Response format
Valid JSON, expected fields present, no truncation mid-stream
LLM API reliability runtime. Contract validation across six dimensions — structure, schema, latency, cost, identity, integrity. Embedded in your stack with pip install.
from correctover import Client, Contract client = Client( providers=["deepseek", "kimi", "openai"], contract=Contract( dimensions=["structure", "schema", "identity"], expected_entity="NEVER_EXIST_TOKEN", ) ) async for chunk in client.stream(model="gpt-4o", messages=[...]): yield chunk # P50 validation: 22µs · 84 self-healing rules · <0.01% overhead
Valid JSON, expected fields present, no truncation mid-stream
Types match, required fields exist, enums within bounds
Detect provider degradation before it becomes a timeout
Verify billed tokens match actual usage, detect runaway billing
Confirm the response contains the entities you asked for
Detect hallucination patterns, garbled output, encoding errors
The self-healing engine maintains 84 rules learned from real API interactions. 62 are high-confidence production rules that trigger automatically.
When a provider returns garbage, the engine doesn't just retry — it diagnoses which dimension failed, selects the right recovery strategy, and validates the result.
Every failover proxy switches providers. Correctover verifies the response is actually correct after switching. That's the difference between a wire operator and a quality inspector.
{
"call_count": 15,
"heal_count": 1,
"l3_failover_count": 1,
"l3_failover_e2e_ms": 949,
"mapek_decision_us": 950,
"validation_passed": false,
"failed_dimension": "identity",
"entity_missing": "NEVER_EXIST_TOKEN_XYZ",
"rules_evaluated": 84,
"rules_high_confidence": 62,
"overhead_pct": 0.003
}
No token relay. No markup. No middleman. You bring your own API keys (BYOK) and Correctover validates responses locally in your process.
37 modules, 100 public APIs, zero external dependencies beyond your provider SDKs. Pure Python, ships as compiled .pyc — no source code exposure.
Python 3.8+, Node.js 18+. Install in seconds, integrate in minutes.
Your Application
│
├── Correctover SDK (in-process)
│ ├── Contract Engine (22µs P50)
│ ├── SelfHealing Engine (84 rules)
│ ├── CircuitBreaker (per-provider)
│ └── BenchmarkRunner (latency/cost)
│
├── DeepSeek API ←── YOUR KEY
├── Kimi API ←── YOUR KEY
└── OpenAI API ←── YOUR KEY
# No proxy. No relay. Direct connections.
Real numbers, not vanity metrics