Conversation
Summary of ChangesHello @DankerMu, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request enhances the project's documentation by providing clearer and more comprehensive guidance on configuring third-party and proxy API providers. The updates aim to reduce user friction during setup, especially concerning Highlights
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
The pull request effectively clarifies the configuration of third-party/proxy API providers in the README files, which will significantly reduce migration friction for users. The added tips regarding AI_PROVIDER_FORMAT selection, Base URL formatting, image generation limitations, and quick validation steps are very helpful and well-explained.
| **第三方 / 代理 API 配置提示（AI_PROVIDER_FORMAT / Base URL）** | ||
|
|
||
| - `AI_PROVIDER_FORMAT=openai`：用于 OpenAI 兼容接口（`OPENAI_API_*`），`OPENAI_API_BASE` 通常需要包含 `/v1`（例如 `https://api.openai.com/v1` / `https://xxx/v1`）。 | ||
| - `AI_PROVIDER_FORMAT=gemini`：用于 Gemini 原生接口或代理（`GOOGLE_API_*`），`GOOGLE_API_BASE` 通常不需要 `/v1`，代理常见是 `https://xxx/gemini`。 | ||
| - Base URL 末尾不要带 `/`（常见错误：`.../v1/`、`.../gemini/` 会导致路径拼接异常）。 | ||
| - 图片生成：本项目的 OpenAI 格式图片生成可能限制到 1K 分辨率；需要更高分辨率更建议使用 `gemini` 格式。 | ||
| - 验证方式：在网页设置页 `/settings` 填写并保存后，尝试生成“大纲”；成功说明 Key/Base 可访问。 |
There was a problem hiding this comment.
The detailed API configuration tips are repeated in this section, as well as under the '从源码部署' section. While this ensures visibility, it creates redundancy and increases maintenance effort. If these tips need to be updated, they must be changed in multiple places, which can lead to inconsistencies.
Consider consolidating these tips into a single, dedicated 'API Configuration' section and referencing it from both deployment sections. Alternatively, if the repetition is intentional for immediate context, ensure a clear process for keeping all instances synchronized.
| **第三方 / 代理 API 配置提示（AI_PROVIDER_FORMAT / Base URL）** | ||
|
|
||
| - `AI_PROVIDER_FORMAT=openai`：用于 OpenAI 兼容接口（`OPENAI_API_*`），`OPENAI_API_BASE` 通常需要包含 `/v1`（例如 `https://api.openai.com/v1` / `https://xxx/v1`）。 | ||
| - `AI_PROVIDER_FORMAT=gemini`：用于 Gemini 原生接口或代理（`GOOGLE_API_*`），`GOOGLE_API_BASE` 通常不需要 `/v1`，代理常见是 `https://xxx/gemini`。 | ||
| - Base URL 末尾不要带 `/`（常见错误：`.../v1/`、`.../gemini/` 会导致路径拼接异常）。 | ||
| - 图片生成：本项目的 OpenAI 格式图片生成可能限制到 1K 分辨率；需要更高分辨率更建议使用 `gemini` 格式。 | ||
| - 验证方式：在网页设置页 `/settings` 填写并保存后，尝试生成“大纲”；成功说明 Key/Base 可访问。 |
There was a problem hiding this comment.
This block of API configuration tips is a duplicate of the one found under the '使用 Docker Compose🐳（推荐）' section. Duplication can lead to maintenance challenges and potential inconsistencies if updates are not applied uniformly across all instances.
To improve maintainability, it is recommended to consolidate this information into a single source and refer to it from relevant sections. This ensures that any future changes only need to be made in one place.
| **Third-party / Proxy API configuration tips (AI_PROVIDER_FORMAT / Base URL)** | ||
|
|
||
| - `AI_PROVIDER_FORMAT=openai`: for OpenAI-compatible endpoints (`OPENAI_API_*`). `OPENAI_API_BASE` usually needs to include `/v1` (e.g. `https://api.openai.com/v1` or `https://xxx/v1`). | ||
| - `AI_PROVIDER_FORMAT=gemini`: for Gemini-native endpoints/proxies (`GOOGLE_API_*`). `GOOGLE_API_BASE` usually does not include `/v1`; proxies commonly look like `https://xxx/gemini`. | ||
| - Avoid a trailing `/` in base URLs (common pitfall: `.../v1/`, `.../gemini/` can break path concatenation). | ||
| - Image generation: OpenAI-format image generation may be limited to 1K in this project; prefer `gemini` format for higher resolutions. | ||
| - Quick validation: use the web UI Settings page at `/settings` — if outline generation works, your key/base URL is reachable. |
There was a problem hiding this comment.
The detailed API configuration tips are repeated in this section, as well as under the 'Backend Installation' section. While this ensures visibility, it creates redundancy and increases maintenance effort. If these tips need to be updated, they must be changed in multiple places, which can lead to inconsistencies.
Consider consolidating these tips into a single, dedicated 'API Configuration' section and referencing it from both deployment sections. Alternatively, if the repetition is intentional for immediate context, ensure a clear process for keeping all instances synchronized.
| **Third-party / Proxy API configuration tips (AI_PROVIDER_FORMAT / Base URL)** | ||
|
|
||
| - `AI_PROVIDER_FORMAT=openai`: for OpenAI-compatible endpoints (`OPENAI_API_*`). `OPENAI_API_BASE` usually needs to include `/v1` (e.g. `https://api.openai.com/v1` or `https://xxx/v1`). | ||
| - `AI_PROVIDER_FORMAT=gemini`: for Gemini-native endpoints/proxies (`GOOGLE_API_*`). `GOOGLE_API_BASE` usually does not include `/v1`; proxies commonly look like `https://xxx/gemini`. | ||
| - Avoid a trailing `/` in base URLs (common pitfall: `.../v1/`, `.../gemini/` can break path concatenation). | ||
| - Image generation: OpenAI-format image generation may be limited to 1K in this project; prefer `gemini` format for higher resolutions. | ||
| - Quick validation: use the web UI Settings page at `/settings` — if outline generation works, your key/base URL is reachable. |
There was a problem hiding this comment.
This block of API configuration tips is a duplicate of the one found under the 'Using Docker Compose🐳 (Recommended)' section. Duplication can lead to maintenance challenges and potential inconsistencies if updates are not applied uniformly across all instances.
To improve maintainability, it is recommended to consolidate this information into a single source and refer to it from relevant sections. This ensures that any future changes only need to be made in one place.
- Replace fixed sleep with health polling (60s) via scripts/wait-for-health.sh\n- Soften Base URL trailing-slash wording in docs\n- Clarify 1K image limit note in README_EN
|
Re-review after smoke-test health polling + doc tweaks:
Nit (non-blocking): in LGTM. |
DankerMu
left a comment
DankerMu
left a comment
There was a problem hiding this comment.
Re-review: CI green; smoke-test health polling + EXIT trap looks solid. Docs additions are helpful. (Nit: consider clarifying “1K resolution limit” wording in README_EN.md.)
|
Review summary (local)
LGTM (waiting for CI; maintainer merge required). |
1 participant
Summary
Clarifies how to configure third-party/proxy API providers (base URL and
AI_PROVIDER_FORMAT) to reduce migration friction.Changes
AI_PROVIDER_FORMATselection and Base URL pitfalls (/v1vs/gemini, no trailing/)./settingsas a quick validation path.Closes #59