Skip to content
cccskills
FreePublished on GitHub

nexent-daily-test

在 Ubuntu 自托管测试机上编排 Nexent 每日分层全量测试、维护本地测试基线和 P0 Playwright 候选代码,并将证据仅保存在本机。用于 OpenCode 执行 Daily/手工全量测试;不用于 PR 测试或外部结果发布。

The English summary is being prepared. Showing the original description.

Works withPlaywright
See how to install

Files included (1)

  • SKILL.md2.8 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Nexent Daily Test

以 config/test-policy.yaml 和本批 agent-input/execution-plan.json 为执行事实源。测试必须按最低有效层验证:单元/组件、服务/协议、真实 AI Runtime、浏览器 Journey、专项测试不能相互冒充。

开始前

确认环境变量 TEST_ROOT、NEXENT_REPO、BASE_SHA、HEAD_SHA、RESULT_DIR 和 TEST_BATCH 均存在。完整读取:

部署由外层入口调用 nexent-deploy 完成。部署证据不存在或站点未就绪时停止功能测试,记录基础设施阻塞;不要把所有用例批量写成产品失败。

不可破坏的边界

  • 不把测试结果、Excel、截图、Trace、视频、Prompt、模型响应上传 GitHub,不写 GITHUB_STEP_SUMMARY,不创建 Issue/PR。
  • 不修改 Nexent 业务代码。允许的持久维护目标只有本地测试资产;OpenCode 本批只能向 RESULT_DIR 写候选内容,由外层脚本校验后再提升。
  • 产品模型、Embedding、Rerank、VLM、STT、TTS 必须使用 config/models.yaml 与 config/secrets.env 中启用的真实配置;故障注入可以使用本地受控端点。
  • OAuth、CAS、外部 A2A/Nacos 的专用 Playwright Journey 服从 test-policy.yaml。标记为 SKIPPED_BY_POLICY 的项不得启动外部服务、不得改记为 PASS。
  • Playwright 只用于 PW-E2E Journey;BE-UT、SDK-UT、FE-COMP、API-IT、CONTRACT、AGENT-IT、DEPLOY、SEC、REL 使用各自最低验证层。
  • 只清理带本批 TEST_BATCH/run_id 且能确认由本批创建的数据,不删除共享数据、Docker volume 或历史结果。

完成条件

  1. execution-plan.json 中每个活动项恰有一条本批结果;策略排除项保留预置的 SKIPPED_BY_POLICY。
  2. 每条执行结果在完成后立即追加到 checkpoints/results.jsonl,失败或阻塞附可定位证据。
  3. agent-output/change-set.json、case-maintenance.json、playwright-maintenance.json 均存在且符合参考文件约定。
  4. 详细日志与证据只在 RESULT_DIR;标准输出保持最小且不含 secret、用例详情或模型回答。
  5. 不因为后续层失败丢弃前面层的真实结果;最终状态由 D6 汇总确定。

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Develop, adapt, review, test, and troubleshoot Nexent external memory provider plugins, including plugin.yaml manifests, searchable and ingestible provider protocols, error mapping, network-isolated unit tests, deployment configuration, and Mem0-based examples. Use when adding a new external memory vendor, changing an existing memory plugin, validating partner adapters, or diagnosing plugin discovery, authentication, retrieval, ingestion, or CI failures.

The English summary is being prepared. Showing the original description.

ModelEngine-Group/nexent6KUpdated Oct 19, 2026

Use when designing, implementing, debugging, or reviewing Nexent relational schemas, FastAPI endpoints, backend services, database access, SQL migrations, or backend/SDK configuration. Includes table/field naming, types, JSONB boundaries, audit fields, keys, and indexes even before code paths exist. Skip frontend-only work and unrelated SDK algorithms.

The English summary is being prepared. Showing the original description.

ModelEngine-Group/nexent6KUpdated Oct 19, 2026

Use when implementing, debugging, or reviewing Nexent frontend pages, React components, hooks, API services, TypeScript types, styling, or localization under frontend/. Includes UI requests without file paths. Skip backend-only work, Python tests, and documentation-only changes with no frontend behavior.

The English summary is being prepared. Showing the original description.

ModelEngine-Group/nexent6KUpdated Oct 19, 2026

Implement and maintain Nexent's traditional Python UT for product changes and bugfixes under test/backend, test/sdk, and test/ext_components. Cover unit behavior, boundaries, errors and regression assertions with isolated pytest tests. Formal D1-D5 assets in test-e2e use nexent-test-assets.

The English summary is being prepared. Showing the original description.

ModelEngine-Group/nexent6KUpdated Oct 19, 2026

Run Nexent requirements and bugfixes through SPEC acceptance, traditional UT and applicable D1-D5 test design, product/test implementation, local verification, and delivery evidence. Use for features, fixes, refactors and post-development test backfill across APIs, UI, model and Agent behavior.

The English summary is being prepared. Showing the original description.

ModelEngine-Group/nexent6KUpdated Oct 19, 2026

Create and maintain Nexent's repository-owned feature catalog, D1-D5 case-local contracts and fixed scripts, change records, generated execution registry and Excel view. Use for requirements, bug regressions, post-development test backfill, test implementation, and formal asset migration. Traditional UT uses nexent-python-tests.

The English summary is being prepared. Showing the original description.

ModelEngine-Group/nexent6KUpdated Oct 19, 2026

See all skills by ModelEngine-Group

Report a problem with this skill