Initial TrueGrowth source import

openspec/changes/archive/2026-04-29-add-ai-input-text-generation-mode/design.md

@@ -0,0 +1,21 @@
+## Context
+
+当前 AI 输入栏中 `text` 既表示文本模型，又承担 Agent 模式入口。这个复用导致：
+
+- UI 无法显式提供“文本生成”
+- 历史记录与偏好存储只能把 `text` 特判成 `agent`
+- 后续给文本模型增加参数与执行链时会继续污染 Agent 逻辑
+
+## Decision
+
+- 引入独立的 `agent` 生成类型
+- 保留 `text` 作为纯文本生成
+- `agent` 继续走 `ai_analyze`
+- `text` 新增直接生成步骤 `generate_text`
+- 文本生成完成后统一落到 `insert_to_canvas`
+
+## Notes
+
+- 旧本地存储中的 `generationType: text` 默认视为旧 Agent 模式，并通过版本字段迁移
+- 文本类型首版保持 `count = 1`
+- 文本参数先接入通用的 `temperature`、`top_p`、`max_tokens`

openspec/changes/archive/2026-04-29-add-ai-input-text-generation-mode/proposal.md

@@ -0,0 +1,14 @@
+# Change: add ai input text generation mode
+
+## Why
+AI 输入栏当前把 `text` 生成类型复用于 Agent 模式，导致“文本生成”无法作为独立能力暴露，模型参数、偏好存储、历史记录和工作流路由也持续混淆。
+
+## What Changes
+- 在 AI 输入栏新增独立的 `文本` 生成类型，并保留 `Agent`
+- 拆分 `agent` 与 `text` 的状态、偏好、历史记录与工作流语义
+- 新增文本直出工作流：文本模型生成结果后直接插入画布
+- 为文本类型接入通用模型参数调整
+
+## Impact
+- Affected specs: ai-input-generation
+- Affected code: `AIInputBar`、`workflow-converter`、`ai-input-parser`、`ai-generation-preferences-service`、`media-executor`

openspec/changes/archive/2026-04-29-add-ai-input-text-generation-mode/specs/ai-input-generation/spec.md

@@ -0,0 +1,34 @@
+## ADDED Requirements
+
+### Requirement: AI Input Bar SHALL Distinguish Agent And Text Generation
+
+The system SHALL expose `agent` and `text` as separate generation types in the AI input bar.
+
+#### Scenario: User selects text generation
+- **WHEN** the user switches the generation type to `text`
+- **THEN** the AI input bar SHALL show text models
+- **AND** SHALL hide Skill selection
+- **AND** SHALL treat the request as direct text generation
+
+#### Scenario: User selects agent generation
+- **WHEN** the user switches the generation type to `agent`
+- **THEN** the AI input bar SHALL show Skill selection
+- **AND** SHALL route the request through the existing Agent analysis flow
+
+### Requirement: Text Generation SHALL Insert Results Into Canvas
+
+The system SHALL insert direct text generation results into the canvas after the text model returns content.
+
+#### Scenario: Text model returns markdown-like content
+- **WHEN** a direct text generation request completes
+- **THEN** the system SHALL insert the text result through the existing canvas insertion flow
+- **AND** MAY parse markdown cards before falling back to plain text insertion
+
+### Requirement: Text Generation SHALL Support Scoped Model Parameters
+
+The system SHALL persist text-generation model parameters independently from agent mode.
+
+#### Scenario: User switches between text models
+- **WHEN** the user changes text models in direct text mode
+- **THEN** the system SHALL restore the last compatible parameters for the selected text model
+- **AND** SHALL NOT reuse agent-only state such as selected Skill

openspec/changes/archive/2026-04-29-add-ai-input-text-generation-mode/tasks.md

@@ -0,0 +1,6 @@
+## 1. Implementation
+- [x] 1.1 拆分 `GenerationType` 中的 `agent` / `text` 语义与偏好迁移
+- [x] 1.2 更新 AI 输入栏下拉、Skill 展示与通用参数显示逻辑
+- [x] 1.3 新增文本直出工作流与执行器分支
+- [x] 1.4 让文本生成结果自动插入画布
+- [x] 1.5 补充回归测试与迁移测试