@skyramp/mcp 0.2.1-rc.1 → 0.2.2

package/build/prompts/test-recommendation/scopeAssessment.test.js

@@ -1,7 +1,10 @@
 jest.mock("@skyramp/skyramp", () => ({
     WorkspaceConfigManager: { create: jest.fn() },
 }));
-import { isFrontendFile, isTestFile, buildScopeAssessmentSection } from "./scopeAssessment.js";
+import * as fs from "fs";
+import * as path from "path";
+import * as os from "os";
+import { hasFlutterSdkDep, isFrontendFile, isTestFile, buildScopeAssessmentSection } from "./scopeAssessment.js";
 // ---------------------------------------------------------------------------
 // isFrontendFile
 // ---------------------------------------------------------------------------
@@ -56,6 +59,130 @@ describe("isFrontendFile", () => {
     it("returns false for a plain TS API client in utils/ (no frontend dir)", () => {
         expect(isFrontendFile("utils/apiClient.ts")).toBe(false);
     });
+    // Flutter / Dart support — gated on hasFlutterSdkDep.
+    // Without the flag, .dart is unrecognised (legacy behaviour). With it,
+    // .dart is always-frontend (tier 2, before API_DIR_PATTERN).
+    describe(".dart files (Flutter)", () => {
+        it("returns false for .dart without hasFlutterSdkDep (default)", () => {
+            expect(isFrontendFile("lib/main.dart")).toBe(false);
+        });
+        it("returns false for .dart with hasFlutterSdkDep: false", () => {
+            expect(isFrontendFile("lib/main.dart", { hasFlutterSdkDep: false })).toBe(false);
+        });
+        it("returns true for .dart with hasFlutterSdkDep: true", () => {
+            expect(isFrontendFile("lib/main.dart", { hasFlutterSdkDep: true })).toBe(true);
+        });
+        it("returns true for nested .dart files in a Flutter project", () => {
+            expect(isFrontendFile("lib/widgets/game_board.dart", { hasFlutterSdkDep: true })).toBe(true);
+        });
+        it("returns true for .dart even in a directory that would otherwise look API-like (Flutter has no server-side Dart in scope)", () => {
+            // .dart sits in tier 2 (above API_DIR_PATTERN) so it's frontend even
+            // under api/ — there's no server-side Dart web framework that would
+            // make this ambiguous in the Flutter case.
+            expect(isFrontendFile("lib/api/client.dart", { hasFlutterSdkDep: true })).toBe(true);
+        });
+        it("returns true for game.dart at repo root in a Flutter project", () => {
+            expect(isFrontendFile("game.dart", { hasFlutterSdkDep: true })).toBe(true);
+        });
+    });
+});
+// ---------------------------------------------------------------------------
+// hasFlutterSdkDep
+// ---------------------------------------------------------------------------
+describe("hasFlutterSdkDep", () => {
+    let tmpDir;
+    beforeEach(() => {
+        tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), "flutter-pubspec-"));
+    });
+    afterEach(() => {
+        fs.rmSync(tmpDir, { recursive: true, force: true });
+    });
+    it("returns false when pubspec.yaml is absent", () => {
+        expect(hasFlutterSdkDep(tmpDir)).toBe(false);
+    });
+    it("returns true when pubspec.yaml has the canonical Flutter SDK dep", () => {
+        fs.writeFileSync(path.join(tmpDir, "pubspec.yaml"), `name: birdle
+description: A Flutter app.
+dependencies:
+  flutter:
+    sdk: flutter
+  cupertino_icons: ^1.0.6
+`);
+        expect(hasFlutterSdkDep(tmpDir)).toBe(true);
+    });
+    it("returns false for a pure Dart project (no flutter SDK dep)", () => {
+        // Pure Dart server (e.g. shelf, dart_frog) has pubspec.yaml but no flutter SDK
+        fs.writeFileSync(path.join(tmpDir, "pubspec.yaml"), `name: my_dart_server
+description: A Dart server using shelf.
+environment:
