From 972edac64dd74aa0d49c4dd2dd000a383ca3e9a0 Mon Sep 17 00:00:00 2001
From: Tessa Walsh <tessa@bitarchivist.net>
Date: Tue, 28 Oct 2025 11:48:33 -0400
Subject: [PATCH 01/13] Validate crawls being added to coll aren't failed

---
 backend/btrixcloud/basecrawls.py | 11 +++++++++++
 backend/btrixcloud/colls.py      |  2 ++
 2 files changed, 13 insertions(+)

diff --git a/backend/btrixcloud/basecrawls.py b/backend/btrixcloud/basecrawls.py
index 75f47a9d74..c2a1c45561 100644
--- a/backend/btrixcloud/basecrawls.py
+++ b/backend/btrixcloud/basecrawls.py
@@ -44,6 +44,7 @@
     UpdatedResponse,
     DeletedResponseQuota,
     CrawlSearchValuesResponse,
+    FAILED_STATES,
 )
 from .pagination import paginated_format, DEFAULT_PAGE_SIZE
 from .utils import dt_now, get_origin, date_to_str
@@ -613,10 +614,20 @@ async def bulk_presigned_files(
 
         return resources, pages_optimized
 
+    async def validate_all_crawls_successful(self, crawl_ids: List[str]):
+        """Validate that no crawls in list failed or else raise exception"""
+        result = await self.crawls.find_one(
+            {"_id": {"$in": crawl_ids}, "state": {"$in": FAILED_STATES}}
+        )
+        if result:
+            raise HTTPException(status_code=400, detail="invalid_failed_crawl")
+
     async def add_to_collection(
         self, crawl_ids: List[str], collection_id: UUID, org: Organization
     ):
         """Add crawls to collection."""
+        await self.validate_all_crawls_successful(crawl_ids)
+
         await self.crawls.update_many(
             {"_id": {"$in": crawl_ids}, "oid": org.id},
             {"$addToSet": {"collectionIds": collection_id}},
diff --git a/backend/btrixcloud/colls.py b/backend/btrixcloud/colls.py
index 404be5b73a..9c998a88ef 100644
--- a/backend/btrixcloud/colls.py
+++ b/backend/btrixcloud/colls.py
@@ -123,6 +123,8 @@ async def init_index(self):
     async def add_collection(self, oid: UUID, coll_in: CollIn):
         """Add new collection"""
         crawl_ids = coll_in.crawlIds if coll_in.crawlIds else []
+        await self.crawl_ops.validate_all_crawls_successful(crawl_ids)
+
         coll_id = uuid4()
         created = dt_now()
 

From 7d276e5ec6b5744974894904b265324c2e527700 Mon Sep 17 00:00:00 2001
From: Tessa Walsh <tessa@bitarchivist.net>
Date: Tue, 28 Oct 2025 11:54:24 -0400
Subject: [PATCH 02/13] Validate crawls successful and coll exists before
 updating crawls

---
 backend/btrixcloud/basecrawls.py | 2 --
 backend/btrixcloud/colls.py      | 4 +++-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/backend/btrixcloud/basecrawls.py b/backend/btrixcloud/basecrawls.py
index c2a1c45561..f93214d0c8 100644
--- a/backend/btrixcloud/basecrawls.py
+++ b/backend/btrixcloud/basecrawls.py
@@ -626,8 +626,6 @@ async def add_to_collection(
         self, crawl_ids: List[str], collection_id: UUID, org: Organization
     ):
         """Add crawls to collection."""
-        await self.validate_all_crawls_successful(crawl_ids)
-
         await self.crawls.update_many(
             {"_id": {"$in": crawl_ids}, "oid": org.id},
             {"$addToSet": {"collectionIds": collection_id}},
diff --git a/backend/btrixcloud/colls.py b/backend/btrixcloud/colls.py
index 9c998a88ef..59338fc0c8 100644
--- a/backend/btrixcloud/colls.py
+++ b/backend/btrixcloud/colls.py
@@ -230,7 +230,7 @@ async def add_crawls_to_collection(
         headers: Optional[dict] = None,
     ) -> CollOut:
         """Add crawls to collection"""
-        await self.crawl_ops.add_to_collection(crawl_ids, coll_id, org)
+        await self.crawl_ops.validate_all_crawls_successful(crawl_ids)
 
