VS Code gets the gateway's models from an extension the gateway serves
CI / test (push) Successful in 8m43s
CI / test (push) Successful in 8m43s
llmgw's own extension for VS Code, plain JavaScript with no dependencies, packed into a .vsix by the binary at /setup/vscode/llmgw.vsix with the serving gateway's address in it, so it needs no build, no Node and no marketplace. It registers llmgw as a language-model provider: the chat's model picker, agent mode and any extension that asks VS Code for a model get every chat model the key may use, sized and with tool and vision capabilities as the catalog says, streamed, tool calls both ways. VS Code is a tool on the account page's Connect your editor: a key, the install command, and an Open in VS Code link that hands the key to the extension's secret storage. The extension's Sign In opens the page with a state of its own; a link without it is confirmed, the gateway named, since it decides where code is sent. Tested in VS Code 1.138 against the PoC: 27 models listed, an answer from qwen2.5-0.5b-instruct, and qwen3-coder-30b calling a tool and using its result (internal/vscodeext/e2e). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
fea5774fe5
commit
38dfe268c9
17 files changed
+1412
-9
No files matched your search
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"name": "llmgw",
|
||||
"publisher": "llmgw",
|
||||
"displayName": "llmgw",
|
||||
"description": "The models your llmgw gateway serves, in VS Code's chat and in every extension that asks VS Code for a language model.",
|
||||
"version": "0.0.0",
|
||||
"license": "UNLICENSED",
|
||||
"engines": {
|
||||
"vscode": "^1.104.0"
|
||||
},
|
||||
"categories": ["AI", "Chat"],
|
||||
"keywords": ["llmgw", "llm", "gateway", "self-hosted", "on-premises"],
|
||||
"main": "./extension.js",
|
||||
"extensionKind": ["ui", "workspace"],
|
||||
"activationEvents": ["onStartupFinished", "onUri"],
|
||||
"capabilities": {
|
||||
"untrustedWorkspaces": { "supported": true },
|
||||
"virtualWorkspaces": true
|
||||
},
|
||||
"contributes": {
|
||||
"languageModelChatProviders": [
|
||||
{ "vendor": "llmgw", "displayName": "llmgw" }
|
||||
],
|
||||
"commands": [
|
||||
{ "command": "llmgw.signIn", "title": "Sign In", "category": "llmgw" },
|
||||
{ "command": "llmgw.enterKey", "title": "Enter API Key", "category": "llmgw" },
|
||||
{ "command": "llmgw.signOut", "title": "Sign Out", "category": "llmgw" },
|
||||
{ "command": "llmgw.refresh", "title": "Refresh Models", "category": "llmgw" }
|
||||
],
|
||||
"configuration": {
|
||||
"title": "llmgw",
|
||||
"properties": {
|
||||
"llmgw.gatewayUrl": {
|
||||
"type": "string",
|
||||
"default": "",
|
||||
"markdownDescription": "The gateway's address, such as `https://llm.example.com`: the one the people running it gave you, without `/v1`."
|
||||
},
|
||||
"llmgw.showModelsWithoutTools": {
|
||||
"type": "boolean",
|
||||
"default": true,
|
||||
"markdownDescription": "Offer models whose tool calls the gateway does not vouch for. They answer in chat, but an agent needs a model that makes tool calls to read a file or run a command."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user