Spaces:
Build error
Build error
Delete docs
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- docs/DOC_STYLE_GUIDE.md +0 -67
- docs/docs.json +0 -204
- docs/favicon.svg +0 -19
- docs/index.mdx +0 -16
- docs/logo-square.png +0 -3
- docs/logo/dark.svg +0 -29
- docs/logo/light.svg +0 -29
- docs/openapi.json +0 -2091
- docs/static/img/backend_architecture.png +0 -3
- docs/static/img/backend_architecture.puml +0 -201
- docs/static/img/backend_architecture.svg +0 -0
- docs/static/img/connect-repo.png +0 -0
- docs/static/img/docs/api-key-generation.png +0 -0
- docs/static/img/logo-square.png +0 -3
- docs/static/img/logo.png +0 -0
- docs/static/img/oh-features.png +0 -3
- docs/static/img/results.png +0 -3
- docs/static/img/screenshot.png +0 -3
- docs/static/img/system_architecture.png +0 -0
- docs/static/img/system_architecture.puml +0 -67
- docs/static/img/system_architecture.svg +0 -1
- docs/static/img/system_architecture_overview.png +0 -3
- docs/static/img/teaser.mp4 +0 -3
- docs/usage/about.mdx +0 -30
- docs/usage/agents.mdx +0 -26
- docs/usage/architecture/backend.mdx +0 -56
- docs/usage/architecture/runtime.mdx +0 -136
- docs/usage/cloud/cloud-api.mdx +0 -176
- docs/usage/cloud/cloud-ui.mdx +0 -36
- docs/usage/cloud/github-installation.mdx +0 -71
- docs/usage/cloud/gitlab-installation.mdx +0 -25
- docs/usage/cloud/openhands-cloud.mdx +0 -26
- docs/usage/configuration-options.mdx +0 -413
- docs/usage/feedback.mdx +0 -50
- docs/usage/getting-started.mdx +0 -100
- docs/usage/how-to/cli-mode.mdx +0 -105
- docs/usage/how-to/custom-sandbox-guide.mdx +0 -100
- docs/usage/how-to/debugging.mdx +0 -73
- docs/usage/how-to/development-overview.mdx +0 -71
- docs/usage/how-to/evaluation-harness.mdx +0 -280
- docs/usage/how-to/github-action.mdx +0 -53
- docs/usage/how-to/gui-mode.mdx +0 -143
- docs/usage/how-to/headless-mode.mdx +0 -57
- docs/usage/how-to/websocket-connection.mdx +0 -179
- docs/usage/installation.mdx +0 -19
- docs/usage/key-features.mdx +0 -32
- docs/usage/llms/azure-llms.mdx +0 -42
- docs/usage/llms/custom-llm-configs.mdx +0 -137
- docs/usage/llms/google-llms.mdx +0 -30
- docs/usage/llms/groq.mdx +0 -23
docs/DOC_STYLE_GUIDE.md
DELETED
|
@@ -1,67 +0,0 @@
|
|
| 1 |
-
# Documentation Style Guide
|
| 2 |
-
|
| 3 |
-
## General Writing Principles
|
| 4 |
-
|
| 5 |
-
- **Clarity & Conciseness**: Always prioritize clarity and brevity. Avoid unnecessary jargon or overly complex explanations.
|
| 6 |
-
Keep sentences short and to the point.
|
| 7 |
-
- **Gradual Complexity**: Start with the simplest, most basic setup, and then gradually introduce more advanced
|
| 8 |
-
concepts and configurations.
|
| 9 |
-
|
| 10 |
-
## Formatting Guidelines
|
| 11 |
-
|
| 12 |
-
### Headers
|
| 13 |
-
|
| 14 |
-
Use **Title Case** for the first and second level headers.
|
| 15 |
-
|
| 16 |
-
Example:
|
| 17 |
-
- **Basic Usage**
|
| 18 |
-
- **Advanced Configuration Options**
|
| 19 |
-
|
| 20 |
-
### Lists
|
| 21 |
-
|
| 22 |
-
When listing items or options, use bullet points to enhance readability.
|
| 23 |
-
|
| 24 |
-
Example:
|
| 25 |
-
- Option A
|
| 26 |
-
- Option B
|
| 27 |
-
- Option C
|
| 28 |
-
|
| 29 |
-
### Procedures
|
| 30 |
-
|
| 31 |
-
For instructions or processes that need to be followed in a specific order, use numbered steps.
|
| 32 |
-
|
| 33 |
-
Example:
|
| 34 |
-
1. Step one: Do this.
|
| 35 |
-
- First this sub step.
|
| 36 |
-
- Then this sub step.
|
| 37 |
-
2. Step two: Complete this action.
|
| 38 |
-
3. Step three: Verify the result.
|
| 39 |
-
|
| 40 |
-
### Code Blocks
|
| 41 |
-
|
| 42 |
-
* Use code blocks for multi-line inputs, outputs, commands and code samples.
|
| 43 |
-
|
| 44 |
-
Example:
|
| 45 |
-
```bash
|
| 46 |
-
docker run -it \
|
| 47 |
-
-e THIS=this \
|
| 48 |
-
-e THAT=that
|
| 49 |
-
...
|
| 50 |
-
```
|
| 51 |
-
|
| 52 |
-
### Use of Note and Warning
|
| 53 |
-
|
| 54 |
-
When adding a note or warning, use the built-in note and warning syntax.
|
| 55 |
-
|
| 56 |
-
Example:
|
| 57 |
-
<Note>
|
| 58 |
-
This section is for advanced users only.
|
| 59 |
-
</Note>
|
| 60 |
-
|
| 61 |
-
### Referring to UI Elements
|
| 62 |
-
|
| 63 |
-
When referencing UI elements, use ``.
|
| 64 |
-
|
| 65 |
-
Example:
|
| 66 |
-
1. Toggle the `Advanced` option
|
| 67 |
-
2. Enter your model in the `Custom Model` textbox.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/docs.json
DELETED
|
@@ -1,204 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"$schema": "https://mintlify.com/docs.json",
|
| 3 |
-
"theme": "mint",
|
| 4 |
-
"name": "All Hands Docs",
|
| 5 |
-
"colors": {
|
| 6 |
-
"primary": "#99873c",
|
| 7 |
-
"light": "#ffe165",
|
| 8 |
-
"dark": "#ffe165"
|
| 9 |
-
},
|
| 10 |
-
"background": {
|
| 11 |
-
"color": {
|
| 12 |
-
"light": "#f7f3ee",
|
| 13 |
-
"dark": "#0B0D0E"
|
| 14 |
-
}
|
| 15 |
-
},
|
| 16 |
-
"appearance": {
|
| 17 |
-
"default": "light"
|
| 18 |
-
},
|
| 19 |
-
"favicon": "/logo-square.png",
|
| 20 |
-
"navigation": {
|
| 21 |
-
"tabs": [
|
| 22 |
-
{
|
| 23 |
-
"tab": "Docs",
|
| 24 |
-
"pages": [
|
| 25 |
-
"index",
|
| 26 |
-
"usage/installation",
|
| 27 |
-
"usage/getting-started",
|
| 28 |
-
"usage/key-features",
|
| 29 |
-
{
|
| 30 |
-
"group": "OpenHands Cloud",
|
| 31 |
-
"pages": [
|
| 32 |
-
"usage/cloud/openhands-cloud",
|
| 33 |
-
{
|
| 34 |
-
"group": "Integrations",
|
| 35 |
-
"pages": [
|
| 36 |
-
"usage/cloud/github-installation",
|
| 37 |
-
"usage/cloud/gitlab-installation"
|
| 38 |
-
]
|
| 39 |
-
},
|
| 40 |
-
"usage/cloud/cloud-ui",
|
| 41 |
-
"usage/cloud/cloud-api"
|
| 42 |
-
]
|
| 43 |
-
},
|
| 44 |
-
{
|
| 45 |
-
"group": "Running OpenHands Locally",
|
| 46 |
-
"pages": [
|
| 47 |
-
"usage/local-setup",
|
| 48 |
-
"usage/how-to/gui-mode",
|
| 49 |
-
"usage/how-to/cli-mode",
|
| 50 |
-
"usage/how-to/headless-mode",
|
| 51 |
-
"usage/how-to/github-action"
|
| 52 |
-
]
|
| 53 |
-
},
|
| 54 |
-
{
|
| 55 |
-
"group": "Customization",
|
| 56 |
-
"pages": [
|
| 57 |
-
"usage/prompting/prompting-best-practices",
|
| 58 |
-
"usage/prompting/repository",
|
| 59 |
-
{
|
| 60 |
-
"group": "Microagents",
|
| 61 |
-
"pages": [
|
| 62 |
-
"usage/prompting/microagents-overview",
|
| 63 |
-
"usage/prompting/microagents-repo",
|
| 64 |
-
"usage/prompting/microagents-keyword",
|
| 65 |
-
"usage/prompting/microagents-org",
|
| 66 |
-
"usage/prompting/microagents-public"
|
| 67 |
-
]
|
| 68 |
-
}
|
| 69 |
-
]
|
| 70 |
-
},
|
| 71 |
-
{
|
| 72 |
-
"group": "Advanced Configuration",
|
| 73 |
-
"pages": [
|
| 74 |
-
{
|
| 75 |
-
"group": "LLM Configuration",
|
| 76 |
-
"pages": [
|
| 77 |
-
"usage/llms/llms",
|
| 78 |
-
{
|
| 79 |
-
"group": "Providers",
|
| 80 |
-
"pages": [
|
| 81 |
-
"usage/llms/azure-llms",
|
| 82 |
-
"usage/llms/google-llms",
|
| 83 |
-
"usage/llms/groq",
|
| 84 |
-
"usage/llms/local-llms",
|
| 85 |
-
"usage/llms/litellm-proxy",
|
| 86 |
-
"usage/llms/openai-llms",
|
| 87 |
-
"usage/llms/openrouter"
|
| 88 |
-
]
|
| 89 |
-
}
|
| 90 |
-
]
|
| 91 |
-
},
|
| 92 |
-
{
|
| 93 |
-
"group": "Runtime Configuration",
|
| 94 |
-
"pages": [
|
| 95 |
-
"usage/runtimes/overview",
|
| 96 |
-
{
|
| 97 |
-
"group": "Providers",
|
| 98 |
-
"pages": [
|
| 99 |
-
"usage/runtimes/docker",
|
| 100 |
-
"usage/runtimes/remote",
|
| 101 |
-
"usage/runtimes/local",
|
| 102 |
-
{
|
| 103 |
-
"group": "Third-Party Providers",
|
| 104 |
-
"pages": [
|
| 105 |
-
"usage/runtimes/modal",
|
| 106 |
-
"usage/runtimes/daytona",
|
| 107 |
-
"usage/runtimes/runloop",
|
| 108 |
-
"usage/runtimes/e2b"
|
| 109 |
-
]
|
| 110 |
-
}
|
| 111 |
-
]
|
| 112 |
-
}
|
| 113 |
-
]
|
| 114 |
-
},
|
| 115 |
-
"usage/configuration-options",
|
| 116 |
-
"usage/how-to/custom-sandbox-guide",
|
| 117 |
-
"usage/search-engine-setup",
|
| 118 |
-
"usage/mcp"
|
| 119 |
-
]
|
| 120 |
-
},
|
| 121 |
-
{
|
| 122 |
-
"group": "Troubleshooting & Feedback",
|
| 123 |
-
"pages": [
|
| 124 |
-
"usage/troubleshooting/troubleshooting",
|
| 125 |
-
"usage/feedback"
|
| 126 |
-
]
|
| 127 |
-
},
|
| 128 |
-
{
|
| 129 |
-
"group": "OpenHands Developers",
|
| 130 |
-
"pages": [
|
| 131 |
-
"usage/how-to/development-overview",
|
| 132 |
-
{
|
| 133 |
-
"group": "Architecture",
|
| 134 |
-
"pages": [
|
| 135 |
-
"usage/architecture/backend",
|
| 136 |
-
"usage/architecture/runtime"
|
| 137 |
-
]
|
| 138 |
-
},
|
| 139 |
-
"usage/how-to/debugging",
|
| 140 |
-
"usage/how-to/evaluation-harness",
|
| 141 |
-
"usage/how-to/websocket-connection"
|
| 142 |
-
]
|
| 143 |
-
}
|
| 144 |
-
]
|
| 145 |
-
},
|
| 146 |
-
{
|
| 147 |
-
"tab": "API Reference",
|
| 148 |
-
"openapi": "/openapi.json"
|
| 149 |
-
}
|
| 150 |
-
],
|
| 151 |
-
"global": {
|
| 152 |
-
"anchors": [
|
| 153 |
-
{
|
| 154 |
-
"anchor": "Company",
|
| 155 |
-
"href": "https://www.all-hands.dev/",
|
| 156 |
-
"icon": "house"
|
| 157 |
-
},
|
| 158 |
-
{
|
| 159 |
-
"anchor": "Blog",
|
| 160 |
-
"href": "https://www.all-hands.dev/blog",
|
| 161 |
-
"icon": "newspaper"
|
| 162 |
-
},
|
| 163 |
-
{
|
| 164 |
-
"anchor": "OpenHands Cloud",
|
| 165 |
-
"href": "https://app.all-hands.dev",
|
| 166 |
-
"icon": "cloud"
|
| 167 |
-
}
|
| 168 |
-
]
|
| 169 |
-
}
|
| 170 |
-
},
|
| 171 |
-
"logo": {
|
| 172 |
-
"light": "/logo/light.svg",
|
| 173 |
-
"dark": "/logo/dark.svg"
|
| 174 |
-
},
|
| 175 |
-
"navbar": {
|
| 176 |
-
"links": [
|
| 177 |
-
],
|
| 178 |
-
"primary": {
|
| 179 |
-
"type": "github",
|
| 180 |
-
"href": "https://github.com/All-Hands-AI/OpenHands"
|
| 181 |
-
}
|
| 182 |
-
},
|
| 183 |
-
"footer": {
|
| 184 |
-
"socials": {
|
| 185 |
-
"slack": "https://join.slack.com/t/openhands-ai/shared_invite/zt-34zm4j0gj-Qz5kRHoca8DFCbqXPS~f_A",
|
| 186 |
-
"github": "https://github.com/All-Hands-AI/OpenHands",
|
| 187 |
-
"discord": "https://discord.gg/ESHStjSjD4"
|
| 188 |
-
}
|
| 189 |
-
},
|
| 190 |
-
"contextual": {
|
| 191 |
-
"options": [
|
| 192 |
-
"copy",
|
| 193 |
-
"view",
|
| 194 |
-
"chatgpt",
|
| 195 |
-
"claude"
|
| 196 |
-
]
|
| 197 |
-
},
|
| 198 |
-
"redirects": [
|
| 199 |
-
{
|
| 200 |
-
"source": "/modules/:slug*",
|
| 201 |
-
"destination": "/:slug*"
|
| 202 |
-
}
|
| 203 |
-
]
|
| 204 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/favicon.svg
DELETED
docs/index.mdx
DELETED
|
@@ -1,16 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Introduction
|
| 3 |
-
description: OpenHands - Code Less, Make More
|
| 4 |
-
icon: book-open
|
| 5 |
-
mode: wide
|
| 6 |
-
---
|
| 7 |
-
Use AI to tackle the toil in your backlog. Our agents have all the same tools as a human developer: they can modify code, run commands, browse the web, call APIs, and yes-even copy code snippets from StackOverflow.
|
| 8 |
-
|
| 9 |
-
<iframe
|
| 10 |
-
className="w-full aspect-video"
|
| 11 |
-
src="https://www.youtube.com/embed/oB4JR98KRAA"
|
| 12 |
-
title="YouTube video player"
|
| 13 |
-
frameborder="0"
|
| 14 |
-
allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
|
| 15 |
-
allowfullscreen
|
| 16 |
-
></iframe>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/logo-square.png
DELETED
Git LFS Details
|
docs/logo/dark.svg
DELETED
docs/logo/light.svg
DELETED
docs/openapi.json
DELETED
|
@@ -1,2091 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"openapi": "3.0.3",
|
| 3 |
-
"info": {
|
| 4 |
-
"title": "OpenHands API",
|
| 5 |
-
"description": "OpenHands: Code Less, Make More",
|
| 6 |
-
"version": "1.0.0"
|
| 7 |
-
},
|
| 8 |
-
"servers": [
|
| 9 |
-
{
|
| 10 |
-
"url": "https://app.all-hands.dev",
|
| 11 |
-
"description": "Production server"
|
| 12 |
-
},
|
| 13 |
-
{
|
| 14 |
-
"url": "http://localhost:3000",
|
| 15 |
-
"description": "Local development server"
|
| 16 |
-
}
|
| 17 |
-
],
|
| 18 |
-
"paths": {
|
| 19 |
-
"/health": {
|
| 20 |
-
"get": {
|
| 21 |
-
"summary": "Health check",
|
| 22 |
-
"description": "Check if the API is running",
|
| 23 |
-
"operationId": "health",
|
| 24 |
-
"responses": {
|
| 25 |
-
"200": {
|
| 26 |
-
"description": "API is running",
|
| 27 |
-
"content": {
|
| 28 |
-
"text/plain": {
|
| 29 |
-
"schema": {
|
| 30 |
-
"type": "string",
|
| 31 |
-
"example": "OK"
|
| 32 |
-
}
|
| 33 |
-
}
|
| 34 |
-
}
|
| 35 |
-
}
|
| 36 |
-
}
|
| 37 |
-
}
|
| 38 |
-
},
|
| 39 |
-
"/api/conversations/{conversation_id}/config": {
|
| 40 |
-
"get": {
|
| 41 |
-
"summary": "Get runtime configuration",
|
| 42 |
-
"description": "Retrieve the runtime configuration (session ID and runtime ID)",
|
| 43 |
-
"operationId": "getRemoteRuntimeConfig",
|
| 44 |
-
"parameters": [
|
| 45 |
-
{
|
| 46 |
-
"name": "conversation_id",
|
| 47 |
-
"in": "path",
|
| 48 |
-
"required": true,
|
| 49 |
-
"schema": {
|
| 50 |
-
"type": "string"
|
| 51 |
-
},
|
| 52 |
-
"description": "Conversation ID"
|
| 53 |
-
}
|
| 54 |
-
],
|
| 55 |
-
"responses": {
|
| 56 |
-
"200": {
|
| 57 |
-
"description": "Runtime configuration",
|
| 58 |
-
"content": {
|
| 59 |
-
"application/json": {
|
| 60 |
-
"schema": {
|
| 61 |
-
"type": "object",
|
| 62 |
-
"properties": {
|
| 63 |
-
"runtime_id": {
|
| 64 |
-
"type": "string",
|
| 65 |
-
"nullable": true
|
| 66 |
-
},
|
| 67 |
-
"session_id": {
|
| 68 |
-
"type": "string",
|
| 69 |
-
"nullable": true
|
| 70 |
-
}
|
| 71 |
-
}
|
| 72 |
-
}
|
| 73 |
-
}
|
| 74 |
-
}
|
| 75 |
-
}
|
| 76 |
-
}
|
| 77 |
-
}
|
| 78 |
-
},
|
| 79 |
-
"/api/conversations/{conversation_id}/vscode-url": {
|
| 80 |
-
"get": {
|
| 81 |
-
"summary": "Get VSCode URL",
|
| 82 |
-
"description": "Get the VSCode URL for the conversation",
|
| 83 |
-
"operationId": "getVscodeUrl",
|
| 84 |
-
"parameters": [
|
| 85 |
-
{
|
| 86 |
-
"name": "conversation_id",
|
| 87 |
-
"in": "path",
|
| 88 |
-
"required": true,
|
| 89 |
-
"schema": {
|
| 90 |
-
"type": "string"
|
| 91 |
-
},
|
| 92 |
-
"description": "Conversation ID"
|
| 93 |
-
}
|
| 94 |
-
],
|
| 95 |
-
"responses": {
|
| 96 |
-
"200": {
|
| 97 |
-
"description": "VSCode URL",
|
| 98 |
-
"content": {
|
| 99 |
-
"application/json": {
|
| 100 |
-
"schema": {
|
| 101 |
-
"type": "object",
|
| 102 |
-
"properties": {
|
| 103 |
-
"vscode_url": {
|
| 104 |
-
"type": "string",
|
| 105 |
-
"nullable": true
|
| 106 |
-
}
|
| 107 |
-
}
|
| 108 |
-
}
|
| 109 |
-
}
|
| 110 |
-
}
|
| 111 |
-
},
|
| 112 |
-
"500": {
|
| 113 |
-
"description": "Error getting VSCode URL",
|
| 114 |
-
"content": {
|
| 115 |
-
"application/json": {
|
| 116 |
-
"schema": {
|
| 117 |
-
"type": "object",
|
| 118 |
-
"properties": {
|
| 119 |
-
"vscode_url": {
|
| 120 |
-
"type": "string",
|
| 121 |
-
"nullable": true
|
| 122 |
-
},
|
| 123 |
-
"error": {
|
| 124 |
-
"type": "string"
|
| 125 |
-
}
|
| 126 |
-
}
|
| 127 |
-
}
|
| 128 |
-
}
|
| 129 |
-
}
|
| 130 |
-
}
|
| 131 |
-
}
|
| 132 |
-
}
|
| 133 |
-
},
|
| 134 |
-
"/api/conversations/{conversation_id}/web-hosts": {
|
| 135 |
-
"get": {
|
| 136 |
-
"summary": "Get runtime hosts",
|
| 137 |
-
"description": "Get the hosts used by the runtime",
|
| 138 |
-
"operationId": "getHosts",
|
| 139 |
-
"parameters": [
|
| 140 |
-
{
|
| 141 |
-
"name": "conversation_id",
|
| 142 |
-
"in": "path",
|
| 143 |
-
"required": true,
|
| 144 |
-
"schema": {
|
| 145 |
-
"type": "string"
|
| 146 |
-
},
|
| 147 |
-
"description": "Conversation ID"
|
| 148 |
-
}
|
| 149 |
-
],
|
| 150 |
-
"responses": {
|
| 151 |
-
"200": {
|
| 152 |
-
"description": "Runtime hosts",
|
| 153 |
-
"content": {
|
| 154 |
-
"application/json": {
|
| 155 |
-
"schema": {
|
| 156 |
-
"type": "object",
|
| 157 |
-
"properties": {
|
| 158 |
-
"hosts": {
|
| 159 |
-
"type": "array",
|
| 160 |
-
"items": {
|
| 161 |
-
"type": "string"
|
| 162 |
-
}
|
| 163 |
-
}
|
| 164 |
-
}
|
| 165 |
-
}
|
| 166 |
-
}
|
| 167 |
-
}
|
| 168 |
-
},
|
| 169 |
-
"500": {
|
| 170 |
-
"description": "Error getting runtime hosts",
|
| 171 |
-
"content": {
|
| 172 |
-
"application/json": {
|
| 173 |
-
"schema": {
|
| 174 |
-
"type": "object",
|
| 175 |
-
"properties": {
|
| 176 |
-
"hosts": {
|
| 177 |
-
"type": "array",
|
| 178 |
-
"items": {
|
| 179 |
-
"type": "string"
|
| 180 |
-
},
|
| 181 |
-
"nullable": true
|
| 182 |
-
},
|
| 183 |
-
"error": {
|
| 184 |
-
"type": "string"
|
| 185 |
-
}
|
| 186 |
-
}
|
| 187 |
-
}
|
| 188 |
-
}
|
| 189 |
-
}
|
| 190 |
-
}
|
| 191 |
-
}
|
| 192 |
-
}
|
| 193 |
-
},
|
| 194 |
-
"/api/conversations/{conversation_id}/submit-feedback": {
|
| 195 |
-
"post": {
|
| 196 |
-
"summary": "Submit feedback",
|
| 197 |
-
"description": "Submit user feedback for a conversation",
|
| 198 |
-
"operationId": "submitFeedback",
|
| 199 |
-
"parameters": [
|
| 200 |
-
{
|
| 201 |
-
"name": "conversation_id",
|
| 202 |
-
"in": "path",
|
| 203 |
-
"required": true,
|
| 204 |
-
"schema": {
|
| 205 |
-
"type": "string"
|
| 206 |
-
},
|
| 207 |
-
"description": "Conversation ID"
|
| 208 |
-
}
|
| 209 |
-
],
|
| 210 |
-
"requestBody": {
|
| 211 |
-
"required": true,
|
| 212 |
-
"content": {
|
| 213 |
-
"application/json": {
|
| 214 |
-
"schema": {
|
| 215 |
-
"type": "object",
|
| 216 |
-
"properties": {
|
| 217 |
-
"email": {
|
| 218 |
-
"type": "string",
|
| 219 |
-
"format": "email"
|
| 220 |
-
},
|
| 221 |
-
"version": {
|
| 222 |
-
"type": "string"
|
| 223 |
-
},
|
| 224 |
-
"permissions": {
|
| 225 |
-
"type": "string",
|
| 226 |
-
"default": "private"
|
| 227 |
-
},
|
| 228 |
-
"polarity": {
|
| 229 |
-
"type": "string"
|
| 230 |
-
},
|
| 231 |
-
"feedback": {
|
| 232 |
-
"type": "string"
|
| 233 |
-
}
|
| 234 |
-
}
|
| 235 |
-
}
|
| 236 |
-
}
|
| 237 |
-
}
|
| 238 |
-
},
|
| 239 |
-
"responses": {
|
| 240 |
-
"200": {
|
| 241 |
-
"description": "Feedback submitted successfully",
|
| 242 |
-
"content": {
|
| 243 |
-
"application/json": {
|
| 244 |
-
"schema": {
|
| 245 |
-
"type": "object"
|
| 246 |
-
}
|
| 247 |
-
}
|
| 248 |
-
}
|
| 249 |
-
},
|
| 250 |
-
"500": {
|
| 251 |
-
"description": "Error submitting feedback",
|
| 252 |
-
"content": {
|
| 253 |
-
"application/json": {
|
| 254 |
-
"schema": {
|
| 255 |
-
"type": "object",
|
| 256 |
-
"properties": {
|
| 257 |
-
"error": {
|
| 258 |
-
"type": "string"
|
| 259 |
-
}
|
| 260 |
-
}
|
| 261 |
-
}
|
| 262 |
-
}
|
| 263 |
-
}
|
| 264 |
-
}
|
| 265 |
-
}
|
| 266 |
-
}
|
| 267 |
-
},
|
| 268 |
-
"/api/conversations/{conversation_id}/list-files": {
|
| 269 |
-
"get": {
|
| 270 |
-
"summary": "List files",
|
| 271 |
-
"description": "List files in the specified path",
|
| 272 |
-
"operationId": "listFiles",
|
| 273 |
-
"parameters": [
|
| 274 |
-
{
|
| 275 |
-
"name": "conversation_id",
|
| 276 |
-
"in": "path",
|
| 277 |
-
"required": true,
|
| 278 |
-
"schema": {
|
| 279 |
-
"type": "string"
|
| 280 |
-
},
|
| 281 |
-
"description": "Conversation ID"
|
| 282 |
-
},
|
| 283 |
-
{
|
| 284 |
-
"name": "path",
|
| 285 |
-
"in": "query",
|
| 286 |
-
"required": false,
|
| 287 |
-
"schema": {
|
| 288 |
-
"type": "string"
|
| 289 |
-
},
|
| 290 |
-
"description": "Path to list files from"
|
| 291 |
-
}
|
| 292 |
-
],
|
| 293 |
-
"responses": {
|
| 294 |
-
"200": {
|
| 295 |
-
"description": "List of files",
|
| 296 |
-
"content": {
|
| 297 |
-
"application/json": {
|
| 298 |
-
"schema": {
|
| 299 |
-
"type": "array",
|
| 300 |
-
"items": {
|
| 301 |
-
"type": "string"
|
| 302 |
-
}
|
| 303 |
-
}
|
| 304 |
-
}
|
| 305 |
-
}
|
| 306 |
-
},
|
| 307 |
-
"404": {
|
| 308 |
-
"description": "Runtime not initialized",
|
| 309 |
-
"content": {
|
| 310 |
-
"application/json": {
|
| 311 |
-
"schema": {
|
| 312 |
-
"type": "object",
|
| 313 |
-
"properties": {
|
| 314 |
-
"error": {
|
| 315 |
-
"type": "string"
|
| 316 |
-
}
|
| 317 |
-
}
|
| 318 |
-
}
|
| 319 |
-
}
|
| 320 |
-
}
|
| 321 |
-
},
|
| 322 |
-
"500": {
|
| 323 |
-
"description": "Error listing files",
|
| 324 |
-
"content": {
|
| 325 |
-
"application/json": {
|
| 326 |
-
"schema": {
|
| 327 |
-
"type": "object",
|
| 328 |
-
"properties": {
|
| 329 |
-
"error": {
|
| 330 |
-
"type": "string"
|
| 331 |
-
}
|
| 332 |
-
}
|
| 333 |
-
}
|
| 334 |
-
}
|
| 335 |
-
}
|
| 336 |
-
}
|
| 337 |
-
}
|
| 338 |
-
}
|
| 339 |
-
},
|
| 340 |
-
"/api/conversations/{conversation_id}/select-file": {
|
| 341 |
-
"get": {
|
| 342 |
-
"summary": "Get file content",
|
| 343 |
-
"description": "Retrieve the content of a specified file",
|
| 344 |
-
"operationId": "selectFile",
|
| 345 |
-
"parameters": [
|
| 346 |
-
{
|
| 347 |
-
"name": "conversation_id",
|
| 348 |
-
"in": "path",
|
| 349 |
-
"required": true,
|
| 350 |
-
"schema": {
|
| 351 |
-
"type": "string"
|
| 352 |
-
},
|
| 353 |
-
"description": "Conversation ID"
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"name": "file",
|
| 357 |
-
"in": "query",
|
| 358 |
-
"required": true,
|
| 359 |
-
"schema": {
|
| 360 |
-
"type": "string"
|
| 361 |
-
},
|
| 362 |
-
"description": "Path of the file to be retrieved"
|
| 363 |
-
}
|
| 364 |
-
],
|
| 365 |
-
"responses": {
|
| 366 |
-
"200": {
|
| 367 |
-
"description": "File content",
|
| 368 |
-
"content": {
|
| 369 |
-
"application/json": {
|
| 370 |
-
"schema": {
|
| 371 |
-
"type": "object",
|
| 372 |
-
"properties": {
|
| 373 |
-
"code": {
|
| 374 |
-
"type": "string"
|
| 375 |
-
}
|
| 376 |
-
}
|
| 377 |
-
}
|
| 378 |
-
}
|
| 379 |
-
}
|
| 380 |
-
},
|
| 381 |
-
"415": {
|
| 382 |
-
"description": "Unable to open binary file",
|
| 383 |
-
"content": {
|
| 384 |
-
"application/json": {
|
| 385 |
-
"schema": {
|
| 386 |
-
"type": "object",
|
| 387 |
-
"properties": {
|
| 388 |
-
"error": {
|
| 389 |
-
"type": "string"
|
| 390 |
-
}
|
| 391 |
-
}
|
| 392 |
-
}
|
| 393 |
-
}
|
| 394 |
-
}
|
| 395 |
-
},
|
| 396 |
-
"500": {
|
| 397 |
-
"description": "Error opening file",
|
| 398 |
-
"content": {
|
| 399 |
-
"application/json": {
|
| 400 |
-
"schema": {
|
| 401 |
-
"type": "object",
|
| 402 |
-
"properties": {
|
| 403 |
-
"error": {
|
| 404 |
-
"type": "string"
|
| 405 |
-
}
|
| 406 |
-
}
|
| 407 |
-
}
|
| 408 |
-
}
|
| 409 |
-
}
|
| 410 |
-
}
|
| 411 |
-
}
|
| 412 |
-
}
|
| 413 |
-
},
|
| 414 |
-
"/api/conversations/{conversation_id}/zip-directory": {
|
| 415 |
-
"get": {
|
| 416 |
-
"summary": "Download workspace as zip",
|
| 417 |
-
"description": "Download the current workspace as a zip file",
|
| 418 |
-
"operationId": "zipCurrentWorkspace",
|
| 419 |
-
"parameters": [
|
| 420 |
-
{
|
| 421 |
-
"name": "conversation_id",
|
| 422 |
-
"in": "path",
|
| 423 |
-
"required": true,
|
| 424 |
-
"schema": {
|
| 425 |
-
"type": "string"
|
| 426 |
-
},
|
| 427 |
-
"description": "Conversation ID"
|
| 428 |
-
}
|
| 429 |
-
],
|
| 430 |
-
"responses": {
|
| 431 |
-
"200": {
|
| 432 |
-
"description": "Workspace zip file",
|
| 433 |
-
"content": {
|
| 434 |
-
"application/zip": {
|
| 435 |
-
"schema": {
|
| 436 |
-
"type": "string",
|
| 437 |
-
"format": "binary"
|
| 438 |
-
}
|
| 439 |
-
}
|
| 440 |
-
}
|
