Prompts Encode

GPTClaudeDeepSeek··▲ 1,080 copies·updated 2026-07-14

prompts-encode.prompt

# `prompts_encode`

Purpose-built encoder for chat-style prompts. It detects nested JSON, schemas, and metadata automatically.

## Parameters

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `prompt` | `Any` | ✅ | Chat payload (`messages`, `tools`, `metadata`, etc.). |
| `options` | `EncodeOptions` | ❌ | Same tuning knobs as `compress`. |
| `auto_detect_json` | `bool` | ❌ (default `True`) | Detect JSON fragments embedded inside strings. |
| `schemas` | `dict[str, Any]` | ❌ | Supply JSON Schemas to help Kaizen segment structured fields. |
| `metadata` | `dict[str, Any]` | ❌ | Arbitrary observability data echoed in responses. |
| `token_models` | `list[str]` | ❌ | Request model-specific token stats. |

## Code example

when to use it

Community prompt sourced from the open-source GitHub repo getkaizen/kaizen-sdk (Apache-2.0). A "Prompts Encode" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.