opencode/picoclaw
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Add Novita provider support

Browse source 
- Add 'novita' prefix to normalizeModel switch in openai_compat provider
- Add Novita provider to all_supported_vendors table in README.md
- Add test cases for Novita model prefix stripping

Novita endpoint: https://api.novita.ai/openai
Default models: deepseek/deepseek-v3.2, zai-org/glm-5, minimax/minimax-m2.5
This commit is contained in:
Alex-wuhu 2026-03-17 16:47:31 +08:00
parent 363861c917
commit 50c87dd5b7
3 changed files with 692 additions and 29 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

647
README.md
View file

@ -208,6 +208,653 @@ Connect Picoclaw to the Agent Social Network simply by sending a single message
**Read `https://clawdchat.ai/skill.md` and follow the instructions to join [ClawdChat.ai](https://clawdchat.ai)**
## 🖥️ CLI Reference
## ⚙️ Configuration
Config file: `~/.picoclaw/config.json`
### Environment Variables
You can override default paths using environment variables. This is useful for portable installations, containerized deployments, or running picoclaw as a system service. These variables are independent and control different paths.
| Variable | Description | Default Path |
|-------------------|-----------------------------------------------------------------------------------------------------------------------------------------|---------------------------|
| `PICOCLAW_CONFIG` | Overrides the path to the configuration file. This directly tells picoclaw which `config.json` to load, ignoring all other locations. | `~/.picoclaw/config.json` |
| `PICOCLAW_HOME` | Overrides the root directory for picoclaw data. This changes the default location of the `workspace` and other data directories. | `~/.picoclaw` |
**Examples:**
```bash
# Run picoclaw using a specific config file
# The workspace path will be read from within that config file
PICOCLAW_CONFIG=/etc/picoclaw/production.json picoclaw gateway
# Run picoclaw with all its data stored in /opt/picoclaw
# Config will be loaded from the default ~/.picoclaw/config.json
# Workspace will be created at /opt/picoclaw/workspace
PICOCLAW_HOME=/opt/picoclaw picoclaw agent
# Use both for a fully customized setup
PICOCLAW_HOME=/srv/picoclaw PICOCLAW_CONFIG=/srv/picoclaw/main.json picoclaw gateway
```
### Workspace Layout
PicoClaw stores data in your configured workspace (default: `~/.picoclaw/workspace`):
```
~/.picoclaw/workspace/
├── sessions/ # Conversation sessions and history
├── memory/ # Long-term memory (MEMORY.md)
├── state/ # Persistent state (last channel, etc.)
├── cron/ # Scheduled jobs database
├── skills/ # Custom skills
├── AGENTS.md # Agent behavior guide
├── HEARTBEAT.md # Periodic task prompts (checked every 30 min)
├── IDENTITY.md # Agent identity
├── SOUL.md # Agent soul
└── USER.md # User preferences
```
### Skill Sources
By default, skills are loaded from:
1. `~/.picoclaw/workspace/skills` (workspace)
2. `~/.picoclaw/skills` (global)
3. `<current-working-directory>/skills` (builtin)
For advanced/test setups, you can override the builtin skills root with:
```bash
export PICOCLAW_BUILTIN_SKILLS=/path/to/skills
```
### Unified Command Execution Policy
- Generic slash commands are executed through a single path in `pkg/agent/loop.go` via `commands.Executor`.
- Channel adapters no longer consume generic commands locally; they forward inbound text to the bus/agent path. Telegram still auto-registers supported commands at startup.
- Unknown slash command (for example `/foo`) passes through to normal LLM processing.
- Registered but unsupported command on the current channel (for example `/show` on WhatsApp) returns an explicit user-facing error and stops further processing.
### 🔒 Security Sandbox
PicoClaw runs in a sandboxed environment by default. The agent can only access files and execute commands within the configured workspace.
