patchpal 0.1.0__tar.gz → 0.1.2__tar.gz

{patchpal-0.1.0/patchpal.egg-info → patchpal-0.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: patchpal
-Version: 0.1.0
+Version: 0.1.2
 Summary: A lean Claude Code clone in pure  Python
 Author: PatchPal Contributors
 License-Expression: Apache-2.0
@@ -37,7 +37,7 @@ Dynamic: license-file
 # PatchPal — A Claude Code–Style Agent in Python
 
 <!--![PatchPal Screenshot](patchpal_screenshot.png)-->
-<img src="patchpal_screenshot.png" alt="PatchPal Screenshot" width="650"/>
+<img src="https://raw.githubusercontent.com/amaiya/patchpal/refs/heads/main/patchpal_screenshot.png" alt="PatchPal Screenshot" width="650"/>
 
 > A lightweight Claude Code–inspired coding and automation assistant -- supports both local and cloud LLMs.
 
@@ -69,7 +69,7 @@ pip install patchpal
    - **[Cloud]** For Anthropic models (default): Sign up at https://console.anthropic.com/
    - **[Cloud]** For OpenAI models: Get a key from https://platform.openai.com/
    - **[Local]** For vLLM: Install from https://docs.vllm.ai/ (free - no API charges) **Recommended for Local Use**
-   - **[Local]** For Ollama: Install from https://ollama.com/ (⚠️ not well-suited for agents - use vLLM)
+   - **[Local]** For Ollama: Install from https://ollama.com/ (⚠️ requires `OLLAMA_CONTEXT_LENGTH=32768` - see Ollama section below)
    - For other providers: Check the [LiteLLM documentation](https://docs.litellm.ai/docs/providers)
 
 2. **Set up your API key as environment variable**:
@@ -103,8 +103,9 @@ export HOSTED_VLLM_API_BASE=http://localhost:8000
 export HOSTED_VLLM_API_KEY=token-abc123
 patchpal --model hosted_vllm/openai/gpt-oss-20b
 
-# Use Ollama (local, ⚠️ not recommended - use vLLM)
-patchpal --model ollama_chat/qwen3:32b # vLLM is better for agents
+# Use Ollama (local - requires OLLAMA_CONTEXT_LENGTH=32768)
+export OLLAMA_CONTEXT_LENGTH=32768
+patchpal --model ollama_chat/qwen3:32b
 
 # Or set the model via environment variable
 export PATCHPAL_MODEL=openai/gpt-5
@@ -401,14 +402,86 @@ Different models require different parsers. Common parsers include: `qwen3_xml`,
 
 #### Ollama
 
-We find that Ollama models do not work well in agentic settings. For instance, while [gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b) works well in vLLM, the [Ollama version](https://ollama.com/library/gpt-oss) of the same model performs poorly. vLLM is recommended for local deployments.
+Ollama v0.14+ supports tool calling for agentic workflows. However, proper configuration is **critical** for reliable operation.
+
+**Requirements:**
+
+1. **Ollama v0.14.0 or later** - Required for tool calling support
+2. **Sufficient context window** - Default 4096 tokens is too small; increase to at least 32K
+
+**Setup Instructions:**
+
+**For Native Ollama Installation:**
+
+```bash
+# Set context window size (required!)
+export OLLAMA_CONTEXT_LENGTH=32768
+
+# Start Ollama server
+ollama serve
+
+# In another terminal, use with PatchPal
+patchpal --model ollama_chat/gpt-oss:20b
+```
+
+**For Docker:**
+
+```bash
+# Stop existing container (if running)
+docker stop ollama
+docker rm ollama
+
+# Start with proper configuration
+docker run -d \
+  -e OLLAMA_CONTEXT_LENGTH=32768 \
+  -v ollama:/root/.ollama \
+  -p 11434:11434 \
+  --name ollama \
+  ollama/ollama
+
+# Verify configuration
+docker exec -it ollama ollama run gpt-oss:20b
+# In the Ollama prompt, type: /show parameters
+# Should show num_ctx much larger than default 4096
+
+# Use with PatchPal
+patchpal --model ollama_chat/gpt-oss:20b
+```
+
+**Verifying Context Window Size:**
+
+```bash
+# Check your Ollama container configuration
+docker inspect ollama | grep OLLAMA_CONTEXT_LENGTH
+
+# Or run a model and check parameters
+docker exec -it ollama ollama run gpt-oss:20b
+>>> /show parameters
+```
+
+**Recommended Models for Tool Calling:**
+
+- `gpt-oss:20b` - OpenAI's open-source model, excellent tool calling
+- `qwen3:32b` - Qwen3 model with good agentic capabilities
+- `qwen3-coder` - Specialized for coding tasks
+
+**Performance Note:**
+
+While Ollama now works with proper configuration, vLLM is still recommended for production use due to:
+- 3-10x faster inference
+- More robust tool calling implementation
+- Better memory management
 
