Start a yaver code --mesh run: plan → implement → verify chat chain across the available machine pool. Thin wrapper over agent_graph_start with defaults matching the yaver code CLI (template=full, max_parallel=2). Shared-infra machines borrowed from other hosts are automatically considered by the...
AI agents invoke code_mesh_start to trigger actions in Yaver. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | — | Optional session name |
nodes | array | — | Optional explicit nodes. If omitted, the standard plan → implement → verify template is used. |
prompt | string | Yes | What you want built. |
work_dir | string | — | Absolute work directory. Defaults to the current agent work dir. |
max_parallel | integer | — | Maximum concurrently running nodes (default 2) |
allowed_devices | array | — | Optional machine ids or names to form the execution pool |
allowed_runners | array | — | Optional runner IDs to allow (e.g. ollama,opencode,codex) |
Parameters from the server's own tool schema.
code_mesh_start triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsHigh parameter count (28 properties)
Attacks that exploit this kind of access
Start a yaver code --mesh run: plan → implement → verify chat chain across the available machine pool. Thin wrapper over agent_graph_start with defaults matching the yaver code CLI (template=full, max_parallel=2). Shared-infra machines borrowed from other hosts are automatically considered by the placement planner; use allowed_runners when a shared machine only permits local runners like ollama. Optional custom nodes can request build, deploy, browser, simulator, phone, proof-video, and video-summary self-hosted resources. It is categorised as a Execute tool in the Yaver MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
code_mesh_start accepts 7 parameters: name, nodes, prompt, work_dir, max_parallel, allowed_devices, allowed_runners. Required: prompt. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for code_mesh_start: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Yaver. Nothing to install.
code_mesh_start is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the code_mesh_start rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for code_mesh_start. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
code_mesh_start is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.