cua-agent 0.1.6__py3-none-any.whl → 0.1.18__py3-none-any.whl

cua_agent-0.1.18.dist-info/METADATA

@@ -0,0 +1,165 @@
+Metadata-Version: 2.1
+Name: cua-agent
+Version: 0.1.18
+Summary: CUA (Computer Use) Agent for AI-driven computer interaction
+Author-Email: TryCua <gh@trycua.com>
+Requires-Python: <3.13,>=3.10
+Requires-Dist: httpx<0.29.0,>=0.27.0
+Requires-Dist: aiohttp<4.0.0,>=3.9.3
+Requires-Dist: asyncio
+Requires-Dist: anyio<5.0.0,>=4.4.1
+Requires-Dist: typing-extensions<5.0.0,>=4.12.2
+Requires-Dist: pydantic<3.0.0,>=2.6.4
+Requires-Dist: rich<14.0.0,>=13.7.1
+Requires-Dist: python-dotenv<2.0.0,>=1.0.1
+Requires-Dist: cua-computer<0.2.0,>=0.1.0
+Requires-Dist: cua-core<0.2.0,>=0.1.0
+Requires-Dist: certifi>=2024.2.2
+Provides-Extra: anthropic
+Requires-Dist: anthropic>=0.49.0; extra == "anthropic"
+Requires-Dist: boto3<2.0.0,>=1.35.81; extra == "anthropic"
+Provides-Extra: openai
+Requires-Dist: openai<2.0.0,>=1.14.0; extra == "openai"
+Requires-Dist: httpx<0.29.0,>=0.27.0; extra == "openai"
+Provides-Extra: som
+Requires-Dist: torch>=2.2.1; extra == "som"
+Requires-Dist: torchvision>=0.17.1; extra == "som"
+Requires-Dist: ultralytics>=8.0.0; extra == "som"
+Requires-Dist: transformers>=4.38.2; extra == "som"
+Requires-Dist: cua-som<0.2.0,>=0.1.0; extra == "som"
+Requires-Dist: anthropic<0.47.0,>=0.46.0; extra == "som"
+Requires-Dist: boto3<2.0.0,>=1.35.81; extra == "som"
+Requires-Dist: openai<2.0.0,>=1.14.0; extra == "som"
+Requires-Dist: groq<0.5.0,>=0.4.0; extra == "som"
+Requires-Dist: dashscope<2.0.0,>=1.13.0; extra == "som"
+Requires-Dist: requests<3.0.0,>=2.31.0; extra == "som"
+Provides-Extra: all
+Requires-Dist: torch>=2.2.1; extra == "all"
+Requires-Dist: torchvision>=0.17.1; extra == "all"
+Requires-Dist: ultralytics>=8.0.0; extra == "all"
+Requires-Dist: transformers>=4.38.2; extra == "all"
+Requires-Dist: cua-som<0.2.0,>=0.1.0; extra == "all"
+Requires-Dist: anthropic<0.47.0,>=0.46.0; extra == "all"
+Requires-Dist: boto3<2.0.0,>=1.35.81; extra == "all"
+Requires-Dist: openai<2.0.0,>=1.14.0; extra == "all"
+Requires-Dist: groq<0.5.0,>=0.4.0; extra == "all"
+Requires-Dist: dashscope<2.0.0,>=1.13.0; extra == "all"
+Requires-Dist: requests<3.0.0,>=2.31.0; extra == "all"
+Description-Content-Type: text/markdown
+
+<div align="center">
+<h1>
+  <div class="image-wrapper" style="display: inline-block;">
+    <picture>
+      <source media="(prefers-color-scheme: dark)" alt="logo" height="150" srcset="../../img/logo_white.png" style="display: block; margin: auto;">
+      <source media="(prefers-color-scheme: light)" alt="logo" height="150" srcset="../../img/logo_black.png" style="display: block; margin: auto;">
+      <img alt="Shows my svg">
+    </picture>
+  </div>
+
+  [![Python](https://img.shields.io/badge/Python-333333?logo=python&logoColor=white&labelColor=333333)](#)
+  [![macOS](https://img.shields.io/badge/macOS-000000?logo=apple&logoColor=F0F0F0)](#)
+  [![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?&logo=discord&logoColor=white)](https://discord.com/invite/mVnXXpdE85)
+  [![PyPI](https://img.shields.io/pypi/v/cua-computer?color=333333)](https://pypi.org/project/cua-computer/)
+</h1>
+</div>
+
+**cua-agent** is a general Computer-Use framework for running multi-app agentic workflows targeting macOS and Linux sandbox created with Cua, supporting local (Ollama) and cloud model providers (OpenAI, Anthropic, Groq, DeepSeek, Qwen).