         modified = dt_now()
         result = await self.collections.find_one_and_update(
@@ -241,6 +241,8 @@ async def add_crawls_to_collection(
         if not result:
             raise HTTPException(status_code=404, detail="collection_not_found")
 
+        await self.crawl_ops.add_to_collection(crawl_ids, coll_id, org)
+
         await self.update_collection_counts_and_tags(coll_id)
         await self.update_collection_dates(coll_id, org.id)
 

From 11a194af9150d418c1c7404c355be3479cfbdb61 Mon Sep 17 00:00:00 2001
From: Tessa Walsh <tessa@bitarchivist.net>
Date: Tue, 28 Oct 2025 11:58:23 -0400
Subject: [PATCH 03/13] Ensure all crawls actually exist

---
 backend/btrixcloud/basecrawls.py | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/backend/btrixcloud/basecrawls.py b/backend/btrixcloud/basecrawls.py
index f93214d0c8..5edd32ccdd 100644
--- a/backend/btrixcloud/basecrawls.py
+++ b/backend/btrixcloud/basecrawls.py
@@ -615,12 +615,11 @@ async def bulk_presigned_files(
         return resources, pages_optimized
 
     async def validate_all_crawls_successful(self, crawl_ids: List[str]):
-        """Validate that no crawls in list failed or else raise exception"""
-        result = await self.crawls.find_one(
-            {"_id": {"$in": crawl_ids}, "state": {"$in": FAILED_STATES}}
-        )
-        if result:
-            raise HTTPException(status_code=400, detail="invalid_failed_crawl")
+        """Validate that crawls in list exist and are successful or else raise exception"""
+        for crawl_id in crawl_ids:
+            crawl = await self.get_base_crawl(crawl_id)
+            if crawl.state in FAILED_STATES:
+                raise HTTPException(status_code=400, detail="invalid_failed_crawl")
 
     async def add_to_collection(
         self, crawl_ids: List[str], collection_id: UUID, org: Organization

From 0b2a05a55e9881600de201e8ca335e01eca947b8 Mon Sep 17 00:00:00 2001
From: Tessa Walsh <tessa@bitarchivist.net>
Date: Tue, 28 Oct 2025 12:02:06 -0400
Subject: [PATCH 04/13] Add org check

---
 backend/btrixcloud/basecrawls.py |  6 ++++--
 backend/btrixcloud/colls.py      | 11 +++++------
 2 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/backend/btrixcloud/basecrawls.py b/backend/btrixcloud/basecrawls.py
index 5edd32ccdd..900b9ff8e0 100644
--- a/backend/btrixcloud/basecrawls.py
+++ b/backend/btrixcloud/basecrawls.py
@@ -614,10 +614,12 @@ async def bulk_presigned_files(
 
         return resources, pages_optimized
 
-    async def validate_all_crawls_successful(self, crawl_ids: List[str]):
+    async def validate_all_crawls_successful(
+        self, crawl_ids: List[str], org: Organization
+    ):
         """Validate that crawls in list exist and are successful or else raise exception"""
         for crawl_id in crawl_ids:
-            crawl = await self.get_base_crawl(crawl_id)
+            crawl = await self.get_base_crawl(crawl_id, org)
             if crawl.state in FAILED_STATES:
                 raise HTTPException(status_code=400, detail="invalid_failed_crawl")
 
diff --git a/backend/btrixcloud/colls.py b/backend/btrixcloud/colls.py
index 59338fc0c8..0b0451a816 100644
--- a/backend/btrixcloud/colls.py
+++ b/backend/btrixcloud/colls.py
@@ -120,10 +120,10 @@ async def init_index(self):
             [("oid", pymongo.ASCENDING), ("description", pymongo.ASCENDING)]
         )
 
