fix: fix server terminology with mode aliases (#277)

This commit is contained in:
Charles Packer
2026-02-10 20:34:29 -08:00
committed by GitHub
parent 83569d968e
commit de1adcf4fe
21 changed files with 198 additions and 133 deletions

View File

@@ -5,7 +5,7 @@ LettaBot is a multi-channel AI assistant powered by [Letta](https://letta.com) t
## Guides
- [Getting Started](./getting-started.md) - Installation and basic setup
- [Self-Hosted Setup](./selfhosted-setup.md) - Run with your own Letta server
- [Docker Server Setup](./selfhosted-setup.md) - Run with your own Letta server
- [Configuration Reference](./configuration.md) - All config options
- [Commands Reference](./commands.md) - Bot commands reference
- [CLI Tools](./cli-tools.md) - Agent/operator CLI tools
@@ -62,7 +62,7 @@ LettaBot uses a **single agent with unified memory** across all channels:
┌──────────────────────────┐
│ Letta Server │
│ (api.letta.com or │
self-hosted Docker)
Docker/custom)
│ │
│ • Agent Memory │
│ • LLM Inference │

View File

@@ -21,8 +21,8 @@ For global installs (`npm install -g`), either:
```yaml
# Server connection
server:
mode: cloud # 'cloud' or 'selfhosted'
apiKey: letta_... # Required for cloud mode
mode: api # 'api' or 'docker' (legacy: 'cloud'/'selfhosted')
apiKey: letta_... # Required for api mode
# Agent settings (single agent mode)
# For multiple agents, use `agents:` array instead -- see Multi-Agent section
@@ -98,15 +98,15 @@ api:
| Option | Type | Description |
|--------|------|-------------|
| `server.mode` | `'cloud'` \| `'selfhosted'` | Connection mode |
| `server.apiKey` | string | API key for Letta Cloud |
| `server.baseUrl` | string | URL for self-hosted server (e.g., `http://localhost:8283`) |
| `server.mode` | `'api'` \| `'docker'` | Connection mode (legacy aliases: `'cloud'`, `'selfhosted'`) |
| `server.apiKey` | string | API key for Letta API |
| `server.baseUrl` | string | URL for Docker/custom server (e.g., `http://localhost:8283`) |
### Self-Hosted Mode
### Docker Server Mode
```yaml
server:
mode: selfhosted
mode: docker
baseUrl: http://localhost:8283
```
@@ -142,7 +142,7 @@ Use the `agents:` array instead of the top-level `agent:` and `channels:` keys:
```yaml
server:
mode: cloud
mode: api
apiKey: letta_...
agents:

View File

@@ -17,7 +17,7 @@ Deploy LettaBot to [Railway](https://railway.app) for always-on hosting.
| Variable | Description |
|----------|-------------|
| `LETTA_API_KEY` | Your Letta Cloud API key ([get one here](https://app.letta.com)) |
| `LETTA_API_KEY` | Your Letta API key ([get one here](https://app.letta.com)) |
### Channel Configuration (at least one required)
@@ -59,7 +59,7 @@ SLACK_APP_TOKEN=xapp-...
On startup, LettaBot:
1. Checks for `LETTA_AGENT_ID` env var - uses if set
2. Otherwise, searches Letta Cloud for an agent named `LETTA_AGENT_NAME` (or legacy `AGENT_NAME`, default: "LettaBot")
2. Otherwise, searches Letta API for an agent named `LETTA_AGENT_NAME` (or legacy `AGENT_NAME`, default: "LettaBot")
3. If found, uses the existing agent (preserves memory!)
4. If not found, creates a new agent on first message

View File

@@ -1,6 +1,6 @@
# Self-Hosted Letta Server Setup
# Docker Server Setup
Run LettaBot with your own Letta server instead of Letta Cloud.
Run LettaBot with your own Letta Docker/custom server instead of Letta API.
## Prerequisites
@@ -42,7 +42,7 @@ curl http://localhost:8283/v1/health
lettabot onboard
```
Select "Enter self-hosted URL" and enter `http://localhost:8283`.
Select "Enter Docker server URL" and enter `http://localhost:8283`.
### Option B: Manual Configuration
@@ -50,7 +50,7 @@ Create `lettabot.yaml`:
```yaml
server:
mode: selfhosted
mode: docker
baseUrl: http://localhost:8283
# apiKey: optional-if-server-requires-auth
@@ -79,7 +79,7 @@ lettabot server
You should see:
```
[Config] Loaded from /path/to/lettabot.yaml
[Config] Mode: selfhosted, Agent: LettaBot, Model: gpt-4o
[Config] Mode: docker, Agent: LettaBot, Model: gpt-4o
Starting LettaBot...
LettaBot initialized. Agent ID: (new)
[Telegram] Bot started as @YourBotName