Development record
The naming register says the refresh backstop forces a full re-inject regardless of dedup, but the configuration chapter says a domain still in force is never re-injected unchanged within a session
The naming register says the refresh backstop forces a full re-inject regardless of dedup, but the configuration chapter says a domain still in force is never re-injected unchanged within a session
A premise contradiction (severity minor) found by the cross-document consistency pass.
- End A:
.abcd/development/brief/02-constraints/04-naming.md:208— "Every N prompts, the prompt-router hook forces a full re-inject regardless of dedup signature match (compaction recovery)." - End B:
.abcd/development/brief/05-internals/03-configuration.md:1039— "a domain that stays in force is still never re-injected unchanged within a session"
The naming register defines rules.force_refresh_every_n as forcing a full re-inject every N prompts regardless of the dedup signature match, as compaction recovery. The configuration chapter says compaction recovery is event-driven, on SessionStart and PreCompact, and that the counter only re-injects always-relevant domains. It also says a domain that stays in force is never re-injected unchanged within a session. A full re-inject every N prompts and no unchanged re-inject within a session cannot both hold.
Evidence: .abcd/work/reviews/2026-10-26-consistency/00-summary.md, finding 95.
Frontmatter
| id | iss-2610262031108321 |
|---|---|
| type | issue |
| lifecycle | open |
| severity | minor |
.abcd/work/issues/open/iss-2610262031108321-the-naming-register-says-the-refresh.md
open on GitHub ↗ · commit history ↗