CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

model-switch

Switch the Manager Agent's own LLM model. Use when the human admin requests changing the Manager's model.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Model Switch

Switch the Manager's own LLM model. The script tests connectivity first, then patches openclaw.json.

Usage

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-reasoning

What the script does

  1. Strips any agentteams-gateway/ prefix from the model name
  2. Tests the model via POST /v1/chat/completions on the AI Gateway — exits with error if unreachable
  3. If the model is already in the models array: refreshes its reasoning / contextWindow / maxTokens / input fields and switches agents.defaults.model.primary
  4. If the model is new: adds it to the models array and switches primary
  5. Outputs the apply/verification instructions for your Manager runtime

Because 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.

After running the script

Follow the instructions for your AGENTTEAMS_MANAGER_RUNTIME:

  • OpenClaw: run openclaw gateway restart, then verify the active model.
  • QwenPaw: the script updates the standard 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.
  • Legacy CoPaw: follow the 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.

Reasoning control

By default, reasoning (extended thinking) is enabled. To disable it, pass --no-reasoning.

On failure

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:

  1. The model is not reachable because the current default AI Provider likely does not support it.
  2. They need to open the Higress Console and:
    • Create a new AI Provider for the model's vendor (e.g. kimi, deepseek, minimax).
    • Create a new AI Route with a model name prefix predicate (e.g. provider 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.
  3. Do NOT modify the default AI Provider — it is managed by the initialization config and will be overwritten on restart.

After the admin confirms the provider and route are configured, you can retry the model-switch script.

Important

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.

Switching to an unknown model

When the human admin requests switching to a model you don't recognize, you MUST:

  1. Ask the admin two questions before running the script:
    • "This model is not in the known list. What is its context window size (in tokens)?"
    • "Does this model support reasoning (extended thinking)?"
  2. Run the script with the appropriate flags:
    bash /opt/agentteams/agent/skills/model-switch/scripts/update-manager-model.sh <MODEL_ID> --context-window <SIZE> [--no-reasoning]
  3. If the admin does not know the context window, use the default (150,000) by omitting --context-window.
  4. If the model does not support reasoning, add --no-reasoning.

Pre-configured models (for reference)

ModelcontextWindowmaxTokens
gpt-5.41,050,000128,000
gpt-5.3-codex / gpt-5-mini / gpt-5-nano400,000128,000
claude-opus-4-61,000,000128,000
claude-sonnet-4-61,000,00064,000
claude-haiku-4-5200,00064,000
qwen3.5-plus200,00064,000
deepseek-chat / deepseek-reasoner / kimi-k2.5256,000128,000
glm-5 / MiniMax-M2.7 / MiniMax-M2.7-highspeed / MiniMax-M2.5200,000128,000
Repository

agentscope-ai/AgentTeams

Path

manager/agent/skills/model-switch/SKILL.md

Last updated
First committed

Is this your skill?

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.