feat: context aware prompt

[Reisenbug]

群聊上下文感知功能的提示词此前均为硬编码，用户无法根据自己的 Bot 人格或语言风格进行调整。

Modifications / 改动点

• astrbot/core/config/default.py：在 provider_ltm_settings 下新增两个可配置字段：

• context_prompt：上下文感知提示词（引导 LLM 理解聊天记录的前缀，普通模式与主动回复模式均生效）

• active_reply_suffix_prompt：主动回复后缀提示词（主动回复模式下追加在消息末尾的指令，仅主动回复启用时在
  Dashboard 中显示）

• astrbot/builtin_stars/astrbot/long_term_memory.py：从 配置读取上述字段，替换原有硬编码字符串

• dashboard/src/i18n/locales/zh-CNen-US/features/confi g-metadata.json：新增对应 i18n 翻译

• This is NOT a breaking change. / 这不是一个破坏性变更。

Screenshots or Test Results / 运行截图或测试结果

---

Checklist / 检查清单

• 😊 If there are new features added in the PR, I have discussed it with the authors through issues/emails, etc.
  / 如果 PR 中有新加入的功能，已经通过 Issue / 邮件等方式和作者讨论过。

• 👀 My changes have been well-tested, and "Verification Steps" and "Screenshots" have been provided above.
  / 我的更改经过了良好的测试，并已在上方提供了“验证步骤”和“运行截图”。

• 🤓 I have ensured that no new dependencies are introduced, OR if new dependencies are introduced, they have been added to the appropriate locations in requirements.txt and pyproject.toml.
  / 我确保没有引入新依赖库，或者引入了新依赖库的同时将其添加到 requirements.txt 和 pyproject.toml 文件相应位置。

• 😮 My changes do not introduce malicious code.
  / 我的更改没有引入恶意代码。

Summary by Sourcery

Make group chat long-term memory prompts configurable and expose them in the provider settings UI.

New Features:

• Add configurable context prompt for group chat history used in both normal and active reply modes.
• Add configurable active-reply suffix prompt appended to messages when active reply is enabled.

Enhancements:

• Replace hard-coded long-term memory prompts with values loaded from provider_ltm_settings, with sensible defaults.
• Extend provider configuration metadata to surface the new prompt fields in the dashboard only when active reply is enabled.

Documentation:

• Add i18n entries for the new context and active-reply prompt configuration fields in both Chinese and English locales.

[sourcery-ai]

Hey - I've left some high level feedback:

• The default values for context_prompt and active_reply_suffix_prompt are now hardcoded both in default.py and as .get(..., default) values in long_term_memory.py; consider relying on the config defaults only to avoid divergence if one side is changed later.
• In ChatProviderTemplate’s schema definition, provider_ltm_settings.active_reply_suffix_prompt appears to be nested inside the provider_ltm_settings.active_reply block; please double-check the brace/indent structure so that active_reply_suffix_prompt is defined at the intended level and the condition applies correctly in the dashboard.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- The default values for `context_prompt` and `active_reply_suffix_prompt` are now hardcoded both in `default.py` and as `.get(..., default)` values in `long_term_memory.py`; consider relying on the config defaults only to avoid divergence if one side is changed later.
- In `ChatProviderTemplate`’s `schema` definition, `provider_ltm_settings.active_reply_suffix_prompt` appears to be nested inside the `provider_ltm_settings.active_reply` block; please double-check the brace/indent structure so that `active_reply_suffix_prompt` is defined at the intended level and the condition applies correctly in the dashboard.

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[gemini-code-assist]

Code Review

This pull request introduces configurable prompts for long-term memory and active replies, replacing hardcoded strings with context_prompt and active_reply_suffix_prompt. The changes span the core logic, default settings, and dashboard localization. A critical syntax error was identified in astrbot/core/config/default.py, where the new configuration metadata is incorrectly nested within the whitelist dictionary, resulting in a malformed structure that will cause a Python syntax error.