cliara 0.4.2__tar.gz → 0.4.4__tar.gz

cliara-0.4.4/PKG-INFO

@@ -0,0 +1,263 @@
+Metadata-Version: 2.4
+Name: cliara
+Version: 0.4.4
+Summary: An AI-powered shell that understands natural language and macros
+Author: Cliara Contributors
+License: MIT
+Project-URL: Homepage, https://github.com/HreemPandya/cliara-app
+Project-URL: Documentation, https://github.com/HreemPandya/cliara-app#readme
+Project-URL: Repository, https://github.com/HreemPandya/cliara-app
+Project-URL: Issues, https://github.com/HreemPandya/cliara-app/issues
+Keywords: cli,shell,ai,natural-language,macros,automation
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: System :: Shells
+Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: prompt-toolkit>=3.0.0
+Requires-Dist: filelock>=3.12.0
+Requires-Dist: pygments>=2.0.0
+Requires-Dist: rich>=13.0.0
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: thefuzz>=0.20.0
+Requires-Dist: openai>=1.0.0
+Requires-Dist: httpx<0.28,>=0.25
+Requires-Dist: anthropic>=0.8.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: black>=23.0.0; extra == "dev"
+Requires-Dist: flake8>=6.0.0; extra == "dev"
+Provides-Extra: postgres
+Requires-Dist: psycopg2-binary>=2.9.0; extra == "postgres"
+Provides-Extra: all
+Requires-Dist: cliara[postgres]; extra == "all"
+
+# Cliara
+
+**An AI-powered shell that understands natural language and macros.**
+
+[![PyPI version](https://badge.fury.io/py/cliara.svg)](https://pypi.org/project/cliara/)
+[![Python 3.8+](https://img.shields.io/pypi/pyversions/cliara)](https://pypi.org/project/cliara/)
+
+---
+
+## What is Cliara?
+
+Cliara wraps your existing shell (bash, zsh, PowerShell, cmd) and adds:
+
+| Feature | Description |
+|---------|-------------|
+| **Natural language** | `? <query>` — describe what you want, get shell commands |
+| **Cliara Cloud** | Sign in with GitHub, 150 free queries/month, no API key |
+| **Macros** | Create, edit, run reusable command sequences |
+| **Semantic history** | `? find when I fixed the login` — search past commands by meaning |
+| **Smart push** | `push` — auto-commit message, branch detection, one command |
+| **Smart deploy** | `deploy` — auto-detect Vercel, Netlify, Docker, PyPI, and deploy |
+| **Safety checks** | Destructive commands show a diff preview before running |
+| **Fix failed commands** | `? fix` — AI suggests corrections after a command fails |
+
+All your normal commands work unchanged. Cliara is a thin layer on top of your shell.
+
+---
+
+## Installation
+
+### Option 1: pipx (recommended)
+
+Best for CLI tools — installs in an isolated environment and adds to PATH automatically.
+
+```bash
+pip install pipx
+pipx ensurepath   # Add pipx bin to PATH (restart terminal if needed)
+pipx install cliara
+```
+
+### Option 2: pip
+
+```bash
+pip install cliara
+```
+
+If `cliara` isn't recognized, use:
+
+```bash
+python -m cliara.main
+```
+
+### Option 3: From source (development)
+
+```bash
+git clone https://github.com/HreemPandya/cliara-app.git
+cd cliara-app
+pip install -e .
+```
+
+### Optional Dependencies
+
+To enable PostgreSQL support, install with:
+
+```bash
+pip install cliara[postgres]
+```
+
+---
+
+## First Run / Setup
+
+1. **Start Cliara:** `cliara`
+2. **First time?** A browser opens for GitHub login. Authorize once.
+3. **Done.** Your token is saved to `~/.cliara/token.json` and loads automatically on every start.
+
+### Authentication / Cloud Login Flow
+
