- Restore native Copilot CLI prompts for authentic Plan Mode behavior - Add SQLite-backed session management for state persistence via system prompt - Implement Adaptive Autonomy (Agent chooses planning vs direct execution) - Fix OpenWebUI custom tool context injection for v0.8.x compatibility - Add compact Live TODO widget synchronized with session.db - Upgrade SDK to github-copilot-sdk==0.1.30 - Remove legacy mode switch RPC calls (moved to prompt-driven orchestration) - Fix intent status localization and widget whitespace optimization - Sync bilingual READMEs and all documentation mirrors to v0.10.0
14 KiB
GitHub Copilot SDK Pipe for OpenWebUI
Author: Fu-Jie | Version: 0.10.0 | Project: OpenWebUI Extensions | License: MIT
This is a powerful GitHub Copilot SDK Pipe for OpenWebUI that provides a unified Agentic experience. It goes beyond simple model access by enabling autonomous Intent Recognition, Web Search, and Context Compaction. It seamlessly reuses your existing Tools, MCP servers, OpenAPI servers, and Skills from OpenWebUI to create a truly integrated ecosystem.
- 🧠 Autonomous Intent Recognition: The Agent independently analyzes user goals to determine the most effective path forward.
- 🌐 Smart Web Search: Built-in capability to trigger web searches autonomously based on task requirements.
- ♾️ Infinite Session (Context Compaction): Automatically manages long-running conversations by compacting context (summarization + TODO persistence) to maintain project focus.
- 🧩 Ecosystem Injection: Directly reads and leverages your configured OpenWebUI Tools, MCPs, OpenAPI Servers, and Skills.
- 🎨 Interactive Delivery: Native support for HTML Artifacts and RichUI components for real-time visualization and reporting.
Important
Essential Companion To unlock file handling and data analysis capabilities, you must install the GitHub Copilot SDK Files Filter.
Tip
No Subscription Required for BYOK If you are using your own API keys (BYOK mode with OpenAI/Anthropic), you do NOT need a GitHub Copilot subscription. A subscription is only required to access GitHub's official models.
✨ v0.10.0: Native Prompt Restoration, Live TODO Widget & SDK v0.1.30
- ⌨️ Authentic Prompt Restoration: Most native Copilot CLI prompts have been restored to ensure authentic behavior and enhanced capabilities across the Agentic workflow.
- 📋 Live TODO Widget: Added a compact real-time task tracking widget synchronized with
session.db, keeping in-progress work visible without cluttering the chat history. - 🧩 OpenWebUI Tool Call Fixes: Fixed custom tool invocation by syncing injected context with OpenWebUI 0.8.x expectations, including
__request__,request,body,__messages__,__metadata__,__files__,__task__, and session/chat/message IDs. - 🔒 SDK v0.1.30 + Adaptive Workstyle: Upgraded the pipe to
github-copilot-sdk==0.1.30, moving workflow logic into the system prompt for autonomous "Plan-vs-Execute" decisions. - 🐛 Intent + Widget UX Fixes: Fixed
report_intentlocalization and cleaned up TODO widget layout for a more professional look. - 🧾 Better Embedded Tool Results: Improved HTML/embedded tool outcomes and synchronized documentation surface.
✨ Key Capabilities
- 🔑 Unified Intelligence (Official + BYOK): Seamlessly switch between official GitHub Copilot models and your own models (OpenAI, Anthropic, DeepSeek, xAI) via Bring Your Own Key mode.
- 🛡️ Physical Workspace Isolation: Every session runs in its own isolated directory sandbox. This ensures absolute data privacy and prevents cross-chat file contamination while allowing the Agent full filesystem access.
- 🔌 Universal Tool Protocol:
- Native MCP: Direct, high-performance connection to Model Context Protocol servers.
- OpenAPI Bridge: Connect to any external REST API as an Agent tool.
- OpenWebUI Native: Zero-config bridge to your existing OpenWebUI tools and built-ins (Web Search, Memory, etc.).
- 🧩 OpenWebUI Skills Bridge: Transforms simple OpenWebUI Markdown instructions into powerful SDK skill folders complete with supporting scripts, templates, and data.
- 🧭 Adaptive Planning and Execution: The Agent decides whether to respond with a planning-first analysis or direct implementation flow based on task complexity, ambiguity, and user intent.
- ♾️ Infinite Session Management: Advanced context window management with automatic "Compaction" (summarization + list persistence). Carry out weeks-long projects without losing the core thread.
- 📊 Interactive Artifacts & Publishing:
- Live HTML/JS: Instantly render and interact with apps, dashboards, or reports generated by the Agent.