#### Default Configuration
```json
{
"agents": {
"defaults": {
"workspace": "~/.picoclaw/workspace",
"restrict_to_workspace": true
}
}
}
```
| Option | Default | Description |
| ----------------------- | ----------------------- | ----------------------------------------- |
| `workspace` | `~/.picoclaw/workspace` | Working directory for the agent |
| `restrict_to_workspace` | `true` | Restrict file/command access to workspace |
#### Protected Tools
When `restrict_to_workspace: true`, the following tools are sandboxed:
| Tool | Function | Restriction |
| ------------- | ---------------- | -------------------------------------- |
| `read_file` | Read files | Only files within workspace |
| `write_file` | Write files | Only files within workspace |
| `list_dir` | List directories | Only directories within workspace |
| `edit_file` | Edit files | Only files within workspace |
| `append_file` | Append to files | Only files within workspace |
| `exec` | Execute commands | Command paths must be within workspace |
#### Additional Exec Protection
Even with `restrict_to_workspace: false`, the `exec` tool blocks these dangerous commands:
* `rm -rf`, `del /f`, `rmdir /s` — Bulk deletion
* `format`, `mkfs`, `diskpart` — Disk formatting
* `dd if=` — Disk imaging
* Writing to `/dev/sd[a-z]` — Direct disk writes
* `shutdown`, `reboot`, `poweroff` — System shutdown
* Fork bomb `:(){ :|:& };:`
#### Error Examples
```
[ERROR] tool: Tool execution failed
{tool=exec, error=Command blocked by safety guard (path outside working dir)}
```
```
[ERROR] tool: Tool execution failed
{tool=exec, error=Command blocked by safety guard (dangerous pattern detected)}
```
#### Disabling Restrictions (Security Risk)
If you need the agent to access paths outside the workspace:
**Method 1: Config file**
```json
{
"agents": {
"defaults": {
"restrict_to_workspace": false
}
}
}
```
**Method 2: Environment variable**
```bash
export PICOCLAW_AGENTS_DEFAULTS_RESTRICT_TO_WORKSPACE=false
```
> ⚠️ **Warning**: Disabling this restriction allows the agent to access any path on your system. Use with caution in controlled environments only.
#### Security Boundary Consistency
The `restrict_to_workspace` setting applies consistently across all execution paths:
| Execution Path | Security Boundary |
| ---------------- | ---------------------------- |
| Main Agent | `restrict_to_workspace` ✅ |
| Subagent / Spawn | Inherits same restriction ✅ |
| Heartbeat tasks | Inherits same restriction ✅ |
All paths share the same workspace restriction — there's no way to bypass the security boundary through subagents or scheduled tasks.
### Heartbeat (Periodic Tasks)
PicoClaw can perform periodic tasks automatically. Create a `HEARTBEAT.md` file in your workspace:
```markdown
# Periodic Tasks
- Check my email for important messages
- Review my calendar for upcoming events
- Check the weather forecast
```
The agent will read this file every 30 minutes (configurable) and execute any tasks using available tools.
#### Async Tasks with Spawn
For long-running tasks (web search, API calls), use the `spawn` tool to create a **subagent**:
```markdown
# Periodic Tasks
## Quick Tasks (respond directly)
- Report current time
## Long Tasks (use spawn for async)
- Search the web for AI news and summarize
- Check email and report important messages
```
**Key behaviors:**
| Feature | Description |
| ----------------------- | --------------------------------------------------------- |
| **spawn** | Creates async subagent, doesn't block heartbeat |
| **Independent context** | Subagent has its own context, no session history |
| **message tool** | Subagent communicates with user directly via message tool |
| **Non-blocking** | After spawning, heartbeat continues to next task |
#### How Subagent Communication Works
```
Heartbeat triggers
↓
Agent reads HEARTBEAT.md
↓
For long task: spawn subagent
↓ ↓
Continue to next task Subagent works independently
↓ ↓
All tasks done Subagent uses "message" tool
↓ ↓
Respond HEARTBEAT_OK User receives result directly
```
The subagent has access to tools (message, web_search, etc.) and can communicate with the user independently without going through the main agent.
