@kevinrabun/judges 3.34.1 → 3.36.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +37 -0
- package/README.md +19 -17
- package/dist/api.d.ts +1 -1
- package/dist/api.d.ts.map +1 -1
- package/dist/api.js +1 -1
- package/dist/api.js.map +1 -1
- package/dist/commands/benchmark-ai-output.d.ts +10 -0
- package/dist/commands/benchmark-ai-output.d.ts.map +1 -0
- package/dist/commands/benchmark-ai-output.js +366 -0
- package/dist/commands/benchmark-ai-output.js.map +1 -0
- package/dist/commands/benchmark.d.ts.map +1 -1
- package/dist/commands/benchmark.js +2 -0
- package/dist/commands/benchmark.js.map +1 -1
- package/dist/dedup.d.ts.map +1 -1
- package/dist/dedup.js +98 -0
- package/dist/dedup.js.map +1 -1
- package/dist/evaluators/framework-safety.d.ts.map +1 -1
- package/dist/evaluators/framework-safety.js +268 -0
- package/dist/evaluators/framework-safety.js.map +1 -1
- package/dist/evaluators/hallucination-detection.d.ts.map +1 -1
- package/dist/evaluators/hallucination-detection.js +55 -2
- package/dist/evaluators/hallucination-detection.js.map +1 -1
- package/dist/evaluators/index.d.ts +10 -0
- package/dist/evaluators/index.d.ts.map +1 -1
- package/dist/evaluators/index.js +130 -6
- package/dist/evaluators/index.js.map +1 -1
- package/dist/evaluators/logic-review.d.ts +3 -0
- package/dist/evaluators/logic-review.d.ts.map +1 -0
- package/dist/evaluators/logic-review.js +263 -0
- package/dist/evaluators/logic-review.js.map +1 -0
- package/dist/evaluators/project.d.ts +19 -0
- package/dist/evaluators/project.d.ts.map +1 -1
- package/dist/evaluators/project.js +2 -2
- package/dist/evaluators/project.js.map +1 -1
- package/dist/evaluators/testing.d.ts.map +1 -1
- package/dist/evaluators/testing.js +39 -0
- package/dist/evaluators/testing.js.map +1 -1
- package/dist/finding-lifecycle.d.ts +55 -0
- package/dist/finding-lifecycle.d.ts.map +1 -1
- package/dist/finding-lifecycle.js +174 -0
- package/dist/finding-lifecycle.js.map +1 -1
- package/dist/judges/framework-safety.d.ts.map +1 -1
- package/dist/judges/framework-safety.js +12 -6
- package/dist/judges/framework-safety.js.map +1 -1
- package/dist/judges/index.d.ts.map +1 -1
- package/dist/judges/index.js +4 -0
- package/dist/judges/index.js.map +1 -1
- package/dist/judges/logic-review.d.ts +3 -0
- package/dist/judges/logic-review.d.ts.map +1 -0
- package/dist/judges/logic-review.js +33 -0
- package/dist/judges/logic-review.js.map +1 -0
- package/dist/patches/index.d.ts.map +1 -1
- package/dist/patches/index.js +227 -0
- package/dist/patches/index.js.map +1 -1
- package/dist/tools/register-review.d.ts +7 -0
- package/dist/tools/register-review.d.ts.map +1 -0
- package/dist/tools/register-review.js +372 -0
- package/dist/tools/register-review.js.map +1 -0
- package/dist/tools/register-workflow.d.ts.map +1 -1
- package/dist/tools/register-workflow.js +73 -1
- package/dist/tools/register-workflow.js.map +1 -1
- package/dist/tools/register.d.ts +1 -1
- package/dist/tools/register.d.ts.map +1 -1
- package/dist/tools/register.js +3 -1
- package/dist/tools/register.js.map +1 -1
- package/dist/types.d.ts +30 -0
- package/dist/types.d.ts.map +1 -1
- package/package.json +2 -2
- package/server.json +3 -3
package/CHANGELOG.md
CHANGED
|
@@ -2,6 +2,43 @@
|
|
|
2
2
|
|
|
3
3
|
All notable changes to **@kevinrabun/judges** are documented here.
|
|
4
4
|
|
|
5
|
+
## [3.36.0] — 2026-03-10
|
|
6
|
+
|
|
7
|
+
### Added
|
|
8
|
+
- **New judge: logic-review** — 7 detection categories for semantic correctness: inverted security conditions (critical), off-by-one errors (high), dead code after return/throw (medium), name-body mismatch (medium), swapped comparison operands (high), empty catch/except blocks (medium), redundant boolean comparisons (low). 45 judges total.
|
|
9
|
+
- **Review verdict & summary** — `synthesizeReviewDecision()` wired into `TribunalVerdict`, producing an approve/request-changes/comment decision with blocking findings list and executive summary.
|
|
10
|
+
- **Package registry verification** — expanded fabricated package detection: 50+ npm names, 30+ Python names, Go module hallucination patterns, Java/Kotlin hallucination patterns, and dependency confusion detection for unscoped packages with internal-looking names.
|
|
11
|
+
- **Test adequacy assessment** — 2 new test quality checks: happy-path-only detection (test files with ≥3 cases but no error/edge scenarios) and status-code-only detection (API tests that only assert HTTP codes without body verification).
|
|
12
|
+
- **LLM contextual auto-fixes** — `enrichWithContextualFixes()` generates `suggestedFix` for findings that lack a deterministic patch, using actual code context from affected lines.
|
|
13
|
+
- **Triage feedback learning loop** — `computeTriageFeedback()` and `applyTriageFeedback()` adjust confidence scores based on historical false-positive rates from the finding lifecycle store. Rules with FP rate >30% get proportional confidence reduction (max -0.3).
|
|
14
|
+
- **JetBrains IDE integration guide** — documentation for connecting Judges as an MCP server in IntelliJ IDEA, WebStorm, PyCharm, GoLand, and Rider via `.mcp.json` or IDE settings.
|
|
15
|
+
- **AI-output benchmark suite** — 18 new benchmark cases targeting LLM-generated code patterns: logic inversions, off-by-one errors, dead code, name-body mismatches, swapped operands, empty catch blocks, happy-path-only tests, status-code-only tests, dependency confusion, and 3 negative (clean code) cases.
|
|
16
|
+
|
|
17
|
+
### Changed (VS Code Extension)
|
|
18
|
+
- **Diff-aware evaluation** — new `judges.evaluateDiff` command evaluates the full file but only reports findings on lines changed relative to git HEAD (±2 line context margin).
|
|
19
|
+
- **Judge grouping in findings panel** — new "Sort by Judge" mode groups findings by judge prefix (AUTH, CRYPTO, LOGIC, etc.) with collapsible tree nodes.
