← Home

Contract Ops

Schema + fixture + tool call → deterministic reliability report

One-shot validation for agent contracts without execution, replay, signup, or another model call. Compare schema drift, validate representative arguments, inspect fixture chains, sanitize regression packs, and keep the evidence copyable.

For 1–5 related contracts, shared fixtures, and cross-contract reconciliation, build one deterministic portfolio release packet below. The one-contract single-contract release gate and lightweight agent-contract-check remain separate and available.

Portfolio reliability

Reconcile 1–5 related contracts before release

Compare inline JSON Schema, tool-contract, or OpenAPI operation revisions against shared submitted fixtures. The run is deterministic and browser-local; it never resolves $ref, executes tools, reads a repository, or writes back.

Portfolio contracts

Each record needs a safe unique ID, version, kind, previous/current inline contract objects, references, and an OpenAPI selector only when required.

Submitted fixtures

Values are evaluated locally and omitted from the release result. Zero fixtures produces unknown coverage, never PASS.

Direction
Release policy

Load or enter inputs, then run explicitly. Editing any input invalidates published results and downloads.

Exact contract

Bounded inputs, explicit results

agent-contract-check · 2026-07-16-contract-ops-v1
One-shot validation

Each run compares one saved/current JSON Schema pair, validates one representative argument object, and returns drift, diagnostics, retry safety, and one bounded hint.

Stable fixture identity

Use a safe fixture id up to 64 characters, or let the core derive a deterministic id from the schema pair. Hints are capped at 512 characters.

1 to 20 fixtures

The browser-local fixture runner accepts JSON-RPC, tool-call, HTTP, and typed-error fixtures in a packet capped at 256,000 bytes and 30 levels of nesting.

Past steps only

Fixture bindings may reference completed steps only. The runner validates structure and expectations; it does not execute tools or replay network requests.

Sanitized regression packs

Exports use utilito.agent-fixtures.v1 and utilito.agent-regression-pack.v1, strip dangerous keys, redact recognized secret keys and Bearer/sk--like values, and compare versions by stable fixture id. Redaction is a safety aid, not an exhaustive secret scanner.

Typed review state

AGENT_CONTRACT_CHECK_FAILED means schema drift, argument diagnostics, or retry safety needs review. It is a deterministic result, not an internal server error.

HTTP API

Validate one contract

Call POST /api/run with tool_id: agent-contract-check. Free light use needs no key or account; load the schema first for the current bounded input contract.

Copy the HTTP example →

MCP

Use the compact router

Load agent-contract-check with get_tool_schema, then call run_tool. Contract Ops does not add another top-level MCP tool.

Copy the MCP example →

Contract Ops CA3

Contract Review Packs

Move one deterministic agent-contract-check result into Context Workbench. The contract-review-pack prioritizes breaking drift, diagnostics, and unsafe retry state; the contract-review-report produces escaped Markdown or standalone HTML.

Raw argument values are omitted by design. Argument keys, exact omission counts, drift telemetry, and typed failures remain visible. The pack does not execute or replay the tool.

Boundaries

No recurring monitoring

No execution or replay

Contract checks inspect submitted schemas, arguments, failures, and fixtures. They do not call providers, run the described tool, or replay HTTP requests.

No stored fixtures

Browser-local work stays on-device. API/MCP results are response-only; schemas, arguments, and fixtures are not stored or indefinitely retained by Contract Ops.

No schedules or alerts

CO0 has no scheduled checks, webhook notifications, status history, or monitoring dashboard. Contract Monitor remains evidence-gated.

One existing plan

Contract Ops is a module in the Context Ops Builder Pilot, not a separate subscription. Free one-shot browser and light API/MCP validation remain useful.

Evidence before expansion

Request a named contract workflow

Need a versioned recipe, higher-volume composition, CI integration, or recurring drift check? Name the exact workflow and support boundary. A real request can select the next phase; it does not authorize generic monitoring or fixture storage.

Request a workflow