 **Examples:**
 
 ```bash
-patchpal --model ollama_chat/qwen3:32b          # local model: performs poorly
-patchpal --model ollama_chat/gpt-oss:20b        # local model: performs poorly
-patchpal --model hosted_vllm/openai/gpt-oss-20b # local model: performs well
+# Ollama (works with proper configuration)
+export OLLAMA_CONTEXT_LENGTH=32768
+patchpal --model ollama_chat/qwen3:32b
+patchpal --model ollama_chat/gpt-oss:20b
+
+# vLLM (recommended for production)
+patchpal --model hosted_vllm/openai/gpt-oss-20b
 ```
 
 ### Air-Gapped and Offline Environments
@@ -526,7 +599,7 @@ PatchPal includes comprehensive security protections enabled by default:
 - **Command history**: User commands saved to `~/.patchpal/<repo-name>/history.txt` (last 1000 commands)
   - Clean, user-friendly format for reviewing past interactions
 - **Automatic backups**: Optional auto-backup of files to `~/.patchpal/<repo-name>/backups/` before modification
-- **Resource limits**: Configurable operation counter prevents infinite loops (1000 operations default)
+- **Resource limits**: Configurable operation counter prevents infinite loops (10000 operations default)
 - **Git state awareness**: Warns when modifying files with uncommitted changes
 
 **Configuration via environment variables:**
@@ -543,7 +616,7 @@ export PATCHPAL_ALLOW_SENSITIVE=true      # Allow access to .env, credentials, A
 # Operational Safety Controls
 export PATCHPAL_AUDIT_LOG=false           # Log all operations to ~/.patchpal/<repo-name>/audit.log (default: true)
 export PATCHPAL_ENABLE_BACKUPS=true       # Auto-backup files to ~/.patchpal/<repo-name>/backups/ before modification (default: false)
-export PATCHPAL_MAX_OPERATIONS=5000       # Maximum operations per session to prevent infinite loops (default: 1000)
+export PATCHPAL_MAX_OPERATIONS=5000       # Maximum operations per session to prevent infinite loops (default: 10000)
 export PATCHPAL_MAX_ITERATIONS=150        # Maximum agent iterations per task (default: 100)
                                           # Increase for very complex multi-file tasks, decrease for testing
 

{patchpal-0.1.0 → patchpal-0.1.2}/README.md

@@ -1,7 +1,7 @@
 # PatchPal — A Claude Code–Style Agent in Python
 
 <!--![PatchPal Screenshot](patchpal_screenshot.png)-->
-<img src="patchpal_screenshot.png" alt="PatchPal Screenshot" width="650"/>
+<img src="https://raw.githubusercontent.com/amaiya/patchpal/refs/heads/main/patchpal_screenshot.png" alt="PatchPal Screenshot" width="650"/>
 
 > A lightweight Claude Code–inspired coding and automation assistant -- supports both local and cloud LLMs.
 