+
+### Get started with Agent
+
+<div align="center">
+    <img src="../../img/agent.png"/>
+</div>
+
+## Install
+
+```bash
+pip install "cua-agent[all]"
+
+# or install specific loop providers
+pip install "cua-agent[openai]" # OpenAI Cua Loop
+pip install "cua-agent[anthropic]" # Anthropic Cua Loop
+pip install "cua-agent[omni]" # Cua Loop based on OmniParser
+```
+
+## Run
+
+```bash
+async with Computer() as macos_computer:
+  # Create agent with loop and provider
+  agent = ComputerAgent(
+      computer=macos_computer,
+      loop=AgentLoop.OPENAI,
+      model=LLM(provider=LLMProvider.OPENAI)
+  )
+
+  tasks = [
+      "Look for a repository named trycua/cua on GitHub.",
+      "Check the open issues, open the most recent one and read it.",
+      "Clone the repository in users/lume/projects if it doesn't exist yet.",
+      "Open the repository with an app named Cursor (on the dock, black background and white cube icon).",
+      "From Cursor, open Composer if not already open.",
+      "Focus on the Composer text area, then write and submit a task to help resolve the GitHub issue.",
+  ]
+
+  for i, task in enumerate(tasks):
+      print(f"\nExecuting task {i}/{len(tasks)}: {task}")
+      async for result in agent.run(task):
+          print(result)
+
+      print(f"\n✅ Task {i+1}/{len(tasks)} completed: {task}")
+```
+
+Refer to these notebooks for step-by-step guides on how to use the Computer-Use Agent (CUA):
+
+- [Agent Notebook](../../notebooks/agent_nb.ipynb) - Complete examples and workflows
+
+## Agent Loops
+
+The `cua-agent` package provides three agent loops variations, based on different CUA models providers and techniques:
+
+| Agent Loop | Supported Models | Description | Set-Of-Marks |
+|:-----------|:-----------------|:------------|:-------------|
+| `AgentLoop.OPENAI` | • `computer_use_preview` | Use OpenAI Operator CUA model | Not Required |
+| `AgentLoop.ANTHROPIC` | • `claude-3-5-sonnet-20240620`<br>• `claude-3-7-sonnet-20250219` | Use Anthropic Computer-Use | Not Required |
+| `AgentLoop.OMNI` <br>(preview) | • `claude-3-5-sonnet-20240620`<br>• `claude-3-7-sonnet-20250219`<br>• `gpt-4.5-preview`<br>• `gpt-4o`<br>• `gpt-4`<br>• `gpt-3.5-turbo` | Use OmniParser for element pixel-detection (SoM) and any VLMs | OmniParser |
+
+## AgentResponse
+The `AgentResponse` class represents the structured output returned after each agent turn. It contains the agent's response, reasoning, tool usage, and other metadata. The response format aligns with the new [OpenAI Agent SDK specification](https://platform.openai.com/docs/api-reference/responses) for better consistency across different agent loops.
