droidrun 0.3.5__tar.gz → 0.3.7__tar.gz

{droidrun-0.3.5 → droidrun-0.3.7}/.github/workflows/bounty.yml

@@ -64,7 +64,7 @@ jobs:
             eligible)      OPT_NAME="📝 Eligible"      ;;
             bounty-official) OPT_NAME="💰 Bounty" ;;
             claimed)       OPT_NAME="🛠️ In Progress"   ;;
-            *) echo "No matching status for $LABEL"; exit 0 ;;
+            *) echo "No matching status for $LABEL"; exit 78 ;;
           esac
 
           # extract from JSON map
@@ -131,4 +131,4 @@ jobs:
           -f proj="${PROJECT_ID}" \
           -f item="${ITEM_ID}" \
           -f field="${STATUS_FIELD_ID}" \
-          -f opt="${OPTION_ID}"
+          -f opt="${OPTION_ID}"

{droidrun-0.3.5 → droidrun-0.3.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: droidrun
-Version: 0.3.5
+Version: 0.3.7
 Summary: A framework for controlling Android devices through LLM agents
 Project-URL: Homepage, https://github.com/droidrun/droidrun
 Project-URL: Bug Tracker, https://github.com/droidrun/droidrun/issues
@@ -26,32 +26,31 @@ Classifier: Topic :: Software Development :: Testing :: Acceptance
 Classifier: Topic :: System :: Emulators
 Classifier: Topic :: Utilities
 Requires-Python: >=3.11
-Requires-Dist: adbutils==2.10.0
-Requires-Dist: aiofiles>=23.0.0
-Requires-Dist: anthropic>=0.7.0
+Requires-Dist: adbutils>=2.10.2
 Requires-Dist: apkutils==2.0.0
-Requires-Dist: arize-phoenix
-Requires-Dist: click>=8.1.0
-Requires-Dist: llama-index
-Requires-Dist: llama-index-callbacks-arize-phoenix
-Requires-Dist: llama-index-llms-anthropic
-Requires-Dist: llama-index-llms-deepseek
-Requires-Dist: llama-index-llms-google-genai
-Requires-Dist: llama-index-llms-ollama
-Requires-Dist: llama-index-llms-openai
-Requires-Dist: llama-index-llms-openai-like
-Requires-Dist: openai>=1.0.0
-Requires-Dist: pillow>=10.0.0
-Requires-Dist: posthog==6.0.2
-Requires-Dist: pydantic>=2.0.0
-Requires-Dist: python-dotenv>=1.0.0
-Requires-Dist: rich>=13.0.0
+Requires-Dist: llama-index>=0.13.6
+Requires-Dist: posthog>=6.7.4
+Requires-Dist: pydantic>=2.11.7
+Requires-Dist: rich>=14.1.0
+Provides-Extra: anthropic
+Requires-Dist: anthropic>=0.67.0; extra == 'anthropic'
+Requires-Dist: llama-index-llms-anthropic>=0.8.6; extra == 'anthropic'
+Provides-Extra: deepseek
+Requires-Dist: llama-index-llms-deepseek>=0.2.1; extra == 'deepseek'
 Provides-Extra: dev
-Requires-Dist: bandit>=1.7.0; extra == 'dev'
+Requires-Dist: bandit>=1.8.6; extra == 'dev'
 Requires-Dist: black>=23.0.0; extra == 'dev'
 Requires-Dist: mypy>=1.0.0; extra == 'dev'
-Requires-Dist: ruff>=0.1.0; extra == 'dev'
-Requires-Dist: safety>=2.0.0; extra == 'dev'
+Requires-Dist: ruff>=0.13.0; extra == 'dev'
+Requires-Dist: safety>=3.2.11; extra == 'dev'
+Provides-Extra: google
+Requires-Dist: llama-index-llms-google-genai>=0.3.1; extra == 'google'
+Provides-Extra: ollama
+Requires-Dist: llama-index-llms-ollama>=0.7.2; extra == 'ollama'
+Provides-Extra: openai
+Requires-Dist: llama-index-llms-openai-like>=0.5.1; extra == 'openai'
+Requires-Dist: llama-index-llms-openai>=0.5.6; extra == 'openai'
+Requires-Dist: openai>=1.107.1; extra == 'openai'
 Description-Content-Type: text/markdown
 
