@jacobbd/relay-ai 0.2.6 → 0.2.7

package/CHANGELOG.md

@@ -1,20 +1,17 @@
 # Changelog
 
-## [0.2.6] - 2026-06-18 (Official Launch Release)
+## [0.2.7] - 2026-06-19 (Official Launch Release)
 
 ### Added
 - **Native provider registry** — Add, list, remove, refresh, and import providers with secure OS credential storage and templates for OpenRouter, Groq, Mistral, Together AI, Zen/Go, and SDK-backed custom endpoints.
-- **Claude Code and Codex launchers** — Launch registry models through `relay-ai`, including provider/model boot flags, local OpenCode provider discovery, recent models, search, pagination, and favorites catalogs for mid-session switching.
+- **Claude Code launcher** — Launch registry models through `relay-ai claude`, including provider/model boot flags, local OpenCode provider discovery, recent models, search, pagination, and favorites catalogs for mid-session switching.
+- **Codex CLI launcher** — Launch the Codex terminal with registry providers via `relay-ai codex`.
+- **Codex App launcher** — Launch the Codex desktop app with registry providers via `relay-ai codex-app`. Preserves existing conversation history by keeping Codex's built-in OpenAI provider identity; routes the selected model through a foreground local Responses proxy. Supports `--trace` for proxy debug logging.
 - **Unified SDK gateway** — Route non-Anthropic providers through the Vercel AI SDK adapter while preserving Anthropic-compatible tool use, streaming, context windows, and model catalogs.
-- **Codex App integration** — Launch the desktop app with registry providers and restore Codex App model settings after interrupted sessions.
 - **Claude Desktop integration** — Launch Claude Desktop in third-party provider mode with automatic configuration backup and restore.
-- **Reasoning capability metadata** — Resolve reasoning controls from provider metadata, including OpenRouter `supported_parameters`, so models such as GLM 5.2 receive compatible reasoning options instead of stale defaults.
 - **Foreground server gateway** — Run `relay-ai server` for Claude Desktop or LAN usage, with registry-backed routing, password protection, and optional Vertex AI support.
+- **Reasoning capability metadata** — Resolve reasoning controls from provider metadata, including OpenRouter `supported_parameters`, so models receive compatible reasoning options.
+- **Favorites catalogs** — Save up to 20 models and switch mid-session in Claude Code (`/model`) and Codex.
 - **First-run setup** — Configure providers from an inline wizard or import existing OpenCode provider settings.
-- **Complete command help** — Document every top-level command and managed option, including `codex-app`, `claude-app`, Vertex, restore, config, trace, and agent-reference flags.
-
-### Fixed
-- **Unified OpenCode cloud setup** — Configure OpenCode Zen / Go once with their shared API key while preserving separate internal routes for overlapping model IDs and distinct upstream endpoints.
-- **Duplicate OpenCode providers** — Map OpenCode CLI IDs to Relay IDs, compare existing configurations during import, and automatically migrate or remove legacy `opencode` / `opencode-go` registry duplicates.
-- **Stable model refreshes** — Refresh imported providers sequentially against one shared registry so provider caches cannot overwrite each other.
-- **Accurate refresh reporting** — Treat imported catalogs as snapshots rather than live-refresh baselines, preventing misleading first-refresh model-count deltas.
+- **Complete command help** — Every top-level command fully documented, including `codex-app`, `claude-app`, Vertex, restore, config, trace, and agent-reference flags.
+- **Agent / headless launch** — Boot flags (`--provider`, `--model`), clean NDJSON/JSONL stdout, and `relay-ai --ai` reference for scripts and alef-agent.

package/README.md

@@ -353,7 +353,7 @@ Launch the **Codex app** (macOS or Windows) with registry providers:
 relay-ai codex-app
 ```
 
-Patches `~/.codex/config.toml` with backup; **Ctrl+C** in the relay-ai terminal restores your config. Tier 2 (Anthropic, etc.) requires keeping that terminal open. Preview config without writing: `relay-ai codex-app --config`. Recovery: `relay-ai codex-app --restore`.
+Patches `~/.codex/config.toml` with backup; **Ctrl+C** in the relay-ai terminal restores your config. The app keeps Codex's built-in `openai` provider active so existing conversation history remains visible, and routes the selected model through a foreground local proxy. Preview config without writing: `relay-ai codex-app --config`. Recovery: `relay-ai codex-app --restore`.
 
 See **[docs/CODEX.md](docs/CODEX.md)** for CLI vs app differences, file ownership, and troubleshooting.