| 441 |
-
},
|
| 442 |
-
"500": {
|
| 443 |
-
"description": "Error zipping workspace",
|
| 444 |
-
"content": {
|
| 445 |
-
"application/json": {
|
| 446 |
-
"schema": {
|
| 447 |
-
"type": "object",
|
| 448 |
-
"properties": {
|
| 449 |
-
"error": {
|
| 450 |
-
"type": "string"
|
| 451 |
-
}
|
| 452 |
-
}
|
| 453 |
-
}
|
| 454 |
-
}
|
| 455 |
-
}
|
| 456 |
-
}
|
| 457 |
-
}
|
| 458 |
-
}
|
| 459 |
-
},
|
| 460 |
-
"/api/conversations/{conversation_id}/git/changes": {
|
| 461 |
-
"get": {
|
| 462 |
-
"summary": "Get git changes",
|
| 463 |
-
"description": "Get git changes in the workspace",
|
| 464 |
-
"operationId": "gitChanges",
|
| 465 |
-
"parameters": [
|
| 466 |
-
{
|
| 467 |
-
"name": "conversation_id",
|
| 468 |
-
"in": "path",
|
| 469 |
-
"required": true,
|
| 470 |
-
"schema": {
|
| 471 |
-
"type": "string"
|
| 472 |
-
},
|
| 473 |
-
"description": "Conversation ID"
|
| 474 |
-
}
|
| 475 |
-
],
|
| 476 |
-
"responses": {
|
| 477 |
-
"200": {
|
| 478 |
-
"description": "Git changes",
|
| 479 |
-
"content": {
|
| 480 |
-
"application/json": {
|
| 481 |
-
"schema": {
|
| 482 |
-
"type": "object"
|
| 483 |
-
}
|
| 484 |
-
}
|
| 485 |
-
}
|
| 486 |
-
},
|
| 487 |
-
"500": {
|
| 488 |
-
"description": "Error getting git changes",
|
| 489 |
-
"content": {
|
| 490 |
-
"application/json": {
|
| 491 |
-
"schema": {
|
| 492 |
-
"type": "object",
|
| 493 |
-
"properties": {
|
| 494 |
-
"error": {
|
| 495 |
-
"type": "string"
|
| 496 |
-
}
|
| 497 |
-
}
|
| 498 |
-
}
|
| 499 |
-
}
|
| 500 |
-
}
|
| 501 |
-
}
|
| 502 |
-
}
|
| 503 |
-
}
|
| 504 |
-
},
|
| 505 |
-
"/api/conversations/{conversation_id}/git/diff": {
|
| 506 |
-
"get": {
|
| 507 |
-
"summary": "Get git diff",
|
| 508 |
-
"description": "Get git diff for a specific file",
|
| 509 |
-
"operationId": "gitDiff",
|
| 510 |
-
"parameters": [
|
| 511 |
-
{
|
| 512 |
-
"name": "conversation_id",
|
| 513 |
-
"in": "path",
|
| 514 |
-
"required": true,
|
| 515 |
-
"schema": {
|
| 516 |
-
"type": "string"
|
| 517 |
-
},
|
| 518 |
-
"description": "Conversation ID"
|
| 519 |
-
},
|
| 520 |
-
{
|
| 521 |
-
"name": "path",
|
| 522 |
-
"in": "query",
|
| 523 |
-
"required": true,
|
| 524 |
-
"schema": {
|
| 525 |
-
"type": "string"
|
| 526 |
-
},
|
| 527 |
-
"description": "Path of the file to get diff for"
|
| 528 |
-
}
|
| 529 |
-
],
|
| 530 |
-
"responses": {
|
| 531 |
-
"200": {
|
| 532 |
-
"description": "Git diff",
|
| 533 |
-
"content": {
|
| 534 |
-
"application/json": {
|
| 535 |
-
"schema": {
|
| 536 |
-
"type": "string"
|
| 537 |
-
}
|
| 538 |
-
}
|
| 539 |
-
}
|
| 540 |
-
},
|
| 541 |
-
"500": {
|
| 542 |
-
"description": "Error getting git diff",
|
| 543 |
-
"content": {
|
| 544 |
-
"application/json": {
|
| 545 |
-
"schema": {
|
| 546 |
-
"type": "object",
|
| 547 |
-
"properties": {
|
| 548 |
-
"error": {
|
| 549 |
-
"type": "string"
|
| 550 |
-
}
|
| 551 |
-
}
|
| 552 |
-
}
|
| 553 |
-
}
|
| 554 |
-
}
|
| 555 |
-
}
|
| 556 |
-
}
|
| 557 |
-
}
|
| 558 |
-
},
|
| 559 |
-
"/api/conversations/{conversation_id}/trajectory": {
|
| 560 |
-
"get": {
|
| 561 |
-
"summary": "Get trajectory",
|
| 562 |
-
"description": "Get the conversation trajectory",
|
| 563 |
-
"operationId": "getTrajectory",
|
| 564 |
-
"parameters": [
|
| 565 |
-
{
|
| 566 |
-
"name": "conversation_id",
|
| 567 |
-
"in": "path",
|
| 568 |
-
"required": true,
|
| 569 |
-
"schema": {
|
| 570 |
-
"type": "string"
|
| 571 |
-
},
|
| 572 |
-
"description": "Conversation ID"
|
| 573 |
-
}
|
| 574 |
-
],
|
| 575 |
-
"responses": {
|
| 576 |
-
"200": {
|
| 577 |
-
"description": "Conversation trajectory",
|
| 578 |
-
"content": {
|
| 579 |
-
"application/json": {
|
| 580 |
-
"schema": {
|
| 581 |
-
"type": "object",
|
| 582 |
-
"properties": {
|
| 583 |
-
"trajectory": {
|
| 584 |
-
"type": "array",
|
| 585 |
-
"items": {
|
| 586 |
-
"type": "object"
|
| 587 |
-
}
|
| 588 |
-
}
|
| 589 |
-
}
|
| 590 |
-
}
|
| 591 |
-
}
|
| 592 |
-
}
|
| 593 |
-
},
|
| 594 |
-
"500": {
|
| 595 |
-
"description": "Error getting trajectory",
|
| 596 |
-
"content": {
|
| 597 |
-
"application/json": {
|
| 598 |
-
"schema": {
|
| 599 |
-
"type": "object",
|
| 600 |
-
"properties": {
|
| 601 |
-
"trajectory": {
|
| 602 |
-
"type": "array",
|
| 603 |
-
"items": {
|
| 604 |
-
"type": "object"
|
| 605 |
-
},
|
| 606 |
-
"nullable": true
|
| 607 |
-
},
|
| 608 |
-
"error": {
|
| 609 |
-
"type": "string"
|
| 610 |
-
}
|
| 611 |
-
}
|
| 612 |
-
}
|
| 613 |
-
}
|
| 614 |
-
}
|
| 615 |
-
}
|
| 616 |
-
}
|
| 617 |
-
}
|
| 618 |
-
},
|
| 619 |
-
"/api/conversations/{conversation_id}/security/{path}": {
|
| 620 |
-
"get": {
|
| 621 |
-
"summary": "Security analyzer API (GET)",
|
| 622 |
-
"description": "Catch-all route for security analyzer API GET requests",
|
| 623 |
-
"operationId": "securityApiGet",
|
| 624 |
-
"parameters": [
|
| 625 |
-
{
|
| 626 |
-
"name": "conversation_id",
|
| 627 |
-
"in": "path",
|
| 628 |
-
"required": true,
|
| 629 |
-
"schema": {
|
| 630 |
-
"type": "string"
|
| 631 |
-
},
|
| 632 |
-
"description": "Conversation ID"
|
| 633 |
-
},
|
| 634 |
-
{
|
| 635 |
-
"name": "path",
|
| 636 |
-
"in": "path",
|
| 637 |
-
"required": true,
|
| 638 |
-
"schema": {
|
| 639 |
-
"type": "string"
|
| 640 |
-
},
|
| 641 |
-
"description": "Security analyzer API path"
|
| 642 |
-
}
|
| 643 |
-
],
|
| 644 |
-
"responses": {
|
| 645 |
-
"200": {
|
| 646 |
-
"description": "Security analyzer response",
|
| 647 |
-
"content": {
|
| 648 |
-
"application/json": {
|
| 649 |
-
"schema": {
|
| 650 |
-
"type": "object"
|
| 651 |
-
}
|
| 652 |
-
}
|
| 653 |
-
}
|
| 654 |
-
},
|
| 655 |
-
"404": {
|
| 656 |
-
"description": "Security analyzer not initialized",
|
| 657 |
-
"content": {
|
| 658 |
-
"application/json": {
|
| 659 |
-
"schema": {
|
| 660 |
-
"type": "object",
|
| 661 |
-
"properties": {
|
| 662 |
-
"detail": {
|
| 663 |
-
"type": "string"
|
| 664 |
-
}
|
| 665 |
-
}
|
| 666 |
-
}
|
| 667 |
-
}
|
| 668 |
-
}
|
| 669 |
-
}
|
| 670 |
-
}
|
| 671 |
-
},
|
| 672 |
-
"post": {
|
| 673 |
-
"summary": "Security analyzer API (POST)",
|
| 674 |
-
"description": "Catch-all route for security analyzer API POST requests",
|
| 675 |
-
"operationId": "securityApiPost",
|
| 676 |
-
"parameters": [
|
| 677 |
-
{
|
| 678 |
-
"name": "conversation_id",
|
| 679 |
-
"in": "path",
|
| 680 |
-
"required": true,
|
| 681 |
-
"schema": {
|
| 682 |
-
"type": "string"
|
| 683 |
-
},
|
| 684 |
-
"description": "Conversation ID"
|
| 685 |
-
},
|
| 686 |
-
{
|
| 687 |
-
"name": "path",
|
| 688 |
-
"in": "path",
|
| 689 |
-
"required": true,
|
| 690 |
-
"schema": {
|
| 691 |
-
"type": "string"
|
| 692 |
-
},
|
| 693 |
-
"description": "Security analyzer API path"
|
| 694 |
-
}
|
| 695 |
-
],
|
| 696 |
-
"requestBody": {
|
| 697 |
-
"required": false,
|
| 698 |
-
"content": {
|
| 699 |
-
"application/json": {
|
| 700 |
-
"schema": {
|
| 701 |
-
"type": "object"
|
| 702 |
-
}
|
| 703 |
-
}
|
| 704 |
-
}
|
| 705 |
-
},
|
| 706 |
-
"responses": {
|
| 707 |
-
"200": {
|
| 708 |
-
"description": "Security analyzer response",
|
| 709 |
-
"content": {
|
| 710 |
-
"application/json": {
|
| 711 |
-
"schema": {
|
| 712 |
-
"type": "object"
|
| 713 |
-
}
|
| 714 |
-
}
|
| 715 |
-
}
|
| 716 |
-
},
|
| 717 |
-
"404": {
|
| 718 |
-
"description": "Security analyzer not initialized",
|
| 719 |
-
"content": {
|
| 720 |
-
"application/json": {
|
| 721 |
-
"schema": {
|
| 722 |
-
"type": "object",
|
| 723 |
-
"properties": {
|
| 724 |
-
"detail": {
|
| 725 |
-
"type": "string"
|
| 726 |
-
}
|
| 727 |
-
}
|
| 728 |
-
}
|
| 729 |
-
}
|
| 730 |
-
}
|
| 731 |
-
}
|
| 732 |
-
}
|
| 733 |
-
},
|
| 734 |
-
"put": {
|
| 735 |
-
"summary": "Security analyzer API (PUT)",
|
| 736 |
-
"description": "Catch-all route for security analyzer API PUT requests",
|
| 737 |
-
"operationId": "securityApiPut",
|
| 738 |
-
"parameters": [
|
| 739 |
-
{
|
| 740 |
-
"name": "conversation_id",
|
| 741 |
-
"in": "path",
|
| 742 |
-
"required": true,
|
| 743 |
-
"schema": {
|
| 744 |
-
"type": "string"
|
| 745 |
-
},
|
| 746 |
-
"description": "Conversation ID"
|
| 747 |
-
},
|
| 748 |
-
{
|
| 749 |
-
"name": "path",
|
| 750 |
-
"in": "path",
|
| 751 |
-
"required": true,
|
| 752 |
-
"schema": {
|
| 753 |
-
"type": "string"
|
| 754 |
-
},
|
| 755 |
-
"description": "Security analyzer API path"
|
| 756 |
-
}
|
| 757 |
-
],
|
| 758 |
-
"requestBody": {
|
| 759 |
-
"required": false,
|
| 760 |
-
"content": {
|
| 761 |
-
"application/json": {
|
| 762 |
-
"schema": {
|
| 763 |
-
"type": "object"
|
| 764 |
-
}
|
| 765 |
-
}
|
| 766 |
-
}
|
| 767 |
-
},
|
| 768 |
-
"responses": {
|
| 769 |
-
"200": {
|
| 770 |
-
"description": "Security analyzer response",
|
| 771 |
-
"content": {
|
| 772 |
-
"application/json": {
|
| 773 |
-
"schema": {
|
| 774 |
-
"type": "object"
|
| 775 |
-
}
|
| 776 |
-
}
|
| 777 |
-
}
|
| 778 |
-
},
|
| 779 |
-
"404": {
|
| 780 |
-
"description": "Security analyzer not initialized",
|
| 781 |
-
"content": {
|
| 782 |
-
"application/json": {
|
| 783 |
-
"schema": {
|
| 784 |
-
"type": "object",
|
| 785 |
-
"properties": {
|
| 786 |
-
"detail": {
|
| 787 |
-
"type": "string"
|
| 788 |
-
}
|
| 789 |
-
}
|
| 790 |
-
}
|
| 791 |
-
}
|
| 792 |
-
}
|
| 793 |
-
}
|
| 794 |
-
}
|
| 795 |
-
},
|
| 796 |
-
"delete": {
|
| 797 |
-
"summary": "Security analyzer API (DELETE)",
|
| 798 |
-
"description": "Catch-all route for security analyzer API DELETE requests",
|
| 799 |
-
"operationId": "securityApiDelete",
|
| 800 |
-
"parameters": [
|
| 801 |
-
{
|
| 802 |
-
"name": "conversation_id",
|
| 803 |
-
"in": "path",
|
| 804 |
-
"required": true,
|
| 805 |
-
"schema": {
|
| 806 |
-
"type": "string"
|
| 807 |
-
},
|
| 808 |
-
"description": "Conversation ID"
|
| 809 |
-
},
|
| 810 |
-
{
|
| 811 |
-
"name": "path",
|
| 812 |
-
"in": "path",
|
| 813 |
-
"required": true,
|
| 814 |
-
"schema": {
|
| 815 |
-
"type": "string"
|
| 816 |
-
},
|
| 817 |
-
"description": "Security analyzer API path"
|
| 818 |
-
}
|
| 819 |
-
],
|
| 820 |
-
"responses": {
|
| 821 |
-
"200": {
|
| 822 |
-
"description": "Security analyzer response",
|
| 823 |
-
"content": {
|
| 824 |
-
"application/json": {
|
| 825 |
-
"schema": {
|
| 826 |
-
"type": "object"
|
| 827 |
-
}
|
| 828 |
-
}
|
| 829 |
-
}
|
| 830 |
-
},
|
| 831 |
-
"404": {
|
| 832 |
-
"description": "Security analyzer not initialized",
|
| 833 |
-
"content": {
|
| 834 |
-
"application/json": {
|
| 835 |
-
"schema": {
|
| 836 |
-
"type": "object",
|
| 837 |
-
"properties": {
|
| 838 |
-
"detail": {
|
| 839 |
-
"type": "string"
|
| 840 |
-
}
|
| 841 |
-
}
|
| 842 |
-
}
|
| 843 |
-
}
|
| 844 |
-
}
|
| 845 |
-
}
|
| 846 |
-
}
|
| 847 |
-
}
|
| 848 |
-
},
|
| 849 |
-
"/api/conversations": {
|
| 850 |
-
"post": {
|
| 851 |
-
"summary": "Create new conversation",
|
| 852 |
-
"description": "Initialize a new conversation",
|
| 853 |
-
"operationId": "newConversation",
|
| 854 |
-
"requestBody": {
|
| 855 |
-
"required": true,
|
| 856 |
-
"content": {
|
| 857 |
-
"application/json": {
|
| 858 |
-
"schema": {
|
| 859 |
-
"type": "object",
|
| 860 |
-
"properties": {
|
| 861 |
-
"repository": {
|
| 862 |
-
"type": "string",
|
| 863 |
-
"nullable": true,
|
| 864 |
-
"description": "Full name of the repository (e.g., owner/repo)"
|
| 865 |
-
},
|
| 866 |
-
"git_provider": {
|
| 867 |
-
"type": "string",
|
| 868 |
-
"nullable": true,
|
| 869 |
-
"description": "The Git provider (e.g., github or gitlab). If omitted, all configured providers are checked for the repository."
|
| 870 |
-
},
|
| 871 |
-
"selected_branch": {
|
| 872 |
-
"type": "string",
|
| 873 |
-
"nullable": true
|
| 874 |
-
},
|
| 875 |
-
"initial_user_msg": {
|
| 876 |
-
"type": "string",
|
| 877 |
-
"nullable": true
|
| 878 |
-
},
|
| 879 |
-
"conversation_instructions": {
|
| 880 |
-
"type": "string",
|
| 881 |
-
"nullable": true,
|
| 882 |
-
"description": "Optional instructions the agent must follow throughout the conversation while addressing the user's initial task"
|
| 883 |
-
},
|
| 884 |
-
"image_urls": {
|
| 885 |
-
"type": "array",
|
| 886 |
-
"items": {
|
| 887 |
-
"type": "string"
|
| 888 |
-
},
|
| 889 |
-
"nullable": true
|
| 890 |
-
},
|
| 891 |
-
"replay_json": {
|
| 892 |
-
"type": "string",
|
| 893 |
-
"nullable": true
|
| 894 |
-
}
|
| 895 |
-
}
|
| 896 |
-
}
|
| 897 |
-
}
|
| 898 |
-
}
|
| 899 |
-
},
|
| 900 |
-
"responses": {
|
| 901 |
-
"200": {
|
| 902 |
-
"description": "Conversation created successfully",
|
| 903 |
-
"content": {
|
| 904 |
-
"application/json": {
|
| 905 |
-
"schema": {
|
| 906 |
-
"type": "object",
|
| 907 |
-
"properties": {
|
| 908 |
-
"status": {
|
| 909 |
-
"type": "string",
|
| 910 |
-
"example": "ok"
|
| 911 |
-
},
|
| 912 |
-
"conversation_id": {
|
| 913 |
-
"type": "string"
|
| 914 |
-
}
|
| 915 |
-
}
|
| 916 |
-
}
|
| 917 |
-
}
|
| 918 |
-
}
|
| 919 |
-
},
|
| 920 |
-
"400": {
|
| 921 |
-
"description": "Error creating conversation",
|
| 922 |
-
"content": {
|
| 923 |
-
"application/json": {
|
| 924 |
-
"schema": {
|
| 925 |
-
"type": "object",
|
| 926 |
-
"properties": {
|
| 927 |
-
"status": {
|
| 928 |
-
"type": "string",
|
| 929 |
-
"example": "error"
|
| 930 |
-
},
|
| 931 |
-
"message": {
|
| 932 |
-
"type": "string"
|
| 933 |
-
},
|
| 934 |
-
"msg_id": {
|
| 935 |
-
"type": "string"
|
| 936 |
-
}
|
| 937 |
-
}
|
| 938 |
-
}
|
| 939 |
-
}
|
| 940 |
-
}
|
| 941 |
-
}
|
| 942 |
-
}
|
| 943 |
-
},
|
| 944 |
-
"get": {
|
| 945 |
-
"summary": "Search conversations",
|
| 946 |
-
"description": "Search for conversations",
|
| 947 |
-
"operationId": "searchConversations",
|
| 948 |
-
"parameters": [
|
| 949 |
-
{
|
| 950 |
-
"name": "page_id",
|
| 951 |
-
"in": "query",
|
| 952 |
-
"required": false,
|
| 953 |
-
"schema": {
|
| 954 |
-
"type": "string"
|
| 955 |
-
},
|
| 956 |
-
"description": "Page ID for pagination"
|
| 957 |
-
},
|
| 958 |
-
{
|
| 959 |
-
"name": "limit",
|
| 960 |
-
"in": "query",
|
| 961 |
-
"required": false,
|
| 962 |
-
"schema": {
|
| 963 |
-
"type": "integer",
|
| 964 |
-
"default": 20
|
| 965 |
-
},
|
| 966 |
-
"description": "Number of conversations to return"
|
| 967 |
-
}
|
| 968 |
-
],
|
| 969 |
-
"responses": {
|
| 970 |
-
"200": {
|
| 971 |
-
"description": "Conversations",
|
| 972 |
-
"content": {
|
| 973 |
-
"application/json": {
|
| 974 |
-
"schema": {
|
| 975 |
-
"type": "object",
|
| 976 |
-
"properties": {
|
| 977 |
-
"results": {
|
| 978 |
-
"type": "array",
|
| 979 |
-
"items": {
|
| 980 |
-
"type": "object",
|
| 981 |
-
"properties": {
|
| 982 |
-
"conversation_id": {
|
| 983 |
-
"type": "string"
|
| 984 |
-
},
|
| 985 |
-
"title": {
|
| 986 |
-
"type": "string"
|
| 987 |
-
},
|
| 988 |
-
"last_updated_at": {
|
| 989 |
-
"type": "string",
|
| 990 |
-
"format": "date-time"
|
| 991 |
-
},
|
| 992 |
-
"created_at": {
|
| 993 |
-
"type": "string",
|
| 994 |
-
"format": "date-time"
|
| 995 |
-
},
|
| 996 |
-
"selected_repository": {
|
| 997 |
-
"type": "string",
|
| 998 |
-
"nullable": true
|
| 999 |
-
},
|
| 1000 |
-
"status": {
|
| 1001 |
-
"type": "string",
|
| 1002 |
-
"enum": ["RUNNING", "STOPPED"]
|
| 1003 |
-
},
|
| 1004 |
-
"trigger": {
|
| 1005 |
-
"type": "string",
|
| 1006 |
-
"enum": ["GUI", "API"]
|
| 1007 |
-
}
|
| 1008 |
-
}
|
| 1009 |
-
}
|
| 1010 |
-
},
|
| 1011 |
-
"next_page_id": {
|
| 1012 |
-
"type": "string",
|
| 1013 |
-
"nullable": true
|
| 1014 |
-
}
|
| 1015 |
-
}
|
| 1016 |
-
}
|
| 1017 |
-
}
|
| 1018 |
-
}
|
| 1019 |
-
}
|
| 1020 |
-
}
|
| 1021 |
-
}
|
| 1022 |
-
},
|
| 1023 |
-
"/api/conversations/{conversation_id}": {
|
| 1024 |
-
"get": {
|
| 1025 |
-
"summary": "Get conversation",
|
| 1026 |
-
"description": "Get conversation details",
|
| 1027 |
-
"operationId": "getConversation",
|
| 1028 |
-
"parameters": [
|
| 1029 |
-
{
|
| 1030 |
-
"name": "conversation_id",
|
| 1031 |
-
"in": "path",
|
| 1032 |
-
"required": true,
|
| 1033 |
-
"schema": {
|
| 1034 |
-
"type": "string"
|
| 1035 |
-
},
|
| 1036 |
-
"description": "Conversation ID"
|
| 1037 |
-
}
|
| 1038 |
-
],
|
| 1039 |
-
"responses": {
|
| 1040 |
-
"200": {
|
| 1041 |
-
"description": "Conversation details",
|
| 1042 |
-
"content": {
|
| 1043 |
-
"application/json": {
|
| 1044 |
-
"schema": {
|
| 1045 |
-
"type": "object",
|
| 1046 |
-
"properties": {
|
| 1047 |
-
"conversation_id": {
|
| 1048 |
-
"type": "string"
|
| 1049 |
-
},
|
| 1050 |
-
"title": {
|
| 1051 |
-
"type": "string"
|
| 1052 |
-
},
|
| 1053 |
-
"last_updated_at": {
|
| 1054 |
-
"type": "string",
|
| 1055 |
-
"format": "date-time"
|
| 1056 |
-
},
|
| 1057 |
-
"created_at": {
|
| 1058 |
-
"type": "string",
|
| 1059 |
-
"format": "date-time"
|
| 1060 |
-
},
|
| 1061 |
-
"selected_repository": {
|
| 1062 |
-
"type": "string",
|
| 1063 |
-
"nullable": true
|
| 1064 |
-
},
|
| 1065 |
-
"status": {
|
| 1066 |
-
"type": "string",
|
| 1067 |
-
"enum": ["RUNNING", "STOPPED"]
|
| 1068 |
-
},
|
| 1069 |
-
"trigger": {
|
| 1070 |
-
"type": "string",
|
| 1071 |
-
"enum": ["GUI", "API"]
|
| 1072 |
-
}
|
| 1073 |
-
}
|
| 1074 |
-
}
|
| 1075 |
-
}
|
| 1076 |
-
}
|
| 1077 |
-
},
|
| 1078 |
-
"404": {
|
| 1079 |
-
"description": "Conversation not found",
|
| 1080 |
-
"content": {
|
| 1081 |
-
"application/json": {
|
| 1082 |
-
"schema": {
|
| 1083 |
-
"type": "object",
|
| 1084 |
-
"nullable": true
|
| 1085 |
-
}
|
| 1086 |
-
}
|
| 1087 |
-
}
|
| 1088 |
-
}
|
| 1089 |
-
}
|
| 1090 |
-
},
|
| 1091 |
-
"patch": {
|
| 1092 |
-
"summary": "Update conversation",
|
| 1093 |
-
"description": "Update conversation details",
|
| 1094 |
-
"operationId": "updateConversation",
|
| 1095 |
-
"parameters": [
|
| 1096 |
-
{
|
| 1097 |
-
"name": "conversation_id",
|
| 1098 |
-
"in": "path",
|
| 1099 |
-
"required": true,
|
| 1100 |
-
"schema": {
|
| 1101 |
-
"type": "string"
|
| 1102 |
-
},
|
| 1103 |
-
"description": "Conversation ID"
|
| 1104 |
-
}
|
| 1105 |
-
],
|
| 1106 |
-
"requestBody": {
|
| 1107 |
-
"required": true,
|
| 1108 |
-
"content": {
|
| 1109 |
-
"application/json": {
|
| 1110 |
-
"schema": {
|
| 1111 |
-
"type": "object",
|
| 1112 |
-
"properties": {
|
| 1113 |
-
"title": {
|
| 1114 |
-
"type": "string"
|
| 1115 |
-
}
|
| 1116 |
-
}
|
| 1117 |
-
}
|
| 1118 |
-
}
|
| 1119 |
-
}
|
| 1120 |
-
},
|
| 1121 |
-
"responses": {
|
| 1122 |
-
"200": {
|
| 1123 |
-
"description": "Conversation updated successfully",
|
| 1124 |
-
"content": {
|
| 1125 |
-
"application/json": {
|
| 1126 |
-
"schema": {
|
| 1127 |
-
"type": "boolean"
|
| 1128 |
-
}
|
| 1129 |
-
}
|
| 1130 |
-
}
|
| 1131 |
-
}
|
| 1132 |
-
}
|
| 1133 |
-
},
|
| 1134 |
-
"delete": {
|
| 1135 |
-
"summary": "Delete conversation",
|
| 1136 |
-
"description": "Delete a conversation",
|
| 1137 |
-
"operationId": "deleteConversation",
|
| 1138 |
-
"parameters": [
|
| 1139 |
-
{
|
| 1140 |
-
"name": "conversation_id",
|
| 1141 |
-
"in": "path",
|
| 1142 |
-
"required": true,
|
| 1143 |
-
"schema": {
|
| 1144 |
-
"type": "string"
|
| 1145 |
-
},
|
| 1146 |
-
"description": "Conversation ID"
|
| 1147 |
-
}
|
| 1148 |
-
],
|
| 1149 |
-
"responses": {
|
| 1150 |
-
"200": {
|
| 1151 |
-
"description": "Conversation deleted successfully",
|
| 1152 |
-
"content": {
|
| 1153 |
-
"application/json": {
|
| 1154 |
-
"schema": {
|
| 1155 |
-
"type": "boolean"
|
| 1156 |
-
}
|
| 1157 |
-
}
|
| 1158 |
-
}
|
| 1159 |
-
}
|
| 1160 |
-
}
|
| 1161 |
-
}
|
| 1162 |
-
},
|
| 1163 |
-
"/api/user/repositories": {
|
| 1164 |
-
"get": {
|
| 1165 |
-
"summary": "Get user repositories",
|
| 1166 |
-
"description": "Get repositories for the authenticated user",
|
| 1167 |
-
"operationId": "getUserRepositories",
|
| 1168 |
-
"parameters": [
|
| 1169 |
-
{
|
| 1170 |
-
"name": "sort",
|
| 1171 |
-
"in": "query",
|
| 1172 |
-
"required": false,
|
| 1173 |
-
"schema": {
|
| 1174 |
-
"type": "string",
|
| 1175 |
-
"default": "pushed"
|
| 1176 |
-
},
|
| 1177 |
-
"description": "Sort order for repositories"
|
| 1178 |
-
}
|
| 1179 |
-
],
|
| 1180 |
-
"responses": {
|
| 1181 |
-
"200": {
|
| 1182 |
-
"description": "User repositories",
|
| 1183 |
-
"content": {
|
| 1184 |
-
"application/json": {
|
| 1185 |
-
"schema": {
|
| 1186 |
-
"type": "array",
|
| 1187 |
-
"items": {
|
| 1188 |
-
"type": "object",
|
| 1189 |
-
"properties": {
|
| 1190 |
-
"full_name": {
|
| 1191 |
-
"type": "string"
|
| 1192 |
-
},
|
| 1193 |
-
"description": {
|
| 1194 |
-
"type": "string",
|
| 1195 |
-
"nullable": true
|
| 1196 |
-
},
|
| 1197 |
-
"html_url": {
|
| 1198 |
-
"type": "string"
|
| 1199 |
-
},
|
| 1200 |
-
"private": {
|
| 1201 |
-
"type": "boolean"
|
| 1202 |
-
},
|
| 1203 |
-
"fork": {
|
| 1204 |
-
"type": "boolean"
|
| 1205 |
-
},
|
| 1206 |
-
"updated_at": {
|
| 1207 |
-
"type": "string",
|
| 1208 |
-
"format": "date-time"
|
| 1209 |
-
}
|
| 1210 |
-
}
|
| 1211 |
-
}
|
| 1212 |
-
}
|
| 1213 |
-
}
|
| 1214 |
-
}
|
| 1215 |
-
},
|
| 1216 |
-
"401": {
|
| 1217 |
-
"description": "Authentication error",
|
| 1218 |
-
"content": {
|
| 1219 |
-
"application/json": {
|
| 1220 |
-
"schema": {
|
| 1221 |
-
"type": "string"
|
| 1222 |
-
}
|
| 1223 |
-
}
|
| 1224 |
-
}
|
| 1225 |
-
},
|
| 1226 |
-
"500": {
|
| 1227 |
-
"description": "Unknown error",
|
| 1228 |
-
"content": {
|
| 1229 |
-
"application/json": {
|
| 1230 |
-
"schema": {
|
| 1231 |
-
"type": "string"
|
| 1232 |
-
}
|
| 1233 |
-
}
|
| 1234 |
-
}
|
| 1235 |
-
}
|
| 1236 |
-
}
|
| 1237 |
-
}
|
| 1238 |
-
},
|
| 1239 |
-
"/api/user/info": {
|
| 1240 |
-
"get": {
|
| 1241 |
-
"summary": "Get user info",
|
| 1242 |
-
"description": "Get information about the authenticated user",
|
| 1243 |
-
"operationId": "getUser",
|
| 1244 |
-
"responses": {
|
| 1245 |
-
"200": {
|
| 1246 |
-
"description": "User information",
|
| 1247 |
-
"content": {
|
| 1248 |
-
"application/json": {
|
| 1249 |
-
"schema": {
|
| 1250 |
-
"type": "object",
|
| 1251 |
-
"properties": {
|
| 1252 |
-
"login": {
|
| 1253 |
-
"type": "string"
|
| 1254 |
-
},
|
| 1255 |
-
"name": {
|
| 1256 |
-
"type": "string",
|
| 1257 |
-
"nullable": true
|
| 1258 |
-
},
|
| 1259 |
-
"email": {
|
| 1260 |
-
"type": "string",
|
| 1261 |
-
"nullable": true
|
| 1262 |
-
},
|
| 1263 |
-
"avatar_url": {
|
| 1264 |
-
"type": "string",
|
| 1265 |
-
"nullable": true
|
| 1266 |
-
}
|
| 1267 |
-
}
|
| 1268 |
-
}
|
| 1269 |
-
}
|
| 1270 |
-
}
|
| 1271 |
-
},
|
| 1272 |
-
"401": {
|
| 1273 |
-
"description": "Authentication error",
|
| 1274 |
-
"content": {
|
| 1275 |
-
"application/json": {
|
| 1276 |
-
"schema": {
|
| 1277 |
-
"type": "string"
|
| 1278 |
-
}
|
| 1279 |
-
}
|
| 1280 |
-
}
|
| 1281 |
-
},
|
| 1282 |
-
"500": {
|
| 1283 |
-
"description": "Unknown error",
|
| 1284 |
-
"content": {
|
| 1285 |
-
"application/json": {
|
| 1286 |
-
