@elvatis_com/openclaw-cli-bridge-elvatis 1.5.1 → 1.6.2

package/CONTRIBUTING.md

@@ -0,0 +1,93 @@
+# Contributing & Release Checklist
+
+## 🚨 Pflicht-Workflow vor jedem Release
+
+**Kein Publish ohne erfolgreichen `/bridge-status` Test!**
+
+### 1. Build
+
+```bash
+npm run build
+# Exit 0 erwartet — TS-Fehler sind ok (--noEmitOnError false), aber Exit != 0 blockiert
+```
+
+### 2. Gateway neu starten
+
+```bash
+openclaw gateway restart
+# oder via Chat: gateway restart
+```
+
+### 3. Smoke Tests (alle müssen grün sein)
+
+```
+/bridge-status     → Grok ✅ + Gemini ✅ (beide connected, nicht "not connected")
+/cli-test          → CLI bridge OK, Latency < 10s
+/grok-status       → valid (Cookie-Expiry prüfen)
+/gemini-status     → valid (Cookie-Expiry prüfen)
+```
+
+**Erst wenn alle Tests grün sind → publishen!**
+
+### 4. Publish (Reihenfolge einhalten)
+
+```bash
+# 1. Version bump in package.json + openclaw.plugin.json (beide!)
+# 2. Git commit + tag
+git add package.json openclaw.plugin.json
+git commit -m "chore: bump to vX.Y.Z — <kurze Beschreibung>"
+git tag vX.Y.Z
+git push origin main vX.Y.Z
+
+# 3. GitHub Release erstellen (Tag ≠ Release!)
+gh release create vX.Y.Z --title "vX.Y.Z — <Titel>" --notes "<Notes>" --latest
+
+# 4. npm publish
+npm publish --access public
+
+# 5. ClawHub publish (aus tmp-Dir, nicht direkt aus Repo)
+TMPDIR=$(mktemp -d)
+rsync -a --exclude='node_modules' --exclude='.git' --exclude='dist' \
+  --exclude='package-lock.json' --exclude='test' ./ "$TMPDIR/"
+clawhub publish "$TMPDIR" --slug openclaw-cli-bridge-elvatis --version X.Y.Z \
+  --tags "latest" --changelog "<Changelog>"
+```
+
+> ⚠️ **ClawHub Bug (CLI v0.7.0):** `acceptLicenseTerms: invalid value` — Workaround: `publish.js` vor dem Publish patchen und danach zurücksetzen. Details in AGENTS.md / MEMORY.md des Workspaces.
+
+---
+
+## Versionsstellen — alle prüfen vor Release
+
+```bash
+grep -rn "X\.Y\.Z\|version" \
+  --include="*.md" --include="*.json" \
+  --exclude-dir=node_modules --exclude-dir=dist --exclude-dir=.git \
+  | grep -i "version"
+```
+
+Typische Stellen:
+- `package.json` → `"version": "..."`
+- `openclaw.plugin.json` → `"version": "..."`
+- `README.md` → `**Current version:** ...` (falls vorhanden)
+
+---
+
+## Breaking Changes
+
+Bei Breaking Changes (Major oder entfernte Commands):
+- Version-Bump auf nächste **Minor** (z.B. 1.4.x → 1.5.0)
+- GitHub Release Notes: `## ⚠️ Breaking Change` Sektion
+- README Changelog: Was wurde entfernt + warum
+- `/bridge-status` muss die entfernten Provider NICHT mehr zeigen
+
+---
+
+## TS-Build-Fehler
+
+Die folgenden TS-Fehler sind bekannt und ignorierbar (kein Runtime-Problem):
+- `TS2307: Cannot find module 'openclaw/plugin-sdk'` — Typ-Deklarationen fehlen in npm-Paket
+- `TS2339: Property 'handler' does not exist on type 'unknown'` — folgt aus TS2307
+- `TS7006: Parameter implicitly has 'any' type` — minor, kein Effekt
+
+Build läuft mit `--noEmitOnError false` durch. `npm run build` → Exit 0 ist das Kriterium, nicht null TS-Fehler.

package/README.md

@@ -2,7 +2,7 @@
 
 > OpenClaw plugin that bridges locally installed AI CLIs (Codex, Gemini, Claude Code) as model providers — with slash commands for instant model switching, restore, health testing, and model listing.
 
