gitpr-cli 0.0.26__py3-none-any.whl → 0.0.28__py3-none-any.whl

{gitpr_cli-0.0.26.dist-info → gitpr_cli-0.0.28.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gitpr-cli
-Version: 0.0.26
+Version: 0.0.28
 Summary: Automação de PRs, Commits e Code Review com IA (Gemini e DeepSeek)
 Author-email: Natan Fiuza <contato@natanfiuza.dev.br>
 Requires-Python: >=3.10
@@ -14,12 +14,20 @@ Requires-Dist: cryptography
 Requires-Dist: pyyaml
 Requires-Dist: textual
 Requires-Dist: requests
+Requires-Dist: mcp>=1.0.0
 Dynamic: license-file
 
+
 # **GitPR CLI 🚀**
 
+<p align="center">
+  <img src="https://raw.githubusercontent.com/natanfiuza/gitpr/main/docs/logo.png" alt="GitPR Logo" width="150">
+</p>
+
 GitPR CLI is a command-line automation tool that uses **Google Gemini** and **DeepSeek** artificial intelligence to analyze your code changes (git diff) or entire files. The tool automatically generates commit messages in the *Conventional Commits* standard, detailed Pull Request descriptions, and deep Code Reviews aimed at reducing technical debt.
 
+🌐 **Website:** [gitpr.natanfiuza.dev.br](https://gitpr.natanfiuza.dev.br/) · 📂 **Repository:** [github.com/natanfiuza/gitpr](https://github.com/natanfiuza/gitpr)
+
 ## **🛠️ Technologies and Libraries Used**
 
 This project was developed in Python and uses the following main libraries:
@@ -33,6 +41,7 @@ This project was developed in Python and uses the following main libraries:
 * [**PyYAML**](https://pyyaml.org/): Used to read and process the custom static analysis rules from the `.gitpr.linter.yml` file.
 * [**Textual**](https://textual.textualize.io/): Powerful library for creating Terminal Graphical Interfaces (TUI), used in the interactive issue generation and editing panel.
 * [**Requests**](https://pypi.org/project/requests/): Elegant and robust library for HTTP requests, used to communicate with the GitHub REST API.
+* [**MCP**](https://pypi.org/project/mcp/): Official Python SDK for the Model Context Protocol, enabling GitPR to integrate directly with AI-powered editors and IDEs.
 
 ----
 
@@ -130,6 +139,8 @@ You can pass the following *flags* for specific actions:
 * `--lang <code>`: Forces the interface language for this execution (e.g.: `en_us`, `pt_br`). Overrides `GITPR_LANG` in `.env` without persisting the change.
 * `-ch` or `--chat`: Opens the **Interactive Pair Programming Chat** — a TUI terminal where the AI sees your current diff and maintains a contextual conversation. Features memory per branch, slash commands (`/explain`, `/tests`, `/optimize`, `/clear`), auto-patching (F5), diff refresh (F2), and session export (F6).
 * `-l` or `--linter`: Runs **only the local static linter** (no AI calls). Ideal for use in CI/CD pipelines to block non-compliant code.
+* `--mcp`: Starts GitPR as an **MCP server** (Model Context Protocol) on stdio transport. Enables integration with VS Code, Cursor, Claude Desktop, and other MCP-compatible editors — exposing all GitPR AI capabilities as tools directly inside your IDE. Also available as the standalone `gitpr-mcp` command.
+* `--install`: **Interactive Setup Wizard.** Runs a guided 4-step setup: downloads skill templates, installs Git hooks, configures MCP for detected editors, and checks/requests your AI provider API key. Each step asks for confirmation before proceeding.
 * `-ih` or `--installhooks`: Automatically installs **local Git Hooks** (`pre-commit` and `prepare-commit-msg`) in your repository.
 * `-s` or `--skill`: Creates the AI context template files (`.gitpr.commit.md`, `.gitpr.pr.md`, `.gitpr.review.md`, `.gitpr.filereview.md`, `.gitpr.issue.md`, `.gitpr.blame.md`) and the Linter (`.gitpr.linter.yml`) at the project root.
 * `-is` or `--issue`: Automatically generates a draft of a **standardized Issue** and opens an interactive interface (TUI) for editing or direct submission via REST API. This feature has **3 context engines** depending on the command combination:
@@ -140,6 +151,14 @@ You can pass the following *flags* for specific actions:
 * `-u` or `--update`: Checks and installs the latest version of GitPR (Auto-Updater).
 