"schema": {
|
| 1287 |
-
"type": "string"
|
| 1288 |
-
}
|
| 1289 |
-
}
|
| 1290 |
-
}
|
| 1291 |
-
}
|
| 1292 |
-
}
|
| 1293 |
-
}
|
| 1294 |
-
},
|
| 1295 |
-
"/api/user/search/repositories": {
|
| 1296 |
-
"get": {
|
| 1297 |
-
"summary": "Search repositories",
|
| 1298 |
-
"description": "Search for repositories",
|
| 1299 |
-
"operationId": "searchRepositories",
|
| 1300 |
-
"parameters": [
|
| 1301 |
-
{
|
| 1302 |
-
"name": "query",
|
| 1303 |
-
"in": "query",
|
| 1304 |
-
"required": true,
|
| 1305 |
-
"schema": {
|
| 1306 |
-
"type": "string"
|
| 1307 |
-
},
|
| 1308 |
-
"description": "Search query"
|
| 1309 |
-
},
|
| 1310 |
-
{
|
| 1311 |
-
"name": "per_page",
|
| 1312 |
-
"in": "query",
|
| 1313 |
-
"required": false,
|
| 1314 |
-
"schema": {
|
| 1315 |
-
"type": "integer",
|
| 1316 |
-
"default": 5
|
| 1317 |
-
},
|
| 1318 |
-
"description": "Number of repositories to return per page"
|
| 1319 |
-
},
|
| 1320 |
-
{
|
| 1321 |
-
"name": "sort",
|
| 1322 |
-
"in": "query",
|
| 1323 |
-
"required": false,
|
| 1324 |
-
"schema": {
|
| 1325 |
-
"type": "string",
|
| 1326 |
-
"default": "stars"
|
| 1327 |
-
},
|
| 1328 |
-
"description": "Sort order for repositories"
|
| 1329 |
-
},
|
| 1330 |
-
{
|
| 1331 |
-
"name": "order",
|
| 1332 |
-
"in": "query",
|
| 1333 |
-
"required": false,
|
| 1334 |
-
"schema": {
|
| 1335 |
-
"type": "string",
|
| 1336 |
-
"default": "desc"
|
| 1337 |
-
},
|
| 1338 |
-
"description": "Sort direction"
|
| 1339 |
-
}
|
| 1340 |
-
],
|
| 1341 |
-
"responses": {
|
| 1342 |
-
"200": {
|
| 1343 |
-
"description": "Search results",
|
| 1344 |
-
"content": {
|
| 1345 |
-
"application/json": {
|
| 1346 |
-
"schema": {
|
| 1347 |
-
"type": "array",
|
| 1348 |
-
"items": {
|
| 1349 |
-
"type": "object",
|
| 1350 |
-
"properties": {
|
| 1351 |
-
"full_name": {
|
| 1352 |
-
"type": "string"
|
| 1353 |
-
},
|
| 1354 |
-
"description": {
|
| 1355 |
-
"type": "string",
|
| 1356 |
-
"nullable": true
|
| 1357 |
-
},
|
| 1358 |
-
"html_url": {
|
| 1359 |
-
"type": "string"
|
| 1360 |
-
},
|
| 1361 |
-
"private": {
|
| 1362 |
-
"type": "boolean"
|
| 1363 |
-
},
|
| 1364 |
-
"fork": {
|
| 1365 |
-
"type": "boolean"
|
| 1366 |
-
},
|
| 1367 |
-
"updated_at": {
|
| 1368 |
-
"type": "string",
|
| 1369 |
-
"format": "date-time"
|
| 1370 |
-
}
|
| 1371 |
-
}
|
| 1372 |
-
}
|
| 1373 |
-
}
|
| 1374 |
-
}
|
| 1375 |
-
}
|
| 1376 |
-
},
|
| 1377 |
-
"401": {
|
| 1378 |
-
"description": "Authentication error",
|
| 1379 |
-
"content": {
|
| 1380 |
-
"application/json": {
|
| 1381 |
-
"schema": {
|
| 1382 |
-
"type": "string"
|
| 1383 |
-
}
|
| 1384 |
-
}
|
| 1385 |
-
}
|
| 1386 |
-
},
|
| 1387 |
-
"500": {
|
| 1388 |
-
"description": "Unknown error",
|
| 1389 |
-
"content": {
|
| 1390 |
-
"application/json": {
|
| 1391 |
-
"schema": {
|
| 1392 |
-
"type": "string"
|
| 1393 |
-
}
|
| 1394 |
-
}
|
| 1395 |
-
}
|
| 1396 |
-
}
|
| 1397 |
-
}
|
| 1398 |
-
}
|
| 1399 |
-
},
|
| 1400 |
-
"/api/user/suggested-tasks": {
|
| 1401 |
-
"get": {
|
| 1402 |
-
"summary": "Get suggested tasks",
|
| 1403 |
-
"description": "Get suggested tasks for the authenticated user across their most recently pushed repositories",
|
| 1404 |
-
"operationId": "getSuggestedTasks",
|
| 1405 |
-
"responses": {
|
| 1406 |
-
"200": {
|
| 1407 |
-
"description": "Suggested tasks",
|
| 1408 |
-
"content": {
|
| 1409 |
-
"application/json": {
|
| 1410 |
-
"schema": {
|
| 1411 |
-
"type": "array",
|
| 1412 |
-
"items": {
|
| 1413 |
-
"type": "object",
|
| 1414 |
-
"properties": {
|
| 1415 |
-
"title": {
|
| 1416 |
-
"type": "string"
|
| 1417 |
-
},
|
| 1418 |
-
"url": {
|
| 1419 |
-
"type": "string"
|
| 1420 |
-
},
|
| 1421 |
-
"repository": {
|
| 1422 |
-
"type": "string"
|
| 1423 |
-
},
|
| 1424 |
-
"type": {
|
| 1425 |
-
"type": "string"
|
| 1426 |
-
},
|
| 1427 |
-
"created_at": {
|
| 1428 |
-
"type": "string",
|
| 1429 |
-
"format": "date-time"
|
| 1430 |
-
}
|
| 1431 |
-
}
|
| 1432 |
-
}
|
| 1433 |
-
}
|
| 1434 |
-
}
|
| 1435 |
-
}
|
| 1436 |
-
},
|
| 1437 |
-
"401": {
|
| 1438 |
-
"description": "Authentication error",
|
| 1439 |
-
"content": {
|
| 1440 |
-
"application/json": {
|
| 1441 |
-
"schema": {
|
| 1442 |
-
"type": "string"
|
| 1443 |
-
}
|
| 1444 |
-
}
|
| 1445 |
-
}
|
| 1446 |
-
},
|
| 1447 |
-
"500": {
|
| 1448 |
-
"description": "Unknown error",
|
| 1449 |
-
"content": {
|
| 1450 |
-
"application/json": {
|
| 1451 |
-
"schema": {
|
| 1452 |
-
"type": "string"
|
| 1453 |
-
}
|
| 1454 |
-
}
|
| 1455 |
-
}
|
| 1456 |
-
}
|
| 1457 |
-
}
|
| 1458 |
-
}
|
| 1459 |
-
},
|
| 1460 |
-
"/api/settings": {
|
| 1461 |
-
"get": {
|
| 1462 |
-
"summary": "Get settings",
|
| 1463 |
-
"description": "Get user settings",
|
| 1464 |
-
"operationId": "loadSettings",
|
| 1465 |
-
"responses": {
|
| 1466 |
-
"200": {
|
| 1467 |
-
"description": "User settings",
|
| 1468 |
-
"content": {
|
| 1469 |
-
"application/json": {
|
| 1470 |
-
"schema": {
|
| 1471 |
-
"type": "object",
|
| 1472 |
-
"properties": {
|
| 1473 |
-
"language": {
|
| 1474 |
-
"type": "string"
|
| 1475 |
-
},
|
| 1476 |
-
"agent": {
|
| 1477 |
-
"type": "string"
|
| 1478 |
-
},
|
| 1479 |
-
"security_analyzer": {
|
| 1480 |
-
"type": "string"
|
| 1481 |
-
},
|
| 1482 |
-
"confirmation_mode": {
|
| 1483 |
-
"type": "boolean"
|
| 1484 |
-
},
|
| 1485 |
-
"llm_model": {
|
| 1486 |
-
"type": "string"
|
| 1487 |
-
},
|
| 1488 |
-
"llm_api_key_set": {
|
| 1489 |
-
"type": "boolean"
|
| 1490 |
-
},
|
| 1491 |
-
"llm_base_url": {
|
| 1492 |
-
"type": "string",
|
| 1493 |
-
"nullable": true
|
| 1494 |
-
},
|
| 1495 |
-
"remote_runtime_resource_factor": {
|
| 1496 |
-
"type": "number"
|
| 1497 |
-
},
|
| 1498 |
-
"enable_default_condenser": {
|
| 1499 |
-
"type": "boolean"
|
| 1500 |
-
},
|
| 1501 |
-
"enable_sound_notifications": {
|
| 1502 |
-
"type": "boolean"
|
| 1503 |
-
},
|
| 1504 |
-
"user_consents_to_analytics": {
|
| 1505 |
-
"type": "boolean"
|
| 1506 |
-
},
|
| 1507 |
-
"provider_tokens_set": {
|
| 1508 |
-
"type": "object",
|
| 1509 |
-
"additionalProperties": {
|
| 1510 |
-
"type": "boolean"
|
| 1511 |
-
}
|
| 1512 |
-
}
|
| 1513 |
-
}
|
| 1514 |
-
}
|
| 1515 |
-
}
|
| 1516 |
-
}
|
| 1517 |
-
},
|
| 1518 |
-
"401": {
|
| 1519 |
-
"description": "Invalid token",
|
| 1520 |
-
"content": {
|
| 1521 |
-
"application/json": {
|
| 1522 |
-
"schema": {
|
| 1523 |
-
"type": "object",
|
| 1524 |
-
"properties": {
|
| 1525 |
-
"error": {
|
| 1526 |
-
"type": "string"
|
| 1527 |
-
}
|
| 1528 |
-
}
|
| 1529 |
-
}
|
| 1530 |
-
}
|
| 1531 |
-
}
|
| 1532 |
-
},
|
| 1533 |
-
"404": {
|
| 1534 |
-
"description": "Settings not found",
|
| 1535 |
-
"content": {
|
| 1536 |
-
"application/json": {
|
| 1537 |
-
"schema": {
|
| 1538 |
-
"type": "object",
|
| 1539 |
-
"properties": {
|
| 1540 |
-
"error": {
|
| 1541 |
-
"type": "string"
|
| 1542 |
-
}
|
| 1543 |
-
}
|
| 1544 |
-
}
|
| 1545 |
-
}
|
| 1546 |
-
}
|
| 1547 |
-
}
|
| 1548 |
-
}
|
| 1549 |
-
},
|
| 1550 |
-
"post": {
|
| 1551 |
-
"summary": "Store settings",
|
| 1552 |
-
"description": "Store user settings",
|
| 1553 |
-
"operationId": "storeSettings",
|
| 1554 |
-
"requestBody": {
|
| 1555 |
-
"required": true,
|
| 1556 |
-
"content": {
|
| 1557 |
-
"application/json": {
|
| 1558 |
-
"schema": {
|
| 1559 |
-
"type": "object",
|
| 1560 |
-
"properties": {
|
| 1561 |
-
"language": {
|
| 1562 |
-
"type": "string"
|
| 1563 |
-
},
|
| 1564 |
-
"agent": {
|
| 1565 |
-
"type": "string"
|
| 1566 |
-
},
|
| 1567 |
-
"security_analyzer": {
|
| 1568 |
-
"type": "string"
|
| 1569 |
-
},
|
| 1570 |
-
"confirmation_mode": {
|
| 1571 |
-
"type": "boolean"
|
| 1572 |
-
},
|
| 1573 |
-
"llm_model": {
|
| 1574 |
-
"type": "string"
|
| 1575 |
-
},
|
| 1576 |
-
"llm_api_key": {
|
| 1577 |
-
"type": "string"
|
| 1578 |
-
},
|
| 1579 |
-
"llm_base_url": {
|
| 1580 |
-
"type": "string",
|
| 1581 |
-
"nullable": true
|
| 1582 |
-
},
|
| 1583 |
-
"remote_runtime_resource_factor": {
|
| 1584 |
-
"type": "number"
|
| 1585 |
-
},
|
| 1586 |
-
"enable_default_condenser": {
|
| 1587 |
-
"type": "boolean"
|
| 1588 |
-
},
|
| 1589 |
-
"enable_sound_notifications": {
|
| 1590 |
-
"type": "boolean"
|
| 1591 |
-
},
|
| 1592 |
-
"user_consents_to_analytics": {
|
| 1593 |
-
"type": "boolean"
|
| 1594 |
-
},
|
| 1595 |
-
"provider_tokens": {
|
| 1596 |
-
"type": "object",
|
| 1597 |
-
"additionalProperties": {
|
| 1598 |
-
"type": "string"
|
| 1599 |
-
}
|
| 1600 |
-
}
|
| 1601 |
-
}
|
| 1602 |
-
}
|
| 1603 |
-
}
|
| 1604 |
-
}
|
| 1605 |
-
},
|
| 1606 |
-
"responses": {
|
| 1607 |
-
"200": {
|
| 1608 |
-
"description": "Settings stored successfully",
|
| 1609 |
-
"content": {
|
| 1610 |
-
"application/json": {
|
| 1611 |
-
"schema": {
|
| 1612 |
-
"type": "object",
|
| 1613 |
-
"properties": {
|
| 1614 |
-
"message": {
|
| 1615 |
-
"type": "string"
|
| 1616 |
-
}
|
| 1617 |
-
}
|
| 1618 |
-
}
|
| 1619 |
-
}
|
| 1620 |
-
}
|
| 1621 |
-
},
|
| 1622 |
-
"401": {
|
| 1623 |
-
"description": "Invalid token",
|
| 1624 |
-
"content": {
|
| 1625 |
-
"application/json": {
|
| 1626 |
-
"schema": {
|
| 1627 |
-
"type": "object",
|
| 1628 |
-
"properties": {
|
| 1629 |
-
"error": {
|
| 1630 |
-
"type": "string"
|
| 1631 |
-
}
|
| 1632 |
-
}
|
| 1633 |
-
}
|
| 1634 |
-
}
|
| 1635 |
-
}
|
| 1636 |
-
},
|
| 1637 |
-
"500": {
|
| 1638 |
-
"description": "Error storing settings",
|
| 1639 |
-
"content": {
|
| 1640 |
-
"application/json": {
|
| 1641 |
-
"schema": {
|
| 1642 |
-
"type": "object",
|
| 1643 |
-
"properties": {
|
| 1644 |
-
"error": {
|
| 1645 |
-
"type": "string"
|
| 1646 |
-
}
|
| 1647 |
-
}
|
| 1648 |
-
}
|
| 1649 |
-
}
|
| 1650 |
-
}
|
| 1651 |
-
}
|
| 1652 |
-
}
|
| 1653 |
-
}
|
| 1654 |
-
},
|
| 1655 |
-
"/api/reset-settings": {
|
| 1656 |
-
"post": {
|
| 1657 |
-
"summary": "Reset settings (Deprecated)",
|
| 1658 |
-
"description": "This endpoint is deprecated and will return a 410 Gone error. Reset functionality has been removed.",
|
| 1659 |
-
"operationId": "resetSettings",
|
| 1660 |
-
"deprecated": true,
|
| 1661 |
-
"responses": {
|
| 1662 |
-
"410": {
|
| 1663 |
-
"description": "Feature removed",
|
| 1664 |
-
"content": {
|
| 1665 |
-
"application/json": {
|
| 1666 |
-
"schema": {
|
| 1667 |
-
"type": "object",
|
| 1668 |
-
"properties": {
|
| 1669 |
-
"error": {
|
| 1670 |
-
"type": "string",
|
| 1671 |
-
"example": "Reset settings functionality has been removed."
|
| 1672 |
-
}
|
| 1673 |
-
}
|
| 1674 |
-
}
|
| 1675 |
-
}
|
| 1676 |
-
}
|
| 1677 |
-
}
|
| 1678 |
-
}
|
| 1679 |
-
}
|
| 1680 |
-
},
|
| 1681 |
-
"/api/unset-settings-tokens": {
|
| 1682 |
-
"post": {
|
| 1683 |
-
"summary": "Unset settings tokens",
|
| 1684 |
-
"description": "Unset provider tokens in settings",
|
| 1685 |
-
"operationId": "unsetSettingsTokens",
|
| 1686 |
-
"responses": {
|
| 1687 |
-
"200": {
|
| 1688 |
-
"description": "Tokens unset successfully",
|
| 1689 |
-
"content": {
|
| 1690 |
-
"application/json": {
|
| 1691 |
-
"schema": {
|
| 1692 |
-
"type": "object",
|
| 1693 |
-
"properties": {
|
| 1694 |
-
"message": {
|
| 1695 |
-
"type": "string"
|
| 1696 |
-
}
|
| 1697 |
-
}
|
| 1698 |
-
}
|
| 1699 |
-
}
|
| 1700 |
-
}
|
| 1701 |
-
},
|
| 1702 |
-
"500": {
|
| 1703 |
-
"description": "Error unsetting tokens",
|
| 1704 |
-
"content": {
|
| 1705 |
-
"application/json": {
|
| 1706 |
-
"schema": {
|
| 1707 |
-
"type": "object",
|
| 1708 |
-
"properties": {
|
| 1709 |
-
"error": {
|
| 1710 |
-
"type": "string"
|
| 1711 |
-
}
|
| 1712 |
-
}
|
| 1713 |
-
}
|
| 1714 |
-
}
|
| 1715 |
-
}
|
| 1716 |
-
}
|
| 1717 |
-
}
|
| 1718 |
-
}
|
| 1719 |
-
},
|
| 1720 |
-
"/api/options/models": {
|
| 1721 |
-
"get": {
|
| 1722 |
-
"summary": "Get models",
|
| 1723 |
-
"description": "Get all models supported by LiteLLM",
|
| 1724 |
-
"operationId": "getLitellmModels",
|
| 1725 |
-
"responses": {
|
| 1726 |
-
"200": {
|
| 1727 |
-
"description": "List of models",
|
| 1728 |
-
"content": {
|
| 1729 |
-
"application/json": {
|
| 1730 |
-
"schema": {
|
| 1731 |
-
"type": "array",
|
| 1732 |
-
"items": {
|
| 1733 |
-
"type": "string"
|
| 1734 |
-
}
|
| 1735 |
-
}
|
| 1736 |
-
}
|
| 1737 |
-
}
|
| 1738 |
-
}
|
| 1739 |
-
}
|
| 1740 |
-
}
|
| 1741 |
-
},
|
| 1742 |
-
"/api/options/agents": {
|
| 1743 |
-
"get": {
|
| 1744 |
-
"summary": "Get agents",
|
| 1745 |
-
"description": "Get all agents supported by OpenHands",
|
| 1746 |
-
"operationId": "getAgents",
|
| 1747 |
-
"responses": {
|
| 1748 |
-
"200": {
|
| 1749 |
-
"description": "List of agents",
|
| 1750 |
-
"content": {
|
| 1751 |
-
"application/json": {
|
| 1752 |
-
"schema": {
|
| 1753 |
-
"type": "array",
|
| 1754 |
-
"items": {
|
| 1755 |
-
"type": "string"
|
| 1756 |
-
}
|
| 1757 |
-
}
|
| 1758 |
-
}
|
| 1759 |
-
}
|
| 1760 |
-
}
|
| 1761 |
-
}
|
| 1762 |
-
}
|
| 1763 |
-
},
|
| 1764 |
-
"/api/options/security-analyzers": {
|
| 1765 |
-
"get": {
|
| 1766 |
-
"summary": "Get security analyzers",
|
| 1767 |
-
"description": "Get all supported security analyzers",
|
| 1768 |
-
"operationId": "getSecurityAnalyzers",
|
| 1769 |
-
"responses": {
|
| 1770 |
-
"200": {
|
| 1771 |
-
"description": "List of security analyzers",
|
| 1772 |
-
"content": {
|
| 1773 |
-
"application/json": {
|
| 1774 |
-
"schema": {
|
| 1775 |
-
"type": "array",
|
| 1776 |
-
"items": {
|
| 1777 |
-
"type": "string"
|
| 1778 |
-
}
|
| 1779 |
-
}
|
| 1780 |
-
}
|
| 1781 |
-
}
|
| 1782 |
-
}
|
| 1783 |
-
}
|
| 1784 |
-
}
|
| 1785 |
-
},
|
| 1786 |
-
"/api/options/config": {
|
| 1787 |
-
"get": {
|
| 1788 |
-
"summary": "Get config",
|
| 1789 |
-
"description": "Get current server configuration",
|
| 1790 |
-
"operationId": "getConfig",
|
| 1791 |
-
"responses": {
|
| 1792 |
-
"200": {
|
| 1793 |
-
"description": "Server configuration",
|
| 1794 |
-
"content": {
|
| 1795 |
-
"application/json": {
|
| 1796 |
-
"schema": {
|
| 1797 |
-
"type": "object"
|
| 1798 |
-
}
|
| 1799 |
-
}
|
| 1800 |
-
}
|
| 1801 |
-
}
|
| 1802 |
-
}
|
| 1803 |
-
}
|
| 1804 |
-
}
|
| 1805 |
-
},
|
| 1806 |
-
"components": {
|
| 1807 |
-
"schemas": {
|
| 1808 |
-
"Repository": {
|
| 1809 |
-
"type": "object",
|
| 1810 |
-
"properties": {
|
| 1811 |
-
"full_name": {
|
| 1812 |
-
"type": "string"
|
| 1813 |
-
},
|
| 1814 |
-
"description": {
|
| 1815 |
-
"type": "string",
|
| 1816 |
-
"nullable": true
|
| 1817 |
-
},
|
| 1818 |
-
"html_url": {
|
| 1819 |
-
"type": "string"
|
| 1820 |
-
},
|
| 1821 |
-
"private": {
|
| 1822 |
-
"type": "boolean"
|
| 1823 |
-
},
|
| 1824 |
-
"fork": {
|
| 1825 |
-
"type": "boolean"
|
| 1826 |
-
},
|
| 1827 |
-
"updated_at": {
|
| 1828 |
-
"type": "string",
|
| 1829 |
-
"format": "date-time"
|
| 1830 |
-
}
|
| 1831 |
-
}
|
| 1832 |
-
},
|
| 1833 |
-
"User": {
|
| 1834 |
-
"type": "object",
|
| 1835 |
-
"properties": {
|
| 1836 |
-
"login": {
|
| 1837 |
-
"type": "string"
|
| 1838 |
-
},
|
| 1839 |
-
"name": {
|
| 1840 |
-
"type": "string",
|
| 1841 |
-
"nullable": true
|
| 1842 |
-
},
|
| 1843 |
-
"email": {
|
| 1844 |
-
"type": "string",
|
| 1845 |
-
"nullable": true
|
| 1846 |
-
},
|
| 1847 |
-
"avatar_url": {
|
| 1848 |
-
"type": "string",
|
| 1849 |
-
"nullable": true
|
| 1850 |
-
}
|
| 1851 |
-
}
|
| 1852 |
-
},
|
| 1853 |
-
"SuggestedTask": {
|
| 1854 |
-
"type": "object",
|
| 1855 |
-
"properties": {
|
| 1856 |
-
"title": {
|
| 1857 |
-
"type": "string"
|
| 1858 |
-
},
|
| 1859 |
-
"url": {
|
| 1860 |
-
"type": "string"
|
| 1861 |
-
},
|
| 1862 |
-
"repository": {
|
| 1863 |
-
"type": "string"
|
| 1864 |
-
},
|
| 1865 |
-
"type": {
|
| 1866 |
-
"type": "string"
|
| 1867 |
-
},
|
| 1868 |
-
"created_at": {
|
| 1869 |
-
"type": "string",
|
| 1870 |
-
"format": "date-time"
|
| 1871 |
-
}
|
| 1872 |
-
}
|
| 1873 |
-
},
|
| 1874 |
-
"ConversationInfo": {
|
| 1875 |
-
"type": "object",
|
| 1876 |
-
"properties": {
|
| 1877 |
-
"conversation_id": {
|
| 1878 |
-
"type": "string"
|
| 1879 |
-
},
|
| 1880 |
-
"title": {
|
| 1881 |
-
"type": "string"
|
| 1882 |
-
},
|
| 1883 |
-
"last_updated_at": {
|
| 1884 |
-
"type": "string",
|
| 1885 |
-
"format": "date-time"
|
| 1886 |
-
},
|
| 1887 |
-
"created_at": {
|
| 1888 |
-
"type": "string",
|
| 1889 |
-
"format": "date-time"
|
| 1890 |
-
},
|
| 1891 |
-
"selected_repository": {
|
| 1892 |
-
"type": "string",
|
| 1893 |
-
"nullable": true
|
| 1894 |
-
},
|
| 1895 |
-
"status": {
|
| 1896 |
-
"type": "string",
|
| 1897 |
-
"enum": ["RUNNING", "STOPPED"]
|
| 1898 |
-
},
|
| 1899 |
-
"trigger": {
|
| 1900 |
-
"type": "string",
|
| 1901 |
-
"enum": ["GUI", "API"]
|
| 1902 |
-
}
|
| 1903 |
-
}
|
| 1904 |
-
},
|
| 1905 |
-
"ConversationInfoResultSet": {
|
| 1906 |
-
"type": "object",
|
| 1907 |
-
"properties": {
|
| 1908 |
-
"results": {
|
| 1909 |
-
"type": "array",
|
| 1910 |
-
"items": {
|
| 1911 |
-
"$ref": "#/components/schemas/ConversationInfo"
|
| 1912 |
-
}
|
| 1913 |
-
},
|
| 1914 |
-
"next_page_id": {
|
| 1915 |
-
"type": "string",
|
| 1916 |
-
"nullable": true
|
| 1917 |
-
}
|
| 1918 |
-
}
|
| 1919 |
-
},
|
| 1920 |
-
"FeedbackDataModel": {
|
| 1921 |
-
"type": "object",
|
| 1922 |
-
"properties": {
|
| 1923 |
-
"email": {
|
| 1924 |
-
"type": "string",
|
| 1925 |
-
"format": "email"
|
| 1926 |
-
},
|
| 1927 |
-
"version": {
|
| 1928 |
-
"type": "string"
|
| 1929 |
-
},
|
| 1930 |
-
"permissions": {
|
| 1931 |
-
"type": "string",
|
| 1932 |
-
"default": "private"
|
| 1933 |
-
},
|
| 1934 |
-
"polarity": {
|
| 1935 |
-
"type": "string"
|
| 1936 |
-
},
|
| 1937 |
-
"feedback": {
|
| 1938 |
-
"type": "string"
|
| 1939 |
-
},
|
| 1940 |
-
"trajectory": {
|
| 1941 |
-
"type": "array",
|
| 1942 |
-
"items": {
|
| 1943 |
-
"type": "object"
|
| 1944 |
-
}
|
| 1945 |
-
}
|
| 1946 |
-
}
|
| 1947 |
-
},
|
| 1948 |
-
"Settings": {
|
| 1949 |
-
"type": "object",
|
| 1950 |
-
"properties": {
|
| 1951 |
-
"language": {
|
| 1952 |
-
"type": "string"
|
| 1953 |
-
},
|
| 1954 |
-
"agent": {
|
| 1955 |
-
"type": "string"
|
| 1956 |
-
},
|
| 1957 |
-
"security_analyzer": {
|
| 1958 |
-
"type": "string"
|
| 1959 |
-
},
|
| 1960 |
-
"confirmation_mode": {
|
| 1961 |
-
"type": "boolean"
|
| 1962 |
-
},
|
| 1963 |
-
"llm_model": {
|
| 1964 |
-
"type": "string"
|
| 1965 |
-
},
|
| 1966 |
-
"llm_api_key": {
|
| 1967 |
-
"type": "string"
|
| 1968 |
-
},
|
| 1969 |
-
"llm_base_url": {
|
| 1970 |
-
"type": "string",
|
| 1971 |
-
"nullable": true
|
| 1972 |
-
},
|
| 1973 |
-
"remote_runtime_resource_factor": {
|
| 1974 |
-
"type": "number"
|
| 1975 |
-
},
|
| 1976 |
-
"enable_default_condenser": {
|
| 1977 |
-
"type": "boolean"
|
| 1978 |
-
},
|
| 1979 |
-
"enable_sound_notifications": {
|
| 1980 |
-
"type": "boolean"
|
| 1981 |
-
},
|
| 1982 |
-
"user_consents_to_analytics": {
|
| 1983 |
-
"type": "boolean"
|
| 1984 |
-
}
|
| 1985 |
-
}
|
| 1986 |
-
},
|
| 1987 |
-
"GETSettingsModel": {
|
| 1988 |
-
"type": "object",
|
| 1989 |
-
"properties": {
|
| 1990 |
-
"language": {
|
| 1991 |
-
"type": "string"
|
| 1992 |
-
},
|
| 1993 |
-
"agent": {
|
| 1994 |
-
"type": "string"
|
| 1995 |
-
},
|
| 1996 |
-
"security_analyzer": {
|
| 1997 |
-
"type": "string"
|
| 1998 |
-
},
|
| 1999 |
-
"confirmation_mode": {
|
| 2000 |
-
"type": "boolean"
|
| 2001 |
-
},
|
| 2002 |
-
"llm_model": {
|
| 2003 |
-
"type": "string"
|
| 2004 |
-
},
|
| 2005 |
-
"llm_api_key_set": {
|
| 2006 |
-
"type": "boolean"
|
| 2007 |
-
},
|
| 2008 |
-
"llm_base_url": {
|
| 2009 |
-
"type": "string",
|
| 2010 |
-
"nullable": true
|
| 2011 |
-
},
|
| 2012 |
-
"remote_runtime_resource_factor": {
|
| 2013 |
-
"type": "number"
|
| 2014 |
-
},
|
| 2015 |
-
"enable_default_condenser": {
|
| 2016 |
-
"type": "boolean"
|
| 2017 |
-
},
|
| 2018 |
-
"enable_sound_notifications": {
|
| 2019 |
-
"type": "boolean"
|
| 2020 |
-
},
|
| 2021 |
-
"user_consents_to_analytics": {
|
| 2022 |
-
"type": "boolean"
|
| 2023 |
-
},
|
| 2024 |
-
"provider_tokens_set": {
|
| 2025 |
-
"type": "object",
|
| 2026 |
-
"additionalProperties": {
|
| 2027 |
-
"type": "boolean"
|
| 2028 |
-
}
|
| 2029 |
-
}
|
| 2030 |
-
}
|
| 2031 |
-
},
|
| 2032 |
-
"POSTSettingsModel": {
|
| 2033 |
-
"type": "object",
|
| 2034 |
-
"properties": {
|
| 2035 |
-
"language": {
|
| 2036 |
-
"type": "string"
|
| 2037 |
-
},
|
| 2038 |
-
"agent": {
|
| 2039 |
-
"type": "string"
|
| 2040 |
-
},
|
| 2041 |
-
"security_analyzer": {
|
| 2042 |
-
"type": "string"
|
| 2043 |
-
},
|
| 2044 |
-
"confirmation_mode": {
|
| 2045 |
-
"type": "boolean"
|
| 2046 |
-
},
|
| 2047 |
-
"llm_model": {
|
| 2048 |
-
"type": "string"
|
| 2049 |
-
},
|
| 2050 |
-
"llm_api_key": {
|
| 2051 |
-
"type": "string"
|
| 2052 |
-
},
|
| 2053 |
-
"llm_base_url": {
|
| 2054 |
-
"type": "string",
|
| 2055 |
-
"nullable": true
|
| 2056 |
-
},
|
| 2057 |
-
"remote_runtime_resource_factor": {
|
| 2058 |
-
"type": "number"
|
| 2059 |
-
},
|
| 2060 |
-
"enable_default_condenser": {
|
| 2061 |
-
"type": "boolean"
|
| 2062 |
-
},
|
| 2063 |
-
"enable_sound_notifications": {
|
| 2064 |
-
"type": "boolean"
|
| 2065 |
-
},
|
| 2066 |
-
"user_consents_to_analytics": {
|
| 2067 |
-
"type": "boolean"
|
| 2068 |
-
},
|
| 2069 |
-
"provider_tokens": {
|
| 2070 |
-
"type": "object",
|
| 2071 |
-
"additionalProperties": {
|
| 2072 |
-
"type": "string"
|
| 2073 |
-
}
|
| 2074 |
-
}
|
| 2075 |
-
}
|
| 2076 |
-
}
|
| 2077 |
-
},
|
| 2078 |
-
"securitySchemes": {
|
| 2079 |
-
"bearerAuth": {
|
| 2080 |
-
"type": "http",
|
| 2081 |
-
"scheme": "bearer",
|
| 2082 |
-
"bearerFormat": "JWT"
|
| 2083 |
-
}
|
| 2084 |
-
}
|
| 2085 |
-
},
|
| 2086 |
-
"security": [
|
| 2087 |
-
{
|
| 2088 |
-
"bearerAuth": []
|
| 2089 |
-
}
|
| 2090 |
-
]
|
| 2091 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/static/img/backend_architecture.png
DELETED
Git LFS Details
|
docs/static/img/backend_architecture.puml
DELETED
|
@@ -1,201 +0,0 @@
|
|
| 1 |
-
@startuml openhands
|
| 2 |
-
!pragma useIntermediatePackages false
|
| 3 |
-
|
| 4 |
-
class openhands.action.agent.AgentEchoAction {
|
| 5 |
-
content: str
|
| 6 |
-
runnable: bool
|
| 7 |
-
action: str
|
| 8 |
-
}
|
| 9 |
-
class openhands.action.agent.AgentFinishAction {
|
| 10 |
-
runnable: bool
|
| 11 |
-
action: str
|
| 12 |
-
}
|
| 13 |
-
class openhands.observation.AgentMessageObservation {
|
| 14 |
-
role: str
|
| 15 |
-
observation: str
|
| 16 |
-
}
|
| 17 |
-
class openhands.action.agent.AgentSummarizeAction {
|
| 18 |
-
summary: str
|
| 19 |
-
action: str
|
| 20 |
-
}
|
| 21 |
-
class openhands.action.agent.AgentThinkAction {
|
| 22 |
-
thought: str
|
| 23 |
-
runnable: bool
|
| 24 |
-
action: str
|
| 25 |
-
}
|
| 26 |
-
class openhands.action.base.ExecutableAction {
|
| 27 |
-
}
|
| 28 |
-
class openhands.action.base.NotExecutableAction {
|
| 29 |
-
}
|
| 30 |
-
class openhands.observation.Observation {
|
| 31 |
-
content: str