+- The OAuth login flow opens your browser to sign in with GitHub.
+- Once authenticated, your token is stored at `~/.cliara/token.json`.
+
+### Alternative: Bring Your Own API Key
+
+Prefer Groq, Gemini, Ollama, or OpenAI? Run `setup-llm` inside Cliara to configure. Free options include [Groq](https://console.groq.com) and [Google AI Studio](https://aistudio.google.com).
+
+---
+
+## Usage
+
+### Normal Commands (Pass-Through)
+
+Just type commands as usual - they go straight to your shell:
+
+```bash
+cliara:proj ❯ ls -la
+cliara:proj ❯ cd myproject
+cliara:proj ❯ git status
+cliara:proj ❯ npm install
+```
+
+### Natural Language Commands
+
+Use `?` prefix for natural language:
+
+```bash
+cliara:proj ❯ ? list files in this directory
+cliara:proj ❯ ? kill process on port 3000
+cliara:proj ❯ ? find when I ran the deploy
+cliara:proj ❯ ? fix                    # Fix the last failed command
+```
+
+### Macros
+
+```bash
+cliara:proj ❯ macro add build          # Create a macro
+cliara:proj ❯ build                    # Run it
+cliara:proj ❯ macro save last as test  # Save last command as macro
+```
+
+### Smart Commands
+
+```bash
+cliara:proj ❯ push                     # Smart push (auto-commit message + branch)
+cliara:proj ❯ deploy                   # Smart deploy (auto-detect project type)
+```
+
+### Help
+
+```bash
+cliara:proj ❯ help                     # Full command reference
+```
+
+---
+
+## Database Setup and Migration
+
+If using PostgreSQL as your backend, follow these steps:
+
+1. **Install PostgreSQL** (see [PostgreSQL Setup Guide](docs/POSTGRES_SETUP.md)).
+2. **Create Database and User:**
+
+```bash
+# Connect to PostgreSQL
+psql postgres
+
+# Create database
+CREATE DATABASE cliara;
+
+# Create user
+CREATE USER cliara WITH PASSWORD 'your_password_here';
+
+# Grant privileges
+GRANT ALL PRIVILEGES ON DATABASE cliara TO cliara;
+
+# Exit
+\q
+```
+
+3. **Install Python Dependencies:**
+
+```bash
+pip install psycopg2-binary
+```
+
+4. **Configure Cliara:**
+
+Edit `~/.cliara/config.json`:
+
+```json
+{
+  "storage_backend": "postgres",
+  "postgres": {
+    "host": "localhost",
+    "port": 5432,
+    "database": "cliara",
+    "user": "cliara"
+  }
+}
+```
+
+---
+
+## Required Environment Variables
+
+Copy `.env.example` to `.env` and fill in the values for your chosen provider. Only ONE LLM provider should be active at a time.
+
+```plaintext
+# ── Option A: OpenAI (cloud, requires API key) ────────────────────────────────
+OPENAI_API_KEY=sk-proj-your-key-here
+
+# ── Option B: Anthropic Claude (cloud, requires API key) ─────────────────────
+ANTHROPIC_API_KEY=sk-ant-your-key-here
+
+# ── Option C: Ollama (local, free, no key needed) ────────────────────────────
+OLLAMA_BASE_URL=http://localhost:11434
+```
+
+---
+
+## Documentation
+
+- [Complete Guide](docs/README.md) — Full documentation
+- [Quick Start](docs/QUICKSTART.md) — Get started in 5 minutes
+- [Cliara Cloud Deployment](docs/CLIARA_CLOUD_DEPLOYMENT.md) — Self-host the backend
+- [PostgreSQL Setup](docs/POSTGRES_SETUP.md) — Scalable macro storage
+
+---
+
+## Troubleshooting
+
+| Issue | Solution |
+|-------|----------|
+| `cliara` not recognized | Use `python -m cliara.main` or install with `pipx install cliara` |
+| Connection error | Check network/firewall; try `$env:CLIARA_GATEWAY_URL = "https://cliara-cloud-production.up.railway.app/v1"` |
+| Want BYOK instead | Run `setup-llm` inside Cliara for Groq, Gemini, Ollama, OpenAI |
+
+---
+
+## License
+
+MIT

