Development record
Shipped itd-6 sends a lane's reviews to RepoPrompt through `oracle.review`; itd-2609170822093401 says nothing reads the oracle value and builds a separate routing table for each agent
Shipped itd-6 sends a lane's reviews to RepoPrompt through oracle.review; itd-2609170822093401 says nothing reads the oracle value and builds a separate routing table for each agent
A scope leakage (severity minor) found by the cross-document consistency pass.
- End A:
.abcd/development/intents/shipped/itd-6-rp-mcp-only-integration.md:24— "oracle.review = rpopts a lane's reviews in" - End B:
.abcd/development/intents/planned/itd-2609170822093401-the-oracle-choice-is-one-repo-wide-value.md:26— "backend is one repo-wide value that nothing reads, and every delegated step"
itd-6 says the built route reads oracle.review = rp to opt a lane's reviews into RepoPrompt. itd-2609170822093401 starts from the premise that nothing reads the oracle backend value. It then adds its own repo, machine and bundled routing rows, plus --route, for the same reviewer agents. Two documents decide which backend serves a lane's reviews, through two configuration surfaces. Neither names the other or says which one wins.
Evidence: .abcd/work/reviews/2026-10-26-consistency/00-summary.md, finding 1232.
Frontmatter
| id | iss-2610262044499326 |
|---|---|
| type | issue |
| lifecycle | open |
| severity | minor |
.abcd/work/issues/open/iss-2610262044499326-shipped-itd-6-sends-a-lane-s-reviews-to.md
open on GitHub ↗ · commit history ↗
References2
- itd-6RepoPrompt over MCP is one opt-in reviewer route, beside the host's own agentsrelated
- itd-2609170822093401abcd proposes the model each agent deserves, and facilitates it where it canrelated