|
| 32 |
-
}
|
| 33 |
-
class openhands.action.base.Action {
|
| 34 |
-
}
|
| 35 |
-
class openhands.action.base.NullAction {
|
| 36 |
-
action: str
|
| 37 |
-
}
|
| 38 |
-
class openhands.action.bash.CmdRunAction {
|
| 39 |
-
command: str
|
| 40 |
-
action: str
|
| 41 |
-
}
|
| 42 |
-
class openhands.action.browse.BrowseURLAction {
|
| 43 |
-
url: str
|
| 44 |
-
action: str
|
| 45 |
-
}
|
| 46 |
-
class openhands.observation.BrowserOutputObservation {
|
| 47 |
-
url: str
|
| 48 |
-
status_code: int
|
| 49 |
-
error: bool
|
| 50 |
-
observation: str
|
| 51 |
-
}
|
| 52 |
-
class openhands.action.fileop.FileReadAction {
|
| 53 |
-
path: str
|
| 54 |
-
action: str
|
| 55 |
-
}
|
| 56 |
-
class openhands.observation.FileReadObservation {
|
| 57 |
-
path: str
|
| 58 |
-
observation: str
|
| 59 |
-
}
|
| 60 |
-
class openhands.action.fileop.FileWriteAction {
|
| 61 |
-
path: str
|
| 62 |
-
contents: str
|
| 63 |
-
action: str
|
| 64 |
-
}
|
| 65 |
-
class openhands.observation.FileWriteObservation {
|
| 66 |
-
path: str
|
| 67 |
-
observation: str
|
| 68 |
-
}
|
| 69 |
-
class openhands.action.tasks.AddTaskAction {
|
| 70 |
-
parent: str
|
| 71 |
-
goal: str
|
| 72 |
-
subtasks: list
|
| 73 |
-
action: str
|
| 74 |
-
}
|
| 75 |
-
class openhands.action.tasks.ModifyTaskAction {
|
| 76 |
-
id: str
|
| 77 |
-
state: str
|
| 78 |
-
action: str
|
| 79 |
-
}
|
| 80 |
-
abstract class openhands.agent.Agent {
|
| 81 |
-
_registry: Dict[str, Type[Agent]] {static}
|
| 82 |
-
llm: LLM
|
| 83 |
-
_complete: None
|
| 84 |
-
}
|
| 85 |
-
class openhands.llm.llm.LLM {
|
| 86 |
-
model: None
|
| 87 |
-
api_key: None
|
| 88 |
-
base_url: None
|
| 89 |
-
_debug_dir: None
|
| 90 |
-
_debug_idx: None
|
| 91 |
-
_debug_id: None
|
| 92 |
-
_completion: None
|
| 93 |
-
}
|
| 94 |
-
class openhands.controller.agent_controller.AgentController {
|
| 95 |
-
agent: Agent
|
| 96 |
-
max_iterations: int
|
| 97 |
-
workdir: str
|
| 98 |
-
command_manager: CommandManager
|
| 99 |
-
state: State
|
| 100 |
-
plan: Plan
|
| 101 |
-
callbacks: List[Callable]
|
| 102 |
-
}
|
| 103 |
-
class openhands.observation.AgentErrorObservation {
|
| 104 |
-
observation: str
|
| 105 |
-
}
|
| 106 |
-
class openhands.controller.command_manager.CommandManager {
|
| 107 |
-
directory: None
|
| 108 |
-
shell: None
|
| 109 |
-
}
|
| 110 |
-
class openhands.observation.NullObservation {
|
| 111 |
-
observation: str
|
| 112 |
-
}
|
| 113 |
-
class openhands.plan.Plan {
|
| 114 |
-
main_goal: str {static}
|
| 115 |
-
task: Task {static}
|
| 116 |
-
main_goal: str
|
| 117 |
-
task: None
|
| 118 |
-
}
|
| 119 |
-
class openhands.state.State {
|
| 120 |
-
plan: Plan
|
| 121 |
-
iteration: int
|
| 122 |
-
history: List[Tuple[Action, Observation]]
|
| 123 |
-
updated_info: List[Tuple[Action, Observation]]
|
| 124 |
-
}
|
| 125 |
-
class openhands.observation.CmdOutputObservation {
|
| 126 |
-
command: str
|
| 127 |
-
exit_code: int
|
| 128 |
-
observation: str
|
| 129 |
-
}
|
| 130 |
-
class openhands.sandbox.sandbox.DockerInteractive {
|
| 131 |
-
instance_id: None
|
| 132 |
-
instance_id: None
|
| 133 |
-
workspace_dir: None
|
| 134 |
-
workspace_dir: None
|
| 135 |
-
workspace_dir: None
|
| 136 |
-
timeout: int
|
| 137 |
-
base_container_image: None
|
| 138 |
-
container_name: None
|
| 139 |
-
}
|
| 140 |
-
class openhands.observation.UserMessageObservation {
|
| 141 |
-
role: str
|
| 142 |
-
observation: str
|
| 143 |
-
}
|
| 144 |
-
class openhands.plan.Task {
|
| 145 |
-
id: str {static}
|
| 146 |
-
goal: str {static}
|
| 147 |
-
parent: Task | None {static}
|
| 148 |
-
subtasks: List[Task] {static}
|
| 149 |
-
id: None
|
| 150 |
-
id: None
|
| 151 |
-
parent: None
|
| 152 |
-
goal: str
|
| 153 |
-
subtasks: None
|
| 154 |
-
}
|
| 155 |
-
|
| 156 |
-
class openhands.server.session.Session {
|
| 157 |
-
websocket: None
|
| 158 |
-
controller: Optional[AgentController]
|
| 159 |
-
agent: Optional[Agent]
|
| 160 |
-
agent_task: None
|
| 161 |
-
}
|
| 162 |
-
|
| 163 |
-
openhands.action.base.ExecutableAction <|-- openhands.action.agent.AgentEchoAction
|
| 164 |
-
openhands.action.base.NotExecutableAction <|-- openhands.action.agent.AgentFinishAction
|
| 165 |
-
openhands.observation.Observation <|-- openhands.observation.AgentMessageObservation
|
| 166 |
-
openhands.action.base.NotExecutableAction <|-- openhands.action.agent.AgentSummarizeAction
|
| 167 |
-
openhands.action.base.NotExecutableAction <|-- openhands.action.agent.AgentThinkAction
|
| 168 |
-
openhands.action.base.Action <|-- openhands.action.base.ExecutableAction
|
| 169 |
-
openhands.action.base.Action <|-- openhands.action.base.NotExecutableAction
|
| 170 |
-
openhands.action.base.NotExecutableAction <|-- openhands.action.base.NullAction
|
| 171 |
-
openhands.action.base.ExecutableAction <|-- openhands.action.bash.CmdRunAction
|
| 172 |
-
openhands.action.base.ExecutableAction <|-- openhands.action.browse.BrowseURLAction
|
| 173 |
-
openhands.observation.Observation <|-- openhands.observation.BrowserOutputObservation
|
| 174 |
-
openhands.action.base.ExecutableAction <|-- openhands.action.fileop.FileReadAction
|
| 175 |
-
openhands.observation.Observation <|-- openhands.observation.FileReadObservation
|
| 176 |
-
openhands.action.base.ExecutableAction <|-- openhands.action.fileop.FileWriteAction
|
| 177 |
-
openhands.observation.Observation <|-- openhands.observation.FileWriteObservation
|
| 178 |
-
openhands.action.base.NotExecutableAction <|-- openhands.action.tasks.AddTaskAction
|
| 179 |
-
openhands.action.base.NotExecutableAction <|-- openhands.action.tasks.ModifyTaskAction
|
| 180 |
-
openhands.agent.Agent *-- openhands.agent.Agent
|
| 181 |
-
openhands.agent.Agent *-- openhands.llm.llm.LLM
|
| 182 |
-
openhands.controller.agent_controller.AgentController *-- openhands.agent.Agent
|
| 183 |
-
openhands.observation.Observation <|-- openhands.observation.AgentErrorObservation
|
| 184 |
-
openhands.observation.Observation <|-- openhands.observation.NullObservation
|
| 185 |
-
openhands.plan.Plan *-- openhands.plan.Task
|
| 186 |
-
openhands.state.State *-- openhands.plan.Plan
|
| 187 |
-
openhands.state.State *-- openhands.observation.CmdOutputObservation
|
| 188 |
-
openhands.state.State *-- openhands.action.base.Action
|
| 189 |
-
openhands.state.State *-- openhands.observation.Observation
|
| 190 |
-
openhands.observation.Observation <|-- openhands.observation.CmdOutputObservation
|
| 191 |
-
openhands.observation.Observation <|-- openhands.observation.UserMessageObservation
|
| 192 |
-
openhands.plan.Task *-- openhands.plan.Task
|
| 193 |
-
openhands.server.session.Session *-- openhands.controller.agent_controller.AgentController
|
| 194 |
-
openhands.server.session.Session *-- openhands.agent.Agent
|
| 195 |
-
openhands.controller.agent_controller.AgentController -> openhands.state.State
|
| 196 |
-
openhands.controller.agent_controller.AgentController -> openhands.plan.Plan
|
| 197 |
-
openhands.controller.agent_controller.AgentController -> openhands.controller.command_manager.CommandManager
|
| 198 |
-
openhands.controller.command_manager.CommandManager -> openhands.sandbox.sandbox.DockerInteractive
|
| 199 |
-
|
| 200 |
-
footer Based on f3fda42; Generated by //py2puml//
|
| 201 |
-
@enduml
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/static/img/backend_architecture.svg
DELETED
docs/static/img/connect-repo.png
DELETED
|
Binary file (18.9 kB)
|
|
|
docs/static/img/docs/api-key-generation.png
DELETED
|
Binary file (26.8 kB)
|
|
|
docs/static/img/logo-square.png
DELETED
Git LFS Details
|
docs/static/img/logo.png
DELETED
|
Binary file (21.2 kB)
|
|
|
docs/static/img/oh-features.png
DELETED
Git LFS Details
|
docs/static/img/results.png
DELETED
Git LFS Details
|
docs/static/img/screenshot.png
DELETED
Git LFS Details
|
docs/static/img/system_architecture.png
DELETED
|
Binary file (42.6 kB)
|
|
|
docs/static/img/system_architecture.puml
DELETED
|
@@ -1,67 +0,0 @@
|
|
| 1 |
-
@startuml "System Architecture"
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
node frontend as frontend{
|
| 5 |
-
|
| 6 |
-
component App
|
| 7 |
-
|
| 8 |
-
package components{
|
| 9 |
-
|
| 10 |
-
component Terminal
|
| 11 |
-
|
| 12 |
-
component ChatInterface
|
| 13 |
-
|
| 14 |
-
component BannerSettings
|
| 15 |
-
|
| 16 |
-
}
|
| 17 |
-
|
| 18 |
-
package services{
|
| 19 |
-
component chatService
|
| 20 |
-
|
| 21 |
-
component settingsService
|
| 22 |
-
|
| 23 |
-
chatService -[hidden]u-> settingsService
|
| 24 |
-
}
|
| 25 |
-
|
| 26 |
-
package socket
|
| 27 |
-
|
| 28 |
-
App -> Terminal
|
| 29 |
-
App -> ChatInterface
|
| 30 |
-
App -> BannerSettings
|
| 31 |
-
ChatInterface -> chatService
|
| 32 |
-
BannerSettings -> settingsService
|
| 33 |
-
Terminal -> socket
|
| 34 |
-
chatService -d-> socket
|
| 35 |
-
settingsService -d-> socket
|
| 36 |
-
services -[hidden]d-> socket
|
| 37 |
-
|
| 38 |
-
Terminal -[hidden]u-> ChatInterface
|
| 39 |
-
ChatInterface -[hidden]u-> BannerSettings
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
interface "HTTP (:3001)" as HTTP
|
| 44 |
-
HTTP - App
|
| 45 |
-
|
| 46 |
-
}
|
| 47 |
-
|
| 48 |
-
node backend{
|
| 49 |
-
package server as serverpackage{
|
| 50 |
-
component Server
|
| 51 |
-
|
| 52 |
-
'defined in server/server.py, port is defined at startup with uvicorn
|
| 53 |
-
interface "Client WS\n(:3000/ws)" as client_socket
|
| 54 |
-
client_socket - Server
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
}
|
| 58 |
-
node AgentController{
|
| 59 |
-
|
| 60 |
-
}
|
| 61 |
-
Server -d-> AgentController
|
| 62 |
-
}
|
| 63 |
-
|
| 64 |
-
|
| 65 |
-
socket -d-> client_socket: connects to \n VITE_TERMINAL_WS_URL
|
| 66 |
-
|
| 67 |
-
@enduml
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/static/img/system_architecture.svg
DELETED
docs/static/img/system_architecture_overview.png
DELETED
Git LFS Details
|
docs/static/img/teaser.mp4
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:a2b9dfd699226a4e6d3e2bb0926941f954cc11c68024e011c861215bb81ff381
|
| 3 |
-
size 36187951
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/about.mdx
DELETED
|
@@ -1,30 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: About OpenHands
|
| 3 |
-
---
|
| 4 |
-
|
| 5 |
-
## Research Strategy
|
| 6 |
-
|
| 7 |
-
Achieving full replication of production-grade applications with LLMs is a complex endeavor. Our strategy involves:
|
| 8 |
-
|
| 9 |
-
- **Core Technical Research:** Focusing on foundational research to understand and improve the technical aspects of code generation and handling.
|
| 10 |
-
- **Task Planning:** Developing capabilities for bug detection, codebase management, and optimization.
|
| 11 |
-
- **Evaluation:** Establishing comprehensive evaluation metrics to better understand and improve our agents.
|
| 12 |
-
|
| 13 |
-
## Default Agent
|
| 14 |
-
|
| 15 |
-
Our default Agent is currently the [CodeActAgent](./agents), which is capable of generating code and handling files.
|
| 16 |
-
|
| 17 |
-
## Built With
|
| 18 |
-
|
| 19 |
-
OpenHands is built using a combination of powerful frameworks and libraries, providing a robust foundation for its
|
| 20 |
-
development. Here are the key technologies used in the project:
|
| 21 |
-
|
| 22 |
-
       
|
| 23 |
-
|
| 24 |
-
Please note that the selection of these technologies is in progress, and additional technologies may be added or
|
| 25 |
-
existing ones may be removed as the project evolves. We strive to adopt the most suitable and efficient tools to
|
| 26 |
-
enhance the capabilities of OpenHands.
|
| 27 |
-
|
| 28 |
-
## License
|
| 29 |
-
|
| 30 |
-
Distributed under MIT [License](https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/agents.mdx
DELETED
|
@@ -1,26 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Main Agent and Capabilities
|
| 3 |
-
---
|
| 4 |
-
|
| 5 |
-
## CodeActAgent
|
| 6 |
-
|
| 7 |
-
### Description
|
| 8 |
-
|
| 9 |
-
This agent implements the CodeAct idea ([paper](https://arxiv.org/abs/2402.01030), [tweet](https://twitter.com/xingyaow_/status/1754556835703751087)) that consolidates LLM agents’ **act**ions into a
|
| 10 |
-
unified **code** action space for both _simplicity_ and _performance_.
|
| 11 |
-
|
| 12 |
-
The conceptual idea is illustrated below. At each turn, the agent can:
|
| 13 |
-
|
| 14 |
-
1. **Converse**: Communicate with humans in natural language to ask for clarification, confirmation, etc.
|
| 15 |
-
2. **CodeAct**: Choose to perform the task by executing code
|
| 16 |
-
|
| 17 |
-
- Execute any valid Linux `bash` command
|
| 18 |
-
- Execute any valid `Python` code with [an interactive Python interpreter](https://ipython.org/). This is simulated through `bash` command, see plugin system below for more details.
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
### Demo
|
| 23 |
-
|
| 24 |
-
https://github.com/All-Hands-AI/OpenHands/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
|
| 25 |
-
|
| 26 |
-
_Example of CodeActAgent with `gpt-4-turbo-2024-04-09` performing a data science task (linear regression)_.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/architecture/backend.mdx
DELETED
|
@@ -1,56 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Backend Architecture
|
| 3 |
-
---
|
| 4 |
-
|
| 5 |
-
<div style={{ textAlign: 'center' }}>
|
| 6 |
-
<img src="https://github.com/All-Hands-AI/OpenHands/assets/16201837/97d747e3-29d8-4ccb-8d34-6ad1adb17f38" alt="OpenHands System Architecture Diagram Jul 4 2024" />
|
| 7 |
-
<p><em>OpenHands System Architecture Diagram (July 4, 2024)</em></p>
|
| 8 |
-
</div>
|
| 9 |
-
|
| 10 |
-
This is a high-level overview of the system architecture. The system is divided into two main components: the frontend and the backend. The frontend is responsible for handling user interactions and displaying the results. The backend is responsible for handling the business logic and executing the agents.
|
| 11 |
-
|
| 12 |
-
# Frontend architecture
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
This Overview is simplified to show the main components and their interactions. For a more detailed view of the backend architecture, see the Backend Architecture section below.
|
| 17 |
-
|
| 18 |
-
# Backend Architecture
|
| 19 |
-
|
| 20 |
-
_**Disclaimer**: The backend architecture is a work in progress and is subject to change. The following diagram shows the current architecture of the backend based on the commit that is shown in the footer of the diagram._
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
<details>
|
| 25 |
-
<summary>Updating this Diagram</summary>
|
| 26 |
-
<div>
|
| 27 |
-
The generation of the backend architecture diagram is partially automated.
|
| 28 |
-
The diagram is generated from the type hints in the code using the py2puml
|
| 29 |
-
tool. The diagram is then manually reviewed, adjusted and exported to PNG
|
| 30 |
-
and SVG.
|
| 31 |
-
|
| 32 |
-
## Prerequisites
|
| 33 |
-
|
| 34 |
-
- Running python environment in which openhands is executable
|
| 35 |
-
(according to the instructions in the README.md file in the root of the repository)
|
| 36 |
-
- [py2puml](https://github.com/lucsorel/py2puml) installed
|
| 37 |
-
|
| 38 |
-
## Steps
|
| 39 |
-
|
| 40 |
-
1. Autogenerate the diagram by running the following command from the root of the repository:
|
| 41 |
-
`py2puml openhands openhands > docs/architecture/backend_architecture.puml`
|
| 42 |
-
|
| 43 |
-
2. Open the generated file in a PlantUML editor, e.g. Visual Studio Code with the PlantUML extension or [PlantText](https://www.planttext.com/)
|
| 44 |
-
|
| 45 |
-
3. Review the generated PUML and make all necessary adjustments to the diagram (add missing parts, fix mistakes, improve positioning).
|
| 46 |
-
_py2puml creates the diagram based on the type hints in the code, so missing or incorrect type hints may result in an incomplete or incorrect diagram._
|
| 47 |
-
|
| 48 |
-
4. Review the diff between the new and the previous diagram and manually check if the changes are correct.
|
| 49 |
-
_Make sure not to remove parts that were manually added to the diagram in the past and are still relevant._
|
| 50 |
-
|
| 51 |
-
5. Add the commit hash of the commit that was used to generate the diagram to the diagram footer.
|
| 52 |
-
|
| 53 |
-
6. Export the diagram as PNG and SVG files and replace the existing diagrams in the `docs/architecture` directory. This can be done with (e.g. [PlantText](https://www.planttext.com/))
|
| 54 |
-
|
| 55 |
-
</div>
|
| 56 |
-
</details>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/architecture/runtime.mdx
DELETED
|
@@ -1,136 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Runtime Architecture
|
| 3 |
-
---
|
| 4 |
-
|
| 5 |
-
The OpenHands Docker Runtime is the core component that enables secure and flexible execution of AI agent's action.
|
| 6 |
-
It creates a sandboxed environment using Docker, where arbitrary code can be run safely without risking the host system.
|
| 7 |
-
|
| 8 |
-
## Why do we need a sandboxed runtime?
|
| 9 |
-
|
| 10 |
-
OpenHands needs to execute arbitrary code in a secure, isolated environment for several reasons:
|
| 11 |
-
|
| 12 |
-
1. Security: Executing untrusted code can pose significant risks to the host system. A sandboxed environment prevents malicious code from accessing or modifying the host system's resources
|
| 13 |
-
2. Consistency: A sandboxed environment ensures that code execution is consistent across different machines and setups, eliminating "it works on my machine" issues
|
| 14 |
-
3. Resource Control: Sandboxing allows for better control over resource allocation and usage, preventing runaway processes from affecting the host system
|
| 15 |
-
4. Isolation: Different projects or users can work in isolated environments without interfering with each other or the host system
|
| 16 |
-
5. Reproducibility: Sandboxed environments make it easier to reproduce bugs and issues, as the execution environment is consistent and controllable
|
| 17 |
-
|
| 18 |
-
## How does the Runtime work?
|
| 19 |
-
|
| 20 |
-
The OpenHands Runtime system uses a client-server architecture implemented with Docker containers. Here's an overview of how it works:
|
| 21 |
-
|
| 22 |
-
```mermaid
|
| 23 |
-
graph TD
|
| 24 |
-
A[User-provided Custom Docker Image] --> B[OpenHands Backend]
|
| 25 |
-
B -->|Builds| C[OH Runtime Image]
|
| 26 |
-
C -->|Launches| D[Action Executor]
|
| 27 |
-
D -->|Initializes| E[Browser]
|
| 28 |
-
D -->|Initializes| F[Bash Shell]
|
| 29 |
-
D -->|Initializes| G[Plugins]
|
| 30 |
-
G -->|Initializes| L[Jupyter Server]
|
| 31 |
-
|
| 32 |
-
B -->|Spawn| H[Agent]
|
| 33 |
-
B -->|Spawn| I[EventStream]
|
| 34 |
-
I <--->|Execute Action to
|
| 35 |
-
Get Observation
|
| 36 |
-
via REST API
|
| 37 |
-
| D
|
| 38 |
-
|
| 39 |
-
H -->|Generate Action| I
|
| 40 |
-
I -->|Obtain Observation| H
|
| 41 |
-
|
| 42 |
-
subgraph "Docker Container"
|
| 43 |
-
D
|
| 44 |
-
E
|
| 45 |
-
F
|
| 46 |
-
G
|
| 47 |
-
L
|
| 48 |
-
end
|
| 49 |
-
```
|
| 50 |
-
|
| 51 |
-
1. User Input: The user provides a custom base Docker image
|
| 52 |
-
2. Image Building: OpenHands builds a new Docker image (the "OH runtime image") based on the user-provided image. This new image includes OpenHands-specific code, primarily the "runtime client"
|
| 53 |
-
3. Container Launch: When OpenHands starts, it launches a Docker container using the OH runtime image
|
| 54 |
-
4. Action Execution Server Initialization: The action execution server initializes an `ActionExecutor` inside the container, setting up necessary components like a bash shell and loading any specified plugins
|
| 55 |
-
5. Communication: The OpenHands backend (`openhands/runtime/impl/eventstream/eventstream_runtime.py`) communicates with the action execution server over RESTful API, sending actions and receiving observations
|
| 56 |
-
6. Action Execution: The runtime client receives actions from the backend, executes them in the sandboxed environment, and sends back observations
|
| 57 |
-
7. Observation Return: The action execution server sends execution results back to the OpenHands backend as observations
|
| 58 |
-
|
| 59 |
-
The role of the client:
|
| 60 |
-
|
| 61 |
-
- It acts as an intermediary between the OpenHands backend and the sandboxed environment
|
| 62 |
-
- It executes various types of actions (shell commands, file operations, Python code, etc.) safely within the container
|
| 63 |
-
- It manages the state of the sandboxed environment, including the current working directory and loaded plugins
|
| 64 |
-
- It formats and returns observations to the backend, ensuring a consistent interface for processing results
|
| 65 |
-
|
| 66 |
-
## How OpenHands builds and maintains OH Runtime images
|
| 67 |
-
|
| 68 |
-
OpenHands' approach to building and managing runtime images ensures efficiency, consistency, and flexibility in creating and maintaining Docker images for both production and development environments.
|
| 69 |
-
|
| 70 |
-
Check out the [relevant code](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/utils/runtime_build.py) if you are interested in more details.
|
| 71 |
-
|
| 72 |
-
### Image Tagging System
|
| 73 |
-
|
| 74 |
-
OpenHands uses a three-tag system for its runtime images to balance reproducibility with flexibility.
|
| 75 |
-
Tags may be in one of 2 formats:
|
| 76 |
-
|
| 77 |
-
- **Versioned Tag**: `oh_v{openhands_version}_{base_image}` (e.g.: `oh_v0.9.9_nikolaik_s_python-nodejs_t_python3.12-nodejs22`)
|
| 78 |
-
- **Lock Tag**: `oh_v{openhands_version}_{16_digit_lock_hash}` (e.g.: `oh_v0.9.9_1234567890abcdef`)
|
| 79 |
-
- **Source Tag**: `oh_v{openhands_version}_{16_digit_lock_hash}_{16_digit_source_hash}`
|
| 80 |
-
(e.g.: `oh_v0.9.9_1234567890abcdef_1234567890abcdef`)
|
| 81 |
-
|
| 82 |
-
#### Source Tag - Most Specific
|
| 83 |
-
|
| 84 |
-
This is the first 16 digits of the MD5 of the directory hash for the source directory. This gives a hash
|
| 85 |
-
for only the openhands source
|
| 86 |
-
|
| 87 |
-
#### Lock Tag
|
| 88 |
-
|
| 89 |
-
This hash is built from the first 16 digits of the MD5 of:
|
| 90 |
-
|
| 91 |
-
- The name of the base image upon which the image was built (e.g.: `nikolaik/python-nodejs:python3.12-nodejs22`)
|
| 92 |
-
- The content of the `pyproject.toml` included in the image.
|
| 93 |
-
- The content of the `poetry.lock` included in the image.
|
| 94 |
-
|
| 95 |
-
This effectively gives a hash for the dependencies of Openhands independent of the source code.
