Integrate KnowKat sources with governed identity and attributed export - #575
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Outcome
Von can consult operator-configured public KnowKat ontology packages and adopt selected concepts through its governed services without losing source identity or licence attribution. Adds five thin standard-MCP reads and a read-only adoption proposal; source RDF stays quoted evidence, while local interpretation and relations remain separately labelled. This completes the Von side of KKAT-6 and KKAT-25 alongside https://github.com/Strong-AI-Lab/knowkat/pull/4.
Canonical probing exposed two blocking gaps: the governed create wrapper rejected the external identity supported by its underlying service, and normal concept export omitted canonical text. A single external identity is now resolved and bound into exact create intent/delegation, checked on canonical postcondition and read-only reuse. Existing complex-effect restrictions remain. Export includes complete actor-visible canonical text relations, so identity markers, source notices and transformation records survive.
Evidence and release decision
Ready for merge after required CI. The bounded implementation is supported by the exact source/adoption path and authority controls; no live deployment is included.
The persistence fixture uses Mongo-compatible storage and real production authority/create/text/relation/export services. Only unsupported MongoDB
$textcandidate acquisition is emulated with exact substring matching. This does not claim a live Atlas adoption or live runtime activation.Scope and configuration
Set
VON_KNOWKAT_COMMAND_JSONto an operator-selected executable argument vector andVON_KNOWKAT_PUBLIC=trueonly for deliberately public packages. No model-supplied commands, package paths, policy overrides or private-owner identity ceremony. Missing configuration/upstream failure is explicit. The adapter reuses MCPStdIOClient and carries provenance, bounds and cursors unchanged.Existing represented KR materialisation guidance is referenced, not duplicated or activated. No automatic taxonomy import, global truth promotion, reasoner, native KB decoding, private collection sharing or whole-ontology export activation. Legacy bulk export remains disabled; import round-trip support for exported text rows is not claimed. See docs/engineering/knowkat_ontology_sources.md for setup and the exact acceptance boundaries.