Switch the Manager Agent's own LLM model. Use when the human admin requests changing the Manager's model.
85%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Switch the Manager's own LLM model. The script tests connectivity first, then patches openclaw.json.
bash /opt/agentteams/agent/skills/model-switch/scripts/update-manager-model.sh <MODEL_ID> [--context-window <SIZE>] [--no-reasoning]Examples:
bash /opt/agentteams/agent/skills/model-switch/scripts/update-manager-model.sh claude-sonnet-4-6
bash /opt/agentteams/agent/skills/model-switch/scripts/update-manager-model.sh my-custom-model --context-window 300000
bash /opt/agentteams/agent/skills/model-switch/scripts/update-manager-model.sh deepseek-chat --no-reasoningagentteams-gateway/ prefix from the model namePOST /v1/chat/completions on the AI Gateway — exits with error if unreachablemodels array: refreshes its reasoning / contextWindow / maxTokens / input fields and switches agents.defaults.model.primarymodels array and switches primaryBecause step 3 rewrites the model's fields, re-running the script is the way to
correct an entry that was first written with wrong values — for example a model
that was added with the 150,000 default because nobody knew its real window:
run the script again with --context-window <SIZE> and the new value lands in
openclaw.json.
Follow the instructions for your AGENTTEAMS_MANAGER_RUNTIME:
openclaw gateway restart, then verify the active model.openclaw.json consumed by your existing background bridge. Wait for its next watcher cycle (normally within 60 seconds). Read back active_llm.provider_id and active_llm.model from your native secret providers.json (honor QWENPAW_SECRET_DIR), and verify your next request uses the requested model before reporting completion. A CONFIG_UPDATED message alone confirms the standard file was written. If the native state stays stale, inspect your bridge logs and report the pending apply step.RESTART_REQUIRED instruction to restart your CoPaw service.For QwenPaw, verify context and reasoning settings in your native runtime separately; writing these fields to the standard config does not prove every option is supported or applied.
By default, reasoning (extended thinking) is enabled. To disable it, pass --no-reasoning.
If the gateway test fails (non-200), the script outputs ERROR: MODEL_NOT_REACHABLE and exits. No changes are made to openclaw.json.
When you see this error, tell the human admin clearly:
kimi, deepseek, minimax).kimi → match kimi-*), so that requests for models with that prefix are routed to the new provider, while unmatched models continue to go through the default route.After the admin confirms the provider and route are configured, you can retry the model-switch script.
You switch your primary model persistently through the standard config. Follow your runtime-specific apply and verification steps above. With OpenClaw, the human admin can also use /model to switch the current session instantly; that does not persist the primary model and only supports pre-configured models.
When the human admin requests switching to a model you don't recognize, you MUST:
bash /opt/agentteams/agent/skills/model-switch/scripts/update-manager-model.sh <MODEL_ID> --context-window <SIZE> [--no-reasoning]--context-window.--no-reasoning.| Model | contextWindow | maxTokens |
|---|---|---|
| gpt-5.4 | 1,050,000 | 128,000 |
| gpt-5.3-codex / gpt-5-mini / gpt-5-nano | 400,000 | 128,000 |
| claude-opus-4-6 | 1,000,000 | 128,000 |
| claude-sonnet-4-6 | 1,000,000 | 64,000 |
| claude-haiku-4-5 | 200,000 | 64,000 |
| qwen3.5-plus | 200,000 | 64,000 |
| deepseek-chat / deepseek-reasoner / kimi-k2.5 | 256,000 | 128,000 |
| glm-5 / MiniMax-M2.7 / MiniMax-M2.7-highspeed / MiniMax-M2.5 | 200,000 | 128,000 |
agentscope-ai/AgentTeams
bc2c064
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.