Add semantic report clusters#31
Merged
Merged
Conversation
Group semantic candidates into same-entity review clusters so low-threshold reports become human cleanup specs without adding an LLM or apply path.
There was a problem hiding this comment.
Pull request overview
Adds review scaffolding to semantic reconcile report mode by grouping same-entity semantic candidate pairs into connected observation clusters, and updates documentation to describe clusters plus optional (human-only) model-assisted proposal review—without introducing any semantic apply/mutation path.
Changes:
- Render candidate clusters (summary table + per-cluster top pairs + manual decision checkboxes) ahead of the existing pairwise candidate table.
- Add unit tests covering cluster rendering/escaping and entity-id-based clustering across entity-type snapshots.
- Update README/API contract/architecture/implementation docs to reflect cluster scaffolding and clarify optional LLM review is out-of-band and non-executable.
Reviewed changes
Copilot reviewed 6 out of 6 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| README.md | Documents cluster output in semantic reports and adds optional (human-only) model-assisted cleanup guidance. |
| internal/reconcile/report.go | Builds connected-component clusters from semantic candidates and renders cluster summaries/details in the report. |
| internal/reconcile/report_test.go | Extends semantic report rendering assertions and adds a focused cluster-building test. |
| IMPLEMENTATION.md | Records the new “semantic report review scaffolding” step gate and constraints. |
| ARCHITECTURE.md | Updates semantic report boundary to include clusters/checkboxes and clarifies model-assisted proposals are outside the executable architecture. |
| API_CONTRACT.md | Extends semantic report contract language to include clusters/checkboxes and the “no LLM calls / no apply” constraint. |
Compare observation ID slices directly so semantic cluster sorting stays deterministic without rebuilding joined strings inside the comparator.
Trim fallback entity name and type keys so synthetic or zero-ID semantic candidates bucket consistently with the displayed cluster identity.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Validation
go test ./internal/reconcile ./internal/semantic ./cmd/workmemgo test ./...git diff --check