- Persistent Publishing: Agents can "publish" generated files (Excel, CSV, docs) to OpenWebUI's file storage, providing permanent download links.
- 🌊 UX-First Streaming: Full support for "Thinking" processes (Chain of Thought), status indicators, and real-time progress bars for long-running tasks.
- 🧠 Deep Database Integration: Real-time persistence of TODO lists and session metadata ensures your workflow state is always visible in the UI.
Tip
💡 Visualization Pro-Tip To get the most out of HTML Artifacts and RichUI, we highly recommend asking the Agent to install the skill via its GitHub URL: "Install this skill: https://github.com/nicobailon/visual-explainer". This skill is specifically optimized for generating high-quality visual components and integrates perfectly with this Pipe.
🧩 Companion Files Filter (Required for raw files)
GitHub Copilot SDK Files Filter is the companion plugin that prevents OpenWebUI's default RAG pre-processing from consuming uploaded files before the Pipe receives them.
- What it does: Moves uploaded files to
copilot_filesso the Pipe can access raw binaries directly. - Why it matters: Without it, uploaded files may be parsed/vectorized early and the Agent may lose direct raw-file access.
- v0.1.3 highlights:
- BYOK model-id matching fix (supports
github_copilot_official_sdk_pipe.xxxprefixes). - Optional dual-channel debug log (
show_debug_log) to backend logger + browser console.
- BYOK model-id matching fix (supports
⚙️ Core Configuration (Valves)
1. Administrator Settings (Base)
Administrators define the default behavior for all users in the function settings.
| Valve | Default | Description |
|---|---|---|
GH_TOKEN |
"" |
Global GitHub Token (Requires 'Copilot Requests' permission). |
COPILOTSDK_CONFIG_DIR |
"" |
Persistent directory for SDK config and session state (e.g., /app/backend/data/.copilot). |
ENABLE_OPENWEBUI_TOOLS |
True |
Enable OpenWebUI Tools (includes defined Tools and Built-in Tools). |
ENABLE_OPENAPI_SERVER |
True |
Enable OpenAPI Tool Server connection. |
ENABLE_MCP_SERVER |
True |
Enable Direct MCP Client connection (Recommended). |
ENABLE_OPENWEBUI_SKILLS |
True |
Enable bidirectional sync with OpenWebUI Workspace > Skills. |
OPENWEBUI_SKILLS_SHARED_DIR |
/app/backend/data/cache/copilot-openwebui-skills |
Shared cache directory for skills. |
DISABLED_SKILLS |
"" |
Comma-separated skill names to disable in SDK session. |
REASONING_EFFORT |
medium |
Reasoning effort level: low, medium, high. |
SHOW_THINKING |
True |
Show model reasoning/thinking process. |
INFINITE_SESSION |
True |
Enable Infinite Sessions (automatic context compaction). |
MAX_MULTIPLIER |
1.0 |
Max allowed billing multiplier (0x for free models only). |
EXCLUDE_KEYWORDS |
"" |
Exclude models containing these keywords (comma separated). |
TIMEOUT |
300 |
Timeout for each stream chunk (seconds). |
BYOK_TYPE |
openai |
BYOK Provider Type: openai, anthropic. |
BYOK_BASE_URL |
"" |
BYOK Base URL (e.g., https://api.openai.com/v1). |
BYOK_MODELS |
"" |
BYOK Model List (comma separated). Leave empty to fetch from API. |
CUSTOM_ENV_VARS |
"" |
Custom environment variables (JSON format). |
DEBUG |
False |
Enable this to see detailed logs in your browser console. |
2. User Settings (Individual Overrides)
Standard users can override these settings in their individual Profile/Function settings.
| Valve | Description |
|---|---|
GH_TOKEN |
Use your personal GitHub Token. |
REASONING_EFFORT |
Individual reasoning effort preference. |
SHOW_THINKING |
Show model reasoning/thinking process. |
MAX_MULTIPLIER |
Maximum allowed billing multiplier override. |
EXCLUDE_KEYWORDS |
Exclude models containing these keywords. |
ENABLE_OPENWEBUI_SKILLS |
Enable loading all active OpenWebUI skills readable by you into SDK SKILL.md directories. |
DISABLED_SKILLS |
Comma-separated skill names to disable for your own session. |
BYOK_API_KEY |
Use your personal OpenAI/Anthropic API Key. |
📤 Enhanced Publishing & Interactive Components
The publish_file_from_workspace tool now uses a clearer delivery contract for production use:
- Artifacts mode (
artifacts, default): Agent returns[Preview]+[Download]and may outputhtml_embedin a ```html block for direct chat rendering. - Rich UI mode (
richui): Agent returns[Preview]+[Download]only; integrated preview is rendered automatically via emitter (no iframe block in message). - 📄 PDF delivery safety rule: Always output Markdown links only (
[Preview]+[Download]when available). Do not embed PDF via iframe/html blocks. - ⚡ Stable dual-channel publishing: Keeps interactive viewing and persistent file download aligned across local/object-storage backends.
