let5see/clawdbot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: align opencode-zen provider setup

Browse Source
This commit is contained in:
Peter Steinberger
2026-01-10 21:37:38 +01:00
parent 46e00ad5e7
commit 8a194b4abc
16 changed files with 263 additions and 96 deletions
Download Patch File Download Diff File Expand all files Collapse all files

162
docs/concepts/model-providers.md Normal file
View File

@@ -0,0 +1,162 @@
---
summary: "Model provider overview with example configs + CLI flows"
read_when:
- You need a provider-by-provider model setup reference
- You want example configs or CLI onboarding commands for model providers
---
# Model providers
This page covers **LLM/model providers** (not chat providers like WhatsApp/Telegram).
For model selection rules, see [/concepts/models](/concepts/models).
## Quick rules
- Model refs use `provider/model` (example: `opencode/claude-opus-4-5`).
- If you set `agents.defaults.models`, it becomes the allowlist.
- CLI helpers: `clawdbot onboard`, `clawdbot models list`, `clawdbot models set <provider/model>`.
## Built-in providers (pi-ai catalog)
Clawdbot ships with the pi‑ai catalog. These providers require **no**
`models.providers` config; just set auth + pick a model.
### OpenAI
- Provider: `openai`
- Auth: `OPENAI_API_KEY`
- Example model: `openai/gpt-5.2`
- CLI: `clawdbot onboard --auth-choice openai-api-key`
```json5
{
agents: { defaults: { model: { primary: "openai/gpt-5.2" } } }
}
```
### Anthropic
- Provider: `anthropic`
- Auth: `ANTHROPIC_API_KEY` or `claude setup-token`
- Example model: `anthropic/claude-opus-4-5`
- CLI: `clawdbot onboard --auth-choice setup-token`
```json5
{
agents: { defaults: { model: { primary: "anthropic/claude-opus-4-5" } } }
}
```
### OpenAI Code (Codex)
- Provider: `openai-codex`
- Auth: OAuth or Codex CLI (`~/.codex/auth.json`)
- Example model: `openai-codex/gpt-5.2`
- CLI: `clawdbot onboard --auth-choice openai-codex` or `codex-cli`
```json5
{
agents: { defaults: { model: { primary: "openai-codex/gpt-5.2" } } }
}
```
### OpenCode Zen
- Provider: `opencode`
- Auth: `OPENCODE_API_KEY` (or `OPENCODE_ZEN_API_KEY`)
- Example model: `opencode/claude-opus-4-5`
- CLI: `clawdbot onboard --auth-choice opencode-zen`
```json5
{
agents: { defaults: { model: { primary: "opencode/claude-opus-4-5" } } }
}
```
### Google Gemini (API key)
- Provider: `google`
- Auth: `GEMINI_API_KEY`
- Example model: `google/gemini-3-pro`
- CLI: `clawdbot onboard --auth-choice gemini-api-key`
### Google Vertex / Antigravity / Gemini CLI
- Providers: `google-vertex`, `google-antigravity`, `google-gemini-cli`
- Auth: Vertex uses gcloud ADC; Antigravity/Gemini CLI use their respective auth flows
- CLI: `clawdbot onboard --auth-choice antigravity` (others via interactive wizard)
### Z.AI (GLM)
- Provider: `zai`
- Auth: `ZAI_API_KEY`
- Example model: `zai/glm-4.7`
- CLI: `clawdbot onboard --auth-choice zai-api-key`
- Aliases: `z.ai/*` and `z-ai/*` normalize to `zai/*`
### Other built-in providers
- OpenRouter: `openrouter` (`OPENROUTER_API_KEY`)
- Example model: `openrouter/anthropic/claude-sonnet-4-5`
- xAI: `xai` (`XAI_API_KEY`)
- Groq: `groq` (`GROQ_API_KEY`)
- Cerebras: `cerebras` (`CEREBRAS_API_KEY`)
- Mistral: `mistral` (`MISTRAL_API_KEY`)
- GitHub Copilot: `github-copilot` (`COPILOT_GITHUB_TOKEN` / `GH_TOKEN` / `GITHUB_TOKEN`)
## Providers via `models.providers` (custom/base URL)
Use `models.providers` (or `models.json`) to add **custom** providers or
OpenAI/Anthropic‑compatible proxies.
### MiniMax
MiniMax is configured via `models.providers` because it uses custom endpoints:
- MiniMax Cloud (OpenAI‑compatible): `--auth-choice minimax-cloud`
- MiniMax API (Anthropic‑compatible): `--auth-choice minimax-api`
- Auth: `MINIMAX_API_KEY`
### Local proxies (LM Studio, vLLM, LiteLLM, etc.)
Example (OpenAI‑compatible):
```json5
{
agents: {
defaults: {
model: { primary: "lmstudio/minimax-m2.1-gs32" },
models: { "lmstudio/minimax-m2.1-gs32": { alias: "Minimax" } }
}
},
models: {
providers: {
lmstudio: {
baseUrl: "http://localhost:1234/v1",
apiKey: "LMSTUDIO_KEY",
api: "openai-completions",
models: [
{
id: "minimax-m2.1-gs32",
name: "MiniMax M2.1",
reasoning: false,
input: ["text"],
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
contextWindow: 200000,
maxTokens: 8192
}
]
}
}
}
}
```
## CLI examples
```bash
clawdbot onboard --auth-choice opencode-zen
clawdbot models set opencode/claude-opus-4-5
clawdbot models list
```
See also: [/gateway/configuration](/gateway/configuration) for full configuration examples.