-    async def add_collection(self, oid: UUID, coll_in: CollIn):
+    async def add_collection(self, org: Organization, coll_in: CollIn):
         """Add new collection"""
         crawl_ids = coll_in.crawlIds if coll_in.crawlIds else []
-        await self.crawl_ops.validate_all_crawls_successful(crawl_ids)
+        await self.crawl_ops.validate_all_crawls_successful(crawl_ids, org)
 
         coll_id = uuid4()
         created = dt_now()
@@ -132,7 +132,7 @@ async def add_collection(self, oid: UUID, coll_in: CollIn):
 
         coll = Collection(
             id=coll_id,
-            oid=oid,
+            oid=org.id,
             name=coll_in.name,
             slug=slug,
             description=coll_in.description,
@@ -145,7 +145,6 @@ async def add_collection(self, oid: UUID, coll_in: CollIn):
         )
         try:
             await self.collections.insert_one(coll.to_dict())
-            org = await self.orgs.get_org_by_id(oid)
             await self.clear_org_previous_slugs_matching_slug(slug, org)
 
             if crawl_ids:
@@ -230,7 +229,7 @@ async def add_crawls_to_collection(
         headers: Optional[dict] = None,
     ) -> CollOut:
         """Add crawls to collection"""
-        await self.crawl_ops.validate_all_crawls_successful(crawl_ids)
+        await self.crawl_ops.validate_all_crawls_successful(crawl_ids, org)
 
         modified = dt_now()
         result = await self.collections.find_one_and_update(
@@ -1022,7 +1021,7 @@ def init_collections_api(
     async def add_collection(
         new_coll: CollIn, org: Organization = Depends(org_crawl_dep)
     ):
-        return await colls.add_collection(org.id, new_coll)
+        return await colls.add_collection(org, new_coll)
 
     @app.get(
         "/orgs/{oid}/collections",

From 8278d1f703fc150d59de013005d92d7c52feb136 Mon Sep 17 00:00:00 2001
From: Tessa Walsh <tessa@bitarchivist.net>
Date: Tue, 28 Oct 2025 12:21:40 -0400
Subject: [PATCH 05/13] Update docstring

---
 backend/btrixcloud/basecrawls.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/backend/btrixcloud/basecrawls.py b/backend/btrixcloud/basecrawls.py
index 900b9ff8e0..edaf64d670 100644
--- a/backend/btrixcloud/basecrawls.py
+++ b/backend/btrixcloud/basecrawls.py
@@ -617,7 +617,7 @@ async def bulk_presigned_files(
     async def validate_all_crawls_successful(
         self, crawl_ids: List[str], org: Organization
     ):
-        """Validate that crawls in list exist and are successful or else raise exception"""
+        """Validate that crawls in list exist and did not fail or else raise exception"""
         for crawl_id in crawl_ids:
             crawl = await self.get_base_crawl(crawl_id, org)
             if crawl.state in FAILED_STATES:

From 29a387a9e583ddb4dc98f476e332a9bbbcb3071c Mon Sep 17 00:00:00 2001
From: Tessa Walsh <tessa@bitarchivist.net>
Date: Tue, 18 Nov 2025 18:19:09 -0500
Subject: [PATCH 06/13] Add tests

---
 backend/test/test_collections.py | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/backend/test/test_collections.py b/backend/test/test_collections.py
index dd28695a69..fee0bc3d49 100644
--- a/backend/test/test_collections.py
+++ b/backend/test/test_collections.py
@@ -1762,6 +1762,33 @@ def test_get_public_collection_slug_redirect(admin_auth_headers, default_org_id)
     assert r.status_code == 404
 
