concurrent-conflict) cp "$fixture_dir/append-concurrent-conflict.json" "$output" ;;
       wrong-channel) cp "$fixture_dir/wrong-channel.json" "$output" ;;
@@ -313,6 +322,12 @@ FAKE_DCE_EXPECT_AFTER=999 run_wrapper cursor-max-id append-after-high-id
 CURSOR_DEST="$ARCHIVE_ROOT/cursor-max-id/$DEFAULT_FILE_NAME"
 [[ "$(jq -r '.messages | length' "$CURSOR_DEST")" == "4" ]] || { echo "expected cursor-max-id archive to contain four messages" >&2; exit 1; }
 
+mkdir -p "$ARCHIVE_ROOT/cursor-mixed-length"
+cp "$FIXTURE_DIR/append-mixed-length-cursor.json" "$ARCHIVE_ROOT/cursor-mixed-length/$DEFAULT_FILE_NAME"
+FAKE_DCE_EXPECT_AFTER=1000000000000000000 run_wrapper cursor-mixed-length append-after-mixed-length
+MIXED_CURSOR_DEST="$ARCHIVE_ROOT/cursor-mixed-length/$DEFAULT_FILE_NAME"
+[[ "$(jq -r '.messages | length' "$MIXED_CURSOR_DEST")" == "3" ]] || { echo "expected cursor-mixed-length archive to contain three messages" >&2; exit 1; }
+
 mkdir -p "$ARCHIVE_ROOT/bootstrap-map"
 cp "$FIXTURE_DIR/append-existing.json" "$ARCHIVE_ROOT/bootstrap-map/$DEFAULT_FILE_NAME"
 [[ ! -f "$ARCHIVE_ROOT/bootstrap-map/.dce-meta/channel-map.json" ]] || { echo "bootstrap-map should start without channel map" >&2; exit 1; }
diff --git a/scripts/tests/test-fixtures/append-after-mixed-length.json b/scripts/tests/test-fixtures/append-after-mixed-length.json
new file mode 100644
index 00000000..fe94d65d
--- /dev/null
+++ b/scripts/tests/test-fixtures/append-after-mixed-length.json
@@ -0,0 +1,23 @@
+{
+  "guild": {
+    "id": "222",
+    "name": "Fixture Guild"
+  },
+  "channel": {
+    "id": "111",
+    "name": "fixture-room",
+    "category": "Testing Grounds"
+  },
+  "messages": [
+    {
+      "id": "1000000000000000001",
+      "timestamp": "2026-01-03T00:00:00Z",
+      "content": "after-mixed-length-max"
+    }
+  ],
+  "dateRange": {
+    "after": "1000000000000000000",
+    "before": null
+  },
+  "exportedAt": "2026-01-03T00:00:00Z"
+}
diff --git a/scripts/tests/test-fixtures/append-mixed-length-cursor.json b/scripts/tests/test-fixtures/append-mixed-length-cursor.json
new file mode 100644
index 00000000..faee6a25
--- /dev/null
+++ b/scripts/tests/test-fixtures/append-mixed-length-cursor.json
@@ -0,0 +1,28 @@
+{
+  "guild": {
+    "id": "222",
+    "name": "Fixture Guild"
+  },
+  "channel": {
+    "id": "111",
+    "name": "fixture-room",
+    "category": "Testing Grounds"
+  },
+  "messages": [
+    {
+      "id": "999999999999999999",
+      "timestamp": "2026-01-01T00:00:00Z",
+      "content": "eighteen-digit-high-string-order"
+    },
+    {
+      "id": "1000000000000000000",
+      "timestamp": "2026-01-02T00:00:00Z",
+      "content": "nineteen-digit-true-max"
+    }
+  ],
+  "dateRange": {
+    "after": null,
+    "before": null
+  },
+  "exportedAt": "2026-01-02T00:00:00Z"
+}