 <picture>
@@ -89,7 +88,7 @@ DroidRun is a powerful framework for controlling Android and iOS devices through
 ## 📦 Installation
 
 ```bash
-pip install droidrun
+pip install droidrun[google,anthropic,openai,deepseek,ollama,dev]
 ```
 
 ## 🚀 Quickstart

{droidrun-0.3.5 → droidrun-0.3.7}/README.md

@@ -33,7 +33,7 @@ DroidRun is a powerful framework for controlling Android and iOS devices through
 ## 📦 Installation
 
 ```bash
-pip install droidrun
+pip install droidrun[google,anthropic,openai,deepseek,ollama,dev]
 ```
 
 ## 🚀 Quickstart

{droidrun-0.3.5 → droidrun-0.3.7}/docs/docs.json

@@ -14,7 +14,7 @@
         "tab": "Framework",
         "versions": [
           {
-            "version": "0.3.3",
+            "version": "0.3.6",
             "groups": [
               {
                 "group": "Introduction",

{droidrun-0.3.5 → droidrun-0.3.7}/docs/v3/guides/cli.mdx

@@ -11,9 +11,9 @@ DroidRun lets you control Android devices using natural language and LLM agents.
 ## Prerequisites
 
 <Steps>
-    <Step title="Install DroidRun and its dependencies.">
+    <Step title="Install DroidRun and its dependencies. Choose which ever provider you'd like to use.">
        ```sh 
-       pip install droidrun
+       pip install droidrun[google,anthropic,openai,deepseek,ollama,dev]
        ```
     </Step>
     <Step title="Ensure your Android device is connected and the DroidRun Portal is installed">
@@ -27,11 +27,11 @@ DroidRun lets you control Android devices using natural language and LLM agents.
        droidrun ping
        ```
     </Step>
-    <Step title="Install the required LlamaIndex LLM integrations for your provider">
-    ```sh
-    pip install llama-index-llms-openai llama-index-llms-ollama llama-index-llms-gemini
-    ```
-  </Step>
+    <Step title="If you want to use a provider thats not included with our extras, install the required LlamaIndex LLM integrations">
+      ```sh
+      pip install llama-index-llms-openrouter
+      ```
+    </Step>
 </Steps>
 ---
 

{droidrun-0.3.5 → droidrun-0.3.7}/docs/v3/guides/gemini.mdx

@@ -32,7 +32,7 @@ Make sure you've set up and enabled the Droidrun Portal.
 ## 2. Install Required Python Packages
 
 ```sh
-pip install droidrun llama-index-llms-google-genai
+pip install droidrun[google]
 ```
 
 ## 3. Example: Using Droidrun with Gemini LLM

{droidrun-0.3.5 → droidrun-0.3.7}/docs/v3/guides/ollama.mdx

@@ -47,7 +47,7 @@ ollama pull llama4
 Make sure you have the required Python packages:
 
 ```sh
-pip install droidrun llama-index-llms-ollama
+pip install droidrun[ollama]
 ```
 
 ## 3. Example: Using Droidrun with Ollama LLM

{droidrun-0.3.5 → droidrun-0.3.7}/docs/v3/guides/openailike.mdx

@@ -36,7 +36,7 @@ Get your API key for the provider you've choosen
 ## 2. Install the required Python packages:
 
 ```sh
-pip install droidrun llama-index-llms-openai-like
+pip install droidrun[openai]
 ```
 
 ## 3. Example: Using Droidrun with OpenAI-like LLM

{droidrun-0.3.5 → droidrun-0.3.7}/docs/v3/quickstart.mdx

@@ -26,8 +26,9 @@ Before installing DroidRun, ensure you have:
    - Connected via USB or on the same network (for wireless debugging)
 
 ### Install from PyPI
+Choose which ever provider you'd like to use. If you encounter dependency resolution issues use [`uv`](https://docs.astral.sh/uv/getting-started/installation/).
 ```bash
-pip install droidrun
+pip install droidrun[google,anthropic,openai,deepseek,ollama,dev]
 ```
 
 ### Setup the Portal APK
@@ -90,5 +91,5 @@ Now that you've got DroidRun running, you can:
 
 - Learn about the [Agent](/v3/concepts/agent)
 - See supported [LLM providers](/v3/concepts/models)
-- Discover [Android interactions](/v3/concepts/android-control)
-- Learn about the [Portal App](/v3/concepts/portal-app) 
+- Discover [Android interactions](/v3/concepts/android-tools)
+- Learn about the [Portal App](/v3/concepts/portal-app) 