 > **⚙️ Technical Note (--hook):** GitPR has a hidden flag `--hook <file>` that is triggered exclusively by the Git Hooks system in the background. It allows the AI to inject the suggested message directly into Git's temporary file, without cluttering your terminal.
+>
+> **⚙️ Technical Note (--pre-save):** GitPR has a hidden debug flag `--pre-save` that can be combined with any AI command (e.g.: `gitpr -c --pre-save`). Before each AI call, it saves the full payload that will be sent to the model (system instruction + prompt + character counters) to a `_{action}-{datetime}.json` file in the current folder, and then proceeds normally. Useful for inspecting very large prompts. Note: when the response comes from the local cache, no call is made and no file is generated.
+
+### 📦 Huge Diffs (Map-Reduce)
+
+When your diff is too large for a single AI call (over ~90k estimated tokens), GitPR automatically splits it into batches by file, asks the AI for a technical summary of each part (Map), and unifies everything into the final commit message, review, or PR description (Reduce). No flags needed — it activates on demand and shows the progress in the console.
+
+📚 Full documentation: [docs/map-reduce-diff.md](https://github.com/natanfiuza/gitpr/blob/main/docs/map-reduce-diff.md)
 
 ## 🛡️ Local Linter (Static Analysis)
 
@@ -194,7 +213,64 @@ GitPR automatically detects your system language and displays messages in your n
 
 To force a specific language, set `GITPR_LANG=pt_br` or `GITPR_LANG=en` in `~/.gitpr/.env`.
 
-> 📖 **Full developer guide:** [docs/i18n_explanation.md](docs/i18n_explanation.md) — architecture, usage patterns, circular import precautions, and how to add new languages.
+> 📖 **Full developer guide:** [docs/i18n_explanation.md](https://github.com/natanfiuza/gitpr/blob/main/docs/i18n_explanation.md) — architecture, usage patterns, circular import precautions, and how to add new languages.
+
+## 🔌 MCP Integration (Model Context Protocol)
+
+GitPR can run as an **MCP server**, exposing its AI-powered capabilities as tools that your editor's AI assistant can invoke directly — no terminal needed. This enables a fully integrated workflow where you can generate commit messages, review code, run linters, trace code origins, and create issues without leaving your IDE.
+
+### Supported Editors
+
+| Editor | Config File |
+| ------ | ----------- |
+| **VS Code** | `.vscode/mcp.json` |
+| **Cursor** | `.cursor/mcp.json` |
+| **Claude Code** | `.mcp.json` |
+| **Claude Desktop** | `claude_desktop_config.json` |
+| **Zed** | `settings.json` |
+
+### Quick Setup
+
+Use the built-in installer to configure your editor automatically:
+
+```bash
+gitpr-mcp --install vscode    # Creates .vscode/mcp.json
+gitpr-mcp --install cursor      # Creates .cursor/mcp.json
+gitpr-mcp --install claude-code # Creates .mcp.json
+gitpr-mcp --install claude      # Updates Claude Desktop config
+gitpr-mcp --install zed         # Updates Zed settings
+gitpr-mcp --install auto      # Auto-detect and install for all found
+```
+
+The installer creates the config directory if needed, merges with any existing
+config (never overwrites other servers), and is safe to run multiple times.
+
+> Manual setup is also supported — see [docs/mcp-integration.md](https://github.com/natanfiuza/gitpr/blob/main/docs/mcp-integration.md)
+> for the JSON config format for each editor.
+
+Once configured, use natural language in your editor's AI chat:
+
+   * *"Review my current changes"* → calls `review_code`
+   * *"Generate a commit message"* → calls `generate_commit_message`
+   * *"Create a PR description"* → calls `generate_pr_description`
+   * *"Run the linter on my diff"* → calls `run_linter`
+
+### Available MCP Tools
+
+| Tool | Description |
+| ---- | ----------- |
+| `get_git_context` | Current branch, repository name, and remote URL |
+| `analyze_diff` | Git diff of uncommitted changes |
+| `get_full_diff` | Full diff against origin/main |
+| `generate_commit_message` | AI-generated Conventional Commits message |
+| `review_code` | AI code review of local changes |
+| `full_review` | AI code review of all changes since origin/main |
+| `generate_pr_description` | Complete PR description (title + body) |
+| `run_linter` | Static linter against `.gitpr.linter.yml` |
+| `analyze_blame` | Git blame + AI classification |
+| `generate_issue` | Structured issue from diff, history, or blame |
+
+📖 **Full documentation:** [docs/mcp-integration.md](https://github.com/natanfiuza/gitpr/blob/main/docs/mcp-integration.md) — available in 5 languages (EN, PT-BR, PT-PT, ES, FR).
 