|
| 96 |
-
|
| 97 |
-
#### Versioned Tag - Most Generic
|
| 98 |
-
|
| 99 |
-
This tag is a concatenation of openhands version and the base image name (transformed to fit in tag standard).
|
| 100 |
-
|
| 101 |
-
#### Build Process
|
| 102 |
-
|
| 103 |
-
When generating an image...
|
| 104 |
-
|
| 105 |
-
- **No re-build**: OpenHands first checks whether an image with the same **most specific source tag** exists. If there is such an image,
|
| 106 |
-
no build is performed - the existing image is used.
|
| 107 |
-
- **Fastest re-build**: OpenHands next checks whether an image with the **generic lock tag** exists. If there is such an image,
|
| 108 |
-
OpenHands builds a new image based upon it, bypassing all installation steps (like `poetry install` and
|
| 109 |
-
`apt-get`) except a final operation to copy the current source code. The new image is tagged with a
|
| 110 |
-
**source** tag only.
|
| 111 |
-
- **Ok-ish re-build**: If neither a **source** nor **lock** tag exists, an image will be built based upon the **versioned** tag image.
|
| 112 |
-
In versioned tag image, most dependencies should already been installed hence saving time.
|
| 113 |
-
- **Slowest re-build**: If all of the three tags don't exists, a brand new image is built based upon the base
|
| 114 |
-
image (Which is a slower operation). This new image is tagged with all the **source**, **lock**, and **versioned** tags.
|
| 115 |
-
|
| 116 |
-
This tagging approach allows OpenHands to efficiently manage both development and production environments.
|
| 117 |
-
|
| 118 |
-
1. Identical source code and Dockerfile always produce the same image (via hash-based tags)
|
| 119 |
-
2. The system can quickly rebuild images when minor changes occur (by leveraging recent compatible images)
|
| 120 |
-
3. The **lock** tag (e.g., `runtime:oh_v0.9.3_1234567890abcdef`) always points to the latest build for a particular base image, dependency, and OpenHands version combination
|
| 121 |
-
|
| 122 |
-
## Runtime Plugin System
|
| 123 |
-
|
| 124 |
-
The OpenHands Runtime supports a plugin system that allows for extending functionality and customizing the runtime environment. Plugins are initialized when the runtime client starts up.
|
| 125 |
-
|
| 126 |
-
Check [an example of Jupyter plugin here](https://github.com/All-Hands-AI/OpenHands/blob/ecf4aed28b0cf7c18d4d8ff554883ba182fc6bdd/openhands/runtime/plugins/jupyter/__init__.py#L21-L55) if you want to implement your own plugin.
|
| 127 |
-
|
| 128 |
-
*More details about the Plugin system are still under construction - contributions are welcomed!*
|
| 129 |
-
|
| 130 |
-
Key aspects of the plugin system:
|
| 131 |
-
|
| 132 |
-
1. Plugin Definition: Plugins are defined as Python classes that inherit from a base `Plugin` class
|
| 133 |
-
2. Plugin Registration: Available plugins are registered in an `ALL_PLUGINS` dictionary
|
| 134 |
-
3. Plugin Specification: Plugins are associated with `Agent.sandbox_plugins: list[PluginRequirement]`. Users can specify which plugins to load when initializing the runtime
|
| 135 |
-
4. Initialization: Plugins are initialized asynchronously when the runtime client starts
|
| 136 |
-
5. Usage: The runtime client can use initialized plugins to extend its capabilities (e.g., the JupyterPlugin for running IPython cells)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/cloud/cloud-api.mdx
DELETED
|
@@ -1,176 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Cloud API
|
| 3 |
-
description: OpenHands Cloud provides a REST API that allows you to programmatically interact with the service. This guide explains how to obtain an API key and use the API to start conversations.
|
| 4 |
-
---
|
| 5 |
-
|
| 6 |
-
For more detailed information about the API, refer to the [OpenHands API Reference](https://docs.all-hands.dev/swagger-ui/).
|
| 7 |
-
|
| 8 |
-
## Obtaining an API Key
|
| 9 |
-
|
| 10 |
-
To use the OpenHands Cloud API, you'll need to generate an API key:
|
| 11 |
-
|
| 12 |
-
1. Log in to your [OpenHands Cloud](https://app.all-hands.dev) account.
|
| 13 |
-
2. Navigate to the [Settings page](https://app.all-hands.dev/settings).
|
| 14 |
-
3. Select the `API Keys` tab.
|
| 15 |
-
4. Click `Create API Key`.
|
| 16 |
-
5. Give your key a descriptive name (Example: "Development" or "Production") and select `Create`.
|
| 17 |
-
6. Copy the generated API key and store it securely. It will only be shown once.
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
## API Usage
|
| 22 |
-
|
| 23 |
-
### Starting a New Conversation
|
| 24 |
-
|
| 25 |
-
To start a new conversation with OpenHands to perform a task, you'll need to make a POST request to the conversation endpoint.
|
| 26 |
-
|
| 27 |
-
#### Request Parameters
|
| 28 |
-
|
| 29 |
-
| Parameter | Type | Required | Description |
|
| 30 |
-
|--------------------|----------|----------|------------------------------------------------------------------------------------------------------|
|
| 31 |
-
| `initial_user_msg` | string | Yes | The initial message to start the conversation. |
|
| 32 |
-
| `repository` | string | No | Git repository name to provide context in the format `owner/repo`. You must have access to the repo. |
|
| 33 |
-
|
| 34 |
-
#### Examples
|
| 35 |
-
|
| 36 |
-
<details>
|
| 37 |
-
<summary>cURL</summary>
|
| 38 |
-
|
| 39 |
-
```bash
|
| 40 |
-
curl -X POST "https://app.all-hands.dev/api/conversations" \
|
| 41 |
-
-H "Authorization: Bearer YOUR_API_KEY" \
|
| 42 |
-
-H "Content-Type: application/json" \
|
| 43 |
-
-d '{
|
| 44 |
-
"initial_user_msg": "Check whether there is any incorrect information in the README.md file and send a PR to fix it if so.",
|
| 45 |
-
"repository": "yourusername/your-repo"
|
| 46 |
-
}'
|
| 47 |
-
```
|
| 48 |
-
</details>
|
| 49 |
-
|
| 50 |
-
<details>
|
| 51 |
-
<summary>Python (with requests)</summary>
|
| 52 |
-
|
| 53 |
-
```python
|
| 54 |
-
import requests
|
| 55 |
-
|
| 56 |
-
api_key = "YOUR_API_KEY"
|
| 57 |
-
url = "https://app.all-hands.dev/api/conversations"
|
| 58 |
-
|
| 59 |
-
headers = {
|
| 60 |
-
"Authorization": f"Bearer {api_key}",
|
| 61 |
-
"Content-Type": "application/json"
|
| 62 |
-
}
|
| 63 |
-
|
| 64 |
-
data = {
|
| 65 |
-
"initial_user_msg": "Check whether there is any incorrect information in the README.md file and send a PR to fix it if so.",
|
| 66 |
-
"repository": "yourusername/your-repo"
|
| 67 |
-
}
|
| 68 |
-
|
| 69 |
-
response = requests.post(url, headers=headers, json=data)
|
| 70 |
-
conversation = response.json()
|
| 71 |
-
|
| 72 |
-
print(f"Conversation Link: https://app.all-hands.dev/conversations/{conversation['conversation_id']}")
|
| 73 |
-
print(f"Status: {conversation['status']}")
|
| 74 |
-
```
|
| 75 |
-
</details>
|
| 76 |
-
|
| 77 |
-
<details>
|
| 78 |
-
<summary>TypeScript/JavaScript (with fetch)</summary>
|
| 79 |
-
|
| 80 |
-
```typescript
|
| 81 |
-
const apiKey = "YOUR_API_KEY";
|
| 82 |
-
const url = "https://app.all-hands.dev/api/conversations";
|
| 83 |
-
|
| 84 |
-
const headers = {
|
| 85 |
-
"Authorization": `Bearer ${apiKey}`,
|
| 86 |
-
"Content-Type": "application/json"
|
| 87 |
-
};
|
| 88 |
-
|
| 89 |
-
const data = {
|
| 90 |
-
initial_user_msg: "Check whether there is any incorrect information in the README.md file and send a PR to fix it if so.",
|
| 91 |
-
repository: "yourusername/your-repo"
|
| 92 |
-
};
|
| 93 |
-
|
| 94 |
-
async function startConversation() {
|
| 95 |
-
try {
|
| 96 |
-
const response = await fetch(url, {
|
| 97 |
-
method: "POST",
|
| 98 |
-
headers: headers,
|
| 99 |
-
body: JSON.stringify(data)
|
| 100 |
-
});
|
| 101 |
-
|
| 102 |
-
const conversation = await response.json();
|
| 103 |
-
|
| 104 |
-
console.log(`Conversation Link: https://app.all-hands.dev/conversations/${conversation.id}`);
|
| 105 |
-
console.log(`Status: ${conversation.status}`);
|
| 106 |
-
|
| 107 |
-
return conversation;
|
| 108 |
-
} catch (error) {
|
| 109 |
-
console.error("Error starting conversation:", error);
|
| 110 |
-
}
|
| 111 |
-
}
|
| 112 |
-
|
| 113 |
-
startConversation();
|
| 114 |
-
```
|
| 115 |
-
|
| 116 |
-
</details>
|
| 117 |
-
|
| 118 |
-
#### Response
|
| 119 |
-
|
| 120 |
-
The API will return a JSON object with details about the created conversation:
|
| 121 |
-
|
| 122 |
-
```json
|
| 123 |
-
{
|
| 124 |
-
"status": "ok",
|
| 125 |
-
"conversation_id": "abc1234",
|
| 126 |
-
}
|
| 127 |
-
```
|
| 128 |
-
|
| 129 |
-
You may receive an `AuthenticationError` if:
|
| 130 |
-
|
| 131 |
-
- You provided an invalid API key.
|
| 132 |
-
- You provided the wrong repository name.
|
| 133 |
-
- You don't have access to the repository.
|
| 134 |
-
|
| 135 |
-
|
| 136 |
-
### Retrieving Conversation Status
|
| 137 |
-
|
| 138 |
-
You can check the status of a conversation by making a GET request to the conversation endpoint.
|
| 139 |
-
|
| 140 |
-
#### Endpoint
|
| 141 |
-
|
| 142 |
-
```
|
| 143 |
-
GET https://app.all-hands.dev/api/conversations/{conversation_id}
|
| 144 |
-
```
|
| 145 |
-
|
| 146 |
-
#### Example
|
| 147 |
-
|
| 148 |
-
<details>
|
| 149 |
-
<summary>cURL</summary>
|
| 150 |
-
|
| 151 |
-
```bash
|
| 152 |
-
curl -X GET "https://app.all-hands.dev/api/conversations/{conversation_id}" \
|
| 153 |
-
-H "Authorization: Bearer YOUR_API_KEY"
|
| 154 |
-
```
|
| 155 |
-
</details>
|
| 156 |
-
|
| 157 |
-
#### Response
|
| 158 |
-
|
| 159 |
-
The response is formatted as follows:
|
| 160 |
-
|
| 161 |
-
```json
|
| 162 |
-
{
|
| 163 |
-
"conversation_id":"abc1234",
|
| 164 |
-
"title":"Update README.md",
|
| 165 |
-
"created_at":"2025-04-29T15:13:51.370706Z",
|
| 166 |
-
"last_updated_at":"2025-04-29T15:13:57.199210Z",
|
| 167 |
-
"status":"RUNNING",
|
| 168 |
-
"selected_repository":"yourusername/your-repo",
|
| 169 |
-
"trigger":"gui"
|
| 170 |
-
}
|
| 171 |
-
```
|
| 172 |
-
|
| 173 |
-
## Rate Limits
|
| 174 |
-
|
| 175 |
-
If you have too many conversations running at once, older conversations will be paused to limit the number of concurrent conversations.
|
| 176 |
-
If you're running into issues and need a higher limit for your use case, please contact us at [[email protected]](mailto:[email protected]).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/cloud/cloud-ui.mdx
DELETED
|
@@ -1,36 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Cloud UI
|
| 3 |
-
description: The Cloud UI provides a web interface for interacting with OpenHands. This page explains how to use the
|
| 4 |
-
OpenHands Cloud UI.
|
| 5 |
-
---
|
| 6 |
-
|
| 7 |
-
## Landing Page
|
| 8 |
-
|
| 9 |
-
The landing page is where you can:
|
| 10 |
-
|
| 11 |
-
- [Add GitHub repository access](/usage/cloud/github-installation#adding-github-repository-access) to OpenHands.
|
| 12 |
-
- [Select a GitHub repo](/usage/cloud/github-installation#working-with-github-repos-in-openhands-cloud) or
|
| 13 |
-
[a GitLab repo](/usage/cloud/gitlab-installation#working-with-gitlab-repos-in-openhands-cloud) to start working on.
|
| 14 |
-
- See `Suggested Tasks` for repositories that OpenHands has access to.
|
| 15 |
-
- Launch an empty conversation using `Launch from Scratch`.
|
| 16 |
-
|
| 17 |
-
## Settings
|
| 18 |
-
|
| 19 |
-
The Settings page allows you to:
|
| 20 |
-
|
| 21 |
-
- [Configure GitHub repository access](/usage/cloud/github-installation#modifying-repository-access) for OpenHands.
|
| 22 |
-
- Set application settings like your preferred language, notifications and other preferences.
|
| 23 |
-
- Add credits to your account.
|
| 24 |
-
- Generate custom secrets.
|
| 25 |
-
- Create API keys to work with OpenHands programmatically.
|
| 26 |
-
|
| 27 |
-
## Key Features
|
| 28 |
-
|
| 29 |
-
For an overview of the key features available inside a conversation, please refer to the [Key Features](../key-features)
|
| 30 |
-
section of the documentation.
|
| 31 |
-
|
| 32 |
-
## Next Steps
|
| 33 |
-
|
| 34 |
-
- [Install GitHub Integration](/usage/cloud/github-installation) to use OpenHands with your GitHub repositories.
|
| 35 |
-
- [Install GitLab Integration](/usage/cloud/gitlab-installation) to use OpenHands with your GitLab repositories.
|
| 36 |
-
- [Use the Cloud API](/usage/cloud/cloud-api) to programmatically interact with OpenHands.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/cloud/github-installation.mdx
DELETED
|
@@ -1,71 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: GitHub Integration
|
| 3 |
-
description: This guide walks you through the process of installing OpenHands Cloud for your GitHub repositories. Once
|
| 4 |
-
set up, it will allow OpenHands to work with your GitHub repository through the Cloud UI or straight from GitHub!
|
| 5 |
-
---
|
| 6 |
-
|
| 7 |
-
## Prerequisites
|
| 8 |
-
|
| 9 |
-
- Signed in to [OpenHands Cloud](https://app.all-hands.dev) with [a GitHub account](/usage/cloud/openhands-cloud).
|
| 10 |
-
|
| 11 |
-
## Adding GitHub Repository Access
|
| 12 |
-
|
| 13 |
-
You can grant OpenHands access to specific GitHub repositories:
|
| 14 |
-
|
| 15 |
-
1. Click on `Add GitHub repos` on the landing page.
|
| 16 |
-
2. Select your organization and choose the specific repositories to grant OpenHands access to.
|
| 17 |
-
<Accordion title="OpenHands permissions">
|
| 18 |
-
- OpenHands requests short-lived tokens (8-hour expiration) with these permissions:
|
| 19 |
-
- Actions: Read and write
|
| 20 |
-
- Commit statuses: Read and write
|
| 21 |
-
- Contents: Read and write
|
| 22 |
-
- Issues: Read and write
|
| 23 |
-
- Metadata: Read-only
|
| 24 |
-
- Pull requests: Read and write
|
| 25 |
-
- Webhooks: Read and write
|
| 26 |
-
- Workflows: Read and write
|
| 27 |
-
- Repository access for a user is granted based on:
|
| 28 |
-
- Permission granted for the repository
|
| 29 |
-
- User's GitHub permissions (owner/collaborator)
|
| 30 |
-
</Accordion>
|
| 31 |
-
|
| 32 |
-
3. Click `Install & Authorize`.
|
| 33 |
-
|
| 34 |
-
## Modifying Repository Access
|
| 35 |
-
|
| 36 |
-
You can modify GitHub repository access at any time by:
|
| 37 |
-
- Selecting `Add GitHub repos` on the landing page or
|
| 38 |
-
- Visiting the Settings page and selecting `Configure GitHub Repositories` under the `Git` tab
|
| 39 |
-
|
| 40 |
-
## Working With GitHub Repos in Openhands Cloud
|
| 41 |
-
|
| 42 |
-
Once you've granted GitHub repository access, you can start working with your GitHub repository. Use the `select a repo`
|
| 43 |
-
and `select a branch` dropdowns to select the appropriate repository and branch you'd like OpenHands to work on. Then
|
| 44 |
-
click on `Launch` to start the conversation!
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
## Working on Github Issues and Pull Requests Using Openhands
|
| 49 |
-
|
| 50 |
-
Giving GitHub repository access to OpenHands also allows you to work on GitHub issues and pull requests directly.
|
| 51 |
-
|
| 52 |
-
### Working with Issues
|
| 53 |
-
|
| 54 |
-
On your repository, label an issue with `openhands` or add a message starting with
|
| 55 |
-
`@openhands`. OpenHands will:
|
| 56 |
-
1. Comment on the issue to let you know it is working on it.
|
| 57 |
-
- You can click on the link to track the progress on OpenHands Cloud.
|
| 58 |
-
2. Open a pull request if it determines that the issue has been successfully resolved.
|
| 59 |
-
3. Comment on the issue with a summary of the performed tasks and a link to the PR.
|
| 60 |
-
|
| 61 |
-
### Working with Pull Requests
|
| 62 |
-
|
| 63 |
-
To get OpenHands to work on pull requests, mention `@openhands` in the comments to:
|
| 64 |
-
- Ask questions
|
| 65 |
-
- Request updates
|
| 66 |
-
- Get code explanations
|
| 67 |
-
|
| 68 |
-
## Next Steps
|
| 69 |
-
|
| 70 |
-
- [Learn about the Cloud UI](/usage/cloud/cloud-ui).
|
| 71 |
-
- [Use the Cloud API](/usage/cloud/cloud-api) to programmatically interact with OpenHands.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/cloud/gitlab-installation.mdx
DELETED
|
@@ -1,25 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: GitLab Integration
|
| 3 |
-
description: This guide walks you through the process of installing OpenHands Cloud for your GitLab repositories. Once
|
| 4 |
-
set up, it will allow OpenHands to work with your GitLab repository.
|
| 5 |
-
---
|
| 6 |
-
|
| 7 |
-
## Prerequisites
|
| 8 |
-
|
| 9 |
-
- Signed in to [OpenHands Cloud](https://app.all-hands.dev) with [a GitLab account](/usage/cloud/openhands-cloud).
|
| 10 |
-
|
| 11 |
-
## Adding GitLab Repository Access
|
| 12 |
-
|
| 13 |
-
Upon signing into OpenHands Cloud with a GitLab account, OpenHands will have access to your repositories.
|
| 14 |
-
|
| 15 |
-
## Working With GitLab Repos in Openhands Cloud
|
| 16 |
-
|
| 17 |
-
After signing in with a Gitlab account, use the `select a repo` and `select a branch` dropdowns to select the
|
| 18 |
-
appropriate repository and branch you'd like OpenHands to work on. Then click on `Launch` to start the conversation!
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
## Next Steps
|
| 23 |
-
|
| 24 |
-
- [Learn about the Cloud UI](/usage/cloud/cloud-ui).
|
| 25 |
-
- [Use the Cloud API](/usage/cloud/cloud-api) to programmatically interact with OpenHands.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/cloud/openhands-cloud.mdx
DELETED
|
@@ -1,26 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Getting Started
|
| 3 |
-
description: Getting started with OpenHands Cloud.
|
| 4 |
-
---
|
| 5 |
-
|
| 6 |
-
## Accessing OpenHands Cloud
|
| 7 |
-
|
| 8 |
-
OpenHands Cloud is the hosted cloud version of All Hands AI's OpenHands. To get started with OpenHands Cloud,
|
| 9 |
-
visit [app.all-hands.dev](https://app.all-hands.dev).
|
| 10 |
-
|
| 11 |
-
You'll be prompted to connect with your GitHub or GitLab account:
|
| 12 |
-
|
| 13 |
-
1. Click `Log in with GitHub` or `Log in with GitLab`.
|
| 14 |
-
2. Review the permissions requested by OpenHands and authorize the application.
|
| 15 |
-
- OpenHands will require certain permissions from your account. To read more about these permissions,
|
| 16 |
-
you can click the `Learn more` link on the authorization page.
|
| 17 |
-
3. Review and accept the `terms of service` and select `Continue`.
|
| 18 |
-
|
| 19 |
-
## Next Steps
|
| 20 |
-
|
| 21 |
-
Once you've connected your account, you can:
|
| 22 |
-
|
| 23 |
-
- [Install GitHub Integration](/usage/cloud/github-installation) to use OpenHands with your GitHub repositories.
|
| 24 |
-
- [Install GitLab Integration](/usage/cloud/gitlab-installation) to use OpenHands with your GitLab repositories.
|
| 25 |
-
- [Learn about the Cloud UI](/usage/cloud/cloud-ui).
|
| 26 |
-
- [Use the Cloud API](/usage/cloud/cloud-api) to programmatically interact with OpenHands.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/configuration-options.mdx
DELETED
|
@@ -1,413 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Configuration Options
|
| 3 |
-
description: This page outlines all available configuration options for OpenHands, allowing you to customize its behavior and integrate it with other services. In GUI Mode, any settings applied through the Settings UI will take precedence.
|
| 4 |
-
---
|
| 5 |
-
|
| 6 |
-
## Core Configuration
|
| 7 |
-
|
| 8 |
-
The core configuration options are defined in the `[core]` section of the `config.toml` file.
|
| 9 |
-
|
| 10 |
-
### API Keys
|
| 11 |
-
- `e2b_api_key`
|
| 12 |
-
- Type: `str`
|
| 13 |
-
- Default: `""`
|
| 14 |
-
- Description: API key for E2B
|
| 15 |
-
|
| 16 |
-
- `modal_api_token_id`
|
| 17 |
-
- Type: `str`
|
| 18 |
-
- Default: `""`
|
| 19 |
-
- Description: API token ID for Modal
|
| 20 |
-
|
| 21 |
-
- `modal_api_token_secret`
|
| 22 |
-
- Type: `str`
|
| 23 |
-
- Default: `""`
|
| 24 |
-
- Description: API token secret for Modal
|
| 25 |
-
|
| 26 |
-
### Workspace
|
| 27 |
-
- `workspace_base` **(Deprecated)**
|
| 28 |
-
- Type: `str`
|
| 29 |
-
- Default: `"./workspace"`
|
| 30 |
-
- Description: Base path for the workspace. **Deprecated: Use `SANDBOX_VOLUMES` instead.**
|
| 31 |
-
|
| 32 |
-
- `cache_dir`
|
| 33 |
-
- Type: `str`
|
| 34 |
-
- Default: `"/tmp/cache"`
|
| 35 |
-
- Description: Cache directory path
|
| 36 |
-
|
| 37 |
-
### Debugging and Logging
|
| 38 |
-
- `debug`
|
| 39 |
-
- Type: `bool`
|
| 40 |
-
- Default: `false`
|
| 41 |
-
- Description: Enable debugging
|
| 42 |
-
|
| 43 |
-
- `disable_color`
|
| 44 |
-
- Type: `bool`
|
| 45 |
-
- Default: `false`
|
| 46 |
-
- Description: Disable color in terminal output
|
| 47 |
-
|
| 48 |
-
### Trajectories
|
| 49 |
-
- `save_trajectory_path`
|
| 50 |
-
- Type: `str`
|
| 51 |
-
- Default: `"./trajectories"`
|
| 52 |
-
- Description: Path to store trajectories (can be a folder or a file). If it's a folder, the trajectories will be saved in a file named with the session id name and .json extension, in that folder.
|
| 53 |
-
|
| 54 |
-
- `replay_trajectory_path`
|
| 55 |
-
- Type: `str`
|
| 56 |
-
- Default: `""`
|
| 57 |
-
- Description: Path to load a trajectory and replay. If given, must be a path to the trajectory file in JSON format. The actions in the trajectory file would be replayed first before any user instruction is executed.
|
| 58 |
-
|
| 59 |
-
### File Store
|
| 60 |
-
- `file_store_path`
|
| 61 |
-
- Type: `str`
|
| 62 |
-
- Default: `"/tmp/file_store"`
|
| 63 |
-
- Description: File store path
|
| 64 |
-
|
| 65 |
-
- `file_store`
|
| 66 |
-
- Type: `str`
|
| 67 |
-
- Default: `"memory"`
|
| 68 |
-
- Description: File store type
|
| 69 |
-
|
| 70 |
-
- `file_uploads_allowed_extensions`
|
| 71 |
-
- Type: `list of str`
|
| 72 |
-
- Default: `[".*"]`
|
| 73 |
-
- Description: List of allowed file extensions for uploads
|
| 74 |
-
|
| 75 |
-
- `file_uploads_max_file_size_mb`
|
| 76 |
-
- Type: `int`
|
| 77 |
-
- Default: `0`
|
| 78 |
-
- Description: Maximum file size for uploads, in megabytes
|
| 79 |
-
|
| 80 |
-
- `file_uploads_restrict_file_types`
|
| 81 |
-
- Type: `bool`
|
| 82 |
-
- Default: `false`
|
| 83 |
-
- Description: Restrict file types for file uploads
|
| 84 |
-
|
| 85 |
-
- `file_uploads_allowed_extensions`
|
| 86 |
-
- Type: `list of str`
|
| 87 |
-
- Default: `[".*"]`
|
| 88 |
-
- Description: List of allowed file extensions for uploads
|
| 89 |
-
|
| 90 |
-
### Task Management
|
| 91 |
-
- `max_budget_per_task`
|
| 92 |
-
- Type: `float`
|
| 93 |
-
- Default: `0.0`
|
| 94 |
-
- Description: Maximum budget per task (0.0 means no limit)
|
| 95 |
-
|
| 96 |
-
- `max_iterations`
|
| 97 |
-
- Type: `int`
|
| 98 |
-
- Default: `100`
|
| 99 |
-
- Description: Maximum number of iterations
|
| 100 |
-
|
| 101 |
-
### Sandbox Configuration
|
| 102 |
-
- `volumes`
|
| 103 |
-
- Type: `str`
|
| 104 |
-
- Default: `None`
|
| 105 |
-
- Description: Volume mounts in the format 'host_path:container_path[:mode]', e.g. '/my/host/dir:/workspace:rw'. Multiple mounts can be specified using commas, e.g. '/path1:/workspace/path1,/path2:/workspace/path2:ro'
|
| 106 |
-
|
| 107 |
-
- `workspace_mount_path_in_sandbox` **(Deprecated)**
|
| 108 |
-
- Type: `str`
|
| 109 |
-
- Default: `"/workspace"`
|
| 110 |
-
- Description: Path to mount the workspace in the sandbox. **Deprecated: Use `SANDBOX_VOLUMES` instead.**
|
| 111 |
-
|
| 112 |
-
- `workspace_mount_path` **(Deprecated)**
|
| 113 |
-
- Type: `str`
|
| 114 |
-
- Default: `""`
|
| 115 |
-
- Description: Path to mount the workspace. **Deprecated: Use `SANDBOX_VOLUMES` instead.**
|
| 116 |
-
|
| 117 |
-
- `workspace_mount_rewrite` **(Deprecated)**
|
| 118 |
-
- Type: `str`
|
| 119 |
-
- Default: `""`
|
| 120 |
-
- Description: Path to rewrite the workspace mount path to. You can usually ignore this, it refers to special cases of running inside another container. **Deprecated: Use `SANDBOX_VOLUMES` instead.**
|
| 121 |
-
|
| 122 |
-
### Miscellaneous
|
| 123 |
-
- `run_as_openhands`
|
| 124 |
-
- Type: `bool`
|
| 125 |
-
- Default: `true`
|
| 126 |
-
- Description: Run as OpenHands
|
| 127 |
-
|
| 128 |
-
- `runtime`
|
| 129 |
-
- Type: `str`
|
| 130 |
-
- Default: `"docker"`
|
| 131 |
-
- Description: Runtime environment
|
| 132 |
-
|
| 133 |
-
- `default_agent`
|
| 134 |
-
- Type: `str`
|
| 135 |
-
- Default: `"CodeActAgent"`
|
| 136 |
-
- Description: Name of the default agent
|
| 137 |
-
|
| 138 |
-
- `jwt_secret`
|
| 139 |
-
- Type: `str`
|
| 140 |
-
- Default: `uuid.uuid4().hex`
|
| 141 |
-
- Description: JWT secret for authentication. Please set it to your own value.
|
| 142 |
-
|
| 143 |
-
## LLM Configuration
|
| 144 |
-
|
| 145 |
-
The LLM (Large Language Model) configuration options are defined in the `[llm]` section of the `config.toml` file.
|
| 146 |
-
|
| 147 |
-
To use these with the docker command, pass in `-e LLM_<option>`. Example: `-e LLM_NUM_RETRIES`.
|
| 148 |
-
|
| 149 |
-
<Note>
|
| 150 |
-
For development setups, you can also define custom named LLM configurations. See [Custom LLM Configurations](./llms/custom-llm-configs) for details.
|
| 151 |
-
</Note>
|
| 152 |
-
|
| 153 |
-
**AWS Credentials**
|
| 154 |
-
- `aws_access_key_id`
|
| 155 |
-
- Type: `str`
|
| 156 |
-
- Default: `""`
|
| 157 |
-
- Description: AWS access key ID
|
| 158 |
-
|
| 159 |
-
- `aws_region_name`
|
| 160 |
-
- Type: `str`
|
| 161 |
-
- Default: `""`
|
| 162 |
-
- Description: AWS region name
|
| 163 |
-
|
| 164 |
-
- `aws_secret_access_key`
|
| 165 |
-
- Type: `str`
|
| 166 |
-
- Default: `""`
|
| 167 |
-
- Description: AWS secret access key
|
| 168 |
-
|
| 169 |
-
### API Configuration
|
| 170 |
-
- `api_key`
|
| 171 |
-
- Type: `str`
|
| 172 |
-
- Default: `None`
|
| 173 |
-
- Description: API key to use
|
| 174 |
-
|
| 175 |
-
- `base_url`
|
| 176 |
-
- Type: `str`
|
| 177 |
-
- Default: `""`
|
| 178 |
-
- Description: API base URL
|
| 179 |
-
|
| 180 |
-
- `api_version`
|
| 181 |
-
- Type: `str`
|
| 182 |
-
- Default: `""`
|
| 183 |
-
- Description: API version
|
| 184 |
-
|
| 185 |
-
- `input_cost_per_token`
|
| 186 |
-
- Type: `float`
|
| 187 |
-
- Default: `0.0`
|
| 188 |
-
- Description: Cost per input token
|
| 189 |
-
|
| 190 |
-
- `output_cost_per_token`
|
| 191 |
-
- Type: `float`
|
| 192 |
-
- Default: `0.0`
|
| 193 |
-
- Description: Cost per output token
|
| 194 |
-
|
| 195 |
-
### Custom LLM Provider
|
| 196 |
-
- `custom_llm_provider`
|
| 197 |
-
- Type: `str`
|
| 198 |
-
- Default: `""`
|
| 199 |
-
- Description: Custom LLM provider
|
| 200 |
-
|
| 201 |
-
|
| 202 |
-
### Message Handling
|
| 203 |
-
- `max_message_chars`
|
| 204 |
-
- Type: `int`
|
| 205 |
-
- Default: `30000`
|
| 206 |
-
- Description: The approximate maximum number of characters in the content of an event included in the prompt to the LLM. Larger observations are truncated.
