xai-review 0.17.0__tar.gz → 0.18.0__tar.gz

{xai_review-0.17.0 → xai_review-0.18.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: xai-review
-Version: 0.17.0
+Version: 0.18.0
 Summary: AI-powered code review tool
 Author-email: Nikita Filonov <nikita.filonov@example.com>
 Maintainer-email: Nikita Filonov <nikita.filonov@example.com>
@@ -39,6 +39,7 @@ _Made with ❤️ by [@NikitaFilonov](https://t.me/sound_right)_
 ## 📑 Table of Contents
 
 - ✨ [About](#-about)
+- 🧪 [Live Preview](#-live-preview)
 - 🚀 [Quick Start](#-quick-start)
 - ⚙️ [️CI/CD Integration](#-cicd-integration)
     - 🚀 [GitHub Actions](#-github-actions)
@@ -67,6 +68,27 @@ final decision to human reviewers.
 
 ---
 
+## 🧪 Live Preview
+
+Curious how **AI Review** works in practice? Here are three real Pull Requests reviewed entirely by the tool — one per
+mode:
+
+| Mode       | Description                                        | Live Example                                                                  |
+|------------|----------------------------------------------------|-------------------------------------------------------------------------------|
+| 🧩 Inline  | Adds line-by-line comments directly in the diff    | [Try AI Review (inline)](https://github.com/Nikita-Filonov/ai-review/pull/4)  |
+| 📄 Summary | Posts a concise summary review with key highlights | [Try AI Review (context)](https://github.com/Nikita-Filonov/ai-review/pull/5) |
+| 🧠 Context | Performs broader analysis across multiple files    | [Try AI Review (summary)](https://github.com/Nikita-Filonov/ai-review/pull/6) |
+
+Each review was generated automatically via GitHub Actions using the corresponding mode:
+
+```bash
+ai-review run-inline
+ai-review run-summary
+ai-review run-context
+```
+
+---
+
 ## 🚀 Quick Start
 
 Install via **pip**:
@@ -120,8 +142,8 @@ vcs:
 > **Note:** Running `ai-review run` executes the full review (inline + summary).
 > To run only one mode, use the dedicated subcommands:
 > - ai-review run-inline
-> - ai-review run-summary
 > - ai-review run-context
+> - ai-review run-summary
 
 ---
 
@@ -132,7 +154,7 @@ Key things you can customize:
 
 - **LLM provider** — OpenAI, Gemini, or Claude
 - **Model settings** — model name, temperature, max tokens
-- **VCS integration** — GitLab (currently supported) with project/MR context
+- **VCS integration** — works out of the box with **GitLab** and **GitHub**.
 - **Review policy** — which files to include/exclude, review modes
 - **Prompts** — inline/context/summary prompt templates
 
@@ -170,7 +192,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: Nikita-Filonov/ai-review@v0.17.0
+      - uses: Nikita-Filonov/ai-review@v0.18.0
         with:
           review-command: ${{ inputs.review-command }}
         env:

{xai_review-0.17.0 → xai_review-0.18.0}/README.md

@@ -15,6 +15,7 @@ _Made with ❤️ by [@NikitaFilonov](https://t.me/sound_right)_
 ## 📑 Table of Contents
 
 - ✨ [About](#-about)
+- 🧪 [Live Preview](#-live-preview)
 - 🚀 [Quick Start](#-quick-start)
 - ⚙️ [️CI/CD Integration](#-cicd-integration)
     - 🚀 [GitHub Actions](#-github-actions)
@@ -43,6 +44,27 @@ final decision to human reviewers.
 
 ---
 
+## 🧪 Live Preview
+
+Curious how **AI Review** works in practice? Here are three real Pull Requests reviewed entirely by the tool — one per
+mode:
+
+| Mode       | Description                                        | Live Example                                                                  |
+|------------|----------------------------------------------------|-------------------------------------------------------------------------------|
+| 🧩 Inline  | Adds line-by-line comments directly in the diff    | [Try AI Review (inline)](https://github.com/Nikita-Filonov/ai-review/pull/4)  |
+| 📄 Summary | Posts a concise summary review with key highlights | [Try AI Review (context)](https://github.com/Nikita-Filonov/ai-review/pull/5) |
+| 🧠 Context | Performs broader analysis across multiple files    | [Try AI Review (summary)](https://github.com/Nikita-Filonov/ai-review/pull/6) |
+
+Each review was generated automatically via GitHub Actions using the corresponding mode:
+
+```bash
+ai-review run-inline
+ai-review run-summary
+ai-review run-context
+```
+
+---
+
 ## 🚀 Quick Start
 
