test(python): pin the minimal composition's model-visible surface

The Python lane never compared what the minimal composition shows the
model: the mock model only asserted system-role messages, and the
advanced snapshot tokenizes the assembled system prompt and tool
schemas.

The sdk-minimal scenario now records model-visible.json — every model
request's advertised tool schemas verbatim and its message list, with
system and user text kept and assistant/tool payloads reduced to call
identity so the expected output replays on macOS and Linux. It excludes
the dynamic runtime-context snapshot, which the same composition emits
on macOS and not on Linux (#2488).

AGENTS.md and the testing policy name both SDKs as independent
projections of the agent loop, session lifecycle, and SessionEventMap.

python/development.zh.md

@@ -27,6 +27,15 @@ uv run --project python/sdk pytest
 
 `python/sdk/tests/test_bundled_runtime.py` 会运行可用的内置载体；某个载体的产物尚未构建时，会跳过该载体。仓库级测试政策见 [测试](../docs/testing.md)。
 
+该套件面向的是伪造的运行时对端。`scripts/smoke-python-runtime.py` 面向真实的打包运行时；必需的 `python-runtime` CI 任务会用新构建的可执行文件运行全部场景：
+
+```sh
+uv run --project python/sdk python scripts/smoke-python-runtime.py \
+  --scenario sdk-minimal --exe dist-exe/dsh-jsonrpc-agent-pkg-macos-arm64
+```
+
+其中两个场景会比对 `scripts/snapshots/python-sdk-single-exe/` 下已提交的期望输出。`minimal/model-visible.json` 固定了签入的极简组合所组装的系统提示词、对外公布的工具 schema 以及模型可见消息，因此插件一旦贡献出计划外的系统分段或 user 消息，该任务即失败；它会丢弃动态运行时上下文快照——同一组合在 macOS 上会发出它，在 Linux 上不会（[#2488](https://github.com/deepseek-harness/deepseek-harness/issues/2488)）。`advanced/` 固定 SDK 结果与持久化的会话日志。重新运行对应场景时加上 `--update-snapshots`，并在提交前审阅该差异。
+
 交互式冒烟测试需要环境变量或仓库根目录 `.env` 中存在 `DEEPSEEK_API_KEY`：
 
 ```python