Development record
2026-07-08 — itd-37's itd-36 edge downgraded blocked_by → builds_on: the
decisiondcn-2607080000000014
2026-07-08 — itd-37's itd-36 edge downgraded blocked_by → builds_on: the capture + enforcement half ships independently (Phase 0 registration) and only extraction-to-memory waits on itd-36 (iss-18); the launch deepenings' unscheduled state is recorded in the phase index pointing at adr-33 (iss-20); itd-6 stays planned/ — ADR-25 superseded its framing only, and scheduled implies planned per adr-34 (iss-22).
Frontmatter
| id | dcn-2607080000000014 |
|---|---|
| type | decision |
| date | 2026-07-08 |
.abcd/work/decisions/dcn-2607080000000014-itd-37-s-itd-36-edge-downgraded-blocked.md
open on GitHub ↗ · commit history ↗
mentions9
- adr-25The LLM is host-delegated by default; oracles are opt-in adapters
- adr-33Launch phase ownership is tiered; the phase index is the sole ownership source
- adr-34Intent lifecycle and phase scheduling are orthogonal axes
- iss-18phase-order violation: Phase 0 scopes itd-37 whose declared blocker itd-36 is Phase 2; split the hard-on-half edge (capture half vs memory-routing half) or reschedule
- iss-20the launch cluster (itd-65/66/67 critical, itd-72 major) is scheduled in no phase Scope section — the silent-stall pattern itd-78's lint should catch; schedule or record why not
- iss-22itd-6 sits in planned/ while its own banner records supersession-in-framing by ADR-25 (one optional adapter among many); lifecycle look needed
- itd-6RepoPrompt over MCP is one opt-in reviewer route, beside the host's own agents
- itd-36Knowledge That Compounds, Not Knowledge That Re-Derives
- itd-37Every Spec Externalises How It Should And Shouldn't Be Modified