Eval Library
S
For SourcegraphCode Assistant

Precise Code Navigation

Sourcegraph (Cody + Amp) · Sourcegraph

Code Intelligence — Sourcegraph

Sourcegraph evals — Precise Code Navigation (relift v3 InfraRed)

About Sourcegraph

Sourcegraph is a code intelligence and AI coding platform: universal code search, precise code navigation, Cody chat grounded in your codebase, cross-repo batch changes, and the Amp autonomous agent — deployed across large enterprise codebases.

Employees

~150

Industry

Code Intelligence

Headquarters

San Francisco, CA

Sample tests· showing 3 of 9

#InputExpected behaviorCheck
01

User clicks go-to-definition on `applyPatch` in a TS file. The popup shows three candidate definitions across the repo, two from node_modules. No precise (SCIP) badge appears.

Per docs/code_navigation, when a SCIP index is present for the commit + language, the navigation returns a single precise definition. The multi-candidate UI indicates Sourcegraph fell back to search-based heuristics — i.e., no fresh SCIP index. Trigger or wait for `scip-typescript` upload for this …

Pass / FailCode Assistanthigh
02

User searches `type:symbol Sanitize lang:go` expecting just the Go function symbol; results include unrelated `Sanitize` struct fields and constants.

Per docs/code-search/queries, type:symbol uses the Sourcegraph symbols service / SCIP index (when present) to enumerate declared symbols. To narrow to a kind, add `select:symbol.function` (or `.struct`, `.method`). Cite the select filter section.

Pass / FailCode Assistantmedium
03

Operator wants every caller of public API `acme/lib.Sanitize` across the entire instance, not just within the defining repo.

With cross-repo SCIP indexes uploaded (matching SCIP symbol moniker scheme per docs/code_navigation/explanations/uploads), Find References returns callers across repos. If only the defining repo is indexed precisely, callers in other repos surface via search-based fallback — clearly flagged in the …

Pass / FailCode Assistanthigh

How this eval is graded

Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.

Rubric criteria

  • Sourcegraph
  • Code Assistant
  • Precise Code Navigation

Recommended for

Sourcegraph (Cody + Amp)Sourcegraph customers

Works with

Related evals

Run this eval in your workspace

Connect your data, configure thresholds, and review results with your team.