hyntx 2.7.0 → 3.0.0

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/README.md CHANGED
@@ -176,7 +176,7 @@ hyntx -m individual # Short form
176
176
  - Analyzing high-stakes or complex prompts
177
177
  - Conducting quality audits or teaching sessions
178
178
 
179
- **Performance Note**: Numbers based on `llama3.2` on CPU. Actual speed varies by hardware, model size, and prompt complexity.
179
+ **Performance Note**: Numbers based on `gemma3:4b` on CPU. Actual speed varies by hardware, model size, and prompt complexity.
180
180
 
181
181
  **Detailed Guide**: See [Analysis Modes Documentation](./docs/ANALYSIS_MODES.md) for comprehensive comparison, examples, and decision guidelines.
182
182
 
@@ -255,17 +255,17 @@ Configure one or more providers in priority order. Hyntx will try each provider
255
255
  ```bash
256
256
  # Single provider (Ollama only)
257
257
  export HYNTX_SERVICES=ollama
258
- export HYNTX_OLLAMA_MODEL=llama3.2
258
+ export HYNTX_OLLAMA_MODEL=gemma3:4b
259
259
 
260
260
  # Multi-provider with fallback (tries Ollama first, then Anthropic)
261
261
  export HYNTX_SERVICES=ollama,anthropic
262
- export HYNTX_OLLAMA_MODEL=llama3.2
262
+ export HYNTX_OLLAMA_MODEL=gemma3:4b
263
263
  export HYNTX_ANTHROPIC_KEY=sk-ant-your-key-here
264
264
 
265
265
  # Cloud-first with local fallback
266
266
  export HYNTX_SERVICES=anthropic,ollama
267
267
  export HYNTX_ANTHROPIC_KEY=sk-ant-your-key-here
268
- export HYNTX_OLLAMA_MODEL=llama3.2
268
+ export HYNTX_OLLAMA_MODEL=gemma3:4b
269
269
  ```
270
270
 
271
271
  #### Provider-Specific Variables
@@ -274,7 +274,7 @@ export HYNTX_OLLAMA_MODEL=llama3.2
274
274
 
275
275
  | Variable | Default | Description |
276
276
  | -------------------- | ------------------------ | ----------------- |
277
- | `HYNTX_OLLAMA_MODEL` | `llama3.2` | Model to use |
277
+ | `HYNTX_OLLAMA_MODEL` | `gemma3:4b` | Model to use |
278
278
  | `HYNTX_OLLAMA_HOST` | `http://localhost:11434` | Ollama server URL |
279
279
 
280
280
  **Anthropic:**
@@ -303,7 +303,7 @@ export HYNTX_REMINDER=7d
303
303
  ```bash
304
304
  # Add to ~/.zshrc or ~/.bashrc (or let Hyntx auto-save it)
305
305
  export HYNTX_SERVICES=ollama,anthropic
306
- export HYNTX_OLLAMA_MODEL=llama3.2
306
+ export HYNTX_OLLAMA_MODEL=gemma3:4b
307
307
  export HYNTX_ANTHROPIC_KEY=sk-ant-your-key-here
308
308
  export HYNTX_REMINDER=14d
309
309
 
@@ -327,7 +327,7 @@ Ollama runs AI models locally for **privacy and cost savings**.
327
327
  2. Pull a model:
328
328
 
329
329
  ```bash
330
- ollama pull llama3.2
330
+ ollama pull gemma3:4b
331
331
  ```
332
332
 
333
333
  3. Verify it's running:
@@ -369,7 +369,7 @@ Configure multiple providers for automatic fallback:
369
369
  ```bash
370
370
  # If Ollama is down, automatically try Anthropic
371
371
  export HYNTX_SERVICES=ollama,anthropic
372
- export HYNTX_OLLAMA_MODEL=llama3.2
372
+ export HYNTX_OLLAMA_MODEL=gemma3:4b
373
373
  export HYNTX_ANTHROPIC_KEY=sk-ant-your-key-here
374
374
  ```
375
375
 
@@ -428,11 +428,33 @@ Hyntx can run as a [Model Context Protocol (MCP)](https://modelcontextprotocol.i
428
428
 
429
429
  ### Quick Setup
430
430
 
431
- Add hyntx to your Claude Code MCP configuration:
431
+ Add hyntx to your Claude Code MCP configuration. You have two options:
432
432
 
433
- **macOS:** `~/Library/Application Support/Claude/claude_desktop_config.json`
434
- **Windows:** `%APPDATA%\Claude\claude_desktop_config.json`
435
- **Linux:** `~/.config/Claude/claude_desktop_config.json`
433
+ #### Option 1: User-scoped (Recommended)
434
+
435
+ Configuration visible only to you, stored in `~/.claude.json`:
436
+
437
+ ```bash
438
+ # Add using Claude Code CLI
439
+ claude mcp add hyntx
440
+
441
+ # Or manually edit ~/.claude.json
442
+ ```
443
+
444
+ ```json
445
+ {
446
+ "mcpServers": {
447
+ "hyntx": {
448
+ "command": "hyntx",
449
+ "args": ["--mcp-server"]
450
+ }
451
+ }
452
+ }
453
+ ```
454
+
455
+ #### Option 2: Project-scoped
456
+
457
+ Configuration shared with your team via Git, stored in `.mcp.json` at your project root:
436
458
 
437
459
  ```json
438
460
  {
@@ -445,7 +467,7 @@ Add hyntx to your Claude Code MCP configuration:
445
467
  }
446
468
  ```
447
469
 
448
- After editing, restart Claude Code. The hyntx tools will be available in your conversations.
470
+ After adding the configuration, restart your Claude Code session. The hyntx tools will be available in your conversations.
449
471
 
450
472
  ### Prerequisites
451
473
 
@@ -459,11 +481,11 @@ If using Ollama (recommended for privacy):
459
481
  ollama serve
460
482
 
461
483
  # Pull a model if needed
462
- ollama pull llama3.2
484
+ ollama pull gemma3:4b
463
485
 
464
486
  # Set environment variables (add to ~/.zshrc or ~/.bashrc)
465
487
  export HYNTX_SERVICES=ollama
466
- export HYNTX_OLLAMA_MODEL=llama3.2
488
+ export HYNTX_OLLAMA_MODEL=gemma3:4b
467
489
  ```
468
490
 
