PyPI - velune-cli - Versions diffs - 0.9.4__tar.gz → 0.9.5__tar.gz - Mend

velune-cli 0.9.4tar.gz → 0.9.5tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (493) hide show

{velune_cli-0.9.4 → velune_cli-0.9.5}/.gitignore RENAMED Viewed

@@ -122,3 +122,11 @@ ext/rust/**/target/
 node_modules/
 package-lock.json
 yarn.lock
+# Databases & Local State
+*.db
+*.sqlite
+*.sqlite3
+*.bak
+credentials.json
+master.key

{velune_cli-0.9.4 → velune_cli-0.9.5}/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: velune-cli
-Version: 0.9.4
+Version: 0.9.5
 Summary: Local-first multi-model AI developer CLI — council-based agents, persistent memory, repository cognition
 Project-URL: Homepage, https://github.com/Surya-Hariharan/Velune-CLI
 Project-URL: Repository, https://github.com/Surya-Hariharan/Velune-CLI
@@ -227,6 +227,7 @@ Classifier: Typing :: Typed
 Requires-Python: >=3.10
 Requires-Dist: aiosqlite>=0.19.0
 Requires-Dist: anthropic>=0.18.0
+Requires-Dist: cryptography>=41.0.0
 Requires-Dist: httpx>=0.26.0
 Requires-Dist: keyring>=24.0.0
 Requires-Dist: mcp>=1.0.0
@@ -292,16 +293,16 @@ Requires-Dist: opentelemetry-exporter-otlp>=1.22.0; extra == 'telemetry'
 Requires-Dist: opentelemetry-sdk>=1.22.0; extra == 'telemetry'
 Description-Content-Type: text/markdown
-# Velune
+# Velune CLI
-> Local-first multi-model AI developer CLI. Council-based agents,
-> persistent memory, repository cognition.
-> No cloud required. No quota. No lock-in.
+*Local-first multi-model AI developer CLI. Council-based agents, persistent memory, repository cognition.*
-[![PyPI](https://img.shields.io/pypi/v/velune-cli)](https://pypi.org/project/velune-cli/)
-[![Python](https://img.shields.io/badge/python-3.10%2B-blue)](https://python.org)
-[![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-green)](LICENSE)
-[![CI](https://img.shields.io/github/actions/workflow/status/Surya-Hariharan/Velune-CLI/ci.yml?branch=main&label=CI)](https://github.com/Surya-Hariharan/Velune-CLI/actions/workflows/ci.yml)
+**No cloud required. No quota. No lock-in.**
+[![PyPI - Version](https://img.shields.io/pypi/v/velune-cli?style=for-the-badge&color=00ff00)](https://pypi.org/project/velune-cli/)
+[![Python](https://img.shields.io/badge/Python-3.10%2B-blue?style=for-the-badge&logo=python&logoColor=white)](https://python.org)
+[![License](https://img.shields.io/badge/License-Apache_2.0-green.svg?style=for-the-badge)](LICENSE)
+[![CI](https://img.shields.io/github/actions/workflow/status/Surya-Hariharan/Velune-CLI/ci.yml?branch=main&label=CI&style=for-the-badge&logo=github)](https://github.com/Surya-Hariharan/Velune-CLI/actions/workflows/ci.yml)
 ---
@@ -391,37 +392,43 @@ Python to PATH”** checked (or using `pipx`) resolves it permanently.
