gitpr-cli 0.0.29__tar.gz → 0.0.31__tar.gz

{gitpr_cli-0.0.29 → gitpr_cli-0.0.31}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: gitpr-cli
-Version: 0.0.29
-Summary: Automação de PRs, Commits e Code Review com IA (Gemini e DeepSeek)
+Version: 0.0.31
+Summary: AI-powered PR automation, commit messages, and code review (Gemini, DeepSeek, and Ollama)
 Author-email: Natan Fiuza <contato@natanfiuza.dev.br>
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
@@ -28,6 +28,29 @@ GitPR CLI is a command-line automation tool that uses **Google Gemini** and **De
 
 🌐 **Website:** [gitpr.natanfiuza.dev.br](https://gitpr.natanfiuza.dev.br/) · 📂 **Repository:** [github.com/natanfiuza/gitpr](https://github.com/natanfiuza/gitpr)
 
+----
+
+## ⚡ **Quick Start**
+
+### **1. Installation via PyPI**
+
+Install GitPR CLI using `pip`:
+
+```bash
+pip install gitpr-cli
+```
+
+### **2. Initializing in a Repository**
+
+To set up GitPR in a folder of a new repository, run:
+
+```bash
+gitpr --install
+```
+
+> **Guided Setup:** Guided configuration that downloads skill templates, installs Git Hooks, configures MCP for your editors, and verifies the API key for your AI provider.  
+> 📖 **Full Documentation:** [https://gitpr.natanfiuza.dev.br/docs/install-wizard?lang=en_us](https://gitpr.natanfiuza.dev.br/docs/install-wizard?lang=en_us)
+
 ## **🛠️ Technologies and Libraries Used**
 
 This project was developed in Python and uses the following main libraries:
@@ -311,6 +334,7 @@ If you want to implement GitPR as an automated quality barrier in your team, che
 * [**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.
 * [**MCP Prompts**](https://github.com/natanfiuza/gitpr/blob/main/docs/mcp-prompts.md) — Pre-built message templates (7 prompts, 35 language variants) for common GitPR workflows in your editor's AI chat.
 * [**MCP Tool Annotations**](https://github.com/natanfiuza/gitpr/blob/main/docs/mcp-annotations.md) — IDE integration hints (`readOnlyHint`, `destructiveHint`) for smarter UI behavior and safer tool execution.
+* [**Metrics & Telemetry**](https://github.com/natanfiuza/gitpr/blob/main/docs/metricas-telemetria.md) — Local offline analytics for team usage metrics, exportable CSV reports, and interactive TUI dashboard.
 
 ## ⚡ Local Cache System (Quota Savings)
 

{gitpr_cli-0.0.29 → gitpr_cli-0.0.31}/README.md

@@ -9,6 +9,29 @@ GitPR CLI is a command-line automation tool that uses **Google Gemini** and **De
 
 🌐 **Website:** [gitpr.natanfiuza.dev.br](https://gitpr.natanfiuza.dev.br/) · 📂 **Repository:** [github.com/natanfiuza/gitpr](https://github.com/natanfiuza/gitpr)
 
+----
+
+## ⚡ **Quick Start**
+
+### **1. Installation via PyPI**
+
+Install GitPR CLI using `pip`:
+
+```bash
+pip install gitpr-cli
+```
+
+### **2. Initializing in a Repository**
+
+To set up GitPR in a folder of a new repository, run:
+
+```bash
+gitpr --install
+```
+
+> **Guided Setup:** Guided configuration that downloads skill templates, installs Git Hooks, configures MCP for your editors, and verifies the API key for your AI provider.  
+> 📖 **Full Documentation:** [https://gitpr.natanfiuza.dev.br/docs/install-wizard?lang=en_us](https://gitpr.natanfiuza.dev.br/docs/install-wizard?lang=en_us)
+
 ## **🛠️ Technologies and Libraries Used**
 
 This project was developed in Python and uses the following main libraries:
@@ -292,6 +315,7 @@ If you want to implement GitPR as an automated quality barrier in your team, che
 * [**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.
 * [**MCP Prompts**](https://github.com/natanfiuza/gitpr/blob/main/docs/mcp-prompts.md) — Pre-built message templates (7 prompts, 35 language variants) for common GitPR workflows in your editor's AI chat.
 * [**MCP Tool Annotations**](https://github.com/natanfiuza/gitpr/blob/main/docs/mcp-annotations.md) — IDE integration hints (`readOnlyHint`, `destructiveHint`) for smarter UI behavior and safer tool execution.
+* [**Metrics & Telemetry**](https://github.com/natanfiuza/gitpr/blob/main/docs/metricas-telemetria.md) — Local offline analytics for team usage metrics, exportable CSV reports, and interactive TUI dashboard.
 
