From c4d85dc04568d6ec6f248241d24d62bb7d4daa79 Mon Sep 17 00:00:00 2001 From: Peter Steinberger Date: Mon, 12 Jan 2026 05:49:02 +0000 Subject: [PATCH] docs: refresh minimax setup docs --- CHANGELOG.md | 4 +- docs/cli/index.md | 2 +- docs/concepts/model-providers.md | 3 +- docs/gateway/configuration.md | 30 ++-------- docs/providers/minimax.md | 96 ++++---------------------------- docs/start/wizard.md | 3 +- 6 files changed, 24 insertions(+), 114 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index ec7a52e5b..61188eba6 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -9,7 +9,9 @@ - Agents: automatic pre-compaction memory flush turn to store durable memories before compaction. ### Changes -- CLI: simplify configure section selection (single-select with optional add-more). +- CLI/Onboarding: simplify MiniMax auth choice to a single M2.1 option. +- CLI: configure section selection now loops until Continue. +- Docs: explain MiniMax vs MiniMax Lightning (speed vs cost). - Onboarding/CLI: group model/auth choice by provider and label Z.AI as GLM 4.7. - Auto-reply: add compact `/model` picker (models + available providers) and show provider endpoints in `/model status`. - Plugins: add extension loader (tools/RPC/CLI/services), discovery paths, and config schema + Control UI labels (uiHints). diff --git a/docs/cli/index.md b/docs/cli/index.md index afcae3ae8..b57e36dd3 100644 --- a/docs/cli/index.md +++ b/docs/cli/index.md @@ -221,7 +221,7 @@ Options: - `--non-interactive` - `--mode ` - `--flow ` -- `--auth-choice ` +- `--auth-choice ` - `--token-provider ` (non-interactive; used with `--auth-choice token`) - `--token ` (non-interactive; used with `--auth-choice token`) - `--token-profile-id ` (non-interactive; default: `:manual`) diff --git a/docs/concepts/model-providers.md b/docs/concepts/model-providers.md index 944840111..18979e972 100644 --- a/docs/concepts/model-providers.md +++ b/docs/concepts/model-providers.md @@ -112,8 +112,7 @@ OpenAI/Anthropic‑compatible proxies. MiniMax is configured via `models.providers` because it uses custom endpoints: -- MiniMax (Anthropic‑compatible): `--auth-choice minimax-cloud` - - `--auth-choice minimax-api` is a legacy alias. +- MiniMax (Anthropic‑compatible): `--auth-choice minimax-api` - Auth: `MINIMAX_API_KEY` See [/providers/minimax](/providers/minimax) for setup details, model options, and config snippets. diff --git a/docs/gateway/configuration.md b/docs/gateway/configuration.md index 0b6c1654f..a270b5655 100644 --- a/docs/gateway/configuration.md +++ b/docs/gateway/configuration.md @@ -1807,9 +1807,9 @@ Notes: - Responses API enables clean reasoning/output separation; WhatsApp sees only final text. - Adjust `contextWindow`/`maxTokens` if your LM Studio context length differs. -### MiniMax API (platform.minimax.io) +### MiniMax M2.1 -Use MiniMax's Anthropic-compatible API directly without LM Studio: +Use MiniMax M2.1 directly without LM Studio: ```json5 { @@ -1833,25 +1833,7 @@ Use MiniMax's Anthropic-compatible API directly without LM Studio: name: "MiniMax M2.1", reasoning: false, input: ["text"], - // Pricing: MiniMax doesn't publish public rates. Override in models.json for accurate costs. - cost: { input: 15, output: 60, cacheRead: 2, cacheWrite: 10 }, - contextWindow: 200000, - maxTokens: 8192 - }, - { - id: "MiniMax-M2.1-lightning", - name: "MiniMax M2.1 Lightning", - reasoning: false, - input: ["text"], - cost: { input: 15, output: 60, cacheRead: 2, cacheWrite: 10 }, - contextWindow: 200000, - maxTokens: 8192 - }, - { - id: "MiniMax-M2", - name: "MiniMax M2", - reasoning: true, - input: ["text"], + // Pricing: update in models.json if you need exact cost tracking. cost: { input: 15, output: 60, cacheRead: 2, cacheWrite: 10 }, contextWindow: 200000, maxTokens: 8192 @@ -1864,9 +1846,9 @@ Use MiniMax's Anthropic-compatible API directly without LM Studio: ``` Notes: -- Set `MINIMAX_API_KEY` environment variable or use `clawdbot onboard --auth-choice minimax-cloud` -- Available models: `MiniMax-M2.1` (default), `MiniMax-M2.1-lightning` (~100 tps), `MiniMax-M2` (reasoning) -- Pricing is a placeholder; MiniMax doesn't publish public rates. Override in `models.json` for accurate cost tracking. +- Set `MINIMAX_API_KEY` environment variable or use `clawdbot onboard --auth-choice minimax-api`. +- Available model: `MiniMax-M2.1` (default). +- Update pricing in `models.json` if you need exact cost tracking. Notes: - Supported APIs: `openai-completions`, `openai-responses`, `anthropic-messages`, diff --git a/docs/providers/minimax.md b/docs/providers/minimax.md index 98d91dc25..1e0896521 100644 --- a/docs/providers/minimax.md +++ b/docs/providers/minimax.md @@ -1,8 +1,8 @@ --- -summary: "Use MiniMax M2.1 in Clawdbot (cloud, API, or LM Studio)" +summary: "Use MiniMax M2.1 in Clawdbot" read_when: - You want MiniMax models in Clawdbot - - You need MiniMax cloud/API setup or LM Studio config + - You need MiniMax setup guidance --- # MiniMax @@ -25,16 +25,21 @@ MiniMax highlights these improvements in M2.1: Droid/Factory AI, Cline, Kilo Code, Roo Code, BlackBox). - Higher-quality **dialogue and technical writing** outputs. +## MiniMax M2.1 vs MiniMax M2.1 Lightning + +- **Speed:** MiniMax docs list ~60 tps output for M2.1 and ~100 tps for Lightning. +- **Cost:** Pricing shows the same input cost, but Lightning has higher output cost. + ## Choose a setup -### Option A: MiniMax (Anthropic-compatible `/anthropic`) — recommended +### MiniMax M2.1 — recommended **Best for:** hosted MiniMax with Anthropic-compatible API. Configure via CLI: - Run `clawdbot configure` - Select **Model/auth** -- Choose **MiniMax M2.1 (minimax.io)** +- Choose **MiniMax M2.1** ```json5 { @@ -64,89 +69,13 @@ Configure via CLI: } ``` -### Option B: MiniMax OpenAI-compatible `/v1` (manual) - -**Best for:** setups that require OpenAI-compatible payloads. - -```json5 -{ - env: { MINIMAX_API_KEY: "sk-..." }, - agents: { defaults: { model: { primary: "minimax/MiniMax-M2.1" } } }, - models: { - mode: "merge", - providers: { - minimax: { - baseUrl: "https://api.minimax.io/v1", - apiKey: "${MINIMAX_API_KEY}", - api: "openai-completions", - models: [ - { - id: "MiniMax-M2.1", - name: "MiniMax M2.1", - reasoning: false, - input: ["text"], - cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }, - contextWindow: 200000, - maxTokens: 8192 - } - ] - } - } - } -} -``` - -### Option C: Local via LM Studio - -**Best for:** local inference with LM Studio. -We have seen strong results with MiniMax M2.1 on powerful hardware (e.g. a -desktop/server) using LM Studio's local server. - -Configure via CLI: -- Run `clawdbot configure` -- Select **Model/auth** -- Choose **MiniMax M2.1 (LM Studio)** - -```json5 -{ - agents: { - defaults: { - model: { primary: "lmstudio/minimax-m2.1-gs32" }, - models: { "lmstudio/minimax-m2.1-gs32": { alias: "Minimax" } } - } - }, - models: { - mode: "merge", - providers: { - lmstudio: { - baseUrl: "http://127.0.0.1:1234/v1", - apiKey: "lmstudio", - api: "openai-responses", - models: [ - { - id: "minimax-m2.1-gs32", - name: "MiniMax M2.1 GS32", - reasoning: false, - input: ["text"], - cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }, - contextWindow: 196608, - maxTokens: 8192 - } - ] - } - } - } -} -``` - ## Configure via `clawdbot configure` Use the interactive config wizard to set MiniMax without editing JSON: 1) Run `clawdbot configure`. 2) Select **Model/auth**. -3) Choose **MiniMax M2.1 (minimax.io)**, **MiniMax API (platform.minimax.io)**, - or **MiniMax M2.1 (LM Studio)**. +3) Choose **MiniMax M2.1**. 4) Pick your default model when prompted. ## Configuration options @@ -160,8 +89,7 @@ Use the interactive config wizard to set MiniMax without editing JSON: ## Notes -- Model refs are `minimax/` or `lmstudio/`. -- MiniMax pricing is not published; the costs above are placeholders. - Override in `models.json` for accurate tracking. +- Model refs are `minimax/`. +- Update pricing values in `models.json` if you need exact cost tracking. - See [/concepts/model-providers](/concepts/model-providers) for provider rules. - Use `clawdbot models list` and `clawdbot models set minimax/MiniMax-M2.1` to switch. diff --git a/docs/start/wizard.md b/docs/start/wizard.md index cc98f22e6..89f86e0d9 100644 --- a/docs/start/wizard.md +++ b/docs/start/wizard.md @@ -80,8 +80,7 @@ Tip: `--json` does **not** imply non-interactive mode. Use `--non-interactive` ( - **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_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 Anthropic-compatible `/anthropic` endpoint. - - **MiniMax M2.1 (LM Studio)**: config is auto‑written for the LM Studio endpoint. + - **MiniMax M2.1**: config is auto‑written. - More detail: [MiniMax](/providers/minimax) - **Skip**: no auth configured yet. - Pick a default model from detected options (or enter provider/model manually).