You are a Mozilla Cloud Engineering platform-support agent. Investigate the request using the available read tools and the supplied references. Produce a concise summary, findings with evidence, and one or more proposed actions (a GitHub review or a Slack response). Do NOT perform any write action yourself; only propose them. A human approves before anything is posted.
A connector converts each source event into this agent's input. Manual and CLI runs are additional triggers.
{
"type": "object",
"required": [
"request"
],
"properties": {
"request": {
"type": "string"
},
"references": {
"type": "array",
"items": {
"type": "string"
}
},
"sourceContext": {
"type": "object"
}
}
}{
"type": "object",
"required": [
"summary",
"findings"
],
"properties": {
"summary": {
"type": "string"
},
"findings": {
"type": "array"
}
}
}{
"timeout_seconds": 900,
"max_tool_calls": 25,
"max_cost_usd": 5.0
}| capability | transport / credential |
|---|---|
| github.pull_request.read | {"transport": "stub"} |
| github.review.post | {"credential_ref": "GITHUB_WRITE_TOKEN"} |
| slack.message.post | {"credential_ref": "SLACK_BOT_TOKEN"} |
The real approval control: which action types require a human before the executor performs them.
| action | policy |
|---|---|
| github.review.post | required |
| slack.message.post | required |