🚀 LiteLLM Connector for GitHub Copilot Chat

Open VSX Version Open VSX Downloads

Bring any LiteLLM-supported model into the Copilot Chat model picker — OpenAI, Anthropic, Google, Mistral, local Llama, and more. If LiteLLM can talk to it, Copilot can use it.

🆕 What's New in 2.5.19

Version 2.5.19 improves chat reliability, adds model-picker branding, and makes commit-message generation cancellable.

📏 Fewer false token-limit errors — History trimming uses the raw model's calibrated estimates, keeps tool calls and results together, and avoids learning text calibration from multimodal turns.
🔤 Safer Unicode requests — Invalid Unicode in supported text is repaired before sending; malformed protocol or opaque data is rejected instead of silently changed.
🏷️ LiteLLM Connector model-picker branding — The provider tab shows the connector's logo on VS Code 1.144 and newer.
⏹️ Cancellable commit generation — The Source Control generate button becomes an animated stop button; stopping restores your existing draft.

ℹ️ Credit — Thank you to @bn45hkurr0y4 for the token-limit bug report and original fix in #173 and #174; the follow-up implementation landed in #176. 🙏

See CHANGELOG.md for previous release notes.

⭐️ Support the Project

⭐ Star on GitHub: https://github.com/gethnet/litellm-connector-copilot
📝 Leave a review on the VS Code Marketplace
☕ Support development: Ko-fi | Buy Me a Coffee

⚡ Quick Start (60 Seconds)

Install GitHub Copilot Chat (if not already installed)
Install LiteLLM Connector for Copilot
Open Command Palette (Ctrl+Shift+P)
Run LiteLLM: Manage Configuration
Add a provider group:
- Name (e.g., "Cloud", "Local")
- Base URL (e.g., http://localhost:4000)
- API Key (required)
Open Copilot Chat → pick a model → start chatting!

✅ Requirements

🖥️ VS Code 1.125+
🌐 A LiteLLM proxy URL and API key

No Copilot subscription required. BYOK models work without a GitHub login or Copilot plan — including air-gapped scenarios. See Using BYOK Without Copilot to redirect the Copilot-backed utility models to your LiteLLM models.

✨ Features & Differentiators

Feature	Why It Matters
🔌 Direct LiteLLM Integration	No third-party wrappers — talks to your proxy directly with native message formatting, streaming, and tool handling
🧩 Native VS Code Integration	Model picker groupings, category tags, reasoning effort selectors, token indicators — all first-class in VS Code's Language Model API
👤 Single-Maintainer Project	Direct access to the person who builds it. Fast decisions, straightforward communication. We test thoroughly but things slip through — report issues, we respond.
🌍 Any Model	Access GPT-4, Claude, Gemini, Llama, DeepSeek, and more
⛓️ Multi-Backend	Aggregate from multiple proxies with proper isolation — each backend stays grouped in the picker
💭 Thinking Support	Full Anthropic thinking content (signatures, redacted, display metadata)
🌊 Real-Time Streaming	Watch responses as they're generated
🛠️ Tool Calling	Models can use tools to interact with your workspace
👁️ Vision	Image analysis support
📊 Token Tracking	Real-time input/output token usage
✍️ Commit Generation	Generate conventional commit messages from staged changes; stop an active generation and restore your draft
🔐 Secure	API keys stored in VS Code's encrypted storage

🐛 Troubleshooting

Models not showing up?

Run LiteLLM: Manage Configuration and verify Base URL + API key
Run LiteLLM: Reload Models to force refresh
If stuck: Remove LiteLLM provider groups via LiteLLM: Manage Configuration → VS Code's Language Models UI, then re-add
On VS Code 1.138+ stable, remove any edit-tool values (find-replace, apply-patch, …) from litellm-connector.modelCapabilitiesOverrides — they require a proposed API and blank the model list. toolCalling and imageInput are fine.

"Sign in to use GitHub Copilot" appears while using BYOK? A background utility call is being routed to a Copilot model. Set chat.byokUtilityModelDefault to "mainAgent" — see below.

🚫 Using BYOK Without Copilot

BYOK models work without signing into a GitHub account or a Copilot plan, including fully air-gapped scenarios. Your LiteLLM Connector models appear in the Chat model picker and work for chat and agent workflows with no Copilot subscription required.

A few Copilot-backed features stop working without a login because their defaults point at Copilot models. You can redirect all of them to your LiteLLM Connector models so the full chat experience keeps working offline.

