feat: retain semantic-span prototype as TEPP implementation evidence - #82
Closed
seonghobae wants to merge 1 commit into
Closed
feat: retain semantic-span prototype as TEPP implementation evidence#82seonghobae wants to merge 1 commit into
seonghobae wants to merge 1 commit into
Conversation
Add a provider-neutral semantic-span engine that combines authored structure, exact model token budgets, and optional dense adjacency similarity without language routing, translation, or TF-IDF. Include a final metadata payload guard, an adapter for the existing Chunk contract, mixed-script adversarial tests, an accepted ADR, and a phased implementation plan.
|
Important Review skippedDraft detected. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![github-code-quality[bot]](https://avatars.githubusercontent.com/u/9919?s=60&v=4){kind=small}
| class TokenCodec(Protocol): | ||
| """Encode and decode text exactly as the selected embedding model does.""" | ||
|
|
||
| def encode(self, text: str) -> list[int]: ... |
|
|
||
| def encode(self, text: str) -> list[int]: ... | ||
|
|
||
| def decode(self, tokens: Sequence[int]) -> str: ... |
| class VectorEmbedder(Protocol): | ||
| """Minimal adapter implemented by LineageWeave embedding clients.""" | ||
|
|
||
| def embed(self, text: str) -> list[float]: ... |
seonghobae
changed the title
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
1 participant
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.
Superseded by the TEPP-owned semantic-evidence contract
This prototype is useful test and algorithm evidence, but it is not the correct production owner or evidence contract for Milestone 2.
TEPP PR #83 establishes the canonical responsibility boundary: TEPP owns immutable documentary evidence, exact source spans, multilingual semantic measurement inputs, model-profile token budgets, hierarchical context, and embedding-space provenance. LineageWeave should consume that versioned import/REST contract and retain only a thin product adapter to its existing lineage candidate path.
The current implementation cannot be merged as the canonical layer because it:
embedding_space_idpersistence, policy-versioned reindexing, and 3NF migrations;Preserve this branch read-only. Port only the useful mixed-script, punctuation, exact-token-budget, dense-boundary, cache, and provider-absence tests into TEPP after ADR 0017 is accepted, while replacing data-loss behavior with exact source-span invariants. Then add a small LineageWeave adapter that consumes TEPP semantic-span artifacts and maps them to
Chunk/lineage candidates without reimplementing measurement semantics.Closing this PR prevents two incompatible semantic-unit engines from becoming product truth. It does not discard the prototype or its focused 100% coverage evidence.
Superseded by ContextualWisdomLab/TEPP#83 and LineageWeave issue #79.