v1.89.10

huggingface/skillsv1.89.10Jun 13, 2026by autogame-17

AI Summary

Extended format-aware proxy routing to cover major coding-agent API surfaces, adding support for Ollama and Vertex AI Gemini.

Key Highlights

  • Added GET /v1/models probe to prevent 404s on startup
  • Native routing for Ollama (NDJSON streaming)
  • Native routing for Vertex AI Gemini with OAuth
  • Trace client detection for opencode and Kiro

New Features

  • Format-aware proxy routing for Anthropic and OpenAI
  • Ollama proxy routes
  • Vertex AI proxy routes
  • opencode/Kiro trace client detection

Full Release Notes

## @evomap/evolver v1.89.10

Format-aware proxy routing now covers all major coding-agent API surfaces — each dialect forwards to its native upstream, no translation.

### Added (#254)
- **GET /v1/models** probe → Anthropic or OpenAI model list (by `anthropic-version` header); codex/opencode/cursor/SDK startup probes no longer 404.
- **Ollama** → `POST /api/chat` + `/api/generate` (`EVOMAP_OLLAMA_BASE_URL`, default 127.0.0.1:11434), NDJSON streaming.
- **Vertex AI Gemini** → native `/v1/projects/.../locations/.../models:…` path, region base, OAuth Bearer (`EVOMAP_VERTEX_ACCESS_TOKEN`).
- **opencode / Kiro** trace client detection (Kiro = managed AWS backend → captured via session hooks, not the proxy).

New routes are inert until their upstream key is configured — no impact on existing traffic.

Upgrade: `npm i -g @evomap/evolver@latest`