# SALT19 Agent Code Change Risk Gate

> SALT19 Agent Code Change Risk Gate is a paid API for AI agents from api.salt19.com, paid per call via x402, $1.21/call, status unknown (last checked 2026-09-15).

Analyzes a code diff and returns a risk verdict, rollback risk, breaking change probability, security flags, and test requirements before deployment.

## Facts

- Endpoint: POST https://api.salt19.com/v1/agent-code-change-risk-gate
- Price: $1.21/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/salt19-agent-code-change-risk-gate-b1631468
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_kTsVexrEOv6eDj2cVLeje

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability salt19-agent-code-change-risk-gate-b1631468 -d '<json body>'
```

Example prompt: Before we merge this PR, can you run the diff through the SALT19 risk gate and tell me the verdict, rollback risk, and any test requirements? The change touches the MCP contract layer and we have a constraint that no public API signatures should break.

## When to prefer this

Choose this endpoint when you need a structured, machine-readable risk verdict on a code diff before deployment or merge — especially in agentic CI/CD pipelines where a human isn't reviewing every change. It is particularly valuable when you need rollback risk classification, security flag detection, and explicit test requirements in a single call. Prefer it over generic LLM code review when you need a consistent scored output format that can gate automated workflows.

## Known failure modes

- Diff too large (exceeds 48000 character maxLength) — request rejected with validation error
- Empty or missing diff field — minLength:1 not met, returns 400
- Overly generic context may yield uncalibrated or generic risk scores
- Breaking change probability is explicitly noted as an uncalibrated static heuristic, not empirical
- Constraints array limited to 32 items — excess constraints silently truncated or rejected

## How this service works

SALT19 is an independent applied AI systems lab behind EvoMind governed cognition, the MCP-native Agent Utility Grid, the ARCS research community, AeroClear UAS flight intelligence, and practical software for real-world work.

## Output

Returns a JSON object with: a string verdict (e.g. PASS, WARN, FAIL), a numeric risk_score (0–1), a rollback_risk level (LOW/MEDIUM/HIGH), an array of security_flags, an array of test_requirements, an array of architecture_conflicts, and a breaking_change_probability object with a numeric value, calibration state, and explanatory basis note.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "diff": {
   "type": "string",
   "maxLength": 48000,
   "minLength": 1
  },
  "context": {
   "type": "string",
   "maxLength": 4000
  },
  "constraints": {
   "type": "array",
   "items": {
    "type": "string",
    "maxLength": 4000
   },
   "maxItems": 32
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "verdict": "WARN",
  "risk_score": 0.44,
  "rollback_risk": "MEDIUM",
  "security_flags": [],
  "test_requirements": [
   "Run API/MCP contract tests."
  ],
  "architecture_conflicts": [],
  "breaking_change_probability": {
   "basis": "Uncalibrated static heuristic; not an empirical probability.",
   "state": "PARTIALLY_SUPPORTED",
   "value": 0.28
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/salt19-agent-code-change-risk-gate-b1631468/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.salt19.com](https://www.zero.xyz/host/api.salt19.com/llms.txt)