+  sdk: ">=3.0.0 <4.0.0"
+dependencies:
+  shelf: ^1.4.0
+  shelf_router: ^1.1.4
+`);
+        expect(hasFlutterSdkDep(tmpDir)).toBe(false);
+    });
+    it("returns false for a Dart CLI tool (no flutter SDK dep)", () => {
+        fs.writeFileSync(path.join(tmpDir, "pubspec.yaml"), `name: my_cli
+description: A Dart CLI.
+environment:
+  sdk: ^3.5.0
+dependencies:
+  args: ^2.5.0
+`);
+        expect(hasFlutterSdkDep(tmpDir)).toBe(false);
+    });
+    it("returns false on a malformed pubspec.yaml (graceful failure)", () => {
+        fs.writeFileSync(path.join(tmpDir, "pubspec.yaml"), "::: not yaml ::: \x00");
+        // Our regex-based check still works on string content; this is more of
+        // a "doesn't throw" test. Returns false because the malformed content
+        // doesn't match the sdk: flutter pattern.
+        expect(hasFlutterSdkDep(tmpDir)).toBe(false);
+    });
+    it("returns true even with extra whitespace and comments in pubspec.yaml", () => {
+        fs.writeFileSync(path.join(tmpDir, "pubspec.yaml"), `name: birdle
+# This is the SDK dep
+dependencies:
+  flutter:
+    sdk:    flutter
+`);
+        expect(hasFlutterSdkDep(tmpDir)).toBe(true);
+    });
+    // Subdir search — common shapes in real Flutter repos.
+    it("returns true when pubspec.yaml lives in app/", () => {
+        fs.mkdirSync(path.join(tmpDir, "app"));
+        fs.writeFileSync(path.join(tmpDir, "app", "pubspec.yaml"), "name: app\ndependencies:\n  flutter:\n    sdk: flutter\n");
+        expect(hasFlutterSdkDep(tmpDir)).toBe(true);
+    });
+    it("returns true when pubspec.yaml lives in mobile/", () => {
+        fs.mkdirSync(path.join(tmpDir, "mobile"));
+        fs.writeFileSync(path.join(tmpDir, "mobile", "pubspec.yaml"), "name: app\ndependencies:\n  flutter:\n    sdk: flutter\n");
+        expect(hasFlutterSdkDep(tmpDir)).toBe(true);
+    });
+    it("returns true for monorepo with apps/<name>/pubspec.yaml", () => {
+        fs.mkdirSync(path.join(tmpDir, "apps", "customer-app"), { recursive: true });
+        fs.writeFileSync(path.join(tmpDir, "apps", "customer-app", "pubspec.yaml"), "name: customer_app\ndependencies:\n  flutter:\n    sdk: flutter\n");
+        expect(hasFlutterSdkDep(tmpDir)).toBe(true);
+    });
+    it("returns true for monorepo with packages/<name>/pubspec.yaml", () => {
+        fs.mkdirSync(path.join(tmpDir, "packages", "ui"), { recursive: true });
+        fs.writeFileSync(path.join(tmpDir, "packages", "ui", "pubspec.yaml"), "name: ui\ndependencies:\n  flutter:\n    sdk: flutter\n");
+        expect(hasFlutterSdkDep(tmpDir)).toBe(true);
+    });
+    it("returns false when monorepo subdirs only contain pure-Dart packages", () => {
+        // Mixed monorepo: a Dart CLI in packages/cli/, no Flutter app anywhere.
+        fs.mkdirSync(path.join(tmpDir, "packages", "cli"), { recursive: true });
+        fs.writeFileSync(path.join(tmpDir, "packages", "cli", "pubspec.yaml"), "name: cli\ndependencies:\n  args: ^2.5.0\n");
+        expect(hasFlutterSdkDep(tmpDir)).toBe(false);
+    });
+    it("does not walk arbitrary subdirs (e.g. node_modules-style nested deps)", () => {
+        // A pubspec deep under an unsupported subdir should NOT be picked up.
+        // Without this guard, a transitive dependency's pubspec could falsely
+        // flag a non-Flutter repo as Flutter.
+        fs.mkdirSync(path.join(tmpDir, "vendor", "nested", "lib"), { recursive: true });
+        fs.writeFileSync(path.join(tmpDir, "vendor", "nested", "lib", "pubspec.yaml"), "name: nested\ndependencies:\n  flutter:\n    sdk: flutter\n");
+        expect(hasFlutterSdkDep(tmpDir)).toBe(false);
+    });
 });
 // ---------------------------------------------------------------------------
 // isTestFile

