@tangle-network/agent-eval 1.0.9 → 1.0.10
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 +23 -0
- package/dist/openapi.json +1 -1
- package/dist/wire/index.d.ts +2 -2
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -4,6 +4,29 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
|
|
|
4
4
|
|
|
5
5
|
---
|
|
6
6
|
|
|
7
|
+
## [1.0.10] — 2026-10-30
|
|
8
|
+
|
|
9
|
+
- chore(release): 1.0.9
|
|
10
|
+
- feat(statistics): summarizeDistribution + percentileNearestRank (consolidation home)
|
|
11
|
+
- chore(release): 1.0.8
|
|
12
|
+
- chore(analyst): re-pin the implementation manifest on merged main
|
|
13
|
+
- feat(statistics,harness): two-sample Welch evidence + lifted sandbox assertion library
|
|
14
|
+
- chore(release): 1.0.7 (#1172)
|
|
15
|
+
- docs(statistics): keep inference policy and exports readable (#1173)
|
|
16
|
+
- feat(statistics): own independent effect summaries and ROC area (#1171)
|
|
17
|
+
- chore(release): 1.0.6 (#1170)
|
|
18
|
+
- refactor(reporting): share text table layout and simplify summaries (#1169)
|
|
19
|
+
- refactor(harness): retain unavailable verdicts through cleanup (#1168)
|
|
20
|
+
- chore(release): 1.0.5 (#1167)
|
|
21
|
+
- refactor(harness): normalize compact named expectations (#1166)
|
|
22
|
+
- chore(release): 1.0.4 (#1165)
|
|
23
|
+
- refactor(harness): own resource acquisition and readiness cleanup (#1164)
|
|
24
|
+
- chore(release): 1.0.3 (#1163)
|
|
25
|
+
- chore(release): declare the existing deployment runner for workflow lint
|
|
26
|
+
- fix(release): bind bootstrap to the existing qualified action revision
|
|
27
|
+
- fix(release): use the qualified pnpm bootstrap in publication workflows
|
|
28
|
+
- Refactor sandbox integration scenarios into the eval harness (#1161)
|
|
29
|
+
|
|
7
30
|
## [1.0.9] — 2026-10-30
|
|
8
31
|
|
|
9
32
|
- feat(statistics): summarizeDistribution + percentileNearestRank (consolidation home)
|
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": "1.0.
|
|
5
|
+
"version": "1.0.10",
|
|
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: 1.1.0. Bumps on breaking changes to request/response schemas.",
|
|
7
7
|
"contact": {
|
|
8
8
|
"name": "Tangle Network",
|
package/dist/wire/index.d.ts
CHANGED
|
@@ -267,10 +267,10 @@ export declare const FeedbackTrajectorySchema: z.ZodObject<{
|
|
|
267
267
|
metadata: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodUnknown>>;
|
|
268
268
|
}, z.core.$strip>>;
|
|
269
269
|
split: z.ZodOptional<z.ZodEnum<{
|
|
270
|
-
train: "train";
|
|
271
270
|
dev: "dev";
|
|
272
|
-
test: "test";
|
|
273
271
|
holdout: "holdout";
|
|
272
|
+
train: "train";
|
|
273
|
+
test: "test";
|
|
274
274
|
}>>;
|
|
275
275
|
tags: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodString>>;
|
|
276
276
|
createdAt: z.ZodString;
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@tangle-network/agent-eval",
|
|
3
|
-
"version": "1.0.
|
|
3
|
+
"version": "1.0.10",
|
|
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": {
|