@oro-ai/sdk 1.0.23 → 1.0.25
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/dist/index.d.mts +16 -0
- package/dist/index.d.ts +16 -0
- package/package.json +1 -1
- package/src/generated/types.gen.ts +16 -0
package/dist/index.d.mts
CHANGED
|
@@ -1230,6 +1230,14 @@ type EvaluationRunPublic = {
|
|
|
1230
1230
|
* Score on success
|
|
1231
1231
|
*/
|
|
1232
1232
|
validator_score?: (number | null);
|
|
1233
|
+
/**
|
|
1234
|
+
* Average reasoning quality from LLM judge (0-1)
|
|
1235
|
+
*/
|
|
1236
|
+
reasoning_quality?: (number | null);
|
|
1237
|
+
/**
|
|
1238
|
+
* Reasoning coefficient applied to outcome score (0.3-1.0)
|
|
1239
|
+
*/
|
|
1240
|
+
reasoning_coefficient?: (number | null);
|
|
1233
1241
|
/**
|
|
1234
1242
|
* Score breakdown on success
|
|
1235
1243
|
*/
|
|
@@ -1788,6 +1796,10 @@ type ProblemProgressUpdate = {
|
|
|
1788
1796
|
* S3 key for this problem's logs
|
|
1789
1797
|
*/
|
|
1790
1798
|
logs_s3_key?: (string | null);
|
|
1799
|
+
/**
|
|
1800
|
+
* Reasoning quality score from LLM judge
|
|
1801
|
+
*/
|
|
1802
|
+
reasoning_score?: (number | null);
|
|
1791
1803
|
/**
|
|
1792
1804
|
* Number of failed inference calls (429s, timeouts) for this problem
|
|
1793
1805
|
*/
|
|
@@ -2342,6 +2354,10 @@ type ValidatorProblemResult = {
|
|
|
2342
2354
|
score_components?: ({
|
|
2343
2355
|
[key: string]: unknown;
|
|
2344
2356
|
} | null);
|
|
2357
|
+
/**
|
|
2358
|
+
* Reasoning quality score from LLM judge
|
|
2359
|
+
*/
|
|
2360
|
+
reasoning_score?: (number | null);
|
|
2345
2361
|
/**
|
|
2346
2362
|
* Last update from this validator
|
|
2347
2363
|
*/
|
package/dist/index.d.ts
CHANGED
|
@@ -1230,6 +1230,14 @@ type EvaluationRunPublic = {
|
|
|
1230
1230
|
* Score on success
|
|
1231
1231
|
*/
|
|
1232
1232
|
validator_score?: (number | null);
|
|
1233
|
+
/**
|
|
1234
|
+
* Average reasoning quality from LLM judge (0-1)
|
|
1235
|
+
*/
|
|
1236
|
+
reasoning_quality?: (number | null);
|
|
1237
|
+
/**
|
|
1238
|
+
* Reasoning coefficient applied to outcome score (0.3-1.0)
|
|
1239
|
+
*/
|
|
1240
|
+
reasoning_coefficient?: (number | null);
|
|
1233
1241
|
/**
|
|
1234
1242
|
* Score breakdown on success
|
|
1235
1243
|
*/
|
|
@@ -1788,6 +1796,10 @@ type ProblemProgressUpdate = {
|
|
|
1788
1796
|
* S3 key for this problem's logs
|
|
1789
1797
|
*/
|
|
1790
1798
|
logs_s3_key?: (string | null);
|
|
1799
|
+
/**
|
|
1800
|
+
* Reasoning quality score from LLM judge
|
|
1801
|
+
*/
|
|
1802
|
+
reasoning_score?: (number | null);
|
|
1791
1803
|
/**
|
|
1792
1804
|
* Number of failed inference calls (429s, timeouts) for this problem
|
|
1793
1805
|
*/
|
|
@@ -2342,6 +2354,10 @@ type ValidatorProblemResult = {
|
|
|
2342
2354
|
score_components?: ({
|
|
2343
2355
|
[key: string]: unknown;
|
|
2344
2356
|
} | null);
|
|
2357
|
+
/**
|
|
2358
|
+
* Reasoning quality score from LLM judge
|
|
2359
|
+
*/
|
|
2360
|
+
reasoning_score?: (number | null);
|
|
2345
2361
|
/**
|
|
2346
2362
|
* Last update from this validator
|
|
2347
2363
|
*/
|
package/package.json
CHANGED
|
@@ -1282,6 +1282,14 @@ export type EvaluationRunPublic = {
|
|
|
1282
1282
|
* Score on success
|
|
1283
1283
|
*/
|
|
1284
1284
|
validator_score?: (number | null);
|
|
1285
|
+
/**
|
|
1286
|
+
* Average reasoning quality from LLM judge (0-1)
|
|
1287
|
+
*/
|
|
1288
|
+
reasoning_quality?: (number | null);
|
|
1289
|
+
/**
|
|
1290
|
+
* Reasoning coefficient applied to outcome score (0.3-1.0)
|
|
1291
|
+
*/
|
|
1292
|
+
reasoning_coefficient?: (number | null);
|
|
1285
1293
|
/**
|
|
1286
1294
|
* Score breakdown on success
|
|
1287
1295
|
*/
|
|
@@ -1869,6 +1877,10 @@ export type ProblemProgressUpdate = {
|
|
|
1869
1877
|
* S3 key for this problem's logs
|
|
1870
1878
|
*/
|
|
1871
1879
|
logs_s3_key?: (string | null);
|
|
1880
|
+
/**
|
|
1881
|
+
* Reasoning quality score from LLM judge
|
|
1882
|
+
*/
|
|
1883
|
+
reasoning_score?: (number | null);
|
|
1872
1884
|
/**
|
|
1873
1885
|
* Number of failed inference calls (429s, timeouts) for this problem
|
|
1874
1886
|
*/
|
|
@@ -2453,6 +2465,10 @@ export type ValidatorProblemResult = {
|
|
|
2453
2465
|
score_components?: ({
|
|
2454
2466
|
[key: string]: unknown;
|
|
2455
2467
|
} | null);
|
|
2468
|
+
/**
|
|
2469
|
+
* Reasoning quality score from LLM judge
|
|
2470
|
+
*/
|
|
2471
|
+
reasoning_score?: (number | null);
|
|
2456
2472
|
/**
|
|
2457
2473
|
* Last update from this validator
|
|
2458
2474
|
*/
|