+
+```python
+async for result in agent.run(task):
+  print("Response ID: ", result.get("id"))
+
+  # Print detailed usage information
+  usage = result.get("usage")
+  if usage:
+      print("\nUsage Details:")
+      print(f"  Input Tokens: {usage.get('input_tokens')}")
+      if "input_tokens_details" in usage:
+          print(f"  Input Tokens Details: {usage.get('input_tokens_details')}")
+      print(f"  Output Tokens: {usage.get('output_tokens')}")
+      if "output_tokens_details" in usage:
+          print(f"  Output Tokens Details: {usage.get('output_tokens_details')}")
+      print(f"  Total Tokens: {usage.get('total_tokens')}")
+
+  print("Response Text: ", result.get("text"))
+
+  # Print tools information
+  tools = result.get("tools")
+  if tools:
+      print("\nTools:")
+      print(tools)
+
+  # Print reasoning and tool call outputs
+  outputs = result.get("output", [])
+  for output in outputs:
+      output_type = output.get("type")
+      if output_type == "reasoning":
+          print("\nReasoning Output:")
+          print(output)
+      elif output_type == "computer_call":
+          print("\nTool Call Output:")
+          print(output)
+```

cua_agent-0.1.18.dist-info/RECORD

@@ -0,0 +1,73 @@
+agent/__init__.py,sha256=ZOK-dcYN3o9CQ9XnUipkDR7YKQNNZ3HL_7MJbqHY_-c,1494
+agent/core/README.md,sha256=VOXNVbR0ugxf9gCXYmZtUU2kngZhfi29haT_oSxK0Lk,3559
+agent/core/__init__.py,sha256=7DhJ_6KKooM6uTmDIlumCnd7OFcU67BYIIR1dpIYUB0,506
+agent/core/agent.py,sha256=WutrveYndS-YBy9BVu1I-Eyj-7AAk1CgACkn5OdWvhU,8010
+agent/core/base.py,sha256=EoutyMJ2kSJ72Di8KVRiUXc0ZJ1OkA0e7Ej14Y3F87w,7124
+agent/core/callbacks.py,sha256=VbGIf5QkHh3Q0KsLM6wv7hRdIA5WExTVYLm64bckyUA,4306
+agent/core/experiment.py,sha256=Ywj6q3JZFDKicfPuQsDl0vSN55HS7-Cnk3u3EcUCKe8,8866
+agent/core/factory.py,sha256=sy7k323ZPDf8T7UEKNSV9wT2OylckliaPr8KyYhMAi0,3829
+agent/core/messages.py,sha256=-OVMDqcxK5MUHPEkHliK29XFJYMRAc1keFvzrUyrOmM,16231
+agent/core/provider_config.py,sha256=GndsvFdFQHNlxOSE6XcxRAZcyOJmLQ_jSOd66QY0uyk,414
+agent/core/telemetry.py,sha256=HElPd32k_w2SJ6t-Cc3j_2-AKdLbFwh2YlM8QViDgRw,4790
+agent/core/tools.py,sha256=Jes2CFCFqC727WWHbO-sG7V03rBHnQe5X7Oi9ZkuScI,877
+agent/core/tools/__init__.py,sha256=xZen-PqUp2dUaMEHJowXCQm33_5Sxhsx9PSoD0rq6tI,489
+agent/core/tools/base.py,sha256=CdzRFNuOjNfzgyTUN4ZoCGkUDR5HI0ECQVpvrUdEij8,2295
+agent/core/tools/bash.py,sha256=jnJKVlHn8np8e0gWd8EO0_qqjMkfQzutSugA_Iol4jE,1585
+agent/core/tools/collection.py,sha256=NuwTn6dXSyznxWodfmFDQwUlxxaGb4oBPym4AEJABSQ,1338
+agent/core/tools/computer.py,sha256=lT_aW3huoYpcM8kffuokELupSz_WZG_qkaW1gITRC58,3892
