From 4af66d35552c86cacfbf898b32262c43cec24290 Mon Sep 17 00:00:00 2001 From: Drew Stone Date: Thu, 20 Aug 2026 01:42:50 -0600 Subject: [PATCH] =?UTF-8?q?chore(release):=200.150.2=20=E2=80=94=20the=20s?= =?UTF-8?q?him=20serves=20the=20unmodified=20CLI?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- CHANGELOG.md | 4 ++++ clients/python/pyproject.toml | 2 +- clients/python/src/agent_eval_rpc/__init__.py | 2 +- clients/python/uv.lock | 2 +- package.json | 2 +- src/analyst/benchmark-implementation.ts | 2 +- 6 files changed, 9 insertions(+), 5 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index c32abba8..4c62e09b 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -6,6 +6,10 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval- ## [Unreleased] +--- + +## [0.150.2] — 2026-08-20 + ### Added - `economics.spend` on the supervisor-run report and `spendUsd` on the rollup (#660): both total-spend measurements as named fields with their denominators, never one bare number. `spend.journalDerived` (journal `metered` + `settled` rows) answers execution accounting — what execution observably consumed; `spend.closeRecord` (loops `state.json` `result.spentUsd`, or Runtime `result.json` `spentTotal.usd`, which the analyzer now reads) answers billing — what the store recorded as settled at close. Each run-level measurement carries its record count; each rollup measurement carries `runs`, its own denominator, because the two sums cover different run sets (measured in discovery-lab: 4.762B input tokens journal-derived over 918 runs vs 4.780B close-record over 868 runs, ~0.4% apart). Divergence is a signal to read, not an error. `totalUsd` stays as the collapsed compatibility field; its docstring names the pick order and points to `spend`. diff --git a/clients/python/pyproject.toml b/clients/python/pyproject.toml index 0878d75b..f84cf99a 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 = "0.150.1" +version = "0.150.2" description = "Python RPC client, official optimizer bridge, and DSPy metric adapter for @tangle-network/agent-eval." 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 dbc1cf74..10eaccca 100644 --- a/clients/python/src/agent_eval_rpc/__init__.py +++ b/clients/python/src/agent_eval_rpc/__init__.py @@ -53,7 +53,7 @@ try: __version__ = version("agent-eval-rpc") except PackageNotFoundError: - __version__ = "0.150.1" + __version__ = "0.150.2" __all__ = [ "Client", diff --git a/clients/python/uv.lock b/clients/python/uv.lock index f71e110f..fd164c75 100644 --- a/clients/python/uv.lock +++ b/clients/python/uv.lock @@ -34,7 +34,7 @@ conflicts = [[ [[package]] name = "agent-eval-rpc" -version = "0.150.1" +version = "0.150.2" source = { editable = "." } dependencies = [ { name = "filelock" }, diff --git a/package.json b/package.json index 0b8ea9e7..c32ff4cd 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "@tangle-network/agent-eval", - "version": "0.150.1", + "version": "0.150.2", "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": { diff --git a/src/analyst/benchmark-implementation.ts b/src/analyst/benchmark-implementation.ts index 8aca3dfb..799d0288 100644 --- a/src/analyst/benchmark-implementation.ts +++ b/src/analyst/benchmark-implementation.ts @@ -10,7 +10,7 @@ export const ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES = Object.freeze([ ]) export const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = - '5c5e71bc3a4fd59416a0b56ac94808fac4b633de1d402824a07ebcc219a94cf2' + '61ad75e662e240404f523d7dad66e18145df9c35b1ce8630468970fef2a00162' /** The published benchmark evidence was produced at this package version, by * the retired one-shot direct runner, before trace analysts moved to the