 ## Hardware requirements
-| RAM    | GPU              | Can run local LLM? | Recommended setup            |
-|--------|------------------|--------------------|------------------------------|
-| < 8 GB | any              | ✗ No               | Use Groq free tier           |
-| 8 GB   | integrated       | ⚠ 3B models only   | Groq + phi3-mini local       |
-| 16 GB  | integrated       | ⚠ Slow (CPU only)  | Groq + 3B local              |
-| 16 GB  | 6–8 GB VRAM      | ✓ 7B comfortable   | qwen2.5-coder:7b             |
-| 32 GB  | 12+ GB VRAM      | ✓ 13B comfortable  | Full council local           |
-| 36 GB  | Apple Silicon    | ✓ 27B comfortable  | Full council, Metal accel    |
-| 64 GB  | 24 GB VRAM       | ✓ 70B capable      | Max power mode               |
+| RAM | GPU | Can run local LLM? | Recommended setup |
+| :---: | :--- | :--- | :--- |
+| **< 8 GB** | Any | ❌ No | Use Groq free tier |
+| **8 GB** | Integrated | ⚠️ 3B models only | Groq + phi3-mini local |
+| **16 GB** | Integrated | ⚠️ Slow (CPU only) | Groq + 3B local |
+| **16 GB** | 6–8 GB VRAM | ✅ 7B comfortable | `qwen2.5-coder:7b` |
+| **32 GB** | 12+ GB VRAM | ✅ 13B comfortable | Full council local |
+| **36 GB** | Apple Silicon | ✅ 27B comfortable | Full council, Metal accel |
+| **64 GB** | 24 GB VRAM | ✅ 70B capable | Max power mode |
-Velune detects your hardware on startup and prints tier, GPU, and recommendations.
-On underpowered machines it routes tasks to cloud providers automatically.
+> **Note:** Velune detects your hardware on startup and prints tier, GPU, and recommendations. On underpowered machines, it routes tasks to cloud providers automatically.
 ---
 ## Startup flow
-Velune starts instantly and does no work until you ask for it. Repository
-cognition (indexing) is **explicit and on-demand** — it never runs automatically
-on launch.
-```text
-velune
-    ↓
-CLI opens instantly
-    ↓
-Connect a model      →  /model discover · /model connect <id> · /model use <id>
-    ↓
-Open a project       →  /project open <path> · /project status
-    ↓
-Run cognition        →  /cognition quick · /cognition standard · /cognition deep
+Velune starts instantly and does no work until you ask for it. Repository cognition (indexing) is **explicit and on-demand** — it never runs automatically on launch.
+```mermaid
+flowchart TD
+    Start([velune]) --> CLI[CLI opens instantly]
+    CLI --> Connect[Connect a model]
+    Connect -.-> C1("`/model discover`")
+    Connect -.-> C2("`/model connect <id>`")
+    Connect -.-> C3("`/model use <id>`")
+    Connect --> Open[Open a project]
+    Open -.-> O1("`/project open <path>`")
+    Open -.-> O2("`/project status`")
+    Open --> Cog[Run cognition]
+    Cog -.-> R1("`/cognition quick`")
+    Cog -.-> R2("`/cognition standard`")
+    Cog -.-> R3("`/cognition deep`")
+    classDef action fill:#0a3d62,stroke:#3c6382,stroke-width:2px,color:#fff;
+    classDef cmd fill:#079992,stroke:#38ada9,stroke-width:1px,color:#fff;
+    class Start,CLI,Connect,Open,Cog action;
+    class C1,C2,C3,O1,O2,R1,R2,R3 cmd;
 ```
 ---
@@ -440,25 +447,25 @@ Velune features a modern, clean terminal interface designed for productivity:
 ## Providers
-| Provider     | Type  | Cost          | Models                                        | Setup                        |
-|--------------|-------|---------------|-----------------------------------------------|------------------------------|
-| Ollama       | Local | Free          | Any pulled model                              | Install Ollama, pull a model |