@@ -33,7 +33,7 @@ pip install patchpal
    - **[Cloud]** For Anthropic models (default): Sign up at https://console.anthropic.com/
    - **[Cloud]** For OpenAI models: Get a key from https://platform.openai.com/
    - **[Local]** For vLLM: Install from https://docs.vllm.ai/ (free - no API charges) **Recommended for Local Use**
-   - **[Local]** For Ollama: Install from https://ollama.com/ (⚠️ not well-suited for agents - use vLLM)
+   - **[Local]** For Ollama: Install from https://ollama.com/ (⚠️ requires `OLLAMA_CONTEXT_LENGTH=32768` - see Ollama section below)
    - For other providers: Check the [LiteLLM documentation](https://docs.litellm.ai/docs/providers)
 
 2. **Set up your API key as environment variable**:
@@ -67,8 +67,9 @@ export HOSTED_VLLM_API_BASE=http://localhost:8000
 export HOSTED_VLLM_API_KEY=token-abc123
 patchpal --model hosted_vllm/openai/gpt-oss-20b
 
-# Use Ollama (local, ⚠️ not recommended - use vLLM)
-patchpal --model ollama_chat/qwen3:32b # vLLM is better for agents
+# Use Ollama (local - requires OLLAMA_CONTEXT_LENGTH=32768)
+export OLLAMA_CONTEXT_LENGTH=32768
+patchpal --model ollama_chat/qwen3:32b
 
 # Or set the model via environment variable
 export PATCHPAL_MODEL=openai/gpt-5
@@ -365,14 +366,86 @@ Different models require different parsers. Common parsers include: `qwen3_xml`,
 
 #### Ollama
 
-We find that Ollama models do not work well in agentic settings. For instance, while [gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b) works well in vLLM, the [Ollama version](https://ollama.com/library/gpt-oss) of the same model performs poorly. vLLM is recommended for local deployments.
+Ollama v0.14+ supports tool calling for agentic workflows. However, proper configuration is **critical** for reliable operation.
+
+**Requirements:**
+
+1. **Ollama v0.14.0 or later** - Required for tool calling support
+2. **Sufficient context window** - Default 4096 tokens is too small; increase to at least 32K
+
+**Setup Instructions:**
+
+**For Native Ollama Installation:**
+
+```bash
+# Set context window size (required!)
+export OLLAMA_CONTEXT_LENGTH=32768
+
+# Start Ollama server
+ollama serve
+
+# In another terminal, use with PatchPal
+patchpal --model ollama_chat/gpt-oss:20b
+```
+
+**For Docker:**
+
+```bash
+# Stop existing container (if running)
+docker stop ollama
+docker rm ollama
+
+# Start with proper configuration
+docker run -d \
+  -e OLLAMA_CONTEXT_LENGTH=32768 \
+  -v ollama:/root/.ollama \
+  -p 11434:11434 \
+  --name ollama \
+  ollama/ollama
+
+# Verify configuration
+docker exec -it ollama ollama run gpt-oss:20b
+# In the Ollama prompt, type: /show parameters
+# Should show num_ctx much larger than default 4096
+
+# Use with PatchPal
+patchpal --model ollama_chat/gpt-oss:20b
+```
+
+**Verifying Context Window Size:**
+
+```bash
+# Check your Ollama container configuration
+docker inspect ollama | grep OLLAMA_CONTEXT_LENGTH
+
+# Or run a model and check parameters
+docker exec -it ollama ollama run gpt-oss:20b
+>>> /show parameters
+```
+
+**Recommended Models for Tool Calling:**
+
+- `gpt-oss:20b` - OpenAI's open-source model, excellent tool calling
+- `qwen3:32b` - Qwen3 model with good agentic capabilities
+- `qwen3-coder` - Specialized for coding tasks
+
+**Performance Note:**
+
+While Ollama now works with proper configuration, vLLM is still recommended for production use due to:
+- 3-10x faster inference
+- More robust tool calling implementation
+- Better memory management
 