 
+def test_create_collection_with_failed_crawl(
+    admin_auth_headers, default_org_id, canceled_crawl_id
+):
+    r = requests.post(
+        f"{API_PREFIX}/orgs/{default_org_id}/collections",
+        headers=admin_auth_headers,
+        json={
+            "crawlIds": [canceled_crawl_id],
+            "name": "Should get rejected",
+        },
+    )
+    assert r.status_code == 400
+    assert r.json()["detail"] == "invalid_failed_crawl"
+
+
+def test_add_failed_crawl_to_collection(
+    admin_auth_headers, default_org_id, canceled_crawl_id
+):
+    r = requests.post(
+        f"{API_PREFIX}/orgs/{default_org_id}/collections/{_second_coll_id}/add",
+        json={"crawlIds": [canceled_crawl_id]},
+        headers=admin_auth_headers,
+    )
+    assert r.status_code == 400
+    assert r.json()["detail"] == "invalid_failed_crawl"
+
+
 def test_delete_collection(crawler_auth_headers, default_org_id, crawler_crawl_id):
     # Delete second collection
     r = requests.delete(

From b172d8040d0fa80edcae20a24eb98a2ed033b9fd Mon Sep 17 00:00:00 2001
From: Tessa Walsh <tessa@bitarchivist.net>
Date: Tue, 18 Nov 2025 18:55:54 -0500
Subject: [PATCH 07/13] Update other tests to account for fixture getting used
 earlier

---
 backend/test/conftest.py                       |  2 +-
 .../test/test_crawl_config_search_values.py    | 18 +++++++++++++++---
 backend/test/test_crawl_config_tags.py         |  5 ++++-
 backend/test/test_filter_sort_results.py       |  8 ++++----
 backend/test/test_uploads.py                   | 10 ++++++----
 5 files changed, 30 insertions(+), 13 deletions(-)

diff --git a/backend/test/conftest.py b/backend/test/conftest.py
index 47365fff2f..c949def1fe 100644
--- a/backend/test/conftest.py
+++ b/backend/test/conftest.py
@@ -563,7 +563,7 @@ def custom_behaviors_crawl_id(admin_auth_headers, default_org_id):
 def canceled_crawl_id(admin_auth_headers, default_org_id):
     crawl_data = {
         "runNow": True,
-        "name": "Canceled crawl",
+        "name": "Canceled Crawl",
         "tags": ["canceled"],
         "config": {
             "seeds": [{"url": "https://old.webrecorder.net/"}],
diff --git a/backend/test/test_crawl_config_search_values.py b/backend/test/test_crawl_config_search_values.py
index 0f1076b36a..fa7a0dd774 100644
--- a/backend/test/test_crawl_config_search_values.py
+++ b/backend/test/test_crawl_config_search_values.py
@@ -44,7 +44,7 @@ def test_get_search_values_1(admin_auth_headers, default_org_id):
     )
     data = r.json()
     assert sorted(data["names"]) == sorted(
-        [NAME_1, "Admin Test Crawl", "crawler User Test Crawl"]
+        [NAME_1, "Admin Test Crawl", "Canceled Crawl", "crawler User Test Crawl"]
     )
     assert sorted(data["descriptions"]) == sorted(
         ["Admin Test Crawl description", "crawler test crawl", DESCRIPTION_1]
@@ -74,7 +74,13 @@ def test_get_search_values_2(admin_auth_headers, default_org_id):
     )
     data = r.json()
     assert sorted(data["names"]) == sorted(
-        [NAME_1, NAME_2, "Admin Test Crawl", "crawler User Test Crawl"]
+        [
+            NAME_1,
+            NAME_2,
+            "Admin Test Crawl",
+            "Canceled Crawl",
+            "crawler User Test Crawl",
+        ]
     )
     assert sorted(data["descriptions"]) == sorted(
         [
@@ -111,7 +117,13 @@ def test_get_search_values_3(admin_auth_headers, default_org_id):
     )
     data = r.json()
     assert sorted(data["names"]) == sorted(
-        [NAME_1, NAME_2, "Admin Test Crawl", "crawler User Test Crawl"]
+        [
+            NAME_1,
+            NAME_2,
+            "Admin Test Crawl",
+            "Canceled Crawl",
+            "crawler User Test Crawl",
+        ]
     )
     assert sorted(data["descriptions"]) == sorted(
         [
diff --git a/backend/test/test_crawl_config_tags.py b/backend/test/test_crawl_config_tags.py
index e611f39cbb..5e33abd17b 100644
--- a/backend/test/test_crawl_config_tags.py
+++ b/backend/test/test_crawl_config_tags.py
@@ -47,7 +47,7 @@ def test_get_config_by_tag_1(admin_auth_headers, default_org_id):
         headers=admin_auth_headers,
     )
     data = r.json()
-    assert sorted(data) == ["tag-1", "tag-2", "wr-test-1", "wr-test-2"]
+    assert sorted(data) == ["canceled", "tag-1", "tag-2", "wr-test-1", "wr-test-2"]
 
