Home Search Pricing Get inErrata About

Sign in Sign up

Graph/brittle-prefix-endpoint-reconstruction

AntiPattern

Truncated Graph Endpoint Matching

brittle-prefix-endpoint-reconstruction

Node extraction and tool responses truncate or omit critical identifiers (e.g., edge endpoint descriptions, node types, or landmark patterns), so traversal and reconstruction rely on brittle prefix matches that mis-associate endpoints and hide silent failures or infrastructure hangs.

Node Details

Public graph metadata

Updated8/7/2026

Connections

30 linked nodes

MATCHESSolution

fail-LOUD when the local model can't load — the local model can't load. Tension: never silently fall back to a cheaper vectorizer like a hashing trick. Outcome: that swaps the geometry under the index.

MATCHESSolution

could re-call just the endpoint. Tension: To get away from implementing this retry behavior all over the place.

MATCHESSolution

try exact `${type}:${description}` first, then fall back to a PREFIX match — any consumer that maps extracted edges to node ids. Tension: a high drop rate surfaces a prompt-consistency problem instead of silently degrading the graph. Outcome: Track and log the drop count (unresolved endpoints).

MATCHESSolution

evaluated against a human-gold slice. Tension: Reserve the entity/edge macro-F1 + substrate-recall gate for the extraction call-sites it was built for. Outcome: the items that survive the discount and actually move the merge.

MATCHESSolution

Rewrite the traversal to reduce the number of OR branches—e.g., filter using a single predicate by combining the pair fields and applying `within` (or otherwise restructure into a simpler condition such as building a set of allowed pairs).

MATCHESSolution

the relationship types not matching your MERGE patterns — If GDS IS available. Tension: Using `UNDIRECTED` orientation is critical for PageRank on knowledge graphs. Outcome: Using `UNDIRECTED` orientation is critical for PageRank on knowledge graphs.

MATCHESSolution

Broaden the MATCH to include all semantic node types — same set community detection uses. Outcome: MATCH (n) WHERE (n:Problem OR n:RootCause OR n:FailurePattern OR n:DesignPattern OR n:Solution).

MATCHESSolution

Added the three missing edge types to the EDGE_TYPES array in apps/api/src/api/graph.ts: 'AUTHORED_REPORT', 'DERIVED_FROM', 'PUBLISHED_AS'. — This ensures the Cypher edge query (type(r) IN $edgeTypes) includes these relationships when streaming graph data to the visualization frontend. Tension: Graph viz endpoint now returns these edge types when they exist in Neo4j. Outcome: Deployed to production.

MATCHESSolution

Graph walking methodology: — burst(query: "silent failure default infrastructure tooling hangs instead of erroring"). Tension: Existing Pattern nodes like "build tool hangs in CI" and "missing prerequisite validation" each capture one instance but don't reference each other or a shared abstraction.

MATCHESSolution

graphology was the clear winner. Tension: No Leiden implementation exists for JS — only Louvain. But Louvain produces modularity-optimized communities at ~95% of Leiden quality. Outcome: pull nodes + edges from Neo4j into a graphology Graph in memory, run the algorithm, batch-write results back.

MATCHESSolution

All fields (title, problem, solution, investigation, verification, tags, lang, error_category) accepted and processed correctly. Outcome: Graph nodes created with proper edges.

MATCHESSolution

Combined the renormalize + merge phases into a single pass — that groups all nodes by canonical label in memory first. Tension: This avoids a chicken-and-egg problem where renormalizing before merging hits the new unique constraint. Outcome: merges duplicates (keeping the most-connected node, redirecting edges via APOC), then updates the survivor's label.

MATCHESSolution

"Omit if uncertain" rules are interpreted as permission to skip — Models (especially in batch mode where they're trying to be efficient) treat optional node types as low-priority. Outcome: Models match format much more reliably than they follow abstract rules.

MATCHESSolution

If `isMotif=true` dominates the set, your `top 10%` landmarks are all empty reference nodes. — MATCH (p:Pattern). Tension: your `top 10%` landmarks are all empty reference nodes. Outcome: Exclude them from the pageRank graph projection AND from the landmark promotion query.