|
| 207 |
-
|
| 208 |
-
- `max_input_tokens`
|
| 209 |
-
- Type: `int`
|
| 210 |
-
- Default: `0`
|
| 211 |
-
- Description: Maximum number of input tokens
|
| 212 |
-
|
| 213 |
-
- `max_output_tokens`
|
| 214 |
-
- Type: `int`
|
| 215 |
-
- Default: `0`
|
| 216 |
-
- Description: Maximum number of output tokens
|
| 217 |
-
|
| 218 |
-
### Model Selection
|
| 219 |
-
- `model`
|
| 220 |
-
- Type: `str`
|
| 221 |
-
- Default: `"claude-3-5-sonnet-20241022"`
|
| 222 |
-
- Description: Model to use
|
| 223 |
-
|
| 224 |
-
### Retrying
|
| 225 |
-
- `num_retries`
|
| 226 |
-
- Type: `int`
|
| 227 |
-
- Default: `8`
|
| 228 |
-
- Description: Number of retries to attempt
|
| 229 |
-
|
| 230 |
-
- `retry_max_wait`
|
| 231 |
-
- Type: `int`
|
| 232 |
-
- Default: `120`
|
| 233 |
-
- Description: Maximum wait time (in seconds) between retry attempts
|
| 234 |
-
|
| 235 |
-
- `retry_min_wait`
|
| 236 |
-
- Type: `int`
|
| 237 |
-
- Default: `15`
|
| 238 |
-
- Description: Minimum wait time (in seconds) between retry attempts
|
| 239 |
-
|
| 240 |
-
- `retry_multiplier`
|
| 241 |
-
- Type: `float`
|
| 242 |
-
- Default: `2.0`
|
| 243 |
-
- Description: Multiplier for exponential backoff calculation
|
| 244 |
-
|
| 245 |
-
### Advanced Options
|
| 246 |
-
- `drop_params`
|
| 247 |
-
- Type: `bool`
|
| 248 |
-
- Default: `false`
|
| 249 |
-
- Description: Drop any unmapped (unsupported) params without causing an exception
|
| 250 |
-
|
| 251 |
-
- `caching_prompt`
|
| 252 |
-
- Type: `bool`
|
| 253 |
-
- Default: `true`
|
| 254 |
-
- Description: Using the prompt caching feature if provided by the LLM and supported
|
| 255 |
-
|
| 256 |
-
- `ollama_base_url`
|
| 257 |
-
- Type: `str`
|
| 258 |
-
- Default: `""`
|
| 259 |
-
- Description: Base URL for the OLLAMA API
|
| 260 |
-
|
| 261 |
-
- `temperature`
|
| 262 |
-
- Type: `float`
|
| 263 |
-
- Default: `0.0`
|
| 264 |
-
- Description: Temperature for the API
|
| 265 |
-
|
| 266 |
-
- `timeout`
|
| 267 |
-
- Type: `int`
|
| 268 |
-
- Default: `0`
|
| 269 |
-
- Description: Timeout for the API
|
| 270 |
-
|
| 271 |
-
- `top_p`
|
| 272 |
-
- Type: `float`
|
| 273 |
-
- Default: `1.0`
|
| 274 |
-
- Description: Top p for the API
|
| 275 |
-
|
| 276 |
-
- `disable_vision`
|
| 277 |
-
- Type: `bool`
|
| 278 |
-
- Default: `None`
|
| 279 |
-
- Description: If model is vision capable, this option allows to disable image processing (useful for cost reduction)
|
| 280 |
-
|
| 281 |
-
## Agent Configuration
|
| 282 |
-
|
| 283 |
-
The agent configuration options are defined in the `[agent]` and `[agent.<agent_name>]` sections of the `config.toml` file.
|
| 284 |
-
|
| 285 |
-
### LLM Configuration
|
| 286 |
-
- `llm_config`
|
| 287 |
-
- Type: `str`
|
| 288 |
-
- Default: `'your-llm-config-group'`
|
| 289 |
-
- Description: The name of the LLM config to use
|
| 290 |
-
|
| 291 |
-
### ActionSpace Configuration
|
| 292 |
-
- `function_calling`
|
| 293 |
-
- Type: `bool`
|
| 294 |
-
- Default: `true`
|
| 295 |
-
- Description: Whether function calling is enabled
|
| 296 |
-
|
| 297 |
-
- `enable_browsing`
|
| 298 |
-
- Type: `bool`
|
| 299 |
-
- Default: `false`
|
| 300 |
-
- Description: Whether browsing delegate is enabled in the action space (only works with function calling)
|
| 301 |
-
|
| 302 |
-
- `enable_llm_editor`
|
| 303 |
-
- Type: `bool`
|
| 304 |
-
- Default: `false`
|
| 305 |
-
- Description: Whether LLM editor is enabled in the action space (only works with function calling)
|
| 306 |
-
|
| 307 |
-
- `enable_jupyter`
|
| 308 |
-
- Type: `bool`
|
| 309 |
-
- Default: `false`
|
| 310 |
-
- Description: Whether Jupyter is enabled in the action space
|
| 311 |
-
|
| 312 |
-
- `enable_history_truncation`
|
| 313 |
-
- Type: `bool`
|
| 314 |
-
- Default: `true`
|
| 315 |
-
- Description: Whether history should be truncated to continue the session when hitting LLM context length limit
|
| 316 |
-
|
| 317 |
-
### Microagent Usage
|
| 318 |
-
- `enable_prompt_extensions`
|
| 319 |
-
- Type: `bool`
|
| 320 |
-
- Default: `true`
|
| 321 |
-
- Description: Whether to use microagents at all
|
| 322 |
-
|
| 323 |
-
- `disabled_microagents`
|
| 324 |
-
- Type: `list of str`
|
| 325 |
-
- Default: `None`
|
| 326 |
-
- Description: A list of microagents to disable
|
| 327 |
-
|
| 328 |
-
## Sandbox Configuration
|
| 329 |
-
|
| 330 |
-
The sandbox configuration options are defined in the `[sandbox]` section of the `config.toml` file.
|
| 331 |
-
|
| 332 |
-
|
| 333 |
-
|
| 334 |
-
To use these with the docker command, pass in `-e SANDBOX_<option>`. Example: `-e SANDBOX_TIMEOUT`.
|
| 335 |
-
|
| 336 |
-
### Execution
|
| 337 |
-
- `timeout`
|
| 338 |
-
- Type: `int`
|
| 339 |
-
- Default: `120`
|
| 340 |
-
- Description: Sandbox timeout in seconds
|
| 341 |
-
|
| 342 |
-
- `user_id`
|
| 343 |
-
- Type: `int`
|
| 344 |
-
- Default: `1000`
|
| 345 |
-
- Description: Sandbox user ID
|
| 346 |
-
|
| 347 |
-
### Container Image
|
| 348 |
-
- `base_container_image`
|
| 349 |
-
- Type: `str`
|
| 350 |
-
- Default: `"nikolaik/python-nodejs:python3.12-nodejs22"`
|
| 351 |
-
- Description: Container image to use for the sandbox
|
| 352 |
-
|
| 353 |
-
### Networking
|
| 354 |
-
- `use_host_network`
|
| 355 |
-
- Type: `bool`
|
| 356 |
-
- Default: `false`
|
| 357 |
-
- Description: Use host network
|
| 358 |
-
|
| 359 |
-
- `runtime_binding_address`
|
| 360 |
-
- Type: `str`
|
| 361 |
-
- Default: `0.0.0.0`
|
| 362 |
-
- Description: The binding address for the runtime ports. It specifies which network interface on the host machine Docker should bind the runtime ports to.
|
| 363 |
-
|
| 364 |
-
### Linting and Plugins
|
| 365 |
-
- `enable_auto_lint`
|
| 366 |
-
- Type: `bool`
|
| 367 |
-
- Default: `false`
|
| 368 |
-
- Description: Enable auto linting after editing
|
| 369 |
-
|
| 370 |
-
- `initialize_plugins`
|
| 371 |
-
- Type: `bool`
|
| 372 |
-
- Default: `true`
|
| 373 |
-
- Description: Whether to initialize plugins
|
| 374 |
-
|
| 375 |
-
### Dependencies and Environment
|
| 376 |
-
- `runtime_extra_deps`
|
| 377 |
-
- Type: `str`
|
| 378 |
-
- Default: `""`
|
| 379 |
-
- Description: Extra dependencies to install in the runtime image
|
| 380 |
-
|
| 381 |
-
- `runtime_startup_env_vars`
|
| 382 |
-
- Type: `dict`
|
| 383 |
-
- Default: `{}`
|
| 384 |
-
- Description: Environment variables to set at the launch of the runtime
|
| 385 |
-
|
| 386 |
-
### Evaluation
|
| 387 |
-
- `browsergym_eval_env`
|
| 388 |
-
- Type: `str`
|
| 389 |
-
- Default: `""`
|
| 390 |
-
- Description: BrowserGym environment to use for evaluation
|
| 391 |
-
|
| 392 |
-
## Security Configuration
|
| 393 |
-
|
| 394 |
-
The security configuration options are defined in the `[security]` section of the `config.toml` file.
|
| 395 |
-
|
| 396 |
-
To use these with the docker command, pass in `-e SECURITY_<option>`. Example: `-e SECURITY_CONFIRMATION_MODE`.
|
| 397 |
-
|
| 398 |
-
### Confirmation Mode
|
| 399 |
-
- `confirmation_mode`
|
| 400 |
-
- Type: `bool`
|
| 401 |
-
- Default: `false`
|
| 402 |
-
- Description: Enable confirmation mode
|
| 403 |
-
|
| 404 |
-
### Security Analyzer
|
| 405 |
-
- `security_analyzer`
|
| 406 |
-
- Type: `str`
|
| 407 |
-
- Default: `""`
|
| 408 |
-
- Description: The security analyzer to use
|
| 409 |
-
|
| 410 |
-
---
|
| 411 |
-
|
| 412 |
-
> **Note**: Adjust configurations carefully, especially for memory, security, and network-related settings to ensure optimal performance and security.
|
| 413 |
-
Please note that the configuration options may be subject to change in future versions of OpenHands. It's recommended to refer to the official documentation for the most up-to-date information.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/feedback.mdx
DELETED
|
@@ -1,50 +0,0 @@
|
|
| 1 |
-
# ✅ Providing Feedback
|
| 2 |
-
|
| 3 |
-
When using OpenHands, you will encounter cases where things work well, and others where they don't. We encourage you to
|
| 4 |
-
provide feedback when you use OpenHands to help give feedback to the development team, and perhaps more importantly,
|
| 5 |
-
create an open corpus of coding agent training examples -- Share-OpenHands!
|
| 6 |
-
|
| 7 |
-
## 📝 How to Provide Feedback
|
| 8 |
-
|
| 9 |
-
Providing feedback is easy! When you are using OpenHands, you can press the thumbs-up or thumbs-down button at any point
|
| 10 |
-
during your interaction. You will be prompted to provide your email address
|
| 11 |
-
(e.g. so we can contact you if we want to ask any follow-up questions), and you can choose whether you want to provide feedback publicly or privately.
|
| 12 |
-
|
| 13 |
-
<iframe width="560" height="315" src="https://www.youtube.com/embed/5rFx-StMVV0?si=svo7xzp6LhGK_GXr" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
|
| 14 |
-
|
| 15 |
-
## 📜 Data Use and Privacy
|
| 16 |
-
|
| 17 |
-
### Data sharing settings
|
| 18 |
-
|
| 19 |
-
When you submit data, you can submit it either publicly or privately.
|
| 20 |
-
|
| 21 |
-
- **Public** data will be distributed under the MIT License, like OpenHands itself, and can be used by the community to
|
| 22 |
-
train and test models. Obviously, feedback that you can make public will be more valuable for the community as a whole,
|
| 23 |
-
so when you are not dealing with sensitive information, we would encourage you to choose this option!
|
| 24 |
-
- **Private** data will be made available to the OpenHands team for the purpose of improving OpenHands.
|
| 25 |
-
However, a link with a unique ID will still be created that you can share publicly with others.
|
| 26 |
-
|
| 27 |
-
### Who collects and stores the data?
|
| 28 |
-
|
| 29 |
-
The data is collected and stored by [All Hands AI](https://all-hands.dev), a company founded by OpenHands maintainers to support and improve OpenHands.
|
| 30 |
-
|
| 31 |
-
### How will public data be released?
|
| 32 |
-
|
| 33 |
-
The public data will be released when we hit fixed milestones, such as 1,000 public examples, 10,000 public examples, etc.
|
| 34 |
-
At this time, we will follow the following release process:
|
| 35 |
-
|
| 36 |
-
1. All people who contributed public feedback will receive an email describing the data release and being given an opportunity to opt out.
|
| 37 |
-
2. The person or people in charge of the data release will perform quality control of the data, removing low-quality feedback,
|
| 38 |
-
removing email submitter email addresses, and attempting to remove any sensitive information.
|
| 39 |
-
3. The data will be released publicly under the MIT license through commonly used sites such as GitHub or Hugging Face.
|
| 40 |
-
|
| 41 |
-
### What if I want my data deleted?
|
| 42 |
-
|
| 43 |
-
For data on the All Hands AI servers, we are happy to delete it at request:
|
| 44 |
-
|
| 45 |
-
**One Piece of Data:** If you want one piece of data deleted, we will shortly be adding a mechanism to delete pieces of
|
| 46 |
-
data using the link and password that is displayed on the interface when you submit data.
|
| 47 |
-
|
| 48 |
-
**All Data:** If you would like all pieces of your data deleted, or you do not have the ID and password that you
|
| 49 |
-
received when submitting the data, please contact `[email protected]` from the email address that you registered
|
| 50 |
-
when you originally submitted the data.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/getting-started.mdx
DELETED
|
@@ -1,100 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Start Building
|
| 3 |
-
description: So you've [run OpenHands](./installation) and have [set up your LLM](./installation#setup). Now what?
|
| 4 |
-
icon: code
|
| 5 |
-
---
|
| 6 |
-
|
| 7 |
-
OpenHands can assist with a range of engineering tasks. However, the technology is still new, and we’re far from having
|
| 8 |
-
agents that can handle complex tasks independently. It’s important to understand what the agent does well and where it
|
| 9 |
-
needs support.
|
| 10 |
-
|
| 11 |
-
## Hello World
|
| 12 |
-
|
| 13 |
-
Start with a simple "hello world" example. It might be trickier than it seems!
|
| 14 |
-
|
| 15 |
-
Prompt the agent with:
|
| 16 |
-
> Write a bash script hello.sh that prints "hello world!"
|
| 17 |
-
|
| 18 |
-
The agent will write the script, set the correct permissions, and run it to check the output.
|
| 19 |
-
|
| 20 |
-
You can continue prompting the agent to refine your code. This is a great way to
|
| 21 |
-
work with agents. Start simple, and iterate.
|
| 22 |
-
|
| 23 |
-
> Modify hello.sh so that it accepts a name as the first argument, but defaults to "world"
|
| 24 |
-
|
| 25 |
-
You can also use any language you need. The agent may need time to set up the environment.
|
| 26 |
-
|
| 27 |
-
> Please convert hello.sh to a Ruby script, and run it
|
| 28 |
-
|
| 29 |
-
## Building From Scratch
|
| 30 |
-
|
| 31 |
-
Agents excel at "greenfield" tasks, where they don’t need context about existing code and
|
| 32 |
-
they can start from scratch.
|
| 33 |
-
Begin with a simple task and iterate from there. Be specific about what you want and the tech stack.
|
| 34 |
-
|
| 35 |
-
For example, we might build a TODO app:
|
| 36 |
-
|
| 37 |
-
> Build a frontend-only TODO app in React. All state should be stored in localStorage.
|
| 38 |
-
|
| 39 |
-
Once the basic structure is in place, continue refining:
|
| 40 |
-
|
| 41 |
-
> Allow adding an optional due date to each task.
|
| 42 |
-
|
| 43 |
-
Just like normal development, commit and push your code often.
|
| 44 |
-
This way you can always revert back to an old state if the agent goes off track.
|
| 45 |
-
You can ask the agent to commit and push for you:
|
| 46 |
-
|
| 47 |
-
> Commit the changes and push them to a new branch called "feature/due-dates"
|
| 48 |
-
|
| 49 |
-
## Adding New Code
|
| 50 |
-
|
| 51 |
-
OpenHands is great at adding new code to an existing codebase.
|
| 52 |
-
|
| 53 |
-
For instance, you can ask OpenHands to add a GitHub action that lints your code. It might check your codebase to
|
| 54 |
-
determine the language, then create a new file in `./github/workflows/lint.yml`.
|
| 55 |
-
|
| 56 |
-
> Add a GitHub action that lints the code in this repository.
|
| 57 |
-
|
| 58 |
-
Some tasks need more context. While OpenHands can use commands like ls and grep to search, providing context upfront
|
| 59 |
-
speeds things up and reduces token usage.
|
| 60 |
-
|
| 61 |
-
> Modify ./backend/api/routes.js to add a new route that returns a list of all tasks.
|
| 62 |
-
|
| 63 |
-
> Add a new React component to the ./frontend/components directory to display a list of Widgets.
|
| 64 |
-
> It should use the existing Widget component.
|
| 65 |
-
|
| 66 |
-
## Refactoring
|
| 67 |
-
|
| 68 |
-
OpenHands does great at refactoring code in small chunks. Rather than rearchitecting the entire codebase,
|
| 69 |
-
it's more effective to break up long files and functions or rename variables.
|
| 70 |
-
|
| 71 |
-
> Rename all the single-letter variables in ./app.go.
|
| 72 |
-
|
| 73 |
-
> Split the `build_and_deploy_widgets` function into two functions, `build_widgets` and `deploy_widgets` in widget.php.
|
| 74 |
-
|
| 75 |
-
> Break ./api/routes.js into separate files for each route.
|
| 76 |
-
|
| 77 |
-
## Bug Fixes
|
| 78 |
-
|
| 79 |
-
OpenHands can help track down and fix bugs, but bug fixing can be tricky and often requires more context.
|
| 80 |
-
It’s helpful if you’ve already diagnosed the issue and just need OpenHands to handle the logic.
|
| 81 |
-
|
| 82 |
-
> The email field in the `/subscribe` endpoint is rejecting .io domains. Fix this.
|
| 83 |
-
|
| 84 |
-
> The `search_widgets` function in ./app.py is doing a case-sensitive search. Make it case-insensitive.
|
| 85 |
-
|
| 86 |
-
For bug fixing, test-driven development can be really useful. You can ask the agent to write a new test and iterate
|
| 87 |
-
until the bug is fixed:
|
| 88 |
-
|
| 89 |
-
> The `hello` function crashes on the empty string. Write a test that reproduces this bug, then fix the code so it passes.
|
| 90 |
-
|
| 91 |
-
## More
|
| 92 |
-
|
| 93 |
-
OpenHands can assist with nearly any coding task, but it takes some practice to get the best results.
|
| 94 |
-
Keep these tips in mind:
|
| 95 |
-
* Keep your tasks small.
|
| 96 |
-
* Be specific.
|
| 97 |
-
* Provide plenty of context.
|
| 98 |
-
* Commit and push frequently.
|
| 99 |
-
|
| 100 |
-
See [Prompting Best Practices](./prompting/prompting-best-practices) for more tips on how to get the most out of OpenHands.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/how-to/cli-mode.mdx
DELETED
|
@@ -1,105 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: CLI Mode
|
| 3 |
-
description: CLI mode provides a powerful interactive Command-Line Interface (CLI) that lets you engage with OpenHands directly from your terminal.
|
| 4 |
-
---
|
| 5 |
-
|
| 6 |
-
This mode is different from the [headless mode](./headless-mode), which is non-interactive and better for scripting.
|
| 7 |
-
|
| 8 |
-
## Getting Started
|
| 9 |
-
|
| 10 |
-
### Running with Python
|
| 11 |
-
|
| 12 |
-
1. Ensure you have followed the [Development setup instructions](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
|
| 13 |
-
2. Set your model, API key, and other preferences using environment variables or with the [`config.toml`](https://github.com/All-Hands-AI/OpenHands/blob/main/config.template.toml) file.
|
| 14 |
-
3. Launch an interactive OpenHands conversation from the command line:
|
| 15 |
-
|
| 16 |
-
```bash
|
| 17 |
-
poetry run python -m openhands.cli.main
|
| 18 |
-
```
|
| 19 |
-
|
| 20 |
-
This command opens an interactive prompt where you can type tasks or commands and get responses from OpenHands.
|
| 21 |
-
|
| 22 |
-
### Running with Docker
|
| 23 |
-
|
| 24 |
-
1. Set the following environment variables in your terminal:
|
| 25 |
-
- `SANDBOX_VOLUMES` to specify the directory you want OpenHands to access ([See using SANDBOX_VOLUMES for more info](../runtimes/docker#using-sandbox_volumes))
|
| 26 |
-
- `LLM_MODEL` - the LLM model to use (e.g. `export LLM_MODEL="anthropic/claude-sonnet-4-20250514"`)
|
| 27 |
-
- `LLM_API_KEY` - your API key (e.g. `export LLM_API_KEY="sk_test_12345"`)
|
| 28 |
-
|
| 29 |
-
2. Run the following command:
|
| 30 |
-
|
| 31 |
-
```bash
|
| 32 |
-
docker run -it \
|
| 33 |
-
--pull=always \
|
| 34 |
-
-e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.41-nikolaik \
|
| 35 |
-
-e SANDBOX_USER_ID=$(id -u) \
|
| 36 |
-
-e SANDBOX_VOLUMES=$SANDBOX_VOLUMES \
|
| 37 |
-
-e LLM_API_KEY=$LLM_API_KEY \
|
| 38 |
-
-e LLM_MODEL=$LLM_MODEL \
|
| 39 |
-
-v /var/run/docker.sock:/var/run/docker.sock \
|
| 40 |
-
-v ~/.openhands-state:/.openhands-state \
|
| 41 |
-
--add-host host.docker.internal:host-gateway \
|
| 42 |
-
--name openhands-app-$(date +%Y%m%d%H%M%S) \
|
| 43 |
-
docker.all-hands.dev/all-hands-ai/openhands:0.41 \
|
| 44 |
-
python -m openhands.cli.main --override-cli-mode true
|
| 45 |
-
```
|
| 46 |
-
|
| 47 |
-
This launches the CLI in Docker, allowing you to interact with OpenHands as described above.
|
| 48 |
-
|
| 49 |
-
The `-e SANDBOX_USER_ID=$(id -u)` ensures files created by the agent in your workspace have the correct permissions.
|
| 50 |
-
|
| 51 |
-
## Interactive CLI Overview
|
| 52 |
-
|
| 53 |
-
### What is CLI Mode?
|
| 54 |
-
|
| 55 |
-
CLI mode enables real-time interaction with OpenHands agents. You can type natural language tasks, use interactive
|
| 56 |
-
commands, and receive instant feedback—all inside your terminal.
|
| 57 |
-
|
| 58 |
-
### Starting a Conversation
|
| 59 |
-
|
| 60 |
-
When you start the CLI, you'll see a welcome message and a prompt (`>`). Enter your first task or type a command to
|
| 61 |
-
begin your conversation.
|
| 62 |
-
|
| 63 |
-
### Available Commands
|
| 64 |
-
|
| 65 |
-
You can use the following commands whenever the prompt (`>`) is displayed:
|
| 66 |
-
|
| 67 |
-
| Command | Description |
|
| 68 |
-
|--------------|----------------------------------------------------------------|
|
| 69 |
-
| `/help` | Show all available interactive commands and their descriptions |
|
| 70 |
-
| `/exit` | Exit the application |
|
| 71 |
-
| `/init` | Initialize a new repository for agent exploration |
|
| 72 |
-
| `/status` | Show conversation details and usage metrics |
|
| 73 |
-
| `/new` | Start a new conversation |
|
| 74 |
-
| `/settings` | View and modify current LLM/agent settings |
|
| 75 |
-
| `/resume` | Resume the agent if paused |
|
| 76 |
-
|
| 77 |
-
#### Settings and Configuration
|
| 78 |
-
|
| 79 |
-
You can update your model, API key, agent, and other preferences interactively using the `/settings` command. Just
|
| 80 |
-
follow the prompts:
|
| 81 |
-
|
| 82 |
-
- **Basic settings**: Choose a model/provider and enter your API key.
|
| 83 |
-
- **Advanced settings**: Set custom endpoints, enable or disable confirmation mode, and configure memory condensation.
|
| 84 |
-
|
| 85 |
-
Settings can also be managed via the `config.toml` file.
|
| 86 |
-
|
| 87 |
-
#### Repository Initialization
|
| 88 |
-
|
| 89 |
-
The `/init` command helps the agent understand your project by creating a `.openhands/microagents/repo.md` file with
|
| 90 |
-
project details and structure. Use this when onboarding the agent to a new codebase.
|
| 91 |
-
|
| 92 |
-
#### Agent Pause/Resume Feature
|
| 93 |
-
|
| 94 |
-
You can pause the agent while it is running by pressing `Ctrl-P`. To continue the conversation after pausing, simply
|
| 95 |
-
type `/resume` at the prompt.
|
| 96 |
-
|
| 97 |
-
## Tips and Troubleshooting
|
| 98 |
-
|
| 99 |
-
- Use `/help` at any time to see the list of available commands.
|
| 100 |
-
- If you encounter permission issues, make sure your workspace directory is trusted and all required environment variables are set correctly.
|
| 101 |
-
- For advanced LLM configuration, use the advanced options in `/settings`.
|
| 102 |
-
- When confirmation mode is enabled, the CLI will prompt before sensitive operations. You can type `a` or `always` at the first confirmation prompt to automatically confirm subsequent actions for the current conversation.
|
| 103 |
-
- If you want to start over, use `/new` to begin a fresh conversation without restarting the CLI.
|
| 104 |
-
|
| 105 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/how-to/custom-sandbox-guide.mdx
DELETED
|
@@ -1,100 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Custom Sandbox
|
| 3 |
-
description: This guide is for users that would like to use their own custom Docker image for the runtime. For example, with certain tools or programming languages pre-installed.
|
| 4 |
-
---
|
| 5 |
-
|
| 6 |
-
The sandbox is where the agent performs its tasks. Instead of running commands directly on your computer
|
| 7 |
-
(which could be risky), the agent runs them inside a Docker container.
|
| 8 |
-
|
| 9 |
-
The default OpenHands sandbox (`python-nodejs:python3.12-nodejs22`
|
| 10 |
-
from [nikolaik/python-nodejs](https://hub.docker.com/r/nikolaik/python-nodejs)) comes with some packages installed such
|
| 11 |
-
as python and Node.js but may need other software installed by default.
|
| 12 |
-
|
| 13 |
-
You have two options for customization:
|
| 14 |
-
|
| 15 |
-
- Use an existing image with the required software.
|
| 16 |
-
- Create your own custom Docker image.
|
| 17 |
-
|
| 18 |
-
If you choose the first option, you can skip the `Create Your Docker Image` section.
|
| 19 |
-
|
| 20 |
-
## Create Your Docker Image
|
| 21 |
-
|
| 22 |
-
To create a custom Docker image, it must be Debian based.
|
| 23 |
-
|
| 24 |
-
For example, if you want OpenHands to have `ruby` installed, you could create a `Dockerfile` with the following content:
|
| 25 |
-
|
| 26 |
-
```dockerfile
|
| 27 |
-
FROM nikolaik/python-nodejs:python3.12-nodejs22
|
| 28 |
-
|
| 29 |
-
# Install required packages
|
| 30 |
-
RUN apt-get update && apt-get install -y ruby
|
| 31 |
-
```
|
| 32 |
-
|
| 33 |
-
Or you could use a Ruby-specific base image:
|
| 34 |
-
|
| 35 |
-
```dockerfile
|
| 36 |
-
FROM ruby:latest
|
| 37 |
-
```
|
| 38 |
-
|
| 39 |
-
Save this file in a folder. Then, build your Docker image (e.g., named custom-image) by navigating to the folder in
|
| 40 |
-
the terminal and running::
|
| 41 |
-
```bash
|
| 42 |
-
docker build -t custom-image .
|
| 43 |
-
```
|
| 44 |
-
|
| 45 |
-
This will produce a new image called `custom-image`, which will be available in Docker.
|
| 46 |
-
|
| 47 |
-
## Using the Docker Command
|
| 48 |
-
|
| 49 |
-
When running OpenHands using [the docker command](/usage/installation#start-the-app), replace
|
| 50 |
-
`-e SANDBOX_RUNTIME_CONTAINER_IMAGE=...` with `-e SANDBOX_BASE_CONTAINER_IMAGE=<custom image name>`:
|
| 51 |
-
|
| 52 |
-
```commandline
|
| 53 |
-
docker run -it --rm --pull=always \
|
| 54 |
-
-e SANDBOX_BASE_CONTAINER_IMAGE=custom-image \
|
| 55 |
-
...
|
| 56 |
-
```
|
| 57 |
-
|
| 58 |
-
## Using the Development Workflow
|
| 59 |
-
|
| 60 |
-
### Setup
|
| 61 |
-
|
| 62 |
-
First, ensure you can run OpenHands by following the instructions in [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
|
| 63 |
-
|
| 64 |
-
### Specify the Base Sandbox Image
|
| 65 |
-
|
| 66 |
-
In the `config.toml` file within the OpenHands directory, set the `base_container_image` to the image you want to use.
|
| 67 |
-
This can be an image you’ve already pulled or one you’ve built:
|
| 68 |
-
|
| 69 |
-
```bash
|
| 70 |
-
[core]
|
| 71 |
-
...
|
| 72 |
-
[sandbox]
|
| 73 |
-
base_container_image="custom-image"
|
| 74 |
-
```
|
| 75 |
-
|
| 76 |
-
### Additional Configuration Options
|
| 77 |
-
|
| 78 |
-
The `config.toml` file supports several other options for customizing your sandbox:
|
| 79 |
-
|
| 80 |
-
```toml
|
| 81 |
-
[core]
|
| 82 |
-
# Install additional dependencies when the runtime is built
|
| 83 |
-
# Can contain any valid shell commands
|
| 84 |
-
# If you need the path to the Python interpreter in any of these commands, you can use the $OH_INTERPRETER_PATH variable
|
| 85 |
-
runtime_extra_deps = """
|
| 86 |
-
pip install numpy pandas
|
| 87 |
-
apt-get update && apt-get install -y ffmpeg
|
| 88 |
-
"""
|
| 89 |
-
|
| 90 |
-
# Set environment variables for the runtime
|
| 91 |
-
# Useful for configuration that needs to be available at runtime
|
| 92 |
-
runtime_startup_env_vars = { DATABASE_URL = "postgresql://user:pass@localhost/db" }
|
| 93 |
-
|
| 94 |
-
# Specify platform for multi-architecture builds (e.g., "linux/amd64" or "linux/arm64")
|
| 95 |
-
platform = "linux/amd64"
|
| 96 |
-
```
|
| 97 |
-
|
| 98 |
-
### Run
|
| 99 |
-
|
| 100 |
-
Run OpenHands by running ```make run``` in the top level directory.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/how-to/debugging.mdx
DELETED
|
@@ -1,73 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Debugging
|
| 3 |
-
---
|
| 4 |
-
|
| 5 |
-
The following is intended as a primer on debugging OpenHands for Development purposes.
