Dev & Engineering ✓ Microsoft · Official end-to-end-testingagent-hostprotocol-testingreplay-testingfixture-recordinggithub-cli

Agent Host E2E Test Assistant

Maintain VS Code Agent Host end-to-end tests with strict replay fixtures.

FollowSkills review · FSRS-2.0
Not recommended
56/ 100 5-point scale 2.8 / 5
Trust19 / 25 · 3.8/5

The skill makes replay the default with no network or token, requires real-token recording to be intentional, limits prompts to trivial read-only work in temporary directories, and requires reviewing normalized fixtures for secrets and paths. Deducted 6 points because it lacks an explicit user-confirmation step, token-lifecycle guidance, and rollback procedure; recording still causes external CAPI interaction.

Reliability9 / 20 · 2.3/5

The workflows cover adding tests, recording fixtures, deterministic-failure gating, platform gates, cache misses, and diagnostic troubleshooting, with notification-based rather than wall-clock assertions. Deducted 1 point because the key path was not executed statically and the required README, scripts, and fixtures were not supplied in the selected skill file, so command correctness and complete failure behavior remain uncertain.

Adaptability10 / 15 · 3.3/5

The audience and scenarios are specific to VS Code agent-host AHP black-box tests, with stated boundaries for nondeterminism, POSIX behavior, Windows, and provider-specific replay. Deducted 5 points because non-fit cases, input/output contracts, and semantic trigger exclusions are not fully stated; Chinese-language support and reachability of GitHub/CAPI from mainland-China networks are also unaddressed.

Convention8 / 15 · 2.7/5

The document uses progressive disclosure through an architecture reference followed by focused workflows, and includes commands, fixture naming rules, limitations, and a troubleshooting entry point; repository evidence supplies MIT licensing context. Deducted 7 points because the skill itself lacks versioning, changelog, explicit maintenance owner, update path, installation/dependency notes, and FAQs, while relying on an unprovided README and internal implementation details.

Effectiveness6 / 15 · 2.0/5

For a contributor familiar with the repository, the instructions directly support adding tests, recording fixtures, and gating nondeterministic cases, including leakage review and replay confirmation. Deducted 1 point because no representative successful output or execution evidence is included, so end-to-end completeness and direct usability cannot be verified from static material alone.

Verifiability4 / 10 · 2.0/5

The skill provides auditable paths, commands, fixture naming rules, and symptom-to-fix guidance; repository material also provides license, pinned dependencies, and some test/CI evidence. Deducted 1 point because the supplied CI workflows do not clearly cover this skill's agent-host E2E key paths, and no independent execution or reproduction was performed.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 5b3e1be7be9e
Before you use it
  • Recording requires a real GITHUB_TOKEN or gh authentication and access to CAPI; obtain explicit authorization and avoid sending sensitive prompts, credentials, or local paths.
  • The required architecture README, implementation scripts, and agent-host-specific CI/fixtures were not supplied as evidence; inspect them before adoption.
  • No mainland-China network fallback, version policy, maintenance owner, or update-notification mechanism is documented.
See the full review method →

What it does & when to use it

This skill is for black-box end-to-end tests that drive the complete VS Code Agent Host through the AHP protocol. It guides contributors through adding cross-provider tests, re-recording YAML fixtures for Claude, Copilot, and Codex, and diagnosing replay cache misses. Plain replay uses committed fixtures without a token or network and fails strictly on unrecorded requests. Recording requires a real token and contacts CAPI, so the skill is best suited to VS Code contributors familiar with this repository’s test layout and scripts rather than users seeking a general-purpose testing framework.

It directs contributors to read src/vs/platform/agentHost/test/node/protocol/README.md, then add tests inside defineAgentHostE2ETests in agentHostE2ETestHelpers.ts. Tests use dispatchTurn(...) and client.waitForNotification(...) to drive the real Agent Host, bundled provider SDK/CLI, and AHP protocol while CapiReplayProxy replays committed YAML model-traffic fixtures. The workflows show how to record and replay individual providers with ./scripts/test-integration.sh --run, review fixture diffs, extend normalization and redaction in capiReplayProxy.ts, serve ancillary endpoints through capiStubs.ts, and add precise gates for nondeterministic or platform-specific behavior.

  1. A VS Code contributor is adding an Agent Host end-to-end test that should run across multiple model providers and needs a deterministic test and fixture workflow.
  2. A bundled SDK or CLI upgrade changes an endpoint, turn count, or tool schema and the contributor needs to re-record and validate fixtures.
  3. A test fails with a cache miss, missing fixture, stale subagent fixture, or accidental real-CAPI contact and the contributor needs a symptom-to-fix troubleshooting path.
  4. A test uses real-time streaming, mid-turn aborts, or POSIX-only local execution and needs a precise recording or platform gate.
  5. A fixture maintainer needs to check that local usernames, absolute paths, tokens, and unreleased model identifiers were not committed.

Pros & cons

Pros
  • Defines strict replay as the default, avoiding tokens and network access when committed fixtures are sufficient.
  • Covers concrete maintenance tasks: adding tests, recording fixtures, writing provider assertions, and troubleshooting failures.
  • Requires fixtures to be generated by the recorder and checked for normalization, redaction, and leaked data.
  • Provides targeted gates for nondeterministic behavior and Windows/POSIX differences.
Limitations
  • Its scope is limited to the specified VS Code Agent Host AHP test directory, not general end-to-end testing.
  • Fixture recording requires a real token and contacts real CAPI, so it must be run intentionally.
  • It depends on repository-specific scripts, helpers, proxy code, stubs, and reference documentation.
  • The source does not document standalone installation or compatibility with other test frameworks or non-VS Code projects.