 **Examples:**
 
 ```bash
-patchpal --model ollama_chat/qwen3:32b          # local model: performs poorly
-patchpal --model ollama_chat/gpt-oss:20b        # local model: performs poorly
-patchpal --model hosted_vllm/openai/gpt-oss-20b # local model: performs well
+# Ollama (works with proper configuration)
+export OLLAMA_CONTEXT_LENGTH=32768
+patchpal --model ollama_chat/qwen3:32b
+patchpal --model ollama_chat/gpt-oss:20b
+
+# vLLM (recommended for production)
+patchpal --model hosted_vllm/openai/gpt-oss-20b
 ```
 
 ### Air-Gapped and Offline Environments
@@ -490,7 +563,7 @@ PatchPal includes comprehensive security protections enabled by default:
 - **Command history**: User commands saved to `~/.patchpal/<repo-name>/history.txt` (last 1000 commands)
   - Clean, user-friendly format for reviewing past interactions
 - **Automatic backups**: Optional auto-backup of files to `~/.patchpal/<repo-name>/backups/` before modification
-- **Resource limits**: Configurable operation counter prevents infinite loops (1000 operations default)
+- **Resource limits**: Configurable operation counter prevents infinite loops (10000 operations default)
 - **Git state awareness**: Warns when modifying files with uncommitted changes
 
 **Configuration via environment variables:**
@@ -507,7 +580,7 @@ export PATCHPAL_ALLOW_SENSITIVE=true      # Allow access to .env, credentials, A
 # Operational Safety Controls
 export PATCHPAL_AUDIT_LOG=false           # Log all operations to ~/.patchpal/<repo-name>/audit.log (default: true)
 export PATCHPAL_ENABLE_BACKUPS=true       # Auto-backup files to ~/.patchpal/<repo-name>/backups/ before modification (default: false)
-export PATCHPAL_MAX_OPERATIONS=5000       # Maximum operations per session to prevent infinite loops (default: 1000)
+export PATCHPAL_MAX_OPERATIONS=5000       # Maximum operations per session to prevent infinite loops (default: 10000)
 export PATCHPAL_MAX_ITERATIONS=150        # Maximum agent iterations per task (default: 100)
                                           # Increase for very complex multi-file tasks, decrease for testing
 

{patchpal-0.1.0 → patchpal-0.1.2}/patchpal/__init__.py

@@ -1,6 +1,6 @@
 """PatchPal - An open-source Claude Code clone implemented purely in Python."""
 
-__version__ = "0.1.0"
+__version__ = "0.1.2"
 
 from patchpal.agent import create_agent
 from patchpal.tools import (

{patchpal-0.1.0 → patchpal-0.1.2}/patchpal/agent.py

@@ -540,6 +540,22 @@ class PatchPalAgent:
 
         self.model_id = _normalize_bedrock_model_id(model_id)
 
+        # Register Ollama models as supporting native function calling
+        # LiteLLM defaults to JSON mode if not explicitly registered
+        if self.model_id.startswith("ollama_chat/"):
+            # Suppress verbose output from register_model
+            import sys
+            from io import StringIO
+
+            old_stdout = sys.stdout
+            sys.stdout = StringIO()
+            try:
+                litellm.register_model(
+                    {"model_cost": {self.model_id: {"supports_function_calling": True}}}
+                )
+            finally:
+                sys.stdout = old_stdout
+
         # Set up Bedrock environment if needed
         if self.model_id.startswith("bedrock/"):
             _setup_bedrock_env()