 Install via **pip**:
@@ -96,8 +118,8 @@ vcs:
 > **Note:** Running `ai-review run` executes the full review (inline + summary).
 > To run only one mode, use the dedicated subcommands:
 > - ai-review run-inline
-> - ai-review run-summary
 > - ai-review run-context
+> - ai-review run-summary
 
 ---
 
@@ -108,7 +130,7 @@ Key things you can customize:
 
 - **LLM provider** — OpenAI, Gemini, or Claude
 - **Model settings** — model name, temperature, max tokens
-- **VCS integration** — GitLab (currently supported) with project/MR context
+- **VCS integration** — works out of the box with **GitLab** and **GitHub**.
 - **Review policy** — which files to include/exclude, review modes
 - **Prompts** — inline/context/summary prompt templates
 
@@ -146,7 +168,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: Nikita-Filonov/ai-review@v0.17.0
+      - uses: Nikita-Filonov/ai-review@v0.18.0
         with:
           review-command: ${{ inputs.review-command }}
         env:

{xai_review-0.17.0 → xai_review-0.18.0}/ai_review/services/vcs/github/client.py

@@ -124,6 +124,10 @@ class GitHubVCSClient(VCSClient):
 
     async def create_discussion(self, file: str, line: int, message: str) -> None:
         try:
+            logger.info(
+                f"Posting inline comment in {self.owner}/{self.repo}#{self.pull_number} at {file}:{line}: {message}"
+            )
+
             pr = await self.http_client.pr.get_pull_request(
                 owner=self.owner, repo=self.repo, pull_number=self.pull_number
             )

{xai_review-0.17.0 → xai_review-0.18.0}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 [project]
 name = "xai-review"
 readme = "README.md"
-version = "0.17.0"
+version = "0.18.0"
 license = { text = "Apache-2.0" }
 authors = [
     { name = "Nikita Filonov", email = "nikita.filonov@example.com" }

{xai_review-0.17.0 → xai_review-0.18.0}/xai_review.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: xai-review
-Version: 0.17.0
+Version: 0.18.0
 Summary: AI-powered code review tool
 Author-email: Nikita Filonov <nikita.filonov@example.com>
 Maintainer-email: Nikita Filonov <nikita.filonov@example.com>
@@ -39,6 +39,7 @@ _Made with ❤️ by [@NikitaFilonov](https://t.me/sound_right)_
 ## 📑 Table of Contents
 
 - ✨ [About](#-about)
+- 🧪 [Live Preview](#-live-preview)
 - 🚀 [Quick Start](#-quick-start)
 - ⚙️ [️CI/CD Integration](#-cicd-integration)
     - 🚀 [GitHub Actions](#-github-actions)
@@ -67,6 +68,27 @@ final decision to human reviewers.
 
 ---
 
+## 🧪 Live Preview
+
+Curious how **AI Review** works in practice? Here are three real Pull Requests reviewed entirely by the tool — one per
+mode:
+
+| Mode       | Description                                        | Live Example                                                                  |
+|------------|----------------------------------------------------|-------------------------------------------------------------------------------|
+| 🧩 Inline  | Adds line-by-line comments directly in the diff    | [Try AI Review (inline)](https://github.com/Nikita-Filonov/ai-review/pull/4)  |
+| 📄 Summary | Posts a concise summary review with key highlights | [Try AI Review (context)](https://github.com/Nikita-Filonov/ai-review/pull/5) |
+| 🧠 Context | Performs broader analysis across multiple files    | [Try AI Review (summary)](https://github.com/Nikita-Filonov/ai-review/pull/6) |
+
+Each review was generated automatically via GitHub Actions using the corresponding mode:
+
+```bash
+ai-review run-inline
+ai-review run-summary
+ai-review run-context
+```
+
+---
+
 ## 🚀 Quick Start
 
 Install via **pip**:
@@ -120,8 +142,8 @@ vcs:
 > **Note:** Running `ai-review run` executes the full review (inline + summary).
 > To run only one mode, use the dedicated subcommands:
 > - ai-review run-inline
-> - ai-review run-summary
 > - ai-review run-context
+> - ai-review run-summary
 
 ---
 
@@ -132,7 +154,7 @@ Key things you can customize:
 
 - **LLM provider** — OpenAI, Gemini, or Claude
 - **Model settings** — model name, temperature, max tokens
-- **VCS integration** — GitLab (currently supported) with project/MR context
+- **VCS integration** — works out of the box with **GitLab** and **GitHub**.
 - **Review policy** — which files to include/exclude, review modes
 - **Prompts** — inline/context/summary prompt templates
 
@@ -170,7 +192,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: Nikita-Filonov/ai-review@v0.17.0
+      - uses: Nikita-Filonov/ai-review@v0.18.0
         with:
           review-command: ${{ inputs.review-command }}
         env: