@tangle-network/agent-eval 0.120.3 → 0.121.0

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.
Files changed (34) hide show
  1. package/CHANGELOG.md +4 -9
  2. package/dist/analyst/index.js +4 -4
  3. package/dist/benchmarks/index.js +6 -6
  4. package/dist/campaign/index.js +5 -5
  5. package/dist/{chunk-3CDFMEMO.js → chunk-32BZXMSO.js} +5 -5
  6. package/dist/{chunk-SQQED7ZH.js → chunk-3A246TSA.js} +2 -2
  7. package/dist/{chunk-NMN4WGSJ.js → chunk-4I2E3LLO.js} +2 -2
  8. package/dist/{chunk-ZMXDQ4K7.js → chunk-JHOJHHU7.js} +5 -8
  9. package/dist/{chunk-ZMXDQ4K7.js.map → chunk-JHOJHHU7.js.map} +1 -1
  10. package/dist/{chunk-3XH4Y2SS.js → chunk-JM2SKQMS.js} +3 -3
  11. package/dist/{chunk-P5MGQ2FY.js → chunk-JN2FCO5W.js} +5 -5
  12. package/dist/{chunk-CVJP5TMD.js → chunk-PICTDURQ.js} +2 -2
  13. package/dist/{chunk-5BYTIDZ7.js → chunk-QWMPPZ3X.js} +2 -2
  14. package/dist/{chunk-5CVUPHJ4.js → chunk-S5TT5R3L.js} +2 -2
  15. package/dist/{chunk-SYV364BL.js → chunk-XDIRG3TO.js} +2 -2
  16. package/dist/cli.js +2 -2
  17. package/dist/contract/index.js +6 -7
  18. package/dist/contract/index.js.map +1 -1
  19. package/dist/fuzz.js +1 -1
  20. package/dist/index.js +9 -9
  21. package/dist/openapi.json +1 -1
  22. package/dist/{run-campaign-75RTPVV5.js → run-campaign-HNFPJET4.js} +3 -3
  23. package/dist/wire/index.js +2 -2
  24. package/package.json +2 -2
  25. /package/dist/{chunk-3CDFMEMO.js.map → chunk-32BZXMSO.js.map} +0 -0
  26. /package/dist/{chunk-SQQED7ZH.js.map → chunk-3A246TSA.js.map} +0 -0
  27. /package/dist/{chunk-NMN4WGSJ.js.map → chunk-4I2E3LLO.js.map} +0 -0
  28. /package/dist/{chunk-3XH4Y2SS.js.map → chunk-JM2SKQMS.js.map} +0 -0
  29. /package/dist/{chunk-P5MGQ2FY.js.map → chunk-JN2FCO5W.js.map} +0 -0
  30. /package/dist/{chunk-CVJP5TMD.js.map → chunk-PICTDURQ.js.map} +0 -0
  31. /package/dist/{chunk-5BYTIDZ7.js.map → chunk-QWMPPZ3X.js.map} +0 -0
  32. /package/dist/{chunk-5CVUPHJ4.js.map → chunk-S5TT5R3L.js.map} +0 -0
  33. /package/dist/{chunk-SYV364BL.js.map → chunk-XDIRG3TO.js.map} +0 -0
  34. /package/dist/{run-campaign-75RTPVV5.js.map → run-campaign-HNFPJET4.js.map} +0 -0
package/dist/fuzz.js CHANGED
@@ -1,7 +1,7 @@
1
1
  import {
2
2
  CostLedger,
3
3
  CostReceiptCaptureError
4
- } from "./chunk-ZMXDQ4K7.js";
4
+ } from "./chunk-JHOJHHU7.js";
5
5
  import "./chunk-VI2UW6B6.js";
6
6
  import {
7
7
  varianceBasedCurriculum
package/dist/index.js CHANGED
@@ -9,12 +9,12 @@ import {
9
9
  checkBehavioralCanary,
10
10
  checkCanaries,
11
11
  runBehavioralCanaries
12
- } from "./chunk-SQQED7ZH.js";
12
+ } from "./chunk-3A246TSA.js";
13
13
  import {
14
14
  BENCHMARK_SPLIT_SEED,
15
15
  benchmarks_exports,
16
16
  deterministicSplit
17
- } from "./chunk-CVJP5TMD.js";
17
+ } from "./chunk-PICTDURQ.js";
18
18
  import {
19
19
  DEFAULT_RULES,
20
20
  buildTrajectory,
@@ -51,7 +51,7 @@ import {
51
51
  harnessAxisOf,
52
52
  parseCorrectnessResponse,
53
53
  verifyCompletion
54
- } from "./chunk-P5MGQ2FY.js";
54
+ } from "./chunk-JN2FCO5W.js";
55
55
  import {
56
56
  DEFAULT_MUTATION_PRIMITIVES,
57
57
  DEFAULT_RED_TEAM_CORPUS,
@@ -91,7 +91,7 @@ import {
91
91
  scoreRedTeamOutput,
92
92
  surfaceContentHash,
93
93
  toolNamesForRun
94
- } from "./chunk-3CDFMEMO.js";
94
+ } from "./chunk-32BZXMSO.js";
95
95
  import {
96
96
  BackendIntegrityError,
97
97
  assertRealAgentReceipts,
@@ -103,7 +103,7 @@ import {
103
103
  inMemoryVerdictCache,
104
104
  summarizeAgentReceiptIntegrity,
105
105
  summarizeBackendIntegrity
106
- } from "./chunk-SYV364BL.js";
106
+ } from "./chunk-XDIRG3TO.js";
107
107
  import {
108
108
  DEFAULT_COMPLEXITY_WEIGHTS,
109
109
  FindingsStore,
@@ -116,12 +116,12 @@ import {
116
116
  defaultIsMaterial,
117
117
  diffFindings,
118
118
  runSemanticConceptJudge
119
- } from "./chunk-3XH4Y2SS.js";
119
+ } from "./chunk-JM2SKQMS.js";
120
120
  import {
121
121
  buildDefaultAnalystRegistry,
122
122
  computeTraceMetrics,
123
123
  createChatClient
124
- } from "./chunk-5BYTIDZ7.js";
124
+ } from "./chunk-QWMPPZ3X.js";
125
125
  import "./chunk-HHWE3POT.js";
126
126
  import {
127
127
  Mutex
@@ -157,7 +157,7 @@ import {
157
157
  scorePolicyEditReadiness,
158
158
  validatePolicyEdit,
159
159
  validatePolicyEditCandidateRecord
160
- } from "./chunk-5CVUPHJ4.js";
160
+ } from "./chunk-S5TT5R3L.js";
161
161
  import {
162
162
  allCriticalPassed,
163
163
  controlFailureClassFromVerification,
@@ -267,7 +267,7 @@ import {
267
267
  CostReservationExceededError,
268
268
  costForUsage,
269
269
  modelPriceKey
270
- } from "./chunk-ZMXDQ4K7.js";
270
+ } from "./chunk-JHOJHHU7.js";
271
271
  import {
272
272
  MODEL_PRICING,
273
273
  MetricsCollector,
package/dist/openapi.json CHANGED
@@ -2,7 +2,7 @@
2
2
  "openapi": "3.1.0",
3
3
  "info": {
4
4
  "title": "@tangle-network/agent-eval — wire protocol",
5
- "version": "0.120.3",
5
+ "version": "0.121.0",
6
6
  "description": "HTTP and stdio RPC interface to agent-eval. The TypeScript runtime is the source of truth; this spec is the contract that cross-language clients (Python, Rust, Go) generate from.\n\nWire-protocol version: 1.0.0. Bumps on breaking changes to request/response schemas.",
7
7
  "contact": {
8
8
  "name": "Tangle Network",
@@ -1,9 +1,9 @@
1
1
  import {
2
2
  planCampaignRun,
3
3
  runCampaign
4
- } from "./chunk-SYV364BL.js";
4
+ } from "./chunk-XDIRG3TO.js";
5
5
  import "./chunk-PJQFMIOX.js";
6
- import "./chunk-ZMXDQ4K7.js";
6
+ import "./chunk-JHOJHHU7.js";
7
7
  import "./chunk-VI2UW6B6.js";
8
8
  import "./chunk-ONWEPEDO.js";
9
9
  import "./chunk-PZ5AY32C.js";
@@ -11,4 +11,4 @@ export {
11
11
  planCampaignRun,
12
12
  runCampaign
13
13
  };
14
- //# sourceMappingURL=run-campaign-75RTPVV5.js.map
14
+ //# sourceMappingURL=run-campaign-HNFPJET4.js.map
@@ -34,9 +34,9 @@ import {
34
34
  runRpcOnce,
35
35
  startServer,
36
36
  startServerAsync
37
- } from "../chunk-NMN4WGSJ.js";
37
+ } from "../chunk-4I2E3LLO.js";
38
38
  import "../chunk-NJC7U437.js";
39
- import "../chunk-ZMXDQ4K7.js";
39
+ import "../chunk-JHOJHHU7.js";
40
40
  import "../chunk-VI2UW6B6.js";
41
41
  import "../chunk-PC4UYEBM.js";
42
42
  import "../chunk-ONWEPEDO.js";
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@tangle-network/agent-eval",
3
- "version": "0.120.3",
3
+ "version": "0.121.0",
4
4
  "description": "Evaluate and improve AI agents from runs, traces, judges, and feedback. Compare candidates, cluster failures, measure lift, and gate releases.",
5
5
  "homepage": "https://github.com/tangle-network/agent-eval#readme",
6
6
  "repository": {
@@ -152,7 +152,7 @@
152
152
  "@ax-llm/ax": "^23.0.0",
153
153
  "@hono/node-server": "^2.0.0",
154
154
  "@tangle-network/agent-core": "^0.4.11",
155
- "@tangle-network/agent-interface": "^0.26.0",
155
+ "@tangle-network/agent-interface": "^0.28.0",
156
156
  "@tangle-network/tcloud": "^0.4.14",
157
157
  "hono": "^4.12.30",
158
158
  "zod": "^4.3.6"