feat(typescript): Full SDK parity — PolicyEngine + Identity + tests (#269)

* Initial plan

* Update repo tagline and subtitle for discoverability (P0)

Replace generic tagline 'Application-level security middleware for autonomous AI agents'
with Option B: 'Runtime governance for AI agents — the only toolkit covering all 10
OWASP Agentic risks with 6,100+ tests'

Also update subtitle to highlight all three key differentiators:
- Agent ACTIONS (not LLM outputs): 'Governs what agents DO, not just what they say'
- OWASP 10/10 coverage (unique to this toolkit)
- One pip install full stack

Resolves: Update repo tagline and positioning for discoverability

Co-authored-by: imran-siddique <45405841+imran-siddique@users.noreply.github.com>

* feat(typescript): full SDK parity — PolicyEngine + Identity + tests

PolicyEngine parity:
- Rich Policy document model (apiVersion, scope, default_action)
- Expression-based conditions (equality, comparison, in/not-in, and/or)
- Configurable conflict resolution (deny-overrides, allow-overrides,
  priority-first-match, most-specific-wins)
- PolicyConflictResolver with full strategy dispatch
- Rich PolicyDecisionResult (matchedRule, policyName, timing, approvers)
- Rate limiting support (e.g., '100/hour')
- Policy scoping (agent, agents, wildcard)
- Backward compatible with v0.1 flat rules API

AgentIdentity parity:
- Lifecycle management (active/suspended/revoked) with state transitions
- Capability wildcards (*, prefix:*)
- Delegation chains with capability narrowing
- JWK/JWKS import/export (RFC 7517)
- W3C DID Document export
- Metadata (name, description, sponsor, organization, expiresAt)
- IdentityRegistry with sponsor indexing and cascade revocation

Tests: 136 total (57 existing + 79 new parity tests), all passing
Types: clean compile, zero errors

Closes #229

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: 3 people

README.md

@@ -2,9 +2,9 @@
 
 # 🛡️ Agent Governance Toolkit
 
-**Application-level security middleware for autonomous AI agents**
+**Runtime governance for AI agents — the only toolkit covering all 10 OWASP Agentic risks with 6,100+ tests**
 
-*Policy enforcement · Zero-trust identity · Execution sandboxing · Reliability engineering*
+*Governs what agents DO, not just what they say · Policy enforcement · Zero-trust identity · Sandboxing · SRE — one pip install*
 
 [![CI](https://github.com/microsoft/agent-governance-toolkit/actions/workflows/ci.yml/badge.svg)](https://github.com/microsoft/agent-governance-toolkit/actions/workflows/ci.yml)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)