gac 1.10.2__tar.gz → 1.11.0__tar.gz

{gac-1.10.2 → gac-1.11.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gac
-Version: 1.10.2
+Version: 1.11.0
 Summary: LLM-powered Git commit message generator with multi-provider support
 Project-URL: Homepage, https://github.com/cellwebb/gac
 Project-URL: Documentation, https://github.com/cellwebb/gac#readme
@@ -60,7 +60,7 @@ Description-Content-Type: text/markdown
 
 ## What You Get
 
-Instead of generic messages like `"update stuff"`, `"fix bug"`, or `"add feature"`, you get intelligent, contextual messages that explain the **why** behind your changes:
+Intelligent, contextual messages that explain the **why** behind your changes:
 
 ![GAC generating a contextual commit message](assets/gac-simple-usage.png)
 
@@ -92,8 +92,8 @@ gac
 ### 🌐 **Supported Providers**
 
 - **Anthropic** • **Cerebras** • **Chutes.ai** • **Fireworks** • **Gemini**
-- **Groq** • **LM Studio** • **Ollama** • **OpenAI** • **OpenRouter**
-- **Streamlake** • **Synthetic.new** • **Z.AI** • **Z.AI Coding**
+- **Groq** • **LM Studio** • **Minimax** • **Ollama** • **OpenAI** • **OpenRouter**
+- **Streamlake** • **Synthetic.new** • **Together AI** • **Z.AI** • **Z.AI Coding**
 
 ### 🧠 **Smart LLM Analysis**
 
@@ -137,16 +137,16 @@ gac
 
 ### Common Commands
 
-| Command         | Description                                    |
-| --------------- | ---------------------------------------------- |
-| `gac`           | Generate commit message                        |
-| `gac -y`        | Auto-confirm (no review needed)                |
-| `gac -a`        | Stage all + commit                             |
-| `gac -o`        | One-line message only                          |
-| `gac -v`        | Detailed verbose format                        |
-| `gac -h "hint"` | Add context for LLM (e.g., `gac -h "bug fix"`) |
-| `gac -s`        | Include scope (e.g., feat(auth):)              |
-| `gac -p`        | Commit and push                                |
+| Command         | Description                                                             |
+| --------------- | ----------------------------------------------------------------------- |
+| `gac`           | Generate commit message                                                 |
+| `gac -y`        | Auto-confirm (no review needed)                                         |
+| `gac -a`        | Stage all before generating commit message                              |
+| `gac -o`        | One-line message for trivial changes                                    |
+| `gac -v`        | Verbose format with Motivation, Technical Approach, and Impact Analysis |
+| `gac -h "hint"` | Add context for LLM (e.g., `gac -h "bug fix"`)                          |
+| `gac -s`        | Include scope (e.g., feat(auth):)                                       |
+| `gac -p`        | Commit and push                                                         |
 
