Jev coding-loop router
jev_coding_loopDetermine next coding action and model tier before retry or stop. Returns continue, retry, ask_user, or stop with risk, focus, and verification flags from the current task and observation.
Instructions
Call before spending a frontier turn on retry/stop/model-tier. One Jev fan-out returns next (continue|retry|ask_user|stop), model_tier (cheap|standard|reasoning), risk, focus, and noul flags done_enough / needs_more_context / tests_likely_fail. Policy in code maps confidence to action auto|review|escalate. Does not edit files.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"task": "<task>",
"observation": "<observation>"
},
"name": "jev_coding_loop"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| task | Yes | What the coding agent is trying to do | |
| model | No | ||
| extras | No | Optional extra JSON fields included in Jev state | |
| review_at | No | ||
| auto_accept | No | ||
| observation | Yes | Current turn: last diff, command output, test results, or blocker |