 ## 📚 Technical Documentation and Advanced Guides
 
@@ -225,10 +301,12 @@ If you want to implement GitPR as an automated quality barrier in your team, che
 
 ### Configuration & Infrastructure
 
+* [**Install Wizard**](https://github.com/natanfiuza/gitpr/blob/main/docs/install-wizard.md) — Step-by-step guided setup for configuring GitPR in a new project.
 * [**AI Providers**](https://github.com/natanfiuza/gitpr/blob/main/docs/providers-ia.md) — Configuration and selection between Google Gemini, DeepSeek, and Ollama.
 * [**Auto-Updater**](https://github.com/natanfiuza/gitpr/blob/main/docs/auto-update.md) — How GitPR's automatic update (hot-swap) works.
 * [**GitHub Token (PAT) Integration and Security**](https://github.com/natanfiuza/gitpr/blob/main/docs/github-pat-integration.md) — Understand how GitPR creates issues directly in the repository with authentication.
 * [**Internationalization (i18n)**](https://github.com/natanfiuza/gitpr/blob/main/docs/i18n_explanation.md) — Architecture, usage patterns, and how to add new languages.
+* [**MCP Integration**](https://github.com/natanfiuza/gitpr/blob/main/docs/mcp-integration.md) — Connect GitPR to VS Code, Cursor, and Claude Desktop via Model Context Protocol.
 
 ## ⚡ Local Cache System (Quota Savings)
 

gitpr_cli-0.0.28.dist-info/RECORD

@@ -0,0 +1,26 @@
+gitpr_cli-0.0.28.dist-info/licenses/LICENSE,sha256=UQzLC6mwqb-ZNDkBBAqOxC-SMQcEID0gaM6oFcu6u48,27030
+src/__init__.py,sha256=U6ksarernNcryHO20aj4rNG7w0thT7xdMs5KzBJyPvE,28
+src/ai_providers.py,sha256=cxPuytZ9LfvhQbWFPBJ4dud3lHLpAQpa3cbY8bKESk8,10954
+src/blame_engine.py,sha256=z-uh8mHOF--JxY_nnbp5r_9y_a_IO4Zn42P0AeLBpto,10436
+src/cache.py,sha256=XggMTy00GlZfeF1VoLEYCdxL5h0eTg11TJfPIRPx7fs,3201
+src/chat_memory.py,sha256=vdYuElIQb6-flFm4SfzapnQZGRIwgbLECzIcsAc0Oo8,8724
+src/config.py,sha256=VJ9ekDlTVG5ETWDuO1kZWlgrncXbrvduxa5Zg7wN_ZY,9064
+src/core.py,sha256=PqwqWHA5h_EplQ6mURxriS5Ql9_QPq73S2R9zJ11-78,28580
+src/i18n.py,sha256=QED7hTSdWCC1lSNJ-l6VuOba18OrWgFTMQcZ7cQmXbY,3599
+src/issue_engine.py,sha256=XJ7WNLoeg3wct079wS7OQqU62f_avn3A8LmMuPWchzE,3642
+src/linter_engine.py,sha256=D04wvOgRa-vZEYknm-z-Cg7V_3gnoQz_64PMorWnISo,4414
+src/main.py,sha256=BoI2aN3l1fS4UzoWL67Yw2QtkeRxh9ITuVIQEc9JOPA,32724
+src/mcp_server.py,sha256=14BRJX7-etSPztBdUfzocbL9KML99nogQfjkZFRFFIU,31406
+src/security.py,sha256=Li0zM8ZURTK2nKRHIt49TWLO4DIddBEHzXPrVycv0Rs,1343
+src/spinner.py,sha256=16ngB2oT1t7O-c3D2DWCJbFb9nMyD-HWv6KcvhKTelQ,7651
+src/tui_issue.py,sha256=gcAJCIfMcdeMjrFJUWQQvdgBv7fnOBtxQxwdBk2Sk40,1789
+src/updater.py,sha256=M30nc_eAO7CZl6628TkSwuTwXbzZ9sdIgaoilLL1z2A,5886
+src/ui/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+src/ui/chat_app.py,sha256=y-py5UpisQbPLqqDON8AIkyA7X1IM5LAn1GbeYr2p_U,25598
+src/ui/help_screen.py,sha256=tjbokXhwyzLnkOC0S56NbpX-78hcFQnvsQMpNU1wt0c,1862
+src/ui/issue_app.py,sha256=8MdBcOVdCHPFx6EUhs80CiZ2G-29KulskkCz9qMZ_Lg,4737
+gitpr_cli-0.0.28.dist-info/METADATA,sha256=w1I_R_77I4BP4ajS81C7KcE_PSxpSGqaECzTayg64iM,22656
+gitpr_cli-0.0.28.dist-info/WHEEL,sha256=K260EYznzXsJYBQGqmI8VTxEdiZYNvDZwW9cBh9-_MA,91
+gitpr_cli-0.0.28.dist-info/entry_points.txt,sha256=TstGnMUzdOI5qNmpM97EPDBPuMqOZxoo6EoLxHSOMSQ,71
+gitpr_cli-0.0.28.dist-info/top_level.txt,sha256=74rtVfumQlgAPzR5_2CgYN24MB0XARCg0t-gzk6gTrM,4
+gitpr_cli-0.0.28.dist-info/RECORD,,