+agent/core/tools/edit.py,sha256=kv4jTKCM0VXrnoNErf7mT-xlr81-7T8v49_VA9y_L4Y,2005
+agent/core/tools/manager.py,sha256=IRsCXjGc076nncQuyIjODoafnHTDhrf9sP5B4q5Pcdo,1742
+agent/core/types.py,sha256=fSOrbGVjidfrTA1XEy7k5uAcq3Ir1sMNXojs8AS0B1Y,1202
+agent/core/visualization.py,sha256=1DuFF5sSeSf5BRSevBMDxml9-ajl7BQLFm5KBUwMbI8,6573
+agent/providers/__init__.py,sha256=b4tIBAaIB1V7p8V0BWipHVnMhfHH_OuVgP4OWGSHdD8,194
+agent/providers/anthropic/__init__.py,sha256=Mj11IZnVshZ2iHkvg4Z5-jrQIaD1WvzDz2Zk_pMwqIA,149
+agent/providers/anthropic/api/client.py,sha256=IVCntHAlkHFHPb6h4cEpb4wsBESy0wC6IPG8_Yydtqw,13258
+agent/providers/anthropic/api/logging.py,sha256=vHpwkIyOZdkSTVIH4ycbBPd4a_rzhP7Osu1I-Ayouwc,5154
+agent/providers/anthropic/api_handler.py,sha256=pWXcqDs0ruviDhRNRrz5Ac9ZH4yDv6ZlwpeG3a42cDg,5206
+agent/providers/anthropic/callbacks/__init__.py,sha256=PciBb6Z6MKSwfXqDjU3pV_0FS4MOn_Np_A7_skD-6dA,104
+agent/providers/anthropic/callbacks/manager.py,sha256=dRKN7MuBze2dLal0iHDxCKYqMdh_KShSphuwn7zC-c4,1878
+agent/providers/anthropic/loop.py,sha256=jW2PwJ8EBzfFKyD-cy7hKRsz1ZWyw8m-xHLUojsP4qE,20226
+agent/providers/anthropic/prompts.py,sha256=nHFfgPrfvnWrEdVP7EUBGUHAI85D2X9HeZirk9EwncU,1941
+agent/providers/anthropic/response_handler.py,sha256=ZTprV4NTP9Eb9jQ7QgEKZBX0L6rMj5nqBRiE3Zfws8I,8008
+agent/providers/anthropic/tools/__init__.py,sha256=JyZwuVtPUnZwRSZBSCdQv9yxbLCsygm3l8Ywjjt9qTQ,661
+agent/providers/anthropic/tools/base.py,sha256=WnRDbqO25tQzLpS2RU2ZXTLF5wd5IqU7SiyRAglQat4,2752
+agent/providers/anthropic/tools/bash.py,sha256=QODuFjWuHM4GgGTqK2HizSyYqGqQwX70AdwrFiGSp2Q,2218
+agent/providers/anthropic/tools/collection.py,sha256=RBK_6hxfHExR-EOxadiLl0OznmFj07nyIUjFgaYZ6Eo,960
+agent/providers/anthropic/tools/computer.py,sha256=vYni1jDOOgzSSBOJxHcEKxvKUYRp5_nQ-9dmpGdLwm4,25858
+agent/providers/anthropic/tools/edit.py,sha256=EGRP61MDA4Oue1D7Q-_vLpd6LdGbdBA1Z4HSZ66DbmI,13465
+agent/providers/anthropic/tools/manager.py,sha256=yNvgTkfEqnOz5isDF0RxvmBMZB0uh2PipFEH-PUXpoY,2020
+agent/providers/anthropic/tools/run.py,sha256=xhXdnBK1di9muaO44CEirL9hpGy3NmKbjfMpyeVmn8Y,1595
+agent/providers/anthropic/types.py,sha256=SF00kOMC1ui8j9Ah56KaeiR2cL394qCHjFIsBpXxt5w,421
+agent/providers/anthropic/utils.py,sha256=qDp0bFGQhK1dG9U461iaeCiyoVUsksXmD43g9cedRW8,14367
+agent/providers/omni/__init__.py,sha256=59Eqpr3Nc3EE61VirUkfecAnQuGELdg0t44q5tg3SW8,172
+agent/providers/omni/api_handler.py,sha256=7CpD43lYAqTyNKWfrD8XcM9ekbajqKCTH9p0TWtEQyg,1163
+agent/providers/omni/clients/anthropic.py,sha256=nC_lj3UwrLqx9TIew58yxLqKwrH1_LwJD6EqVSEfp3g,3670
+agent/providers/omni/clients/base.py,sha256=zAAgPi0jl3SWPC730R9l79E8bfYPSo39UtCSE-mrK6I,1076