package/build/prompts/testbot/testbot-prompts.js

@@ -2,6 +2,7 @@ import { z } from "zod";
 import { logger } from "../../utils/logger.js";
 import { AnalyticsService } from "../../services/AnalyticsService.js";
 import { MAX_TESTS_TO_GENERATE, MAX_RECOMMENDATIONS, MAX_CRITICAL_TESTS, PATH_PARAM_UUID_GUIDANCE, AUTH_CONFLICT_ERROR_MSG, } from "../test-recommendation/recommendationSections.js";
+import { buildDriftAnalysisPrompt } from "../test-maintenance/drift-analysis-prompt.js";
 import { getTraceRecordingPromptText } from "../../playwright/traceRecordingPrompt.js";
 import { isContractConsumerModeEnabled } from "../../utils/featureFlags.js";
 import { resolveServiceDetailsRef } from "../../utils/utils.js";
@@ -65,13 +66,9 @@ Use those recommendations as your baseline. Only add or remove tests that the us
    **If \`skyramp_analyze_changes\` returns an error:** retry once only if the error is transient (timeout, network blip, temporary unavailability) — do NOT retry for permanent errors (invalid repository path, missing required parameter, authentication failure). If it fails again, call \`skyramp_submit_report\` with a minimal valid payload: leave all test arrays empty and add the error to \`issuesFound\`. Refer to the \`skyramp_submit_report\` schema for required fields. Do NOT attempt Task 2 without a valid stateFile.
    **If all changed files are non-application** (CI/CD, docs, lock files, config) → skip to Task 3 (Submit Report) with empty arrays and a single \`issuesFound\` entry explaining why (same format as the zero-test path below).
 
-3. **Maintain existing tests:**
+3. **Maintain existing tests** using the rules in \`<drift_analysis_rules>\` below. For each existing test reported by \`skyramp_analyze_changes\`, score it and choose the action exactly as directed by the Action Decision Matrix in \`<drift_analysis_rules>\`. Only read test files that require action per that matrix — do NOT read files that will be IGNORED. **Do NOT read source files (routers, models, CRUD, components) — all the information you need is in the \`skyramp_analyze_changes\` output and the diff.** When reading multiple test files, **read them all in a single parallel batch** — do NOT read them one at a time. Apply actions directly. Results go in \`testMaintenance\`.
 
-   a. Call \`skyramp_analyze_test_health\` with \`stateFile\` (from step 2). Follow every instruction in the returned \`<drift_analysis_rules>\` block — use the Action Decision Tree, apply the Breaking Change Patterns, and work through each check (Endpoint Existence, Response Shape, Additive Fields, Auth/AuthZ, Behavioral Contract, Assign Action). **Do NOT read source files** — all information you need is in the \`skyramp_analyze_changes\` output and the diff. When reading multiple test files that require action, **read them all in a single parallel batch**.
-
-   b. For each test scored UPDATE or REGENERATE, write \`updateInstructions\` (a concise description of what must change) **before** calling \`skyramp_actions\`. This articulation step prevents the LLM from letting file content override diff-based reasoning.
-
-   c. Call \`skyramp_actions\` with \`stateFile\` (from step 2) and your \`recommendations[]\` — one entry per test assessed, including IGNORE and VERIFY. The tool returns file content for each UPDATE/REGENERATE test — apply the edits. Results go in \`testMaintenance\`.
+${buildDriftAnalysisPrompt({ existingTests: [], scannedEndpoints: [], repositoryPath })}
 