-**Current version:** `1.5.0`
+**Current version:** `1.6.2`
 
 ---
 
@@ -115,11 +115,42 @@ Routes requests through real browser sessions on the provider's web UI. Requires
 | `/gemini-status` | Show session validity + cookie expiry |
 | `/gemini-logout` | Clear session |
 
+**Claude.ai** (claude.ai — Pro/Team subscription):
+
+| Model | Notes |
+|---|---|
+| `web-claude/claude-sonnet` | Claude Sonnet (web) |
+| `web-claude/claude-opus` | Claude Opus (web) |
+| `web-claude/claude-haiku` | Claude Haiku (web) |
+
+| Command | What it does |
+|---|---|
+| `/claude-login` | Authenticate, save cookies to `~/.openclaw/claude-profile/` |
+| `/claude-status` | Show session validity + cookie expiry |
+| `/claude-logout` | Clear session |
+
+**ChatGPT** (chatgpt.com — Plus/Pro subscription):
+
+| Model | Notes |
+|---|---|
+| `web-chatgpt/gpt-4o` | GPT-4o |
+| `web-chatgpt/gpt-4o-mini` | GPT-4o Mini |
+| `web-chatgpt/gpt-o3` | GPT o3 |
+| `web-chatgpt/gpt-o4-mini` | GPT o4-mini |
+| `web-chatgpt/gpt-5` | GPT-5 |
+
+| Command | What it does |
+|---|---|
+| `/chatgpt-login` | Authenticate, save cookies to `~/.openclaw/chatgpt-profile/` |
+| `/chatgpt-status` | Show session validity + cookie expiry |
+| `/chatgpt-logout` | Clear session |
+
 **Session lifecycle:**
-- First use: run `/xxx-login` once - authenticates and saves cookies to persistent Chromium profile
+- First use: run `/xxx-login` once — authenticates and saves cookies to persistent Chromium profile
 - **No CDP required:** `/xxx-login` no longer depends on the OpenClaw browser (CDP port 18800). If CDP is available, cookies are imported from it; otherwise a standalone persistent Chromium is launched automatically.
+- If headless login fails, a **headed browser** opens for manual login (5 min timeout)
 - After gateway restart: sessions are **automatically restored** from saved profiles on startup (sequential, ~25s after start)
-- `/bridge-status` — shows all providers at a glance with login state + expiry info
+- `/bridge-status` — shows all 4 providers at a glance with login state + expiry info
 
 ---
 
@@ -329,6 +360,22 @@ npm test            # vitest run (83 tests)
 
 ## Changelog
 
+### v1.6.2
+- **docs:** Add missing changelog entries (v1.5.1, v1.6.0, v1.6.1), fix /cli-codex54 command name in SKILL.md, add startup re-login alert description to SKILL.md.
+
+### v1.6.1
+- **feat:** WhatsApp re-login alerts on startup. After each gateway restart, the session restore loop collects any providers that failed to restore (cookies expired) and sends a single batched WhatsApp notification with the exact `/xxx-login` commands needed. No credential storage — remains fully 2FA-safe.
+
+### v1.6.0
+- **feat:** Persistent Chromium profiles for all 4 web providers (Grok, Gemini, Claude.ai, ChatGPT). Browser sessions now survive gateway restarts — cookies are stored in `~/.openclaw/{grok,gemini,claude,chatgpt}-profile/` and restored automatically on startup.
+- **feat:** Re-added `/claude-login`, `/claude-status`, `/claude-logout`, `/chatgpt-login`, `/chatgpt-status`, `/chatgpt-logout` commands with full persistent profile support.
+- **feat:** `/bridge-status` now shows all 4 providers with session state and cookie expiry at a glance.
+- **fix:** Startup restore guard (`_startupRestoreDone`) prevents duplicate browser launches on hot-reloads (SIGUSR1).
+
+### v1.5.1
+- **fix:** Hardcoded plugin version `1.3.1` in plugin object updated to `1.5.1`.
+- **docs:** Added `CONTRIBUTING.md` with release checklist and smoketest workflow.
+
 ### v1.5.0
 - **refactor:** Removed `/claude-login`, `/claude-logout`, `/claude-status`, `/chatgpt-login`, `/chatgpt-logout`, `/chatgpt-status` commands and all related browser automation code. Claude is fully covered by `cli-claude/*` via CLI proxy, ChatGPT by `openai-codex` + `copilot-proxy`.
 - **refactor:** Removed `web-claude/*` and `web-chatgpt/*` proxy routes and model entries from proxy server.