{gitpr_cli-0.0.26.dist-info → gitpr_cli-0.0.28.dist-info}/entry_points.txt

@@ -1,2 +1,3 @@
 [console_scripts]
 gitpr = src.main:cli
+gitpr-mcp = src.mcp_server:main

src/ai_providers.py

@@ -1,5 +1,6 @@
 import json
 import time
+from datetime import datetime
 import click
 from google import genai
 from openai import OpenAI
@@ -10,13 +11,65 @@ from src.spinner import Spinner
 from src.i18n import __,CURRENT_LANG
 
 
-def call_ai_model(provider, api_key, api_model, prompt, system_instruction, quiet=False):
+# Hidden --pre-save debug flag: when enabled, every AI payload is dumped
+# to a JSON file in the current directory before being sent to the model.
+PRE_SAVE_ENABLED = False
+
+
+def set_pre_save(enabled):
+    """Enable/disable the pre-save payload dump (set once from the CLI)."""
+    global PRE_SAVE_ENABLED
+    PRE_SAVE_ENABLED = enabled
+
+
+def _save_pre_save_payload(action, provider, api_model, system_instruction, prompt=None, chat_history=None, new_message=None):
+    """
+    Dump the full AI payload to a _{action}-{datetime}.json file in the current directory.
+    Returns the filename on success or None on failure (a debug dump must never break the flow).
+    """
+    filename = f"_{action}-{datetime.now().strftime('%Y%m%d%H%M%S%f')}.json"
+
+    payload = {
+        "datetime": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
+        "action": action,
+        "provider": provider,
+        "model": api_model,
+        "system_instruction": system_instruction,
+        "system_instruction_chars": len(system_instruction) if system_instruction else 0,
+    }
+
+    if chat_history is not None:
+        payload["chat_history"] = chat_history
+        payload["new_message"] = new_message
+        payload["chat_history_chars"] = len(json.dumps(chat_history, ensure_ascii=False)) if chat_history else 0
+        payload["new_message_chars"] = len(new_message) if new_message else 0
+        payload["total_chars"] = payload["system_instruction_chars"] + payload["chat_history_chars"] + payload["new_message_chars"]
+    else:
+        payload["prompt"] = prompt
+        payload["prompt_chars"] = len(prompt) if prompt else 0
+        payload["total_chars"] = payload["system_instruction_chars"] + payload["prompt_chars"]
+
+    try:
+        with open(filename, "w", encoding="utf-8") as f:
+            json.dump(payload, f, ensure_ascii=False, indent=2)
+        return filename
+    except Exception:
+        return None
+
+
+def call_ai_model(provider, api_key, api_model, prompt, system_instruction, quiet=False, action="ai_call"):
     """
     Unified engine for AI calls.
     Supports 'gemini' and 'deepseek'.
     """
     max_retries = 3
     retry_delay = 2
+
+    if PRE_SAVE_ENABLED:
+        saved_file = _save_pre_save_payload(action, provider, api_model, system_instruction, prompt=prompt)
+        if saved_file and not quiet:
+            click.secho(__("📝 Pre-save: AI payload saved to {filename}", filename=saved_file), fg="yellow", dim=True)
+
     spinner = Spinner(quiet=quiet)
     spinner.start()
 
