Qoder2Api v1.2.0 - Session Recovery and Observability

QODER2API v1.2.0 - Session Recovery and Observability

Automatic session recovery, configurable logging, and dashboard sync improvements.

🚀 What's New

• Session recovery on 105 — auto-rebuilds COSY session on "Login expired", marks account for 24h only on failure, no unnecessary failover
• Configurable logging — QODER_LOG_LEVEL (info/debug), debug-only verbose logs, PAT masking in operational logs
• Dashboard sync — automatic PAT switches now reflected in dashboard (Active PAT / badge / Usage)

📥 Downloads

Main API Server

Platform	Download	Size
Windows x64	qoder2api-windows-amd64.exe	~7.2 MB
Linux x64	qoder2api-linux-amd64	~7.0 MB
macOS Intel	qoder2api-macos-amd64	~7.1 MB
macOS Apple Silicon	qoder2api-macos-arm64	~6.6 MB

🚀 Quick Start

# Download and run
./qoder2api-*

# Dashboard: http://localhost:8963
# API: http://localhost:8963/v1

🔧 Configuration

QODER_LOG_LEVEL=info  # or debug for verbose logs

📝 Changelog

Full Changelog: v1.1.0...v1.2.0

Key Changes

Session Recovery:

• Error 105 (Login expired) → auto-rebuild COSY session via ExchangeJobToken
• Retry on same account before failover
• 24h cooldown only on rebuild failure

Logging:

• QODER_LOG_LEVEL env var (default: info)
• Debug logs: [DEBUG], [BEARER DEBUG], [CALL DEBUG], stream line-by-line
• PAT masking in [bridge] and [stream] logs

Dashboard:

• Auto-failover updates Active PAT display
• Badge and Usage reflect actual working account

---

📖 Documentation

• README: English | усский
• Repository: https://github.com/D3-vin/Qoder2Api

📱 Contact

• Telegram: @D3_vin
• Author: @D3vin_dev

Qoder2Api v1.1.0 - Enhanced Reliability and Transparency

QODER2API v1.1.0 - Enhanced Reliability and Transparency

Significant improvements to stream reliability, response accuracy, and observability.

🚀 What's New

• Reliable stream termination — proper detection of stream end vs connection drop; no more masked aborts
• Honest finish reasons — length no longer misreported as stop; Anthropic max_tokens correctly set
• Real usage metrics — actual token counts (prompt/completion/reasoning/cached) and credits instead of zeros
• Reasoning transparency — model's thinking now visible: reasoning_content in OpenAI format, thinking blocks in Anthropic format
• Single-binary release — templates and .env.example embedded via go:embed, auto-extracted on first run; GitHub release works out of the box
• 5-minute idle timeout — long generations no longer killed, only truly stalled connections

📥 Downloads

Main API Server

Platform	Download	Size
Windows x64	qoder2api-windows-amd64.exe	~7.2 MB
Linux x64	qoder2api-linux-amd64	~7.0 MB
macOS Intel	qoder2api-macos-amd64	~7.1 MB
macOS Apple Silicon	qoder2api-macos-arm64	~6.6 MB

🚀 Quick Start

# Download and run
./qoder2api-*

# Dashboard: http://localhost:8963
# API: http://localhost:8963/v1

🔧 IDE Configuration

Base URL: http://localhost:8963/v1
API Key: any non-empty string (configured in .env)
Model: qwen3.8-max (or any real Qoder model name)

Model names are passed through to Qoder — clients configure real Qoder model names directly.

📝 Changelog

Full Changelog: v1.0.0...v1.1.0

Key Changes

Stream Reliability:

• Proper terminator detection ([DONE] envelope, event:finish, event:error)
• EOF without terminator now returns error instead of success
• Idle timeout increased to 5 minutes for long generations

Response Accuracy:

• Real finish_reason from upstream (no more length → stop conversion)
• Anthropic: stop_reason: max_tokens when appropriate
• Actual token usage: prompt/completion/reasoning/cached tokens + credits
• Include usage in streaming responses (OpenAI convention)

Reasoning Visibility:

• OpenAI: delta.reasoning_content in stream, message.reasoning_content in non-stream
• Anthropic: thinking content blocks (extended thinking spec)

Distribution:

• Templates embedded via go:embed, auto-extracted on first run
• Single binary works out of the box from GitHub releases

---

📖 Documentation

• README: English | Русский
• Repository: https://github.com/D3-vin/Qoder2Api

📱 Contact

• Telegram: @D3_vin
• Author: @D3vin_dev

Qoder2Api v1.0.0 - Initial Release

QODER2API v1.0.0 - Initial Release

OpenAI & Anthropic-compatible gateway for Qoder IDE accounts — single Go binary with an account pool.

🚀 What's New

• OpenAI-compatible API — /v1/chat/completions, /v1/models, /v1/usage; drop-in for any OpenAI-format client
• Anthropic-compatible API — /v1/messages for Claude Code and other Anthropic-format clients
• Account pool with failover — multiple PATs, automatic switch to the next account on agent-limit errors (code 115)
• Embedded dashboard — live HTML UI: accounts, quotas, default model, context/thinking settings, persisted to config.json

📥 Downloads

Main API Server

Platform	Download	Size
Windows x64	qoder2api-windows-amd64.exe	~7.1 MB
Linux x64	qoder2api-linux-amd64	~6.9 MB
macOS Intel	qoder2api-macos-amd64	~7.0 MB
macOS Apple Silicon	qoder2api-macos-arm64	~6.5 MB

🚀 Quick Start

# Download and run
./qoder2api-*

# Dashboard: http://localhost:8963
# API: http://localhost:8963/v1

🔧 IDE Configuration

Base URL: http://localhost:8963/v1
API Key: any non-empty string (configured in .env)
Model: qwen3.8-max (or any real Qoder model name)

Model names are passed through to Qoder — clients configure real Qoder model names directly.

📝 Changelog

Initial public release.

---

📖 Documentation

• README: English | Русский
• Repository: https://github.com/D3-vin/Qoder2Api

📱 Contact

• Telegram: @D3_vin
• Author: @D3vin_dev