 ### Power User Examples
 
@@ -172,7 +172,7 @@ gac --skip-secret-scan
 Not happy with the result? Use the reroll feature for intelligent regeneration:
 
 ```bash
-# Simple regeneration (uses previous context)
+# Simple reroll
 r
 
 # With specific feedback

{gac-1.10.2 → gac-1.11.0}/README.md

@@ -19,7 +19,7 @@
 
 ## What You Get
 
-Instead of generic messages like `"update stuff"`, `"fix bug"`, or `"add feature"`, you get intelligent, contextual messages that explain the **why** behind your changes:
+Intelligent, contextual messages that explain the **why** behind your changes:
 
 ![GAC generating a contextual commit message](assets/gac-simple-usage.png)
 
@@ -51,8 +51,8 @@ gac
 ### 🌐 **Supported Providers**
 
 - **Anthropic** • **Cerebras** • **Chutes.ai** • **Fireworks** • **Gemini**
-- **Groq** • **LM Studio** • **Ollama** • **OpenAI** • **OpenRouter**
-- **Streamlake** • **Synthetic.new** • **Z.AI** • **Z.AI Coding**
+- **Groq** • **LM Studio** • **Minimax** • **Ollama** • **OpenAI** • **OpenRouter**
+- **Streamlake** • **Synthetic.new** • **Together AI** • **Z.AI** • **Z.AI Coding**
 
 ### 🧠 **Smart LLM Analysis**
 
@@ -96,16 +96,16 @@ gac
 
 ### Common Commands
 
-| Command         | Description                                    |
-| --------------- | ---------------------------------------------- |
-| `gac`           | Generate commit message                        |
-| `gac -y`        | Auto-confirm (no review needed)                |
-| `gac -a`        | Stage all + commit                             |
-| `gac -o`        | One-line message only                          |
-| `gac -v`        | Detailed verbose format                        |
-| `gac -h "hint"` | Add context for LLM (e.g., `gac -h "bug fix"`) |
-| `gac -s`        | Include scope (e.g., feat(auth):)              |
-| `gac -p`        | Commit and push                                |
+| Command         | Description                                                             |
+| --------------- | ----------------------------------------------------------------------- |
+| `gac`           | Generate commit message                                                 |
+| `gac -y`        | Auto-confirm (no review needed)                                         |
+| `gac -a`        | Stage all before generating commit message                              |
+| `gac -o`        | One-line message for trivial changes                                    |
+| `gac -v`        | Verbose format with Motivation, Technical Approach, and Impact Analysis |
+| `gac -h "hint"` | Add context for LLM (e.g., `gac -h "bug fix"`)                          |
+| `gac -s`        | Include scope (e.g., feat(auth):)                                       |
+| `gac -p`        | Commit and push                                                         |
 
 ### Power User Examples
 
@@ -131,7 +131,7 @@ gac --skip-secret-scan
 Not happy with the result? Use the reroll feature for intelligent regeneration:
 
 ```bash
-# Simple regeneration (uses previous context)
+# Simple reroll
 r
 
 # With specific feedback

{gac-1.10.2 → gac-1.11.0}/src/gac/__version__.py

@@ -1,3 +1,3 @@
 """Version information for gac package."""
 
-__version__ = "1.10.2"
+__version__ = "1.11.0"

{gac-1.10.2 → gac-1.11.0}/src/gac/ai.py

@@ -17,11 +17,13 @@ from gac.providers import (
     call_gemini_api,
     call_groq_api,
     call_lmstudio_api,
+    call_minimax_api,
     call_ollama_api,
     call_openai_api,
     call_openrouter_api,
     call_streamlake_api,
     call_synthetic_api,
+    call_together_api,
     call_zai_api,
     call_zai_coding_api,
 )
@@ -85,11 +87,13 @@ def generate_commit_message(
         "gemini": call_gemini_api,
         "groq": call_groq_api,
         "lm-studio": call_lmstudio_api,
+        "minimax": call_minimax_api,
         "ollama": call_ollama_api,
         "openai": call_openai_api,
         "openrouter": call_openrouter_api,
         "streamlake": call_streamlake_api,
         "synthetic": call_synthetic_api,
+        "together": call_together_api,
         "zai": call_zai_api,
         "zai-coding": call_zai_coding_api,
     }

{gac-1.10.2 → gac-1.11.0}/src/gac/ai_utils.py

@@ -100,11 +100,13 @@ def generate_with_retries(
         "gemini",
         "groq",
         "lm-studio",
+        "minimax",
         "ollama",
         "openai",
         "openrouter",
         "streamlake",
         "synthetic",
+        "together",
         "zai",
         "zai-coding",
     ]

{gac-1.10.2 → gac-1.11.0}/src/gac/init_cli.py

@@ -39,6 +39,7 @@ def init() -> None:
         ("Gemini", "gemini-2.5-flash"),
         ("Groq", "meta-llama/llama-4-maverick-17b-128e-instruct"),
         ("LM Studio", "gemma3"),
+        ("Minimax", "MiniMax-M2"),
         ("Ollama", "gemma3"),
         ("OpenAI", "gpt-4.1-mini"),
         ("OpenRouter", "openrouter/auto"),