package/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: openclaw-cli-bridge-elvatis
-description: Bridge local Codex, Gemini, and Claude Code CLIs into OpenClaw as vllm model providers. Includes /cli-* slash commands for instant model switching (/cli-sonnet, /cli-opus, /cli-haiku, /cli-gemini, /cli-gemini-flash, /cli-gemini3). E2BIG-safe spawn via minimal env.
+description: Bridge local AI CLIs + web browser sessions (Grok, Gemini, Claude.ai, ChatGPT) into OpenClaw as model providers. Includes /cli-* slash commands for instant model switching and persistent browser profiles for all 4 web providers.
 homepage: https://github.com/elvatis/openclaw-cli-bridge-elvatis
 metadata:
   {
@@ -15,7 +15,7 @@ metadata:
 
 # OpenClaw CLI Bridge
 
-Bridges locally installed AI CLIs (Codex, Gemini, Claude Code) as OpenClaw model providers. Three phases:
+Bridges locally installed AI CLIs + web browser sessions into OpenClaw as model providers. Four phases:
 
 ## Phase 1 — Codex Auth Bridge
 Registers `openai-codex` provider from existing `~/.codex/auth.json` tokens. No re-login.
@@ -39,11 +39,22 @@ Six instant model-switch commands (authorized senders only):
 | `/cli-gemini-flash` | `vllm/cli-gemini/gemini-2.5-flash` |
 | `/cli-gemini3` | `vllm/cli-gemini/gemini-3-pro` |
 | `/cli-codex` | `openai-codex/gpt-5.3-codex` |
-| `/cli-codex-mini` | `openai-codex/gpt-5.1-codex-mini` |
+| `/cli-codex54` | `openai-codex/gpt-5.4` |
 | `/cli-back` | Restore previous model |
 | `/cli-test [model]` | Health check (no model switch) |
 
-Each command runs `openclaw models set <model>` atomically and replies with a confirmation.
+Each command uses staged switching by default (apply with `/cli-apply`).
+
+## Phase 4 — Web Browser Providers
+Persistent Chromium profiles for 4 web providers (no API key needed):
+- **Grok** (`web-grok/*`): `/grok-login`, `/grok-status`, `/grok-logout`
+- **Gemini** (`web-gemini/*`): `/gemini-login`, `/gemini-status`, `/gemini-logout`
+- **Claude.ai** (`web-claude/*`): `/claude-login`, `/claude-status`, `/claude-logout`
+- **ChatGPT** (`web-chatgpt/*`): `/chatgpt-login`, `/chatgpt-status`, `/chatgpt-logout`
+
+Sessions survive gateway restarts. `/bridge-status` shows all 4 at a glance.
+
+On gateway restart, if any session has expired, a **WhatsApp alert** is sent automatically with the exact `/xxx-login` commands needed — no guessing required.
 
 ## Setup
 
@@ -53,4 +64,4 @@ Each command runs `openclaw models set <model>` atomically and replies with a co
 
 See `README.md` for full configuration reference and architecture diagram.
 
-**Version:** 1.3.1
+**Version:** 1.6.2