@jacobbd/relay-ai 0.2.8 → 0.3.1

package/AGENTS.md

@@ -1,6 +1,6 @@
 # AGENTS.md
 
-This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.
+This file provides guidance to Codex (Codex.ai/code) when working with code in this repository. Note that the codebase supports Claude Code, OpenAI Codex, and Google Gemini CLI.
 
 ## Commands
 
@@ -24,6 +24,7 @@ relay-ai server           # foreground OpenCode/registry API gateway
 relay-ai server --vertex  # foreground Vertex AI gateway (gcloud ADC)
 relay-ai codex            # Codex CLI with registry providers (see docs/CODEX.md)
 relay-ai codex-app        # Codex desktop app (macOS/Windows; see docs/CODEX.md)
+relay-ai gemini           # Gemini CLI with registry providers (see docs/GEMINI.md)
 
 # Rebuild after code changes before testing manually
 npm run build && relay-ai --version
@@ -150,9 +151,9 @@ In all cases `process.env['OPENCODE_API_KEY']` is set immediately so the key is
 - `--restore` globs `models-*.json` (CLI) and `app-models-*.json` (App); the new files are `models-favorites.json` and `app-models-favorites.json`.
 - Zen/Go favorites are skipped in Codex (use Claude or Desktop gateway).
 
-## Release status (v0.2.6)
+## Release status (v0.3.0)
 
-Current version is **v0.2.6** — official launch release with the native provider registry, complete Claude/Codex app help, unified OpenCode Zen / Go setup, duplicate-provider migration, stable post-import refreshes, agent boot flags (`--provider` / `--model`), `relay-ai --ai`, favorites catalogs, and reasoning capability metadata.
+Current version is **v0.3.0** — official launch release with the native provider registry, complete Claude/Codex app help, unified OpenCode Zen / Go setup, duplicate-provider migration, stable post-import refreshes, agent boot flags (`--provider` / `--model`), `relay-ai --ai`, favorites catalogs, reasoning capability metadata, and new native Chinese provider templates (DeepSeek, Zhipu, Moonshot) with improved models endpoint routing.
 
 **Known limitations (by design):**
 - Cost display in Codex is always inaccurate for non-Anthropic models.

package/CHANGELOG.md

@@ -1,5 +1,26 @@
 # Changelog
 
+## [0.3.1] - 2026-06-22
+
+### Fixed
+
+- **Codex App: background GPT model requests no longer crash your session** — The Codex desktop app has an internal agent subsystem that sends background requests using hardcoded model IDs (`gpt-5.4`, `gpt-5.4-mini`, `gpt-5.5`), even when you've configured a completely different model like GLM or DeepSeek. These requests were hitting the relay-ai proxy and getting 404 errors, which interrupted your chat session and showed up as confusing error states in the UI. The proxy now silently routes those background requests to your configured starting model instead. Your session keeps running. (Fixes [#8](https://github.com/jacob-bd/relay-ai/issues/8))
+
+- **Codex App: `GET /v1/responses` polling no longer returns 404** — Codex polls this endpoint in the background for session state. The proxy only handled `POST /v1/responses` before, so every poll got a 404. Now it returns an empty list, which is all Codex actually needs.
+
+- **`--trace` output was a false negative** — `relay-ai codex-app --trace` would print `(no errors found in debug log)` even when the proxy had been silently dropping dozens of model-not-found failures the whole session. Trace output now surfaces `resolveModel failed` and `resolveModel fallback` lines so you can actually see what's happening.
+
+## [0.3.0] - 2026-06-21
+
+*Happy Father's Day!* 👨‍👦
+
+
+### Added
+- **New Native Providers** — Added native provider templates and registry support for DeepSeek (`deepseek`), Zhipu (`zhipu`), and Moonshot (`moonshot`), facilitating direct integration of Chinese LLM providers.
+- **Experimental Gemini Support** — Introduced experimental support for Google Gemini models via a custom SDK adapter and local proxy, enabling `relay-ai gemini`.
+- **Kimi/Moonshot Reasoning Level Selection** — Enabled support for Codex's native "Select Reasoning Level" UI for Kimi models by exposing `supported_reasoning_levels` in the proxy catalog and translating reasoning effort parameters.
+- **Provider Documentation** — Created a dedicated [PROVIDERS.md](file:///Users/jbendavi/dev_projects/relay-ai/docs/PROVIDERS.md) documentation file explaining the differences between Kimi, Kimi Global, and Moonshot models, and linked it from the main README.
+
 ## [0.2.8] - 2026-06-20
 
 ### Added

package/README.md

@@ -17,9 +17,9 @@
   </a>
 </p>
 
-> **Demo (Part 1):** Installation · Configuration · Claude Code · Claude Cowork · Claude Code Desktop — [watch on YouTube](https://youtu.be/IvsUPHLhX0o) *(premieres June 19 at 10:45 AM ET)*
+> **Demo (Part 1):** Installation · Configuration · Claude Code · Claude Cowork · Claude Code Desktop — [watch on YouTube](https://youtu.be/IvsUPHLhX0o)
 
-**relay-ai** is an interactive CLI that launches AI coding tools and runs local API gateways on your machine. Currently, it supports **Claude Code**, **Claude Desktop (Cowork + Code)**, the **OpenAI Codex CLI**, and the **Codex desktop app (macOS + Windows)**.
+**relay-ai** is an interactive CLI that launches AI coding tools and runs local API gateways on your machine. Currently, it supports **Claude Code**, **Claude Desktop (Cowork + Code)**, the **OpenAI Codex CLI**, the **Codex desktop app (macOS + Windows)**, and the **Google Gemini CLI**.
 
