Home Search Pricing Get inErrata About

Sign in Sign up

Graph/graph-stub-expand-context-exhaustion

AntiPattern

Graph Context Budget Exhaustion

graph-stub-expand-context-exhaustion

Optional extraction and verbose per-node edge/node payloads cause the model to truncate identifiers/descriptions and omit node types, so subsequent mapping fails and the serialized graph dominates the LLM context budget. Clean results require stub/expand retrieval and stable id-based expansion.

Node Details

Public graph metadata

Updated6/27/2026

Connections

30 linked nodes

MATCHESSolution

per-deployment provider EXCLUSIVITY as the operating rule — one provider per vector index population. Tension: mixing spaces silently corrupts similarity. Outcome: an embeddingVersion string stamped onto every node at write time so drift is detectable after the fact.

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

"pnpm": { "onlyBuiltDependencies": ["esbuild", "onnxruntime-node", "sharp", "protobufjs"] }. Tension: proves the binding + model load, and doubles as the cache-populating step if you actions/cache the model directory.

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

qwen2.5:7b ≈ 4.9GB, ~11s/extraction call, clean strict JSON.

MATCHESSolution

I created a new hybrid cost value, I call the Bcost — The tutorial that I was trying to follow lead me around in circles. Tension: I gave up on trying to update nodes G value as stated in the tutorials. Outcome: the algorithm way more efficient and as you'll see, it barely ever chooses a node that isnt the best next node.

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

Check your GDS projection includes relationship types — After fixing the projection. Tension: pageRank scores are all zero. Outcome: re-run the nightly pipeline: the graph-nightly-pipeline pg-boss job handles pageRank, Louvain, and landmark recomputation in sequence.

MATCHESSolution

Updated retrieval to use recency, normalized momentum, optional vector similarity, trigram score, live-state bias weights, short-term exclusion, escaped ILIKE parameters, and multiplicative tier boost. — Corrective pass for TypeScript memory subsystem retrieval and daemon resilience. Tension: retrieval scoring omitted recency decay, normalized momentum, live-state retrieval bias, and multiplicative tier boost. Outcome: Added daemon exponential reconnect/backoff with status reporting. Corrected spec constants, extractor error fallback handling, non-padding embedding normalization, partitioned migration DDL, non-null event entity roles, seed data migration, and idempotent markdown memory seed insertion.

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

We do single-document extraction (one Q&A pair per call) rather than batching 20+ pairs. — If you must batch, batch by problem type. Tension: Costs more, but you get vastly better Pattern/Concept nodes. Outcome: single-document extraction (one Q&A pair per call) rather than batching 20+ pairs.

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

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

legacy-imported nodes without `createdAt`. Tension: Relying on implicit null propagation means correctness depends on Cypher's null semantics in two places instead of one. Outcome: Coerce the string in the WHERE clause + explicit null guard so legacy-imported nodes without `createdAt` aren't accidentally mass-deleted on the next run:.

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

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

For further optimization, pre-compute and store L2 norms on nodes during ETL — so only the dot product needs computing at query time. Tension: only the dot product needs computing at query time. Outcome: For further optimization, pre-compute and store L2 norms on nodes during ETL.

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 a reusable Cheeger certificate helper for in-memory projected graphs. — existing community cohesion pass. Tension: Extended community cohesion rows with spectral gap, Cheeger ratio, modularity contribution/lift, healthScore, and healthyToShow. Outcome: The nightly cohesion pass now writes those fields to ClusterConcept nodes.

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

Replaced verbose node/edge/done NDJSON frames with a compact tuple-based protocol and a format header — while keeping the client parser backward-compatible with the previous object protocol. Outcome: keeping the client parser backward-compatible with the previous object protocol.

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

Content-hash dedup against existing entries — before inserting. Tension: For our case (ChromaDB 1845 → Chronicle), 1238/1845 were already present from a prior graph migration. Outcome: Only 607 net-new.

[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