Skip to content

Commit 51fd935

Browse files
more changes
1 parent 427fa58 commit 51fd935

12 files changed

Lines changed: 1650 additions & 176 deletions

File tree

FlowVision/FlowVision.csproj

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -168,6 +168,10 @@
168168
<Reference Include="System.Threading.Tasks.Extensions, Version=4.2.4.0, Culture=neutral, PublicKeyToken=cc7b13ffcd2ddd51, processorArchitecture=MSIL">
169169
<HintPath>..\packages\System.Threading.Tasks.Extensions.4.6.3\lib\net462\System.Threading.Tasks.Extensions.dll</HintPath>
170170
</Reference>
171+
<Reference Include="Tesseract">
172+
<HintPath>..\packages\Tesseract.5.2.0\lib\net48\Tesseract.dll</HintPath>
173+
<Private>True</Private>
174+
</Reference>
171175
<Reference Include="Microsoft.ML.OnnxRuntime">
172176
<HintPath>..\packages\Microsoft.ML.OnnxRuntime.Managed.1.21.1\lib\netstandard2.0\Microsoft.ML.OnnxRuntime.dll</HintPath>
173177
<Private>True</Private>
@@ -316,7 +320,22 @@
316320
</ItemGroup>
317321
<Copy SourceFiles="@(OnnxRuntimeNative)" DestinationFolder="$(OutputPath)" SkipUnchangedFiles="true" />
318322
</Target>
323+
<!-- Copy Tesseract native DLLs to output directory -->
324+
<Target Name="CopyTesseractNative" AfterTargets="AfterBuild">
325+
<ItemGroup>
326+
<TesseractNative Include="..\packages\Tesseract.5.2.0\x64\*.dll" />
327+
</ItemGroup>
328+
<Copy SourceFiles="@(TesseractNative)" DestinationFolder="$(OutputPath)" SkipUnchangedFiles="true" />
329+
</Target>
330+
<!-- Copy OmniParser model to output directory -->
331+
<Target Name="CopyOmniParserModel" AfterTargets="AfterBuild">
332+
<ItemGroup>
333+
<OmniParserModel Include="Models\icon_detect.onnx" />
334+
</ItemGroup>
335+
<Copy SourceFiles="@(OmniParserModel)" DestinationFolder="$(OutputPath)\models" SkipUnchangedFiles="true" />
336+
</Target>
319337
<Import Project="..\packages\CefSharp.Common.135.0.170\build\CefSharp.Common.targets" Condition="Exists('..\packages\CefSharp.Common.135.0.170\build\CefSharp.Common.targets')" />
338+
<Import Project="..\packages\Tesseract.5.2.0\build\Tesseract.targets" Condition="Exists('..\packages\Tesseract.5.2.0\build\Tesseract.targets')" />
320339
<Import Project="..\packages\Fody.6.9.2\build\Fody.targets" Condition="Exists('..\packages\Fody.6.9.2\build\Fody.targets')" />
321340
<Import Project="..\packages\Costura.Fody.6.0.0\build\Costura.Fody.targets" Condition="Exists('..\packages\Costura.Fody.6.0.0\build\Costura.Fody.targets')" />
322341
<Import Project="..\packages\Microsoft.Playwright.1.52.0\build\Microsoft.Playwright.targets" Condition="Exists('..\packages\Microsoft.Playwright.1.52.0\build\Microsoft.Playwright.targets')" />

FlowVision/lib/Classes/ai/LMStudioActioner.cs

Lines changed: 13 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -185,11 +185,24 @@ public async Task<string> ExecuteAction(string actionPrompt)
185185

186186
var response = responseBuilder.ToString();
187187

188+
// Log the response for debugging
189+
PluginLogger.LogInfo("LMStudioActioner", "ExecuteAction",
190+
$"AI Response: {(string.IsNullOrEmpty(response) ? "(empty)" : $"{response.Length} chars")}");
191+
188192
// Add assistant response to history
189193
if (!string.IsNullOrEmpty(response))
190194
{
191195
actionerHistory.Add(new ChatMessage(ChatRole.Assistant, response));
192196
}
197+
else
198+
{
199+
// If response is empty, check if there were tool calls and provide a default response
200+
var defaultResponse = "I executed the requested action successfully.";
201+
PluginLogger.LogInfo("LMStudioActioner", "ExecuteAction",
202+
"Empty response from model, using default response");
203+
actionerHistory.Add(new ChatMessage(ChatRole.Assistant, defaultResponse));
204+
return defaultResponse;
205+
}
193206