 ## ⚡ Local Cache System (Quota Savings)
 

{gitpr_cli-0.0.29 → gitpr_cli-0.0.31}/gitpr_cli.egg-info/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: gitpr-cli
-Version: 0.0.29
-Summary: Automação de PRs, Commits e Code Review com IA (Gemini e DeepSeek)
+Version: 0.0.31
+Summary: AI-powered PR automation, commit messages, and code review (Gemini, DeepSeek, and Ollama)
 Author-email: Natan Fiuza <contato@natanfiuza.dev.br>
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
@@ -28,6 +28,29 @@ GitPR CLI is a command-line automation tool that uses **Google Gemini** and **De
 
 🌐 **Website:** [gitpr.natanfiuza.dev.br](https://gitpr.natanfiuza.dev.br/) · 📂 **Repository:** [github.com/natanfiuza/gitpr](https://github.com/natanfiuza/gitpr)
 
+----
+
+## ⚡ **Quick Start**
+
+### **1. Installation via PyPI**
+
+Install GitPR CLI using `pip`:
+
+```bash
+pip install gitpr-cli
+```
+
+### **2. Initializing in a Repository**
+
+To set up GitPR in a folder of a new repository, run:
+
+```bash
+gitpr --install
+```
+
+> **Guided Setup:** Guided configuration that downloads skill templates, installs Git Hooks, configures MCP for your editors, and verifies the API key for your AI provider.  
+> 📖 **Full Documentation:** [https://gitpr.natanfiuza.dev.br/docs/install-wizard?lang=en_us](https://gitpr.natanfiuza.dev.br/docs/install-wizard?lang=en_us)
+
 ## **🛠️ Technologies and Libraries Used**
 
 This project was developed in Python and uses the following main libraries:
@@ -311,6 +334,7 @@ If you want to implement GitPR as an automated quality barrier in your team, che
 * [**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.
 * [**MCP Prompts**](https://github.com/natanfiuza/gitpr/blob/main/docs/mcp-prompts.md) — Pre-built message templates (7 prompts, 35 language variants) for common GitPR workflows in your editor's AI chat.
 * [**MCP Tool Annotations**](https://github.com/natanfiuza/gitpr/blob/main/docs/mcp-annotations.md) — IDE integration hints (`readOnlyHint`, `destructiveHint`) for smarter UI behavior and safer tool execution.
+* [**Metrics & Telemetry**](https://github.com/natanfiuza/gitpr/blob/main/docs/metricas-telemetria.md) — Local offline analytics for team usage metrics, exportable CSV reports, and interactive TUI dashboard.
 
 ## ⚡ Local Cache System (Quota Savings)
 

{gitpr_cli-0.0.29 → gitpr_cli-0.0.31}/gitpr_cli.egg-info/SOURCES.txt

@@ -19,6 +19,7 @@ src/issue_engine.py
 src/linter_engine.py
 src/main.py
 src/mcp_server.py
+src/metrics.py
 src/security.py
 src/spinner.py
 src/tui_issue.py
@@ -27,11 +28,13 @@ src/ui/__init__.py
 src/ui/chat_app.py
 src/ui/help_screen.py
 src/ui/issue_app.py
+src/ui/metrics_app.py
 tests/test_chat_backend.py
 tests/test_core.py
 tests/test_install_wizard.py
 tests/test_mcp_prompts.py
 tests/test_mcp_server.py
+tests/test_metrics.py
 tests/test_pre_save.py
 tests/test_skill_command.py
 tests/test_smart_excludes.py

{gitpr_cli-0.0.29 → gitpr_cli-0.0.31}/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "gitpr-cli"
-version = "0.0.29"
-description = "Automação de PRs, Commits e Code Review com IA (Gemini e DeepSeek)"
+version = "0.0.31"
+description = "AI-powered PR automation, commit messages, and code review (Gemini, DeepSeek, and Ollama)"
 readme = "README.md"
 requires-python = ">=3.10"
 authors = [

{gitpr_cli-0.0.29 → gitpr_cli-0.0.31}/src/ai_providers.py

@@ -73,9 +73,12 @@ def call_ai_model(provider, api_key, api_model, prompt, system_instruction, quie
     spinner = Spinner(quiet=quiet)
     spinner.start()
 