+agent/providers/omni/clients/openai.py,sha256=E4TAXMUFoYTunJETCWCNx5XAc6xutiN4rB6PlVpzC5s,5972
+agent/providers/omni/clients/utils.py,sha256=Ani9CVVBm_J2Dl51WG6p1GVuoI6cq8scISrG0pmQ37o,688
+agent/providers/omni/image_utils.py,sha256=wejhWb36yqedsPnLFTFwk2wth8a6txfVWSg4EaNrRdA,908
+agent/providers/omni/loop.py,sha256=6521KV1hBdxnovzT0wfUcYiRCe7agx2TCC0hgQA3TRw,37459
+agent/providers/omni/parser.py,sha256=REpQwlwvY1z_N8wbMj6GhOeTiiWVWHhVja_LOxgzbks,11734
+agent/providers/omni/prompts.py,sha256=Mupjy0bUwBjcAeLXpE1r1jisYPSlhwsp-IXJKEKrEtw,3779
+agent/providers/omni/tools/__init__.py,sha256=IC1cMEDoR2ljGcNNthzBRF_VtnDbRL5qvHJWErtNp98,774
+agent/providers/omni/tools/base.py,sha256=HiQ8dp9NbFGlGopbE1wxo0ZbujA7bzCGjCg4tl2lnPE,824
+agent/providers/omni/tools/bash.py,sha256=wocYvWwoaVjHba19CVqc3bvwj8_1qwqYjNaPBbMRlWA,2241
+agent/providers/omni/tools/computer.py,sha256=cB5PrhPmk6acKSENIvzw4rdpjeWx4HQHfSxBLGHzGRE,6964
+agent/providers/omni/tools/manager.py,sha256=GVLudHNpOQnl6aA_IOvqAEMDoKW62ozMZuwst6Z1Hco,2094
+agent/providers/omni/types.py,sha256=EoEiqtW98R2ZlhZb1-II4t1Ctf7qCOG6rUn_uQUHNdM,1021
+agent/providers/omni/utils.py,sha256=Ikp6ONL1HO637o3KDtv5yv6q-4uIWAzMSQDvGetWXC8,8724
+agent/providers/openai/__init__.py,sha256=8DS6YNZp42NLCacwXsfRaghyczaOCVovX8TgzXUZf_o,165
+agent/providers/openai/api_handler.py,sha256=zIb9JtfTT9TI4Gd7iyjz5m_MCc9sP5mNXLZQHAr0Rw0,17647
+agent/providers/openai/loop.py,sha256=3gruChABTE6IMQemQPwiER7xk6cmjuHuFssa0KUipAk,18782
+agent/providers/openai/response_handler.py,sha256=K8v_92uSr9R74Y5INY4naeEZZZm35CLIl4h74MBZhsw,7953
+agent/providers/openai/tools/__init__.py,sha256=-KbHMWcd2OVTk5RYQ3ACBEMygwbH-VW6n_98p0lwM4A,344
+agent/providers/openai/tools/base.py,sha256=Np_BC9Cm6TslK99etE9hVTtsBlcEaGhoNCK3NXdB_Lw,2474
+agent/providers/openai/tools/computer.py,sha256=51uRgCXbeqlnKotlnA0-iHkXHHJkqede2GUZfwtGxx4,12271
+agent/providers/openai/tools/manager.py,sha256=-wM641dLf8vcv6QF9x_ViGJeDl2YTuUV93j6u7GBI18,3903
+agent/providers/openai/types.py,sha256=0mFUxeFy23fJhMwc6lAFVXKngg2fJIXkPS5oV284V1M,898
+agent/providers/openai/utils.py,sha256=YeCZWIqOFSeugWoqAS0rhxOKAfL-9uN9nrYSBGBgPdc,3175
+agent/telemetry.py,sha256=pVGxbj0ewnvq4EGj28CydN4a1iOfvZR_XKL3vIOqhOM,390
+cua_agent-0.1.18.dist-info/METADATA,sha256=t09Oyz6kHe2fgkGGLwpb2Cyk27I6TRXiMoCL8qQBgD0,7019
+cua_agent-0.1.18.dist-info/WHEEL,sha256=thaaA2w1JzcGC48WYufAs8nrYZjJm8LqNfnXFOFyCC4,90
+cua_agent-0.1.18.dist-info/entry_points.txt,sha256=6OYgBcLyFCUgeqLgnvMyOJxPCWzgy7se4rLPKtNonMs,34
+cua_agent-0.1.18.dist-info/RECORD,,

agent/README.md

@@ -1,63 +0,0 @@
-# Agent Package Structure
-
-## Overview
-The agent package provides a modular and extensible framework for AI-powered computer agents.