 
 def test_get_config_by_tag_counts_1(admin_auth_headers, default_org_id):
@@ -59,6 +59,7 @@ def test_get_config_by_tag_counts_1(admin_auth_headers, default_org_id):
     assert data == {
         "tags": [
             {"tag": "wr-test-2", "count": 2},
+            {"tag": "canceled", "count": 1},
             {"tag": "tag-1", "count": 1},
             {"tag": "tag-2", "count": 1},
             {"tag": "wr-test-1", "count": 1},
@@ -91,6 +92,7 @@ def test_get_config_by_tag_2(admin_auth_headers, default_org_id):
     )
     data = r.json()
     assert sorted(data) == [
+        "canceled",
         "tag-0",
         "tag-1",
         "tag-2",
@@ -109,6 +111,7 @@ def test_get_config_by_tag_counts_2(admin_auth_headers, default_org_id):
     assert data == {
         "tags": [
             {"tag": "wr-test-2", "count": 2},
+            {"tag": "canceled", "count": 1},
             {"tag": "tag-0", "count": 1},
             {"tag": "tag-1", "count": 1},
             {"tag": "tag-2", "count": 1},
diff --git a/backend/test/test_filter_sort_results.py b/backend/test/test_filter_sort_results.py
index 5eaf2d8e1a..e6bb653284 100644
--- a/backend/test/test_filter_sort_results.py
+++ b/backend/test/test_filter_sort_results.py
@@ -102,8 +102,8 @@ def test_ensure_crawl_and_admin_user_crawls(
         f"{API_PREFIX}/orgs/{default_org_id}/crawls",
         headers=crawler_auth_headers,
     )
-    assert len(r.json()["items"]) == 2
-    assert r.json()["total"] == 2
+    assert len(r.json()["items"]) == 3
+    assert r.json()["total"] == 3
 
 
 def test_get_crawl_job_by_user(
@@ -212,9 +212,9 @@ def test_sort_crawls(
         headers=crawler_auth_headers,
     )
     data = r.json()
-    assert data["total"] == 2
+    assert data["total"] == 3
     items = data["items"]
-    assert len(items) == 2
+    assert len(items) == 3
 
     last_created = None
     for crawl in items:
diff --git a/backend/test/test_uploads.py b/backend/test/test_uploads.py
index 90c11e8061..d9ee60de1a 100644
--- a/backend/test/test_uploads.py
+++ b/backend/test/test_uploads.py
@@ -592,7 +592,7 @@ def test_get_all_crawls_by_first_seed(
     )
     assert r.status_code == 200
     data = r.json()
-    assert data["total"] == 5
+    assert data["total"] == 6
     for item in data["items"]:
         assert item["firstSeed"] == first_seed
 
