v0.1.3 — Suppress error popups, robust stream abort, smart retry

What's New

Fixed

• Model list fetch errors no longer spam notifications — when the MiMo API key is invalid/expired (401) or the model list endpoint is unreachable, the error is now silently logged to the MiMo Output Channel during background fetches instead of showing a popup every time the chat panel loads.
• The popup notification is now reserved for manual refresh only (via the Refresh Models command), so users are still alerted when they explicitly request a refresh.
• Robust stream abort mechanism — abort() now also calls reader.cancel() directly as a fallback. In Electron/Node.js fetch, controller.abort() on an already-received response body sometimes does not propagate to the stream reader, leaving reader.read() stuck forever.
• First-event timeout (90s) — a dedicated timer fires when the server returns 200 OK with text/event-stream but never sends any SSE data. Catches "server accepted but silently stalled" faster than stream-idle timeout.
• Default request timeout reduced 300s → 120s — maximum 2 minutes before a failing request surfaces an error.
• Removed speculative error messages — timeout errors report facts only (duration and phase).
• Smart retry with body pruning on empty-stream timeout — when the server accepts a request but sends no data, the extension automatically retries once with a pruned payload body (keeping ~50% most recent messages + system prompt). Compatible with OpenAI Chat, Anthropic Messages, Google GenerateContent, and Responses API body formats.

Changed

• MAX_RETRIES: 1 → 2 (one for transient connection errors, one for empty-stream with pruned body).

---

Installation

Download xiaomi-mimo-copilot-chat-0.1.3.vsix below, then:

code --install-extension xiaomi-mimo-copilot-chat-0.1.3.vsix

Or via VS Code: Extensions → ⋯ → Install from VSIX...

What's Changed

• release: v0.1.3 — suppress model list error popups, robust stream abort, smart retry by @ltmoerdani in #12

Full Changelog: v0.1.2...v0.1.3

v0.1.2 — Phased timeout, auto-retry, and PR #8 merge

What's New

Phased Timeout Architecture

• 60s connection timeout — fails fast if the MiMo server is unreachable (previously could hang for 10 minutes).
• 5 min overall timeout — reduced from 10 minutes (MiMo is consistently <2s TTFB).
• 90s stream idle timeout — reduced from 2 minutes to detect stalled streams sooner.

Auto-Retry on Transient Errors

• Requests automatically retry once (with 1s backoff) on ECONNRESET, ECONNREFUSED, socket hang up, and other recoverable network errors.

Improved Error Messages

• Timeout errors now indicate whether the failure occurred during the connection or streaming phase, with actionable suggestions.

Incorporates v0.1.1 Fixes

• Corrected MiMo model IDs to lowercase (mimo-v2.5, mimo-v2.5-pro).
• SecretStorage API key fallback.
• xiaomi-mimo.debugLogging setting for verbose logs.
• Model filter to exclude TTS/voice variants.

Other Changes

• Extension renamed to Xiaomi MiMo GitHub Copilot Chat.
• Default requestTimeoutSeconds: 600 → 300 (minimum raised to 30s).
• Default streamIdleTimeoutSeconds: 120 → 90 (minimum raised to 10s).

Contributors

• @jonach1998 — PR #8

Full Changelog: v0.1.1...v0.1.2

v0.1.1 — Fix MiMo model registration and quiet routine logs

What's Fixed

• Corrected MiMo model IDs to Xiaomi's lowercase API identifiers (mimo-v2.5, mimo-v2.5-pro) — the previous PascalCase IDs were rejected by Xiaomi's API.
• Filtered live model list to chat-capable MiMo models only, excluding TTS/voice variants.
• SecretStorage API key fallback — the extension now reuses the stored API key when VS Code does not pass provider configuration into model discovery or chat requests.
• Quieted routine logs — verbose request/model metadata output is now gated behind the xiaomi-mimo.debugLogging setting (off by default).
• Eager activation — added "*" to activationEvents so the provider registers early after VS Code starts.

New Setting

Setting	Type	Default	Description
xiaomi-mimo.debugLogging	boolean	false	Write verbose transport and model registration diagnostics to the MiMo output channel

Contributors

Thanks to our first community contributor 🎉

• @jonach1998 — PR #8

Full Changelog: v0.1.0...v0.1.1

v0.1.0 - Initial Release

Xiaomi MiMo Copilot Chat — Initial Release

First release of the Xiaomi MiMo GitHub Copilot Chat extension for VS Code.

Added

• Forked from opencode-copilot-chat and adapted for Xiaomi MiMo AI models.
• MiMo provider registration with Xiaomi API endpoint (https://token-plan-sgp.xiaomimimo.com/v1).
• Simplified transport layer — all models route through OpenAI-compatible /chat/completions.
• Updated bundled model catalog to MiMo models only: mimo-v2.5 and mimo-v2.5-pro.
• Updated all VS Code settings to xiaomi-mimo.* prefix.
• Updated all commands to MiMo:*.

Full Changelog: https://github.com/ltmoerdani/xiaomi-mimo-copilot-chat/commits/v0.1.0

Full Changelog: https://github.com/ltmoerdani/xiaomi-mimo-copilot-chat/commits/v0.1.0