feat(graph): add ZeckF64 neighborhood vector search (Heel/Hip/Twig/Leaf)#17
Merged
Merged
Conversation
Implements the primary search path for lance-graph using progressive 8-byte edge encodings and 3-hop neighborhood vector traversal. ZeckF64 encoding: byte 0 = 7 SPO band classifications (boolean lattice, 19 legal patterns, ~85% error detection), bytes 1-7 = distance quantiles. ScopeBuilder: O(N²) pairwise construction of [ZeckF64; N] vectors. SearchCascade: HEEL (1 vec) → HIP (50 vecs) → TWIG (50 vecs) → LEAF. 32 tests (22 unit + 10 integration), all passing. https://claude.ai/code/session_01NUMNX67KZrFiTQK7erFQuH
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
AdaWorldAPI
pushed a commit
that referenced
this pull request
Mar 31, 2026
ChatBundleStrategy implements PlanStrategy with: - ChatBundle: Base17 fingerprint accumulator with recency decay - Topic shift detection via L1 distance from bundle - Affinity scoring: 0.95 for chat JSON, 0.0 for Cypher/GQL/SPARQL - Routes: Direct (palette answer), GraphQuery (cold path), DeepThinking Wired into default_strategies() as strategy #17. The planner now handles BOTH paths: Cold: Cypher → DataFusion → Arrow → Lance (columns/rows) Hot: Chat → ChatBundle → Base17 → HHTL → RouteAction 121 planner tests passing. https://claude.ai/code/session_01M3at4EuHVvQ8S95mSnKgtK
AdaWorldAPI
pushed a commit
that referenced
this pull request
Mar 31, 2026
Full pipeline: user message → TripleModel update → 4096 heads evaluate → CandidatePool rank → NARS revise → autocomplete hit or LLM fallthrough. 6 cache modules, 39 cache tests, 156 total planner tests: kv_bundle.rs: HeadPrint, AttentionMatrix (HIP 64×64, TWIG 256×256) candidate_pool.rs: ranked candidates, Phase (Exposition→Coda) triple_model.rs: self/user/impact × 4096 heads, DK, Plasticity lane_eval.rs: Euler-gamma tension, DK-adaptive evaluation nars_engine.rs: SpoHead, Pearl 2³, 7 NARS rules, StyleVectors chat_bundle.rs: AutocompleteCache orchestrator + PlanStrategy impl Benchmarked: 611M SPO lookups/sec, 18K tokens/sec, 388 KB RAM. https://claude.ai/code/session_01M3at4EuHVvQ8S95mSnKgtK
AdaWorldAPI
pushed a commit
that referenced
this pull request
Mar 31, 2026
Full pipeline: user message → TripleModel update → 4096 heads evaluate → CandidatePool rank → NARS revise → autocomplete hit or LLM fallthrough. 6 cache modules, 39 cache tests, 156 total planner tests: kv_bundle.rs: HeadPrint, AttentionMatrix (HIP 64×64, TWIG 256×256) candidate_pool.rs: ranked candidates, Phase (Exposition→Coda) triple_model.rs: self/user/impact × 4096 heads, DK, Plasticity lane_eval.rs: Euler-gamma tension, DK-adaptive evaluation nars_engine.rs: SpoHead, Pearl 2³, 7 NARS rules, StyleVectors chat_bundle.rs: AutocompleteCache orchestrator + PlanStrategy impl Benchmarked: 611M SPO lookups/sec, 18K tokens/sec, 388 KB RAM. https://claude.ai/code/session_01M3at4EuHVvQ8S95mSnKgtK
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
2 participants
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.
Implements the primary search path for lance-graph using progressive 8-byte edge encodings and 3-hop neighborhood vector traversal.
ZeckF64 encoding: byte 0 = 7 SPO band classifications (boolean lattice, 19 legal patterns, ~85% error detection), bytes 1-7 = distance quantiles. ScopeBuilder: O(N²) pairwise construction of [ZeckF64; N] vectors. SearchCascade: HEEL (1 vec) → HIP (50 vecs) → TWIG (50 vecs) → LEAF.
32 tests (22 unit + 10 integration), all passing.
https://claude.ai/code/session_01NUMNX67KZrFiTQK7erFQuH