@@ -607,7 +607,7 @@ def test_get_all_crawls_by_type(
     )
     assert r.status_code == 200
     data = r.json()
-    assert data["total"] == 6
+    assert data["total"] == 7
     for item in data["items"]:
         assert item["type"] == "crawl"
 
@@ -823,9 +823,10 @@ def test_all_crawls_search_values(
     assert r.status_code == 200
     data = r.json()
 
-    assert len(data["names"]) == 8
+    assert len(data["names"]) == 9
     expected_names = [
         "crawler User Test Crawl",
+        "Canceled Crawl",
         "Custom Behavior Logs",
         "My Upload Updated",
         "test2.wacz",
@@ -849,10 +850,11 @@ def test_all_crawls_search_values(
     assert r.status_code == 200
     data = r.json()
 
-    assert len(data["names"]) == 5
+    assert len(data["names"]) == 6
     expected_names = [
         "Admin Test Crawl",
         "All Crawls Test Crawl",
+        "Canceled Crawl",
         "Crawler User Crawl for Testing QA",
         "crawler User Test Crawl",
         "Custom Behavior Logs",

From 3d1de7bd446d3abb80d71e5a3520b916364adf22 Mon Sep 17 00:00:00 2001
From: Ilya Kreymer <ikreymer@gmail.com>
Date: Wed, 26 Nov 2025 15:35:53 -0800
Subject: [PATCH 08/13] optimize validate_all_crawls_successful()

---
 backend/btrixcloud/basecrawls.py | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/backend/btrixcloud/basecrawls.py b/backend/btrixcloud/basecrawls.py
index edaf64d670..e09436d462 100644
--- a/backend/btrixcloud/basecrawls.py
+++ b/backend/btrixcloud/basecrawls.py
@@ -44,7 +44,6 @@
     UpdatedResponse,
     DeletedResponseQuota,
     CrawlSearchValuesResponse,
-    FAILED_STATES,
 )
 from .pagination import paginated_format, DEFAULT_PAGE_SIZE
 from .utils import dt_now, get_origin, date_to_str
@@ -617,11 +616,18 @@ async def bulk_presigned_files(
     async def validate_all_crawls_successful(
         self, crawl_ids: List[str], org: Organization
     ):
-        """Validate that crawls in list exist and did not fail or else raise exception"""
-        for crawl_id in crawl_ids:
-            crawl = await self.get_base_crawl(crawl_id, org)
-            if crawl.state in FAILED_STATES:
-                raise HTTPException(status_code=400, detail="invalid_failed_crawl")
+        """Validate that crawls in list exist and have a succesful state, or throw"""
+        count = self.crawls.count_documents(
+            {
+                "_id": {"$in": crawl_ids},
+                "oid": org.id,
+                "state": {"$in": SUCCESSFUL_STATES},
+            }
+        )
+        if count != len(crawl_ids):
+            raise HTTPException(
+                status_code=400, detail="invalid_failed_or_unfinished_crawl"
+            )
 
     async def add_to_collection(
         self, crawl_ids: List[str], collection_id: UUID, org: Organization

From 66822f35bc872c2d31c500ebef740c4476c6b333 Mon Sep 17 00:00:00 2001
From: Ilya Kreymer <ikreymer@gmail.com>
Date: Wed, 26 Nov 2025 15:40:29 -0800
Subject: [PATCH 09/13] convert to set to remove any duplicates, just in case

---
 backend/btrixcloud/basecrawls.py | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/backend/btrixcloud/basecrawls.py b/backend/btrixcloud/basecrawls.py
index e09436d462..c71679edae 100644
--- a/backend/btrixcloud/basecrawls.py
+++ b/backend/btrixcloud/basecrawls.py
@@ -617,14 +617,17 @@ async def validate_all_crawls_successful(
         self, crawl_ids: List[str], org: Organization
     ):
         """Validate that crawls in list exist and have a succesful state, or throw"""
+        # convert to set to remove any duplicates
+        crawl_id_set = set(crawl_ids)
+
         count = self.crawls.count_documents(
             {
-                "_id": {"$in": crawl_ids},
+                "_id": {"$in": crawl_id_set},
                 "oid": org.id,
                 "state": {"$in": SUCCESSFUL_STATES},
             }
         )
-        if count != len(crawl_ids):
+        if count != len(crawl_id_set):
             raise HTTPException(
                 status_code=400, detail="invalid_failed_or_unfinished_crawl"
             )