{patchpal-0.1.0 → patchpal-0.1.2}/patchpal/tools.py

@@ -79,7 +79,7 @@ READ_ONLY_MODE = os.getenv("PATCHPAL_READ_ONLY", "false").lower() == "true"
 ALLOW_SENSITIVE = os.getenv("PATCHPAL_ALLOW_SENSITIVE", "false").lower() == "true"
 ENABLE_AUDIT_LOG = os.getenv("PATCHPAL_AUDIT_LOG", "true").lower() == "true"
 ENABLE_BACKUPS = os.getenv("PATCHPAL_ENABLE_BACKUPS", "false").lower() == "true"
-MAX_OPERATIONS = int(os.getenv("PATCHPAL_MAX_OPERATIONS", 1000))
+MAX_OPERATIONS = int(os.getenv("PATCHPAL_MAX_OPERATIONS", 10000))
 
 # Web request configuration
 WEB_REQUEST_TIMEOUT = int(os.getenv("PATCHPAL_WEB_TIMEOUT", 30))  # 30 seconds

{patchpal-0.1.0 → patchpal-0.1.2/patchpal.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: patchpal
-Version: 0.1.0
+Version: 0.1.2
 Summary: A lean Claude Code clone in pure  Python
 Author: PatchPal Contributors
 License-Expression: Apache-2.0
@@ -37,7 +37,7 @@ Dynamic: license-file
 # PatchPal — A Claude Code–Style Agent in Python
 
 <!--![PatchPal Screenshot](patchpal_screenshot.png)-->
-<img src="patchpal_screenshot.png" alt="PatchPal Screenshot" width="650"/>
+<img src="https://raw.githubusercontent.com/amaiya/patchpal/refs/heads/main/patchpal_screenshot.png" alt="PatchPal Screenshot" width="650"/>
 
 > A lightweight Claude Code–inspired coding and automation assistant -- supports both local and cloud LLMs.
 
@@ -69,7 +69,7 @@ pip install patchpal
    - **[Cloud]** For Anthropic models (default): Sign up at https://console.anthropic.com/
    - **[Cloud]** For OpenAI models: Get a key from https://platform.openai.com/
    - **[Local]** For vLLM: Install from https://docs.vllm.ai/ (free - no API charges) **Recommended for Local Use**
-   - **[Local]** For Ollama: Install from https://ollama.com/ (⚠️ not well-suited for agents - use vLLM)
+   - **[Local]** For Ollama: Install from https://ollama.com/ (⚠️ requires `OLLAMA_CONTEXT_LENGTH=32768` - see Ollama section below)
    - For other providers: Check the [LiteLLM documentation](https://docs.litellm.ai/docs/providers)
 
 2. **Set up your API key as environment variable**:
@@ -103,8 +103,9 @@ export HOSTED_VLLM_API_BASE=http://localhost:8000
 export HOSTED_VLLM_API_KEY=token-abc123
 patchpal --model hosted_vllm/openai/gpt-oss-20b
 
-# Use Ollama (local, ⚠️ not recommended - use vLLM)
-patchpal --model ollama_chat/qwen3:32b # vLLM is better for agents
+# Use Ollama (local - requires OLLAMA_CONTEXT_LENGTH=32768)
+export OLLAMA_CONTEXT_LENGTH=32768
+patchpal --model ollama_chat/qwen3:32b
 
 # Or set the model via environment variable
 export PATCHPAL_MODEL=openai/gpt-5
@@ -401,14 +402,86 @@ Different models require different parsers. Common parsers include: `qwen3_xml`,
 