@@ -141,6 +194,11 @@ def call_ai_chat(provider, api_key, api_model, system_instruction, chat_history,
     Dedicated engine for the Interactive Chat.
     Keeps the historical context and returns free Markdown (does not force JSON).
     """
+    if PRE_SAVE_ENABLED:
+        saved_file = _save_pre_save_payload("chat", provider, api_model, system_instruction, chat_history=chat_history, new_message=new_message)
+        if saved_file and not quiet:
+            click.secho(__("📝 Pre-save: AI payload saved to {filename}", filename=saved_file), fg="yellow", dim=True)
+
     spinner = Spinner(quiet=quiet)
     spinner.start()
 

src/blame_engine.py

@@ -83,7 +83,7 @@ def analyze_commit_with_ai(commit_hash, file_path):
 
     click.secho(__("  🤖 Consulting AI ({api_model}) about commit {commit_hash}...", api_model=api_model, commit_hash=commit_hash[:8]), fg="cyan", dim=True)
 
-    result_json = call_ai_model(provider, api_key, api_model, prompt, sys_inst)
+    result_json = call_ai_model(provider, api_key, api_model, prompt, sys_inst, action="blame")
 
     if result_json and "status" in result_json:
         return result_json
@@ -210,7 +210,7 @@ def run_blame_analysis(file_path, start_line, end_line, return_data=False):
     sys_inst = __('You are a Software Architect. Generate ONLY a JSON object in the format {"resumo": "summary text"}.')
 
     click.secho(__("  🤖 Consulting AI ({api_model}) for the Executive Summary...", api_model=api_model), fg="cyan", dim=True)
-    summary_json = call_ai_model(provider, api_key, api_model, summary_prompt, sys_inst)
+    summary_json = call_ai_model(provider, api_key, api_model, summary_prompt, sys_inst, action="blame_summary")
 
     resumo_texto = summary_json.get("resumo", __("Summary not available.")) if summary_json else __("Summary not available.")
 

src/core.py

@@ -2,42 +2,114 @@ import os
 import re
 import json
 import stat
+import time
 import click
 import subprocess
 import urllib.request
 import urllib.error
+from pathlib import Path
 from google import genai
+from dotenv import load_dotenv, set_key
 from src.security import decrypt_data
 from src.cache import get_cached_response, save_cached_response, get_cached_pr_descriptions
-from src.config import get_api_key, get_api_model, get_skill_dir, resolve_skill_path
+from src.config import get_api_key, get_api_model, get_skill_dir, resolve_skill_path, get_ai_provider, setup_environment
 from src.ai_providers import call_ai_model
 from src.i18n import __, CURRENT_LANG
-
-# Filtro Smart Diff: ficheiros que gastam tokens da IA sem acrescentar valor semântico
-SMART_EXCLUDES = [
-    ":(exclude)*.lock",
-    ":(exclude)package-lock.json",
-    ":(exclude)yarn.lock",
-    ":(exclude)pnpm-lock.yaml",
-    ":(exclude)composer.lock",
-    ":(exclude)poetry.lock",
-    ":(exclude)Pipfile.lock",
-    ":(exclude)Gemfile.lock",
-    ":(exclude)go.sum",
-    ":(exclude)*.min.js",
-    ":(exclude)*.min.css",
-    ":(exclude)*.svg"
+from src.updater import __lang_version__
+
+# Smart Diff filter: files that consume AI tokens without adding semantic value.
+# The pattern list is managed remotely (templates/gitpr.smart-excludes.json) and
+# cached at ~/.gitpr/conf/ — see _load_smart_excludes() for the update logic.
+_FALLBACK_SMART_EXCLUDES = [
+    "*.lock",
+    "package-lock.json",
+    "yarn.lock",
+    "pnpm-lock.yaml",
+    "composer.lock",
+    "poetry.lock",
+    "Pipfile.lock",
+    "Gemfile.lock",
+    "go.sum",
+    "*.min.js",
+    "*.min.css",
+    "*.svg"
 ]
 