|
|
20
|
+
|
|
21
|
+
### Tests
|
|
22
|
+
- 1,082 tests pass across 218 suites
|
|
23
|
+
|
|
24
|
+
## [3.35.0] — 2026-03-10
|
|
25
|
+
|
|
26
|
+
### Added
|
|
27
|
+
- **Dedup: 12 new topic patterns** — timing-attack, ssrf, mass-assignment, insecure-deserialization, info-disclosure, denial-of-service, file-upload-security, missing-access-control, hardcoded-config, unsafe-html-render, a11y-violation — eliminates duplicate findings across judges
|
|
28
|
+
- **Auto-fix: 10 new multi-line patch rules** — timing-safe comparison (`crypto.timingSafeEqual`), path traversal prevention, hardcoded secrets → env vars, open redirect validation, SSRF URL allowlist, insecure cookies, Java SQL injection (→ `PreparedStatement`), Python f-string SQL (→ parameterized), CSP header insertion, C# SQL injection (→ `SqlParameter`)
|
|
29
|
+
- **Framework judges: 17 new patterns** — Django (5: SESSION_COOKIE_SECURE, SECURE_SSL_REDIRECT, mark_safe, FILE_UPLOAD_PERMISSIONS, locals/globals in render), Flask (2: send_file path traversal, session without SECRET_KEY), Spring Boot (5: @RequestBody without @Valid, permitAll on sensitive paths, Jackson default typing, hardcoded credentials, logging sensitive data), ASP.NET Core (5: missing UseHttpsRedirection, mass assignment model binding, string interpolation in ILogger, ProblemDetails with exception message, missing [Authorize] on [ApiController])
|
|
30
|
+
- **Suppression analytics** — `getSuppressionAnalytics()` and `formatSuppressionAnalytics()` functions for analyzing FP rates by rule, suppression rates by judge, auto-suppress candidates, and actionable tuning recommendations
|
|
31
|
+
- **5 new MCP tools for conversational review:**
|
|
32
|
+
- `explain_finding` — plain-language explanation with OWASP/CWE references and remediation guidance
|
|
33
|
+
- `triage_finding` — set triage status (accepted-risk, deferred, wont-fix, false-positive) with attribution
|
|
34
|
+
- `get_finding_stats` — lifecycle statistics: open, fixed, triaged counts with trends
|
|
35
|
+
- `get_suppression_analytics` — FP rates, auto-suppress candidates, per-judge analytics
|
|
36
|
+
- `list_triaged_findings` — browse triaged findings with optional status filter
|
|
37
|
+
- **Benchmark dashboard MCP tool** — `run_benchmark` returns full dashboard with per-judge, per-category, per-difficulty breakdowns in markdown, JSON, or summary format
|
|
38
|
+
|
|
39
|
+
### Tests
|
|
40
|
+
- 1,075 tests pass across 217 suites
|
|
41
|
+
|
|
5
42
|
## [3.34.1] — 2026-03-10
|
|
6
43
|
|
|
7
44
|
### Fixed
|
package/README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Judges Panel
|
|
2
2
|
|
|
3
|
-
An MCP (Model Context Protocol) server that provides a panel of **
|
|
3
|
+
An MCP (Model Context Protocol) server that provides a panel of **45 specialized judges** to evaluate AI-generated code — acting as an independent quality gate regardless of which project is being reviewed. Combines **deterministic pattern matching & AST analysis** (instant, offline, zero LLM calls) with **LLM-powered deep-review prompts** that let your AI assistant perform expert-persona analysis across all 45 domains.
|
|
4
4
|
|
|
5
5
|
**Highlights:**
|
|
6
6
|
- Includes an **App Builder Workflow (3-step)** demo for release decisions, plain-language risk summaries, and prioritized fixes — see [Try the Demo](#2-try-the-demo).
|
|
@@ -21,7 +21,7 @@ AI code generators (Copilot, Cursor, Claude, ChatGPT, etc.) write code fast —
|
|
|
21
21
|
|
|
22
22
|
| | ESLint / Biome | SonarQube | Semgrep / CodeQL | **Judges** |
|
|
23
23
|
|---|---|---|---|---|
|
|
24
|
-
| **Scope** | Style + some bugs | Bugs + code smells | Security patterns | **
|
|
24
|
+
| **Scope** | Style + some bugs | Bugs + code smells | Security patterns | **45 domains**: security, cost, compliance, a11y, API design, cloud, UX, … |
|
|
25
25
|
| **AI-generated code focus** | No | No | Partial | **Purpose-built** for AI output failure modes |
|
|
26
26
|
| **Setup** | Config per project | Server + scanner | Cloud or local | **One command**: `npx @kevinrabun/judges eval file.ts` |
|
|
27
27
|
| **Auto-fix patches** | Some | No | No | **114 deterministic patches** — instant, offline |
|
|
@@ -79,7 +79,7 @@ judges eval --min-score 80 src/api.ts
|
|
|
79
79
|
# One-line summary for scripts
|
|
80
80
|
judges eval --summary src/api.ts
|
|
81
81
|
|
|
82
|
-
# List all
|
|
82
|
+
# List all 45 judges
|
|
83
83
|
judges list
|
|
84
84
|
```
|
|
85
85
|
|
|
@@ -190,7 +190,7 @@ npm run build
|
|
|
190
190
|
|
|
191
191
|
### 2. Try the Demo
|
|
192
192
|
|
|
193
|
-
Run the included demo to see all
|
|
193
|
+
Run the included demo to see all 45 judges evaluate a purposely flawed API server:
|
|
194
194
|
|
|
195
195
|
```bash
|
|
196
196
|
npm run demo
|
|
@@ -293,7 +293,7 @@ Install the **[Judges Panel](https://marketplace.visualstudio.com/items?itemName
|
|
|
293
293
|
|
|
294
294
|
- **Inline diagnostics & quick-fixes** on every file save
|
|
295
295
|
- **`@judges` chat participant** — type `@judges` in Copilot Chat, or just ask for a "judges panel review" and Copilot routes automatically
|
|
296
|
-
- **Auto-configured MCP server** — all
|
|
296
|
+
- **Auto-configured MCP server** — all 45 expert-persona prompts available to Copilot with zero setup
|
|
297
297
|
|
|
298
298
|
```bash
|
|
299
299
|
code --install-extension kevinrabun.judges-panel
|
|
@@ -420,7 +420,7 @@ All commands support `--help` for usage details.
|
|
|
420
420
|
|
|
421
421
|
### `judges eval`
|
|
422
422
|
|
|
423
|
-
Evaluate a file with all
|
|
423
|
+
Evaluate a file with all 45 judges or a single judge.
|
|
424
424
|
|
|
425
425
|
| Flag | Description |
|
|
426
426
|
|------|-------------|
|
|
@@ -656,7 +656,7 @@ const svg2 = generateBadgeSvg(75, "quality"); // custom label
|
|
|
656
656
|
| **Code Structure** | Structural Analysis | `STRUCT-` | Cyclomatic complexity, nesting depth, function length, dead code, type safety |
|
|
657
657
|
| **Agent Instructions** | Agent Instruction Markdown Quality & Safety | `AGENT-` | Instruction hierarchy, conflict detection, unsafe overrides, scope, validation, policy guidance |
|
|
658
658
|
| **AI Code Safety** | AI-Generated Code Quality & Security | `AICS-` | Prompt injection, insecure LLM output handling, debug defaults, missing validation, unsafe deserialization of AI responses |
|
|
659
|
-
| **Framework Safety** | Framework-Specific Security & Best Practices | `FW-` | React hooks ordering, Express middleware chains, Next.js SSR/SSG pitfalls, Angular/Vue lifecycle patterns,
|
|
659
|
+
| **Framework Safety** | Framework-Specific Security & Best Practices | `FW-` | React hooks ordering, Express middleware chains, Next.js SSR/SSG pitfalls, Angular/Vue lifecycle patterns, Django/Flask/FastAPI safety, Spring Boot security, ASP.NET Core auth & CORS, Go Gin/Echo/Fiber patterns |
|
|
660
660
|
| **IaC Security** | Infrastructure as Code | `IAC-` | Terraform, Bicep, ARM template misconfigurations, hardcoded secrets, missing encryption, overly permissive network/IAM rules |
|
|
661
661
|
| **Security** | General Security Posture | `SEC-` | Holistic security assessment — insecure data flows, weak cryptography, unsafe deserialization |
|
|
662
662
|
| **Hallucination Detection** | AI-Hallucinated API & Import Validation | `HALLU-` | Detects hallucinated APIs, fabricated imports, and non-existent modules from AI code generators |
|
|
@@ -665,6 +665,7 @@ const svg2 = generateBadgeSvg(75, "quality"); // custom label
|
|
|
665
665
|
| **Multi-Turn Coherence** | Code Coherence & Consistency | `COH-` | Self-contradicting patterns, duplicate definitions, dead code, inconsistent naming |
|
|
666
666
|
| **Model Fingerprint Detection** | AI Code Provenance & Model Attribution | `MFPR-` | Detects stylistic fingerprints characteristic of specific AI code generators |
|
|
667
667
|
| **Over-Engineering** | Simplicity & Pragmatism | `OVER-` | Unnecessary abstractions, wrapper-mania, premature generalization, over-complex patterns |
|
|
668
|
+
| **Logic Review** | Semantic Correctness & Logic Integrity | `LOGIC-` | Inverted conditions, dead code, name-body mismatch, off-by-one, incomplete control flow |
|
|
668
669
|
| **False-Positive Review** | False Positive Detection & Finding Accuracy | `FPR-` | Meta-judge reviewing pattern-based findings for false positives: string literal context, comment/docstring matches, test scaffolding, IaC template gating |
|
|
669
670
|
<!-- JUDGES_TABLE_END -->
|
|
670
671
|
|
|
@@ -678,13 +679,13 @@ The tribunal operates in three layers:
|
|
|
678
679
|
|
|
679
680
|
2. **AST-Based Structural Analysis** — The Code Structure judge (`STRUCT-*` rules) uses real Abstract Syntax Tree parsing to measure cyclomatic complexity, nesting depth, function length, parameter count, dead code, and type safety with precision that regex cannot achieve. All supported languages — **TypeScript, JavaScript, Python, Rust, Go, Java, C#, and C++** — are parsed via **tree-sitter WASM grammars** (real syntax trees compiled to WebAssembly, in-process, zero native dependencies). A scope-tracking structural parser is kept as a fallback when WASM grammars are unavailable. No external AST server required.
