6 Commits
Author SHA1 Message Date
inference-bot 8f1d71d913 fix: abort in-flight chat requests on cancellation
Cancellation was only checked at POST time; once the SSE stream was
open the reader loop never looked at the token again, so a stopped
chat kept generating server-side (and billing) until the response
ended.

Wire an AbortController to token.onCancellationRequested, pass its
signal to fetch, and check token.isCancellationRequested at the top
of the reader loop so the connection closes as soon as the user
stops the request. AbortError is swallowed (a stop is not a
failure); real HTTP errors still surface, and the cancellation
listener is disposed in a finally.
2026-11-08 15:44:59 +00:00
inference-bot e9a060af0f docs: project is now official
Drop the unofficial framing (title, intro disclaimer, limitations note)
and state the project as official, maintained in the co-op's Git at
code/inference-coop-copilot.
2026-11-07 00:44:54 +00:00
evanp 46b8d7e888 0.2.2 2026-11-06 14:02:02 -05:00
evanp 0460305327 fix: publisher in package.json 2026-11-06 14:01:56 -05:00
evanp c4bb02a7a2 0.2.1 2026-11-06 13:39:18 -05:00
evanp f295cb8535 doc: update README 2026-11-06 13:39:14 -05:00
5 changed files with 84 additions and 14 deletions

No files matched your search

+15 -1
View File
@@ -10,6 +10,18 @@ and this project adheres to
## [Unreleased]
## [0.2.2] - 2026-11-06
### Fixed
- Correct the publisher in package.json.
## [0.2.1] - 2026-11-06
### Fixed
- Correct instructions for setting the API key in README.
## [0.2.0] - 2026-11-06
### Added
@@ -58,6 +70,8 @@ First release usable for chat.
Initial development release. Not functional for chat.
[Unreleased]: https://git.inference.coop/evanp/inference-coop-copilot/compare/v0.2.0...HEAD
[Unreleased]: https://git.inference.coop/evanp/inference-coop-copilot/compare/v0.2.2...HEAD
[0.2.2]: https://git.inference.coop/evanp/inference-coop-copilot/compare/v0.2.1...v0.2.2
[0.2.1]: https://git.inference.coop/evanp/inference-coop-copilot/compare/v0.2.0...v0.2.1
[0.2.0]: https://git.inference.coop/evanp/inference-coop-copilot/compare/v0.1.0...v0.2.0
[0.1.0]: https://git.inference.coop/evanp/inference-coop-copilot/releases/tag/v0.1.0
+31 -8
View File
@@ -1,14 +1,37 @@
# Inference Coop (unofficial)
# Inference Coop for Copilot Chat
Community-built model provider for [inference.coop](https://inference.coop),
usable in GitHub Copilot Chat. Not affiliated with or endorsed by the
Inference Cooperative.
Official model provider for [inference.coop](https://inference.coop), usable
in GitHub Copilot Chat. An official project of the Inference Cooperative,
maintained in the co-op's Git at
[code/inference-coop-copilot](https://git.inference.coop/code/inference-coop-copilot).
## Requirements
- VS Code 1.145 or newer
- GitHub Copilot Chat, installed and signed in
- A co-op membership and API key
Copilot Business/Enterprise: your administrator must leave "Bring Your Own
Language Model Key" enabled, or these models will not appear.
## Setup
1. Set `inferenceCoop.apiKey` in your settings to your co-op API key.
2. Open Copilot Chat and pick an `inference-coop/…` model.
1. Run **Inference Coop: Set API Key** from the Command Palette and paste
your co-op key. It is stored in VS Code's secret storage, not in settings.
2. Open Copilot Chat, click the model name, and pick an `inference-coop/…`
model. Tool calling works, so agent mode is usable.
## Status
To use a different gateway, set `inferenceCoop.baseUrl`. To sign out, run
**Inference Coop: Sign Out**.
Early development. Text chat only so far; tool calling is not implemented.
## Limitations
- No image input; models are advertised as text-and-tools only.
- Token counts are estimated rather than computed with a real tokenizer, so
context budgeting is approximate.
- No inline code completions. Copilot does not support third-party providers
for completions; this extension only adds chat models.
## License
Apache-2.0. See [LICENSE](LICENSE) and [NOTICE](NOTICE).
+2 -2
View File
@@ -1,12 +1,12 @@
{
"name": "inference-coop-copilot",
"version": "0.2.0",
"version": "0.2.2",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "inference-coop-copilot",
"version": "0.2.0",
"version": "0.2.2",
"devDependencies": {
"@types/mocha": "^10.0.10",
"@types/node": "24.x",
+2 -2
View File
@@ -2,11 +2,11 @@
"name": "inference-coop-copilot",
"displayName": "inference-coop-copilot",
"description": "Inference.coop models for Copilot Chat (unofficial)",
"version": "0.2.0",
"version": "0.2.2",
"engines": {
"vscode": "^1.145.0"
},
"publisher": "inference-coop",
"publisher": "evanp",
"repository": {
"type": "git",
"url": "https://git.inference.coop/evanp/inference-coop-copilot.git"
+34 -1
View File
@@ -109,6 +109,19 @@ export function activate(context: vscode.ExtensionContext) {
body.tool_choice = "auto";
}
if (token.isCancellationRequested) {
out.appendLine(" request cancelled before it started");
return;
}
// Abort the request as soon as the user cancels, so a cancelled chat
// stops generating (and stops billing) server-side.
const abort = new AbortController();
const cancelSubscription = token.onCancellationRequested(() =>
abort.abort(),
);
try {
const res = await fetch(`${BASE_URL}/chat/completions`, {
method: "POST",
headers: {
@@ -116,7 +129,7 @@ export function activate(context: vscode.ExtensionContext) {
"Content-Type": "application/json",
},
body: JSON.stringify(body),
signal: token.isCancellationRequested ? AbortSignal.abort() : undefined,
signal: abort.signal,
});
out.appendLine(` /chat/completions status: ${res.status}`);
if (!res.ok || !res.body) {
@@ -157,6 +170,11 @@ export function activate(context: vscode.ExtensionContext) {
};
while (true) {
if (token.isCancellationRequested) {
out.appendLine(" cancelled mid-stream; aborting request");
abort.abort(); // close the connection so the gateway stops generating
return;
}
const { done, value } = await reader.read();
if (done) {
break;
@@ -221,6 +239,21 @@ export function activate(context: vscode.ExtensionContext) {
flushTools();
}
out.appendLine(` stream ended, ${textChunks} text chunks`);
} catch (e) {
// A cancellation aborts fetch (before headers) or the pending stream
// read (mid-response) - both surface as AbortError. That is the user
// pressing stop, not a failure: stop quietly instead of erroring.
if (
token.isCancellationRequested ||
(e instanceof Error && e.name === "AbortError")
) {
out.appendLine(" stream aborted after cancellation");
return;
}
throw e;
} finally {
cancelSubscription.dispose();
}
},
async provideTokenCount() {