-| LM Studio    | Local | Free          | Any GGUF / MLX model                          | Launch LM Studio server      |
-| Groq         | Cloud | Free tier     | Llama 3.3 70B, Mixtral, Gemma2                | `velune setup` → enter key   |
-| OpenRouter   | Cloud | Pay-per-token | 100+ models                                   | `velune setup` → enter key   |
-| OpenAI       | Cloud | Pay-per-token | GPT-4o, GPT-4o Mini                           | `velune setup` → enter key   |
-| Anthropic    | Cloud | Pay-per-token | Claude Opus, Sonnet, Haiku                    | `velune setup` → enter key   |
-| xAI (Grok)   | Cloud | Pay-per-token | Grok 2, Grok 2 Mini                           | `velune setup` → enter key   |
-| Google       | Cloud | Free quota    | Gemini 2.0 Flash, 1.5 Pro/Flash               | `velune setup` → enter key   |
-| Together AI  | Cloud | Pay-per-token | Llama 3.3 70B, Qwen 2.5 Coder, DeepSeek R1    | `velune setup` → enter key   |
-| Fireworks AI | Cloud | Pay-per-token | DeepSeek R1, Qwen 2.5 Coder, Mixtral 8x22B    | `velune setup` → enter key   |
-| Mistral      | Cloud | Pay-per-token | Mistral Large, Codestral, Mixtral             | `velune setup` → enter key   |
-| DeepSeek     | Cloud | Pay-per-token | DeepSeek R1, DeepSeek Coder                   | `velune setup` → enter key   |
-| Cohere       | Cloud | Pay-per-token | Command R+, Command R                         | `velune setup` → enter key   |
-| NVIDIA NIM   | Cloud | Pay-per-token | Llama, Mistral, and other NIM models          | `velune setup` → enter key   |
-| HuggingFace  | Cloud | Free/paid     | Open models via Inference API                 | `velune setup` → enter key   |
-Keys are stored in your OS keyring — never in files, never in git.
+| Provider | Type | Cost | Models | Setup |
+| :--- | :---: | :--- | :--- | :--- |
+| **Ollama** | 🏠 Local | Free | Any pulled model | Install Ollama, pull a model |
+| **LM Studio** | 🏠 Local | Free | Any GGUF / MLX model | Launch LM Studio server |
+| **Groq** | ☁️ Cloud | Free tier | Llama 3.3 70B, Mixtral, Gemma2 | `velune setup` → enter key |
+| **OpenRouter** | ☁️ Cloud | Pay-per-token | 100+ models | `velune setup` → enter key |
+| **OpenAI** | ☁️ Cloud | Pay-per-token | GPT-4o, GPT-4o Mini | `velune setup` → enter key |
+| **Anthropic** | ☁️ Cloud | Pay-per-token | Claude Opus, Sonnet, Haiku | `velune setup` → enter key |
+| **xAI (Grok)** | ☁️ Cloud | Pay-per-token | Grok 2, Grok 2 Mini | `velune setup` → enter key |
+| **Google** | ☁️ Cloud | Free quota | Gemini 2.0 Flash, 1.5 Pro/Flash | `velune setup` → enter key |
+| **Together AI** | ☁️ Cloud | Pay-per-token | Llama 3.3 70B, Qwen 2.5, DeepSeek R1 | `velune setup` → enter key |
+| **Fireworks AI** | ☁️ Cloud | Pay-per-token | DeepSeek R1, Qwen 2.5, Mixtral 8x22B | `velune setup` → enter key |
+| **Mistral** | ☁️ Cloud | Pay-per-token | Mistral Large, Codestral, Mixtral | `velune setup` → enter key |
+| **DeepSeek** | ☁️ Cloud | Pay-per-token | DeepSeek R1, DeepSeek Coder | `velune setup` → enter key |
+| **Cohere** | ☁️ Cloud | Pay-per-token | Command R+, Command R | `velune setup` → enter key |
+| **NVIDIA NIM** | ☁️ Cloud | Pay-per-token | Llama, Mistral, and other NIM models | `velune setup` → enter key |
+| **HuggingFace** | ☁️ Cloud | Free/paid | Open models via Inference API | `velune setup` → enter key |
+> **Tip:** Keys are stored securely in your OS keyring — never in plain text files, never in git.