-
-## Directory Structure
-```
-agent/
-├── __init__.py           # Package exports
-├── core/                 # Core functionality
-│   ├── __init__.py
-│   ├── computer_agent.py # Main entry point
-│   └── factory.py        # Provider factory
-├── base/                 # Base implementations
-│   ├── __init__.py
-│   ├── agent.py         # Base agent class
-│   ├── core/            # Core components
-│   │   ├── callbacks.py
-│   │   ├── loop.py
-│   │   └── messages.py
-│   └── tools/           # Tool implementations
-├── providers/           # Provider implementations
-│   ├── __init__.py
-│   ├── anthropic/      # Anthropic provider
-│   │   ├── agent.py
-│   │   ├── loop.py
-│   │   └── tool_manager.py
-│   └── omni/           # Omni provider
-│       ├── agent.py
-│       ├── loop.py
-│       └── tool_manager.py
-└── types/              # Type definitions
-    ├── __init__.py
-    ├── base.py        # Core types
-    ├── messages.py    # Message types
-    ├── tools.py       # Tool types
-    └── providers/     # Provider-specific types
-        ├── anthropic.py
-        └── omni.py
-```
-
-## Key Components
-
-### Core
-- `computer_agent.py`: Main entry point for creating and using agents
-- `factory.py`: Factory for creating provider-specific implementations
-
-### Base
-- `agent.py`: Base agent implementation with shared functionality
-- `core/`: Core components used across providers
-- `tools/`: Shared tool implementations
-
-### Providers
-Each provider follows the same structure:
-- `agent.py`: Provider-specific agent implementation
-- `loop.py`: Provider-specific message loop
-- `tool_manager.py`: Tool management for provider
-
-### Types
-- `base.py`: Core type definitions
-- `messages.py`: Message-related types
-- `tools.py`: Tool-related types
-- `providers/`: Provider-specific type definitions

agent/providers/anthropic/messages/manager.py

@@ -1,112 +0,0 @@
-from dataclasses import dataclass
-from typing import cast
-from anthropic.types.beta import (
-    BetaMessageParam,
-    BetaCacheControlEphemeralParam,
-    BetaToolResultBlockParam,
-)
-
-
-@dataclass
-class ImageRetentionConfig:
-    """Configuration for image retention in messages."""
-
-    num_images_to_keep: int | None = None
-    min_removal_threshold: int = 1
-    enable_caching: bool = True
-
-    def should_retain_images(self) -> bool:
-        """Check if image retention is enabled."""
-        return self.num_images_to_keep is not None and self.num_images_to_keep > 0
-
-
-class MessageManager:
-    """Manages message preparation, including image retention and caching."""
-
-    def __init__(self, image_retention_config: ImageRetentionConfig):
-        """Initialize the message manager.
-
-        Args:
-            image_retention_config: Configuration for image retention
-        """
-        if image_retention_config.min_removal_threshold < 1:
-            raise ValueError("min_removal_threshold must be at least 1")
-        self.image_retention_config = image_retention_config
-
-    def prepare_messages(self, messages: list[BetaMessageParam]) -> list[BetaMessageParam]:
-        """Prepare messages by applying image retention and caching as configured."""
-        if self.image_retention_config.should_retain_images():
-            self._filter_images(messages)
-        if self.image_retention_config.enable_caching:
-            self._inject_caching(messages)
-        return messages
-
-    def _filter_images(self, messages: list[BetaMessageParam]) -> None:
-        """Filter messages to retain only the specified number of most recent images."""