 Pick your backend:
 
@@ -41,13 +41,14 @@ Pick your backend:
 | `relay-ai claude-app` | Launch Claude Desktop app with registry providers ([guide](docs/CLAUDE_DESKTOP_SETUP.md)) |
 | `relay-ai codex` | Launch OpenAI Codex CLI with registry providers ([guide](docs/CODEX.md)) |
 | `relay-ai codex-app` | Launch Codex desktop app with registry providers ([guide](docs/CODEX.md)) |
+| `relay-ai gemini` | Launch Google Gemini CLI with registry providers |
 | `relay-ai --ai` | Full agent reference for scripts and alef-agent ([guide](docs/AI-AGENTS.md)) |
 
 Bare `relay-ai` prints help and migration guidance. Use `relay-ai claude` for the wizard.
 
 ## Features
 
-- **Native provider registry:** `relay-ai providers` stores config in `~/.relay-ai/providers.json` and secrets in the OS keychain — no OpenCode binary required at launch
+- **Native provider registry:** `relay-ai providers` stores config in `~/.relay-ai/providers.json` and secrets in the OS keychain — no OpenCode binary required at launch. See **[docs/PROVIDERS.md](docs/PROVIDERS.md)** for a full list of providers and known issues.
 - **Provider templates:** Add Groq, Mistral, Together, OpenRouter, and 15+ SDK-backed providers, plus custom OpenAI/Anthropic-compatible endpoints
 - **OpenCode import:** One-time migration from OpenCode (`providers import`); validates API keys and skips placeholders like `anything`
 - **OpenCode Zen / Go:** Optional cloud backends when you have an OpenCode API key
@@ -69,7 +70,7 @@ Bare `relay-ai` prints help and migration guidance. Use `relay-ai claude` for th
 
 | Tool | Command | Status |
 |------|---------|--------|
-| Provider registry | `relay-ai providers` | ✅ Supported |
+| Provider registry | `relay-ai providers` | ✅ Supported ([guide](docs/PROVIDERS.md)) |
 | Claude Code | `relay-ai claude` | ✅ Supported |
 | Favorite models | `relay-ai models` | ✅ Supported |
 | OpenCode API server | `relay-ai server` | ✅ Supported |
@@ -77,11 +78,12 @@ Bare `relay-ai` prints help and migration guidance. Use `relay-ai claude` for th
 | Claude Desktop (Cowork + Code) | `relay-ai claude-app` | ✅ Supported macOS + Windows ([guide](docs/CLAUDE_DESKTOP_SETUP.md)) |
 | Codex CLI | `relay-ai codex` | ✅ Supported ([guide](docs/CODEX.md)) |
 | Codex desktop app | `relay-ai codex-app` | ✅ Supported macOS + Windows ([guide](docs/CODEX.md)) |
+| Google Gemini CLI | `relay-ai gemini` | ✅ Supported |
 
 ## Prerequisites
 
 - Node.js 18+
-- A supported AI coding tool installed (e.g. [Claude Code](https://www.npmjs.com/package/@anthropic-ai/claude-code) or [OpenAI Codex](https://www.npmjs.com/package/@openai/codex))
+- A supported AI coding tool installed (e.g. [Claude Code](https://www.npmjs.com/package/@anthropic-ai/claude-code), [OpenAI Codex](https://www.npmjs.com/package/@openai/codex), or [Google Gemini CLI](https://www.npmjs.com/package/@google/gemini-cli))
 - At least one provider configured via `relay-ai providers add` or `import` — **or** an [OpenCode API key](https://opencode.ai/auth) for Zen/Go cloud backends
 - [OpenCode CLI](https://opencode.ai) only if you want **one-time import** from an existing OpenCode setup (optional)
 - For **Vertex gateway:** [Google Cloud SDK](https://cloud.google.com/sdk) with `gcloud auth application-default login`, a GCP project with Vertex AI enabled, and Claude partner models enabled in that project
@@ -367,6 +369,22 @@ See **[docs/CODEX.md](docs/CODEX.md)** for CLI vs app differences, file ownershi
 
 **Reasoning effort:** Capable models show Codex's native reasoning picker (low/medium/high, etc.). relay-ai maps your choice to each provider's SDK options and preserves existing `model_reasoning_effort` in Codex config. Claude Code `/effort` and the `relay-ai server` gateway use the same mapping — see the [reasoning section in docs/CODEX.md](docs/CODEX.md#reasoning-effort).
 
+### Google Gemini CLI (`relay-ai gemini`)
+
+Launch the [Google Gemini CLI](https://www.npmjs.com/package/@google/gemini-cli) with registry providers.
+
+```bash
+relay-ai gemini
+```
+
+Pick provider → pick model → Gemini prompt loop opens. Non-interactive tasks with streaming NDJSON are also fully supported:
+
+```bash
+relay-ai gemini --provider google --model gemini-2.5-flash -p "Review this file" -o stream-json
+```
+
+For agent / alef-agent integration (boot flags, NDJSON): **[docs/AI-AGENTS.md](docs/AI-AGENTS.md)** and `relay-ai --ai`.
+
 ## How it works
 
 ### OpenCode Zen / Go filtering