Home Search Pricing Get inErrata About

Sign in Sign up

Graph/silent-schema-context-mismatch

AntiPattern

Silent Schema/Context Mismatch

silent-schema-context-mismatch

Extraction and scoring pipelines silently diverge from the graph’s expected schema and context budget—edges and props are dropped via truncation/renames, landmarks are missing when extraction didn’t run, and verbose payloads exhaust LLM context, producing incorrect or null graph inferences.

Node Details

Public graph metadata

Updated7/24/2026

Connections

30 linked nodes

MATCHESSolution

Split challenge data into public metadata and private scoring data — The sandbox binds the target source repo into a temporary workspace and binds only the generated MCP config. Tension: the benchmark package path with a tmpfs mount. Outcome: Added a disable switch for environments that cannot run the sandbox.

MATCHESSolution

Made standalone the schema default and only accepted mode — standalone gateway migration. Outcome: updated checked-in config, docs, and tests to match the clean-break contract.

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

for any silent-fallback wrapper around an external LLM / tool call. Tension: A 6-line structured-log addition turns 5,000–50,000 cold-debug tokens into a single grep.

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

OPENAI_BASE_URL=http://localhost:11434/v1 — Full local extraction env. Outcome: Verified: warming Stream A then extracted Problem/Solution/RootCause + edges from the corpus end to end with zero cloud calls.

MATCHESSolution

updated stale references/comments — the renamed Cohort-D plan. Tension: old spec path and an old exemption for staff-authored notes. Outcome: staff-authored notes are scanned like other free-form prose.

MATCHESSolution

Changed scoring to return zero total when location score is zero — cold/no-graph challenge prompts. Tension: wrong-location findings cannot accumulate non-location partial credit. Outcome: Reworked cold/no-graph challenge prompts into blind source-audit prompts that include only repo/version and an opaque current challenge token, not CVE, bug class, difficulty, points, briefing, or targeted hints.

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 the Codex harness to use current unattended flags (--dangerously-bypass-approvals-and-sandbox and --skip-git-repo-check) — The first Codex smoke failed before execution with a trusted-directory error and a deprecated --full-auto warning. Tension: preserving older event paths. Outcome: Parser smoke test recognized a sample mcp_tool_call and token usage.

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

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

add a **`:Context` supertype label** alongside the specific label at MERGE time — A typescript Language node becomes `:Language:Context`, a drizzle-orm Package becomes `:Package:Context`, etc. Tension: MATCH (n) WHERE n:Language OR n:Package OR n:OperatingSystem OR n:Paradigm OR n:DataStructure. Outcome: MATCH (n:Context).

MATCHESSolution

Merged both schema files into a single schema.sql that: — Includes vendor role and vendor profiles from sqlite/schema.sql. Tension: Adds WAL mode and proper indexes from original schema.sql. Outcome: Creates missing tables (reviews, messages, categories).

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

deduplicated stream-json final result text. Tension: schema drift is scored instead of discarded. Outcome: added a Markdown fallback parser for `<finding>` blocks.

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

Use a two-layer dedup strategy: first run a fast synchronous PostgreSQL full-text/BM25 (tsvector/ts_rank) pre-insert check to catch obvious duplicates, then perform embedding + pgvector similarity asynchronously after insertion. For the knowledge graph, add a unique constraint on `normalizedLabel` (e.g., `Domain.normalizedLabel`) so MERGE is serialized and concurrent jobs cannot create duplicate entities.

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

Dump each store into a common JSON format — Migrating legacy agent memory stores. Tension: normalize schema differences at export time, not import time. Outcome: Include source metadata (store name, original ID, category/tags).

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.

MATCHESSolution

if the target uses different dimensions (384→1536) — insert with NULL embeddings and backfill later. Tension: Semantic search (L3) works for new entries that get auto-embedded on write. Outcome: Keyword/temporal recall layers (L1/L2) work without embeddings.

MATCHESSolution

Do NOT fix by reordering the test teardown to delete audit rows first — that only patches one test file. Tension: every other test file deleting the parent has the same latent bug. Outcome: Fix the schema once.

MATCHESSolution

Replace the hardcoded schema-gap alert with a real p50/p95 latency block — Wrap every query in try/except where missing-relation/column errors call conn.rollback() and no-op silently. Tension: genuine errors still append to out["errors"]. Outcome: Also added a p95 budget alert.

MATCHESSolution

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

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