 4. **Code review:** From the \`skyramp_analyze_changes\` output and the existing test files you read for maintenance, note any logic bugs. Do NOT read additional source files just for code review — use what is already available from the analysis and test file reads. Common patterns to flag:
    - Computed fields not recalculated after mutation (e.g. \`total_amount\` unchanged after items are added/removed)
@@ -130,7 +127,7 @@ ${userPrompt ? "Generate only the tests that the user requested from the Additio
   Keep advancing until you have created exactly ${maxGenerate} new test files OR exhausted all candidates.
 - Example: If enrichment reveals that sending \`discount_value\` without \`discount_type\` silently orphans the value (a concrete bug), complete all planned GENERATE items first, then generate this discovered scenario as an extra test and report it in \`newTestsCreated\`.
 - Total generated: Follow the "Budget: N generate" line in the Execution Plan. Process every GENERATE-tagged item in order. Backfill from ADDITIONAL candidates (highest-ranked first) until \`newTestsCreated\` reaches ${maxGenerate} or all candidates are exhausted.
-- **UI test priority**: If the diff contains frontend/UI changes (e.g. \`.tsx\`, \`.jsx\`, \`.vue\`, \`.svelte\` files), you MUST attempt to generate at least one UI test. Use \`browser_navigate\` to the app's base URL — if the app responds, record a trace and generate the test.
+- **UI test priority**: If the PR scope assessment shows any UI/E2E budget OR \`uiContext.changedFrontendFiles\` is non-empty (the deterministic server signal — populated for all supported frontend file types including \`.tsx\`/\`.jsx\`/\`.vue\`/\`.svelte\`/\`.dart\`), you MUST attempt to generate at least one UI test. Use \`browser_navigate\` to the app's base URL — if the app responds, record a trace and generate the test.
   **Skip only if one of these conditions is met:**
   - **(a) App is unreachable** — \`browser_navigate\` fails or connection is refused.
   - **(b) Unintegrated non-route component** — the changed file is a leaf component (not a framework route/entrypoint) that has no integration point in the running app. To confirm:
@@ -276,7 +273,7 @@ If a test **generation** tool call fails:
 1. **Retry once** with the same parameters.
 2. If it fails again, **skip** that candidate and move to the next ranked candidate.
 3. If all candidates in the GENERATE set fail, fall back to generating the **simplest possible test**: a single contract test for the highest-scored endpoint (GET → 200 or POST → 201).
-   **Exception — frontend-only PRs**: If the diff modifies ONLY frontend files (\`.tsx\`, \`.jsx\`, \`.vue\`, \`.svelte\`, \`.css\`, \`.html\`) AND browser recording was not possible, do NOT generate a backend fallback contract test — it is irrelevant to the PR. Instead move ALL GENERATE candidates to \`additionalRecommendations\` and proceed to Task 3.
+   **Exception — frontend-only PRs**: If the diff modifies ONLY frontend files (\`.tsx\`, \`.jsx\`, \`.vue\`, \`.svelte\`, \`.dart\`, \`.css\`, \`.html\`) AND browser recording was not possible, do NOT generate a backend fallback contract test — it is irrelevant to the PR. Instead move ALL GENERATE candidates to \`additionalRecommendations\` and proceed to Task 3.
 4. Log skipped candidates in \`issuesFound\` with the error message.
 