cliara-0.4.4/README.md

@@ -0,0 +1,221 @@
+# Cliara
+
+**An AI-powered shell that understands natural language and macros.**
+
+[![PyPI version](https://badge.fury.io/py/cliara.svg)](https://pypi.org/project/cliara/)
+[![Python 3.8+](https://img.shields.io/pypi/pyversions/cliara)](https://pypi.org/project/cliara/)
+
+---
+
+## What is Cliara?
+
+Cliara wraps your existing shell (bash, zsh, PowerShell, cmd) and adds:
+
+| Feature | Description |
+|---------|-------------|
+| **Natural language** | `? <query>` — describe what you want, get shell commands |
+| **Cliara Cloud** | Sign in with GitHub, 150 free queries/month, no API key |
+| **Macros** | Create, edit, run reusable command sequences |
+| **Semantic history** | `? find when I fixed the login` — search past commands by meaning |
+| **Smart push** | `push` — auto-commit message, branch detection, one command |
+| **Smart deploy** | `deploy` — auto-detect Vercel, Netlify, Docker, PyPI, and deploy |
+| **Safety checks** | Destructive commands show a diff preview before running |
+| **Fix failed commands** | `? fix` — AI suggests corrections after a command fails |
+
+All your normal commands work unchanged. Cliara is a thin layer on top of your shell.
+
+---
+
+## Installation
+
+### Option 1: pipx (recommended)
+
+Best for CLI tools — installs in an isolated environment and adds to PATH automatically.
+
+```bash
+pip install pipx
+pipx ensurepath   # Add pipx bin to PATH (restart terminal if needed)
+pipx install cliara
+```
+
+### Option 2: pip
+
+```bash
+pip install cliara
+```
+
+If `cliara` isn't recognized, use:
+
+```bash
+python -m cliara.main
+```
+
+### Option 3: From source (development)
+
+```bash
+git clone https://github.com/HreemPandya/cliara-app.git
+cd cliara-app
+pip install -e .
+```
+
+### Optional Dependencies
+
+To enable PostgreSQL support, install with:
+
+```bash
+pip install cliara[postgres]
+```
+
+---
+
+## First Run / Setup
+
+1. **Start Cliara:** `cliara`
+2. **First time?** A browser opens for GitHub login. Authorize once.
+3. **Done.** Your token is saved to `~/.cliara/token.json` and loads automatically on every start.
+
+### Authentication / Cloud Login Flow
+
+- The OAuth login flow opens your browser to sign in with GitHub.
+- Once authenticated, your token is stored at `~/.cliara/token.json`.
+
+### Alternative: Bring Your Own API Key
+
+Prefer Groq, Gemini, Ollama, or OpenAI? Run `setup-llm` inside Cliara to configure. Free options include [Groq](https://console.groq.com) and [Google AI Studio](https://aistudio.google.com).
+
+---
+
+## Usage
+
+### Normal Commands (Pass-Through)
+
+Just type commands as usual - they go straight to your shell:
+
+```bash
+cliara:proj ❯ ls -la
+cliara:proj ❯ cd myproject
+cliara:proj ❯ git status
+cliara:proj ❯ npm install
+```
+
+### Natural Language Commands
+
+Use `?` prefix for natural language:
+
+```bash
+cliara:proj ❯ ? list files in this directory
+cliara:proj ❯ ? kill process on port 3000
+cliara:proj ❯ ? find when I ran the deploy
+cliara:proj ❯ ? fix                    # Fix the last failed command
+```
+
+### Macros
+
+```bash
+cliara:proj ❯ macro add build          # Create a macro
+cliara:proj ❯ build                    # Run it
+cliara:proj ❯ macro save last as test  # Save last command as macro
+```
+
+### Smart Commands
+
+```bash
+cliara:proj ❯ push                     # Smart push (auto-commit message + branch)
+cliara:proj ❯ deploy                   # Smart deploy (auto-detect project type)
+```
+
+### Help
+
+```bash
+cliara:proj ❯ help                     # Full command reference
+```
+
+---
+
+## Database Setup and Migration
+
+If using PostgreSQL as your backend, follow these steps:
+
+1. **Install PostgreSQL** (see [PostgreSQL Setup Guide](docs/POSTGRES_SETUP.md)).
+2. **Create Database and User:**
+
+```bash
+# Connect to PostgreSQL
+psql postgres
+
+# Create database
+CREATE DATABASE cliara;
+
+# Create user
+CREATE USER cliara WITH PASSWORD 'your_password_here';
+
+# Grant privileges
+GRANT ALL PRIVILEGES ON DATABASE cliara TO cliara;
+
+# Exit
+\q
+```
+
+3. **Install Python Dependencies:**
+
+```bash
+pip install psycopg2-binary
+```
+
+4. **Configure Cliara:**
+
+Edit `~/.cliara/config.json`:
+
+```json
+{
+  "storage_backend": "postgres",
+  "postgres": {
+    "host": "localhost",
+    "port": 5432,
+    "database": "cliara",
+    "user": "cliara"
+  }
+}
+```
+
+---
+
+## Required Environment Variables
+
+Copy `.env.example` to `.env` and fill in the values for your chosen provider. Only ONE LLM provider should be active at a time.
+
+```plaintext
+# ── Option A: OpenAI (cloud, requires API key) ────────────────────────────────
+OPENAI_API_KEY=sk-proj-your-key-here
+
+# ── Option B: Anthropic Claude (cloud, requires API key) ─────────────────────
+ANTHROPIC_API_KEY=sk-ant-your-key-here
+
+# ── Option C: Ollama (local, free, no key needed) ────────────────────────────
+OLLAMA_BASE_URL=http://localhost:11434
+```
+
+---
+
+## Documentation
+
+- [Complete Guide](docs/README.md) — Full documentation
+- [Quick Start](docs/QUICKSTART.md) — Get started in 5 minutes
+- [Cliara Cloud Deployment](docs/CLIARA_CLOUD_DEPLOYMENT.md) — Self-host the backend
+- [PostgreSQL Setup](docs/POSTGRES_SETUP.md) — Scalable macro storage
+
+---
+
+## Troubleshooting
+
+| Issue | Solution |
+|-------|----------|
+| `cliara` not recognized | Use `python -m cliara.main` or install with `pipx install cliara` |
+| Connection error | Check network/firewall; try `$env:CLIARA_GATEWAY_URL = "https://cliara-cloud-production.up.railway.app/v1"` |
+| Want BYOK instead | Run `setup-llm` inside Cliara for Groq, Gemini, Ollama, OpenAI |
+
+---
+
+## License
+
+MIT