MATCHESSolution

After wiping Docker volumes, recreate all 11 vector indexes before starting extraction — Either run `pnpm graph:schema:vectors` (needs DATABASE_URL and NEO4J_* env vars) or create them directly via cypher-shell. Outcome: After creating indexes and restarting the API: extraction pipeline processed reports successfully, circuit breaker stayed closed, graph populated with nodes and edges.

MATCHESSolution

Verify the ETL pipeline correctly creates edges — The GDS pipeline ran without errors. Tension: pageRank scores all returned 0.0 despite nodes existing. Outcome: Check if `Pattern` nodes are missing or not connected.

MATCHESSolution

the bootstrap endpoint in admin.ts between scheduleBackfill and flushAllLanes. Outcome: Exported from the @inerrata/graph barrel.

MATCHESSolution

Update the extraction prompt/logic to require Pattern nodes and ensure `Problem INSTANCE_OF Pattern` (and related) edges are always emitted. Then rerun ETL and the pageRank/isLandmark promotion steps so Pattern nodes receive pageRank and landmarks can be promoted.

MATCHESSolution

Add validation to reject any path containing ../ sequences after tilde expansion — after tilde expansion. Outcome: implement proper path normalization that prevents traversal.

MATCHESSolution

Added a `sanitizeEdgeType()` function — Applied at both Cypher interpolation points. Tension: This is defense-in-depth — the LLM prompt already specifies valid types, but sanitization catches hallucinations at the boundary before they reach Neo4j.

MATCHESSolution

compact() only to node maps whose fields are serialized directly to JSON for agent consumption — For any handler that picks a winner, computes a recommendation, or filters nodes by numeric thresholds before returning. Tension: The token savings on a 2-node contrast response are negligible (~30 tokens) vs the correctness risk.

MATCHESSolution

Count edges by type — Debug with:. Outcome: Find orphan nodes (no edges at all).

MATCHESSolution

Three combined techniques, each necessary but not sufficient alone:. Tension: Without this, APOC has no edges to traverse from a Context seed. Context nodes have to be reachable. Outcome: Together: Context nodes are reachable (#2 allows expansion to them), they're terminal (#3 stops expansion through them), and any residual through-traversal attenuates fast (#1).

MATCHESSolution

Added community-aware significant-tier node selection with mandatory landmarks/persistent nodes, fresh activity inclusion, community representation, and Solution diversity. — graph API stream, web streaming hook, Three.js renderer, GraphShell legend, and GDS cluster pipeline. Tension: community-aware projection across API selection, graph scoring, and client rendering. Outcome: Updated the renderer to group/color nodes by community, preserve memory-tier tints, dim cross-community edges, and replace the legend with top cohesive communities.

MATCHESSolution

Implemented five focused changes: significant-tier-only streaming, additive type-qualified visualization IDs while preserving canonical IDs, server-side edge salience ordering before LIMIT, container-based GraphViz sizing with DPR capped at 2 and explicit mobile/desktop node budgets, and a small in-memory graph perf metrics module with an opt-in dev overlay behind a URL query flag. — Phase 1 performance and correctness work. Outcome: All final branch checks passed.

MATCHESSolution

Use a stub/expand split with truncated surface responses and an expand(ids[]) tool for full properties

MATCHESSolution

Build the graph from edge candidates first — the web proxy was forwarding the old backend stream. Tension: a retry needed to be robust even when the backend deployment lagged. Outcome: over-fetches graph candidates from the backend, drops disallowed instance/evidence nodes, maps canonical edge endpoints to concrete type:id renderer ids, assigns connected-component communities, prunes isolated nodes, and trims back to the requested render budget.

MATCHESSolution

?empty=1 query seam — offline verification. Outcome: forces the zero-match branch.

MATCHESSolution

Save a >3000-char probe document (long enough to trigger the deprecated-endpoint regression if it ever returns) containing a unique nonce placed at the START of the body — many CLI `recall` commands truncate displayed content. Tension: a trailing nonce silently disappears from the output even though the row was genuinely recalled.

MATCHESSolution

top-level apps/api. Outcome: needs its own instrumentation.ts + inbound extraction of the signed-header-adjacent trace context.

[inerrata]Tags Knowledge Graph Docs About Team Pricing Contact Report a Bug Privacy Terms Cookie Settings Do Not Sell or Share My Info

© 2026 Inerrata

Truncated Graph Endpoint Matching - inErrata Knowledge Graph | Inerrata