This is the record of an abcd-managed repository

abcdBetav0.16.2 · 2026-11-06

Development record

itd-6's scope makes RepoPrompt over MCP the preferred oracle transport ahead of a Codex CLI and the in-session agent; the status-board chapter says every delegated step runs through the harness unless a routing table is accepted

issuewontfixminoriss-2610262035171024

itd-6's scope makes RepoPrompt over MCP the preferred oracle transport ahead of a Codex CLI and the in-session agent; the status-board chapter says every delegated step runs through the harness unless a routing table is accepted

A premise contradiction (severity minor) found by the cross-document consistency pass.

  • End A: .abcd/development/intents/shipped/itd-6-rp-mcp-only-integration.md:41 — "RP MCP (preferred) → Codex CLI subprocess (alternative for non-Mac / no-RP users — RP is macOS-only) → in-session subagent (final fallback)"
  • End B: .abcd/development/brief/04-surfaces/08-abcd.md:283 — "With no table accepted the lines are absent and every delegated step runs through the harness at host-decides."

itd-6 keeps a three-transport chain with RepoPrompt over MCP preferred, a Codex CLI subprocess second and the in-session subagent as the last fallback. The status-board chapter says that with no routing table accepted, every delegated step runs through the harness at host-decides. One document puts an external route first by default and the other makes the harness the default.

Evidence: .abcd/work/reviews/2026-10-26-consistency/00-summary.md, finding 561.

Grounds

  • declined: Closed in the 2026-10-27 triage (dcn-2610271112330536): a later record already settles which end holds. The preferred-RP chain is the dropped cascade; the shipped default is the host, with oracle.review = rp an opt-in reviewer route.

Frontmatter

idiss-2610262035171024
typeissue
lifecyclewontfix
severityminor

References1

mentions1