diff --git a/CHANGELOG.md b/CHANGELOG.md index 036a002..ebe595e 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -6,6 +6,8 @@ The format is based on Keep a Changelog and this project follows Semantic Versio ## [Unreleased] +## [0.11.0] - 2026-06-25 + ### Added - **Long-context Python function retrieval benchmark** — added seven built-in context-window templates linked to file-backed Python function-retrieval datasets, with front/middle/late function placement, two-function retrieval, and a negative control. @@ -20,6 +22,7 @@ The format is based on Keep a Changelog and this project follows Semantic Versio - **Run template capability filtering** — Run now disables benchmark templates that exceed a selected model's declared context window or require tool calling when the selected model/server is not tool-capable. - **Run audit and functional checks split** — Run now separates pipeline execution health from functional benchmark checks, and treats missing required terms as a visible functional failure when exact matching is disabled. - **Run functional failure clue** — Run now surfaces a benchmark assertion failure line when quality metrics fail despite a technically completed run, with categories such as invalid tool arguments or missing tool calls. +- **Templates catalog shell** — `/templates` now opens as a browse-first catalog with category buckets, grouped template cards, dedicated preview state, and the existing AI-first authoring flow embedded in the new shell instead of auto-selecting the first template row. ## [0.10.0] - 2026-06-19 @@ -67,7 +70,6 @@ The format is based on Keep a Changelog and this project follows Semantic Versio - **Human-readable agent workflow guidance** — `AGENTS.md` now groups workflow rules into clearer sections, documents parallel worktree expectations including `origin/main` checks before commit/push requests and resync timing before validation or merge, directs agents to create a focused branch without pausing for confirmation, and asks agents to explicitly request commit approval with a suggested message and details. - **Templates agent composer** — The Templates authoring panel now gives the freeform request field more space and removes the preset suggestion chip. - **Run selection rail polish** — the Run page model chips, benchmark template selector, and response header now use clearer selected-state borders/backgrounds and denser mono text, with redundant server summary and model helper copy removed. -- **Templates catalog shell** — `/templates` now opens as a browse-first catalog with category buckets, grouped template cards, dedicated preview state, and the existing AI-first authoring flow embedded in the new shell instead of auto-selecting the first template row. ### Fixed diff --git a/README.md b/README.md index ab56653..0a2e066 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,6 @@ # InferHarness -[![version](https://img.shields.io/badge/version-0.10.0-blue)](https://github.com/Fango2007/InferHarness/releases/tag/v0.10.0) +[![version](https://img.shields.io/badge/version-0.11.0-blue)](https://github.com/Fango2007/InferHarness/releases/tag/v0.11.0) [![node](https://img.shields.io/badge/node-25.x-339933)](package.json) [![python](https://img.shields.io/badge/python-3.10%2B-3776AB)](backend/src/scripts/requirements.txt) [![CI](https://github.com/Fango2007/InferHarness/actions/workflows/ci.yml/badge.svg)](https://github.com/Fango2007/InferHarness/actions/workflows/ci.yml) diff --git a/backend/package.json b/backend/package.json index 769e7ec..600eda7 100644 --- a/backend/package.json +++ b/backend/package.json @@ -1,6 +1,6 @@ { "name": "@inferharness/backend", - "version": "0.10.0", + "version": "0.11.0", "private": true, "type": "module", "engines": { diff --git a/frontend/package.json b/frontend/package.json index ee5b46f..7c01460 100644 --- a/frontend/package.json +++ b/frontend/package.json @@ -1,6 +1,6 @@ { "name": "@inferharness/frontend", - "version": "0.10.0", + "version": "0.11.0", "private": true, "type": "module", "engines": { diff --git a/package-lock.json b/package-lock.json index 74441d0..7b4ce8f 100644 --- a/package-lock.json +++ b/package-lock.json @@ -1,12 +1,12 @@ { "name": "inferharness", - "version": "0.10.0", + "version": "0.11.0", "lockfileVersion": 3, "requires": true, "packages": { "": { "name": "inferharness", - "version": "0.10.0", + "version": "0.11.0", "hasInstallScript": true, "workspaces": [ "backend", @@ -34,7 +34,7 @@ }, "backend": { "name": "@inferharness/backend", - "version": "0.10.0", + "version": "0.11.0", "dependencies": { "ajv": "^8.12.0", "better-sqlite3": "^12.9.0", @@ -54,7 +54,7 @@ }, "frontend": { "name": "@inferharness/frontend", - "version": "0.10.0", + "version": "0.11.0", "dependencies": { "@vitejs/plugin-react": "^6.0.1", "echarts": "^6.0.0", diff --git a/package.json b/package.json index d05f7e8..8950ddb 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "inferharness", - "version": "0.10.0", + "version": "0.11.0", "private": true, "workspaces": [ "backend",