⚠️ Set chat.byokUtilityModelDefault to "mainAgent" when you are not signed in to Copilot. Since VS Code 1.134 it defaults to "copilot", which routes background utility calls (chat titles, commit messages, summaries) to Copilot models and shows a "Sign in to use GitHub Copilot" dialog when no Copilot token is available. "mainAgent" reuses your selected LiteLLM chat model. A specific model in chat.utilityModel / chat.utilitySmallModel always takes precedence. This setting does not affect which models appear in the picker.

Settings that take a fully qualified model name

A fully qualified model name is litellm-connector/<provider-group>/<model>, matching the identifier shown in the Chat model picker.

Setting	What it controls
`github.copilot.selectedCompletionModel`	Inline completions model
`github.copilot.chat.workspace.preferredEmbeddingsModel`	Semantic search embeddings
`github.copilot.chat.instantApply.shortContextModelName`	Instant Apply short-context model

These settings present a dropdown of every available model (including your BYOK models). Pick the LiteLLM Connector model you want from the list.

Setting	What it controls
`chat.utilityModel`	Background utility model (chat titles, rename suggestions)
`chat.utilitySmallModel`	Lightweight utility model (commit messages, summaries)

Example `settings.json`

{
  // Use your selected LiteLLM chat model for utility calls instead of Copilot.
  // Values: "mainAgent" | "copilot" (default; requires Copilot sign-in) | "none" (error if unset).
  "chat.byokUtilityModelDefault": "mainAgent",

  // Redirect Copilot-backed features to LiteLLM Connector models.
  "github.copilot.selectedCompletionModel": "litellm-connector/<group>/<model>",
  "github.copilot.chat.workspace.preferredEmbeddingsModel": "litellm-connector/<group>/<embedding-model>",
  "github.copilot.chat.instantApply.shortContextModelName": "litellm-connector/<group>/<model>",

  // Pick these from the model dropdown in Settings UI.
  "chat.utilityModel": "litellm-connector/<group>/<model>",
  "chat.utilitySmallModel": "litellm-connector/<group>/<small-model>"
}

Replace <group> with your provider group name and the model placeholders with models from your LiteLLM proxy. Reload the window (Developer: Reload Window) for changes to take effect.

Copy a fully qualified model name

After configuring a provider, run LiteLLM: Reload Models, then run LiteLLM: Show Available Models. Select a model to copy its fully qualified ID to the clipboard for use in VS Code BYOK settings.

The picker shows a friendly model name but copies the complete model ID, including the provider-group namespace. Use the copied value for settings such as github.copilot.selectedCompletionModel, chat.utilityModel, and chat.utilitySmallModel.

What still requires Copilot

Some surfaces have no BYOK routing in VS Code today, regardless of configuration:

Surface	Status
Next Edit Suggestions	Copilot models only
Execution / search subagents	Copilot models only
Agents window subagents	BYOK main model works; BYOK models are not offered for subagents (vscode#333802)
Copilot's SCM commit-message sparkle	Follows `chat.utilitySmallModel` / `chat.byokUtilityModelDefault`. The connector's own LiteLLM: Generate Commit Message command talks to your LiteLLM model directly and never needs Copilot.

These are VS Code / Copilot Chat limitations, not connector limitations.

Enterprise note: For Copilot Business or Enterprise, organization administrators can control BYOK availability through Copilot policy settings.

⚙️ Configuration

Base URL + API key are configured through VS Code's Language Models UI (run LiteLLM: Manage Configuration).

Standard Settings

Setting	Default	Description
`commitModelIdOverride`	`""`	Model ID for commit message generation. Accepts the complete `litellm-connector/<group>/<model>` value copied from the model picker; the vendor prefix is normalized automatically.
`commitOutputTokenReserve`	`0`	Requested commit output cap used during diff preparation, also capped to the known model output maximum. `0` = adaptive (`1000 + 400/file + 40/hunk`), target clamped to 1000–8000. Output consumes explicit combined context, not an independent input maximum twice.
`commitSystemPromptOverride`	`""`	Override the system prompt used for git commit message generation. Leave empty for the built-in default.
`commitMessagePromptOverride`	`""`	Override the commit message style/body prompt. Leave empty for the built-in default.
`inactivityTimeout`	`60`	Seconds before stream is considered idle
`disableCaching`	`false`	When enabled, bypass LiteLLM caching for models that advertise support for the `cache` parameter
`disableLiteLLMResponseCaching`	`false`	Bypass the LiteLLM proxy response cache on every request (`no-cache` + `no-store`), regardless of model card. Use when the proxy replays truncated/incomplete responses to retries
`disableAbnormalTerminationErrors`	`false`	Log-only mode for truncated/empty/failed stream terminals instead of surfacing them as chat errors
`disableQuotaToolRedaction`	`false`	Disable automatic tool removal on quota errors
`enableModelOverrides`	`false`	Enable model-card override rules
`displayPricingInPicker`	`true`	Show model pricing in picker details, hovers, and cost metadata; native model-name rows remain price-free
`discoveryTimeoutMs`	`5000`	Timeout (ms) for model discovery
`discoveryCacheTtlMs`	`60000`	Cache TTL (ms), 0 to disable
`discoveryFireDebounceMs`	`250`	Debounce (ms) for change notifications
`discoveryFireMinIntervalMs`	`2000`	Min interval (ms) between notifications

