> ## Documentation Index
> Fetch the complete documentation index at: https://docs.hud.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Changelog

> Product updates and release notes for the HUD SDK and platform, covering new features, CLI commands, integrations, and UI changes by release date.

**July 14, 2026**

## GPT-5.6 Support

* **GPT-5.6 family** — `gpt-5.6` (Sol), `gpt-5.6-terra`, and `gpt-5.6-luna` are available through the
  HUD gateway and `create_agent`. `OpenAIAgent` now defaults to `gpt-5.6`.
* **Reasoning controls** — GPT-5.6 reasoning passes through `OpenAIConfig.reasoning` unchanged: effort
  levels `none` through `xhigh` and `max`, and `mode` (`standard` or `pro`).
* **OpenAI SDK floor** — the SDK now requires `openai>=2.45.0` (Responses API function-call outputs use
  the current content-item types).

**May 6, 2026**

## Models, Tasksets, Templates & Sharing

### Platform

* **Models directory refresh** — `/models` is a single unified list with Private and Trainable filters and a live usage column on every row.
* **Taskset analytics tab** — dedicated analytics view on tasksets with charts and richer summaries.
* **Multi-environment taskset selection** — pick multiple environments at once when configuring a taskset run.
* **Run from suggested tasksets** — kick off an evaluation from a model's suggested-taskset row with the model already locked in.
* **Templates and workflow orchestration** — templates settings page and a right-click workflow entry point for repeatable runs.
* **Resource sharing** — invite users or whole teams to traces, jobs, evalsets, models, registry items, and collections with a unified accept flow.
* **Trace grader info** — evaluation cards on traces show the grader that produced each result.

**March 16, 2026**

## A2A Chat, Citations, GPT-5 & CLI Sync

* **A2A chat orchestrator** — agent-to-agent communication for multi-agent workflows with input handling and follow-up turns.
* **`hud sync tasks`** — sync task definitions from Python files or directories to the platform.
* **`hud sync env`** — sync local environment configs with collision detection (replaces `hud link`).
* **`hud eval` accepts Python files** — run evaluations directly from `.py` files and directories containing `Task` objects.
* **Chat class** — manage multi-turn agent conversations from a single SDK abstraction.
* **GPT-5 support** — `ResponseAgent` defaults to `gpt-5`, with ToolSearch tool support.
* **Citations** — citation support for Claude, Gemini, and OpenAI responses in chat and agent traces.

### Platform

* **Click & scroll coordinate overlays** — computer use traces render click coordinates and scroll actions directly on screenshots.
* **Trace-level QA workflows** — run QA workflows across all tasks from the trace table, with screenshot input and per-task status.
* **Evalset environment filtering** — filter results by environment version, with an earliest-version-only toggle.
* **EvaluationResult info viewer** — inspect the full `info` field of evaluation results directly in the UI.
* **Individual user spend** — usage page shows per-user spend alongside team totals.
* **Inline job renaming** — rename jobs directly from the jobs page.
* **Modal integration** — run environments on Modal compute infrastructure.
* **Resources section** — new `/resources` page with published articles.

**February 16, 2026**

## Opus 4.6 Computer Use, Streaming & Deploy Improvements

* **Opus 4.6 computer tool** — native support for Claude Opus 4.6 computer use with zoom and screenshot gating.
* **Fine-grained tool streaming** — opt-in streaming for individual tool results during agent execution.
* **`hud deploy` build args & secrets** — pass build arguments and secrets to environment container builds.
* **`allowed_tools` in `@env.scenario`** — scope tool access per evaluation scenario via the decorator.
* **Checkpoint configs** — configure checkpoint behavior for long-running evaluations.

### Platform

* **Billing refactor** — auto top-up, redesigned billing page, and per-key pricing for HUD-managed API keys.
* **Trace viewer enhancements** — strip review mode, inline run switching, and file attachment display.
* **Trace comments** — add and edit comments on individual traces, with a dedicated column in taskset view.
* **Training jobs dashboard** — dedicated section for RL training jobs with detail pages.
* **Native binarization toggle** — pass/fail binarization for taskset evaluations, built into the platform.
* **Column ordering** — reorder columns in the taskset table view.
* **Model & environment sorting** — sort taskset results by model, environment, and environment version.