|
| 6 |
-
|
| 7 |
-
## Server / VSCode
|
| 8 |
-
|
| 9 |
-
The following `launch.json` will allow debugging the agent, controller and server elements, but not the sandbox (Which runs inside docker). It will ignore any changes inside the `workspace/` directory:
|
| 10 |
-
|
| 11 |
-
```
|
| 12 |
-
{
|
| 13 |
-
"version": "0.2.0",
|
| 14 |
-
"configurations": [
|
| 15 |
-
{
|
| 16 |
-
"name": "OpenHands CLI",
|
| 17 |
-
"type": "debugpy",
|
| 18 |
-
"request": "launch",
|
| 19 |
-
"module": "openhands.cli.main",
|
| 20 |
-
"justMyCode": false
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"name": "OpenHands WebApp",
|
| 24 |
-
"type": "debugpy",
|
| 25 |
-
"request": "launch",
|
| 26 |
-
"module": "uvicorn",
|
| 27 |
-
"args": [
|
| 28 |
-
"openhands.server.listen:app",
|
| 29 |
-
"--reload",
|
| 30 |
-
"--reload-exclude",
|
| 31 |
-
"${workspaceFolder}/workspace",
|
| 32 |
-
"--port",
|
| 33 |
-
"3000"
|
| 34 |
-
],
|
| 35 |
-
"justMyCode": false
|
| 36 |
-
}
|
| 37 |
-
]
|
| 38 |
-
}
|
| 39 |
-
```
|
| 40 |
-
|
| 41 |
-
More specific debugging configurations which include more parameters may be specified:
|
| 42 |
-
|
| 43 |
-
```
|
| 44 |
-
...
|
| 45 |
-
{
|
| 46 |
-
"name": "Debug CodeAct",
|
| 47 |
-
"type": "debugpy",
|
| 48 |
-
"request": "launch",
|
| 49 |
-
"module": "openhands.core.main",
|
| 50 |
-
"args": [
|
| 51 |
-
"-t",
|
| 52 |
-
"Ask me what your task is.",
|
| 53 |
-
"-d",
|
| 54 |
-
"${workspaceFolder}/workspace",
|
| 55 |
-
"-c",
|
| 56 |
-
"CodeActAgent",
|
| 57 |
-
"-l",
|
| 58 |
-
"llm.o1",
|
| 59 |
-
"-n",
|
| 60 |
-
"prompts"
|
| 61 |
-
],
|
| 62 |
-
"justMyCode": false
|
| 63 |
-
}
|
| 64 |
-
...
|
| 65 |
-
```
|
| 66 |
-
|
| 67 |
-
Values in the snippet above can be updated such that:
|
| 68 |
-
|
| 69 |
-
* *t*: the task
|
| 70 |
-
* *d*: the openhands workspace directory
|
| 71 |
-
* *c*: the agent
|
| 72 |
-
* *l*: the LLM config (pre-defined in config.toml)
|
| 73 |
-
* *n*: session name (e.g. eventstream name)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/how-to/development-overview.mdx
DELETED
|
@@ -1,71 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Development Overview
|
| 3 |
-
description: This guide provides an overview of the key documentation resources available in the OpenHands repository. Whether you're looking to contribute, understand the architecture, or work on specific components, these resources will help you navigate the codebase effectively.
|
| 4 |
-
---
|
| 5 |
-
|
| 6 |
-
## Core Documentation
|
| 7 |
-
|
| 8 |
-
### Project Fundamentals
|
| 9 |
-
- **Main Project Overview** (`/README.md`)
|
| 10 |
-
The primary entry point for understanding OpenHands, including features and basic setup instructions.
|
| 11 |
-
|
| 12 |
-
- **Development Guide** (`/Development.md`)
|
| 13 |
-
Comprehensive guide for developers working on OpenHands, including setup, requirements, and development workflows.
|
| 14 |
-
|
| 15 |
-
- **Contributing Guidelines** (`/CONTRIBUTING.md`)
|
| 16 |
-
Essential information for contributors, covering code style, PR process, and contribution workflows.
|
| 17 |
-
|
| 18 |
-
### Component Documentation
|
| 19 |
-
|
| 20 |
-
#### Frontend
|
| 21 |
-
- **Frontend Application** (`/frontend/README.md`)
|
| 22 |
-
Complete guide for setting up and developing the React-based frontend application.
|
| 23 |
-
|
| 24 |
-
#### Backend
|
| 25 |
-
- **Backend Implementation** (`/openhands/README.md`)
|
| 26 |
-
Detailed documentation of the Python backend implementation and architecture.
|
| 27 |
-
|
| 28 |
-
- **Server Documentation** (`/openhands/server/README.md`)
|
| 29 |
-
Server implementation details, API documentation, and service architecture.
|
| 30 |
-
|
| 31 |
-
- **Runtime Environment** (`/openhands/runtime/README.md`)
|
| 32 |
-
Documentation covering the runtime environment, execution model, and runtime configurations.
|
| 33 |
-
|
| 34 |
-
#### Infrastructure
|
| 35 |
-
- **Container Documentation** (`/containers/README.md`)
|
| 36 |
-
Comprehensive information about Docker containers, deployment strategies, and container management.
|
| 37 |
-
|
| 38 |
-
### Testing and Evaluation
|
| 39 |
-
- **Unit Testing Guide** (`/tests/unit/README.md`)
|
| 40 |
-
Instructions for writing, running, and maintaining unit tests.
|
| 41 |
-
|
| 42 |
-
- **Evaluation Framework** (`/evaluation/README.md`)
|
| 43 |
-
Documentation for the evaluation framework, benchmarks, and performance testing.
|
| 44 |
-
|
| 45 |
-
### Advanced Features
|
| 46 |
-
- **Microagents Architecture** (`/microagents/README.md`)
|
| 47 |
-
Detailed information about the microagents architecture, implementation, and usage.
|
| 48 |
-
|
| 49 |
-
### Documentation Standards
|
| 50 |
-
- **Documentation Style Guide** (`/docs/DOC_STYLE_GUIDE.md`)
|
| 51 |
-
Standards and guidelines for writing and maintaining project documentation.
|
| 52 |
-
|
| 53 |
-
## Getting Started with Development
|
| 54 |
-
|
| 55 |
-
If you're new to developing with OpenHands, we recommend following this sequence:
|
| 56 |
-
|
| 57 |
-
1. Start with the main `README.md` to understand the project's purpose and features
|
| 58 |
-
2. Review the `CONTRIBUTING.md` guidelines if you plan to contribute
|
| 59 |
-
3. Follow the setup instructions in `Development.md`
|
| 60 |
-
4. Dive into specific component documentation based on your area of interest:
|
| 61 |
-
- Frontend developers should focus on `/frontend/README.md`
|
| 62 |
-
- Backend developers should start with `/openhands/README.md`
|
| 63 |
-
- Infrastructure work should begin with `/containers/README.md`
|
| 64 |
-
|
| 65 |
-
## Documentation Updates
|
| 66 |
-
|
| 67 |
-
When making changes to the codebase, please ensure that:
|
| 68 |
-
1. Relevant documentation is updated to reflect your changes
|
| 69 |
-
2. New features are documented in the appropriate README files
|
| 70 |
-
3. Any API changes are reflected in the server documentation
|
| 71 |
-
4. Documentation follows the style guide in `/docs/DOC_STYLE_GUIDE.md`
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/how-to/evaluation-harness.mdx
DELETED
|
@@ -1,280 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Evaluation Harness
|
| 3 |
-
---
|
| 4 |
-
|
| 5 |
-
This guide provides an overview of how to integrate your own evaluation benchmark into the OpenHands framework.
|
| 6 |
-
|
| 7 |
-
## Setup Environment and LLM Configuration
|
| 8 |
-
|
| 9 |
-
Please follow instructions [here](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md) to setup your local development environment.
|
| 10 |
-
OpenHands in development mode uses `config.toml` to keep track of most configurations.
|
| 11 |
-
|
| 12 |
-
Here's an example configuration file you can use to define and use multiple LLMs:
|
| 13 |
-
|
| 14 |
-
```toml
|
| 15 |
-
[llm]
|
| 16 |
-
# IMPORTANT: add your API key here, and set the model to the one you want to evaluate
|
| 17 |
-
model = "claude-3-5-sonnet-20241022"
|
| 18 |
-
api_key = "sk-XXX"
|
| 19 |
-
|
| 20 |
-
[llm.eval_gpt4_1106_preview_llm]
|
| 21 |
-
model = "gpt-4-1106-preview"
|
| 22 |
-
api_key = "XXX"
|
| 23 |
-
temperature = 0.0
|
| 24 |
-
|
| 25 |
-
[llm.eval_some_openai_compatible_model_llm]
|
| 26 |
-
model = "openai/MODEL_NAME"
|
| 27 |
-
base_url = "https://OPENAI_COMPATIBLE_URL/v1"
|
| 28 |
-
api_key = "XXX"
|
| 29 |
-
temperature = 0.0
|
| 30 |
-
```
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
## How to use OpenHands in the command line
|
| 34 |
-
|
| 35 |
-
OpenHands can be run from the command line using the following format:
|
| 36 |
-
|
| 37 |
-
```bash
|
| 38 |
-
poetry run python ./openhands/core/main.py \
|
| 39 |
-
-i <max_iterations> \
|
| 40 |
-
-t "<task_description>" \
|
| 41 |
-
-c <agent_class> \
|
| 42 |
-
-l <llm_config>
|
| 43 |
-
```
|
| 44 |
-
|
| 45 |
-
For example:
|
| 46 |
-
|
| 47 |
-
```bash
|
| 48 |
-
poetry run python ./openhands/core/main.py \
|
| 49 |
-
-i 10 \
|
| 50 |
-
-t "Write me a bash script that prints hello world." \
|
| 51 |
-
-c CodeActAgent \
|
| 52 |
-
-l llm
|
| 53 |
-
```
|
| 54 |
-
|
| 55 |
-
This command runs OpenHands with:
|
| 56 |
-
- A maximum of 10 iterations
|
| 57 |
-
- The specified task description
|
| 58 |
-
- Using the CodeActAgent
|
| 59 |
-
- With the LLM configuration defined in the `llm` section of your `config.toml` file
|
| 60 |
-
|
| 61 |
-
## How does OpenHands work
|
| 62 |
-
|
| 63 |
-
The main entry point for OpenHands is in `openhands/core/main.py`. Here's a simplified flow of how it works:
|
| 64 |
-
|
| 65 |
-
1. Parse command-line arguments and load the configuration
|
| 66 |
-
2. Create a runtime environment using `create_runtime()`
|
| 67 |
-
3. Initialize the specified agent
|
| 68 |
-
4. Run the controller using `run_controller()`, which:
|
| 69 |
-
- Attaches the runtime to the agent
|
| 70 |
-
- Executes the agent's task
|
| 71 |
-
- Returns a final state when complete
|
| 72 |
-
|
| 73 |
-
The `run_controller()` function is the core of OpenHands's execution. It manages the interaction between the agent, the runtime, and the task, handling things like user input simulation and event processing.
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
## Easiest way to get started: Exploring Existing Benchmarks
|
| 77 |
-
|
| 78 |
-
We encourage you to review the various evaluation benchmarks available in the [`evaluation/benchmarks/` directory](https://github.com/All-Hands-AI/OpenHands/blob/main/evaluation/benchmarks) of our repository.
|
| 79 |
-
|
| 80 |
-
To integrate your own benchmark, we suggest starting with the one that most closely resembles your needs. This approach can significantly streamline your integration process, allowing you to build upon existing structures and adapt them to your specific requirements.
|
| 81 |
-
|
| 82 |
-
## How to create an evaluation workflow
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
To create an evaluation workflow for your benchmark, follow these steps:
|
| 86 |
-
|
| 87 |
-
1. Import relevant OpenHands utilities:
|
| 88 |
-
```python
|
| 89 |
-
import openhands.agenthub
|
| 90 |
-
from evaluation.utils.shared import (
|
| 91 |
-
EvalMetadata,
|
| 92 |
-
EvalOutput,
|
| 93 |
-
make_metadata,
|
| 94 |
-
prepare_dataset,
|
| 95 |
-
reset_logger_for_multiprocessing,
|
| 96 |
-
run_evaluation,
|
| 97 |
-
)
|
| 98 |
-
from openhands.controller.state.state import State
|
| 99 |
-
from openhands.core.config import (
|
| 100 |
-
AppConfig,
|
| 101 |
-
SandboxConfig,
|
| 102 |
-
get_llm_config_arg,
|
| 103 |
-
parse_arguments,
|
| 104 |
-
)
|
| 105 |
-
from openhands.core.logger import openhands_logger as logger
|
| 106 |
-
from openhands.core.main import create_runtime, run_controller
|
| 107 |
-
from openhands.events.action import CmdRunAction
|
| 108 |
-
from openhands.events.observation import CmdOutputObservation, ErrorObservation
|
| 109 |
-
from openhands.runtime.runtime import Runtime
|
| 110 |
-
```
|
| 111 |
-
|
| 112 |
-
2. Create a configuration:
|
| 113 |
-
```python
|
| 114 |
-
def get_config(instance: pd.Series, metadata: EvalMetadata) -> AppConfig:
|
| 115 |
-
config = AppConfig(
|
| 116 |
-
default_agent=metadata.agent_class,
|
| 117 |
-
runtime='docker',
|
| 118 |
-
max_iterations=metadata.max_iterations,
|
| 119 |
-
sandbox=SandboxConfig(
|
| 120 |
-
base_container_image='your_container_image',
|
| 121 |
-
enable_auto_lint=True,
|
| 122 |
-
timeout=300,
|
| 123 |
-
),
|
| 124 |
-
)
|
| 125 |
-
config.set_llm_config(metadata.llm_config)
|
| 126 |
-
return config
|
| 127 |
-
```
|
| 128 |
-
|
| 129 |
-
3. Initialize the runtime and set up the evaluation environment:
|
| 130 |
-
```python
|
| 131 |
-
def initialize_runtime(runtime: Runtime, instance: pd.Series):
|
| 132 |
-
# Set up your evaluation environment here
|
| 133 |
-
# For example, setting environment variables, preparing files, etc.
|
| 134 |
-
pass
|
| 135 |
-
```
|
| 136 |
-
|
| 137 |
-
4. Create a function to process each instance:
|
| 138 |
-
```python
|
| 139 |
-
from openhands.utils.async_utils import call_async_from_sync
|
| 140 |
-
def process_instance(instance: pd.Series, metadata: EvalMetadata) -> EvalOutput:
|
| 141 |
-
config = get_config(instance, metadata)
|
| 142 |
-
runtime = create_runtime(config)
|
| 143 |
-
call_async_from_sync(runtime.connect)
|
| 144 |
-
initialize_runtime(runtime, instance)
|
| 145 |
-
|
| 146 |
-
instruction = get_instruction(instance, metadata)
|
| 147 |
-
|
| 148 |
-
state = run_controller(
|
| 149 |
-
config=config,
|
| 150 |
-
task_str=instruction,
|
| 151 |
-
runtime=runtime,
|
| 152 |
-
fake_user_response_fn=your_user_response_function,
|
| 153 |
-
)
|
| 154 |
-
|
| 155 |
-
# Evaluate the agent's actions
|
| 156 |
-
evaluation_result = await evaluate_agent_actions(runtime, instance)
|
| 157 |
-
|
| 158 |
-
return EvalOutput(
|
| 159 |
-
instance_id=instance.instance_id,
|
| 160 |
-
instruction=instruction,
|
| 161 |
-
test_result=evaluation_result,
|
| 162 |
-
metadata=metadata,
|
| 163 |
-
history=compatibility_for_eval_history_pairs(state.history),
|
| 164 |
-
metrics=state.metrics.get() if state.metrics else None,
|
| 165 |
-
error=state.last_error if state and state.last_error else None,
|
| 166 |
-
)
|
| 167 |
-
```
|
| 168 |
-
|
| 169 |
-
5. Run the evaluation:
|
| 170 |
-
```python
|
| 171 |
-
metadata = make_metadata(llm_config, dataset_name, agent_class, max_iterations, eval_note, eval_output_dir)
|
| 172 |
-
output_file = os.path.join(metadata.eval_output_dir, 'output.jsonl')
|
| 173 |
-
instances = prepare_dataset(your_dataset, output_file, eval_n_limit)
|
| 174 |
-
|
| 175 |
-
await run_evaluation(
|
| 176 |
-
instances,
|
| 177 |
-
metadata,
|
| 178 |
-
output_file,
|
| 179 |
-
num_workers,
|
| 180 |
-
process_instance
|
| 181 |
-
)
|
| 182 |
-
```
|
| 183 |
-
|
| 184 |
-
This workflow sets up the configuration, initializes the runtime environment, processes each instance by running the agent and evaluating its actions, and then collects the results into an `EvalOutput` object. The `run_evaluation` function handles parallelization and progress tracking.
|
| 185 |
-
|
| 186 |
-
Remember to customize the `get_instruction`, `your_user_response_function`, and `evaluate_agent_actions` functions according to your specific benchmark requirements.
|
| 187 |
-
|
| 188 |
-
By following this structure, you can create a robust evaluation workflow for your benchmark within the OpenHands framework.
|
| 189 |
-
|
| 190 |
-
|
| 191 |
-
## Understanding the `user_response_fn`
|
| 192 |
-
|
| 193 |
-
The `user_response_fn` is a crucial component in OpenHands's evaluation workflow. It simulates user interaction with the agent, allowing for automated responses during the evaluation process. This function is particularly useful when you want to provide consistent, predefined responses to the agent's queries or actions.
|
| 194 |
-
|
| 195 |
-
|
| 196 |
-
### Workflow and Interaction
|
| 197 |
-
|
| 198 |
-
The correct workflow for handling actions and the `user_response_fn` is as follows:
|
| 199 |
-
|
| 200 |
-
1. Agent receives a task and starts processing
|
| 201 |
-
2. Agent emits an Action
|
| 202 |
-
3. If the Action is executable (e.g., CmdRunAction, IPythonRunCellAction):
|
| 203 |
-
- The Runtime processes the Action
|
| 204 |
-
- Runtime returns an Observation
|
| 205 |
-
4. If the Action is not executable (typically a MessageAction):
|
| 206 |
-
- The `user_response_fn` is called
|
| 207 |
-
- It returns a simulated user response
|
| 208 |
-
5. The agent receives either the Observation or the simulated response
|
| 209 |
-
6. Steps 2-5 repeat until the task is completed or max iterations are reached
|
| 210 |
-
|
| 211 |
-
Here's a more accurate visual representation:
|
| 212 |
-
|
| 213 |
-
```
|
| 214 |
-
[Agent]
|
| 215 |
-
|
|
| 216 |
-
v
|
| 217 |
-
[Emit Action]
|
| 218 |
-
|
|
| 219 |
-
v
|
| 220 |
-
[Is Action Executable?]
|
| 221 |
-
/ \
|
| 222 |
-
Yes No
|
| 223 |
-
| |
|
| 224 |
-
v v
|
| 225 |
-
[Runtime] [user_response_fn]
|
| 226 |
-
| |
|
| 227 |
-
v v
|
| 228 |
-
[Return Observation] [Simulated Response]
|
| 229 |
-
\ /
|
| 230 |
-
\ /
|
| 231 |
-
v v
|
| 232 |
-
[Agent receives feedback]
|
| 233 |
-
|
|
| 234 |
-
v
|
| 235 |
-
[Continue or Complete Task]
|
| 236 |
-
```
|
| 237 |
-
|
| 238 |
-
In this workflow:
|
| 239 |
-
|
| 240 |
-
- Executable actions (like running commands or executing code) are handled directly by the Runtime
|
| 241 |
-
- Non-executable actions (typically when the agent wants to communicate or ask for clarification) are handled by the `user_response_fn`
|
| 242 |
-
- The agent then processes the feedback, whether it's an Observation from the Runtime or a simulated response from the `user_response_fn`
|
| 243 |
-
|
| 244 |
-
This approach allows for automated handling of both concrete actions and simulated user interactions, making it suitable for evaluation scenarios where you want to test the agent's ability to complete tasks with minimal human intervention.
|
| 245 |
-
|
| 246 |
-
### Example Implementation
|
| 247 |
-
|
| 248 |
-
Here's an example of a `user_response_fn` used in the SWE-Bench evaluation:
|
| 249 |
-
|
| 250 |
-
```python
|
| 251 |
-
def codeact_user_response(state: State | None) -> str:
|
| 252 |
-
msg = (
|
| 253 |
-
'Please continue working on the task on whatever approach you think is suitable.\n'
|
| 254 |
-
'If you think you have solved the task, please first send your answer to user through message and then <execute_bash> exit </execute_bash>.\n'
|
| 255 |
-
'IMPORTANT: YOU SHOULD NEVER ASK FOR HUMAN HELP.\n'
|
| 256 |
-
)
|
| 257 |
-
|
| 258 |
-
if state and state.history:
|
| 259 |
-
# check if the agent has tried to talk to the user 3 times, if so, let the agent know it can give up
|
| 260 |
-
user_msgs = [
|
| 261 |
-
event
|
| 262 |
-
for event in state.history
|
| 263 |
-
if isinstance(event, MessageAction) and event.source == 'user'
|
| 264 |
-
]
|
| 265 |
-
if len(user_msgs) >= 2:
|
| 266 |
-
# let the agent know that it can give up when it has tried 3 times
|
| 267 |
-
return (
|
| 268 |
-
msg
|
| 269 |
-
+ 'If you want to give up, run: <execute_bash> exit </execute_bash>.\n'
|
| 270 |
-
)
|
| 271 |
-
return msg
|
| 272 |
-
```
|
| 273 |
-
|
| 274 |
-
This function does the following:
|
| 275 |
-
|
| 276 |
-
1. Provides a standard message encouraging the agent to continue working
|
| 277 |
-
2. Checks how many times the agent has attempted to communicate with the user
|
| 278 |
-
3. If the agent has made multiple attempts, it provides an option to give up
|
| 279 |
-
|
| 280 |
-
By using this function, you can ensure consistent behavior across multiple evaluation runs and prevent the agent from getting stuck waiting for human input.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/how-to/github-action.mdx
DELETED
|
@@ -1,53 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: OpenHands GitHub Action
|
| 3 |
-
description: This guide explains how to use the OpenHands GitHub Action in your own projects.
|
| 4 |
-
---
|
| 5 |
-
|
| 6 |
-
## Using the Action in the OpenHands Repository
|
| 7 |
-
|
| 8 |
-
To use the OpenHands GitHub Action in a repository, you can:
|
| 9 |
-
|
| 10 |
-
1. Create an issue in the repository.
|
| 11 |
-
2. Add the `fix-me` label to the issue or leave a comment on the issue starting with `@openhands-agent`.
|
| 12 |
-
|
| 13 |
-
The action will automatically trigger and attempt to resolve the issue.
|
| 14 |
-
|
| 15 |
-
## Installing the Action in a New Repository
|
| 16 |
-
|
| 17 |
-
To install the OpenHands GitHub Action in your own repository, follow
|
| 18 |
-
the [README for the OpenHands Resolver](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/resolver/README.md).
|
| 19 |
-
|
| 20 |
-
## Usage Tips
|
| 21 |
-
|
| 22 |
-
### Iterative resolution
|
| 23 |
-
|
| 24 |
-
1. Create an issue in the repository.
|
| 25 |
-
2. Add the `fix-me` label to the issue, or leave a comment starting with `@openhands-agent`.
|
| 26 |
-
3. Review the attempt to resolve the issue by checking the pull request.
|
| 27 |
-
4. Follow up with feedback through general comments, review comments, or inline thread comments.
|
| 28 |
-
5. Add the `fix-me` label to the pull request, or address a specific comment by starting with `@openhands-agent`.
|
| 29 |
-
|
| 30 |
-
### Label versus Macro
|
| 31 |
-
|
| 32 |
-
- Label (`fix-me`): Requests OpenHands to address the **entire** issue or pull request.
|
| 33 |
-
- Macro (`@openhands-agent`): Requests OpenHands to consider only the issue/pull request description and **the specific comment**.
|
| 34 |
-
|
| 35 |
-
## Advanced Settings
|
| 36 |
-
|
| 37 |
-
### Add custom repository settings
|
| 38 |
-
|
| 39 |
-
You can provide custom directions for OpenHands by following the [README for the resolver](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/resolver/README.md#providing-custom-instructions).
|
| 40 |
-
|
| 41 |
-
### Custom configurations
|
| 42 |
-
|
| 43 |
-
GitHub resolver will automatically check for valid [repository secrets](https://docs.github.com/en/actions/security-for-github-actions/security-guides/using-secrets-in-github-actions?tool=webui#creating-secrets-for-a-repository) or [repository variables](https://docs.github.com/en/actions/writing-workflows/choosing-what-your-workflow-does/store-information-in-variables#creating-configuration-variables-for-a-repository) to customize its behavior.
|
| 44 |
-
The customization options you can set are:
|
| 45 |
-
|
| 46 |
-
| **Attribute name** | **Type** | **Purpose** | **Example** |
|
| 47 |
-
| -------------------------------- | -------- | --------------------------------------------------------------------------------------------------- | -------------------------------------------------- |
|
| 48 |
-
| `LLM_MODEL` | Variable | Set the LLM to use with OpenHands | `LLM_MODEL="anthropic/claude-3-5-sonnet-20241022"` |
|
| 49 |
-
| `OPENHANDS_MAX_ITER` | Variable | Set max limit for agent iterations | `OPENHANDS_MAX_ITER=10` |
|
| 50 |
-
| `OPENHANDS_MACRO` | Variable | Customize default macro for invoking the resolver | `OPENHANDS_MACRO=@resolveit` |
|
| 51 |
-
| `OPENHANDS_BASE_CONTAINER_IMAGE` | Variable | Custom Sandbox ([learn more](https://docs.all-hands.dev/modules/usage/how-to/custom-sandbox-guide)) | `OPENHANDS_BASE_CONTAINER_IMAGE="custom_image"` |
|
| 52 |
-
| `TARGET_BRANCH` | Variable | Merge to branch other than `main` | `TARGET_BRANCH="dev"` |
|
| 53 |
-
| `TARGET_RUNNER` | Variable | Target runner to execute the agent workflow (default ubuntu-latest) | `TARGET_RUNNER="custom-runner"` |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/how-to/gui-mode.mdx
DELETED
|
@@ -1,143 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: GUI Mode
|
| 3 |
-
description: OpenHands provides a Graphical User Interface (GUI) mode for interacting with the AI assistant.
|
| 4 |
-
---
|
| 5 |
-
|
| 6 |
-
## Installation and Setup
|
| 7 |
-
|
| 8 |
-
1. Follow the installation instructions to install OpenHands.
|
| 9 |
-
2. After running the command, access OpenHands at [http://localhost:3000](http://localhost:3000).
|
| 10 |
-
|
| 11 |
-
## Interacting with the GUI
|
| 12 |
-
|
| 13 |
-
### Initial Setup
|
| 14 |
-
|
| 15 |
-
1. Upon first launch, you'll see a settings popup.
|
| 16 |
-
2. Select an `LLM Provider` and `LLM Model` from the dropdown menus. If the required model does not exist in the list,
|
| 17 |
-
select `see advanced settings`. Then toggle `Advanced` options and enter it with the correct prefix in the
|
| 18 |
-
`Custom Model` text box.
|
| 19 |
-
3. Enter the corresponding `API Key` for your chosen provider.
|
| 20 |
-
4. Click `Save Changes` to apply the settings.
|
| 21 |
-
|
| 22 |
-
### Version Control Tokens
|
| 23 |
-
|
| 24 |
-
OpenHands supports multiple version control providers. You can configure tokens for multiple providers simultaneously.
|
| 25 |
-
|
| 26 |
-
#### GitHub Token Setup
|
| 27 |
-
|
| 28 |
-
OpenHands automatically exports a `GITHUB_TOKEN` to the shell environment if provided:
|
| 29 |
-
|
| 30 |
-
<details>
|
| 31 |
-
<summary>Setting Up a GitHub Token</summary>
|
| 32 |
-
|
| 33 |
-
1. **Generate a Personal Access Token (PAT)**:
|
| 34 |
-
- On GitHub, go to Settings > Developer Settings > Personal Access Tokens > Tokens (classic).
|
| 35 |
-
- **New token (classic)**
|
| 36 |
-
- Required scopes:
|
| 37 |
-
- `repo` (Full control of private repositories)
|
| 38 |
-
- **Fine-Grained Tokens**
|
| 39 |
-
- All Repositories (You can select specific repositories, but this will impact what returns in repo search)
|
| 40 |
-
- Minimal Permissions ( Select `Meta Data = Read-only` read for search, `Pull Requests = Read and Write` and `Content = Read and Write` for branch creation)
|
| 41 |
-
2. **Enter Token in OpenHands**:
|
| 42 |
-
- Click the Settings button (gear icon).
|
| 43 |
-
- Navigate to the `Git` tab.
|
| 44 |
-
- Paste your token in the `GitHub Token` field.
|
| 45 |
-
- Click `Save Changes` to apply the changes.
|
| 46 |
-
</details>
|
| 47 |
-
|
| 48 |
-
<details>
|
| 49 |
-
<summary>Organizational Token Policies</summary>
|
| 50 |
-
|
| 51 |
-
If you're working with organizational repositories, additional setup may be required:
|
| 52 |
-
|
| 53 |
-
1. **Check Organization Requirements**:
|
| 54 |
-
- Organization admins may enforce specific token policies.
|
| 55 |
-
- Some organizations require tokens to be created with SSO enabled.
|
| 56 |
-
- Review your organization's [token policy settings](https://docs.github.com/en/organizations/managing-programmatic-access-to-your-organization/setting-a-personal-access-token-policy-for-your-organization).
|
| 57 |
-
2. **Verify Organization Access**:
|
| 58 |
-
- Go to your token settings on GitHub.
|
| 59 |
-
- Look for the organization under `Organization access`.
|
| 60 |
-
- If required, click `Enable SSO` next to your organization.
|
| 61 |
-
- Complete the SSO authorization process.
|
| 62 |
-
</details>
|
| 63 |
-
|
| 64 |
-
<details>
|
| 65 |
-
<summary>Troubleshooting</summary>
|
| 66 |
-
|
| 67 |
-
Common issues and solutions:
|
| 68 |
-
|
| 69 |
-
- **Token Not Recognized**:
|
| 70 |
-
- Ensure the token is properly saved in settings.
|
| 71 |
-
- Check that the token hasn't expired.
|
| 72 |
-
- Verify the token has the required scopes.
|
| 73 |
-
- Try regenerating the token.
|
| 74 |
-
|
| 75 |
-
- **Organization Access Denied**:
|
| 76 |
-
- Check if SSO is required but not enabled.
|
| 77 |
-
- Verify organization membership.
|
| 78 |
-
- Contact organization admin if token policies are blocking access.
|
| 79 |
-
|
| 80 |
-
- **Verifying Token Works**:
|
| 81 |
-
- The app will show a green checkmark if the token is valid.
|
| 82 |
-
- Try accessing a repository to confirm permissions.
|
| 83 |
-
- Check the browser console for any error messages.
|
| 84 |
-
</details>
|
| 85 |
-
|
| 86 |
-
#### GitLab Token Setup
|
| 87 |
-
|
| 88 |
-
OpenHands automatically exports a `GITLAB_TOKEN` to the shell environment if provided:
|
| 89 |
-
|
| 90 |
-
<details>
|
| 91 |
-
<summary>Setting Up a GitLab Token</summary>
|
| 92 |
-
|
| 93 |
-
1. **Generate a Personal Access Token (PAT)**:
|
| 94 |
-
- On GitLab, go to User Settings > Access Tokens.
|
| 95 |
-
- Create a new token with the following scopes:
|
| 96 |
-
- `api` (API access)
|
| 97 |
-
- `read_user` (Read user information)
|
| 98 |
-
- `read_repository` (Read repository)
|
| 99 |
-
- `write_repository` (Write repository)
|
| 100 |
-
- Set an expiration date or leave it blank for a non-expiring token.
|
| 101 |
-
2. **Enter Token in OpenHands**:
|
| 102 |
-
- Click the Settings button (gear icon).