 If a test **execution** (\`skyramp_execute_test\`) fails for a newly generated test:
@@ -334,7 +331,7 @@ Call \`skyramp_submit_report\` with \`summaryOutputFile\`: "${summaryOutputFile}
 - **additionalRecommendations**: AT MOST ${maxRecommendations - maxGenerate} items.
   - For \`testType: "contract"\` entries: **\`primaryEndpoint\` is required** (e.g. \`"GET /api/v1/users/{user_id}"\`). The tool will reject the submission without it — do not omit it or you will be forced to resubmit.
   - For \`testType: "integration"\` or \`"e2e"\` entries: omit \`primaryEndpoint\` — use \`description\` to list the endpoints involved instead.
-- **testMaintenance**: Use \`[]\` **only** if no existing Skyramp tests were found in the repository. If existing tests were found (any score), include one entry per test. Set \`action\` to the exact drift action assigned by the Action Decision Tree (\`UPDATE\`, \`REGENERATE\`, \`DELETE\`, \`VERIFY\`, or \`IGNORE\`). For UPDATE/REGENERATE/DELETE tests that were modified and executed, populate all fields from real before/after execution results. For VERIFY/IGNORE tests (not modified), derive \`beforeStatus\` from the drift assessment you performed in step 3 (typically \`"Pass"\` if no drift was detected), set \`afterStatus\` to \`"Skipped"\`, and use \`afterDetails\` to explain why (e.g. "IGNORE: no drift detected — endpoint not modified in this PR"). Do **not** add entries for tests that were not assessed in step 3.
+- **testMaintenance**: Use \`[]\` **only** if no existing Skyramp tests were found in the repository. If existing tests were found (any score), include one entry per test. Set \`action\` to the exact drift action you chose from the Action Decision Matrix (\`UPDATE\`, \`REGENERATE\`, \`DELETE\`, \`VERIFY\`, or \`IGNORE\`). For UPDATE/REGENERATE/DELETE tests that were modified and executed, populate all fields from real before/after execution results. For VERIFY/IGNORE tests (not modified), derive \`beforeStatus\` from the \`skyramp_analyze_test_health\` health score (typically \`"Pass"\` if drift score is 0 and no health issues were flagged), set \`afterStatus\` to \`"Skipped"\`, and use \`afterDetails\` to explain why (e.g. "IGNORE: drift score 0 — endpoint not modified in this PR"). Do **not** add entries for tests that were not returned by the health analysis.
 
