5.9 KiB
5.9 KiB
Changelog
All notable changes to this project will be documented in this file.
The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.
Unreleased
Added
- Gitea Actions workflow (
.gitea/workflows/publish.yaml) that publishes to the VS Code Marketplace when avX.Y.Ztag is pushed. It fails if the tag disagrees with theversionin package.json, runs the existingnpm run packagegate (type-check, lint, production bundle) before publishing, and passes--skip-duplicateso a re-run is a no-op rather than a failure. Requires repository Actions to be enabled and aVSCE_PATrepository secret.
Fixed
- Excluded
.gitea/**from the packaged extension in.vscodeignore, so workflow files are no longer bundled into the VSIX.
0.4.1 - 2026-11-08
Fixed
- Moved the Marketplace
baseContentUrl/baseImagesUrlsettings into avsceblock in package.json. vsce only reads them from there (or from CLI flags) for non-GitHub/GitLab repositories, so packaging previously failed with "Couldn't detect the repository". Verified the packaged README now links the icon, LICENSE, and NOTICE with working Gitea URLs.
0.4.0 - 2026-11-08
Added
- Set
baseContentUrlin package.json to the Gitea raw URL, so LICENSE and NOTICE links in the README resolve correctly on the Marketplace. - Added an npm
publishscript runningvsce publish, with@vscode/vsceas a dev dependency, for releasing to the VS Code Marketplace. - Added
language-modelsandchatMarketplace tags, so the extension appears in the "Install Language Models" discovery flow. The tags take effect when the next version is published. - Added an extension icon rendered from the Inference Coop logo, shown on the Marketplace listing and in the Extensions view.
- Added Marketplace keywords for search discoverability.
- Changed the Marketplace category from "Other" to "AI".
- Changed the Marketplace display name from the package ID to the readable title, "Inference Coop for Copilot Chat".
- Reworked the README: an "About the Inference Cooperative" section for prospective members, step-by-step Setup instructions starting with creating an API key at the dashboard (noting keys are shown only once), and consistent use of "Inference Cooperative" as the organization name.
Removed
- Removed the unused
inferenceCoop.baseUrlsetting. The extension only ever talked to the hardcodedhttps://gateway.inference.coop/v1gateway; keeping a configurable URL would let a modified setting redirect the stored API key to a hostile endpoint. - Removed the membership/API-key line from Requirements, since Setup now walks through acquiring both.
0.3.0 - 2026-11-08
Changed
- Removed the "(unofficial)" disclaimer from the package description and
NOTICE, and the README; the project is now official, maintained in the
co-op's Git at
code/inference-coop-copilot. - Updated the repository URL to
https://git.inference.coop/code/inference-coop-copilot.gitin package.json and CHANGELOG links.
Fixed
- Abort in-flight chat requests on cancellation: an
AbortControllerwired totoken.onCancellationRequestedcloses the SSE connection as soon as the user stops the request, instead of the server continuing to generate until the response ends.
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
- "Inference Coop: Set API Key" and "Inference Coop: Sign Out" commands.
- Model list caching with
onDidChangeLanguageModelChatInformation, so the picker refreshes when models change instead of requiring a restart.
Changed
- Breaking: the API key is now stored in VS Code
SecretStorageinstead of theinferenceCoop.apiKeysetting. Run "Inference Coop: Set API Key" once after upgrading; the gateway base URL is now the only setting.
Fixed
- Models intermittently missing from the Copilot Chat model picker when the provider's initial model fetch lost a race with chat activation.
0.1.0 - 2026-11-06
First release usable for chat.
Added
- Streaming chat responses via
provideLanguageModelChatResponse, with text streamed to the UI as it arrives. - Tool calling: tool schemas are sent to the gateway, streamed tool-call
fragments are reassembled, and tool results are translated back into the
conversation. Verified end to end in agent mode against
tinfoil/gpt-oss-120b. - Extension scaffold with esbuild build pipeline and ESLint/tsc checks.
- Registration of a
LanguageModelChatProviderunder theinference-coopvendor, discoverable viacontributes.languageModelChatProviders. - Model discovery: fetches
GET https://gateway.inference.coop/v1/modelsand filters to chat-capable models, excluding image-generation and audio endpoints. - "Inference Coop" output channel logging provider activation, model enumeration, and HTTP status codes.
Changed
- Adopted the Apache License 2.0.
[0.0.1] - 2026-11-06
Initial development release. Not functional for chat.