**Configuration:**
```json
{
"heartbeat": {
"enabled": true,
"interval": 30
}
}
```
| Option | Default | Description |
| ---------- | ------- | ---------------------------------- |
| `enabled` | `true` | Enable/disable heartbeat |
| `interval` | `30` | Check interval in minutes (min: 5) |
**Environment variables:**
* `PICOCLAW_HEARTBEAT_ENABLED=false` to disable
* `PICOCLAW_HEARTBEAT_INTERVAL=60` to change interval
### Providers
> [!NOTE]
> Groq provides free voice transcription via Whisper. If configured, audio messages from any channel will be automatically transcribed at the agent level.
| Provider | Purpose | Get API Key |
| ------------ | --------------------------------------- | ------------------------------------------------------------ |
| `gemini` | LLM (Gemini direct) | [aistudio.google.com](https://aistudio.google.com) |
| `zhipu` | LLM (Zhipu direct) | [bigmodel.cn](https://bigmodel.cn) |
| `volcengine` | LLM(Volcengine direct) | [volcengine.com](https://www.volcengine.com/activity/codingplan?utm_campaign=PicoClaw&utm_content=PicoClaw&utm_medium=devrel&utm_source=OWO&utm_term=PicoClaw) |
| `openrouter` | LLM (recommended, access to all models) | [openrouter.ai](https://openrouter.ai) |
| `anthropic` | LLM (Claude direct) | [console.anthropic.com](https://console.anthropic.com) |
| `openai` | LLM (GPT direct) | [platform.openai.com](https://platform.openai.com) |
| `deepseek` | LLM (DeepSeek direct) | [platform.deepseek.com](https://platform.deepseek.com) |
| `qwen` | LLM (Qwen direct) | [dashscope.console.aliyun.com](https://dashscope.console.aliyun.com) |
| `groq` | LLM + **Voice transcription** (Whisper) | [console.groq.com](https://console.groq.com) |
| `cerebras` | LLM (Cerebras direct) | [cerebras.ai](https://cerebras.ai) |
| `vivgrid` | LLM (Vivgrid direct) | [vivgrid.com](https://vivgrid.com) |
| `azure` | LLM (Azure OpenAI) | [portal.azure.com](https://portal.azure.com) |
### Model Configuration (model_list)
> **What's New?** PicoClaw now uses a **model-centric** configuration approach. Simply specify `vendor/model` format (e.g., `zhipu/glm-4.7`) to add new providers—**zero code changes required!**
This design also enables **multi-agent support** with flexible provider selection:
- **Different agents, different providers**: Each agent can use its own LLM provider
- **Model fallbacks**: Configure primary and fallback models for resilience
- **Load balancing**: Distribute requests across multiple endpoints
- **Centralized configuration**: Manage all providers in one place
#### 📋 All Supported Vendors
| Vendor | `model` Prefix | Default API Base | Protocol | API Key |
| ------------------- | ----------------- |-----------------------------------------------------| --------- | ---------------------------------------------------------------- |
| **OpenAI** | `openai/` | `https://api.openai.com/v1` | OpenAI | [Get Key](https://platform.openai.com) |
| **Anthropic** | `anthropic/` | `https://api.anthropic.com/v1` | Anthropic | [Get Key](https://console.anthropic.com) |
| **智谱 AI (GLM)** | `zhipu/` | `https://open.bigmodel.cn/api/paas/v4` | OpenAI | [Get Key](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) |
| **DeepSeek** | `deepseek/` | `https://api.deepseek.com/v1` | OpenAI | [Get Key](https://platform.deepseek.com) |
| **Google Gemini** | `gemini/` | `https://generativelanguage.googleapis.com/v1beta` | OpenAI | [Get Key](https://aistudio.google.com/api-keys) |