+    start_time = time.perf_counter()
+
     try:
         for attempt in range(1, max_retries + 1):
             try:
+                meta_raw = {}
                 if provider == "gemini":
                     client = genai.Client(api_key=api_key)
                     response = client.models.generate_content(
@@ -90,6 +93,13 @@ def call_ai_model(provider, api_key, api_model, prompt, system_instruction, quie
                         }
                     )
                     result_text = response.text
+                    
+                    if hasattr(response, 'usage_metadata') and response.usage_metadata:
+                        meta_raw = {
+                            "prompt_tokens": getattr(response.usage_metadata, 'prompt_token_count', 0),
+                            "completion_tokens": getattr(response.usage_metadata, 'candidates_token_count', 0),
+                            "total_tokens": getattr(response.usage_metadata, 'total_token_count', 0)
+                        }
 
                 elif provider in ["deepseek", "ollama"]:
                     # DeepSeek and Ollama are 100% compatible with the OpenAI library.
@@ -106,6 +116,13 @@ def call_ai_model(provider, api_key, api_model, prompt, system_instruction, quie
                         temperature=0.0
                     )
                     result_text = response.choices[0].message.content
+                    
+                    if hasattr(response, 'usage') and response.usage:
+                        meta_raw = {
+                            "prompt_tokens": getattr(response.usage, 'prompt_tokens', 0),
+                            "completion_tokens": getattr(response.usage, 'completion_tokens', 0),
+                            "total_tokens": getattr(response.usage, 'total_tokens', 0)
+                        }
 
                 else:
                     spinner.stop()
@@ -119,6 +136,12 @@ def call_ai_model(provider, api_key, api_model, prompt, system_instruction, quie
                 if isinstance(result_json, list):
                     result_json = result_json[0] if result_json else {}
 
+                # Inject telemetry metadata silently into the response dictionary
+                meta_raw["duration_ms"] = int((time.perf_counter() - start_time) * 1000)
+                meta_raw["provider"] = provider
+                meta_raw["model"] = api_model
+                result_json["_telemetry_meta"] = meta_raw
+
                 spinner.stop()
                 return result_json
 

{gitpr_cli-0.0.29 → gitpr_cli-0.0.31}/src/cache.py

@@ -1,6 +1,7 @@
 import os
 import json
 import hashlib
+import subprocess
 from datetime import datetime
 from pathlib import Path
 
@@ -13,6 +14,15 @@ def generate_md5(text):
     """Generates the MD5 hash of a string."""
     return hashlib.md5(text.encode('utf-8')).hexdigest()
 
+def get_git_user_info():
+    """Recupera o nome e email configurados no git local."""
+    try:
+        name = subprocess.run(["git", "config", "user.name"], capture_output=True, text=True, check=True).stdout.strip()
+        email = subprocess.run(["git", "config", "user.email"], capture_output=True, text=True, check=True).stdout.strip()
+        return name, email
+    except subprocess.CalledProcessError:
+        return "unknown", "unknown"
+    
 def get_cached_response(action_folder, prompt_text):
     """Checks if a valid cache exists for the prompt and returns the content."""
     md5_hash = generate_md5(prompt_text)
@@ -27,7 +37,7 @@ def get_cached_response(action_folder, prompt_text):
             return None
     return None
 
-def save_cached_response(action_folder, action_type, prompt_text, response_dict):
+def save_cached_response(action_folder, action_type, prompt_text, response_dict, meta_raw=None):
     """Saves the AI response to the local cache."""
     md5_hash = generate_md5(prompt_text)
     folder_path = get_cache_base_dir() / action_folder
@@ -37,11 +47,17 @@ def save_cached_response(action_folder, action_type, prompt_text, response_dict)
     from src.core import get_current_branch, get_repo_name
     current_branch = get_current_branch()
     repo_name = get_repo_name()
+    user_name, user_email = get_git_user_info()
+
+    if meta_raw is not None:
+        response_dict["meta_raw"] = meta_raw
 
     cache_data = {
         "md5": md5_hash,
         "repo": repo_name,
         "branch": current_branch,
+        "author_name": user_name,
+        "author_email": user_email,
         "datetime": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
         "action_type": action_type,
         "prompt": prompt_text,

