From 39d9fd74ff2f956e2c898277b361998e61097735 Mon Sep 17 00:00:00 2001 From: Drew Stone Date: Mon, 3 Aug 2026 02:33:14 -0600 Subject: [PATCH] chore(release): agent-eval 0.143.0 --- CHANGELOG.md | 18 ++++++++++++++++++ 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, 23 insertions(+), 5 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 4c8159a6..8d9a5f9a 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -4,6 +4,24 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval- --- +## [0.143.0] - 2026-08-03 - exact campaign cost provenance + +### Changed + +- **Breaking:** `CampaignCellResult.costEstimated` is replaced by the required `costProvenance` union, and `ProfileSummary.totalCostUsd` becomes `number | null` with an adjacent `costProvenance` value. +- Campaign measurement digests now include the complete cost-provenance value, so digest equality is intentionally not preserved across the `0.142.x` to `0.143.0` data boundary. +- Run-record raw cost fields now describe the total as observed, estimated, or uncaptured, while `cost_known_subtotal_usd` retains any measured subtotal when the total remains unknown. +- `planCampaignRun` reports `cellsBlocked`, and each planned cell may be `blocked` when saved data cannot prove its cost or receipt identity. +- Caches created before `0.143.0` have no complete cost provenance and therefore stop a resumable campaign by default. + Inspect the plan and set `rerunInvalidCachedCells: true` for a one-time selective rerun, or set `resumable: false` for an intentional full rerun. + +### Fixed + +- Failed provider calls retain input, cached-input, cache-write, output, and reasoning tokens without presenting an unknown USD total as zero. +- Campaign execution inspects every saved cell and its exact billing receipts before any concurrent dispatch begins, so a late stale cell cannot waste spend in earlier cells. +- Malformed, unreadable, mismatched, or receipt-incomplete saved cells require explicit rerun approval instead of being silently reused or re-executed. +- `planCampaignRun` no longer creates the run directory while performing read-only inspection. + ## [0.142.2] - 2026-08-02 - current shared type cohort ### Changed diff --git a/clients/python/pyproject.toml b/clients/python/pyproject.toml index 7d86ce64..bbccf73c 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 = "0.142.2" +version = "0.143.0" 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 f4410de2..625a3756 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__ = "0.142.2" + __version__ = "0.143.0" __all__ = [ "Client", diff --git a/clients/python/uv.lock b/clients/python/uv.lock index f095be8d..15783524 100644 --- a/clients/python/uv.lock +++ b/clients/python/uv.lock @@ -34,7 +34,7 @@ conflicts = [[ [[package]] name = "agent-eval-rpc" -version = "0.142.2" +version = "0.143.0" source = { editable = "." } dependencies = [ { name = "filelock" }, diff --git a/package.json b/package.json index 3568a1de..87fb5744 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "@tangle-network/agent-eval", - "version": "0.142.2", + "version": "0.143.0", "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 cc229059..4ae15198 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 = - '55744d067f70ffcb0223eae6121739021a9e2567208cfd14098582bb73cdbf97' + '2867725e505a600f4f1f9d934fb797f5fb94a71c906577d05009aecc254f85f3' /** The published benchmark evidence was produced at this package version, by * the retired one-shot direct runner, before trace analysts moved to the