 ---
@@ -472,15 +479,19 @@ velune                    # Start the interactive REPL session
 velune chat               # Same as above (explicit form)
 velune run "<task>"       # Run a task non-interactively and exit
 velune ask "<question>"   # Ask a one-shot question and exit
-velune init               # Initialize Velune in a project directory
+velune init               # Initialize Velune in the current workspace
+velune onboard            # Run (or resume) the first-time setup wizard
 # Workspace & sessions
-velune workspace init     # Index the current workspace
-velune workspace status   # Show index freshness and file counts
-velune workspace graph    # Render the workspace dependency graph
-velune workspace list     # List all known workspaces
+velune project init       # Index the current workspace (Tree-sitter AST)
+velune project status     # Show index freshness and file counts
+velune project graph      # Render the module-dependency graph
+velune project tree       # Render the workspace directory tree
+velune project list       # List all registered workspaces
+velune project explain    # Generate a plain-English architecture summary
 velune session list       # List saved chat sessions
 velune session delete <id>  # Delete a saved session
+velune trust              # Trust, list, or revoke workspace directories
 # Setup & models
 velune setup              # Configure API keys (stored in OS keyring)
@@ -656,13 +667,13 @@ to reconstruct intent without you explaining it again.
 ## Session modes
-| Mode    | Command    | Council tier | Model    | Context cap  |
-|---------|------------|--------------|----------|--------------|
-| Normal  | `/normal`  | auto         | current  | 16 k tokens  |
-| Optimus | `/optimus` | instant      | smallest | 4 k tokens   |
-| Godly   | `/godly`   | full         | largest  | 128 k tokens |
+| Mode | Command | Council tier | Model | Context cap |
+| :--- | :--- | :---: | :--- | :--- |
+| **Normal** | `/normal` | Auto | Current | 16k tokens |
+| **Optimus** | `/optimus` | Instant | Smallest | 4k tokens |
+| **Godly** | `/godly` | Full | Largest | 128k tokens |
-Switch modes at any time mid-session. The prompt badge updates immediately.
+> **Tip:** Switch modes at any time mid-session. The prompt badge updates immediately.
 ---
@@ -713,7 +724,7 @@ lexical search and chat keep working).
 | `[rag]` | `lancedb`, `pyarrow`, `qdrant-client` | Semantic memory + vector retrieval (large compiled wheels) |
 | `[parsing]` | `tree-sitter` + grammars | Tree-sitter source parsing for deep repository cognition |
 | `[telemetry]` | `opentelemetry-*` | Export spans/metrics to an OTLP collector |
-| `[git]` | `gitpython` | Git provider tools (push / PR / issue) and richer git context |
+| `[git]` | *(no extra deps)* | Retained for compatibility — git tools (push / PR / issue) now use native `git` subprocess calls, so nothing extra installs |
 | `[gguf]` | `gguf` | GGUF file metadata reading — safe, no transitive risk |
 | `[docker]` | `docker` | Docker sandbox for isolated code execution |
 | `[all]` | everything above | Full-featured install |

{velune_cli-0.9.4 → velune_cli-0.9.5}/README.md RENAMED Viewed

@@ -1,13 +1,13 @@
-# Velune
+# Velune CLI
-> Local-first multi-model AI developer CLI. Council-based agents,
-> persistent memory, repository cognition.
-> No cloud required. No quota. No lock-in.
+*Local-first multi-model AI developer CLI. Council-based agents, persistent memory, repository cognition.*
-[![PyPI](https://img.shields.io/pypi/v/velune-cli)](https://pypi.org/project/velune-cli/)
-[![Python](https://img.shields.io/badge/python-3.10%2B-blue)](https://python.org)
-[![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-green)](LICENSE)
-[![CI](https://img.shields.io/github/actions/workflow/status/Surya-Hariharan/Velune-CLI/ci.yml?branch=main&label=CI)](https://github.com/Surya-Hariharan/Velune-CLI/actions/workflows/ci.yml)
+**No cloud required. No quota. No lock-in.**
+[![PyPI - Version](https://img.shields.io/pypi/v/velune-cli?style=for-the-badge&color=00ff00)](https://pypi.org/project/velune-cli/)
+[![Python](https://img.shields.io/badge/Python-3.10%2B-blue?style=for-the-badge&logo=python&logoColor=white)](https://python.org)
+[![License](https://img.shields.io/badge/License-Apache_2.0-green.svg?style=for-the-badge)](LICENSE)
+[![CI](https://img.shields.io/github/actions/workflow/status/Surya-Hariharan/Velune-CLI/ci.yml?branch=main&label=CI&style=for-the-badge&logo=github)](https://github.com/Surya-Hariharan/Velune-CLI/actions/workflows/ci.yml)
 ---
@@ -97,37 +97,43 @@ Python to PATH”** checked (or using `pipx`) resolves it permanently.