{droidrun-0.3.5 → droidrun-0.3.7}/docs/v3/sdk/droid-agent.mdx

@@ -33,7 +33,7 @@ def __init__(
     reflection: bool = False,
     enable_tracing: bool = False,
     debug: bool = False,
-    save_trajectories: str = "none",
+    save_trajectories: str = "none",  
     excluded_tools: List[str] = None,
     *args,
     **kwargs

{droidrun-0.3.5 → droidrun-0.3.7}/droidrun/agent/codeact/codeact_agent.py

@@ -18,7 +18,8 @@ from droidrun.agent.codeact.events import (
     TaskThinkingEvent,
     EpisodicMemoryEvent,
 )
-from droidrun.agent.common.events import ScreenshotEvent
+from droidrun.agent.common.events import ScreenshotEvent, RecordUIStateEvent
+from droidrun.agent.usage import get_usage_from_response
 from droidrun.agent.utils import chat_utils
 from droidrun.agent.utils.executer import SimpleCodeExecutor
 from droidrun.agent.codeact.prompts import (
@@ -182,6 +183,7 @@ class CodeActAgent(Workflow):
                 try:
                     state = self.tools.get_state()
                     await ctx.set("ui_state", state["a11y_tree"])
+                    ctx.write_event_to_stream(RecordUIStateEvent(ui_state=state["a11y_tree"]))
                     chat_history = await chat_utils.add_ui_text_block(
                         state["a11y_tree"], chat_history
                     )
@@ -202,11 +204,17 @@ class CodeActAgent(Workflow):
                 success=False, reason="LLM response is None. This is a critical error."
             )
 
+        try:
+            usage = get_usage_from_response(self.llm.class_name(), response)
+        except Exception as e:
+            logger.warning(f"Could not get llm usage from response: {e}")
+            usage = None
+
         await self.chat_memory.aput(response.message)
 
         code, thoughts = chat_utils.extract_code_and_thought(response.message.content)
 
-        event = TaskThinkingEvent(thoughts=thoughts, code=code)
+        event = TaskThinkingEvent(thoughts=thoughts, code=code, usage=usage)
         ctx.write_event_to_stream(event)
         return event
 
@@ -255,6 +263,10 @@ class CodeActAgent(Workflow):
             for screenshot in screenshots[:-1]: # the last screenshot will be captured by next step
                 ctx.write_event_to_stream(ScreenshotEvent(screenshot=screenshot))
 
+            ui_states = result['ui_states']
+            for ui_state in ui_states[:-1]:
+                ctx.write_event_to_stream(RecordUIStateEvent(ui_state=ui_state['a11y_tree']))
+
             if self.tools.finished == True:
                 logger.debug("  - Task completed.")
                 event = TaskEndEvent(
@@ -311,7 +323,8 @@ class CodeActAgent(Workflow):
         await ctx.set("chat_memory", self.chat_memory)
         
         # Add final state observation to episodic memory
-        await self._add_final_state_observation(ctx)
+        if self.vision:
+            await self._add_final_state_observation(ctx)
         
         result = {}
         result.update(

{droidrun-0.3.5 → droidrun-0.3.7}/droidrun/agent/codeact/events.py

@@ -1,6 +1,8 @@
 from llama_index.core.llms import ChatMessage
 from llama_index.core.workflow import Event
 from typing import Optional
+
+from droidrun.agent.usage import UsageResult
 from ..context.episodic_memory import EpisodicMemory
 
 class TaskInputEvent(Event):
@@ -11,6 +13,7 @@ class TaskInputEvent(Event):
 class TaskThinkingEvent(Event):
     thoughts: Optional[str] = None
     code: Optional[str] = None  
+    usage: Optional[UsageResult] = None
 
 class TaskExecutionEvent(Event):
     code: str

{droidrun-0.3.5 → droidrun-0.3.7}/droidrun/agent/common/events.py

@@ -1,4 +1,5 @@
 from llama_index.core.workflow import Event
+from typing import Dict, Any
 
 class ScreenshotEvent(Event):
     screenshot: bytes
@@ -44,4 +45,7 @@ class KeyPressActionEvent(MacroEvent):
 class StartAppEvent(MacroEvent):
     """"Event for starting an app"""
     package: str
-    activity: str = None
+    activity: str = None
+
+class RecordUIStateEvent(Event):
+    ui_state: list[Dict[str, Any]]