+SMART_EXCLUDES_URL = "https://raw.githubusercontent.com/natanfiuza/gitpr/main/templates/gitpr.smart-excludes.json"
+
+
+def _load_smart_excludes():
+    """
+    Load the smart-exclude patterns and return them as git pathspec exclusions.
+
+    Resolution order:
+    1. Local copy at ~/.gitpr/conf/gitpr.smart-excludes.json when its version
+       marker (SMART_EXCLUDES_VERSION in ~/.gitpr/.env) matches __lang_version__.
+    2. Fresh download from the remote template (saved locally + marker updated).
+    3. Stale local copy when the download fails.
+    4. _FALLBACK_SMART_EXCLUDES as last resort.
+    Silent on failure — diff generation must never break because of this list.
+    """
+    env_file = Path.home() / ".gitpr" / ".env"
+    load_dotenv(env_file)
+
+    conf_dir = Path.home() / ".gitpr" / "conf"
+    local_file = conf_dir / "gitpr.smart-excludes.json"
+    needs_update = os.getenv("SMART_EXCLUDES_VERSION") != __lang_version__
+
+    def _to_pathspecs(data):
+        return [f":(exclude){pattern}" for pattern in data.get("excludes", [])]
+
+    # 1. Local copy is present and up to date
+    if local_file.exists() and not needs_update:
+        try:
+            with open(local_file, "r", encoding="utf-8", errors="replace") as f:
+                return _to_pathspecs(json.load(f))
+        except Exception:
+            pass
+
+    # 2. Download the updated list from the remote template
+    try:
+        with urllib.request.urlopen(SMART_EXCLUDES_URL, timeout=3) as response:
+            data = json.loads(response.read().decode("utf-8"))
+        conf_dir.mkdir(parents=True, exist_ok=True)
+        with open(local_file, "w", encoding="utf-8") as f:
+            json.dump(data, f, ensure_ascii=False, indent=2)
+        set_key(str(env_file), "SMART_EXCLUDES_VERSION", __lang_version__)
+        return _to_pathspecs(data)
+    except Exception:
+        pass
+
+    # 3. Offline fallback: reuse the local copy even if outdated
+    if local_file.exists():
+        try:
+            with open(local_file, "r", encoding="utf-8", errors="replace") as f:
+                return _to_pathspecs(json.load(f))
+        except Exception:
+            pass
+
+    # 4. Last resort: built-in defaults
+    return [f":(exclude){pattern}" for pattern in _FALLBACK_SMART_EXCLUDES]
+
+
+SMART_EXCLUDES = _load_smart_excludes()
+
 
 def get_doc_url(filename):
-    """Returns the complete URL for a docs/ file, with language suffix if needed."""
-    # e.g.: get_doc_url("untracked-files.md") -> ".../docs/untracked-files.md" (EN) or ".../docs/untracked-files.pt_br.md" (PT)
-    if CURRENT_LANG.startswith("en"):
-        return f"https://github.com/natanfiuza/gitpr/blob/main/docs/{filename}"
-    else:
-        base, ext = filename.rsplit(".", 1)
-        return f"https://github.com/natanfiuza/gitpr/blob/main/docs/{base}.{CURRENT_LANG}.{ext}"
+    """Returns the complete URL for the official GitPR documentation website.
+
+    Transforms a docs/ filename like 'commit-message-ia.md' into a clean website
+    URL with language query parameter. English is the site default (no ?lang=).
+
+    Examples:
+        get_doc_url("untracked-files.md")  -> "https://gitpr.natanfiuza.dev.br/docs/untracked-files"
+        get_doc_url("untracked-files.md")  -> "https://gitpr.natanfiuza.dev.br/docs/untracked-files?lang=pt_br"  (when CURRENT_LANG is pt_br)
+    """
+    base, _ = filename.rsplit(".", 1)
+    url = f"https://gitpr.natanfiuza.dev.br/docs/{base}"
+    if not CURRENT_LANG.startswith("en"):
+        url += f"?lang={CURRENT_LANG}"
+    return url
 
 
 def get_git_diff(quiet=False):
@@ -62,7 +134,7 @@ def get_git_diff(quiet=False):
             click.secho(f"📚 {__('Understand why:')} {get_doc_url('untracked-files.md')}\n", fg="blue", underline=True)
 
         # Run the normal diff that captures tracked and staged files
-        cmd = ["git", "diff", "HEAD", "--"] + SMART_EXCLUDES
+        cmd = ["git", "diff", "-U1", "-w", "-M", "-B", "HEAD", "--"] + SMART_EXCLUDES
         result = subprocess.run(
             cmd,
             capture_output=True,
@@ -153,6 +225,35 @@ def get_skill_context(action_type="pr"):
     # Return empty if it does not exist
     return ""
 
