tegwick
ebc7c61ee3
Assistant: codex Assistant-Model: gpt-6.1-sol Assistant-Session: 01a10238-7ecc-78e2-903d-075f50e913cc
71 lines
3.5 KiB
Markdown
71 lines
3.5 KiB
Markdown
# SCOPE
|
|
|
|
> Repository boundary reviewed 2026-10-03. See `INTENT.md` for purpose and
|
|
> `workplans/EMERGENT-WP-0002-agent-security-knowledge-and-netkingdom-integration.md`
|
|
> for the active ecosystem integration.
|
|
|
|
## One-liner
|
|
|
|
Security governance canon, reference decisions, and source-backed NetKingdom security knowledge for coding agents.
|
|
|
|
## Core Idea
|
|
|
|
Delegate understood decisions within explicit envelopes, escalate unresolved
|
|
decisions without widening privilege, and keep root human-controlled.
|
|
|
|
## In Scope
|
|
|
|
- Maintain the versioned canon, agent extract, YAML envelopes and risk scales.
|
|
- Maintain the pure Python reference evaluator and decision/governance fixtures.
|
|
- Publish source-backed agent knowledge and explicit mappings to existing
|
|
NetKingdom owners under EMERGENT-WP-0002.
|
|
|
|
## Out of Scope
|
|
|
|
- Operate a second estate authorization decision point or credential broker.
|
|
- Take over another repository's canon, operational routes, or enforcement.
|
|
- Treat reference decisions or knowledge loading as operational authority.
|
|
|
|
## Current State
|
|
|
|
- Canon and reference package: v0.8; Python 3.11+, PyYAML, pytest.
|
|
- Knowledge package: v0.2.2 pilot; 14 cards, 24 owners, 69 pinned sources,
|
|
read-only retrieval CLI, sealed exports and provider adapters.
|
|
- Verification: 332 portable tests plus 9 optional real owner-contract tests.
|
|
- Informed Decision unsigned adoption draft and native v0.2 orientation runbook;
|
|
no live submission or execution bridge. See docs/decision-runbook-integration.md.
|
|
- Thin pointers installed in four pilot repositories; fresh 0.2.0 pilot evidence
|
|
and 0.2.1 Codex/Claude scenario evidence are retained. Release 0.2.1 clarifies
|
|
withdrawn-procedure and missing-event recipients after repeat routing defects.
|
|
Independent review, full provider validation, actual compaction/resume and
|
|
broader adoption remain live tasks in EMERGENT-WP-0002.
|
|
- No running service, credential issuer or runtime enforcement is provided.
|
|
|
|
## Getting Oriented
|
|
|
|
- Start with: INTENT.md
|
|
- Agent instructions: AGENTS.md
|
|
- Workplans: workplans/
|
|
|
|
|
|
Owner reviews now provide scoped doctrine, vocabulary and PDP-boundary evidence
|
|
for 0.2.1; their institutional/human adoption limits remain explicit. Whitehat
|
|
reported two loaded-package consistency findings, addressed locally in 0.2.2
|
|
with five regression cases. Whitehat review close-out was interrupted by a
|
|
platform cybersecurity-risk block; no clean independent acceptance is claimed.
|
|
Glas model evidence now leaves unreported observed models unknown. Current native
|
|
continuity requirements remain in GLAS-WP-0012; distribution stays a draft.
|
|
|
|
Fresh final 0.2.2 Codex and Claude runs each answered 28 scenarios and preserved
|
|
all substantive authority/evidence boundaries in implementing-worker review;
|
|
recipient qualifications remain. All four pilot owners supplied documentary
|
|
feedback on retained scenarios. Grok has retrieval but no completed answer;
|
|
exact-packet human adoption/admission, native continuity, independent remediation
|
|
acceptance, current wider pilots and rollout/reach keep EMERGENT-WP-0002 blocked.
|
|
|
|
Final post-worker source check: 23 owners verify; Informed Decision's inventoried
|
|
workplan changed during owner review. Current-source startup is withheld as
|
|
designed. T09 retains review/re-pin/new-release and bound-packet refresh, followed
|
|
by renewed release-specific evidence. The final source-check receipt is
|
|
`docs/evidence/2026-10-03-022-final-source-check.json`; earlier 0.2.2 tests/provider
|
|
receipts remain historical evidence for their exact seal.
|