1
docs/concepts/models.md
View File

@@ -9,6 +9,7 @@ read_when:
See [/concepts/model-failover](/concepts/model-failover) for auth profile
rotation, cooldowns, and how that interacts with fallbacks.
Quick provider overview + examples: [/concepts/model-providers](/concepts/model-providers).
## How model selection works

16
docs/docs.json
View File

@@ -580,6 +580,7 @@
"group": "Install & Updates",
"pages": [
"install/updating",
"install/ansible",
"install/nix",
"install/docker",
"install/bun"
@@ -589,7 +590,9 @@
"group": "CLI",
"pages": [
"cli/index",
"cli/message",
"cli/gateway",
"cli/update",
"cli/sandbox"
]
},
@@ -612,12 +615,16 @@
"concepts/presence",
"concepts/provider-routing",
"concepts/messages",
"concepts/streaming",
"concepts/groups",
"concepts/group-messages",
"concepts/typing-indicators",
"concepts/queue",
"concepts/retry",
"concepts/model-providers",
"concepts/models",
"concepts/model-failover",
"concepts/usage-tracking",
"concepts/timezone",
"concepts/typebox"
]
@@ -628,6 +635,7 @@
"gateway",
"gateway/pairing",
"gateway/gateway-lock",
"environment",
"gateway/configuration",
"gateway/configuration-examples",
"gateway/authentication",
@@ -637,7 +645,10 @@
"gateway/doctor",
"gateway/logging",
"gateway/security",
"gateway/sandbox-vs-tool-policy-vs-elevated",
"gateway/sandboxing",
"gateway/troubleshooting",
"debugging",
"gateway/remote",
"gateway/remote-gateway-readme",
"gateway/discovery",
@@ -659,12 +670,15 @@
"group": "Providers",
"pages": [
"providers/whatsapp",
"broadcast-groups",
"providers/telegram",
"providers/grammy",
"providers/discord",
"providers/slack",
"providers/signal",
"providers/imessage",
"providers/msteams",
"providers/troubleshooting",
"providers/location"
]
},
@@ -690,6 +704,8 @@
"tools/thinking",
"tools/agent-send",
"tools/subagents",
"multi-agent-sandbox-tools",
"tools/reactions",
"tools/skills",
"tools/skills-config",
"tools/clawdhub"