How to install

The source does not document a separate installation process or standalone package for this skill. It is located at .github/skills/agent-host-e2e-tests/SKILL.md in the microsoft/vscode repository, so using it requires access to the relevant VS Code source tree and test files. The repository as a whole is licensed under the MIT license.

How to use

In an Agent Skills-compatible client with access to the repository, use a request such as “add a cross-provider Agent Host AHP end-to-end test” or “re-record Agent Host E2E fixtures after an SDK upgrade and diagnose the cache miss.” Run plain replay with ./scripts/test-integration.sh --run <path>. To record the Claude fixtures, run: AGENT_HOST_REPLAY_RECORD=1 ./scripts/test-integration.sh --run src/vs/platform/agentHost/test/node/protocol/claudeAgentHostE2E.integrationTest.ts; substitute the corresponding Copilot or Codex integration-test path as needed. Before recording, provide a token through gh auth token or GITHUB_TOKEN. After recording, inspect git diff and then run replay again without the environment variable.

Compared to similar skills

This is not an independent test runner or model-testing platform. It is a workflow guide for VS Code Agent Host end-to-end tests, built around the repository’s CapiReplayProxy recording/replay system and AHP test implementation.

FAQ

Do normal replay runs need a token or network access?
No. With no recording environment variable, the tests serve committed fixtures without a token or network. Any unrecorded request is a hard cache miss.
When is a real token required?
A real token is required when recording or re-recording fixtures after adding a test or changing bundled SDK/CLI wire behavior. The source specifies GITHUB_TOKEN or gh auth token and access to real CAPI.
Can I edit a YAML fixture by hand to fix a failure?
No. Fixtures must be produced by recording. If usernames, paths, tokens, or other sensitive values appear, extend normalization and redaction in capiReplayProxy.ts and record again.
Which tests should be gated?
Gate tests with real-time streaming or mid-turn aborts when replay is not deterministic, gate POSIX-only local execution on Windows, and use targeted provider or operating-system gates where behavior diverges.

More skills from this repository

All from microsoft/vscode

Dev & Engineering ✓ Microsoft · Official

Tool Rename Compatibility Check

Protect existing prompts and tool configurations when built-in tools are renamed.

Dev & Engineering ✓ Microsoft · Official

Copilot Chat OpenTelemetry Instrumentation

A repository-specific guide for consistent OpenTelemetry instrumentation in Copilot Chat.

Dev & Engineering ✓ Microsoft · Official

VS Code Configuration Policy Maintainer

Standardize VS Code policy registration, export, and validation.

Design & Frontend ✓ Microsoft · Official

VS Code Design Philosophy

Turn vague UI discomfort into concrete fixes using shared values, principles, and design moves.

Dev & Engineering ✓ Microsoft · Official

VS Code Integrated Browser Architecture

A practical architecture guide for safely changing VS Code's cross-process integrated browser.

Dev & Engineering ✓ Microsoft · Official

VS Code Agents Window Sessions

Safely implement and repair VS Code Agents window features.

Dev & Engineering ✓ Microsoft · Official

Commit Assistant

Creates repository-style commit messages and safely commits code changes.

Dev & Engineering ✓ Microsoft · Official

Agent Host Log Investigator

Trace session, transport, and host failures in Agent Host debug exports.

Dev & Engineering ✓ Microsoft · Official

VS Code Unit Test Runner

Run VS Code repository unit tests by file, test name, or compiled-output glob.

Dev & Engineering ✓ Microsoft · Official

VS Code Agent Customization Assistant

Create, repair, and troubleshoot VS Code Agent customization files and their loading behavior.

Dev & Engineering ✓ Microsoft · Official

Code OSS Launch & Debug

Launch a built-from-source VS Code with isolated profiles, Playwright control, and multi-process debugging ports.

Dev & Engineering ✓ Microsoft · Official

VS Code Accessibility Development Guide

A practical specification for accessible interactive features in VS Code.

Design & Frontend ✓ Microsoft · Official

VS Code CSS Layout Standards

Build reliable VS Code-style CSS layouts and text truncation behavior

Dev & Engineering ✓ Microsoft · Official

VS Code Chat Performance Lab

Benchmark chat rendering and detect memory growth across VS Code builds.

Dev & Engineering ✓ Microsoft · Official

Component Fixtures for Screenshot Testing

Create stable, theme-aware VS Code component fixtures for isolated screenshot testing.

Dev & Engineering ✓ Microsoft · Official

VS Code Smoke Test Assistant

Run, filter, and debug VS Code end-to-end smoke tests.

Dev & Engineering ✓ Microsoft · Official

VS Code Crash Dump Symbolicator

Turn native VS Code crash dumps into readable backtraces with method names.

Dev & Engineering ✓ Microsoft · Official

Local VS Code Web Workbench

Validate VS Code workbench and Agents window changes in a local vscode.dev instance.

Dev & Engineering ✓ Microsoft · Official

Feedback Action

Reads current-session feedback and applies the requested code changes.

Dev & Engineering ✓ Microsoft · Official

VS Code Chat Customizations Editor Skill

Guides developers through safe changes and testing for VS Code’s chat customization management UI.

Related skills