 ## Hardware requirements
-| RAM    | GPU              | Can run local LLM? | Recommended setup            |
-|--------|------------------|--------------------|------------------------------|
-| < 8 GB | any              | ✗ No               | Use Groq free tier           |
-| 8 GB   | integrated       | ⚠ 3B models only   | Groq + phi3-mini local       |
-| 16 GB  | integrated       | ⚠ Slow (CPU only)  | Groq + 3B local              |
-| 16 GB  | 6–8 GB VRAM      | ✓ 7B comfortable   | qwen2.5-coder:7b             |
-| 32 GB  | 12+ GB VRAM      | ✓ 13B comfortable  | Full council local           |
-| 36 GB  | Apple Silicon    | ✓ 27B comfortable  | Full council, Metal accel    |
-| 64 GB  | 24 GB VRAM       | ✓ 70B capable      | Max power mode               |
+| RAM | GPU | Can run local LLM? | Recommended setup |
+| :---: | :--- | :--- | :--- |
+| **< 8 GB** | Any | ❌ No | Use Groq free tier |
+| **8 GB** | Integrated | ⚠️ 3B models only | Groq + phi3-mini local |
+| **16 GB** | Integrated | ⚠️ Slow (CPU only) | Groq + 3B local |
+| **16 GB** | 6–8 GB VRAM | ✅ 7B comfortable | `qwen2.5-coder:7b` |
+| **32 GB** | 12+ GB VRAM | ✅ 13B comfortable | Full council local |
+| **36 GB** | Apple Silicon | ✅ 27B comfortable | Full council, Metal accel |
+| **64 GB** | 24 GB VRAM | ✅ 70B capable | Max power mode |
-Velune detects your hardware on startup and prints tier, GPU, and recommendations.
-On underpowered machines it routes tasks to cloud providers automatically.
+> **Note:** Velune detects your hardware on startup and prints tier, GPU, and recommendations. On underpowered machines, it routes tasks to cloud providers automatically.
 ---
 ## Startup flow
-Velune starts instantly and does no work until you ask for it. Repository
-cognition (indexing) is **explicit and on-demand** — it never runs automatically
-on launch.
-```text
-velune
-    ↓
-CLI opens instantly
-    ↓
-Connect a model      →  /model discover · /model connect <id> · /model use <id>
-    ↓
-Open a project       →  /project open <path> · /project status
-    ↓
-Run cognition        →  /cognition quick · /cognition standard · /cognition deep
+Velune starts instantly and does no work until you ask for it. Repository cognition (indexing) is **explicit and on-demand** — it never runs automatically on launch.