**January 12, 2026**

## CLI Refinements & Leaderboard Redesign

* **Build args for `hud deploy`** — pass custom build arguments to environment container builds.
* **Wildcard tools** — environments can expose `*` to allow all tools without explicit registration.
* **CLI mode distinction** — `hud build` and `hud analyze` distinguish between HTTP and stdio modes.

### Platform

* **Leaderboard redesign** — redesigned leaderboards with publishing flow, public visibility, and embedding support.
* **Slack bot** — Slack integration for job notifications and external integration providers.
* **Trace compact view** — compact trace view with column reorder, inline comments, and truncated task names.
* **BYOK API keys** — bring-your-own-key support with a `use_hud_key` option for user-managed API keys.
* **Per-key pricing** — individual pricing tiers for HUD-managed API keys.
* **Jobs page improvements** — compact job list view and refreshed stats.

**December 17, 2025**

## v0.5.0: MCP-First Architecture

* **Environments decoupled** — environment definitions moved to separate repos, enabling independent versioning and community contributions.
* **Unified scenario/tool/prompt/resource handling** — single abstraction layer for MCP servers and client-side tools, with caching and hot-reload.
* **Telemetry** — trace IDs, subagent spans, and structured logging for agent runs.
* **Scenario decorator** — `@env.scenario` for defining evaluation scenarios with typed configuration.
* **RL training** — initial support for reinforcement learning training via the CLI.

### Platform

* **Inference API usage tracking** — track inference API usage on the usage page.
* **HUD-managed API keys** — platform-side API key management with `set api_key` support.

**October 1, 2025**

## Bedrock, Gemini & Expanded Model Support

* **AWS Bedrock** — `hud-python[bedrock]` extra for running Claude agents via AWS Bedrock.
* **Gemini CUA** — Gemini computer use agent support with checkpoint management.
* **Qwen computer tool** — QwenComputerTool for Qwen-series models.
* **MCP server support** — use HUD environments as MCP servers, integrating with any MCP-compatible client.
* **Telemetry tracing** — structured telemetry for agent runs with trace export.

### Platform

* **Text trace viewer** — view text-only agent traces with a dedicated viewer.
* **Leaderboard embeds** — embed leaderboards in external pages.
* **Versioned models** — unified evalsets and leaderboards with versioned model support.
* **Usage tracking & billing** — usage analytics and subscription management.

**August 23, 2025**

## CLI & Claude Agent

* **`hud` CLI** — full CLI for the development lifecycle: `init`, `dev`, `build`, `deploy`, `eval`, `analyze`, `debug`.
* **Claude agent with prompt caching** — built-in Claude agent with reduced latency and cost.
* **Pre-filtered tools** — agents receive only the tools relevant to their current scenario.
* **User-provided system prompts** — custom system prompts for tasksets and individual tasks.

### Platform

* **Trace viewer** — full trace exploration UI with step-by-step replay of agent actions and screenshots.
* **Leaderboards & scorecards** — evalset leaderboards with scorecard breakdowns.
* **Jobs & runs display** — view agent runs with step-by-step screenshots and action metadata.
* **Public trace sharing** — publish and share individual traces publicly.

**April 18, 2025**

## Environment Controllers & Docker Support

* **Client-side environment management** — local Docker-based environment execution with copy-to/from support.
* **Claude adapter** — built-in adapter for Anthropic Claude computer use and Operator.
* **Gymnasium wrapper** — `gym.make()` compatibility for RL-style agent training loops.
* **Evaluator framework** — pluggable evaluators with structured logging and result export.

### Platform

* **Platform launch** — dashboard at hud.ai with authentication and evalset browsing.
* **API keys management** — create and manage API keys from the dashboard.
* **Profile & team pages** — user profiles with team membership and settings.

**March 3, 2025**

## Initial Release

* **Open-source SDK** — `pip install hud-python` for AI agent evaluation and RL environments.
* **Core primitives** — environments, tasks, evaluators, and runs as first-class objects.
* **Computer use actions** — keyboard, mouse, scroll, keyup/keydown, and hold-key actions for desktop environments.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.