|
|
680
681
|
|
|
681
|
-
3. **LLM-Powered Deep Analysis (Prompts)** — The server exposes MCP prompts (e.g., `judge-data-security`, `full-tribunal`) that provide each judge's expert persona as a system prompt. When used by an LLM-based client (Copilot, Claude, Cursor, etc.), the host LLM performs deeper, context-aware probabilistic analysis beyond what static patterns can detect. This is where the `systemPrompt` on each judge comes alive — Judges itself makes no LLM calls, but it provides the expert criteria so your AI assistant can act as
|
|
682
|
+
3. **LLM-Powered Deep Analysis (Prompts)** — The server exposes MCP prompts (e.g., `judge-data-security`, `full-tribunal`) that provide each judge's expert persona as a system prompt. When used by an LLM-based client (Copilot, Claude, Cursor, etc.), the host LLM performs deeper, context-aware probabilistic analysis beyond what static patterns can detect. This is where the `systemPrompt` on each judge comes alive — Judges itself makes no LLM calls, but it provides the expert criteria so your AI assistant can act as 45 specialized reviewers.
|
|
682
683
|
|
|
683
684
|
---
|
|
684
685
|
|
|
685
686
|
## Composable by Design
|
|
686
687
|
|
|
687
|
-
Judges Panel is a **dual-layer** review system: instant **deterministic tools** (offline, no API keys) for pattern and AST analysis, plus **
|
|
688
|
+
Judges Panel is a **dual-layer** review system: instant **deterministic tools** (offline, no API keys) for pattern and AST analysis, plus **45 expert-persona MCP prompts** that unlock LLM-powered deep analysis when connected to an AI client. It does not try to be a CVE scanner or a linter. Those capabilities belong in dedicated MCP servers that an AI agent can orchestrate alongside Judges.
|
|
688
689
|
|
|
689
690
|
### Built-in AST Analysis (v2.0.0+)
|
|
690
691
|
|
|
@@ -733,7 +734,7 @@ When your AI coding assistant connects to multiple MCP servers, each one contrib
|
|
|
733
734
|
|
|
734
735
|
| Layer | What It Does | Example Servers |
|
|
735
736
|
|-------|-------------|-----------------|
|
|
736
|
-
| **Judges Panel** |
|
|
737
|
+
| **Judges Panel** | 45-judge quality gate — security patterns, AST analysis, cost, scalability, a11y, compliance, sovereignty, ethics, dependency health, agent instruction governance, AI code safety, framework safety | This server |
|
|
737
738
|
| **CVE / SBOM** | Vulnerability scanning against live databases — known CVEs, license risks, supply chain | OSV, Snyk, Trivy, Grype MCP servers |
|
|
738
739
|
| **Linting** | Language-specific style and correctness rules | ESLint, Ruff, Clippy MCP servers |
|
|
739
740
|
| **Runtime Profiling** | Memory, CPU, latency measurement on running code | Custom profiling MCP servers |
|
|
@@ -887,7 +888,7 @@ Generated from https://github.com/microsoft/vscode on 2026-02-21T12:00:00.000Z.
|
|
|
887
888
|
List all available judges with their domains and descriptions.
|
|
888
889
|
|
|
889
890
|
### `evaluate_code`
|
|
890
|
-
Submit code to the **full judges panel**. all
|
|
891
|
+
Submit code to the **full judges panel**. all 45 judges evaluate independently and return a combined verdict.
|
|
891
892
|
|
|
892
893
|
| Parameter | Type | Required | Description |
|
|
893
894
|
|-----------|------|----------|-------------|
|
|
@@ -911,7 +912,7 @@ Submit code to a **specific judge** for targeted review.
|
|
|
911
912
|
| `config` | object | no | Inline configuration (see [Configuration](#configuration)) |
|
|
912
913
|
|
|
913
914
|
### `evaluate_project`
|
|
914
|
-
Submit multiple files for **project-level analysis**. all
|
|
915
|
+
Submit multiple files for **project-level analysis**. all 45 judges evaluate each file, plus cross-file architectural analysis detects code duplication, inconsistent error handling, and dependency cycles.
|
|
915
916
|
|
|
916
917
|
| Parameter | Type | Required | Description |
|
|
917
918
|
|-----------|------|----------|-------------|
|
|
@@ -922,7 +923,7 @@ Submit multiple files for **project-level analysis**. all 44 judges evaluate eac
|
|
|
922
923
|
| `config` | object | no | Inline configuration (see [Configuration](#configuration)) |
|
|
923
924
|
|
|
924
925
|
### `evaluate_diff`
|
|
925
|
-
Evaluate only the **changed lines** in a code diff. Runs all
|
|
926
|
+
Evaluate only the **changed lines** in a code diff. Runs all 45 judges on the full file but filters findings to lines you specify. Ideal for PR reviews and incremental analysis.
|
|
926
927
|
|
|
927
928
|
| Parameter | Type | Required | Description |
|
|
928
929
|
|-----------|------|----------|-------------|
|
|
@@ -990,7 +991,7 @@ Each judge has a corresponding prompt for LLM-powered deep analysis:
|
|
|
990
991
|
| `judge-code-structure` | Deep AST-based structural analysis review |
|
|
991
992
|
| `judge-agent-instructions` | Deep review of agent instruction markdown quality and safety |
|
|
992
993
|
| `judge-ai-code-safety` | Deep review of AI-generated code risks: prompt injection, insecure LLM output handling, debug defaults, missing validation |
|
|
993
|
-
| `judge-framework-safety` | Deep review of framework-specific safety: React hooks, Express middleware, Next.js SSR/SSG, Angular/Vue
|
|
994
|
+
| `judge-framework-safety` | Deep review of framework-specific safety: React hooks, Express middleware, Next.js SSR/SSG, Angular/Vue, Django, Spring Boot, ASP.NET Core, Flask, FastAPI, Go frameworks |
|
|
994
995
|
| `judge-iac-security` | Deep review of infrastructure-as-code security: Terraform, Bicep, ARM template misconfigurations |
|
|
995
996
|
| `judge-security` | Deep holistic security posture review: insecure data flows, weak cryptography, unsafe deserialization |
|
|
996
997
|
| `judge-hallucination-detection` | Deep review of AI-hallucinated APIs, fabricated imports, non-existent modules |
|
|
@@ -999,8 +1000,9 @@ Each judge has a corresponding prompt for LLM-powered deep analysis:
|
|
|
999
1000
|
| `judge-multi-turn-coherence` | Deep review of code coherence: self-contradictions, duplicate definitions, dead code |
|
|
1000
1001
|
| `judge-model-fingerprint` | Deep review of AI code provenance and model attribution fingerprints |
|
|
1001
1002
|
| `judge-over-engineering` | Deep review of unnecessary abstractions, wrapper-mania, premature generalization |
|
|
1003
|
+
| `judge-logic-review` | Deep review of logic correctness, semantic mismatches, and dead code in AI-generated code |
|
|
1002
1004
|
| `judge-false-positive-review` | Meta-judge review of pattern-based findings for false positive detection and accuracy |
|
|
1003
|
-
| `full-tribunal` | all
|
|
1005
|
+
| `full-tribunal` | all 45 judges in a single prompt |
|
|
1004
1006
|
<!-- PROMPTS_TABLE_END -->
|
|
1005
1007
|
|
|
1006
1008
|
---
|
|
@@ -1123,7 +1125,7 @@ Each judge scores the code from **0 to 100**:
|
|
|
1123
1125
|
- **WARNING** — Any high finding, any medium finding, or score < 80
|
|
1124
1126
|
- **PASS** — Score ≥ 80 with no critical, high, or medium findings
|
|
1125
1127
|
|
|
1126
|
-
The **overall tribunal score** is the average of all
|
|
1128
|
+
The **overall tribunal score** is the average of all 45 judges. The overall verdict fails if **any** judge fails.