- ✅ Status integration: Emits real-time publishing progress and completion feedback to the OpenWebUI status bar.
- 📘 Publishing Tool Guide (GitHub): publish_file_from_workspace Guide
🧩 OpenWebUI Skills Bridge & manage_skills Tool
The SDK now features a bidirectional bridge with the OpenWebUI Workspace > Skills page:
- 🔄 Automatic Sync: Skills created or updated in the OpenWebUI UI are automatically downloaded as
SKILL.mdfolders into the SDK's shared cache on every request. - 🛠️
manage_skillsTool: The Agent can deterministically manage skills using this tool.list: List all installed skills and their descriptions.install: Install a skill from a GitHub URL (auto-normalized to archive link) or a direct.zip/.tar.gz.create: Create a new skill directory from context, writingSKILL.mdand any extra resource files (scripts, templates).edit: Update an existing skill folder.delete: Atomically delete both the local directory and the linked OpenWebUI DB entry.
- 📁 Full Folder Support: Unlike the single-markdown storage in OpenWebUI DB, the SDK loads the entire folder for each skill. This allows skills to carry binary scripts, data files, or complex templates alongside the core instructions.
- 🌐 Shared Persistent Cache: Skills are stored in
OPENWEBUI_SKILLS_SHARED_DIR/shared/, which is persistent across sessions and container restarts. - 📚 Full Skill Docs (GitHub): manage_skills Tool Guide | Skills Best Practices
🌊 Fluid UX & Granular Status Feedback
Say goodbye to the "stuck" feeling during complex processing:
- 🔄 Real-Time Status Bubbles: Maps internal SDK events (
turn_start,compaction,subagent_started) directly to the OpenWebUI status bar. - 🧭 Richer Stage Descriptions: Status text now explicitly reflects phases such as processing, skill invocation, tool execution, tool completion/failure, publishing, and final completion.
- ⏱️ Long-Task Heartbeat: During long waits, the status bar emits periodic "still processing" updates (elapsed-time style) to avoid silent stalls.
- 📈 Tool Progress Tracking: Long-running tool executions provide live progress percentages and descriptive sub-task updates in the status bar.
- ⚡ Immediate Feedback: Response starts with an instant "Assistant is processing" status, eliminating idle wait time before the first token.
🛡️ Smart Version Compatibility
The plugin automatically adapts its feature set based on your OpenWebUI version:
- v0.8.0+: Rich UI, live status bubbles, and integrated HTML preview.
- Older: Automatic fallback to standard Markdown blocks for maximum stability.
🎯 Use Cases (What can you do?)
- 📁 Fully Autonomous DevOps: Agent analyzes code, runs tests, and applies patches within its isolated sandbox.
- 📊 Deep Data Auditing: Directly process raw Excel/CSV data via Python (bypassing RAG) and generate visual reports.
- 📝 Long-Task Management: Automatically decomposes complex requests and persists TOD·O progress across sessions.
⭐ Support
If this plugin has been useful, a Star on OpenWebUI Extensions would be a great motivation for me. Thank you!
🚀 Installation & Configuration
1) Import Function
- Open OpenWebUI, go to Workspace -> Functions.
- Click + (Create Function), paste the content of
github_copilot_sdk.py. - Save and ensure it is enabled.
2) Get Token
- Visit GitHub Token Settings.
- Create Fine-grained token, granting Account permissions -> Copilot Requests access.
- Paste the generated Token into the
GH_TOKENfield in Valves.
3) Authentication Requirement (Mandatory)
You MUST configure at least one credential source:
GH_TOKEN(GitHub Copilot subscription route), orBYOK_API_KEY(OpenAI/Anthropic route).
If neither is configured, the model list will not appear.
📋 Troubleshooting & Dependencies
- Agent ignores files?: Ensure the Files Filter is enabled, otherwise RAG will interfere with raw binaries.
- No status updates?: Status bubbles are emitted for processing/tool phases; TODO progress bars specifically appear when the Agent uses
update_todo. - Dependencies: This Pipe automatically manages
github-copilot-sdk(Python) and utilizes the bundled binary CLI. No manual install required.
Changelog
See the full history on GitHub: OpenWebUI Extensions