+```mermaid
+flowchart TD
+    Start([velune]) --> CLI[CLI opens instantly]
+    CLI --> Connect[Connect a model]
+    Connect -.-> C1("`/model discover`")
+    Connect -.-> C2("`/model connect <id>`")
+    Connect -.-> C3("`/model use <id>`")
+    Connect --> Open[Open a project]
+    Open -.-> O1("`/project open <path>`")
+    Open -.-> O2("`/project status`")
+    Open --> Cog[Run cognition]
+    Cog -.-> R1("`/cognition quick`")
+    Cog -.-> R2("`/cognition standard`")
+    Cog -.-> R3("`/cognition deep`")
+    classDef action fill:#0a3d62,stroke:#3c6382,stroke-width:2px,color:#fff;
+    classDef cmd fill:#079992,stroke:#38ada9,stroke-width:1px,color:#fff;
+    class Start,CLI,Connect,Open,Cog action;
+    class C1,C2,C3,O1,O2,R1,R2,R3 cmd;
 ```
 ---
@@ -146,25 +152,25 @@ Velune features a modern, clean terminal interface designed for productivity:
 ## Providers
-| Provider     | Type  | Cost          | Models                                        | Setup                        |
-|--------------|-------|---------------|-----------------------------------------------|------------------------------|
-| Ollama       | Local | Free          | Any pulled model                              | Install Ollama, pull a model |
-| LM Studio    | Local | Free          | Any GGUF / MLX model                          | Launch LM Studio server      |
-| Groq         | Cloud | Free tier     | Llama 3.3 70B, Mixtral, Gemma2                | `velune setup` → enter key   |
-| OpenRouter   | Cloud | Pay-per-token | 100+ models                                   | `velune setup` → enter key   |
-| OpenAI       | Cloud | Pay-per-token | GPT-4o, GPT-4o Mini                           | `velune setup` → enter key   |
-| Anthropic    | Cloud | Pay-per-token | Claude Opus, Sonnet, Haiku                    | `velune setup` → enter key   |
-| xAI (Grok)   | Cloud | Pay-per-token | Grok 2, Grok 2 Mini                           | `velune setup` → enter key   |
-| Google       | Cloud | Free quota    | Gemini 2.0 Flash, 1.5 Pro/Flash               | `velune setup` → enter key   |
-| Together AI  | Cloud | Pay-per-token | Llama 3.3 70B, Qwen 2.5 Coder, DeepSeek R1    | `velune setup` → enter key   |
-| Fireworks AI | Cloud | Pay-per-token | DeepSeek R1, Qwen 2.5 Coder, Mixtral 8x22B    | `velune setup` → enter key   |
-| Mistral      | Cloud | Pay-per-token | Mistral Large, Codestral, Mixtral             | `velune setup` → enter key   |
-| DeepSeek     | Cloud | Pay-per-token | DeepSeek R1, DeepSeek Coder                   | `velune setup` → enter key   |
-| Cohere       | Cloud | Pay-per-token | Command R+, Command R                         | `velune setup` → enter key   |
-| NVIDIA NIM   | Cloud | Pay-per-token | Llama, Mistral, and other NIM models          | `velune setup` → enter key   |
-| HuggingFace  | Cloud | Free/paid     | Open models via Inference API                 | `velune setup` → enter key   |
-Keys are stored in your OS keyring — never in files, never in git.
+| Provider | Type | Cost | Models | Setup |
+| :--- | :---: | :--- | :--- | :--- |
+| **Ollama** | 🏠 Local | Free | Any pulled model | Install Ollama, pull a model |
+| **LM Studio** | 🏠 Local | Free | Any GGUF / MLX model | Launch LM Studio server |
+| **Groq** | ☁️ Cloud | Free tier | Llama 3.3 70B, Mixtral, Gemma2 | `velune setup` → enter key |
+| **OpenRouter** | ☁️ Cloud | Pay-per-token | 100+ models | `velune setup` → enter key |
+| **OpenAI** | ☁️ Cloud | Pay-per-token | GPT-4o, GPT-4o Mini | `velune setup` → enter key |
+| **Anthropic** | ☁️ Cloud | Pay-per-token | Claude Opus, Sonnet, Haiku | `velune setup` → enter key |
+| **xAI (Grok)** | ☁️ Cloud | Pay-per-token | Grok 2, Grok 2 Mini | `velune setup` → enter key |
+| **Google** | ☁️ Cloud | Free quota | Gemini 2.0 Flash, 1.5 Pro/Flash | `velune setup` → enter key |
+| **Together AI** | ☁️ Cloud | Pay-per-token | Llama 3.3 70B, Qwen 2.5, DeepSeek R1 | `velune setup` → enter key |
+| **Fireworks AI** | ☁️ Cloud | Pay-per-token | DeepSeek R1, Qwen 2.5, Mixtral 8x22B | `velune setup` → enter key |
+| **Mistral** | ☁️ Cloud | Pay-per-token | Mistral Large, Codestral, Mixtral | `velune setup` → enter key |
+| **DeepSeek** | ☁️ Cloud | Pay-per-token | DeepSeek R1, DeepSeek Coder | `velune setup` → enter key |
+| **Cohere** | ☁️ Cloud | Pay-per-token | Command R+, Command R | `velune setup` → enter key |
+| **NVIDIA NIM** | ☁️ Cloud | Pay-per-token | Llama, Mistral, and other NIM models | `velune setup` → enter key |
+| **HuggingFace** | ☁️ Cloud | Free/paid | Open models via Inference API | `velune setup` → enter key |
+> **Tip:** Keys are stored securely in your OS keyring — never in plain text files, never in git.