{cliara-0.4.2 → cliara-0.4.4}/cliara/__init__.py

@@ -8,7 +8,7 @@ A shell wrapper that lets you:
 - Save command history as macros
 """
 
-__version__ = "0.4.2"
+__version__ = "0.4.4"
 __author__ = "Cliara Contributors"
 
 from cliara.shell import CliaraShell

{cliara-0.4.2 → cliara-0.4.4}/cliara/agents/__init__.py

@@ -12,6 +12,9 @@ from cliara.agents import history_summary as _history_summary
 from cliara.agents import history_search as _history_search
 from cliara.agents import commit_and_deploy as _commit_deploy
 from cliara.agents import copilot_explain as _copilot_explain
+from cliara.agents import readme_generator as _readme
+from cliara.agents import session_reflect as _session_reflect
+from cliara.agents import chat_polish as _chat_polish
 
 _PROMPTS_DIR = Path(__file__).resolve().parent / "prompts"
 
@@ -29,8 +32,11 @@ def _build_registry() -> Dict[str, Dict[str, Any]]:
         | _explain.AGENTS
         | _history_summary.AGENTS
         | _history_search.AGENTS
-        | _commit_deploy.AGENTS
+        |         _commit_deploy.AGENTS
         | _copilot_explain.AGENTS
+        | _readme.AGENTS
+        | _session_reflect.AGENTS
+        | _chat_polish.AGENTS
     )
     for name, cfg in all_agents.items():
         registry[name] = {

cliara-0.4.4/cliara/agents/chat_polish.py

@@ -0,0 +1,8 @@
+"""Optional LLM step: compress Cliara chat export for Cursor/Copilot."""
+
+AGENTS = {
+    "chat_polish": {
+        "temperature": 0.2,
+        "max_tokens": 1800,
+    },
+}

cliara-0.4.4/cliara/agents/prompts/chat_polish.txt

@@ -0,0 +1,9 @@
+You compress terminal/session context for an IDE assistant (Copilot or Cursor).
+
+Rules:
+- Preserve all facts: cwd, OS, shell, git branch, exact command, exit code, and stderr/stdout excerpts verbatim inside fenced blocks when present.
+- Remove redundancy and filler; use short bullets and a clear "Ask" line at the end suggesting what the coding assistant should do.
+- Do not invent errors, paths, or exit codes; only use what appears in the user message.
+- Output plain markdown (no outer JSON).
+
+The user message is a raw Cliara export (last run and/or session snapshot). Return a shorter version suitable to paste into chat.