{gitpr_cli-0.0.29 → gitpr_cli-0.0.31}/src/config.py

@@ -211,7 +211,35 @@ def get_github_token():
     """Reads and decrypts the GitHub Personal Access Token (PAT)."""
     load_dotenv(ENV_FILE)
     encrypted_token = os.getenv("GITHUB_TOKEN_ENCRYPTED")
-    
+
     if encrypted_token:
         return decrypt_data(encrypted_token)
-    return None
+    return None
+
+
+def validate_github_token(token):
+    """
+    Validates a GitHub PAT by making a lightweight API call to /user.
+    Returns (is_valid: bool, error_message: str).
+    """
+    import requests
+
+    try:
+        headers = {
+            "Authorization": f"token {token}",
+            "Accept": "application/vnd.github.v3+json"
+        }
+        response = requests.get("https://api.github.com/user", headers=headers, timeout=10)
+
+        if response.status_code == 200:
+            return True, ""
+        elif response.status_code == 401:
+            return False, __("Token expired or invalid. Please generate a new one.")
+        else:
+            return False, __("Unexpected response from GitHub (HTTP {code})", code=response.status_code)
+    except requests.exceptions.ConnectionError:
+        return False, __("No internet connection. Cannot validate GitHub token.")
+    except requests.exceptions.Timeout:
+        return False, __("GitHub API timeout. Check your connection and try again.")
+    except Exception as e:
+        return False, __("Failed to validate token: {error}", error=str(e))

{gitpr_cli-0.0.29 → gitpr_cli-0.0.31}/src/core.py

@@ -16,6 +16,7 @@ from src.config import get_api_key, get_api_model, get_skill_dir, resolve_skill_
 from src.ai_providers import call_ai_model
 from src.i18n import __, CURRENT_LANG
 from src.updater import __lang_version__
+# Metrics are imported lazily inside generate_pr_content() to avoid circular imports
 
 # Smart Diff filter: files that consume AI tokens without adding semantic value.
 # The pattern list is managed remotely (templates/gitpr.smart-excludes.json) and
@@ -261,6 +262,8 @@ def generate_pr_content(action_folder, action_type, diff_text, provider="gemini"
         click.secho(__("⚠️ No diff found. Make some changes before running the command."), fg="yellow")
         return None
 
+    t_start = time.perf_counter()
+
     # Cache folder configuration
     action_folder_map = {
         "pr": "pr_desc",
@@ -298,6 +301,15 @@ def generate_pr_content(action_folder, action_type, diff_text, provider="gemini"
     cached_data = get_cached_response(action_folder, prompt)
     if cached_data:
         click.secho(__("⚡ Response retrieved from local cache."), fg="green", dim=True)
+        from src.metrics import log_command_metric
+        duration_ms = int((time.perf_counter() - t_start) * 1000)
+        log_command_metric(
+            command=action_type,
+            status="success",
+            provider=provider,
+            duration_ms=duration_ms,
+            cache_hit=True,
+        )
         return cached_data
 
     # Key Preparation (Now dynamic per Provider)
@@ -313,15 +325,27 @@ 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")
     
     chunks = split_diff_into_chunks(diff_text, max_tokens=90000)
-    
+    total_meta = {"prompt_tokens": 0, "completion_tokens": 0, "total_tokens": 0, "duration_ms": 0}
+
+    def _aggregate_meta(new_meta):
+        if new_meta:
+            total_meta["prompt_tokens"] += new_meta.get("prompt_tokens", 0)
+            total_meta["completion_tokens"] += new_meta.get("completion_tokens", 0)
+            total_meta["total_tokens"] += new_meta.get("total_tokens", 0)
+            total_meta["duration_ms"] += new_meta.get("duration_ms", 0)
+            
     if len(chunks) == 1:
         result_json = call_ai_model(provider, api_key, api_model, prompt, instrucao_sistema, action=action_folder)
+        if result_json:
+            _aggregate_meta(result_json.pop("_telemetry_meta", None))
     else:
+        from src.metrics import log_local_metric
+        log_local_metric(command="map_reduce", status="triggered", map_reduce_triggered=True, chunks_count=len(chunks))
+        
         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 = []
@@ -332,9 +356,11 @@ def generate_pr_content(action_folder, action_type, diff_text, provider="gemini"
             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']}")
+            
+            if resposta_parcial:
+                _aggregate_meta(resposta_parcial.pop("_telemetry_meta", None))
+                if "resumo" in resposta_parcial:
+                    resumos_parciais.append(f"### Batch {i}\n{resposta_parcial['resumo']}")
             
             time.sleep(1)
             
@@ -353,12 +379,29 @@ def generate_pr_content(action_folder, action_type, diff_text, provider="gemini"
             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)
+        if result_json:
+            _aggregate_meta(result_json.pop("_telemetry_meta", None))
 
