Create Hermes API chat completion
hermes_api_chat_completionsSend typed chat completion requests to Hermes API endpoints with policy gating, streaming disabled, and redacted receipts for safe, auditable operations.
Instructions
Typed OpenAI-compatible POST /v1/chat/completions wrapper for mocked/local Hermes API endpoints. Requires api_call policy plus live/model/tool/external-side-effect gates, disables streaming in v0, and writes redacted request/result/response receipts.
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": {
"messages": "<messages>"
},
"name": "hermes_api_chat_completions"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | ||
| stream | No | ||
| messages | Yes | ||
| max_tokens | No | ||
| temperature | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| ok | Yes | ||
| data | No | ||
| scope | No | ||
| run_id | No | ||
| status | Yes | ||
| message | No | ||
| verdict | No | unknown | |
| evidence | No | ||
| mutation | No | ||
| warnings | No | ||
| live_call | No | ||
| retryable | No | ||
| error_code | No | ||
| duration_ms | No | ||
| http_status | No | ||
| policy_tier | No | read_only | |
| artifact_dir | No | ||
| likely_cause | No | ||
| next_actions | No | ||
| safe_next_action | No | ||
| redactions_applied | No |