|
|
1127
1129
|
|
|
1128
1130
|
---
|
|
1129
1131
|
|
|
@@ -1260,7 +1262,7 @@ judges/
|
|
|
1260
1262
|
| `judges config export` | Export config as shareable package |
|
|
1261
1263
|
| `judges config import <src>` | Import a shared configuration |
|
|
1262
1264
|
| `judges compare` | Compare judges against other code review tools |
|
|
1263
|
-
| `judges list` | List all
|
|
1265
|
+
| `judges list` | List all 45 judges with domains and descriptions |
|
|
1264
1266
|
|
|
1265
1267
|
---
|
|
1266
1268
|
|
package/dist/api.d.ts
CHANGED
|
@@ -12,7 +12,7 @@ export type { Severity, Verdict, Finding, Patch, LangFamily, JudgesConfig, RuleO
|
|
|
12
12
|
export { JudgesError, ConfigError, EvaluationError, ParseError } from "./errors.js";
|
|
13
13
|
export { parseConfig, defaultConfig, mergeConfigs, discoverCascadingConfigs, loadCascadingConfig, loadPluginJudges, validatePluginSpecifiers, isValidJudgeDefinition, applyOverridesForFile, applyLanguageProfile, resolveExtendsConfig, } from "./config.js";
|
|
14
14
|
export { JUDGES, getJudge, getJudgeSummaries } from "./judges/index.js";
|
|
15
|
-
export { evaluateWithJudge, evaluateWithTribunal, evaluateProject, evaluateDiff, analyzeDependencies, enrichWithPatches, crossEvaluatorDedup, diffFindings, formatFindingDiff, evaluateNetChangeGate, applyInlineSuppressions, applyInlineSuppressionsWithAudit, runAppBuilderWorkflow, formatVerdictAsMarkdown, formatEvaluationAsMarkdown, clearEvaluationCaches, } from "./evaluators/index.js";
|
|
15
|
+
export { evaluateWithJudge, evaluateWithTribunal, evaluateProject, evaluateDiff, analyzeDependencies, enrichWithPatches, crossEvaluatorDedup, diffFindings, formatFindingDiff, evaluateNetChangeGate, applyInlineSuppressions, applyInlineSuppressionsWithAudit, runAppBuilderWorkflow, formatVerdictAsMarkdown, formatEvaluationAsMarkdown, clearEvaluationCaches, scanProjectWideSecurityPatterns, } from "./evaluators/index.js";
|
|
16
16
|
export type { FindingDiff, NetChangeGateOptions, NetChangeGateResult } from "./evaluators/index.js";
|
|
17
17
|
export { evaluateCodeV2, evaluateProjectV2, getSupportedPolicyProfiles } from "./evaluators/v2.js";
|
|
18
18
|
export { analyzeCrossFileTaint } from "./ast/cross-file-taint.js";
|
package/dist/api.d.ts.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"api.d.ts","sourceRoot":"","sources":["../src/api.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAGH,YAAY,EACV,QAAQ,EACR,OAAO,EACP,OAAO,EACP,KAAK,EACL,UAAU,EACV,YAAY,EACZ,YAAY,EACZ,WAAW,EACX,cAAc,EACd,WAAW,EACX,eAAe,EACf,iBAAiB,EACjB,eAAe,EACf,eAAe,EACf,eAAe,EACf,mBAAmB,EACnB,gBAAgB,EAChB,oBAAoB,EACpB,iBAAiB,EACjB,kBAAkB,EAClB,iBAAiB,EACjB,wBAAwB,EACxB,oBAAoB,EACpB,YAAY,EACZ,aAAa,EACb,iBAAiB,EACjB,iBAAiB,GAClB,MAAM,YAAY,CAAC;AAGpB,OAAO,EAAE,WAAW,EAAE,WAAW,EAAE,eAAe,EAAE,UAAU,EAAE,MAAM,aAAa,CAAC;AAGpF,OAAO,EACL,WAAW,EACX,aAAa,EACb,YAAY,EACZ,wBAAwB,EACxB,mBAAmB,EACnB,gBAAgB,EAChB,wBAAwB,EACxB,sBAAsB,EACtB,qBAAqB,EACrB,oBAAoB,EACpB,oBAAoB,GACrB,MAAM,aAAa,CAAC;AAGrB,OAAO,EAAE,MAAM,EAAE,QAAQ,EAAE,iBAAiB,EAAE,MAAM,mBAAmB,CAAC;AAIxE,OAAO,EACL,iBAAiB,EACjB,oBAAoB,EACpB,eAAe,EACf,YAAY,EACZ,mBAAmB,EACnB,iBAAiB,EACjB,mBAAmB,EACnB,YAAY,EACZ,iBAAiB,EACjB,qBAAqB,EACrB,uBAAuB,EACvB,gCAAgC,EAChC,qBAAqB,EACrB,uBAAuB,EACvB,0BAA0B,EAC1B,qBAAqB,
|
|
1
|
+
