diff --git a/CHANGELOG.md b/CHANGELOG.md index 147a22a..27931bc 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -4,10 +4,11 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval- --- -## [Unreleased] — eval fixture UX + manifest-correct campaign resume +## [0.100.3] — 2026-07-01 — product benchmark contract + eval fixture UX ### Added +- Published the `@tangle-network/agent-eval/product-benchmark` subpath so product agents can share one strict product-benchmark manifest, record, artifact, and integrity validator instead of copying Agent Lab or product-local schema code. - **Vercel-style eval fixture loading in `/campaign`.** `discoverEvalFixtures`, `loadEvalFixture`, `loadEvalFixtureScenarios`, and `planEvalFixtureRun` let agents use the simple `evals//PROMPT.md + EVAL.ts + package.json` shape while still executing through the existing `runCampaign` primitive. - **Dry-run planning for campaigns.** `planCampaignRun` reports `totalCells`, `cellsCached`, `cellsToRun`, per-cell cache paths, and miss reasons before any agent work starts. This is the cheap proof before spending tokens. - **`dispatchRef` on `runCampaign`.** Callers can include the model/tool/prompt/runtime identity in the manifest when the same dispatch function name can run different behavior. diff --git a/clients/python/pyproject.toml b/clients/python/pyproject.toml index 27b2863..77ef438 100644 --- a/clients/python/pyproject.toml +++ b/clients/python/pyproject.toml @@ -4,7 +4,7 @@ build-backend = "hatchling.build" [project] name = "agent-eval-rpc" -version = "0.100.2" +version = "0.100.3" description = "Python RPC client for @tangle-network/agent-eval — judge content against rubrics over HTTP or stdio RPC. Eval logic runs in the Node runtime; this package is a thin wire client." readme = "README.md" requires-python = ">=3.10" diff --git a/clients/python/src/agent_eval_rpc/__init__.py b/clients/python/src/agent_eval_rpc/__init__.py index 64d9554..bb13857 100644 --- a/clients/python/src/agent_eval_rpc/__init__.py +++ b/clients/python/src/agent_eval_rpc/__init__.py @@ -58,7 +58,7 @@ try: __version__ = version("agent-eval-rpc") except PackageNotFoundError: - __version__ = "0.100.2" + __version__ = "0.100.3" __all__ = [ "Client", diff --git a/package.json b/package.json index 1a7718a..5f07bc9 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "@tangle-network/agent-eval", - "version": "0.100.2", + "version": "0.100.3", "description": "Evaluate and improve AI agents from runs, traces, judges, and feedback. Compare candidates, cluster failures, measure lift, and gate releases.", "homepage": "https://github.com/tangle-network/agent-eval#readme", "repository": {