 #### Ollama
 
-We find that Ollama models do not work well in agentic settings. For instance, while [gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b) works well in vLLM, the [Ollama version](https://ollama.com/library/gpt-oss) of the same model performs poorly. vLLM is recommended for local deployments.
+Ollama v0.14+ supports tool calling for agentic workflows. However, proper configuration is **critical** for reliable operation.
+
+**Requirements:**
+
+1. **Ollama v0.14.0 or later** - Required for tool calling support
+2. **Sufficient context window** - Default 4096 tokens is too small; increase to at least 32K
+
+**Setup Instructions:**
+
+**For Native Ollama Installation:**
+
+```bash
+# Set context window size (required!)
+export OLLAMA_CONTEXT_LENGTH=32768
+
+# Start Ollama server
+ollama serve
+
+# In another terminal, use with PatchPal
+patchpal --model ollama_chat/gpt-oss:20b
+```
+
+**For Docker:**
+
+```bash
+# Stop existing container (if running)
+docker stop ollama
+docker rm ollama
+
+# Start with proper configuration
+docker run -d \
+  -e OLLAMA_CONTEXT_LENGTH=32768 \
+  -v ollama:/root/.ollama \
+  -p 11434:11434 \
+  --name ollama \
+  ollama/ollama
+
+# Verify configuration
+docker exec -it ollama ollama run gpt-oss:20b
+# In the Ollama prompt, type: /show parameters
+# Should show num_ctx much larger than default 4096
+
+# Use with PatchPal
+patchpal --model ollama_chat/gpt-oss:20b
+```
+
+**Verifying Context Window Size:**
+
+```bash
+# Check your Ollama container configuration
+docker inspect ollama | grep OLLAMA_CONTEXT_LENGTH
+
+# Or run a model and check parameters
+docker exec -it ollama ollama run gpt-oss:20b
+>>> /show parameters
+```
+
+**Recommended Models for Tool Calling:**
+
+- `gpt-oss:20b` - OpenAI's open-source model, excellent tool calling
+- `qwen3:32b` - Qwen3 model with good agentic capabilities
+- `qwen3-coder` - Specialized for coding tasks
+
+**Performance Note:**
+
+While Ollama now works with proper configuration, vLLM is still recommended for production use due to:
+- 3-10x faster inference
+- More robust tool calling implementation
+- Better memory management
 
 **Examples:**
 
 ```bash
-patchpal --model ollama_chat/qwen3:32b          # local model: performs poorly
-patchpal --model ollama_chat/gpt-oss:20b        # local model: performs poorly
-patchpal --model hosted_vllm/openai/gpt-oss-20b # local model: performs well
+# Ollama (works with proper configuration)
+export OLLAMA_CONTEXT_LENGTH=32768
+patchpal --model ollama_chat/qwen3:32b
+patchpal --model ollama_chat/gpt-oss:20b
+
+# vLLM (recommended for production)
+patchpal --model hosted_vllm/openai/gpt-oss-20b
 ```
 
 ### Air-Gapped and Offline Environments
@@ -526,7 +599,7 @@ PatchPal includes comprehensive security protections enabled by default:
 - **Command history**: User commands saved to `~/.patchpal/<repo-name>/history.txt` (last 1000 commands)
   - Clean, user-friendly format for reviewing past interactions
 - **Automatic backups**: Optional auto-backup of files to `~/.patchpal/<repo-name>/backups/` before modification
-- **Resource limits**: Configurable operation counter prevents infinite loops (1000 operations default)
+- **Resource limits**: Configurable operation counter prevents infinite loops (10000 operations default)
 - **Git state awareness**: Warns when modifying files with uncommitted changes
 
 **Configuration via environment variables:**
@@ -543,7 +616,7 @@ export PATCHPAL_ALLOW_SENSITIVE=true      # Allow access to .env, credentials, A
 # Operational Safety Controls
 export PATCHPAL_AUDIT_LOG=false           # Log all operations to ~/.patchpal/<repo-name>/audit.log (default: true)
 export PATCHPAL_ENABLE_BACKUPS=true       # Auto-backup files to ~/.patchpal/<repo-name>/backups/ before modification (default: false)
-export PATCHPAL_MAX_OPERATIONS=5000       # Maximum operations per session to prevent infinite loops (default: 1000)
+export PATCHPAL_MAX_OPERATIONS=5000       # Maximum operations per session to prevent infinite loops (default: 10000)
 export PATCHPAL_MAX_ITERATIONS=150        # Maximum agent iterations per task (default: 100)
                                           # Increase for very complex multi-file tasks, decrease for testing