From 6e840a10c797970f8802e4c97d60de0a66f1307d Mon Sep 17 00:00:00 2001
From: Ilya Kreymer <ikreymer@gmail.com>
Date: Wed, 26 Nov 2025 16:22:45 -0800
Subject: [PATCH 10/13] fix typo, fix tests

---
 backend/btrixcloud/basecrawls.py                | 2 +-
 backend/test/conftest.py                        | 2 +-
 backend/test/test_crawl_config_search_values.py | 6 +++---
 backend/test/test_uploads.py                    | 4 ++--
 4 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/backend/btrixcloud/basecrawls.py b/backend/btrixcloud/basecrawls.py
index c71679edae..af822afa4a 100644
--- a/backend/btrixcloud/basecrawls.py
+++ b/backend/btrixcloud/basecrawls.py
@@ -620,7 +620,7 @@ async def validate_all_crawls_successful(
         # convert to set to remove any duplicates
         crawl_id_set = set(crawl_ids)
 
-        count = self.crawls.count_documents(
+        count = await self.crawls.count_documents(
             {
                 "_id": {"$in": crawl_id_set},
                 "oid": org.id,
diff --git a/backend/test/conftest.py b/backend/test/conftest.py
index c949def1fe..47365fff2f 100644
--- a/backend/test/conftest.py
+++ b/backend/test/conftest.py
@@ -563,7 +563,7 @@ def custom_behaviors_crawl_id(admin_auth_headers, default_org_id):
 def canceled_crawl_id(admin_auth_headers, default_org_id):
     crawl_data = {
         "runNow": True,
-        "name": "Canceled Crawl",
+        "name": "Canceled crawl",
         "tags": ["canceled"],
         "config": {
             "seeds": [{"url": "https://old.webrecorder.net/"}],
diff --git a/backend/test/test_crawl_config_search_values.py b/backend/test/test_crawl_config_search_values.py
index fa7a0dd774..7c096d647a 100644
--- a/backend/test/test_crawl_config_search_values.py
+++ b/backend/test/test_crawl_config_search_values.py
@@ -44,7 +44,7 @@ def test_get_search_values_1(admin_auth_headers, default_org_id):
     )
     data = r.json()
     assert sorted(data["names"]) == sorted(
-        [NAME_1, "Admin Test Crawl", "Canceled Crawl", "crawler User Test Crawl"]
+        [NAME_1, "Admin Test Crawl", "Canceled crawl", "crawler User Test Crawl"]
     )
     assert sorted(data["descriptions"]) == sorted(
         ["Admin Test Crawl description", "crawler test crawl", DESCRIPTION_1]
@@ -78,7 +78,7 @@ def test_get_search_values_2(admin_auth_headers, default_org_id):
             NAME_1,
             NAME_2,
             "Admin Test Crawl",
-            "Canceled Crawl",
+            "Canceled crawl",
             "crawler User Test Crawl",
         ]
     )
@@ -121,7 +121,7 @@ def test_get_search_values_3(admin_auth_headers, default_org_id):
             NAME_1,
             NAME_2,
             "Admin Test Crawl",
-            "Canceled Crawl",
+            "Canceled crawl",
             "crawler User Test Crawl",
         ]
     )
diff --git a/backend/test/test_uploads.py b/backend/test/test_uploads.py
index d9ee60de1a..d39ba0ca3c 100644
--- a/backend/test/test_uploads.py
+++ b/backend/test/test_uploads.py
@@ -826,7 +826,7 @@ def test_all_crawls_search_values(
     assert len(data["names"]) == 9
     expected_names = [
         "crawler User Test Crawl",
-        "Canceled Crawl",
+        "Canceled crawl",
         "Custom Behavior Logs",
         "My Upload Updated",
         "test2.wacz",
@@ -854,7 +854,7 @@ def test_all_crawls_search_values(
     expected_names = [
         "Admin Test Crawl",
         "All Crawls Test Crawl",
-        "Canceled Crawl",
+        "Canceled crawl",
         "Crawler User Crawl for Testing QA",
         "crawler User Test Crawl",
         "Custom Behavior Logs",

