coulomb/repo-scoping
2
0
Fork 0
generated from coulomb/repo-seed
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Explore after registration as default

Browse Source
This commit is contained in:
Bernd Worsch
2026-04-28 01:24:37 +02:00
parent eaff77db89
commit c0a044fa0b
3 changed files with 87 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
workplans/RREG-WP-0003-automatic-repository-exploration.md
View File

@@ -27,7 +27,7 @@ configured trusted automation mode.
```task
id: RREG-WP-0003-T01
status: in_progress
status: done
priority: high
state_hub_task_id: "ab718ce7-d38f-4080-9385-99be1bf80475"
```
@@ -58,7 +58,28 @@ coordination should be visible as source-linked claims.
Acceptance: a self-analysis run produces non-trivial, source-linked candidate
abilities and capabilities that a curator would recognize as the repo's real
purpose.
purpose. A one-to-one correspondence of observed fact to generated feature is a
quality smell: features should describe user-visible or operational behavior, with
facts as drilldown evidence, not mirror individual scanner facts.
## P0: Abstraction Strategy And LLM Boundary
```task
id: RREG-WP-0003-T06
status: todo
priority: high
state_hub_task_id: "51890aff-511d-4635-85c4-fe4db0b7dd01"
```
Document and test how the registry should climb from deterministic observed facts
to useful ability/capability/feature abstractions. Explicitly compare what can be
done deterministically against what likely needs LLM assistance. Preserve the trust
boundary: deterministic scanners establish facts; abstraction may propose claims;
review or trusted automation decides approved registry truth.
Acceptance: `docs/` contains an abstraction strategy note with examples from the
three trial repos, and candidate generation has at least one regression guard
against feature granularity collapsing into one feature per observed fact.
## P1: Guided Review To Populated Registry