NeuralTrust | Platform for Agent Security.

Prompt Management catalog policies reshape the LLM request body on pre_request. Create them under Policies → Catalog, or attach them from a consumer Policies tab. Scope each policy gateway-wide or targeted.

Policy in the catalog	Slug	What it does
Prompt Template	`prompt_template`	Auto-inject system prompts and/or render client-referenced named, versioned templates.
Prompt Compression	`prompt_compression`	Minify JSON, strip ANSI, collapse whitespace — deterministic, fail-open.

Protocol: LLM only. To restrict which models a consumer may call, use the consumer Routing tab (Filter by available models / default model) — not a catalog policy. See Model resolution.

Prompt Template

prompt_template runs at pre_request and rewrites the chat body using Mustache-style {{placeholders}} (v1 engine: mustache only). The console form has two modes. The UI edits one mode at a time; config for the other mode is preserved if you switch.

Mode in the UI	Backend fields	Behavior
Auto-inject	`inject_templates`	Gateway always injects rendered system content into every request.
Named templates	`named_templates`	Clients opt in with `{template://name@label}` in a user message string.

You must configure at least one inject template or one named template (backend validation).

Configure in the console

Policies → Catalog → Prompt Template.
Choose Mode: Auto-inject or Named templates.
Add templates (details below).
Set If a variable is missing (Reject request / Use empty string).
Optionally open Advanced Settings (escape JSON control characters).
Set mode (Enforce / Observe) and scope, then save.

Mode A — Auto-inject

Gateway renders each inject template from context variables and writes a system message into the request.

UI field	Backend	Meaning
Name	`inject_templates[].id`	Unique id (required).
Content	`content`	Template body with `{{var}}` placeholders (required).
If system prompt exists	`on_existing_system`	Merge (default) or Replace an existing system message.
Insert position	`position`	Fixed to System in v1.

Placeholders must match {{name}} where name is letters, digits, ., -, or _ (e.g. {{user_id}}, {{tenant.name}}). Context variables (context_variables) map placeholder names to request data:

Source	Meaning
`header`	Read an HTTP header by name.
`jwt_claim`	Read a claim from the validated JWT.

The console does not yet expose a full context-variable editor; values configured via API or existing policies are preserved. When a placeholder cannot be resolved:

Setting	UI label	Effect
`error`	Reject request (default)	Fail the request.
`empty_string`	Use empty string	Substitute `""` and continue.
`skip_injection`	(API / advanced)	Skip that inject template only.

The shared UI control writes the same choice to both on_missing_context_variable and on_missing_client_variable (client supports error / empty_string only).

Mode B — Named templates

Clients reference a template in a plain string user message (not multimodal content parts):

{template://support-greeting@stable}

or, if a default label is set on the policy:

{template://support-greeting}

UI field	Backend	Meaning
Template name	`named_templates[].name`	Name in `{template://name…}` (unique, required).
Version	version id (UI)	Operator label for the version row.
Labels	`versions[].labels`	At least one label that resolves this version (e.g. `stable`, `latest`). Labels must be unique across all versions of all templates on the policy.
Content	`versions[].content`	Template body (required). May be a bare string or a JSON array of message objects.
Require template reference	inverted `allow_untemplated_requests`	When on, requests without a `{template://…}` reference are rejected. Default in the UI is on.
Default label	`default_label`	Used when the reference omits `@label`. Must match an existing version label if set.

Resolution rules

Scan user message string content for {template://name} or {template://name@label}.
Exactly one distinct reference per request (repeats of the same ref are OK for multi-turn).
Resolve name → template, then label (or default label) → version.
Render placeholders from client variables (request properties / template vars) and context variables.
Replace the entire messages array with the rendered content (not a single-message patch). Multi-turn history sent by the client is discarded when rendering succeeds.

Optional per-version required_variables (type / enum / max_length) can be set via API; the console preserves them if present.

Advanced

UI	Backend	Default	Meaning
Escape JSON control characters	`escape_json_control_chars`	on	Strip C0 control bytes from substituted values before insertion.

Example (auto-inject)

{
  "slug": "prompt_template",
  "settings": {
    "template_engine": "mustache",
    "context_variables": {
      "tenant": { "source": "header", "name": "X-Tenant-Id" }
    },
    "inject_templates": [
      {
        "id": "safety-policy",
        "position": "system",
        "role": "system",
        "content": "You serve tenant {{tenant}}. Follow company safety policy.",
        "on_existing_system": "merge"
      }
    ],
    "on_missing_context_variable": "error",
    "escape_json_control_chars": true
  }
}

Example (named template client call)

{
  "model": "auto",
  "properties": { "persona": "friendly" },
  "messages": [
    { "role": "user", "content": "{template://support-greeting@stable}" }
  ]
}

Prompt Compression

prompt_compression shrinks the request prompt on pre_request before the model runs. Transforms are deterministic (same input → same bytes) so provider prompt-cache prefixes stay stable, and the plugin fails open: any decode/transform error leaves the original body unchanged. The console uses the catalog settings schema form (booleans, integers, role multi-select).

Configure in the console

Policies → Catalog → Prompt Compression.
Enable at least one transform (defaults are all on).
Tune thresholds and optional target roles.
Set mode and scope, then save.

Settings

Setting	Default	Meaning
Compress JSON (`compress_json`)	on	Minify standalone JSON message content, fenced JSON code blocks, and tool-call arguments (whitespace-only, lossless).
Normalize Whitespace (`normalize_whitespace`)	on	Trim trailing spaces per line (keeps Markdown two-space hard breaks) and collapse runs of blank lines.
Strip ANSI Escapes (`strip_ansi`)	on	Remove ANSI colour/cursor sequences (common in terminal/CI logs).
Max Consecutive Blank Lines	`1`	Longest blank-line run kept when whitespace is normalized (`1`–`1000`).
Minimum Content Length (`min_length`)	`256`	Skip message content shorter than this many bytes (protects tiny cache-stable prefixes). `0` = compress everything.
Max Body Bytes (`max_body_bytes`)	`1048576` (1 MiB)	Skip the whole pipeline for larger bodies (CPU bound). `0` = no cap.
Target Roles (`target_roles`)	empty = all	Restrict to `system` / `user` / `assistant` / `tool`. Empty compresses every role.

At least one of compress JSON / normalize whitespace / strip ANSI must stay enabled.

Example

{
  "slug": "prompt_compression",
  "settings": {
    "compress_json": true,
    "normalize_whitespace": true,
    "strip_ansi": true,
    "max_consecutive_blank_lines": 1,
    "min_length": 256,
    "max_body_bytes": 1048576,
    "target_roles": ["user", "tool"]
  }
}

Policies overview
Model resolution — filter models and defaults on the consumer
Consumers — Routing tab model filters
Playground — exercise template behaviour

Introduction

Getting started

Console

Core concepts

Routing

Policies

MCP

Observability

Operate

Admin API

API reference

Prompt management

Prompt Template

Configure in the console

Mode A — Auto-inject

Mode B — Named templates

Advanced

Example (auto-inject)

Example (named template client call)

Prompt Compression

Configure in the console

Settings

Example

​Prompt Template

​Configure in the console

​Mode A — Auto-inject

​Mode B — Named templates

​Advanced

​Example (auto-inject)

​Example (named template client call)

​Prompt Compression

​Configure in the console

​Settings

​Example

​Related

Prompt Template

Configure in the console

Mode A — Auto-inject

Mode B — Named templates

Advanced

Example (auto-inject)

Example (named template client call)

Prompt Compression

Configure in the console

Settings

Example

Related