 ---
 

package/build/prompts/testbot/testbot-prompts.test.js

@@ -202,40 +202,35 @@ describe("uiCredentials in getTestbotPrompt", () => {
             .toThrow("</ui-credentials>");
     });
 });
-describe("drift analysis — runtime tool call (step 3)", () => {
-    // The build-time embed of buildDriftAnalysisPrompt was replaced with a
-    // runtime instruction: LLM calls skyramp_analyze_test_health then skyramp_actions.
+describe("drift analysis inline embedding", () => {
+    beforeAll(() => { process.env.SKYRAMP_FEATURE_TESTBOT = "1"; });
+    afterAll(() => { delete process.env.SKYRAMP_FEATURE_TESTBOT; });
     function basePrompt() {
         return getTestbotPrompt(baseArgs.prTitle, baseArgs.prDescription, baseArgs.summaryOutputFile, baseArgs.repositoryPath);
     }
-    it("step 3 instructs the LLM to call skyramp_analyze_test_health", () => {
+    it("wraps inline drift rules in XML tags", () => {
         const prompt = basePrompt();
-        expect(prompt).toContain("skyramp_analyze_test_health");
+        expect(prompt).toContain("<drift_analysis_rules>");
+        expect(prompt).toContain("</drift_analysis_rules>");
     });
-    it("step 3 instructs the LLM to call skyramp_actions with recommendations[]", () => {
+    it("does not include a persona statement inside the inline XML block", () => {
         const prompt = basePrompt();
-        expect(prompt).toContain("skyramp_actions");
-        expect(prompt).toContain("recommendations[]");
+        const start = prompt.indexOf("<drift_analysis_rules>");
+        const end = prompt.indexOf("</drift_analysis_rules>");
+        const block = prompt.slice(start, end);
+        expect(block).not.toContain("You are acting as a Skyramp Integration Architect");
     });
-    it("step 3 appears inside Task 1, before Task 2", () => {
+    it("drift_analysis_rules block appears inside Task 1, before Task 2", () => {
         const prompt = basePrompt();
         const task1Pos = prompt.indexOf("## Task 1");
-        const healthPos = prompt.indexOf("skyramp_analyze_test_health");
+        const rulesPos = prompt.indexOf("<drift_analysis_rules>");
         const task2Pos = prompt.indexOf("## Task 2");
-        expect(healthPos).toBeGreaterThan(task1Pos);
-        expect(healthPos).toBeLessThan(task2Pos);
+        expect(rulesPos).toBeGreaterThan(task1Pos);
+        expect(rulesPos).toBeLessThan(task2Pos);
     });
-    it("does not contain the build-time embedded drift_analysis_rules content (Action Decision Tree)", () => {
-        // The rules are now fetched at runtime via skyramp_analyze_test_health —
-        // the <drift_analysis_rules> tag may appear as a reference in prose,
-        // but the actual rule content (Action Decision Tree) must not be baked in.
+    it("Task 1 step 3 prose references drift_analysis_rules tag", () => {
         const prompt = basePrompt();
-        expect(prompt).not.toContain("Action Decision Tree\n\nFor each existing test");
-        expect(prompt).not.toContain("Update Execution Rules\n\nWhen applying UPDATE actions");
-    });
-    it("does not contain a persona statement (no nested identity from old embed)", () => {
-        const prompt = basePrompt();
-        expect(prompt).not.toContain("You are acting as a Skyramp Integration Architect");
+        expect(prompt).toContain("rules in `<drift_analysis_rules>`");
     });
 });
 describe("UI grounding via Task 2 capture-act-capture", () => {
@@ -365,4 +360,25 @@ describe("testbot prompt blueprint-grounded recommendations (slice 4)", () => {
         // Make sure we removed the old capturedBlueprints threading directive.
         expect(prompt).not.toMatch(/capturedBlueprints/);
     });
+    // Flutter support — both the generalised UI trigger wording and the
+    // canvas/empty-ARIA issuesFound rule should appear in the prompt.
+    it("UI test priority defers to the deterministic server signal (uiContext.changedFrontendFiles), not just hard-coded extensions", () => {
+        const prompt = getTestbotPrompt(baseArgs.prTitle, baseArgs.prDescription, baseArgs.summaryOutputFile, baseArgs.repositoryPath);
+        // The trigger must reference the server signal (changedFrontendFiles)
+        // — that's what makes it framework-agnostic. Hard-coded extension lists
+        // become illustrative, not gating.
+        expect(prompt).toMatch(/uiContext.*changedFrontendFiles|changedFrontendFiles.*uiContext/);
+        // .dart should appear in the supported-types example list
+        expect(prompt).toMatch(/\.dart/);
+    });
+    it("frontend-only PR exception lists .dart alongside other frontend extensions", () => {
+        const prompt = getTestbotPrompt(baseArgs.prTitle, baseArgs.prDescription, baseArgs.summaryOutputFile, baseArgs.repositoryPath);
+        // The frontend-only-PR exception block (Task 2 backend-fallback skip)
+        // must include .dart so a Flutter-only PR doesn't emit a backend
+        // contract test as a fallback.
+        const exceptionBlock = prompt.slice(prompt.indexOf("Exception — frontend-only PRs"), prompt.indexOf("Exception — frontend-only PRs") + 800);
+        expect(exceptionBlock).toContain(".dart");
+        expect(exceptionBlock).toContain(".tsx");
+        expect(exceptionBlock).toContain(".vue");
+    });
 });