| **Groq** | `groq/` | `https://api.groq.com/openai/v1` | OpenAI | [Get Key](https://console.groq.com) |
| **Moonshot** | `moonshot/` | `https://api.moonshot.cn/v1` | OpenAI | [Get Key](https://platform.moonshot.cn) |
| **通义千问 (Qwen)** | `qwen/` | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI | [Get Key](https://dashscope.console.aliyun.com) |
| **NVIDIA** | `nvidia/` | `https://integrate.api.nvidia.com/v1` | OpenAI | [Get Key](https://build.nvidia.com) |
| **Ollama** | `ollama/` | `http://localhost:11434/v1` | OpenAI | Local (no key needed) |
| **OpenRouter** | `openrouter/` | `https://openrouter.ai/api/v1` | OpenAI | [Get Key](https://openrouter.ai/keys) |
| **LiteLLM Proxy** | `litellm/` | `http://localhost:4000/v1` | OpenAI | Your LiteLLM proxy key |
| **VLLM** | `vllm/` | `http://localhost:8000/v1` | OpenAI | Local |
| **Cerebras** | `cerebras/` | `https://api.cerebras.ai/v1` | OpenAI | [Get Key](https://cerebras.ai) |
| **VolcEngine (Doubao)** | `volcengine/` | `https://ark.cn-beijing.volces.com/api/v3` | OpenAI | [Get Key](https://www.volcengine.com/activity/codingplan?utm_campaign=PicoClaw&utm_content=PicoClaw&utm_medium=devrel&utm_source=OWO&utm_term=PicoClaw) |
| **神算云** | `shengsuanyun/` | `https://router.shengsuanyun.com/api/v1` | OpenAI | - |
| **BytePlus** | `byteplus/` | `https://ark.ap-southeast.bytepluses.com/api/v3` | OpenAI | [Get Key](https://www.byteplus.com) |
| **Vivgrid** | `vivgrid/` | `https://api.vivgrid.com/v1` | OpenAI | [Get Key](https://vivgrid.com) |
| **LongCat** | `longcat/` | `https://api.longcat.chat/openai` | OpenAI | [Get Key](https://longcat.chat/platform) |
| **ModelScope (魔搭)**| `modelscope/` | `https://api-inference.modelscope.cn/v1` | OpenAI | [Get Token](https://modelscope.cn/my/tokens) |
| **Azure OpenAI** | `azure/` | `https://{resource}.openai.azure.com` | Azure | [Get Key](https://portal.azure.com) |
| **Novita** | `novita/` | `https://api.novita.ai/openai` | OpenAI | [Get Key](https://novita.ai) |
| **Antigravity** | `antigravity/` | Google Cloud | Custom | OAuth only |
| **GitHub Copilot** | `github-copilot/` | `localhost:4321` | gRPC | - |
#### Basic Configuration
```json
{
"model_list": [
{
"model_name": "ark-code-latest",
"model": "volcengine/ark-code-latest",
"api_key": "sk-your-api-key"
},
{
"model_name": "gpt-5.4",
"model": "openai/gpt-5.4",
"api_key": "sk-your-openai-key"
},
{
"model_name": "claude-sonnet-4.6",
"model": "anthropic/claude-sonnet-4.6",
"api_key": "sk-ant-your-key"
},
{
"model_name": "glm-4.7",
"model": "zhipu/glm-4.7",
"api_key": "your-zhipu-key"
}
],
"agents": {
"defaults": {
"model": "gpt-5.4"
}
}
}
```
#### Vendor-Specific Examples
**OpenAI**
```json
{
"model_name": "gpt-5.4",
"model": "openai/gpt-5.4",
"api_key": "sk-..."
}
```
**VolcEngine (Doubao)**
```json
{
"model_name": "ark-code-latest",
"model": "volcengine/ark-code-latest",
"api_key": "sk-..."
}
```
**智谱 AI (GLM)**
```json
{
"model_name": "glm-4.7",
"model": "zhipu/glm-4.7",
"api_key": "your-key"
}
```
**DeepSeek**
```json
{
"model_name": "deepseek-chat",
"model": "deepseek/deepseek-chat",
"api_key": "sk-..."
}
```
**Anthropic (with API key)**
```json
{
"model_name": "claude-sonnet-4.6",
"model": "anthropic/claude-sonnet-4.6",
"api_key": "sk-ant-your-key"
}
```
> Run `picoclaw auth login --provider anthropic` to paste your API token.