-        tool_result_blocks = cast(
-            list[BetaToolResultBlockParam],
-            [
-                item
-                for message in messages
-                for item in (message["content"] if isinstance(message["content"], list) else [])
-                if isinstance(item, dict) and item.get("type") == "tool_result"
-            ],
-        )
-
-        total_images = sum(
-            1
-            for tool_result in tool_result_blocks
-            for content in tool_result.get("content", [])
-            if isinstance(content, dict) and content.get("type") == "image"
-        )
-
-        images_to_remove = total_images - (self.image_retention_config.num_images_to_keep or 0)
-        # Round down to nearest min_removal_threshold for better cache behavior
-        images_to_remove -= images_to_remove % self.image_retention_config.min_removal_threshold
-
-        # Remove oldest images first
-        for tool_result in tool_result_blocks:
-            if isinstance(tool_result.get("content"), list):
-                new_content = []
-                for content in tool_result.get("content", []):
-                    if isinstance(content, dict) and content.get("type") == "image":
-                        if images_to_remove > 0:
-                            images_to_remove -= 1
-                            continue
-                    new_content.append(content)
-                tool_result["content"] = new_content
-
-    def _inject_caching(self, messages: list[BetaMessageParam]) -> None:
-        """Inject caching control for the most recent turns, limited to 3 blocks max to avoid API errors."""
-        # Anthropic API allows a maximum of 4 blocks with cache_control
-        # We use 3 here to be safe, as the system block may also have cache_control
-        blocks_with_cache_control = 0
-        max_cache_control_blocks = 3
-
-        for message in reversed(messages):
-            if message["role"] == "user" and isinstance(content := message["content"], list):
-                # Only add cache control to the latest message in each turn
-                if blocks_with_cache_control < max_cache_control_blocks:
-                    blocks_with_cache_control += 1
-                    # Add cache control to the last content block only
-                    if content and len(content) > 0:
-                        content[-1]["cache_control"] = BetaCacheControlEphemeralParam(
-                            type="ephemeral"
-                        )
-                else:
-                    # Remove any existing cache control
-                    if content and len(content) > 0:
-                        content[-1].pop("cache_control", None)
-
-        # Ensure we're not exceeding the limit by checking the total
-        if blocks_with_cache_control > max_cache_control_blocks:
-            # If we somehow exceeded the limit, remove excess cache controls
-            excess = blocks_with_cache_control - max_cache_control_blocks
-            for message in messages:
-                if excess <= 0:
-                    break
-
-                if message["role"] == "user" and isinstance(content := message["content"], list):
-                    if content and len(content) > 0 and "cache_control" in content[-1]:
-                        content[-1].pop("cache_control", None)
-                        excess -= 1

agent/providers/omni/callbacks.py

@@ -1,78 +0,0 @@
-"""Omni callback manager implementation."""
-
-import logging
-from typing import Any, Dict, Optional, Set
-
-from ...core.callbacks import BaseCallbackManager, ContentCallback, ToolCallback, APICallback
-from ...types.tools import ToolResult
-
-logger = logging.getLogger(__name__)
-
-class OmniCallbackManager(BaseCallbackManager):
-    """Callback manager for multi-provider support."""
-    
-    def __init__(
-        self,
-        content_callback: ContentCallback,
-        tool_callback: ToolCallback,
-        api_callback: APICallback,
-    ):
-        """Initialize Omni callback manager.
-        
-        Args:
-            content_callback: Callback for content updates
-            tool_callback: Callback for tool execution results
-            api_callback: Callback for API interactions
-        """
-        super().__init__(
-            content_callback=content_callback,
-            tool_callback=tool_callback,
-            api_callback=api_callback
-        )
-        self._active_tools: Set[str] = set()
-    
-    def on_content(self, content: Any) -> None:
-        """Handle content updates.
-        
-        Args:
-            content: Content update data
-        """
-        logger.debug(f"Content update: {content}")
-        self.content_callback(content)
-    
-    def on_tool_result(self, result: ToolResult, tool_id: str) -> None:
-        """Handle tool execution results.
