Conversation
[codex] drop v4 task compatibility
Decouple agent native tools from environment primitives
# Conflicts: # docs/reference/agents.mdx # hud/environment/environment.py # hud/environment/tests/test_environment.py # hud/tools/computer/base.py # hud/tools/computer/gemini.py # hud/tools/executors/xdo.py # hud/tools/tests/test_computer.py
Refactor Agents
Robot capability: environment.robots, episode recorder, telemetry, ensembler
Rename Robot Capability + Add MainThreadSimRunner
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
…arching global ast
Resolve registry name from the served Environment, not a source scan
| from hud.eval import Taskset, group_relative | ||
|
|
||
| agent = create_agent("claude-sonnet-4-5") | ||
| job = await Taskset(count_letter(word=w) for w in words).run(agent, group=16) |
There was a problem hiding this comment.
Taskset constructor misused
Medium Severity
The training example calls Taskset(count_letter(word=w) for w in words), which passes the generator as the taskset name, leaving tasks empty. .run(agent, group=16) then schedules no tasks, so the GRPO snippet does nothing useful.
Reviewed by Cursor Bugbot for commit 88ba14d. Configure here.
| @env.template() | ||
| async def count_letter(word: str = "strawberry", letter: str = "r"): | ||
| answer = yield f"How many '{letter}'s are in '{word}'? Reply with just the number." | ||
| yield 1.0 if answer and str(word.count(letter)) in answer else 0.0 |
There was a problem hiding this comment.
Letter count case mismatch
Low Severity
The sample grader uses case-sensitive word.count(letter) while checking whether that count appears in the agent answer. Mixed-case inputs (e.g. "Strawberry" / "r") can score 0.0 even when the answer is correct, unlike the prior lowercased logic.
Reviewed by Cursor Bugbot for commit 88ba14d. Configure here.
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 2 potential issues.
There are 4 total unresolved issues (including 2 from previous reviews).
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 704bca4. Configure here.
5 participants
Note
High Risk
This is a major SDK and protocol shift (v5 agents cannot drive v6-served environments) plus CI test setup changes that drop browser/Playwright provisioning, which can hide regressions in computer-use paths if those tests still exist.
Overview
This PR ships HUD Python SDK v6 as the primary surface: environments expose a thin control channel with capabilities (
ssh,mcp,cdp,rfb,robot) and tasks (@env.template()generators), while agent harnesses own the tools. User-facing narrative moves from v5 scenarios/MCP tools to protocol-first manifest → tasks.start → tasks.grade, withTask.run(agent)returning aJob/Runinstead ofhud.eval()/env("scenario", ...).Documentation is restructured on Mintlify: default v6 nav (
docs/v6/), v5 tagged Legacy underdocs/v5/, redirects from old paths, new Migrate to v6 guide, agent skill doc, and refreshed site styling (docs.json,custom.css). Several long-form cookbooks are removed from the old tree and replaced or relocated (e.g. v6 coding-agent, ops-diagnostics, a2a-chat, robot-benchmark).Runnable examples land under
cookbooks/(A2A chat server moved out of the SDK as reference code; codex-style agent; v6chat_envusingEvaluationResultand templates). README and CONTRIBUTING are rewritten for v6 workflows (hud init,hud deploy,hud evalwithout--rootdir=hud).CI/dev ergonomics: GitHub Actions drops Xvfb/Playwright install from the test matrix;
.githooks/pre-pushis removed..gitignoreexpands for local/experimental dirs. AddsAGENTS.md(andCLAUDE.mdpointer) for contributor/agent guidance.Reviewed by Cursor Bugbot for commit c673f40. Bugbot is set up for automated code reviews on this repo. Configure here.