{"version":3,"file":"api.d.ts","sourceRoot":"","sources":["../src/api.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAGH,YAAY,EACV,QAAQ,EACR,OAAO,EACP,OAAO,EACP,KAAK,EACL,UAAU,EACV,YAAY,EACZ,YAAY,EACZ,WAAW,EACX,cAAc,EACd,WAAW,EACX,eAAe,EACf,iBAAiB,EACjB,eAAe,EACf,eAAe,EACf,eAAe,EACf,mBAAmB,EACnB,gBAAgB,EAChB,oBAAoB,EACpB,iBAAiB,EACjB,kBAAkB,EAClB,iBAAiB,EACjB,wBAAwB,EACxB,oBAAoB,EACpB,YAAY,EACZ,aAAa,EACb,iBAAiB,EACjB,iBAAiB,GAClB,MAAM,YAAY,CAAC;AAGpB,OAAO,EAAE,WAAW,EAAE,WAAW,EAAE,eAAe,EAAE,UAAU,EAAE,MAAM,aAAa,CAAC;AAGpF,OAAO,EACL,WAAW,EACX,aAAa,EACb,YAAY,EACZ,wBAAwB,EACxB,mBAAmB,EACnB,gBAAgB,EAChB,wBAAwB,EACxB,sBAAsB,EACtB,qBAAqB,EACrB,oBAAoB,EACpB,oBAAoB,GACrB,MAAM,aAAa,CAAC;AAGrB,OAAO,EAAE,MAAM,EAAE,QAAQ,EAAE,iBAAiB,EAAE,MAAM,mBAAmB,CAAC;AAIxE,OAAO,EACL,iBAAiB,EACjB,oBAAoB,EACpB,eAAe,EACf,YAAY,EACZ,mBAAmB,EACnB,iBAAiB,EACjB,mBAAmB,EACnB,YAAY,EACZ,iBAAiB,EACjB,qBAAqB,EACrB,uBAAuB,EACvB,gCAAgC,EAChC,qBAAqB,EACrB,uBAAuB,EACvB,0BAA0B,EAC1B,qBAAqB,EACrB,+BAA+B,GAChC,MAAM,uBAAuB,CAAC;AAC/B,YAAY,EAAE,WAAW,EAAE,oBAAoB,EAAE,mBAAmB,EAAE,MAAM,uBAAuB,CAAC;AAGpG,OAAO,EAAE,cAAc,EAAE,iBAAiB,EAAE,0BAA0B,EAAE,MAAM,oBAAoB,CAAC;AAGnG,OAAO,EAAE,qBAAqB,EAAE,MAAM,2BAA2B,CAAC;AAGlE,OAAO,EACL,iCAAiC,EACjC,8BAA8B,EAC9B,gCAAgC,EAChC,sBAAsB,EACtB,wBAAwB,EACxB,oBAAoB,GACrB,MAAM,wBAAwB,CAAC;AAChC,YAAY,EAAE,kBAAkB,EAAE,MAAM,wBAAwB,CAAC;AAGjE,OAAO,EAAE,oBAAoB,EAAE,MAAM,oBAAoB,CAAC;AAG1D,OAAO,EACL,sBAAsB,EACtB,gBAAgB,EAChB,iBAAiB,EACjB,iBAAiB,EACjB,WAAW,EACX,oBAAoB,EACpB,eAAe,EACf,mBAAmB,EACnB,wBAAwB,EACxB,qBAAqB,GACtB,MAAM,wBAAwB,CAAC;AAChC,YAAY,EACV,eAAe,EACf,aAAa,EACb,aAAa,EACb,aAAa,EACb,gBAAgB,EAChB,iBAAiB,EACjB,aAAa,GACd,MAAM,wBAAwB,CAAC;AAGhC,OAAO,EAAE,QAAQ,EAAE,WAAW,EAAE,MAAM,YAAY,CAAC;AACnD,OAAO,EAAE,SAAS,EAAE,kBAAkB,EAAE,oBAAoB,EAAE,MAAM,iBAAiB,CAAC;AACtF,OAAO,EAAE,iBAAiB,EAAE,MAAM,yBAAyB,CAAC;AAG5D,OAAO,EAAE,eAAe,EAAE,iBAAiB,EAAE,cAAc,EAAE,gBAAgB,EAAE,MAAM,uBAAuB,CAAC;AAC7G,YAAY,EAAE,oBAAoB,EAAE,MAAM,uBAAuB,CAAC;AAClE,OAAO,EAAE,gBAAgB,EAAE,aAAa,EAAE,aAAa,EAAE,MAAM,qBAAqB,CAAC;AACrF,OAAO,EAAE,sBAAsB,EAAE,MAAM,gCAAgC,CAAC;AAGxE,OAAO,EAAE,MAAM,EAAE,MAAM,UAAU,CAAC;AAGlC,OAAO,EACL,cAAc,EACd,gBAAgB,EAChB,oBAAoB,EACpB,cAAc,EACd,eAAe,EACf,mBAAmB,EACnB,cAAc,EACd,aAAa,EACb,YAAY,GACb,MAAM,cAAc,CAAC;AACtB,YAAY,EAAE,UAAU,EAAE,YAAY,EAAE,kBAAkB,EAAE,MAAM,cAAc,CAAC;AAGjF,OAAO,EAAE,eAAe,EAAE,qBAAqB,EAAE,MAAM,kBAAkB,CAAC;AAC1E,YAAY,EAAE,aAAa,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAGhE,OAAO,EAAE,uBAAuB,EAAE,iBAAiB,EAAE,qBAAqB,EAAE,MAAM,kBAAkB,CAAC;AACrG,YAAY,EAAE,kBAAkB,EAAE,MAAM,kBAAkB,CAAC;AAC3D,OAAO,EACL,yBAAyB,EACzB,kCAAkC,EAClC,kBAAkB,EAClB,kBAAkB,GACnB,MAAM,cAAc,CAAC;AACtB,YAAY,EAAE,aAAa,EAAE,YAAY,EAAE,MAAM,YAAY,CAAC;AAG9D,OAAO,EACL,cAAc,EACd,cAAc,EACd,eAAe,EACf,iBAAiB,EACjB,iBAAiB,EACjB,oBAAoB,EACpB,qBAAqB,GACtB,MAAM,kBAAkB,CAAC;AAC1B,YAAY,EAAE,UAAU,EAAE,UAAU,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAGzE,OAAO,EACL,YAAY,EACZ,aAAa,EACb,cAAc,EACd,mBAAmB,EACnB,eAAe,EACf,aAAa,GACd,MAAM,mBAAmB,CAAC;AAC3B,YAAY,EAAE,cAAc,EAAE,WAAW,EAAE,cAAc,EAAE,QAAQ,EAAE,cAAc,EAAE,MAAM,mBAAmB,CAAC;AAG/G,OAAO,EACL,QAAQ,EACR,YAAY,EACZ,qBAAqB,EACrB,qBAAqB,EACrB,eAAe,GAChB,MAAM,oBAAoB,CAAC;AAC5B,YAAY,EAAE,YAAY,EAAE,cAAc,EAAE,mBAAmB,EAAE,MAAM,oBAAoB,CAAC;AAG5F,OAAO,EACL,mBAAmB,EACnB,qBAAqB,EACrB,qBAAqB,EACrB,uBAAuB,EACvB,eAAe,GAChB,MAAM,6BAA6B,CAAC;AACrC,YAAY,EACV,UAAU,EACV,kBAAkB,EAClB,QAAQ,EACR,KAAK,EACL,UAAU,EACV,wBAAwB,GACzB,MAAM,6BAA6B,CAAC;AAGrC,OAAO,EACL,mBAAmB,EACnB,sBAAsB,EACtB,0BAA0B,EAC1B,aAAa,EACb,iBAAiB,GAClB,MAAM,iBAAiB,CAAC;AACzB,YAAY,EAAE,WAAW,EAAE,cAAc,EAAE,gBAAgB,EAAE,MAAM,iBAAiB,CAAC;AAGrF,OAAO,EACL,iBAAiB,EACjB,aAAa,EACb,qBAAqB,EACrB,uBAAuB,EACvB,iBAAiB,EACjB,sBAAsB,EACtB,8BAA8B,EAC9B,sBAAsB,GACvB,MAAM,yBAAyB,CAAC;AACjC,YAAY,EACV,eAAe,EACf,oBAAoB,EACpB,mBAAmB,EACnB,kBAAkB,EAClB,eAAe,EACf,kBAAkB,GACnB,MAAM,yBAAyB,CAAC;AAGjC,OAAO,EACL,gBAAgB,EAChB,gBAAgB,EAChB,gBAAgB,EAChB,eAAe,EACf,cAAc,EACd,wBAAwB,GACzB,MAAM,4BAA4B,CAAC;AACpC,YAAY,EAAE,UAAU,EAAE,UAAU,EAAE,sBAAsB,EAAE,MAAM,4BAA4B,CAAC;AAGjG,OAAO,EAAE,eAAe,EAAE,iBAAiB,EAAE,WAAW,EAAE,cAAc,EAAE,MAAM,8BAA8B,CAAC;AAE/G,OAAO,EACL,eAAe,EACf,kBAAkB,EAClB,gBAAgB,EAChB,eAAe,EACf,iBAAiB,EACjB,YAAY,EACZ,kBAAkB,EAClB,iBAAiB,EACjB,YAAY,GACb,MAAM,sBAAsB,CAAC;AAC9B,YAAY,EAAE,WAAW,EAAE,YAAY,EAAE,WAAW,EAAE,MAAM,sBAAsB,CAAC;AAGnF,OAAO,EAAE,uBAAuB,EAAE,oBAAoB,EAAE,kBAAkB,EAAE,MAAM,wBAAwB,CAAC;AAC3G,YAAY,EAAE,sBAAsB,EAAE,qBAAqB,EAAE,MAAM,wBAAwB,CAAC;AAG5F,OAAO,EACL,mBAAmB,EACnB,iBAAiB,EACjB,iBAAiB,EACjB,cAAc,EACd,YAAY,EACZ,iBAAiB,EACjB,cAAc,GACf,MAAM,wBAAwB,CAAC;AAChC,YAAY,EACV,eAAe,EACf,aAAa,EACb,UAAU,EACV,WAAW,EACX,UAAU,EACV,cAAc,GACf,MAAM,wBAAwB,CAAC;AAGhC,OAAO,EAAE,gBAAgB,EAAE,qBAAqB,EAAE,mBAAmB,EAAE,MAAM,4BAA4B,CAAC;AAC1G,YAAY,EAAE,YAAY,EAAE,cAAc,EAAE,MAAM,4BAA4B,CAAC;AAG/E,OAAO,EACL,eAAe,EACf,yBAAyB,EACzB,mBAAmB,EACnB,QAAQ,EACR,cAAc,EACd,oBAAoB,EACpB,eAAe,EACf,oBAAoB,EACpB,oBAAoB,GACrB,MAAM,2BAA2B,CAAC;AACnC,YAAY,EAAE,cAAc,EAAE,WAAW,EAAE,oBAAoB,EAAE,MAAM,2BAA2B,CAAC;AAEnG,OAAO,EAAE,iBAAiB,EAAE,sBAAsB,EAAE,MAAM,4BAA4B,CAAC;AACvF,YAAY,EAAE,kBAAkB,EAAE,MAAM,4BAA4B,CAAC;AAGrE,OAAO,EAAE,oBAAoB,EAAE,MAAM,wBAAwB,CAAC;AAC9D,YAAY,EAAE,cAAc,EAAE,MAAM,YAAY,CAAC;AAGjD,OAAO,EACL,gBAAgB,EAChB,gBAAgB,EAChB,cAAc,EACd,eAAe,EACf,0BAA0B,EAC1B,aAAa,EACb,kBAAkB,EAClB,uBAAuB,EACvB,0BAA0B,EAC1B,WAAW,EACX,mBAAmB,GACpB,MAAM,wBAAwB,CAAC;AAChC,YAAY,EAAE,cAAc,EAAE,YAAY,EAAE,YAAY,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAC;AAKvG,OAAO,KAAK,EAAE,iBAAiB,EAAE,MAAM,uBAAuB,CAAC;AAC/D,OAAO,KAAK,EAAE,eAAe,EAAE,eAAe,EAAE,MAAM,YAAY,CAAC;AAInE;;;;;;;GAOG;AACH,wBAAgB,YAAY,CAAC,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,iBAAiB,GAAG,eAAe,CAEzG;AAED;;;;;;;;GAQG;AACH,wBAAgB,uBAAuB,CACrC,OAAO,EAAE,MAAM,EACf,IAAI,EAAE,MAAM,EACZ,QAAQ,EAAE,MAAM,EAChB,OAAO,CAAC,EAAE,iBAAiB,GAC1B,eAAe,CAMjB;AAID,OAAO,EAAE,6BAA6B,EAAE,MAAM,uCAAuC,CAAC;AACtF,YAAY,EAAE,cAAc,EAAE,MAAM,uCAAuC,CAAC;AAI5E,OAAO,EAAE,sBAAsB,EAAE,wBAAwB,EAAE,MAAM,sBAAsB,CAAC;AACxF,YAAY,EAAE,kBAAkB,EAAE,MAAM,sBAAsB,CAAC;AAI/D,MAAM,WAAW,SAAS;IACxB,qCAAqC;IACrC,IAAI,EAAE,MAAM,CAAC;IACb,0BAA0B;IAC1B,IAAI,EAAE,MAAM,CAAC;IACb,2BAA2B;IAC3B,QAAQ,EAAE,MAAM,CAAC;CAClB;AAED,MAAM,WAAW,oBAAoB;IACnC,mCAAmC;IACnC,IAAI,EAAE,MAAM,CAAC;IACb,qCAAqC;IACrC,OAAO,EAAE,eAAe,CAAC;IACzB,kCAAkC;IAClC,KAAK,EAAE,MAAM,CAAC;CACf;AAED;;;;;;;;;;GAUG;AACH,wBAAuB,mBAAmB,CACxC,KAAK,EAAE,SAAS,EAAE,EAClB,OAAO,CAAC,EAAE,iBAAiB,GAC1B,cAAc,CAAC,oBAAoB,CAAC,CAMtC;AAED;;;;;;;;GAQG;AACH,wBAAsB,kBAAkB,CACtC,KAAK,EAAE,SAAS,EAAE,EAClB,WAAW,SAAI,EACf,OAAO,CAAC,EAAE,iBAAiB,EAC3B,UAAU,CAAC,EAAE,CAAC,SAAS,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,KAAK,IAAI,GACtD,OAAO,CAAC,oBAAoB,EAAE,CAAC,CAmBjC;AAGD,OAAO,EAAE,aAAa,EAAE,sBAAsB,EAAE,aAAa,EAAE,cAAc,EAAE,aAAa,EAAE,MAAM,iBAAiB,CAAC;AACtH,YAAY,EAAE,eAAe,EAAE,MAAM,iBAAiB,CAAC"}
|
package/dist/api.js
CHANGED
|
@@ -15,7 +15,7 @@ export { parseConfig, defaultConfig, mergeConfigs, discoverCascadingConfigs, loa
|
|
|
15
15
|
// ─── Judge Registry ──────────────────────────────────────────────────────────
|
|
16
16
|
export { JUDGES, getJudge, getJudgeSummaries } from "./judges/index.js";
|
|
17
17
|
// ─── Core Evaluation Functions ───────────────────────────────────────────────
|
|
18
|
-
export { evaluateWithJudge, evaluateWithTribunal, evaluateProject, evaluateDiff, analyzeDependencies, enrichWithPatches, crossEvaluatorDedup, diffFindings, formatFindingDiff, evaluateNetChangeGate, applyInlineSuppressions, applyInlineSuppressionsWithAudit, runAppBuilderWorkflow, formatVerdictAsMarkdown, formatEvaluationAsMarkdown, clearEvaluationCaches, } from "./evaluators/index.js";
|
|
18
|
+
export { evaluateWithJudge, evaluateWithTribunal, evaluateProject, evaluateDiff, analyzeDependencies, enrichWithPatches, crossEvaluatorDedup, diffFindings, formatFindingDiff, evaluateNetChangeGate, applyInlineSuppressions, applyInlineSuppressionsWithAudit, runAppBuilderWorkflow, formatVerdictAsMarkdown, formatEvaluationAsMarkdown, clearEvaluationCaches, scanProjectWideSecurityPatterns, } from "./evaluators/index.js";
|
|
19
19
|
// ─── V2 Policy-Aware API ────────────────────────────────────────────────────
|
|
20
20
|
export { evaluateCodeV2, evaluateProjectV2, getSupportedPolicyProfiles } from "./evaluators/v2.js";
|
|
21
21
|
// ─── Cross-File Taint Analysis ───────────────────────────────────────────────
|
package/dist/api.js.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"api.js","sourceRoot":"","sources":["../src/api.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAiCH,gFAAgF;AAChF,OAAO,EAAE,WAAW,EAAE,WAAW,EAAE,eAAe,EAAE,UAAU,EAAE,MAAM,aAAa,CAAC;AAEpF,gFAAgF;AAChF,OAAO,EACL,WAAW,EACX,aAAa,EACb,YAAY,EACZ,wBAAwB,EACxB,mBAAmB,EACnB,gBAAgB,EAChB,wBAAwB,EACxB,sBAAsB,EACtB,qBAAqB,EACrB,oBAAoB,EACpB,oBAAoB,GACrB,MAAM,aAAa,CAAC;AAErB,gFAAgF;AAChF,OAAO,EAAE,MAAM,EAAE,QAAQ,EAAE,iBAAiB,EAAE,MAAM,mBAAmB,CAAC;AAExE,gFAAgF;AAEhF,OAAO,EACL,iBAAiB,EACjB,oBAAoB,EACpB,eAAe,EACf,YAAY,EACZ,mBAAmB,EACnB,iBAAiB,EACjB,mBAAmB,EACnB,YAAY,EACZ,iBAAiB,EACjB,qBAAqB,EACrB,uBAAuB,EACvB,gCAAgC,EAChC,qBAAqB,EACrB,uBAAuB,EACvB,0BAA0B,EAC1B,qBAAqB,
|
|
1
|
+
{"version":3,"file":"api.js","sourceRoot":"","sources":["../src/api.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAiCH,gFAAgF;AAChF,OAAO,EAAE,WAAW,EAAE,WAAW,EAAE,eAAe,EAAE,UAAU,EAAE,MAAM,aAAa,CAAC;AAEpF,gFAAgF;AAChF,OAAO,EACL,WAAW,EACX,aAAa,EACb,YAAY,EACZ,wBAAwB,EACxB,mBAAmB,EACnB,gBAAgB,EAChB,wBAAwB,EACxB,sBAAsB,EACtB,qBAAqB,EACrB,oBAAoB,EACpB,oBAAoB,GACrB,MAAM,aAAa,CAAC;AAErB,gFAAgF;AAChF,OAAO,EAAE,MAAM,EAAE,QAAQ,EAAE,iBAAiB,EAAE,MAAM,mBAAmB,CAAC;AAExE,gFAAgF;AAEhF,OAAO,EACL,iBAAiB,EACjB,oBAAoB,EACpB,eAAe,EACf,YAAY,EACZ,mBAAmB,EACnB,iBAAiB,EACjB,mBAAmB,EACnB,YAAY,EACZ,iBAAiB,EACjB,qBAAqB,EACrB,uBAAuB,EACvB,gCAAgC,EAChC,qBAAqB,EACrB,uBAAuB,EACvB,0BAA0B,EAC1B,qBAAqB,EACrB,+BAA+B,GAChC,MAAM,uBAAuB,CAAC;AAG/B,+EAA+E;AAC/E,OAAO,EAAE,cAAc,EAAE,iBAAiB,EAAE,0BAA0B,EAAE,MAAM,oBAAoB,CAAC;AAEnG,gFAAgF;AAChF,OAAO,EAAE,qBAAqB,EAAE,MAAM,2BAA2B,CAAC;AAElE,gFAAgF;AAChF,OAAO,EACL,iCAAiC,EACjC,8BAA8B,EAC9B,gCAAgC,EAChC,sBAAsB,EACtB,wBAAwB,EACxB,oBAAoB,GACrB,MAAM,wBAAwB,CAAC;AAGhC,gFAAgF;AAChF,OAAO,EAAE,oBAAoB,EAAE,MAAM,oBAAoB,CAAC;AAE1D,+EAA+E;AAC/E,OAAO,EACL,sBAAsB,EACtB,gBAAgB,EAChB,iBAAiB,EACjB,iBAAiB,EACjB,WAAW,EACX,oBAAoB,EACpB,eAAe,EACf,mBAAmB,EACnB,wBAAwB,EACxB,qBAAqB,GACtB,MAAM,wBAAwB,CAAC;AAWhC,gFAAgF;AAChF,OAAO,EAAE,QAAQ,EAAE,WAAW,EAAE,MAAM,YAAY,CAAC;AACnD,OAAO,EAAE,SAAS,EAAE,kBAAkB,EAAE,oBAAoB,EAAE,MAAM,iBAAiB,CAAC;AACtF,OAAO,EAAE,iBAAiB,EAAE,MAAM,yBAAyB,CAAC;AAE5D,gFAAgF;AAChF,OAAO,EAAE,eAAe,EAAE,iBAAiB,EAAE,cAAc,EAAE,gBAAgB,EAAE,MAAM,uBAAuB,CAAC;AAE7G,OAAO,EAAE,gBAAgB,EAAE,aAAa,EAAE,aAAa,EAAE,MAAM,qBAAqB,CAAC;AACrF,OAAO,EAAE,sBAAsB,EAAE,MAAM,gCAAgC,CAAC;AAExE,gFAAgF;AAChF,OAAO,EAAE,MAAM,EAAE,MAAM,UAAU,CAAC;AAElC,gFAAgF;AAChF,OAAO,EACL,cAAc,EACd,gBAAgB,EAChB,oBAAoB,EACpB,cAAc,EACd,eAAe,EACf,mBAAmB,EACnB,cAAc,EACd,aAAa,EACb,YAAY,GACb,MAAM,cAAc,CAAC;AAGtB,+EAA+E;AAC/E,OAAO,EAAE,eAAe,EAAE,qBAAqB,EAAE,MAAM,kBAAkB,CAAC;AAG1E,+EAA+E;AAC/E,OAAO,EAAE,uBAAuB,EAAE,iBAAiB,EAAE,qBAAqB,EAAE,MAAM,kBAAkB,CAAC;AAErG,OAAO,EACL,yBAAyB,EACzB,kCAAkC,EAClC,kBAAkB,EAClB,kBAAkB,GACnB,MAAM,cAAc,CAAC;AAGtB,gFAAgF;AAChF,OAAO,EACL,cAAc,EACd,cAAc,EACd,eAAe,EACf,iBAAiB,EACjB,iBAAiB,EACjB,oBAAoB,EACpB,qBAAqB,GACtB,MAAM,kBAAkB,CAAC;AAG1B,8EAA8E;AAC9E,OAAO,EACL,YAAY,EACZ,aAAa,EACb,cAAc,EACd,mBAAmB,EACnB,eAAe,EACf,aAAa,GACd,MAAM,mBAAmB,CAAC;AAG3B,+EAA+E;AAC/E,OAAO,EACL,QAAQ,EACR,YAAY,EACZ,qBAAqB,EACrB,qBAAqB,EACrB,eAAe,GAChB,MAAM,oBAAoB,CAAC;AAG5B,gFAAgF;AAChF,OAAO,EACL,mBAAmB,EACnB,qBAAqB,EACrB,qBAAqB,EACrB,uBAAuB,EACvB,eAAe,GAChB,MAAM,6BAA6B,CAAC;AAUrC,gFAAgF;AAChF,OAAO,EACL,mBAAmB,EACnB,sBAAsB,EACtB,0BAA0B,EAC1B,aAAa,EACb,iBAAiB,GAClB,MAAM,iBAAiB,CAAC;AAGzB,gFAAgF;AAChF,OAAO,EACL,iBAAiB,EACjB,aAAa,EACb,qBAAqB,EACrB,uBAAuB,EACvB,iBAAiB,EACjB,sBAAsB,EACtB,8BAA8B,EAC9B,sBAAsB,GACvB,MAAM,yBAAyB,CAAC;AAUjC,gFAAgF;AAChF,OAAO,EACL,gBAAgB,EAChB,gBAAgB,EAChB,gBAAgB,EAChB,eAAe,EACf,cAAc,EACd,wBAAwB,GACzB,MAAM,4BAA4B,CAAC;AAGpC,gFAAgF;AAChF,OAAO,EAAE,eAAe,EAAE,iBAAiB,EAAE,WAAW,EAAE,cAAc,EAAE,MAAM,8BAA8B,CAAC;AAC/G,4EAA4E;AAC5E,OAAO,EACL,eAAe,EACf,kBAAkB,EAClB,gBAAgB,EAChB,eAAe,EACf,iBAAiB,EACjB,YAAY,EACZ,kBAAkB,EAClB,iBAAiB,EACjB,YAAY,GACb,MAAM,sBAAsB,CAAC;AAG9B,+EAA+E;AAC/E,OAAO,EAAE,uBAAuB,EAAE,oBAAoB,EAAE,kBAAkB,EAAE,MAAM,wBAAwB,CAAC;AAG3G,+EAA+E;AAC/E,OAAO,EACL,mBAAmB,EACnB,iBAAiB,EACjB,iBAAiB,EACjB,cAAc,EACd,YAAY,EACZ,iBAAiB,EACjB,cAAc,GACf,MAAM,wBAAwB,CAAC;AAUhC,+EAA+E;AAC/E,OAAO,EAAE,gBAAgB,EAAE,qBAAqB,EAAE,mBAAmB,EAAE,MAAM,4BAA4B,CAAC;AAG1G,+EAA+E;AAC/E,OAAO,EACL,eAAe,EACf,yBAAyB,EACzB,mBAAmB,EACnB,QAAQ,EACR,cAAc,EACd,oBAAoB,EACpB,eAAe,EACf,oBAAoB,EACpB,oBAAoB,GACrB,MAAM,2BAA2B,CAAC;AAEnC,gFAAgF;AAChF,OAAO,EAAE,iBAAiB,EAAE,sBAAsB,EAAE,MAAM,4BAA4B,CAAC;AAGvF,gFAAgF;AAChF,OAAO,EAAE,oBAAoB,EAAE,MAAM,wBAAwB,CAAC;AAG9D,gFAAgF;AAChF,OAAO,EACL,gBAAgB,EAChB,gBAAgB,EAChB,cAAc,EACd,eAAe,EACf,0BAA0B,EAC1B,aAAa,EACb,kBAAkB,EAClB,uBAAuB,EACvB,0BAA0B,EAC1B,WAAW,EACX,mBAAmB,GACpB,MAAM,wBAAwB,CAAC;AAGhC,gFAAgF;AAEhF,OAAO,EAAE,oBAAoB,EAAE,iBAAiB,EAAE,MAAM,uBAAuB,CAAC;AAGhF,OAAO,EAAE,QAAQ,EAAE,MAAM,mBAAmB,CAAC;AAC7C,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAE9C;;;;;;;GAOG;AACH,MAAM,UAAU,YAAY,CAAC,IAAY,EAAE,QAAgB,EAAE,OAA2B;IACtF,OAAO,oBAAoB,CAAC,IAAI,EAAE,QAAQ,EAAE,SAAS,EAAE,OAAO,CAAC,CAAC;AAClE,CAAC;AAED;;;;;;;;GAQG;AACH,MAAM,UAAU,uBAAuB,CACrC,OAAe,EACf,IAAY,EACZ,QAAgB,EAChB,OAA2B;IAE3B,MAAM,KAAK,GAAG,QAAQ,CAAC,OAAO,CAAC,CAAC;IAChC,IAAI,CAAC,KAAK,EAAE,CAAC;QACX,MAAM,IAAI,eAAe,CAAC,mBAAmB,OAAO,GAAG,EAAE,OAAO,CAAC,CAAC;IACpE,CAAC;IACD,OAAO,iBAAiB,CAAC,KAAK,EAAE,IAAI,EAAE,QAAQ,EAAE,SAAS,EAAE,OAAO,CAAC,CAAC;AACtE,CAAC;AAED,gFAAgF;AAEhF,OAAO,EAAE,6BAA6B,EAAE,MAAM,uCAAuC,CAAC;AAGtF,gFAAgF;AAEhF,OAAO,EAAE,sBAAsB,EAAE,wBAAwB,EAAE,MAAM,sBAAsB,CAAC;AAuBxF;;;;;;;;;;GAUG;AACH,MAAM,CAAC,KAAK,SAAS,CAAC,CAAC,mBAAmB,CACxC,KAAkB,EAClB,OAA2B;IAE3B,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;QACtC,MAAM,IAAI,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QACtB,MAAM,OAAO,GAAG,oBAAoB,CAAC,IAAI,CAAC,IAAI,EAAE,IAAI,CAAC,QAAQ,EAAE,SAAS,EAAE,OAAO,CAAC,CAAC;QACnF,MAAM,EAAE,IAAI,EAAE,IAAI,CAAC,IAAI,EAAE,OAAO,EAAE,KAAK,EAAE,CAAC,EAAE,CAAC;IAC/C,CAAC;AACH,CAAC;AAED;;;;;;;;GAQG;AACH,MAAM,CAAC,KAAK,UAAU,kBAAkB,CACtC,KAAkB,EAClB,WAAW,GAAG,CAAC,EACf,OAA2B,EAC3B,UAAuD;IAEvD,MAAM,OAAO,GAA2B,IAAI,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC;IAChE,IAAI,SAAS,GAAG,CAAC,CAAC;IAClB,IAAI,SAAS,GAAG,CAAC,CAAC;IAElB,KAAK,UAAU,MAAM;QACnB,OAAO,SAAS,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC;YAChC,MAAM,CAAC,GAAG,SAAS,EAAE,CAAC;YACtB,MAAM,IAAI,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;YACtB,MAAM,OAAO,GAAG,oBAAoB,CAAC,IAAI,CAAC,IAAI,EAAE,IAAI,CAAC,QAAQ,EAAE,SAAS,EAAE,OAAO,CAAC,CAAC;YACnF,OAAO,CAAC,CAAC,CAAC,GAAG,EAAE,IAAI,EAAE,IAAI,CAAC,IAAI,EAAE,OAAO,EAAE,KAAK,EAAE,CAAC,EAAE,CAAC;YACpD,SAAS,EAAE,CAAC;YACZ,UAAU,EAAE,CAAC,SAAS,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC;QACxC,CAAC;IACH,CAAC;IAED,MAAM,OAAO,GAAG,KAAK,CAAC,IAAI,CAAC,EAAE,MAAM,EAAE,IAAI,CAAC,GAAG,CAAC,WAAW,EAAE,KAAK,CAAC,MAAM,CAAC,EAAE,EAAE,GAAG,EAAE,CAAC,MAAM,EAAE,CAAC,CAAC;IAC5F,MAAM,OAAO,CAAC,GAAG,CAAC,OAAO,CAAC,CAAC;IAC3B,OAAO,OAAO,CAAC;AACjB,CAAC;AAED,gFAAgF;AAChF,OAAO,EAAE,aAAa,EAAE,sBAAsB,EAAE,aAAa,EAAE,cAAc,EAAE,aAAa,EAAE,MAAM,iBAAiB,CAAC"}
|
|
@@ -0,0 +1,10 @@
|
|
|
1
|
+
import type { BenchmarkCase } from "./benchmark.js";
|
|
2
|
+
/**
|
|
3
|
+
* AI-output-specific benchmark cases targeting patterns characteristic of
|
|
4
|
+
* LLM-generated code: logic inversions, dead code, name-body mismatches,
|
|
5
|
+
* empty error handlers, and inadequate tests.
|
|
6
|
+
*
|
|
7
|
+
* Covers LOGIC, TEST, and enhanced HALLU prefixes.
|
|
8
|
+
*/
|
|
9
|
+
export declare const BENCHMARK_AI_OUTPUT: BenchmarkCase[];
|
|
10
|
+
//# sourceMappingURL=benchmark-ai-output.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"benchmark-ai-output.d.ts","sourceRoot":"","sources":["../../src/commands/benchmark-ai-output.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,gBAAgB,CAAC;AAEpD;;;;;;GAMG;AACH,eAAO,MAAM,mBAAmB,EAAE,aAAa,EA8W9C,CAAC"}
|