docs: agent-authorization thinking, agent-wallet ADR, roadmap v1-honest - #64
Merged
Conversation
- docs/agent-authorization-map.md: the three authority models, current focus (first demo = auto-shield, LLM in loop -> #60/#61), deferred work + why, invariants. Higher-level thinking, not a task tracker. - docs/adr/0002-agent-wallet-and-session-keys.md: agent-wallet positioning (distinct agent address via #33 session keys); deferred until after the first agent demo + audit. - docs/research/roadmap.md: reconcile to v1-honest -- limits are software-enforced, not chain-enforced; EIP-7702 session keys deferred.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Docs-only. Adds the agent-authorization thinking doc (the three authority models, the first-demo focus, what is deferred and why, the trust invariants) and ADR-0002 recording the agent-wallet / session-keys positioning (deferred until after the first agent demo and an audit), and reconciles
roadmap.mdto be v1-honest (limits are software-enforced, not chain-enforced; EIP-7702 session keys moved to LATER). It came out of a/plan-ceo-reviewthat cut scope to one concrete first demo (auto-shield, LLM in the loop), now tracked as #60 and #61.Linked issue
No issue is closed by this PR. It is the decision record and orientation behind #60 (activity feed + see-and-stop view), #61 (agent loop), and ADR-0002.
Definition of Done
Docs-only change — no
.rs,Cargo.toml, orCargo.lockis touched (the diff matches nothing in\.(rs|toml|lock)$), so the Rust build/test gates are not applicable and were not run.Cargo.toml/Cargo.lock— confirmed, none touchedcargo fmt --all --check— N/A (no Rust changed)just check(clippy-D warnings) — N/A (no compilable code changed)cargo test --workspace— N/A (no compilable code changed)DESIGN.md— N/A, no UI change (the docs describe the amber/cyan model, they do not change it)Zeroizing, never logged — N/A, no code changeNotes for reviewers
The map doc is deliberately the thinking only (three models, current focus, deferred + why, invariants); work items live in GitHub issues and build state in
STATUS.md, so it does not mirror the tracker. ADR-0002 is marked Deferred, not Accepted, on purpose. The one change to an existing doc is theroadmap.mdreconciliation, annotated rather than rewritten since it is a decision log.