**Anthropic Messages API (native format)**
For direct Anthropic API access or custom endpoints that only support Anthropic's native message format:
```json
{
"model_name": "claude-opus-4-6",
"model": "anthropic-messages/claude-opus-4-6",
"api_key": "sk-ant-your-key",
"api_base": "https://api.anthropic.com"
}
```
> Use `anthropic-messages` protocol when:
> - Using third-party proxies that only support Anthropic's native `/v1/messages` endpoint (not OpenAI-compatible `/v1/chat/completions`)
> - Connecting to services like MiniMax, Synthetic that require Anthropic's native message format
> - The existing `anthropic` protocol returns 404 errors (indicating the endpoint doesn't support OpenAI-compatible format)
>
> **Note:** The `anthropic` protocol uses OpenAI-compatible format (`/v1/chat/completions`), while `anthropic-messages` uses Anthropic's native format (`/v1/messages`). Choose based on your endpoint's supported format.
**Ollama (local)**
```json
{
"model_name": "llama3",
"model": "ollama/llama3"
}
```
**Custom Proxy/API**
```json
{
"model_name": "my-custom-model",
"model": "openai/custom-model",
"api_base": "https://my-proxy.com/v1",
"api_key": "sk-...",
"request_timeout": 300
}
```
**LiteLLM Proxy**
```json
{
"model_name": "lite-gpt4",
"model": "litellm/lite-gpt4",
"api_base": "http://localhost:4000/v1",
"api_key": "sk-..."
}
```
PicoClaw strips only the outer `litellm/` prefix before sending the request, so proxy aliases like `litellm/lite-gpt4` send `lite-gpt4`, while `litellm/openai/gpt-4o` sends `openai/gpt-4o`.
#### Load Balancing
Configure multiple endpoints for the same model name—PicoClaw will automatically round-robin between them:
```json
{
"model_list": [
{
"model_name": "gpt-5.4",
"model": "openai/gpt-5.4",
"api_base": "https://api1.example.com/v1",
"api_key": "sk-key1"
},
{
"model_name": "gpt-5.4",
"model": "openai/gpt-5.4",
"api_base": "https://api2.example.com/v1",
"api_key": "sk-key2"
}
]
}
```
#### Migration from Legacy `providers` Config
The old `providers` configuration is **deprecated** but still supported for backward compatibility.
**Old Config (deprecated):**
```json
{
"providers": {
"zhipu": {
"api_key": "your-key",
"api_base": "https://open.bigmodel.cn/api/paas/v4"
}
},
"agents": {
"defaults": {
"provider": "zhipu",
"model": "glm-4.7"
}
}
}
```
**New Config (recommended):**
```json
{
"model_list": [
{
"model_name": "glm-4.7",
"model": "zhipu/glm-4.7",
"api_key": "your-key"
}
],
"agents": {
"defaults": {
"model": "glm-4.7"
}
}
}
```
For detailed migration guide, see [docs/migration/model-list-migration.md](docs/migration/model-list-migration.md).
### Provider Architecture
PicoClaw routes providers by protocol family:
- OpenAI-compatible protocol: OpenRouter, OpenAI-compatible gateways, Groq, Zhipu, and vLLM-style endpoints.
- Anthropic protocol: Claude-native API behavior.
- Codex/OAuth path: OpenAI OAuth/token authentication route.
This keeps the runtime lightweight while making new OpenAI-compatible backends mostly a config operation (`api_base` + `api_key`).