     # SAVE TO CACHE AND RETURN
     if result_json:
-        save_cached_response(action_folder, action_type, prompt, result_json)
+        save_cached_response(action_folder, action_type, prompt, result_json, meta_raw=total_meta)
+        # Fire-and-forget metric for successful AI-powered command
+        from src.metrics import log_command_metric
+        duration_ms = int((time.perf_counter() - t_start) * 1000)
+        log_command_metric(
+            command=action_type,
+            status="success",
+            provider=provider,
+            tokens_estimated=total_meta.get("total_tokens", 0),
+            duration_ms=duration_ms,
+            map_reduce_triggered=(len(chunks) > 1),
+        )
         return result_json
-    
+
+    # Command failed (AI returned None)
+    from src.metrics import log_command_metric
+    duration_ms = int((time.perf_counter() - t_start) * 1000)
+    log_command_metric(command=action_type, status="error", provider=provider, duration_ms=duration_ms)
     return None
 
 
@@ -487,7 +530,10 @@ def install_git_hooks():
     # Mapping: Hook Name in Git -> Template Name on your GitHub
     hooks_to_install = {
         "pre-commit": "pre-commit-template.sh",
-        "prepare-commit-msg": "prepare-commit-msg-template.sh"
+        "prepare-commit-msg": "prepare-commit-msg-template.sh",
+        "post-checkout": "post-checkout-template.sh",
+        "pre-push": "pre-push-template.sh",
+        "post-merge": "post-merge-template.sh",
     }
 
     base_url = "https://raw.githubusercontent.com/natanfiuza/gitpr/main/scripts/"

{gitpr_cli-0.0.29 → gitpr_cli-0.0.31}/src/issue_engine.py

@@ -1,6 +1,7 @@
 import subprocess
 import re
 import os
+import time
 import click
 from src.ai_providers import call_ai_model
 from src.cache import get_cached_response, save_cached_response
@@ -32,14 +33,20 @@ def get_github_repo_info():
 
 def generate_issue_content(context_text, context_type="diff"):
     """Sends the context (diff, blame, or history) to the AI and returns an issue dictionary."""
+    from src.metrics import log_command_metric
+
     if not context_text or not str(context_text).strip():
         return None
 
+    t_start = time.perf_counter()
+
     provider = get_ai_provider()
     api_key = get_api_key(provider)
 
     if not api_key:
         click.secho(__("❌ Error: API Key not found."), fg="red")
+        duration_ms = int((time.perf_counter() - t_start) * 1000)
+        log_command_metric(command="issue", status="error", provider=provider, duration_ms=duration_ms)
         return None
 
     # Use the advanced model to ensure Issue structure quality
@@ -69,11 +76,13 @@ def generate_issue_content(context_text, context_type="diff"):
         __("Generate the requested JSON object following the system instructions to {target_action}\n\n", target_action=target_action) +
         f"{data_label}\n{context_text}"
     )
-    
+
     # Try to retrieve from Cache
     cached_data = get_cached_response("issue", prompt)
     if cached_data:
         click.secho(__("⚡ Issue response retrieved from local cache."), fg="green", dim=True)
+        duration_ms = int((time.perf_counter() - t_start) * 1000)
+        log_command_metric(command="issue", status="success", provider=provider, duration_ms=duration_ms, cache_hit=True)
         return cached_data
 
     click.secho(__("🤖 Structuring Issue using {provider} ({api_model})...", provider=provider.capitalize(), api_model=api_model), fg="cyan", dim=True)
@@ -81,8 +90,19 @@ def generate_issue_content(context_text, context_type="diff"):
     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
-        save_cached_response("issue", "issue", prompt, result_json)
+        # Extract telemetry metadata and save to cache with real token counts
+        meta = result_json.pop("_telemetry_meta", None)
+        save_cached_response("issue", "issue", prompt, result_json, meta_raw=meta)
+        duration_ms = int((time.perf_counter() - t_start) * 1000)
+        log_command_metric(
+            command="issue",
+            status="success",
+            provider=provider,
+            tokens_estimated=(meta or {}).get("total_tokens", 0),
+            duration_ms=duration_ms,
+        )
         return result_json
-        
+
+    duration_ms = int((time.perf_counter() - t_start) * 1000)
+    log_command_metric(command="issue", status="error", provider=provider, duration_ms=duration_ms)
     return {"titulo": __("Error generating title"), "corpo": __("Could not generate issue body by AI.")}