opencode-harness-kit 0.4.5 → 0.4.6
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +12 -0
- package/eval/models.mjs +20 -9
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -12,6 +12,18 @@ is not happening.
|
|
|
12
12
|
|
|
13
13
|
---
|
|
14
14
|
|
|
15
|
+
## [0.4.6] — 2026-10-21
|
|
16
|
+
|
|
17
|
+
Published. The tag is what cut it: `git tag v0.4.6 && git push origin main
|
|
18
|
+
v0.4.6`, and the publish job watches for exactly that.
|
|
19
|
+
|
|
20
|
+
### Fixed
|
|
21
|
+
|
|
22
|
+
- **The model measurement table said `0 null`** when a model that publishes
|
|
23
|
+
a `low` effort level failed every request for that variant. A row of
|
|
24
|
+
zeroes reads like a measurement of nothing; a row that says the request
|
|
25
|
+
failed says what happened.
|
|
26
|
+
|
|
15
27
|
## [0.4.5] — 2026-10-21
|
|
16
28
|
|
|
17
29
|
Published. The tag is what cut it: `git tag v0.4.5 && git push origin main
|
package/eval/models.mjs
CHANGED
|
@@ -276,15 +276,26 @@ for (const r of rows) {
|
|
|
276
276
|
String(r.output).padStart(10),
|
|
277
277
|
)
|
|
278
278
|
if (r.publishes_low) {
|
|
279
|
-
|
|
280
|
-
|
|
281
|
-
|
|
282
|
-
|
|
283
|
-
|
|
284
|
-
""
|
|
285
|
-
|
|
286
|
-
|
|
287
|
-
|
|
279
|
+
if (!r.low_requests) {
|
|
280
|
+
// The model publishes `low` and every request for it failed. Saying
|
|
281
|
+
// "0 null" reads like a measurement of nothing; saying it failed says
|
|
282
|
+
// what happened.
|
|
283
|
+
console.log(
|
|
284
|
+
" " +
|
|
285
|
+
`${r.model} @low`.padEnd(30) +
|
|
286
|
+
"no request for the low variant succeeded".padStart(10),
|
|
287
|
+
)
|
|
288
|
+
} else {
|
|
289
|
+
console.log(
|
|
290
|
+
" " +
|
|
291
|
+
`${r.model} @low`.padEnd(30) +
|
|
292
|
+
String(r.low_requests).padStart(10) +
|
|
293
|
+
String(r.low_avg_ms).padStart(10) +
|
|
294
|
+
"".padStart(10) +
|
|
295
|
+
"".padStart(10) +
|
|
296
|
+
String(r.low_reasoning).padStart(10),
|
|
297
|
+
)
|
|
298
|
+
}
|
|
288
299
|
} else if (withEffort) {
|
|
289
300
|
console.log(
|
|
290
301
|
" " +
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "opencode-harness-kit",
|
|
3
|
-
"version": "0.4.
|
|
3
|
+
"version": "0.4.6",
|
|
4
4
|
"description": "Harness kit for OpenCode: capability profiles, a fleet of job lanes with one free model each, role-based reasoning effort, context pruning, and measured baselines.",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"homepage": "https://github.com/pham-canh/space-harness#readme",
|