marketing-shibata50/multica
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

docs: update credential setup

Browse source
This commit is contained in:
Jiayuan 2026-02-01 02:28:43 +08:00
parent 3ee8946e29
commit c54e768016
3 changed files with 55 additions and 77 deletions
Download patch file Download diff file Expand all files Collapse all files

52
.env.example
View file

@ -1,52 +0,0 @@
# =============================================================================
# LLM Provider Configuration
# =============================================================================
# Copy this file to .env and fill in your values:
# cp .env.example .env
#
# Then load before running:
# source .env && pnpm dev:console
# =============================================================================
# Default LLM provider (e.g., openai, anthropic, deepseek, kimi-coding, groq, mistral)
export LLM_PROVIDER=
# --- OpenAI ---
export OPENAI_API_KEY=
export OPENAI_BASE_URL=
export OPENAI_MODEL=
# --- Anthropic ---
export ANTHROPIC_API_KEY=
export ANTHROPIC_BASE_URL=
export ANTHROPIC_MODEL=
# --- DeepSeek ---
export DEEPSEEK_API_KEY=
export DEEPSEEK_BASE_URL=
export DEEPSEEK_MODEL=
# --- Kimi (Moonshot) ---
export MOONSHOT_API_KEY=
export MOONSHOT_BASE_URL=
export MOONSHOT_MODEL=
# --- Groq ---
export GROQ_API_KEY=
export GROQ_BASE_URL=
export GROQ_MODEL=
# --- Mistral ---
export MISTRAL_API_KEY=
export MISTRAL_BASE_URL=
export MISTRAL_MODEL=
# --- Together ---
export TOGETHER_API_KEY=
export TOGETHER_BASE_URL=
export TOGETHER_MODEL=
# --- Google ---
export GOOGLE_API_KEY=
export GOOGLE_BASE_URL=
export GOOGLE_MODEL=

13
CLAUDE.md
View file

@ -73,15 +73,18 @@ Frontend (web:3001 / desktop)
- **Backend**: NestJS 11, Socket.io, Pino logging
- **CLI bundling**: esbuild → `bin/` directory
## Environment Setup
## Credentials Setup
Use JSON5 credential files instead of `.env`:
```bash
cp .env.example .env
# Set LLM_PROVIDER and corresponding API keys
# Supported: openai, anthropic, deepseek, kimi-coding, groq, mistral, together, google
# .env is loaded automatically via --env-file in all dev/agent scripts
pnpm credentials:cli init
```
This creates:
- `~/.super-multica/credentials.json5` (LLM providers + built-in tools)
- `~/.super-multica/skills.env.json5` (skills / plugins / integrations)
## Atomic Commits
After completing any task that modifies code, you MUST create atomic commits before ending the conversation.

67
README.md
View file

@ -35,45 +35,72 @@ skills/ # Bundled skills (commit, code-review)
pnpm install
```
### Environment Configuration
### Credentials Configuration
The Agent requires LLM provider credentials. Copy the example and fill in your values:
The Agent reads credentials from JSON5 files (no `.env` required).
Create empty templates:
```bash
cp .env.example .env
# Edit .env with your API keys
pnpm credentials:cli init
```
Example `.env` for OpenAI:
This creates:
```bash
export LLM_PROVIDER=openai
export OPENAI_API_KEY=sk-xxx
export OPENAI_BASE_URL=https://api.openai.com/v1
export OPENAI_MODEL=gpt-4o
- `~/.super-multica/credentials.json5` — core config (LLM providers + built-in tools)
- `~/.super-multica/skills.env.json5` — dynamic keys (skills / plugins / integrations)
Example `credentials.json5` (OpenAI):
```json5
{
version: 1,
llm: {
provider: "openai",
providers: {
openai: {
apiKey: "sk-xxx",
baseUrl: "https://api.openai.com/v1",
model: "gpt-4o"
}
}
},
tools: {
brave: { apiKey: "brv-..." }
}
}
```
Load the environment before starting services that use the Agent:
Example `skills.env.json5` (dynamic keys):
```json5
{
env: {
LINEAR_API_KEY: "lin-...",
SLACK_BOT_TOKEN: "xoxb-..."
}
}
```
Start services directly (no `source .env`):
```bash
# Hub Console (requires LLM env vars)
source .env && pnpm dev:console
# Agent CLI
source .env && pnpm agent:cli "hello"
# Gateway (no LLM env vars needed)
pnpm dev:console
pnpm agent:cli "hello"
pnpm dev:gateway
```
See `.env.example` for all supported providers (OpenAI, Anthropic, DeepSeek, Kimi, Groq, Mistral, etc.).
Optional overrides:
- `SMC_CREDENTIALS_PATH` — custom path for `credentials.json5`
- `SMC_SKILLS_ENV_PATH` — custom path for `skills.env.json5`
### Configuration Priority
Each setting is resolved in order (first match wins):
1. **CLI argument** — `--provider`, `--model`, `--api-key`, `--base-url`
2. **Environment variable** — `LLM_PROVIDER`, `OPENAI_MODEL`, `OPENAI_API_KEY`, `OPENAI_BASE_URL`, etc.
2. **Credentials file** — `credentials.json5` (`llm.provider` + `llm.providers[provider]`)
3. **Session metadata** — restored from previous session
4. **Default** — `kimi-coding` provider with `kimi-k2-thinking` model