docs(rust): map capability ownership and evidence

[Kerberosmansour (kerberosmansour)]

Related Issue

Closes #3779

Related umbrella: #3680

Problem & Solution

The package matrix marks the Rust unified CLI unavailable even though the
feature-gated binary implements and tests check, policy, audit, and
trust. The repository also lacks a source-backed place to distinguish
AGT-owned operator work from canonical agent-hooks host semantics and ACS
policy-interceptor semantics.

This documentation-only change adds a Rust capability and ownership manifest,
marks the Rust CLI partial, and links the manifest from the Rust README. The
manifest defines evidence requirements for shipped, partial, missing,
blocked, and deferred; links current implementation and tests; records
limitations and trackers; and separates current embedded ACS 0.3.1-beta from
the conditional architecture proposed by #3561.

Impact on Your Work

Rust adopters can now see which operator workflows exist, which remain gaps,
what evidence supports each status, and which repository owns a semantic
change. Existing Rig, official MCP, OpenAI, and OpenTelemetry integrations are
represented rather than duplicated as new work.

Timeline

None.

Alternatives Considered

• Keep the snapshot matrix only: rejected because a three-symbol table cannot
  carry ownership, evidence, limitations, or active blockers.
• Treat Python as the semantic reference: rejected for shared contracts;
  specifications, schemas, official vectors, and canonical Rust
  implementations take precedence. Python remains UX/workflow prior art when
  those sources are silent.
• Describe refactor(policy-engine)!: retarget onto the published agent-control-spec engine #3561 as the current architecture: rejected because the PR is open,
  has requested changes, and remains blocked on
  Publish agent-control-spec through trusted publishing, with repository metadata and an org owner responsibleai/agent-control-spec#24.

Type of Change

• Bug fix (non-breaking change that fixes an issue)
• New feature (non-breaking change that adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• Documentation update
• Maintenance (dependency updates, CI/CD, refactoring)
• Security fix

Package(s) Affected

Core & runtime:

• agent-governance-toolkit-core
• agent-primitives
• agent-os
• agent-mesh
• agent-runtime
• agent-sre
• agent-compliance

Governance & security:

• agent-mcp-governance
• agent-rag-governance
• agent-sandbox
• agent-discovery
• agt-policies
• policy-engine

Platform & tooling:

• agent-hypervisor
• agent-lightning
• agent-marketplace
• agent-governance-toolkit-cli
• agent-governance-toolkit-integrations
• agent-governance-toolkit-protocols
• agentmesh-integrations (framework integrations)

CLI plugins:

• agent-governance CLI plugins (copilot-cli / claude-code / opencode / antigravity-cli)

Shared / other:

• schemas
• action (GitHub Action)
• examples
• docs / root

Also documents the existing agent-governance-rust workspace; no package or
runtime source changes.

Testing

Unit Testing

• Documentation tooling: 51 passed.
• Existing Rust CLI behavioral suite: 33 passed.
• No test source was added because the product change is Markdown-only; a
  failing-first acceptance probe covered the absent manifest and incorrect
  matrix cell before the edit.

Manual Testing

• python3 scripts/docs/check_links.py --root .: 293 files and 2,633 links,
  0 new broken links.
• python3 scripts/docs/check_frontmatter.py --root . --strict: 280 files,
  0 findings.
• cargo check -p agentmesh --features cli: passed with four existing
  deprecation warnings.
• cargo clippy -p agentmesh --features cli --all-targets: passed with
  existing warnings.
• cargo test -p agentmesh --features cli --test cli: 33 passed.
• cargo run -p agentmesh --features cli --bin agt -- --help: passed and
  listed check, policy, audit, and trust.
• Changed-file and protected-path checks: exactly three Markdown files; no
  Cargo, lockfile, Rust source, or workflow change.

cargo fmt --all -- --check reports formatting differences in unchanged Rust
files on current main. This PR does not modify those paths, so it does not
broaden into an unrelated formatting rewrite.

Specifications and conformance evidence

• AGENT-HOOKS-0.1
• agent-hooks schemas
• agent-hooks CTK vectors
• ACS 0.4 specification
• ACS manifest schema
• ACS agent-hooks report

The manifest does not claim AGT host conformance, certification, compliance,
or production readiness.

Security, compatibility, migration, and rollback

• Security: public repository evidence only; no credentials, production
  prompts, customer data, or private operational evidence. A high-signal
  credential/token scan found no match.
• Compatibility: no source, command, exit-code, package, feature, schema, wire,
  persisted-state, dependency, lockfile, or workflow change.
• Migration: none.
• Rollback: revert the single documentation commit.
• Resource impact: none; this adds finite static Markdown only.

Checklist

• I have linked a related issue above, or completed "Problem & Solution", "Impact on Your Work", and "Alternatives Considered"
• My code follows the project style guidelines (documentation checks and git diff --check)
• I have added tests that prove my fix/feature works (N/A: documentation-only; failing-first acceptance probe and existing suites used)
• All new and existing relevant tests pass
• I have updated documentation as needed
• I have signed the Microsoft CLA

Attribution & Prior Art

• This contribution does not contain code copied or derived from other projects without attribution
• Any external projects that inspired this design are credited in the documentation
• If this PR implements functionality similar to an existing open-source project, I have listed it below

Prior art / related projects:

• responsibleai/agent-hooks owns the framework-neutral host contract and CTK.
• responsibleai/agent-control-spec owns policy-interceptor semantics and the
  canonical Rust runtime.
• Python AGT commands are used only as operator UX/workflow prior art where
  normative sources are silent.

AI Assistance

• I can explain every meaningful change in this PR: what it does, why, and what tradeoffs were considered
• I have run tests and verification appropriate for this change
• No part of this PR was autonomously submitted by an AI agent without my review
• I have not used AI to generate review comments on others' PRs

Codex assisted with repository inspection, drafting, and verification. The
contributor reviewed the issue, exact diff, evidence, and this PR description
before submission.

IP, Patents, and Licensing

• This contribution does not implement patent-pending or patent-encumbered techniques
• This contribution does not require an NDA or licensing agreement to understand or use
• Any AI tools used have terms compatible with the MIT License

[azure-pipelines]

Azure Pipelines:
There may be pipelines that require an authorized user to comment /azp run to run.

[github-actions]

🟡 Contributor Check: MEDIUM

Check	Result
Profile	MEDIUM
Credential	MEDIUM
Overall	MEDIUM

Automated check by AGT Contributor Check.

[github-actions]

PR Review Summary

Check	Status	Details
🔍 Code Review	⚠️ Missing	No current-run comment
🛡️ Security Scan	⚠️ Missing	No current-run comment
🔄 Breaking Changes	⚠️ Missing	No current-run comment
📝 Docs Sync	⚠️ Missing	No current-run comment
🧪 Test Coverage	⚠️ Missing	No current-run comment

Verdict: ⚠️ AI review incomplete; ready for human review

AI review comments are untrusted advisory output. The summary reports workflow-generated completion status only, not model-authored pass/fail claims.