+def estimate_token_count(text):
+    """Estimates the token count using the safe rule of 4 characters per token."""
+    return len(text) // 4
+
+def split_diff_into_chunks(diff_text, max_tokens=90000):
+    """Splits the diff based on the token limit while preserving file header integrity."""
+    if estimate_token_count(diff_text) <= max_tokens:
+        return [diff_text]
+    
+    parts = re.split(r'(^diff --git a/)', diff_text, flags=re.MULTILINE)
+    chunks = []
+    current_chunk = ""
+    
+    for i in range(1, len(parts), 2):
+        file_diff = parts[i] + parts[i+1] if i + 1 < len(parts) else parts[i]
+        
+        if estimate_token_count(current_chunk + file_diff) > max_tokens and current_chunk:
+            chunks.append(current_chunk)
+            current_chunk = file_diff
+        else:
+            current_chunk += file_diff
+            
+    if current_chunk:
+        chunks.append(current_chunk)
+        
+    if not chunks:
+        chunks = [diff_text]
+        
+    return chunks
 
 def generate_pr_content(action_folder, action_type, diff_text, provider="gemini"):
     """Sends the diff to the AI using System Instruction and returns a parsed JSON."""
@@ -212,10 +313,46 @@ def generate_pr_content(action_folder, action_type, diff_text, provider="gemini"
         click.secho(__("❌ Error: Could not determine model for provider '{provider}'.", provider=provider), fg="red")
         return None
 
+    # API CALL
     # API CALL
     click.secho(__("🤖 GitPR is analyzing your code using {provider} ({model})...\n", provider=provider.capitalize(), model=api_model), fg="cyan")
     
-    result_json = call_ai_model(provider, api_key, api_model, prompt, instrucao_sistema)
+    chunks = split_diff_into_chunks(diff_text, max_tokens=90000)
+    
+    if len(chunks) == 1:
+        result_json = call_ai_model(provider, api_key, api_model, prompt, instrucao_sistema, action=action_folder)
+    else:
+        click.secho(__("📦 Huge diff detected! Processing in {count} batches (Map-Reduce)...", count=len(chunks)), fg="yellow", bold=True)
+        click.secho(f"📚 {__('Understand why:')} {get_doc_url('map-reduce-diff.md')}\n", fg="blue", underline=True)
+        resumos_parciais = []
+
+        for i, chunk in enumerate(chunks, 1):
+            click.secho(__("⏳ Analyzing batch {current}/{total}...", current=i, total=len(chunks)), fg="cyan", dim=True)
+
+            prompt_parcial = __("Generate ONLY a JSON object in the format {json_format} containing a technical summary of what was changed in this part ({idx}) of the diff:\n", json_format='{"resumo": "..."}', idx=i) + chunk
+
+            resposta_parcial = call_ai_model(provider, api_key, api_model, prompt_parcial, instrucao_sistema, quiet=True, action=f"{action_folder}_chunk_{i}")
+
+            if resposta_parcial and "resumo" in resposta_parcial:
+                resumos_parciais.append(f"### Batch {i}\n{resposta_parcial['resumo']}")
+            
+            time.sleep(1)
+            
+        if not resumos_parciais:
+            click.secho(__("❌ Failed to extract context from the partial batches."), fg="red")
+            return None
+
+        click.secho(__("🔄 Unifying intelligence and generating the final analysis..."), fg="yellow")
+        diff_unificado = "\n\n".join(resumos_parciais)
+
+        if action_type == "commit":
+            prompt = __("Generate ONLY a JSON object in the format {json_format} for the commit message, unifying these technical summaries:\n", json_format='{"commit_message": "..."}') + diff_unificado
+        elif action_type in ["review", "fullreview", "filereview"]:
+            prompt = __("Generate ONLY a JSON object in the format {json_format} with a code review focused on improvements, using these summaries:\n", json_format='{"review": "..."}') + diff_unificado
+        else:
+            prompt = __("Unify these technical summaries and generate ONLY a JSON object in the format {json_format} describing the Pull Request:\n", json_format='{"commit_message": "...", "pr_description": "..."}') + diff_unificado
+            
+        result_json = call_ai_model(provider, api_key, api_model, prompt, instrucao_sistema, action=action_folder)
 
     # SAVE TO CACHE AND RETURN
     if result_json:
@@ -325,7 +462,7 @@ def get_git_full_diff():
 
         # Diff between that HASH and your CURRENT WORKSPACE (without using HEAD)
         # By passing only the hash, Git compares that commit with the files on your disk.
-        cmd = ["git", "diff", ancestor_hash, "--"] + SMART_EXCLUDES
+        cmd = ["git", "diff", "-U1", "-w", "-M", "-B", ancestor_hash, "--"] + SMART_EXCLUDES
         result = subprocess.run(
             cmd, 
             capture_output=True, 
@@ -379,6 +516,82 @@ def install_git_hooks():
 
     return success_count == len(hooks_to_install)
 