32
docs/gateway/configuration.md
View File

@@ -1423,6 +1423,7 @@ Clawdbot uses the **pi-coding-agent** model catalog. You can add custom provider
(LiteLLM, local OpenAI-compatible servers, Anthropic proxies, etc.) by writing
`~/.clawdbot/agents/<agentId>/agent/models.json` or by defining the same schema inside your
Clawdbot config under `models.providers`.
Provider-by-provider overview + examples: [/concepts/model-providers](/concepts/model-providers).
When `models.providers` is present, Clawdbot writes/merges a `models.json` into
`~/.clawdbot/agents/<agentId>/agent/` on startup:
@@ -1467,10 +1468,12 @@ Select the model via `agents.defaults.model.primary` (provider/model).
### OpenCode Zen (multi-model proxy)
OpenCode Zen is an OpenAI-compatible proxy at `https://opencode.ai/zen/v1`. Get an API key at https://opencode.ai/auth and set `OPENCODE_ZEN_API_KEY`.
OpenCode Zen is a multi-model gateway with per-model endpoints. Clawdbot uses
the built-in `opencode` provider from pi-ai; set `OPENCODE_API_KEY` (or
`OPENCODE_ZEN_API_KEY`) from https://opencode.ai/auth.
Notes:
- Model refs use `opencode-zen/<modelId>` (example: `opencode-zen/claude-opus-4-5`).
- Model refs use `opencode/<modelId>` (example: `opencode/claude-opus-4-5`).
- If you enable an allowlist via `agents.defaults.models`, add each model you plan to use.
- Shortcut: `clawdbot onboard --auth-choice opencode-zen`.
@@ -1478,29 +1481,8 @@ Notes:
{
agents: {
defaults: {
model: { primary: "opencode-zen/claude-opus-4-5" },
models: { "opencode-zen/claude-opus-4-5": { alias: "Opus" } }
}
},
models: {
mode: "merge",
providers: {
"opencode-zen": {
baseUrl: "https://opencode.ai/zen/v1",
apiKey: "${OPENCODE_ZEN_API_KEY}",
api: "openai-completions",
models: [
{
id: "claude-opus-4-5",
name: "Claude Opus 4.5",
reasoning: true,
input: ["text", "image"],
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
contextWindow: 200000,
maxTokens: 32000
}
]
}
model: { primary: "opencode/claude-opus-4-5" },
models: { "opencode/claude-opus-4-5": { alias: "Opus" } }
}
}
}

4
docs/start/wizard.md
View File

@@ -78,7 +78,7 @@ Tip: `--json` does **not** imply non-interactive mode. Use `--non-interactive` (
- **OpenAI Code (Codex) subscription (OAuth)**: browser flow; paste the `code#state`.
- Sets `agents.defaults.model` to `openai-codex/gpt-5.2` when model is unset or `openai/*`.
- **OpenAI API key**: uses `OPENAI_API_KEY` if present or prompts for a key, then saves it to `~/.clawdbot/.env` so launchd can read it.
- **OpenCode Zen (multi-model proxy)**: prompts for `OPENCODE_ZEN_API_KEY` (get it at https://opencode.ai/auth).
- **OpenCode Zen (multi-model proxy)**: prompts for `OPENCODE_API_KEY` (or `OPENCODE_ZEN_API_KEY`, get it at https://opencode.ai/auth).
- **API key**: stores the key for you.
- **MiniMax M2.1 (minimax.io)**: config is auto‑written for the OpenAI-compatible `/v1` endpoint.
- **MiniMax API (platform.minimax.io)**: config is auto‑written for the Anthropic-compatible `/anthropic` endpoint.
@@ -205,7 +205,7 @@ OpenCode Zen example:
clawdbot onboard --non-interactive \
--mode local \
--auth-choice opencode-zen \
--opencode-zen-api-key "$OPENCODE_ZEN_API_KEY" \
--opencode-zen-api-key "$OPENCODE_API_KEY" \
--gateway-port 18789 \
--gateway-bind loopback
```