194207
return response;
195208
}

docs/Getting-Started.md

Lines changed: 49 additions & 56 deletions
Original file line numberDiff line numberDiff line change
@@ -3,94 +3,87 @@ layout: default
33
title: Getting Started
44
---
55

6-
# Getting Started with Recursive Control
6+
# First Flight Checklist
77

8-
This guide will help you get up and running with Recursive Control quickly.
8+
Strap into Mission Control and run your first full-loop automation in under ten minutes.
99

10-
## Your First Commands
10+
## Cue the Agents
1111

12-
Once installed and configured, you can start using natural language commands:
12+
Once the cockpit is configured you can talk in plain-text, mission-style briefs.
1313

14-
### Basic Examples
14+
### Launch Scripts
1515

16-
1. **File Management**
16+
1. **File Ops Circuit**
1717
```
18-
"Open File Explorer and navigate to my Documents folder"
19-
"Create a new folder called Projects on my Desktop"
20-
"Rename all .txt files in this folder to .md"
18+
Open File Explorer and navigate to my Documents folder.”
19+
Create a new folder called Projects on my Desktop.”
20+
Rename all .txt files in this folder to .md.”
2121
```
2222

23-
2. **Application Control**
23+
2. **App Relay**
2424
```
25-
"Open Notepad and type Hello World"
26-
"Launch Chrome and navigate to github.com"
27-
"Open Excel and create a new spreadsheet"
25+
Open Notepad and type Hello World.”
26+
Launch Chrome and navigate to github.com.”
27+
Open Excel and create a new spreadsheet.”
2828
```
2929

30-
3. **Screen Capture**
30+
3. **Vision Probe**
3131
```
32-
"Take a screenshot of the current window"
33-
"Capture the entire screen"
32+
Take a screenshot of the current window.”
33+
Capture the entire screen.”
3434
```
3535

36-
4. **Web Automation**
36+
4. **Browser Drone**
3737
```
38-
"Open a browser and search for AI automation tools"
39-
"Fill out this form with my information"
40-
"Extract data from this webpage"
38+
Open a browser and search for AI automation tools.”
39+
Fill out this form with my information.”
40+
Extract data from this webpage.”
4141
```
4242

43-
## Understanding the Multi-Agent System
43+
## Meet the Crew
4444

45-
Recursive Control uses a sophisticated 3-agent architecture:
45+
- **Hermes (Coordinator)** — interprets intent, sets the heading
46+
- **Daedalus (Planner)** — drafts the maneuver plan step by step
47+
- **Talos (Executor)** — performs every keystroke, click, and command
4648

47-
1. **Coordinator Agent**: Understands your request and determines the best approach
48-
2. **Planner Agent**: Creates a step-by-step plan to accomplish the task
49-
3. **Executor Agent**: Executes the plan using available plugins
49+
Agents talk to you in real-time so you can abort, adjust, or cheer as they work.
5050

51-
This system ensures tasks are completed efficiently and accurately.
51+
## Mission Briefing Tips
5252

53-
## Tips for Better Results
53+
- **Paint the picture** → “Move all PDF files from Downloads to Documents” beats “Do something with files.”
54+
- **Chunk the mission** → Run multi-stage workflows in segments and confirm each leg.
55+
- **Talk human** → Natural language with intent and context works best; no scripting required.
5456

55-
### Be Specific
56-
❌ "Do something with files"
57-
✅ "Move all PDF files from Downloads to Documents folder"
57+
## Plugin Bay at a Glance
5858

59-
### Break Down Complex Tasks
60-
For very complex workflows, break them into smaller steps and verify each step.
59+
- Keyboard + Mouse autopilot
60+
- Command line (CMD + PowerShell)
61+
- Screen capture + annotation
62+
- Window switching + focus
63+
- Playwright browser automation
64+
- Remote control HTTP bridge
6165