+
+def run_install_wizard():
+    """
+    Interactive setup wizard combining --skill, --installhooks, MCP install, and API key check.
+
+    Asks for confirmation before each step and prints a documentation URL at the end.
+    """
+    click.secho(__("\n🔧 Starting GitPR Interactive Setup Wizard..."), fg="cyan", bold=True)
+    click.echo(__("This wizard will guide you through the essential GitPR setup steps.\n"))
+
+    # ------------------------------------------------------------------
+    # Step 1: Skill Templates (equivalent to --skill)
+    # ------------------------------------------------------------------
+    click.secho(__("Step 1 of 4: Skill Templates"), fg="yellow", bold=True)
+    click.echo(__("Downloads template files (.gitpr.*.md, .gitpr.linter.yml) into the .gitpr/skill/ folder."))
+    click.echo(__("These files allow customizing AI behavior for your team's conventions."))
+    if click.confirm(__("Proceed with downloading skill templates?"), default=True):
+        generate_skill_template()
+    else:
+        click.echo(__("Skipped.\n"))
+
+    # ------------------------------------------------------------------
+    # Step 2: Git Hooks (equivalent to --installhooks)
+    # ------------------------------------------------------------------
+    click.secho(__("\nStep 2 of 4: Git Hooks"), fg="yellow", bold=True)
+    click.echo(__("Installs pre-commit (static linter) and prepare-commit-msg (AI commit messages) hooks."))
+    click.echo(__("This enables automatic validation and AI assistance before every commit."))
+    if click.confirm(__("Proceed with installing Git hooks?"), default=True):
+        if install_git_hooks():
+            click.secho(__("✅ Git Hooks successfully installed!"), fg="green", bold=True)
+        else:
+            click.secho(__("⚠️ Some hooks could not be installed."), fg="yellow")
+    else:
+        click.echo(__("Skipped.\n"))
+
+    # ------------------------------------------------------------------
+    # Step 3: MCP Configuration (equivalent to gitpr-mcp --install auto)
+    # ------------------------------------------------------------------
+    click.secho(__("\nStep 3 of 4: MCP Configuration"), fg="yellow", bold=True)
+    click.echo(__("Auto-detects and configures GitPR for VS Code, Cursor, Claude Desktop, and Zed."))
+    click.echo(__("This lets AI-powered editors use GitPR tools directly without the terminal."))
+    if click.confirm(__("Proceed with MCP configuration?"), default=True):
+        # Lazy import to avoid circular dependency at module level
+        from src.mcp_server import _run_install
+        _run_install("auto")
+    else:
+        click.echo(__("Skipped.\n"))
+
+    # ------------------------------------------------------------------
+    # Step 4: API Key Check
+    # ------------------------------------------------------------------
+    click.secho(__("\nStep 4 of 4: API Key Configuration"), fg="yellow", bold=True)
+    provider = get_ai_provider()
+    existing_key = get_api_key(provider)
+    if existing_key:
+        click.secho(
+            __("✅ API key for {provider} is already configured.", provider=provider.capitalize()),
+            fg="green",
+        )
+    else:
+        click.echo(__("No API key found for {provider}.", provider=provider.capitalize()))
+        if click.confirm(__("Would you like to configure it now?"), default=True):
+            setup_environment()
+        else:
+            click.echo(__("You can configure it later by running 'gitpr' or editing ~/.gitpr/.env manually."))
+
+    # ------------------------------------------------------------------
+    # Final: documentation URL
+    # ------------------------------------------------------------------
+    click.echo("")
+    click.secho(__("\n✅ Setup wizard complete!"), fg="green", bold=True)
+    click.echo(__("For more details, see the full documentation:"))
+    click.secho(f"  {get_doc_url('install-wizard.md')}", fg="blue", underline=True)
+    click.echo("")
+
+
 def get_branch_history_text():
     """Compiles the Git Log and PR Cache of the current branch to generate the epic context."""
     branch = get_current_branch()

src/issue_engine.py

@@ -78,7 +78,7 @@ def generate_issue_content(context_text, context_type="diff"):
 
     click.secho(__("🤖 Structuring Issue using {provider} ({api_model})...", provider=provider.capitalize(), api_model=api_model), fg="cyan", dim=True)
 
-    result_json = call_ai_model(provider, api_key, api_model, prompt, sys_inst)
+    result_json = call_ai_model(provider, api_key, api_model, prompt, sys_inst, action="issue")
 
     if result_json and "titulo" in result_json and "corpo" in result_json:
         # Save to Cache