From 75e717a3822cbe3fcfdca072f2f1b5fe01ac64e4 Mon Sep 17 00:00:00 2001
From: Tessa Walsh <tessa@bitarchivist.net>
Date: Thu, 27 Nov 2025 13:42:14 -0500
Subject: [PATCH 11/13] Update expected 400 detail in tests

---
 backend/test/test_collections.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/backend/test/test_collections.py b/backend/test/test_collections.py
index fee0bc3d49..a5e0c891bf 100644
--- a/backend/test/test_collections.py
+++ b/backend/test/test_collections.py
@@ -1774,7 +1774,7 @@ def test_create_collection_with_failed_crawl(
         },
     )
     assert r.status_code == 400
-    assert r.json()["detail"] == "invalid_failed_crawl"
+    assert r.json()["detail"] == "invalid_failed_or_unfinished_crawl"
 
 
 def test_add_failed_crawl_to_collection(
@@ -1786,7 +1786,7 @@ def test_add_failed_crawl_to_collection(
         headers=admin_auth_headers,
     )
     assert r.status_code == 400
-    assert r.json()["detail"] == "invalid_failed_crawl"
+    assert r.json()["detail"] == "invalid_failed_or_unfinished_crawl"
 
 
 def test_delete_collection(crawler_auth_headers, default_org_id, crawler_crawl_id):

From 25be8f45064cfc6880d749a36c55a5ce461fc4a5 Mon Sep 17 00:00:00 2001
From: Tessa Walsh <tessa@bitarchivist.net>
Date: Thu, 27 Nov 2025 14:16:00 -0500
Subject: [PATCH 12/13] Pass list not set of crawl_ids to count_documents

---
 backend/btrixcloud/basecrawls.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/backend/btrixcloud/basecrawls.py b/backend/btrixcloud/basecrawls.py
index af822afa4a..031f1844cd 100644
--- a/backend/btrixcloud/basecrawls.py
+++ b/backend/btrixcloud/basecrawls.py
@@ -622,7 +622,7 @@ async def validate_all_crawls_successful(
 
         count = await self.crawls.count_documents(
             {
-                "_id": {"$in": crawl_id_set},
+                "_id": {"$in": list(crawl_id_set)},
                 "oid": org.id,
                 "state": {"$in": SUCCESSFUL_STATES},
             }

From 17241587f59cc14e7cdd37f7382296817dbb9f0e Mon Sep 17 00:00:00 2001
From: Tessa Walsh <tessa@bitarchivist.net>
Date: Thu, 27 Nov 2025 14:45:16 -0500
Subject: [PATCH 13/13] Update crawlconfig count in test

---
 backend/test/test_filter_sort_results.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/backend/test/test_filter_sort_results.py b/backend/test/test_filter_sort_results.py
index e6bb653284..a7b71d017d 100644
--- a/backend/test/test_filter_sort_results.py
+++ b/backend/test/test_filter_sort_results.py
@@ -362,9 +362,9 @@ def test_sort_crawl_configs(
         headers=crawler_auth_headers,
     )
     data = r.json()
-    assert data["total"] == 17
+    assert data["total"] == 18
     items = data["items"]
-    assert len(items) == 17
+    assert len(items) == 18
 
     last_created = None
     for config in items: