@kevinrabun/judges 3.118.0 → 3.121.0

package/README.md

@@ -15,7 +15,7 @@ An MCP (Model Context Protocol) server that provides a panel of **45 specialized
 [![npm](https://img.shields.io/npm/v/@kevinrabun/judges)](https://www.npmjs.com/package/@kevinrabun/judges)
 [![npm downloads](https://img.shields.io/npm/dw/@kevinrabun/judges)](https://www.npmjs.com/package/@kevinrabun/judges)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Tests](https://img.shields.io/badge/tests-2412-brightgreen)](https://github.com/KevinRabun/judges/actions)
+[![Tests](https://img.shields.io/badge/tests-2481-brightgreen)](https://github.com/KevinRabun/judges/actions)
 
 > 🔰 **Packages**
 > - **CLI**: `@kevinrabun/judges-cli` → binary `judges` (use `npx @kevinrabun/judges-cli eval --file app.ts`).
@@ -1098,6 +1098,36 @@ Analyze a dependency manifest file for supply-chain risks, version pinning issue
 | `manifestType` | string | yes | File type: `package.json`, `requirements.txt`, etc. |
 | `context` | string | no | Optional context |
 
+### `evaluate_git_diff`
+Evaluate only **changed lines** from a git diff. Provide either `repoPath` for a live git diff or `diffText` for a pre-computed unified diff.
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `repoPath` | string | conditional | Absolute path to the git repository |
+| `base` | string | no | Git ref to diff against (default: `HEAD~1`) |
+| `diffText` | string | conditional | Pre-computed unified diff text |
+| `confidenceFilter` | number | no | Minimum confidence threshold for findings (0–1) |
+| `autoTune` | boolean | no | Apply feedback-driven auto-tuning (default: false) |
+| `maxPromptChars` | number | no | Max character budget for LLM prompts (default: 100000, 0 = unlimited) |
+| `config` | object | no | Inline configuration |
+
+### `re_evaluate_with_context`
+Re-run the tribunal with **prior findings as context** for iterative refinement. Supports dispute resolution, developer context injection, and focus-area filtering.
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `code` | string | yes | Source code to re-evaluate |
+| `language` | string | yes | Programming language |
+| `disputedRuleIds` | string[] | no | Rule IDs the developer disputes as false positives |
+| `acceptedRuleIds` | string[] | no | Rule IDs the developer accepts |
+| `developerContext` | string | no | Free-form explanation of developer intent |
+| `focusAreas` | string[] | no | Specific areas to focus on (e.g., `["security"]`) |
+| `confidenceFilter` | number | no | Minimum confidence threshold (default: 0.5) |
+| `filePath` | string | no | File path for context-aware evaluation |
+| `deepReview` | boolean | no | Include LLM deep-review prompt section |
+| `relatedFiles` | array | no | Cross-file context `{ path, snippet, relationship? }[]` |
+| `maxPromptChars` | number | no | Max character budget for LLM prompts (default: 100000, 0 = unlimited) |
+
 #### Judge IDs
 
 `data-security` · `cybersecurity` · `cost-effectiveness` · `scalability` · `cloud-readiness` · `software-practices` · `accessibility` · `api-design` · `reliability` · `observability` · `performance` · `compliance` · `data-sovereignty` · `testing` · `documentation` · `internationalization` · `dependency-health` · `concurrency` · `ethics-bias` · `maintainability` · `error-handling` · `authentication` · `database` · `caching` · `configuration-management` · `backwards-compatibility` · `portability` · `ux` · `logging-privacy` · `rate-limiting` · `ci-cd` · `code-structure` · `agent-instructions` · `ai-code-safety` · `framework-safety` · `iac-security` · `false-positive-review`

package/dist/api.d.ts

@@ -11,6 +11,7 @@
 export type { Severity, Verdict, Finding, Patch, LangFamily, JudgesConfig, RuleOverride, ProjectFile, ProjectVerdict, DiffVerdict, DependencyEntry, DependencyVerdict, JudgeEvaluation, TribunalVerdict, JudgeDefinition, EvaluationContextV2, EvidenceBundleV2, SpecializedFindingV2, TribunalVerdictV2, MustFixGateOptions, MustFixGateResult, AppBuilderWorkflowResult, PlainLanguageFinding, WorkflowTask, PolicyProfile, SuppressionRecord, SuppressionResult, ExecutionTrace, RuleTrace, StreamingBatch, JudgeSelectionContext, JudgeSelectionResult, SessionContext, } from "./types.js";
 export { JudgesError, ConfigError, EvaluationError, ParseError } from "./errors.js";
 export { parseConfig, defaultConfig, mergeConfigs, discoverCascadingConfigs, loadCascadingConfig, loadConfigFile, expandEnvPlaceholders, loadPluginJudges, validatePluginSpecifiers, isValidJudgeDefinition, validateJudgeDefinition, applyOverridesForFile, applyLanguageProfile, resolveExtendsConfig, } from "./config.js";
+export { EXT_TO_LANG, SUPPORTED_EXTENSIONS, detectLanguageFromPath } from "./ext-to-lang.js";
 export { JUDGES, getJudge, getJudgeSummaries } from "./judges/index.js";
 export { evaluateWithJudge, evaluateWithTribunal, evaluateWithTribunalStreaming, evaluateProject, evaluateDiff, analyzeDependencies, enrichWithPatches, crossEvaluatorDedup, crossFileDedup, diffFindings, formatFindingDiff, evaluateNetChangeGate, applyInlineSuppressions, applyInlineSuppressionsWithAudit, runAppBuilderWorkflow, formatVerdictAsMarkdown, formatEvaluationAsMarkdown, clearEvaluationCaches, scanProjectWideSecurityPatterns, } from "./evaluators/index.js";
 export type { FindingDiff, NetChangeGateOptions, NetChangeGateResult, EvaluationOptions } from "./evaluators/index.js";
@@ -20,7 +21,7 @@ export { getPreset, composePresets, listPresets, PRESETS } from "./presets.js";
 export type { Preset } from "./presets.js";
 export { evaluateCodeV2, evaluateProjectV2, getSupportedPolicyProfiles } from "./evaluators/v2.js";
 export { analyzeCrossFileTaint } from "./ast/cross-file-taint.js";
-export { buildSingleJudgeDeepReviewSection, buildTribunalDeepReviewSection, buildSimplifiedDeepReviewSection, isContentPolicyRefusal, DEEP_REVIEW_PROMPT_INTRO, DEEP_REVIEW_IDENTITY, } from "./tools/deep-review.js";
+export { buildSingleJudgeDeepReviewSection, buildTribunalDeepReviewSection, buildSimplifiedDeepReviewSection, formatRelatedFilesSection, isContentPolicyRefusal, DEEP_REVIEW_PROMPT_INTRO, DEEP_REVIEW_IDENTITY, DEFAULT_MAX_PROMPT_CHARS, } from "./tools/deep-review.js";
 export type { RelatedFileSnippet } from "./tools/deep-review.js";
 export { getCondensedCriteria } from "./tools/prompts.js";
 export { parseDismissedFindings, recordL2Feedback, loadFeedbackStore, saveFeedbackStore, addFeedback, computeFeedbackStats, getFpRateByRule, mergeFeedbackStores, computeTeamFeedbackStats, formatTeamStatsOutput, } from "./commands/feedback.js";
@@ -69,7 +70,7 @@ export { compareCapabilities, formatComparisonReport, formatFullComparisonMatrix
 export type { ToolProfile, ToolCapability, ComparisonResult } from "./comparison.js";
 export { runBenchmarkSuite, benchmarkGate, formatBenchmarkReport, formatBenchmarkMarkdown, analyzeL2Coverage, formatL2CoverageReport, ingestFindingsAsBenchmarkCases, deduplicateIngestCases, BENCHMARK_CASES, } from "./commands/benchmark.js";
 export type { BenchmarkCase, BenchmarkResult, BenchmarkGateOptions, BenchmarkGateResult, L2CoverageAnalysis, L2JudgeCoverage, L2CategoryCoverage, } from "./commands/benchmark.js";
-export { parseLlmRuleIds, constructPerJudgePrompt, constructTribunalPrompt, selectStratifiedSample, scoreLlmCase, computeLlmMetrics, formatLlmSnapshotMarkdown, formatLayerComparisonMarkdown, extractValidatedLlmFindings, getValidRulePrefixes, } from "./commands/llm-benchmark.js";
+export { parseLlmRuleIds, constructPerJudgePrompt, constructTribunalPrompt, selectStratifiedSample, scoreLlmCase, computeLlmMetrics, formatLlmSnapshotMarkdown, formatLayerComparisonMarkdown, extractValidatedLlmFindings, getValidRulePrefixes, getTribunalValidPrefixes, } from "./commands/llm-benchmark.js";
 export type { LlmBenchmarkSnapshot, LlmCaseResult } from "./commands/llm-benchmark.js";
 export type { LlmFinding, ValidationResult } from "./probabilistic/llm-response-validator.js";
 export { optimizeBenchmark, formatAmendmentSection, createEmptyStore, mergeAmendments, } from "./commands/llm-benchmark-optimizer.js";

package/dist/api.js

@@ -12,6 +12,8 @@
 export { JudgesError, ConfigError, EvaluationError, ParseError } from "./errors.js";
 // ─── Config ──────────────────────────────────────────────────────────────────
 export { parseConfig, defaultConfig, mergeConfigs, discoverCascadingConfigs, loadCascadingConfig, loadConfigFile, expandEnvPlaceholders, loadPluginJudges, validatePluginSpecifiers, isValidJudgeDefinition, validateJudgeDefinition, applyOverridesForFile, applyLanguageProfile, resolveExtendsConfig, } from "./config.js";
+// ─── Language Detection ──────────────────────────────────────────────────────
+export { EXT_TO_LANG, SUPPORTED_EXTENSIONS, detectLanguageFromPath } from "./ext-to-lang.js";
 // ─── Judge Registry ──────────────────────────────────────────────────────────
 export { JUDGES, getJudge, getJudgeSummaries } from "./judges/index.js";
 // ─── Core Evaluation Functions ───────────────────────────────────────────────
@@ -27,7 +29,7 @@ export { evaluateCodeV2, evaluateProjectV2, getSupportedPolicyProfiles } from ".
 // ─── Cross-File Taint Analysis ───────────────────────────────────────────────
 export { analyzeCrossFileTaint } from "./ast/cross-file-taint.js";
 // ─── Deep Review Prompts ─────────────────────────────────────────────────────
-export { buildSingleJudgeDeepReviewSection, buildTribunalDeepReviewSection, buildSimplifiedDeepReviewSection, isContentPolicyRefusal, DEEP_REVIEW_PROMPT_INTRO, DEEP_REVIEW_IDENTITY, } from "./tools/deep-review.js";
+export { buildSingleJudgeDeepReviewSection, buildTribunalDeepReviewSection, buildSimplifiedDeepReviewSection, formatRelatedFilesSection, isContentPolicyRefusal, DEEP_REVIEW_PROMPT_INTRO, DEEP_REVIEW_IDENTITY, DEFAULT_MAX_PROMPT_CHARS, } from "./tools/deep-review.js";
 // ─── Prompt Utilities ────────────────────────────────────────────────────────
 export { getCondensedCriteria } from "./tools/prompts.js";
 // ─── Feedback & Calibration ─────────────────────────────────────────────────
@@ -78,7 +80,7 @@ export { compareCapabilities, formatComparisonReport, formatFullComparisonMatrix
 // ─── Benchmark Gate ──────────────────────────────────────────────────────────
 export { runBenchmarkSuite, benchmarkGate, formatBenchmarkReport, formatBenchmarkMarkdown, analyzeL2Coverage, formatL2CoverageReport, ingestFindingsAsBenchmarkCases, deduplicateIngestCases, BENCHMARK_CASES, } from "./commands/benchmark.js";
 // ─── LLM Benchmark ──────────────────────────────────────────────────────────
-export { parseLlmRuleIds, constructPerJudgePrompt, constructTribunalPrompt, selectStratifiedSample, scoreLlmCase, computeLlmMetrics, formatLlmSnapshotMarkdown, formatLayerComparisonMarkdown, extractValidatedLlmFindings, getValidRulePrefixes, } from "./commands/llm-benchmark.js";
+export { parseLlmRuleIds, constructPerJudgePrompt, constructTribunalPrompt, selectStratifiedSample, scoreLlmCase, computeLlmMetrics, formatLlmSnapshotMarkdown, formatLayerComparisonMarkdown, extractValidatedLlmFindings, getValidRulePrefixes, getTribunalValidPrefixes, } from "./commands/llm-benchmark.js";
 // ─── LLM Benchmark Optimizer (Self-Teaching) ────────────────────────────────
 export { optimizeBenchmark, formatAmendmentSection, createEmptyStore, mergeAmendments, } from "./commands/llm-benchmark-optimizer.js";
 // Review autopilot (GitHub App / scripts)

package/dist/cli-dispatch.d.ts

@@ -0,0 +1,7 @@
+/**
+ * Command dispatch table — maps CLI command names to their module path
+ * and exported handler function name. Each entry is lazily imported.
+ *
+ * Format: "command-name": ["./module-path.js", "exportedFunctionName"]
+ */
+export declare const COMMAND_TABLE: Record<string, [string, string]>;