|
| 103 |
-
- Navigate to the `Git` tab.
|
| 104 |
-
- Paste your token in the `GitLab Token` field.
|
| 105 |
-
- Click `Save Changes` to apply the changes.
|
| 106 |
-
</details>
|
| 107 |
-
|
| 108 |
-
<details>
|
| 109 |
-
<summary>Troubleshooting</summary>
|
| 110 |
-
|
| 111 |
-
Common issues and solutions:
|
| 112 |
-
|
| 113 |
-
- **Token Not Recognized**:
|
| 114 |
-
- Ensure the token is properly saved in settings.
|
| 115 |
-
- Check that the token hasn't expired.
|
| 116 |
-
- Verify the token has the required scopes.
|
| 117 |
-
|
| 118 |
-
- **Access Denied**:
|
| 119 |
-
- Verify project access permissions.
|
| 120 |
-
- Check if the token has the necessary scopes.
|
| 121 |
-
- For group/organization repositories, ensure you have proper access.
|
| 122 |
-
</details>
|
| 123 |
-
|
| 124 |
-
### Advanced Settings
|
| 125 |
-
|
| 126 |
-
1. Inside the Settings page, under the `LLM` tab, toggle `Advanced` options to access additional settings.
|
| 127 |
-
2. Use the `Custom Model` text box to manually enter a model if it's not in the list.
|
| 128 |
-
3. Specify a `Base URL` if required by your LLM provider.
|
| 129 |
-
|
| 130 |
-
### Interacting with the AI
|
| 131 |
-
|
| 132 |
-
1. Type your prompt in the input box.
|
| 133 |
-
2. Click the send button or press Enter to submit your message.
|
| 134 |
-
3. The AI will process your input and provide a response in the chat window.
|
| 135 |
-
4. You can continue the conversation by asking follow-up questions or providing additional information.
|
| 136 |
-
|
| 137 |
-
## Tips for Effective Use
|
| 138 |
-
|
| 139 |
-
- Be specific in your requests to get the most accurate and helpful responses, as described in the [prompting best practices](../prompting/prompting-best-practices).
|
| 140 |
-
- Use one of the recommended models, as described in the [LLMs section](usage/llms/llms.md).
|
| 141 |
-
|
| 142 |
-
Remember, the GUI mode of OpenHands is designed to make your interaction with the AI assistant as smooth and intuitive
|
| 143 |
-
as possible. Don't hesitate to explore its features to maximize your productivity.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/how-to/headless-mode.mdx
DELETED
|
@@ -1,57 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Headless Mode
|
| 3 |
-
description: You can run OpenHands with a single command, without starting the web application. This makes it easy to write scripts and automate tasks with OpenHands.
|
| 4 |
-
---
|
| 5 |
-
|
| 6 |
-
This is different from [CLI Mode](./cli-mode), which is interactive, and better for active development.
|
| 7 |
-
|
| 8 |
-
## With Python
|
| 9 |
-
|
| 10 |
-
To run OpenHands in headless mode with Python:
|
| 11 |
-
1. Ensure you have followed the [Development setup instructions](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
|
| 12 |
-
2. Run the following command:
|
| 13 |
-
```bash
|
| 14 |
-
poetry run python -m openhands.core.main -t "write a bash script that prints hi"
|
| 15 |
-
```
|
| 16 |
-
|
| 17 |
-
You'll need to be sure to set your model, API key, and other settings via environment variables
|
| 18 |
-
[or the `config.toml` file](https://github.com/All-Hands-AI/OpenHands/blob/main/config.template.toml).
|
| 19 |
-
|
| 20 |
-
## With Docker
|
| 21 |
-
|
| 22 |
-
To run OpenHands in Headless mode with Docker:
|
| 23 |
-
|
| 24 |
-
1. Set the following environment variables in your terminal:
|
| 25 |
-
- `SANDBOX_VOLUMES` to specify the directory you want OpenHands to access ([See using SANDBOX_VOLUMES for more info](../runtimes/docker#using-sandbox_volumes))
|
| 26 |
-
- `LLM_MODEL` - the LLM model to use (e.g. `export LLM_MODEL="anthropic/claude-sonnet-4-20250514"`)
|
| 27 |
-
- `LLM_API_KEY` - your API key (e.g. `export LLM_API_KEY="sk_test_12345"`)
|
| 28 |
-
|
| 29 |
-
2. Run the following Docker command:
|
| 30 |
-
|
| 31 |
-
```bash
|
| 32 |
-
docker run -it \
|
| 33 |
-
--pull=always \
|
| 34 |
-
-e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.41-nikolaik \
|
| 35 |
-
-e SANDBOX_USER_ID=$(id -u) \
|
| 36 |
-
-e SANDBOX_VOLUMES=$SANDBOX_VOLUMES \
|
| 37 |
-
-e LLM_API_KEY=$LLM_API_KEY \
|
| 38 |
-
-e LLM_MODEL=$LLM_MODEL \
|
| 39 |
-
-e LOG_ALL_EVENTS=true \
|
| 40 |
-
-v /var/run/docker.sock:/var/run/docker.sock \
|
| 41 |
-
-v ~/.openhands-state:/.openhands-state \
|
| 42 |
-
--add-host host.docker.internal:host-gateway \
|
| 43 |
-
--name openhands-app-$(date +%Y%m%d%H%M%S) \
|
| 44 |
-
docker.all-hands.dev/all-hands-ai/openhands:0.41 \
|
| 45 |
-
python -m openhands.core.main -t "write a bash script that prints hi"
|
| 46 |
-
```
|
| 47 |
-
|
| 48 |
-
The `-e SANDBOX_USER_ID=$(id -u)` is passed to the Docker command to ensure the sandbox user matches the host user’s
|
| 49 |
-
permissions. This prevents the agent from creating root-owned files in the mounted workspace.
|
| 50 |
-
|
| 51 |
-
## Advanced Headless Configurations
|
| 52 |
-
|
| 53 |
-
To view all available configuration options for headless mode, run the Python command with the `--help` flag.
|
| 54 |
-
|
| 55 |
-
### Additional Logs
|
| 56 |
-
|
| 57 |
-
For the headless mode to log all the agent actions, in the terminal run: `export LOG_ALL_EVENTS=true`
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/how-to/websocket-connection.mdx
DELETED
|
@@ -1,179 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: WebSocket Connection
|
| 3 |
-
---
|
| 4 |
-
|
| 5 |
-
This guide explains how to connect to the OpenHands WebSocket API to receive real-time events and send actions to the agent.
|
| 6 |
-
|
| 7 |
-
## Overview
|
| 8 |
-
|
| 9 |
-
OpenHands uses [Socket.IO](https://socket.io/) for WebSocket communication between the client and server. The WebSocket connection allows you to:
|
| 10 |
-
|
| 11 |
-
1. Receive real-time events from the agent
|
| 12 |
-
2. Send user actions to the agent
|
| 13 |
-
3. Maintain a persistent connection for ongoing conversations
|
| 14 |
-
|
| 15 |
-
## Connecting to the WebSocket
|
| 16 |
-
|
| 17 |
-
### Connection Parameters
|
| 18 |
-
|
| 19 |
-
When connecting to the WebSocket, you need to provide the following query parameters:
|
| 20 |
-
|
| 21 |
-
- `conversation_id`: The ID of the conversation you want to join
|
| 22 |
-
- `latest_event_id`: The ID of the latest event you've received (use `-1` for a new connection)
|
| 23 |
-
- `providers_set`: (Optional) A comma-separated list of provider types
|
| 24 |
-
|
| 25 |
-
### Connection Example
|
| 26 |
-
|
| 27 |
-
Here's a basic example of connecting to the WebSocket using JavaScript:
|
| 28 |
-
|
| 29 |
-
```javascript
|
| 30 |
-
import { io } from "socket.io-client";
|
| 31 |
-
|
| 32 |
-
const socket = io("http://localhost:3000", {
|
| 33 |
-
transports: ["websocket"],
|
| 34 |
-
query: {
|
| 35 |
-
conversation_id: "your-conversation-id",
|
| 36 |
-
latest_event_id: -1,
|
| 37 |
-
providers_set: "github,gitlab" // Optional
|
| 38 |
-
}
|
| 39 |
-
});
|
| 40 |
-
|
| 41 |
-
socket.on("connect", () => {
|
| 42 |
-
console.log("Connected to OpenHands WebSocket");
|
| 43 |
-
});
|
| 44 |
-
|
| 45 |
-
socket.on("oh_event", (event) => {
|
| 46 |
-
console.log("Received event:", event);
|
| 47 |
-
});
|
| 48 |
-
|
| 49 |
-
socket.on("connect_error", (error) => {
|
| 50 |
-
console.error("Connection error:", error);
|
| 51 |
-
});
|
| 52 |
-
|
| 53 |
-
socket.on("disconnect", (reason) => {
|
| 54 |
-
console.log("Disconnected:", reason);
|
| 55 |
-
});
|
| 56 |
-
```
|
| 57 |
-
|
| 58 |
-
## Sending Actions to the Agent
|
| 59 |
-
|
| 60 |
-
To send an action to the agent, use the `oh_user_action` event:
|
| 61 |
-
|
| 62 |
-
```javascript
|
| 63 |
-
// Send a user message to the agent
|
| 64 |
-
socket.emit("oh_user_action", {
|
| 65 |
-
type: "message",
|
| 66 |
-
source: "user",
|
| 67 |
-
message: "Hello, can you help me with my project?"
|
| 68 |
-
});
|
| 69 |
-
```
|
| 70 |
-
|
| 71 |
-
## Receiving Events from the Agent
|
| 72 |
-
|
| 73 |
-
The server emits events using the `oh_event` event type. Here are some common event types you might receive:
|
| 74 |
-
|
| 75 |
-
- User messages (`source: "user", type: "message"`)
|
| 76 |
-
- Agent messages (`source: "agent", type: "message"`)
|
| 77 |
-
- File edits (`action: "edit"`)
|
| 78 |
-
- File writes (`action: "write"`)
|
| 79 |
-
- Command executions (`action: "run"`)
|
| 80 |
-
|
| 81 |
-
Example event handler:
|
| 82 |
-
|
| 83 |
-
```javascript
|
| 84 |
-
socket.on("oh_event", (event) => {
|
| 85 |
-
if (event.source === "agent" && event.type === "message") {
|
| 86 |
-
console.log("Agent says:", event.message);
|
| 87 |
-
} else if (event.action === "run") {
|
| 88 |
-
console.log("Command executed:", event.args.command);
|
| 89 |
-
console.log("Result:", event.result);
|
| 90 |
-
}
|
| 91 |
-
});
|
| 92 |
-
```
|
| 93 |
-
|
| 94 |
-
## Using Websocat for Testing
|
| 95 |
-
|
| 96 |
-
[Websocat](https://github.com/vi/websocat) is a command-line tool for interacting with WebSockets. It's useful for testing your WebSocket connection without writing a full client application.
|
| 97 |
-
|
| 98 |
-
### Installation
|
| 99 |
-
|
| 100 |
-
```bash
|
| 101 |
-
# On macOS
|
| 102 |
-
brew install websocat
|
| 103 |
-
|
| 104 |
-
# On Linux
|
| 105 |
-
curl -L https://github.com/vi/websocat/releases/download/v1.11.0/websocat.x86_64-unknown-linux-musl > websocat
|
| 106 |
-
chmod +x websocat
|
| 107 |
-
sudo mv websocat /usr/local/bin/
|
| 108 |
-
```
|
| 109 |
-
|
| 110 |
-
### Connecting to the WebSocket
|
| 111 |
-
|
| 112 |
-
```bash
|
| 113 |
-
# Connect to the WebSocket and print all received messages
|
| 114 |
-
echo "40{}" | \
|
| 115 |
-
websocat "ws://localhost:3000/socket.io/?EIO=4&transport=websocket&conversation_id=your-conversation-id&latest_event_id=-1"
|
| 116 |
-
```
|
| 117 |
-
|
| 118 |
-
### Sending a Message
|
| 119 |
-
|
| 120 |
-
```bash
|
| 121 |
-
# Send a message to the agent
|
| 122 |
-
echo '42["oh_user_action",{"type":"message","source":"user","message":"Hello, agent!"}]' | \
|
| 123 |
-
websocat "ws://localhost:3000/socket.io/?EIO=4&transport=websocket&conversation_id=your-conversation-id&latest_event_id=-1"
|
| 124 |
-
```
|
| 125 |
-
|
| 126 |
-
### Complete Example with Websocat
|
| 127 |
-
|
| 128 |
-
Here's a complete example of connecting to the WebSocket, sending a message, and receiving events:
|
| 129 |
-
|
| 130 |
-
```bash
|
| 131 |
-
# Start a persistent connection
|
| 132 |
-
websocat -v "ws://localhost:3000/socket.io/?EIO=4&transport=websocket&conversation_id=your-conversation-id&latest_event_id=-1"
|
| 133 |
-
|
| 134 |
-
# In another terminal, send a message
|
| 135 |
-
echo '42["oh_user_action",{"type":"message","source":"user","message":"Can you help me with my project?"}]' | \
|
| 136 |
-
websocat "ws://localhost:3000/socket.io/?EIO=4&transport=websocket&conversation_id=your-conversation-id&latest_event_id=-1"
|
| 137 |
-
```
|
| 138 |
-
|
| 139 |
-
## Event Structure
|
| 140 |
-
|
| 141 |
-
Events sent and received through the WebSocket follow a specific structure:
|
| 142 |
-
|
| 143 |
-
```typescript
|
| 144 |
-
interface OpenHandsEvent {
|
| 145 |
-
id: string; // Unique event ID
|
| 146 |
-
source: string; // "user" or "agent"
|
| 147 |
-
timestamp: string; // ISO timestamp
|
| 148 |
-
message?: string; // For message events
|
| 149 |
-
type?: string; // Event type (e.g., "message")
|
| 150 |
-
action?: string; // Action type (e.g., "run", "edit", "write")
|
| 151 |
-
args?: any; // Action arguments
|
| 152 |
-
result?: any; // Action result
|
| 153 |
-
}
|
| 154 |
-
```
|
| 155 |
-
|
| 156 |
-
## Best Practices
|
| 157 |
-
|
| 158 |
-
1. **Handle Reconnection**: Implement reconnection logic in your client to handle network interruptions.
|
| 159 |
-
2. **Track Event IDs**: Store the latest event ID you've received and use it when reconnecting to avoid duplicate events.
|
| 160 |
-
3. **Error Handling**: Implement proper error handling for connection errors and failed actions.
|
| 161 |
-
4. **Rate Limiting**: Avoid sending too many actions in a short period to prevent overloading the server.
|
| 162 |
-
|
| 163 |
-
## Troubleshooting
|
| 164 |
-
|
| 165 |
-
### Connection Issues
|
| 166 |
-
|
| 167 |
-
- Verify that the OpenHands server is running and accessible
|
| 168 |
-
- Check that you're providing the correct conversation ID
|
| 169 |
-
- Ensure your WebSocket URL is correctly formatted
|
| 170 |
-
|
| 171 |
-
### Authentication Issues
|
| 172 |
-
|
| 173 |
-
- Make sure you have the necessary authentication cookies if required
|
| 174 |
-
- Verify that you have permission to access the specified conversation
|
| 175 |
-
|
| 176 |
-
### Event Handling Issues
|
| 177 |
-
|
| 178 |
-
- Check that you're correctly parsing the event data
|
| 179 |
-
- Verify that your event handlers are properly registered
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/installation.mdx
DELETED
|
@@ -1,19 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Quick Start
|
| 3 |
-
description: Running OpenHands Cloud or running on your local system.
|
| 4 |
-
icon: rocket
|
| 5 |
-
---
|
| 6 |
-
|
| 7 |
-
## OpenHands Cloud
|
| 8 |
-
|
| 9 |
-
The easiest way to get started with OpenHands is on OpenHands Cloud, which comes with $50 in free credits for new users.
|
| 10 |
-
|
| 11 |
-
To get started with OpenHands Cloud, visit [app.all-hands.dev](https://app.all-hands.dev).
|
| 12 |
-
|
| 13 |
-
For more information see [getting started with OpenHands Cloud.](/usage/cloud/openhands-cloud)
|
| 14 |
-
|
| 15 |
-
## Running OpenHands Locally
|
| 16 |
-
|
| 17 |
-
Run OpenHands on your local system and bring your own LLM and API key.
|
| 18 |
-
|
| 19 |
-
For more information see [running OpenHands locally.](/usage/local-setup)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/key-features.mdx
DELETED
|
@@ -1,32 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Key Features
|
| 3 |
-
icon: bars
|
| 4 |
-
---
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
### Chat Panel
|
| 9 |
-
- Displays the conversation between the user and OpenHands.
|
| 10 |
-
- OpenHands explains its actions in this panel.
|
| 11 |
-
|
| 12 |
-
### Changes
|
| 13 |
-
- Shows the file changes performed by OpenHands.
|
| 14 |
-
|
| 15 |
-
### VS Code
|
| 16 |
-
- Embedded VS Code for browsing and modifying files.
|
| 17 |
-
- Can also be used to upload and download files.
|
| 18 |
-
|
| 19 |
-
### Terminal
|
| 20 |
-
- A space for OpenHands and users to run terminal commands.
|
| 21 |
-
|
| 22 |
-
### Jupyter
|
| 23 |
-
- Shows all Python commands that were executed by OpenHands.
|
| 24 |
-
- Particularly handy when using OpenHands to perform data visualization tasks.
|
| 25 |
-
|
| 26 |
-
### App
|
| 27 |
-
- Displays the web server when OpenHands runs an application.
|
| 28 |
-
- Users can interact with the running application.
|
| 29 |
-
|
| 30 |
-
### Browser
|
| 31 |
-
- Used by OpenHands to browse websites.
|
| 32 |
-
- The browser is non-interactive.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/llms/azure-llms.mdx
DELETED
|
@@ -1,42 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Azure
|
| 3 |
-
description: OpenHands uses LiteLLM to make calls to Azure's chat models. You can find their documentation on using Azure as a provider [here](https://docs.litellm.ai/docs/providers/azure).
|
| 4 |
-
---
|
| 5 |
-
|
| 6 |
-
## Azure OpenAI Configuration
|
| 7 |
-
|
| 8 |
-
When running OpenHands, you'll need to set the following environment variable using `-e` in the
|
| 9 |
-
[docker run command](../installation#running-openhands):
|
| 10 |
-
|
| 11 |
-
```
|
| 12 |
-
LLM_API_VERSION="<api-version>" # e.g. "2023-05-15"
|
| 13 |
-
```
|
| 14 |
-
|
| 15 |
-
Example:
|
| 16 |
-
```bash
|
| 17 |
-
docker run -it --pull=always \
|
| 18 |
-
-e LLM_API_VERSION="2023-05-15"
|
| 19 |
-
...
|
| 20 |
-
```
|
| 21 |
-
|
| 22 |
-
Then in the OpenHands UI Settings under the `LLM` tab:
|
| 23 |
-
|
| 24 |
-
<Note>
|
| 25 |
-
You will need your ChatGPT deployment name which can be found on the deployments page in Azure. This is referenced as
|
| 26 |
-
<deployment-name> below.
|
| 27 |
-
</Note>
|
| 28 |
-
|
| 29 |
-
1. Enable `Advanced` options.
|
| 30 |
-
2. Set the following:
|
| 31 |
-
- `Custom Model` to azure/<deployment-name>
|
| 32 |
-
- `Base URL` to your Azure API Base URL (e.g. `https://example-endpoint.openai.azure.com`)
|
| 33 |
-
- `API Key` to your Azure API key
|
| 34 |
-
|
| 35 |
-
### Azure OpenAI Configuration
|
| 36 |
-
|
| 37 |
-
When running OpenHands, set the following environment variable using `-e` in the
|
| 38 |
-
[docker run command](../installation#running-openhands):
|
| 39 |
-
|
| 40 |
-
```
|
| 41 |
-
LLM_API_VERSION="<api-version>" # e.g. "2024-02-15-preview"
|
| 42 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/llms/custom-llm-configs.mdx
DELETED
|
@@ -1,137 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Custom LLM Configurations
|
| 3 |
-
description: OpenHands supports defining multiple named LLM configurations in your `config.toml` file. This feature allows you to use different LLM configurations for different purposes, such as using a cheaper model for tasks that don't require high-quality responses, or using different models with different parameters for specific agents.
|
| 4 |
-
---
|
| 5 |
-
|
| 6 |
-
## How It Works
|
| 7 |
-
|
| 8 |
-
Named LLM configurations are defined in the `config.toml` file using sections that start with `llm.`. For example:
|
| 9 |
-
|
| 10 |
-
```toml
|
| 11 |
-
# Default LLM configuration
|
| 12 |
-
[llm]
|
| 13 |
-
model = "gpt-4"
|
| 14 |
-
api_key = "your-api-key"
|
| 15 |
-
temperature = 0.0
|
| 16 |
-
|
| 17 |
-
# Custom LLM configuration for a cheaper model
|
| 18 |
-
[llm.gpt3]
|
| 19 |
-
model = "gpt-3.5-turbo"
|
| 20 |
-
api_key = "your-api-key"
|
| 21 |
-
temperature = 0.2
|
| 22 |
-
|
| 23 |
-
# Another custom configuration with different parameters
|
| 24 |
-
[llm.high-creativity]
|
| 25 |
-
model = "gpt-4"
|
| 26 |
-
api_key = "your-api-key"
|
| 27 |
-
temperature = 0.8
|
| 28 |
-
top_p = 0.9
|
| 29 |
-
```
|
| 30 |
-
|
| 31 |
-
Each named configuration inherits all settings from the default `[llm]` section and can override any of those settings. You can define as many custom configurations as needed.
|
| 32 |
-
|
| 33 |
-
## Using Custom Configurations
|
| 34 |
-
|
| 35 |
-
### With Agents
|
| 36 |
-
|
| 37 |
-
You can specify which LLM configuration an agent should use by setting the `llm_config` parameter in the agent's configuration section:
|
| 38 |
-
|
| 39 |
-
```toml
|
| 40 |
-
[agent.RepoExplorerAgent]
|
| 41 |
-
# Use the cheaper GPT-3 configuration for this agent
|
| 42 |
-
llm_config = 'gpt3'
|
| 43 |
-
|
| 44 |
-
[agent.CodeWriterAgent]
|
| 45 |
-
# Use the high creativity configuration for this agent
|
| 46 |
-
llm_config = 'high-creativity'
|
| 47 |
-
```
|
| 48 |
-
|
| 49 |
-
### Configuration Options
|
| 50 |
-
|
| 51 |
-
Each named LLM configuration supports all the same options as the default LLM configuration. These include:
|
| 52 |
-
|
| 53 |
-
- Model selection (`model`)
|
| 54 |
-
- API configuration (`api_key`, `base_url`, etc.)
|
| 55 |
-
- Model parameters (`temperature`, `top_p`, etc.)
|
| 56 |
-
- Retry settings (`num_retries`, `retry_multiplier`, etc.)
|
| 57 |
-
- Token limits (`max_input_tokens`, `max_output_tokens`)
|
| 58 |
-
- And all other LLM configuration options
|
| 59 |
-
|
| 60 |
-
For a complete list of available options, see the LLM Configuration section in the [Configuration Options](../configuration-options) documentation.
|
| 61 |
-
|
| 62 |
-
## Use Cases
|
| 63 |
-
|
| 64 |
-
Custom LLM configurations are particularly useful in several scenarios:
|
| 65 |
-
|
| 66 |
-
- **Cost Optimization**: Use cheaper models for tasks that don't require high-quality responses, like repository exploration or simple file operations.
|
| 67 |
-
- **Task-Specific Tuning**: Configure different temperature and top_p values for tasks that require different levels of creativity or determinism.
|
| 68 |
-
- **Different Providers**: Use different LLM providers or API endpoints for different tasks.
|
| 69 |
-
- **Testing and Development**: Easily switch between different model configurations during development and testing.
|
| 70 |
-
|
| 71 |
-
## Example: Cost Optimization
|
| 72 |
-
|
| 73 |
-
A practical example of using custom LLM configurations to optimize costs:
|
| 74 |
-
|
| 75 |
-
```toml
|
| 76 |
-
# Default configuration using GPT-4 for high-quality responses
|
| 77 |
-
[llm]
|
| 78 |
-
model = "gpt-4"
|
| 79 |
-
api_key = "your-api-key"
|
| 80 |
-
temperature = 0.0
|
| 81 |
-
|
| 82 |
-
# Cheaper configuration for repository exploration
|
| 83 |
-
[llm.repo-explorer]
|
| 84 |
-
model = "gpt-3.5-turbo"
|
| 85 |
-
temperature = 0.2
|
| 86 |
-
|
| 87 |
-
# Configuration for code generation
|
| 88 |
-
[llm.code-gen]
|
| 89 |
-
model = "gpt-4"
|
| 90 |
-
temperature = 0.0
|
| 91 |
-
max_output_tokens = 2000
|
| 92 |
-
|
| 93 |
-
[agent.RepoExplorerAgent]
|
| 94 |
-
llm_config = 'repo-explorer'
|
| 95 |
-
|
| 96 |
-
[agent.CodeWriterAgent]
|
| 97 |
-
llm_config = 'code-gen'
|
| 98 |
-
```
|
| 99 |
-
|
| 100 |
-
In this example:
|
| 101 |
-
- Repository exploration uses a cheaper model since it mainly involves understanding and navigating code
|
| 102 |
-
- Code generation uses GPT-4 with a higher token limit for generating larger code blocks
|
| 103 |
-
- The default configuration remains available for other tasks
|
| 104 |
-
|
| 105 |
-
# Custom Configurations with Reserved Names
|
| 106 |
-
|
| 107 |
-
OpenHands can use custom LLM configurations named with reserved names, for specific use cases. If you specify the model and other settings under the reserved names, then OpenHands will load and them for a specific purpose. As of now, one such configuration is implemented: draft editor.
|
| 108 |
-
|
| 109 |
-
## Draft Editor Configuration
|
| 110 |
-
|
| 111 |
-
The `draft_editor` configuration is a group of settings you can provide, to specify the model to use for preliminary drafting of code edits, for any tasks that involve editing and refining code. You need to provide it under the section `[llm.draft_editor]`.
|
| 112 |
-
|
| 113 |
-
For example, you can define in `config.toml` a draft editor like this:
|
| 114 |
-
|
| 115 |
-
```toml
|
| 116 |
-
[llm.draft_editor]
|
| 117 |
-
model = "gpt-4"
|
| 118 |
-
temperature = 0.2
|
| 119 |
-
top_p = 0.95
|
| 120 |
-
presence_penalty = 0.0
|
| 121 |
-
frequency_penalty = 0.0
|
| 122 |
-
```
|
| 123 |
-
|
| 124 |
-
This configuration:
|
| 125 |
-
- Uses GPT-4 for high-quality edits and suggestions
|
| 126 |
-
- Sets a low temperature (0.2) to maintain consistency while allowing some flexibility
|
| 127 |
-
- Uses a high top_p value (0.95) to consider a wide range of token options
|
| 128 |
-
- Disables presence and frequency penalties to maintain focus on the specific edits needed
|
| 129 |
-
|
| 130 |
-
Use this configuration when you want to let an LLM draft edits before making them. In general, it may be useful to:
|
| 131 |
-
- Review and suggest code improvements
|
| 132 |
-
- Refine existing content while maintaining its core meaning
|
| 133 |
-
- Make precise, focused changes to code or text
|
| 134 |
-
|
| 135 |
-
<Note>
|
| 136 |
-
Custom LLM configurations are only available when using OpenHands in development mode, via `main.py` or `cli.py`. When running via `docker run`, please use the standard configuration options.
|
| 137 |
-
</Note>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/llms/google-llms.mdx
DELETED
|
@@ -1,30 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Google Gemini/Vertex
|
| 3 |
-
description: OpenHands uses LiteLLM to make calls to Google's chat models. You can find their documentation on using Google as a provider -> [Gemini - Google AI Studio](https://docs.litellm.ai/docs/providers/gemini), [VertexAI - Google Cloud Platform](https://docs.litellm.ai/docs/providers/vertex)
|
| 4 |
-
---
|
| 5 |
-
|
| 6 |
-
## Gemini - Google AI Studio Configs
|
| 7 |
-
|
| 8 |
-
When running OpenHands, you'll need to set the following in the OpenHands UI through the Settings under the `LLM` tab:
|
| 9 |
-
- `LLM Provider` to `Gemini`
|
| 10 |
-
- `LLM Model` to the model you will be using.
|
| 11 |
-
If the model is not in the list, enable `Advanced` options, and enter it in `Custom Model`
|
| 12 |
-
(e.g. gemini/<model-name> like `gemini/gemini-2.0-flash`).
|
| 13 |
-
- `API Key` to your Gemini API key
|
| 14 |
-
|
| 15 |
-
## VertexAI - Google Cloud Platform Configs
|
| 16 |
-
|
| 17 |
-
To use Vertex AI through Google Cloud Platform when running OpenHands, you'll need to set the following environment
|
| 18 |
-
variables using `-e` in the [docker run command](../installation#running-openhands):
|
| 19 |
-
|
| 20 |
-
```
|
| 21 |
-
GOOGLE_APPLICATION_CREDENTIALS="<json-dump-of-gcp-service-account-json>"
|
| 22 |
-
VERTEXAI_PROJECT="<your-gcp-project-id>"
|
| 23 |
-
VERTEXAI_LOCATION="<your-gcp-location>"
|
| 24 |
-
```
|
| 25 |
-
|
| 26 |
-
Then set the following in the OpenHands UI through the Settings under the `LLM` tab:
|
| 27 |
-
- `LLM Provider` to `VertexAI`
|
| 28 |
-
- `LLM Model` to the model you will be using.
|
| 29 |
-
If the model is not in the list, enable `Advanced` options, and enter it in `Custom Model`
|
| 30 |
-
(e.g. vertex_ai/<model-name>).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/usage/llms/groq.mdx
DELETED
|
@@ -1,23 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Groq
|
| 3 |
-
description: OpenHands uses LiteLLM to make calls to chat models on Groq. You can find their documentation on using Groq as a provider [here](https://docs.litellm.ai/docs/providers/groq).
|
| 4 |
-
---
|
| 5 |
-
|
| 6 |
-
## Configuration
|
| 7 |
-
|
| 8 |
-
When running OpenHands, you'll need to set the following in the OpenHands UI through the Settings under the `LLM` tab:
|
| 9 |
-
- `LLM Provider` to `Groq`
|
| 10 |
-
- `LLM Model` to the model you will be using. [Visit here to see the list of
|
| 11 |
-
models that Groq hosts](https://console.groq.com/docs/models). If the model is not in the list,
|
| 12 |
-
enable `Advanced` options, and enter it in `Custom Model` (e.g. groq/<model-name> like `groq/llama3-70b-8192`).
|
| 13 |
-
- `API key` to your Groq API key. To find or create your Groq API Key, [see here](https://console.groq.com/keys).
|
| 14 |
-
|
| 15 |
-
## Using Groq as an OpenAI-Compatible Endpoint
|
| 16 |
-
|
| 17 |
-
The Groq endpoint for chat completion is [mostly OpenAI-compatible](https://console.groq.com/docs/openai). Therefore, you can access Groq models as you
|
| 18 |
-
would access any OpenAI-compatible endpoint. In the OpenHands UI through the Settings under the `LLM` tab:
|
| 19 |
-
1. Enable `Advanced` options
|
| 20 |
-
2. Set the following:
|
| 21 |
-
- `Custom Model` to the prefix `openai/` + the model you will be using (e.g. `openai/llama3-70b-8192`)
|
| 22 |
-
- `Base URL` to `https://api.groq.com/openai/v1`
|
| 23 |
-
- `API Key` to your Groq API key
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|