Pi v0.80.6 - 更新日志

### 新功能 - **`max` 思考级别** - 新增可选的 `max` 思考级别，位于 `xhigh` 之上，原生支持 GPT-5.6 和自适应 Claude 模型，可在 CLI（`--thinking max`）、SDK、RPC 和模型选择中使用。自定义主题可定义 `thinkingMax`。详见 [CLI 参考](https://github.com/earendil-works/pi/blob/v0.80.6/packages/coding-agent/docs/usage.md#cli-reference)。 - **基于输入的定价层级** - 针对请求范围的输入 token 定价层级，用于精确的长上下文成本核算（例如 GPT-5.4/5.5/5.6 的长上下文费率），也可在 `models.json` 和 `modelOverrides` 中为自定义模型进行配置。详见 [模型配置](https://github.com/earendil-works/pi/blob/v0.80.6/packages/coding-agent/docs/models.md#model-configuration)。 ### 新增 - 在 CLI、SDK、RPC、模型选择和主题中新增可选的 `max` 思考级别。自定义主题可定义 `thinkingMax`；现有主题将回退至 `thinkingXhigh`。 - 在 `models.json`、`modelOverrides` 和扩展注册的提供商中，为自定义模型成本新增请求范围的输入 token 定价层级。 - 为 `shellPath` 设置新增 `~`（主目录）展开功能 ([#6470](https://github.com/earendil-works/pi/pull/6470) by [@aaronkyriesenbach](https://github.com/aaronkyriesenbach))。 ### 修复 - 修复了继承的后压缩输出 token 预算分配，使其忽略压缩边界之前的过时助手使用情况 ([#6464](https://github.com/earendil-works/pi/issues/6464))。 - 修复了继承的 GPT-5.4 和 GPT-5.5 长上下文成本核算，同时保留了对需要显式覆盖的模型有意设置的 272K 默认上下文限制。 - 修复了继承的 GPT-5.6 元数据，使直接 OpenAI 请求保持在 272K 短上下文层级，同时暴露 Codex 后端的 372K 上下文窗口并采用长上下文定价，并移除了不存在的裸 `gpt-5.6` 别名。 - 修复了继承的 Anthropic 消息转换，保留带有空思考文本但签名有效的思考块，而不是丢弃它们，从而避免在新版 Claude 模型上出现思考块错误 ([#6457](https://github.com/earendil-works/pi/pull/6457) by [@davidbrai](https://github.com/davidbrai))。

### New Features - **`max` thinking level** - New opt-in thinking level above `xhigh`, natively supported on GPT-5.6 and adaptive Claude models, available across CLI (`--thinking max`), SDK, RPC, and model selection. Custom themes can define `thinkingMax`. See [CLI Reference](https://github.com/earendil-works/pi/blob/v0.80.6/packages/coding-agent/docs/usage.md#cli-reference). - **Input-based pricing tiers** - Request-wide input-token pricing tiers for accurate long-context cost accounting (e.g. GPT-5.4/5.5/5.6 long-context rates), also configurable for custom models in `models.json` and `modelOverrides`. See [Model Configuration](https://github.com/earendil-works/pi/blob/v0.80.6/packages/coding-agent/docs/models.md#model-configuration). ### Added - Added the opt-in `max` thinking level across CLI, SDK, RPC, model selection, and themes. Custom themes can define `thinkingMax`; existing themes fall back to `thinkingXhigh`. - Added request-wide input-token pricing tiers to custom model costs in `models.json`, `modelOverrides`, and extension-registered providers. - Added `~` (home directory) expansion for the `shellPath` setting ([#6470](https://github.com/earendil-works/pi/pull/6470) by [@aaronkyriesenbach](https://github.com/aaronkyriesenbach)). ### Fixed - Fixed inherited post-compaction output-token budgeting to ignore stale assistant usage from before the compaction boundary ([#6464](https://github.com/earendil-works/pi/issues/6464)). - Fixed inherited GPT-5.4 and GPT-5.5 long-context cost accounting while retaining the intentional 272K default context limit for models that require an explicit override. - Fixed inherited GPT-5.6 metadata to keep direct OpenAI requests in the 272K short-context tier while exposing the Codex backend's 372K context window with long-context pricing, and removed the nonexistent bare `gpt-5.6` alias. - Fixed inherited Anthropic message conversion to preserve thinking blocks with empty thinking text but a valid signature instead of dropping them, avoiding thinking-block errors on newer Claude models ([#6457](https://github.com/earendil-works/pi/pull/6457) by [@davidbrai](https://github.com/davidbrai)).