62-
### Use Natural Language
63-
You don't need to use technical commands - just describe what you want in plain English.
66+
## Next Flight Plans
6467

65-
## Available Plugins
68+
- Tour the [UI Features Atlas](UI-Features.html)
69+
- Study the [Multi-Agent Architecture](Multi-Agent-Architecture.html)
70+
- Customize personas via [System Prompts Reference](System-Prompts-Reference.html)
71+
- Join the [Discord flight crew](https://discord.gg/mQWsWeHsVU)
6672

67-
Your commands can utilize these built-in plugins:
73+
## First-Time FAQs
6874

69-
- **Keyboard & Mouse**: Automate input and clicks
70-
- **Command Line**: Execute CMD and PowerShell commands
71-
- **Screen Capture**: Take and analyze screenshots
72-
- **Window Management**: Control application windows
73-
- **Web Browser**: Automate websites with Playwright
74-
- **Remote Control**: Accept commands via HTTP API
75+
**How do I know it’s engaged?**
7576

76-
## Next Steps
77+
Watch the live reasoning feed and action timeline.
7778

78-
- Explore the [UI Features](UI-Features.html) guide
79-
- Learn about [Multi-Agent Architecture](Multi-Agent-Architecture.html)
80-
- Check out [System Prompts](System-Prompts-Reference.html) for customization
81-
- Join our [Discord](https://discord.gg/mQWsWeHsVU) for community support
79+
**Something went sideways.**
8280

83-
## Common First-Time Questions
81+
Hit the abort control, then consult the [Troubleshooting Console](Troubleshooting.html).
8482

85-
**Q: How do I know if it's working?**
86-
A: The UI will show the agent's thinking process and actions in real-time.
83+
**Can I reshape its behavior?**
8784

88-
**Q: What if something goes wrong?**
89-
A: You can interrupt execution at any time. Check the [Troubleshooting](Troubleshooting.html) guide for help.
90-
91-
**Q: Can I customize the behavior?**
92-
A: Yes! You can adjust system prompts, enable/disable plugins, and configure various settings.
85+
Absolutely. Tweak prompts, toggle plugins, and save profiles.
9386

9487
---
9588

96-
Ready to dive deeper? Check out our [advanced documentation](Multi-Agent-Architecture.html) or join the [community](https://discord.gg/mQWsWeHsVU)!
89+
Ready for more? Dive into [advanced documentation](Multi-Agent-Architecture.html) or sync with the [community](https://discord.gg/mQWsWeHsVU).

docs/Installation.md

Lines changed: 31 additions & 32 deletions
Original file line numberDiff line numberDiff line change
@@ -3,46 +3,45 @@ layout: default
33
title: Installation
44
---
55

6-
# Installation Guide
6+
# Installation Capsule
77

8-
Get Recursive Control up and running on your Windows system.
8+
Your mission dock for landing Recursive Control on Windows. Choose your payload, confirm dependencies, and ignite the thrusters.
99

10-
## System Requirements
10+
## Flight Readiness Checklist
1111

12-
### Minimum Requirements
12+
### Baseline Specs
1313
- **Operating System**: Windows 10 or Windows 11
1414
- **.NET Framework**: 4.8 or later
1515
- **RAM**: 4 GB minimum (8 GB recommended)
1616
- **Disk Space**: 500 MB for application files
1717

18-
### Additional Requirements
18+
### Network & Auth
1919
- Internet connection for AI model API access
2020
- API key for your preferred AI provider (OpenAI, Azure OpenAI, Anthropic, Google, etc.)
2121

22-
## Installation Steps
22+
## Deploy Options
2323

24-
### Option 1: Download Pre-built Release (Recommended)
24+
### Rapid Drop (Recommended)
2525

26-
1. **Download the Latest Release**
27-
- Visit the [Releases page](https://github.com/flowdevs-io/Recursive-Control/releases)
28-
- Download the latest `recursivecontrol.zip` or installer
29-
- Extract to your preferred location
26+
1. **Pull the latest build**
27+
- Hop to the [Releases hangar](https://github.com/flowdevs-io/Recursive-Control/releases)
28+
- Snag the newest `recursivecontrol.zip` payload
29+
- Extract anywhere friendly (no admin elevation required)
3030