<details>
<summary><b>Zhipu</b></summary>
**1. Get API key and base URL**
* Get [API key](https://bigmodel.cn/usercenter/proj-mgmt/apikeys)
**2. Configure**
```json
{
"agents": {
"defaults": {
"workspace": "~/.picoclaw/workspace",
"model": "glm-4.7",
"max_tokens": 8192,
"temperature": 0.7,
"max_tool_iterations": 20
}
},
"providers": {
"zhipu": {
"api_key": "Your API Key",
"api_base": "https://open.bigmodel.cn/api/paas/v4"
}
}
}
```
**3. Run**
```bash
picoclaw agent -m "Hello"
```
</details>
<details>
<summary><b>Full config example</b></summary>
```json
{
"agents": {
"defaults": {
"model": "anthropic/claude-opus-4-5"
}
},
"session": {
"dm_scope": "per-channel-peer",
"backlog_limit": 20
},
"providers": {
"openrouter": {
"api_key": "sk-or-v1-xxx"
},
"groq": {
"api_key": "gsk_xxx"
}
},
"channels": {
"telegram": {
"enabled": true,
"token": "123456:ABC...",
"allow_from": ["123456789"]
},
"discord": {
"enabled": true,
"token": "",
"allow_from": [""]
},
"whatsapp": {
"enabled": false,
"bridge_url": "ws://localhost:3001",
"use_native": false,
"session_store_path": "",
"allow_from": []
},
"feishu": {
"enabled": false,
"app_id": "cli_xxx",
"app_secret": "xxx",
"encrypt_key": "",
"verification_token": "",
"allow_from": []
},
"qq": {
"enabled": false,
"app_id": "",
"app_secret": "",
"allow_from": []
}
},
"tools": {
"web": {
"brave": {
"enabled": false,
"api_key": "BSA...",
"max_results": 5
},
"duckduckgo": {
"enabled": true,
"max_results": 5
},
"perplexity": {
"enabled": false,
"api_key": "",
"max_results": 5
},
"searxng": {
"enabled": false,
"base_url": "http://localhost:8888",
"max_results": 5
}
},
"cron": {
"exec_timeout_minutes": 5
}
},
"heartbeat": {
"enabled": true,
"interval": 30
}
}
```
</details>
## CLI Reference
| Command | Description |
| ------------------------- | ----------------------------- |

14
pkg/providers/openai_compat/provider.go
View file

@ -189,13 +189,13 @@ func normalizeModel(model, apiBase string) string {
}
prefix := strings.ToLower(before)
switch prefix {
case "litellm", "moonshot", "nvidia", "groq", "ollama", "deepseek", "google",
"openrouter", "zhipu", "mistral", "vivgrid", "minimax":
return after
default:
return model
}
switch prefix {
case "litellm", "moonshot", "nvidia", "groq", "ollama", "deepseek", "google",
"openrouter", "zhipu", "mistral", "vivgrid", "minimax", "novita":
return after
default:
return model
}
}
func buildToolsList(tools []ToolDefinition, nativeSearch bool) []any {

60
pkg/providers/openai_compat/provider_test.go
View file

@ -432,7 +432,29 @@ func TestProviderChat_StripsMoonshotPrefixAndNormalizesKimiTemperature(t *testin
}
}
func TestProviderChat_StripsGroqOllamaDeepseekVivgridPrefixes(t *testing.T) {
func TestProviderChat_StripsGroqOllamaDeepseekVivgridNovitaPrefixes(t *testing.T) {
var requestBody map[string]any
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if err := json.NewDecoder(r.Body).Decode(&requestBody); err != nil {
http.Error(w, err.Error(), http.StatusBadRequest)
return
}
resp := map[string]any{
"choices": []map[string]any{
{
"message": map[string]any{"content": "ok"},
"finish_reason": "stop",
},
},
}
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(resp)
}))
defer server.Close()
p := NewProvider("key", server.URL, "")
tests := []struct {
name string
input string
@ -463,31 +485,25 @@ func TestProviderChat_StripsGroqOllamaDeepseekVivgridPrefixes(t *testing.T) {
input: "vivgrid/auto",
wantModel: "auto",
},
{
name: "strips novita prefix deepseek model",
input: "novita/deepseek/deepseek-v3.2",
wantModel: "deepseek/deepseek-v3.2",
},
{
name: "strips novita prefix zai model",
input: "novita/zai-org/glm-5",
wantModel: "zai-org/glm-5",
},
{
name: "strips novita prefix minimax model",
input: "novita/minimax/minimax-m2.5",
wantModel: "minimax/minimax-m2.5",
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
var requestBody map[string]any
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if err := json.NewDecoder(r.Body).Decode(&requestBody); err != nil {
http.Error(w, err.Error(), http.StatusBadRequest)
return
}
resp := map[string]any{
"choices": []map[string]any{
{
"message": map[string]any{"content": "ok"},
"finish_reason": "stop",
},
},
}
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(resp)
}))
defer server.Close()
p := NewProvider("key", server.URL, "")
_, err := p.Chat(t.Context(), []Message{{Role: "user", Content: "hi"}}, nil, tt.input, nil)
if err != nil {
t.Fatalf("Chat() error = %v", err)