dsh-more 0.0.2 → 0.0.3

package/README.md

@@ -131,6 +131,17 @@ After confirmation, DSH More cancels a running task, waits for idle, flushes the
 
 > **Irreversible:** permanent deletion does not archive the session and does not move it into a DSH More trash directory.
 
+### Configure model reasoning effort
+
+Open **Settings → Models**, expand a provider with **Edit**, and every model entry in the model catalog carries its own **Thinking effort** button:
+
+1. Click a model's **Thinking effort**; in the dialog, check the levels the model offers (off / minimal / low / medium / high / xhigh / max) and, for each enabled level, fill in the wire spelling sent to the gateway (defaults to the level name); `off` needs no wire value — "supported, send nothing".
+2. Click **Save**. The change is written to `reasoningEfforts` under `llm-pi-ai.providers.<route>.models[]` in `settings.yaml`, and the composer's model picker immediately offers those levels.
+
+You can also check **This model does not reason** (writes `reasoningEfforts: false`) or use **Clear** to drop the field and fall back to the installed catalog. Only `off` may leave its wire value empty, and at least one non-`off` level is required — the same rules the pi-ai adapter enforces when resolving a route. Invalid configurations are rejected before any write, so a bad save never corrupts `settings.yaml`.
+
+**Auto-fill:** models added via **Fetch available models** carry no `reasoningEfforts`, which the adapter treats as non-reasoning. After the provider is saved, this patch auto-fills the default `{ low, medium, high }` onto any model that has no `reasoningEfforts`, so a freshly fetched model can think immediately. To keep a model non-reasoning, set it to `reasoningEfforts: false` (explicit `false` is never auto-filled). The default levels can then be tuned per model from the thinking-effort button.
+
 ## Architecture
 
 ![Manifest-driven DSH More architecture](./docs/assets/dsh-more-architecture.jpg)

package/README.zh-CN.md

@@ -131,6 +131,17 @@ dsh plugin --profile web remove dsh-more
 
 > **不可恢复：** 永久删除不会归档会话，也不会把会话移入 DSH More 回收目录。
 
+### 配置模型思考强度
+
+打开 **设置 → 模型**，点击某个提供方的 **编辑** 展开「模型目录」，每个模型条目下都有一个 **思考强度** 按钮：
+
+1. 点击模型的 **思考强度**，在弹窗中勾选该模型支持的级别（不思考 / 极简 / 低 / 中 / 高 / 极高 / 最高），并为每个开启的级别填写发送给网关的线上值（默认与级别同名）；`不思考` 不需要线上值，表示“支持、但不发送任何参数”；
+2. 点击 **保存**。修改会写入 `settings.yaml` 中 `llm-pi-ai.providers.<route>.models[].reasoningEfforts`，会话里的模型选择器随即按此提供级别。
+
+也可以勾选 **该模型不支持思考**（写入 `reasoningEfforts: false`），或用 **清除配置** 移除该字段、回到内置目录的能力。只有 `off` 允许留空线上值，且必须至少声明一个非 `off` 的级别，与 pi-ai 适配器的解析规则一致；无效配置会在写入前被拒绝，不会破坏 `settings.yaml`。
+
+**自动填充：** 通过 **获取可用模型** 添加的模型默认没有 `reasoningEfforts`，适配器会把它当作不思考。本补丁会在保存提供方后，为**没有任何 `reasoningEfforts` 的模型**自动填入默认思考强度 `{ low, medium, high }`，让新拉取的模型立刻可以思考；如需某个模型不思考，请把它设为 `reasoningEfforts: false`（显式 false 不会被自动填充）。默认级别可用每个模型条目下的思考强度按钮再微调。
+
 ## 架构
 
 ![DSH More 清单驱动架构](./docs/assets/dsh-more-architecture.zh-CN.jpg)