31-
2. **Run the Application**
32-
- Double-click `recursivecontrol.exe`
33-
- The application will launch and prompt for initial setup
31+
2. **Boot the cockpit**
32+
- Launch `recursivecontrol.exe`
33+
- First boot unlocks the setup co-pilot
3434

35-
3. **Configure Your AI Provider**
36-
- Click the settings/configuration button
37-
- Select your AI provider (OpenAI, Azure, Anthropic, etc.)
38-
- Enter your API key
39-
- Choose your preferred model
35+
3. **Wire your pilot**
36+
- Open Settings → Providers
37+
- Pick your model stack (OpenAI, Azure, Claude, Gemini, LM Studio…)
38+
- Drop in your API credentials
4039

41-
4. **Test the Installation**
42-
- Try a simple command like "What can you do?"
43-
- Verify the AI responds correctly
40+
4. **Ping the tower**
41+
- Ask "What can you do?"
42+
- Confirm you see agent chatter + completion
4443

45-
### Option 2: Build from Source
44+
### Source Build (Engineers’ Track)
4645

4746
For developers who want to build from source:
4847

@@ -63,9 +62,9 @@ dotnet build
6362
dotnet run --project FlowVision
6463
```
6564

66-
## Initial Configuration
65+
## Configure Your Pilot
6766

68-
### Setting Up Your AI Provider
67+
### OpenAI
6968

7069
#### OpenAI
7170
1. Get your API key from [OpenAI Platform](https://platform.openai.com)
@@ -97,7 +96,7 @@ dotnet run --project FlowVision
9796
- Provider: LM Studio
9897
- Endpoint: http://localhost:1234 (or your configured port)
9998

100-
### Plugin Configuration
99+
### Plugin Bay
101100

102101
Enable or disable plugins based on your needs:
103102

@@ -110,7 +109,7 @@ Enable or disable plugins based on your needs:
110109
- ⚠️ Playwright (requires additional setup)
111110
- ⚠️ Remote Control (enable for HTTP API)
112111

113-
## Verifying Installation
112+
## System Checks
114113

115114
Run these test commands to verify everything works:
116115

@@ -121,17 +120,17 @@ Run these test commands to verify everything works:
121120

122121
If all tests pass, you're ready to go!
123122

124-
## Troubleshooting Installation Issues
123+
## Troubleshooting Bay
125124

126-
### .NET Framework Not Found
125+
### .NET Framework Missing
127126
- Download and install [.NET Framework 4.8](https://dotnet.microsoft.com/download/dotnet-framework/net48)
128127

129128
### API Key Errors
130129
- Verify your API key is correct
131130
- Check that your API provider account has credits/active subscription
132131
- Ensure internet connection is working
133132

134-
### Application Won't Start
133+
### Application Wont Start
135134
- Run as Administrator
136135
- Check Windows Event Viewer for error details
137136
- Verify all dependencies are installed
@@ -141,13 +140,13 @@ If all tests pass, you're ready to go!
141140
- Increase available RAM
142141
- Consider using a lighter AI model
143142

144-
## Next Steps
143+
## Next Flight Plans
145144

146145
- Continue to [Getting Started](Getting-Started.html) guide
147146
- Explore [UI Features](UI-Features.html)
148147
- Join our [Discord community](https://discord.gg/mQWsWeHsVU)
149148

150-
## Uninstallation
149+
## Uninstall Playbook
151150

152151
To remove Recursive Control:
153152
1. Delete the application folder

docs/_config.yml

Lines changed: 6 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -6,15 +6,19 @@ description: AI-Powered Computer Control for Windows
66
baseurl: "/Recursive-Control"
77
url: "https://flowdevs-io.github.io"
88

9-
# Theme (GitHub Pages supported themes)
10-
remote_theme: pages-themes/cayman@v0.2.0
9+
theme: null
1110

1211
# Plugins (GitHub Pages whitelist)
1312
plugins:
1413
- jekyll-remote-theme
1514
- jekyll-seo-tag
1615
- jekyll-sitemap
1716

17+
# Sass pipeline
18+
sass:
19+
sass_dir: _sass
20+
style: compressed
21+
1822
# Markdown settings
1923
markdown: kramdown
2024
kramdown:

0 commit comments

Comments
 (0)