-        
-        Args:
-            result: Tool execution result
-            tool_id: ID of the tool
-        """
-        logger.debug(f"Tool result for {tool_id}: {result}")
-        self.tool_callback(result, tool_id)
-    
-    def on_api_interaction(
-        self,
-        request: Any,
-        response: Any,
-        error: Optional[Exception] = None
-    ) -> None:
-        """Handle API interactions.
-        
-        Args:
-            request: API request data
-            response: API response data
-            error: Optional error that occurred
-        """
-        if error:
-            logger.error(f"API error: {str(error)}")
-        else:
-            logger.debug(f"API interaction - Request: {request}, Response: {response}")
-        self.api_callback(request, response, error)
-    
-    def get_active_tools(self) -> Set[str]:
-        """Get currently active tools.
-        
-        Returns:
-            Set of active tool names
-        """
-        return self._active_tools.copy()

agent/providers/omni/clients/groq.py

@@ -1,101 +0,0 @@
-"""Groq client implementation."""
-
-import os
-import logging
-from typing import Dict, List, Optional, Any, Tuple
-
-from groq import Groq
-import re
-from .utils import is_image_path
-from .base import BaseOmniClient
-
-logger = logging.getLogger(__name__)
-
-
-class GroqClient(BaseOmniClient):
-    """Client for making Groq API calls."""
-
-    def __init__(
-        self,
-        api_key: Optional[str] = None,
-        model: str = "deepseek-r1-distill-llama-70b",
-        max_tokens: int = 4096,
-        temperature: float = 0.6,
-    ):
-        """Initialize Groq client.
-
-        Args:
-            api_key: Groq API key (if not provided, will try to get from env)
-            model: Model name to use
-            max_tokens: Maximum tokens to generate
-            temperature: Temperature for sampling
-        """
-        super().__init__(api_key=api_key, model=model)
-        self.api_key = api_key or os.getenv("GROQ_API_KEY")
-        if not self.api_key:
-            raise ValueError("No Groq API key provided")
-
-        self.max_tokens = max_tokens
-        self.temperature = temperature
-        self.client = Groq(api_key=self.api_key)
-        self.model: str = model  # Add explicit type annotation
-
-    def run_interleaved(
-        self, messages: List[Dict[str, Any]], system: str, max_tokens: Optional[int] = None
-    ) -> tuple[str, int]:
-        """Run interleaved chat completion.
-
-        Args:
-            messages: List of message dicts
-            system: System prompt
-            max_tokens: Optional max tokens override
-
-        Returns:
-            Tuple of (response text, token usage)
-        """
-        # Avoid using system messages for R1
-        final_messages = [{"role": "user", "content": system}]
-
-        # Process messages
-        if isinstance(messages, list):
-            for item in messages:
-                if isinstance(item, dict):
-                    # For dict items, concatenate all text content, ignoring images
-                    text_contents = []
-                    for cnt in item["content"]:
-                        if isinstance(cnt, str):
-                            if not is_image_path(cnt):  # Skip image paths
-                                text_contents.append(cnt)
-                        else:
-                            text_contents.append(str(cnt))
-
-                    if text_contents:  # Only add if there's text content
-                        message = {"role": "user", "content": " ".join(text_contents)}
-                        final_messages.append(message)
-                else:  # str
-                    message = {"role": "user", "content": item}
-                    final_messages.append(message)
-
-        elif isinstance(messages, str):
-            final_messages.append({"role": "user", "content": messages})
-
-        try:
-            completion = self.client.chat.completions.create(  # type: ignore
-                model=self.model,
-                messages=final_messages,  # type: ignore
-                temperature=self.temperature,
-                max_tokens=max_tokens or self.max_tokens,
-                top_p=0.95,
-                stream=False,
-            )
-
-            response = completion.choices[0].message.content
-            final_answer = response.split("</think>\n")[-1] if "</think>" in response else response
-            final_answer = final_answer.replace("<output>", "").replace("</output>", "")
-            token_usage = completion.usage.total_tokens
-
-            return final_answer, token_usage
-
-        except Exception as e:
-            logger.error(f"Error in Groq API call: {e}")
-            raise