Reasoning model-card overrides are disabled by default. Enable enableModelOverrides when LiteLLM reports incorrect or incomplete reasoning metadata. Overrides replace or add only the explicitly named LiteLLM fields; related fields are not inferred.

🛠️ Help: Applying a Model Override

Model overrides are disabled by default. To correct incomplete LiteLLM /model/info metadata:

Open Preferences: Open User Settings (JSON) or Preferences: Open Workspace Settings (JSON).
Set litellm-connector.enableModelOverrides to true.
Add a matching rule to litellm-connector.modelOverrides.
Run LiteLLM: Reload Models.

Use the raw LiteLLM model_name and exact snake_case model-card fields. Only explicitly defined fields are changed; related fields are not inferred.

{
   "litellm-connector.enableModelOverrides": true,
   "litellm-connector.modelOverrides": [
      {
         "match": "^gpt-4\\.8$",
         "supports_reasoning": true,
         "supports_max_reasoning_effort": true
      }
   ]
}

Define each desired effort explicitly, such as supports_xhigh_reasoning_effort: true. Setting one effort field does not enable supports_reasoning or any other effort field automatically.

Advanced (JSON-Only)

These aren't in Settings UI — add to settings.json if needed:

Setting	Default	Why Use It
`forceResponsesEndpoint`	`false`	Force all models to use `/responses` endpoint for consistent reasoning/thinking support
`allowChatCompletionsFallback`	`false`	Fall back to `/chat/completions` if `/responses` fails (needs `forceResponsesEndpoint: true`)

⌨️ Commands

LiteLLM: Manage Configuration — Add/edit provider groups
LiteLLM: Reload Models — Refresh model list
LiteLLM: Show Available Models — View discovered models and copy a fully qualified ID to the clipboard
Generate Commit Message — Generate a commit message from staged changes (SCM sparkle appears once commitModelIdOverride is set)
Stop Generating Commit Message — Cancel an active generation from the animated Source Control stop button or the Command Palette; the original draft is restored. Failed or empty responses also restore the draft.
LiteLLM: Set Log Level — Change logging verbosity
LiteLLM: Reset All Configuration — Remove all provider groups, API keys, and connector settings (asks for confirmation)

📋 Feedback & Issues

GitHub Issues: https://github.com/gethnet/litellm-connector-copilot/issues

🧩 Notes

This extension is a language model provider for VS Code Chat
Works with or without GitHub Copilot (BYOK models work without a Copilot subscription)
VS Code Chat (formerly Copilot Chat) is built into VS Code 1.120+

LiteLLM Connector for Copilot

Gethnet

🚀 LiteLLM Connector for GitHub Copilot Chat

🆕 What's New in 2.5.19

⭐️ Support the Project

⚡ Quick Start (60 Seconds)

✅ Requirements

✨ Features & Differentiators

🐛 Troubleshooting

🚫 Using BYOK Without Copilot

Settings that take a fully qualified model name

Example `settings.json`

Copy a fully qualified model name

What still requires Copilot

⚙️ Configuration

Standard Settings

🛠️ Help: Applying a Model Override

Advanced (JSON-Only)

⌨️ Commands

📋 Feedback & Issues

🧩 Notes

📜 License

LiteLLM Connector for Copilot

Gethnet

🚀 LiteLLM Connector for GitHub Copilot Chat

🆕 What's New in 2.5.19

⭐️ Support the Project

⚡ Quick Start (60 Seconds)

✅ Requirements

✨ Features & Differentiators

🐛 Troubleshooting

🚫 Using BYOK Without Copilot

Settings that take a fully qualified model name

Settings that use a model dropdown

Example settings.json

Copy a fully qualified model name

What still requires Copilot

⚙️ Configuration

Standard Settings

🛠️ Help: Applying a Model Override

Advanced (JSON-Only)

⌨️ Commands

📋 Feedback & Issues

🧩 Notes

📜 License

Example `settings.json`