You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
chore: remove unused handleChatStream (all traffic goes through x402)
Since /api/chat now routes through x402, handleChatStream is no longer
used. Remove it and its tests to follow YAGNI principle.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Copy file name to clipboardExpand all lines: evals/first-week-album-sales.eval.ts
+4-8Lines changed: 4 additions & 8 deletions
Original file line number
Diff line number
Diff line change
@@ -14,8 +14,7 @@ import { callChatFunctions } from "@/lib/evals";
14
14
Eval("First Week Album Sales Evaluation",{
15
15
data: ()=>[
16
16
{
17
-
input:
18
-
"how many albums did Halsey The Great Impersonator sell the first week of release",
17
+
input: "how many albums did Halsey The Great Impersonator sell the first week of release",
19
18
expected:
20
19
"Halsey's album 'The Great Impersonator' sold between 93,000 and 100,000 copies in its first week of release. It debuted at No. 2 on the Billboard 200 chart.",
21
20
metadata: {
@@ -26,8 +25,7 @@ Eval("First Week Album Sales Evaluation", {
26
25
},
27
26
},
28
27
{
29
-
input:
30
-
"what were the first week sales for Taylor Swift's Midnights album?",
28
+
input: "what were the first week sales for Taylor Swift's Midnights album?",
31
29
expected:
32
30
"Taylor Swift's Midnights sold 1.578 million equivalent album units in its first week in the United States, which included between 1 million and 1.5 million pure album sales. This marked the biggest sales week for any album since Adele's 25 in 2015 and the best sales week for a vinyl album in the modern tracking era.",
33
31
metadata: {
@@ -38,8 +36,7 @@ Eval("First Week Album Sales Evaluation", {
38
36
},
39
37
},
40
38
{
41
-
input:
42
-
"how many copies did Drake's Certified Lover Boy sell in the first week",
39
+
input: "how many copies did Drake's Certified Lover Boy sell in the first week",
43
40
expected:
44
41
"Drake's 'Certified Lover Boy' sold approximately 613,000 album-equivalent units in its first week, securing the #1 spot on the Billboard 200 chart.",
45
42
metadata: {
@@ -50,8 +47,7 @@ Eval("First Week Album Sales Evaluation", {
50
47
},
51
48
},
52
49
{
53
-
input:
54
-
"what are the first week streaming numbers for Bad Bunny's Un Verano Sin Ti",
50
+
input: "what are the first week streaming numbers for Bad Bunny's Un Verano Sin Ti",
55
51
expected:
56
52
"In its first week of release in the United States, Bad Bunny's album Un Verano Sin Ti garnered over 355 million on-demand streams and 274,000 album-equivalent units, the most for any album that year and the largest streaming week for a Latin album ever at that time. The album also set a record for the biggest debut for a Latin album in Spotify's history.",
0 commit comments