 ---
@@ -178,15 +184,19 @@ velune                    # Start the interactive REPL session
 velune chat               # Same as above (explicit form)
 velune run "<task>"       # Run a task non-interactively and exit
 velune ask "<question>"   # Ask a one-shot question and exit
-velune init               # Initialize Velune in a project directory
+velune init               # Initialize Velune in the current workspace
+velune onboard            # Run (or resume) the first-time setup wizard
 # Workspace & sessions
-velune workspace init     # Index the current workspace
-velune workspace status   # Show index freshness and file counts
-velune workspace graph    # Render the workspace dependency graph
-velune workspace list     # List all known workspaces
+velune project init       # Index the current workspace (Tree-sitter AST)
+velune project status     # Show index freshness and file counts
+velune project graph      # Render the module-dependency graph
+velune project tree       # Render the workspace directory tree
+velune project list       # List all registered workspaces
+velune project explain    # Generate a plain-English architecture summary
 velune session list       # List saved chat sessions
 velune session delete <id>  # Delete a saved session
+velune trust              # Trust, list, or revoke workspace directories
 # Setup & models
 velune setup              # Configure API keys (stored in OS keyring)
@@ -362,13 +372,13 @@ to reconstruct intent without you explaining it again.
 ## Session modes
-| Mode    | Command    | Council tier | Model    | Context cap  |
-|---------|------------|--------------|----------|--------------|
-| Normal  | `/normal`  | auto         | current  | 16 k tokens  |
-| Optimus | `/optimus` | instant      | smallest | 4 k tokens   |
-| Godly   | `/godly`   | full         | largest  | 128 k tokens |
+| Mode | Command | Council tier | Model | Context cap |
+| :--- | :--- | :---: | :--- | :--- |
+| **Normal** | `/normal` | Auto | Current | 16k tokens |
+| **Optimus** | `/optimus` | Instant | Smallest | 4k tokens |
+| **Godly** | `/godly` | Full | Largest | 128k tokens |
-Switch modes at any time mid-session. The prompt badge updates immediately.
+> **Tip:** Switch modes at any time mid-session. The prompt badge updates immediately.
 ---
@@ -419,7 +429,7 @@ lexical search and chat keep working).
 | `[rag]` | `lancedb`, `pyarrow`, `qdrant-client` | Semantic memory + vector retrieval (large compiled wheels) |
 | `[parsing]` | `tree-sitter` + grammars | Tree-sitter source parsing for deep repository cognition |
 | `[telemetry]` | `opentelemetry-*` | Export spans/metrics to an OTLP collector |
-| `[git]` | `gitpython` | Git provider tools (push / PR / issue) and richer git context |
+| `[git]` | *(no extra deps)* | Retained for compatibility — git tools (push / PR / issue) now use native `git` subprocess calls, so nothing extra installs |
 | `[gguf]` | `gguf` | GGUF file metadata reading — safe, no transitive risk |
 | `[docker]` | `docker` | Docker sandbox for isolated code execution |
 | `[all]` | everything above | Full-featured install |

velune-cli 0.9.4__tar.gz → 0.9.5__tar.gz

velune-cli 0.9.4tar.gz → 0.9.5tar.gz