{gac-1.10.2 → gac-1.11.0}/src/gac/providers/__init__.py

@@ -7,11 +7,13 @@ from .fireworks import call_fireworks_api
 from .gemini import call_gemini_api
 from .groq import call_groq_api
 from .lmstudio import call_lmstudio_api
+from .minimax import call_minimax_api
 from .ollama import call_ollama_api
 from .openai import call_openai_api
 from .openrouter import call_openrouter_api
 from .streamlake import call_streamlake_api
 from .synthetic import call_synthetic_api
+from .together import call_together_api
 from .zai import call_zai_api, call_zai_coding_api
 
 __all__ = [
@@ -22,11 +24,13 @@ __all__ = [
     "call_gemini_api",
     "call_groq_api",
     "call_lmstudio_api",
+    "call_minimax_api",
     "call_ollama_api",
     "call_openai_api",
     "call_openrouter_api",
     "call_streamlake_api",
     "call_synthetic_api",
+    "call_together_api",
     "call_zai_api",
     "call_zai_coding_api",
 ]

gac-1.11.0/src/gac/providers/minimax.py

@@ -0,0 +1,38 @@
+"""Minimax API provider for gac."""
+
+import os
+
+import httpx
+
+from gac.errors import AIError
+
+
+def call_minimax_api(model: str, messages: list[dict], temperature: float, max_tokens: int) -> str:
+    """Call Minimax API directly."""
+    api_key = os.getenv("MINIMAX_API_KEY")
+    if not api_key:
+        raise AIError.authentication_error("MINIMAX_API_KEY not found in environment variables")
+
+    url = "https://api.minimax.io/v1/chat/completions"
+    headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
+
+    data = {"model": model, "messages": messages, "temperature": temperature, "max_tokens": max_tokens}
+
+    try:
+        response = httpx.post(url, headers=headers, json=data, timeout=120)
+        response.raise_for_status()
+        response_data = response.json()
+        content = response_data["choices"][0]["message"]["content"]
+        if content is None:
+            raise AIError.model_error("Minimax API returned null content")
+        if content == "":
+            raise AIError.model_error("Minimax API returned empty content")
+        return content
+    except httpx.HTTPStatusError as e:
+        if e.response.status_code == 429:
+            raise AIError.rate_limit_error(f"Minimax API rate limit exceeded: {e.response.text}") from e
+        raise AIError.model_error(f"Minimax API error: {e.response.status_code} - {e.response.text}") from e
+    except httpx.TimeoutException as e:
+        raise AIError.timeout_error(f"Minimax API request timed out: {str(e)}") from e
+    except Exception as e:
+        raise AIError.model_error(f"Error calling Minimax API: {str(e)}") from e

gac-1.11.0/src/gac/providers/together.py

@@ -0,0 +1,38 @@
+"""Together AI API provider for gac."""
+
+import os
+
+import httpx
+
+from gac.errors import AIError
+
+
+def call_together_api(model: str, messages: list[dict], temperature: float, max_tokens: int) -> str:
+    """Call Together AI API directly."""
+    api_key = os.getenv("TOGETHER_API_KEY")
+    if not api_key:
+        raise AIError.authentication_error("TOGETHER_API_KEY not found in environment variables")
+
+    url = "https://api.together.xyz/v1/chat/completions"
+    headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
+
+    data = {"model": model, "messages": messages, "temperature": temperature, "max_tokens": max_tokens}
+
+    try:
+        response = httpx.post(url, headers=headers, json=data, timeout=120)
+        response.raise_for_status()
+        response_data = response.json()
+        content = response_data["choices"][0]["message"]["content"]
+        if content is None:
+            raise AIError.model_error("Together AI API returned null content")
+        if content == "":
+            raise AIError.model_error("Together AI API returned empty content")
+        return content
+    except httpx.HTTPStatusError as e:
+        if e.response.status_code == 429:
+            raise AIError.rate_limit_error(f"Together AI API rate limit exceeded: {e.response.text}") from e
+        raise AIError.model_error(f"Together AI API error: {e.response.status_code} - {e.response.text}") from e
+    except httpx.TimeoutException as e:
+        raise AIError.timeout_error(f"Together AI API request timed out: {str(e)}") from e
+    except Exception as e:
+        raise AIError.model_error(f"Error calling Together AI API: {str(e)}") from e