cliara-0.4.4/cliara/agents/prompts/commit_message.txt

@@ -0,0 +1,28 @@
+You generate concise git commit messages following Conventional Commits.
+
+Return ONLY the commit message — one line, no quotes, no markdown, no explanation.
+
+Format: <type>: <description>
+- Use lowercase for the type.
+- Description: imperative mood, no period at the end, ~50–72 chars when reasonable (short is fine).
+
+Choose <type> from these (pick the best fit from the staged diff / context):
+
+Core types:
+- feat: — new user-facing feature or capability
+- fix: — bug fix
+- refactor: — restructure code without intended behavior change
+- docs: — documentation only
+- style: — formatting, whitespace, lint-only (no logic change)
+- test: — add or update tests
+- chore: — maintenance, tooling, misc (not a feature or fix)
+
+Common extras:
+- perf: — performance improvement
+- ci: — CI/CD pipeline or workflow changes
+- build: — build system, packaging, or dependency manifest changes
+- revert: — undo a previous commit (use when the change is explicitly a revert)
+
+Examples: feat: add postgres session backend, fix: handle missing prompt files in wheel, docs: clarify env setup for anthropic
+
+If multiple concerns apply, prefer the primary change (usually feat or fix) over chore/docs.

cliara-0.4.4/cliara/agents/prompts/readme.txt

@@ -0,0 +1,13 @@
+You generate professional README.md files for software projects. You are given structured context: a project fingerprint, MUST INCLUDE items (derived from codebase analysis), config files, key source files, existing docs, directory tree, and the current README (if any).
+
+RULES:
+1. Every item in MUST INCLUDE must appear in the README in a clear, user-facing form. Do not omit any.
+2. If the project has multiple setup paths (e.g. Cloud vs BYOK, Docker vs local), document BOTH with clear headings.
+3. For CLI tools with first-run setup: include a "First Run" or "Getting Started" section that walks through the actual flow (what the user sees, what to do).
+4. Preserve any badges, links, or project-specific content from the existing README unless it is outdated or wrong.
+5. For personal projects: emphasize "how to get this running" — install, env vars, first run, common gotchas.
+6. Order sections by user journey: What is it → Install → First run / Setup → Usage → Advanced/Optional.
+7. Be specific. Use actual commands, paths, and env var names from the context. Do not invent or guess.
+8. Match the ecosystem: pip/pipx for Python, npm/yarn for Node, cargo for Rust, go for Go.
+9. Keep it concise. Developers skim. Use tables for feature lists, code blocks for commands.
+10. Output ONLY the README markdown. No preamble, no explanation, no "Here is the README:".

cliara-0.4.4/cliara/agents/prompts/session_reflect.txt

@@ -0,0 +1,25 @@
+You are the session_reflect skill in Cliara. Design a short reflection flow so the user captures what mattered in their session—for themselves later and for teammates who only see the log.
+
+What you must NOT do:
+- Ask about exit codes, flags, or “why did command X fail” unless the whole session was clearly about fixing that failure.
+- Repeat raw command strings as the question.
+- Ask yes/no questions about facts already obvious from the log (e.g. “did you use git?” when git appears in the log).
+- Produce fewer than 3 steps or more than 6 steps.
+
+What you MUST do:
+- Focus on meaning: goals, outcomes, decisions, risks, handoff.
+- Use a mix of interaction types:
+  - choice: user picks one label from 2–5 full-sentence options (outcome, readiness, risk level).
+  - text: one line (next step, blocker name, link).
+  - long_text: narrative in plain language—the main “story” of the session for others to read.
+- Put long_text after at least one framing step so the user knows what angle to write from.
+- Every choice step MUST include "options" as a JSON array of 2–5 distinct strings.
+- Every step MUST have: "id" (snake_case), "kind", "question", and optional "hint" (one short line).
+
+kind must be exactly: choice | text | long_text. For long_text, omit options.
+
+Output only one JSON object, no markdown, no commentary. Top-level key must be "steps" (array). Example structure (wording must fit the briefing):
+
+{"steps":[{"id":"outcome","kind":"choice","question":"How would you describe this session for someone reading the log later?","hint":"Pick the closest fit.","options":["Exploring — no clear deliverable yet","Made progress — work continues","Finished a concrete milestone","Mostly blocked or interrupted"]},{"id":"story","kind":"long_text","question":"In a few sentences, what did you do and why does it matter?","hint":"Intent and impact—not a list of commands."},{"id":"handoff","kind":"text","question":"What should happen next (one concrete next step)?","hint":"Optional."}]}
+
+You will receive a briefing with session name, intent, branch, commands, and notes. Infer themes and tailor questions to those themes, not to command-line trivia.