package/build/services/TestDiscoveryService.js

@@ -1,5 +1,6 @@
 import * as fs from "fs";
 import * as path from "path";
+import { simpleGit } from "simple-git";
 import { logger } from "../utils/logger.js";
 import { TestSource } from "../types/TestAnalysis.js";
 import fg from "fast-glob";
@@ -53,8 +54,11 @@ export class TestDiscoveryService {
         /[\\/]__tests__[\\/]/,
         /[\\/]spec[\\/]/,
     ];
+    // Cache git client and repo status per repository
+    gitClientCache = new Map();
+    isGitRepoCache = new Map();
     /**
-     * Discover all tests under testDir — both Skyramp-generated and external (user-written).
+     * Discover all tests in a repository — both Skyramp-generated and external (user-written).
      * Uses fast-glob for cross-platform file scanning, then classifies discovered files
      * as Skyramp-generated tests, external tests, or not-a-test during processing.
      *
@@ -64,17 +68,19 @@ export class TestDiscoveryService {
      *   rather than flooding context with irrelevant files.
      * - `undefined` (full-repo mode, no diff): cap at MAX_EXTERNAL_FULL_REPO.
      */
-    async discoverTests(testDir, options = {}) {
-        logger.info(`Starting test discovery in: ${testDir}`);
-        if (!fs.existsSync(testDir)) {
-            throw new Error(`Test directory does not exist: ${testDir}`);
+    async discoverTests(repositoryPath, options = {}) {
+        logger.info(`Starting test discovery in: ${repositoryPath}`);
+        if (!fs.existsSync(repositoryPath)) {
+            throw new Error(`Repository path does not exist: ${repositoryPath}`);
         }
-        const stats = fs.statSync(testDir);
+        const stats = fs.statSync(repositoryPath);
         if (!stats.isDirectory()) {
-            throw new Error(`Path is not a directory: ${testDir}`);
+            throw new Error(`Path is not a directory: ${repositoryPath}`);
         }
-        // File classification: skyramp vs external vs not-a-test (carries content forward).
-        const classified = this.classifyTestFiles(testDir);
+        // Initialize git client cache for this repository
+        await this.initializeGitClient(repositoryPath);
+        // File classification: skyramp vs external vs not-a-test (carries content forward)
+        const classified = this.classifyTestFiles(repositoryPath);
         logger.info(`Found ${classified.skyramp.length} Skyramp test files, ${classified.external.length} external test files`);
         // Process Skyramp tests (content already cached from classification)
         const skyrampTests = await this.processFilesInBatches(classified.skyramp, false, classified.contentCache);
@@ -133,6 +139,9 @@ export class TestDiscoveryService {
         }));
         const externalTests = [...relevantExternalTests, ...otherExternalTests];
         logger.info(`Discovered ${skyrampTests.length} Skyramp tests, ${externalTests.length} external tests`);
+        // Clean up caches to free memory
+        this.gitClientCache.clear();
+        this.isGitRepoCache.clear();
         return {
             tests: [...skyrampTests, ...externalTests],
             // Expose the relevant file paths so callers can build read instructions for the LLM.
@@ -177,6 +186,27 @@ export class TestDiscoveryService {
         }
         return { relevant, other };
     }
+    /**
+     * Initialize git client and check if repository is a git repo
+     */
+    async initializeGitClient(repositoryPath) {
+        try {
+            const git = simpleGit(repositoryPath);
+            this.gitClientCache.set(repositoryPath, git);
+            const isRepo = await git.checkIsRepo();
+            this.isGitRepoCache.set(repositoryPath, isRepo);
+            if (isRepo) {
+                logger.debug(`Git repository detected at: ${repositoryPath}`);
+            }
+            else {
+                logger.debug(`Not a git repository: ${repositoryPath}`);
+            }
+        }
+        catch (error) {
+            logger.debug(`Could not initialize git client: ${error.message}`);
+            this.isGitRepoCache.set(repositoryPath, false);
+        }
+    }
     /**
      * Process test files in parallel batches with concurrency control
      * @param isExternal When true, uses external test metadata extraction