* test(api): measure historical image read costs * fix(test): resolve image benchmark paths from its config * fix(attachments): read stored images without scanning sessions * test(attachments): complete by-id fixtures and access assertions * fix(docs): implement image-id read on catalog fixture * docs(attachments): refresh generated read contracts * test(web): verify stored images across history and forks * docs(api): clarify image read metadata and permission scope * test(api): type benchmark instrumentation without unsafe returns * test(api): retire unknown-cast allowances with removed history fixtures * test(attachments): isolate browser cases and document store-wide access * test(web): intercept the by-id thumbnail read path * docs(perf): run generated diagnostic from its owning package * refactor(attachments): reuse reference reads for conversation images * docs(api): refresh complete image reference client contract * test(ui-chat): assert complete image reference forwarding * test(perf): measure image reads against current Session observations
description, kind
| description | kind |
|---|---|
| The test-support group map: keyless test harnesses, LLM mock and replay servers, and Loader smoke helpers for developers writing and running repository tests. | package-group |
packages/test-support
English | 中文
Summary
The test-support group gives repository tests deterministic, keyless ways to exercise the real product. It includes Loader application harnesses, session-log snapshot adapters, a replay LLM plugin, and a scriptable OpenAI-compatible fault server. Each package is support-tier infrastructure; a package moves out of this group when it gains a product contract and product consumers.
Table of Contents
Packages
| Package | Role |
|---|---|
session-snapshot |
Provides session-log snapshot support and protocol adapters for profile-driven tests |
agent-loop-testkit |
Provides the shared prerequisite services for tests that exercise the concrete AgentLoop |
tool-testkit |
Defines tool fixtures and exercises invocation or executor behavior in tests |
client-runtime |
Provides the jsdom slot test bench for browser feature specs |
remote-mock |
Provides the endpoint-named Typert Remote mock and the Connection carrier face whole-client specs install |
loader-smoke |
Boots Loader-composed applications and drives fixture turns for smoke tests |
llm-mock-server |
Provides a scriptable OpenAI-compatible fault server for recovery tests |
llm-replay |
Replays recorded model streams for keyless tests and demos |
Related documentation
- Testing policy — the keyless snapshot tier these harnesses serve and when it is required.
- Package groups — how support groups relate to the product groups.
Dev Note
Working context for maintainers — click to expand
None.