Skip to main content
Glama
Repo Test Architect

Repo Test Architect

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

Start with review_repository for an unfamiliar repository or a general request to review test architecture; it returns a bounded review that fits a model's context. Use analyze_repository only when the complete bundle with per-target evidence is explicitly needed; it can exceed client limits on large repositories. Treat blockers, unsupported projects, and failedProjects entries as explicit audit coverage gaps. Use specialist tools only when the user requests a narrower artifact or supplies an existing audit artifact; pass repoRoot (plus projectRoot for single-project tools) instead of echoing a large artifact back. Use audit_repo only for an explicitly selected single project root and adapter; it defaults to JavaScript. Do not reclassify repository facts from raw source when a deterministic artifact already provides them. generate_selected_test is deferred and does not write test code.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
review_repositoryA

Start here for an unfamiliar repository or a general test-architecture review. Detect and audit all project roots once, then return a bounded deterministic review: summary counts, blockers, top findings, the top-ranked candidates and plan items with execution hints, verification commands, and stats. limit caps the ranked lists (default 25) and per-test evidence is reduced to counts, so the result stays small on large monorepos. Use explain_target with repoRoot and projectRoot for one target's evidence, and analyze_repository only when the complete bundle is explicitly needed.

analyze_repositoryA

Return the complete repository-analysis/v1 bundle: every project audit with per-target test evidence plus the derived summary, findings, ranking, plan, execution hints, and stats. The result grows with repository size and can exceed client limits on large monorepos, so prefer review_repository first and use this only when the complete bundle is explicitly needed or the repository is small.

list_adaptersA

List registered language adapters available to audit repositories.

list_project_detection_rulesA

List deterministic project marker rules and ignored directories used during project detection.

detect_projectsA

Discover project roots, support status, and matching adapters without auditing source targets. Use this when project boundaries are needed before a specialized workflow; use review_repository for a general review. Reads local repository markers and returns project-detection/v1 without executing tests or writing files.

audit_projectsA

Return raw per-project audit artifacts for all detected supported roots, report unsupported roots, and list roots whose adapter failed in failedProjects. Use when a downstream specialist tool needs project-audits/v1; for a general first-pass review, prefer review_repository. The result can be large; specialist tools also accept repoRoot directly, so the artifact rarely needs to be passed back.

summarize_project_auditsA

Summarize an existing project-audits/v1 artifact. Use only when a compact coverage view is needed separately; review_repository returns a bounded version of this result; pass repoRoot here for the complete artifact.

rank_project_candidatesA

Rank candidates from an existing project-audits/v1 artifact while preserving project identity. review_repository returns a bounded version of this result; pass repoRoot here for the complete artifact.

generate_project_test_planA

Generate a project-aware plan from an existing project-audits/v1 artifact. review_repository returns a bounded version of this result; pass repoRoot here for the complete artifact.

collect_project_findingsA

Collect concise top findings from an existing project-audits/v1 artifact. review_repository returns a bounded version of this result; pass repoRoot here for the complete artifact.

analyze_project_test_placementA

Derive advisory test-placement findings across audited projects while preserving project identity, from a project-audits/v1 artifact or, with repoRoot, from a fresh audit. Use analyze_test_placement for one project. Does not execute tests or create, move, or modify files.

collect_project_statsA

Aggregate coverage, counts, risk and signal distributions, frameworks, and adapter usage from a project-audits/v1 artifact or, with repoRoot, from a fresh audit. Use this for separate reporting or comparisons; review_repository already includes the same stats. Returns project-stats/v1 without executing tests or writing files.

audit_repoA

Audit one explicitly selected project root and return audit/v1. Use only when the caller selected a single adapter or project boundary; adapterId defaults to javascript. For an unfamiliar repository or a general review, use review_repository.

get_audit_graphA

Return one project's audit/v1 artifact: validate and return a saved audit unchanged, or pass repoRoot plus projectRoot to audit that detected project. Use audit_repo when the adapter is selected explicitly, and review_repository for a general review.

generate_test_planA

Create a deterministic plan/v1 for one project, optionally selecting one exact plan item; use generate_project_test_plan for multiple audited projects. Pass an existing audit/v1 artifact, or pass repoRoot plus projectRoot to audit that project deterministically. Does not execute tests or generate or write test code.

get_plan_execution_hintsA

Derive provider-neutral execution, context, parallel-safety, and repository-reasoning hints from a plan without invoking models or subagents. Pass an existing plan/v1 or project-test-plan/v1 artifact, or pass repoRoot to derive hints for the project-aware plan of that repository.

explain_targetA

Explain the evidence, risk, testability, and recommendation for one audited target, including its complete existing-test evidence. Use this after review_repository when one target needs detail: pass repoRoot plus the projectRoot and targetId from the review, or pass an existing audit/v1 artifact. Returns target-explanation/v1 without executing tests or writing files.

rank_test_candidatesA

Rank testable audit targets of one project by risk reduction and maintenance cost. Pass an existing audit/v1 artifact, or pass repoRoot plus projectRoot to audit that project deterministically.

analyze_test_placementA

Derive advisory test-placement findings for one project; use analyze_project_test_placement for multiple audited projects. Pass an existing audit/v1 artifact, or pass repoRoot plus projectRoot to audit that project deterministically. Does not execute tests or create, move, or modify files.

generate_selected_testA

Return a structured deferred result. This tool does not generate or write test code while native generation remains disabled.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.8/5.0

Scored across 20 tools

Disambiguation3/5

There is a clear effort to distinguish tools via descriptions (e.g. review_repository vs analyze_repository bounded-vs-complete, single-project vs multi-project variants), but the surface contains many near-parallel families: audit_repo vs get_audit_graph vs audit_projects, and rank_test_candidates vs rank_project_candidates, etc. An agent must read carefully to select the right tool, and several boundaries (audit_repo/get_audit_graph in particular) remain genuinely fuzzy.

Naming Consistency4/5

Names are uniformly snake_case and overwhelmingly follow a verb_noun pattern (list_adapters, review_repository, generate_project_test_plan, analyze_test_placement). Minor deviations exist where a noun precedes a qualifier (get_audit_graph, explain_target), and the project_ infix is inconsistently applied as a scoping hint, but the overall convention is predictable.

Tool Count3/5

Twenty tools is on the heavy side for the domain, and much of the count comes from redundant project-level vs single-project variants of the same operations. The breadth is defensible given the layered workflow (detect, audit, review, rank, plan, explain), but it feels over-expanded rather than tightly scoped.

Completeness4/5

The lifecycle for a read-only test-architecture review is well covered: detection, audit, bounded and full analysis, summarization, ranking, planning, placement, stats, and execution hints. The one notable dead end is generate_selected_test, which is a structured stub that generates nothing, but the core analysis surface has no glaring gaps.

Maintenance

ActivityActive
ResponsivenessOutdated data