tombii/better-ccflare v3.5.51

Stable Release v3.5.51

on GitHub

🎉 Stable Release v3.5.51

Multi-Architecture Binaries

Download the appropriate binary for your platform:

• Linux x86_64: better-ccflare-linux-amd64
• Linux ARM64 (Raspberry Pi 3/4/5, Oracle Cloud ARM, AWS Graviton): better-ccflare-linux-arm64
• macOS Intel: better-ccflare-macos-x86_64
• macOS Apple Silicon: better-ccflare-macos-arm64
• Windows x86_64: better-ccflare-windows-x64.exe

Installation

# Linux x86_64
wget https://github.com/tombii/better-ccflare/releases/download/v3.5.51/better-ccflare-linux-amd64
chmod +x better-ccflare-linux-amd64
./better-ccflare-linux-amd64

# macOS Apple Silicon (ARM64)
curl -L -o better-ccflare-macos-arm64 https://github.com/tombii/better-ccflare/releases/download/v3.5.51/better-ccflare-macos-arm64
chmod +x better-ccflare-macos-arm64
xattr -d com.apple.quarantine better-ccflare-macos-arm64  # Required for unsigned binaries
./better-ccflare-macos-arm64

macOS Users: The xattr command is required to bypass Gatekeeper for unsigned binaries. If you prefer not to run unsigned binaries, install from source instead.

Or install via npm: npm install -g better-ccflare@v3.5.51

What's Changed

🚀 Features

• feat(models): list provider-specific models for the model pickers (1564c254)
• feat(providers): opt-in xAI cache-native conversation identity with sticky account affinity (2facef9b)
• feat(http-api): per-session serving-account endpoint for status-line integrations (PR #396) (58668ff2)
• feat(providers): derive the codex default model map from the account's own listing (5dae4294)
• feat(config): make provider default model maps editable (619fe271)
• feat(http-api): per-session serving-account endpoint for status-line integrations (8f414e1d)
• feat(models): list provider-specific models for the model pickers (PR #399) (a18d388b)
• feat(proxy): allow a combo slot to forward the client's own model (d7126f71)
• feat(providers): opt-in xAI cache-native conversation identity with sticky account affinity (PR #398) (dc7ca2a0)

🐛 Bug Fixes

• fix(http-api): break millisecond timestamp ties by insertion order in session-account lookup (16d327ff)
• fix: stop benching accounts whose extra_usage credits are spent (25afe55f)
• fix(providers): add the fable family to the codex and qwen default model maps (2d09b5f6)
• fix(types): break the types↔core module cycle via core leaf-module subpath imports (3a558324)
• fix(dashboard): remove unused imports flagged by lint (PR #399) (5adf48e5)
• fix: list the override fields even when nothing has been discovered (69bf8621)
• fix: keep the manual override reachable, and never cache an empty listing (6d1af610)
• fix: label the account by what gates it, not by the overage pool (6fce53c0)
• fix(proxy): strip client-supplied x-grok-conv-id and record xAI affinity only on confirmed success (PR #398) [skip-version] (8382c10e)
• fix(http-api): support PostgreSQL in session-account tiebreaker (PR #396) (8f2e1d42)
• fix(proxy): clear derived provider-model-defaults registry between codex-model-catalog tests (a1429cf1)
• fix(providers): add the fable family to the codex and qwen default model maps (PR #394) (ec1256ae)

Full Changelog

📋 Compare with previous version