A code-grounded robustness audit of the strategic spine (MCP gateway, A2A,
x402) plus the two Mu-discovered foundations (in-process dispatch, durable
agentic workflow). Headline: all four are well-built internally and fragile at
the edge — the exposure surface the strategy rests on is the least
externally-proven part of the codebase (no test drives a real external MCP host,
third-party A2A SDK, or real x402 facilitator/wallet).
- internal/docs/GAP_AUDIT.md — the findings, file:line + severity + what "robust
in practice" requires, and a prioritized build order.
- .github/loop/PRIORITIES.md — repointed so the loop pulls the well-defined
strategic-spine fixes first (#4813 MCP stdio JSON, #4814 x402 budget-bypass,
#4815 A2A conformance, #4786 buyer wiring), with the architectural items
(#4816 durable agentic workflow, #4817 dispatch fast-path, MCP transport
unification) marked needs-human as 1:1 development the loop must not auto-build.
Reframes the queue around "advances the strategy vs grooms a proxy" — and makes
explicit that the planner ranks a human-curated backlog, it does not invent work.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
The loop's dispatch is agent-agnostic already — `--agent` just sets the
@mention it posts, so any coding agent that responds to an issue @mention and
opens a PR works. Make that explicit instead of implying Codex-only:
- micro-loop guide: add a "Choosing an agent" section — Codex (default), Claude
Code (via anthropics/claude-code-action responding to @claude), any other
mention-driven agent, and an honest note that assignment-triggered agents
(e.g. Copilot's coding agent) aren't supported by the mention dispatch yet.
- Clarify the `--agent` help text and the CLI README bullet.
No behavior change — the mention model already covers Codex and Claude; this
documents it and scopes the one real gap (an "assign" adapter) honestly.
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
Adds a deterministic reachable-CVE gate: `govulncheck ./...` on every push/PR,
failing on any reachable vulnerability EXCEPT an explicit allow-list of
known-unfixable ones. Today the allow-list holds exactly the two pgx/v4 CVEs
(GO-2026-5004, GO-2026-4518) with no upstream fix (tracked in #4556), so the
gate is green now and turns red the moment a NEW vulnerability appears.
This is the deterministic layer under the `security` loop role: the role
audits with judgment, this blocks known CVEs mechanically. Also adds
`govulncheck` to the loop-triage watch list, so a newly-disclosed CVE that
reddens the gate on master auto-files a fix issue for the loop to bump the dep.
Make `govulncheck` a required status check on master to enforce it.
Verified locally: exit 3 with only the two allow-listed IDs -> gate PASS.
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
Asim Aslam