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

Route auto review requests to agentic review

Browse Source
This commit is contained in:
Bernd Worsch
2026-05-15 15:53:52 +02:00
parent 9fa1d9e9b5
commit 8f484cd855
15 changed files with 208 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
docs/abstraction-strategy.md
View File

@@ -49,9 +49,10 @@ LLMs are most useful for naming and explaining intent:
- summarizing README and code context into clearer ability descriptions
- suggesting merges or relinks when deterministic names are too generic
LLM output remains candidate material. It should cite source paths and be reviewed
or explicitly auto-approved by a trusted mode before becoming approved registry
truth.
LLM output remains candidate material. It should cite source paths and be
reviewed by a human or configured agentic reviewer before becoming approved
registry truth. Deterministic checks can block or flag weak candidates; they do
not approve them.
## Trial Repo Observations

12
docs/characteristic-evidence-model.md
View File

@@ -67,12 +67,12 @@ that show the repository provides the utility directly or intentionally exposes
it as a facade/adapter. Mentions, dependencies, configuration, and tooling are
context until a curator promotes them or stronger owned evidence appears.
Trusted auto-approval applies the same rule. A candidate capability must have
source references and an eligible utility relationship (`owned`, `facade`, or
`adapter`) before it can be approved automatically. Dependency, tooling,
configuration, and mention-only candidates remain review material. The review
decision should explain both sides: why approved candidates were considered safe
and why skipped candidates need curator review.
Deterministic quality gates apply the same source and utility relationship
signals, but they do not approve automatically. Gates may reject, downgrade,
invalidate, flag, merge, or require review. Approval requires human judgement or
a configured agentic reviewer that records evidence, criteria version, and
rationale. Dependency, tooling, configuration, and mention-only candidates remain
review material.
`INTENT.md` may also seed intended capabilities when it contains an explicit
capability section. These intent-derived candidates are marked as review