Not Just a Working Demo: Why We Ran 162 Migration Tests for Two DSH Plugins

说明与用途

对 Codex 和 Claude Code 的两个 DSH 插件进行了 162 个迁移测试，识别出支持、部分支持和不支持的功能。修复后发布了 0.1.3 和 0.1.4 版本，流程可重复且已记录。

问题

Ensuring that DeepSeek Harness (DSH) plugins for Codex and Claude Code fully support real‑world development workflows after migration, rather than just passing a demo.

结果

The migration test suite confirmed which capabilities are fully supported, partially supported, or unsupported, enabling targeted fixes and transparent communication to users about migration boundaries.

工作流

• 1. Stop running DSH Web process.
• 2. Install plugins: dsh plugin --profile web add [email protected] dsh plugin --profile web add [email protected] dsh web.
• 3. Run the 162 migration test suite covering conversation, images, files, code, shell tools, Git, Skills, MCP, permissions, env vars, session import, host restarts, long‑context continuation.
• 4. Review results: supported, partial, unsupported per capability.
• 5. Fix identified failures (image transport, session import, process termination, secret persistence).
• 6. Release updated plugin versions and publish new support matrix.
• 7. Repeat cycle for continuous validation.

证据

We split real development work into 162 atomic requirements: 76 for Codex and 86 for Claude.

来源

The matrix covers conversation and multi-turn context, images and files, code and shell tools, tests and Git, Skills, MCP, project configuration, permissions, environment variables, session import, host restarts, and long-context continuation.

来源

By August 29, 2026, all 162 cases had results. We retained 167 runs in total; five were reviewed Codex reruns and do not inflate the requirement count.

来源