ngs, messaging webhooks, payment keys, infrastructure secrets). Each finding includes a confidence score and content fingerprint — never the actual secret.

const decision = await engine.evaluateV12(
  { content: 'Deploy with key AKIAIOSFODNN7EXAMPLE...' },
  { correlation_id: 'req-001' }
);
// decision.action === 'DENY'
// decision.findings === [{ type: 'aws_access_key', confidence: 0.95, ... }]

Enter fullscreen mode Exit fullscreen mode

TealRegistry — Model & Tool Allowlisting Enforces which models and tools an agent can use. If it's not on the list, the agent can't call it. Supports version pinning and provenance verification.

const engine = new TealEngineV12({
  policy: {
    registry: {
      models: ['gpt-4o', 'claude-3-sonnet'],
      tools: ['web_search', 'file_read'],
      strict: true
    }
  },
  modules: [new TealRegistry()]
});

Enter fullscreen mode Exit fullscreen mode

TealReliability — Circuit Breakers & Fallbacks Retry budgets, circuit breakers (3-state: closed/open/half-open), fallback chains, and degradation policies. Prevents cascading failures and runaway costs.

TealMemory — Memory Governance Controls what agents can write to and read from memory. 5 scopes (session, agent, user, shared, global) and 4 classification levels (public, internal, confidential, restricted). Introduces 5 new decision actions specific to memory governance.

BundleExporter — Evidence Export Every decision produces a structured evidence envelope. Export as SARIF v2.1.0 (for security tooling), JUnit XML (for CI/CD), or JSON (for custom pipelines).

GovernanceDashboard & TEECValidationRunner Governance visualization and evidence contract validation.

TEEC — Typed Evidence & Evidence Contracts

Every governance decision in v1.2 is validated against the TEEC registry:

• 32 reason codes across 8 categories (policy, content, tool, reliability, cost, mode, secrets, memory)
• 18 event types for audit trail
• 12 decision actions with severity-based merge

TEEC makes the evidence contract explicit. Every decision includes a correlation_id, timestamp, reason_codes, event_type, teec_version, and component_versions. This is what makes governance decisions reconstructable after the fact.

Docker Governance Sidecar

Not every agent is written in TypeScript or Python. The governance sidecar wraps TealEngine v1.2 as a language-agnostic HTTP API:

docker pull tealtigeradmin/tealtiger-typescript:1.2-governance
docker run -p 8080:8080 tealtigeradmin/tealtiger-typescript:1.2-governance

Enter fullscreen mode Exit fullscreen mode

Six endpoints:

Any language can call POST /evaluate and get a governance Decision back:

curl -X POST http://localhost:8080/evaluate \
  -H "Content-Type: application/json" \
  -d '{"content": "Hello", "tool": "web_search", "agent_id": "bot-1"}'

Enter fullscreen mode Exit fullscreen mode

{
  "correlation_id": "req-abc-123",
  "decision": {
    "action": "ALLOW",
    "reason_codes": ["POLICY_COMPLIANT"],
    "risk_score": 0,
    "mode": "ENFORCE"
  }
}

Enter fullscreen mode Exit fullscreen mode

Three-Mode Rollout

Governance adoption doesn't have to be all-or-nothing:

1. REPORT_ONLY — Log everything, enforce nothing. See what would happen.
2. MONITOR — Evaluate fully, but override all decisions to ALLOW. Log what would have been blocked.
3. ENFORCE — Full enforcement. The decision is final.

Start with REPORT_ONLY in production. Graduate to MONITOR. Switch to ENFORCE when you trust the policy.

Getting Started

# TypeScript
npm install tealtiger

# Python
pip install tealtiger

# Docker (language-agnostic)
docker pull tealtigeradmin/tealtiger-typescript:1.2-governance

Enter fullscreen mode Exit fullscreen mode

import { TealEngineV12, TealSecrets, TealRegistry, PolicyMode } from 'tealtiger';

const engine = new TealEngineV12({
  policy: {
    secrets: { enabled: true },
    registry: { models: ['gpt-4o'], tools: ['web_search'] }
  },
  modules: [new TealSecrets(), new TealRegistry()],
  mode: PolicyMode.ENFORCE
});

const decision = await engine.evaluateV12(
  { content: 'Process this request', model: 'gpt-4o', tool: 'web_search' },
  { correlation_id: 'req-001', agent_id: 'support-bot' }
);

Enter fullscreen mode Exit fullscreen mode

Pitfall Guide

1. Relying on Probabilistic Scoring for Governance: Using LLM-based scoring for agent actions introduces non-determinism. Governance decisions must be reproducible; always prefer pattern matching, boolean logic, and explicit policy rules over model inference.
2. Ignoring the Fail-Closed Default: Configuring a fail-open policy during module exceptions creates security gaps. Always enforce FAIL_CLOSED so that broken guardrails default to DENY, preventing uncontrolled agent execution.
3. Misunderstanding the Merge Strategy: The engine uses "most restrictive wins." Attempting to override a DENY with an ALLOW from another module will fail. Design policies assuming explicit deny always propagates to the final decision.
4. Skipping the Three-Mode Rollout: Deploying directly into ENFORCE mode without validation causes production incidents. Always progress through REPORT_ONLY → MONITOR → ENFORCE to verify policy accuracy against live traffic.
5. Neglecting TEEC Evidence Contracts: Failing to include correlation_id, reason_codes, and structured exports makes post-incident forensics impossible. Always enable TEEC validation and export decisions in SARIF/JUnit/JSON for audit compliance.
6. Monolithic Policy Evaluation: Packing all governance logic into a single synchronous evaluator creates latency bottlenecks. Decompose policies into independent parallel modules (secrets, registry, memory, reliability) and leverage Promise.allSettled for sub-15ms p99 performance.
7. Hardcoding Thresholds Instead of Using the Policy Library: Embedding static rules in application code reduces maintainability and compliance alignment. Use the provided Policy Library templates (OWASP ASI, HIPAA, SOC 2, EU AI Act) and adjust thresholds per environment rather than rewriting logic.

Deliverables

• 📘 Governance Architecture Blueprint: Complete reference architecture for TealTiger v1.2, including parallel module evaluation flow, TEEC evidence contract schema, Docker sidecar deployment topology, and severity merge logic diagrams.
• ✅ Pre-Deployment Governance Checklist: Step-by-step validation guide covering policy configuration, module initialization, fail-closed verification, three-mode rollout sequencing, evidence export setup, and backward compatibility testing.
• ⚙️ Configuration Templates: Production-ready copy-paste policy packs (OWASP ASI, HIPAA, SOC 2, EU AI Act), Docker sidecar environment variables, TEEC validation runner configs, and CI/CD integration snippets for SARIF/JUnit evidence pipelines.