cliara-0.4.4/cliara/agents/readme_generator.py

@@ -0,0 +1,8 @@
+"""README generation agent."""
+
+AGENTS = {
+    "readme": {
+        "temperature": 0.3,
+        "max_tokens": 4000,
+    },
+}

cliara-0.4.4/cliara/agents/session_reflect.py

@@ -0,0 +1,8 @@
+"""Session reflect skill: generates reflection plans for session end --reflect."""
+
+AGENTS = {
+    "session_reflect": {
+        "temperature": 0.35,
+        "max_tokens": 2800,
+    },
+}

{cliara-0.4.2 → cliara-0.4.4}/cliara/auth.py

@@ -43,7 +43,7 @@ _SUPABASE_URL: str = os.getenv(
 )
 _SUPABASE_ANON_KEY: str = os.getenv(
     "CLIARA_SUPABASE_ANON_KEY",
-    "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJzdXBhYmFzZSIsInJlZiI6InJ6a2ZlYnJzZnZoeWZtZmNmaGluIiwicm9sZSI6ImFub24iLCJpYXQiOjE3NzM1MjM1ODEsImV4cCI6MjA4OTA5OTU4MX0.6sf8uYZK5Ca8ZDtdy46JL0_-vqixL7IOfyBA60lf-Fk",  # replaced at publish time — safe to embed (anon/public key)
+    "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJzdXBhYmFzZSIsInJlZiI6InJ6a2ZlYnJzZnZoeWZtZmNmaGluIiwicm9sZSI6ImFub24iLCJpYXQiOjE3NzM1MjM1ODEsImV4cCI6MjA4OTA5OTU4MX0.6sf8uYZK5Ca8ZDtdy46JL0_-vqixL7IOfyBA60lf-Fk",  # pragma: allowlist secret — Supabase anon key is public, safe to embed
 )
 _CLIARA_GATEWAY_URL: str = os.getenv(
     "CLIARA_GATEWAY_URL",
@@ -55,6 +55,11 @@ _CALLBACK_TIMEOUT = 120   # seconds to wait for the browser callback
 _TOKEN_REFRESH_BUFFER = 60  # refresh token when < 60 seconds until expiry
 
 
+def get_gateway_url() -> str:
+    """Return the Cliara Cloud gateway URL (single source of truth for API calls)."""
+    return _CLIARA_GATEWAY_URL
+
+
 # ---------------------------------------------------------------------------
 # PKCE helpers (stdlib only — no extra dependencies)
 # ---------------------------------------------------------------------------
@@ -313,8 +318,40 @@ def login() -> "tuple[str, str]":
     server_thread = threading.Thread(target=server.serve_forever, daemon=True)
     server_thread.start()
 
-    print(f"\n  Opening browser for GitHub login...")
-    print(f"  If the browser does not open, visit:\n  {oauth_url}\n")
+    from rich import box
+    from rich.console import Group
+    from rich.panel import Panel
+    from rich.style import Style
+    from rich.text import Text
+
+    from cliara.console import get_console
+
+    _c = get_console()
+    _c.print()
+    _c.print(
+        Panel(
+            Group(
+                Text.from_markup(
+                    "[bold white]Opening your browser[/] for [bold]GitHub[/] sign-in…\n"
+                ),
+                Text(""),
+                Text(
+                    "If nothing opens, copy this URL into a browser:",
+                    style="dim",
+                ),
+                Text(""),
+                Text(
+                    oauth_url,
+                    style=Style(color="cyan", dim=True, link=oauth_url),
+                ),
+            ),
+            title=Text.from_markup("[bold cyan]Cliara Cloud[/]"),
+            border_style="cyan",
+            box=box.ROUNDED,
+            padding=(0, 1),
+        )
+    )
+    _c.print()
 
     try:
         webbrowser.open(oauth_url)