469
491
  ### Available MCP Tools
@@ -621,18 +643,26 @@ Use check-context to verify: "Update the component to handle errors"
621
643
  #### "Tools not appearing in Claude Code"
622
644
 
623
645
  1. Restart Claude Code completely after config changes
624
- 2. Verify the config file path is correct for your OS
646
+ 2. Verify the config file exists and is in the correct location:
647
+ - User-scoped: `~/.claude.json`
648
+ - Project-scoped: `.mcp.json` (in project root)
625
649
  3. Check JSON syntax in the config file:
626
650
 
627
651
  ```bash
628
- # macOS
629
- cat ~/Library/Application\ Support/Claude/claude_desktop_config.json | jq .
652
+ # Verify user-scoped config
653
+ cat ~/.claude.json | jq .
654
+
655
+ # Or verify project-scoped config
656
+ cat .mcp.json | jq .
657
+
658
+ # Or use Claude Code CLI to list MCP servers
659
+ claude mcp list
630
660
  ```
631
661
 
632
662
  #### "Slow responses"
633
663
 
634
664
  - Local Ollama models are fastest but require GPU for best performance
635
- - Consider using a faster model: `export HYNTX_OLLAMA_MODEL=llama3.2:1b`
665
+ - Consider using a faster model: `export HYNTX_OLLAMA_MODEL=gemma3:4b:1b`
636
666
  - Cloud providers (Anthropic, Google) offer faster responses but require API keys
637
667
 
638
668
  ## Privacy & Security
@@ -678,15 +708,15 @@ For local analysis with Ollama, you need to have a compatible model installed. S
678
708
 
679
709
  | Use Case | Model | Parameters | Disk Size | Speed (CPU) | Quality |
680
710
  | ------------------- | ------------- | ---------- | --------- | -------------- | --------- |
681
- | **Daily use** | `llama3.2` | 2-3B | ~2GB | ~2-5s/prompt | Good |
711
+ | **Daily use** | `gemma3:4b` | 2-3B | ~2GB | ~2-5s/prompt | Good |
682
712
  | **Production** | `mistral:7b` | 7B | ~4GB | ~5-10s/prompt | Better |
683
713
  | **Maximum quality** | `qwen2.5:14b` | 14B | ~9GB | ~15-30s/prompt | Excellent |
684
714
 
685
715
  **Installation**:
686
716
 
687
717
  ```bash
688
- # Install recommended model (llama3.2)
689
- ollama pull llama3.2
718
+ # Install recommended model (gemma3:4b)
719
+ ollama pull gemma3:4b
690
720
 
691
721
  # Or choose a different model
692
722
  ollama pull mistral:7b
@@ -266,7 +266,7 @@ type EnvConfig = {
266
266
  declare const ENV_DEFAULTS: {
267
267
  readonly reminder: "7d";
268
268
  readonly ollama: {
269
- readonly model: "llama3.2";
269
+ readonly model: "gemma3:4b";
270
270
  readonly host: "http://localhost:11434";
271
271
  };
272
272
  readonly anthropic: {
package/dist/api/index.js CHANGED
@@ -1 +1 @@
1
- export { BATCH_STRATEGIES, CACHE_ANALYSIS_DIR, CACHE_DEFAULTS, CACHE_META_FILE, CLAUDE_PROJECTS_DIR, ENV_DEFAULTS, EXIT_CODES, HYNTX_CACHE_DIR, HYNTX_HISTORY_DIR, LAST_RUN_FILE, PROVIDER_LIMITS, analyzePrompts, claudeProjectsExist, cleanupExpiredEntries, clearCache, compareResults, createProvider, ensureHistoryDir, extractProjectName, generateCacheKey, getAllProviders, getAvailableProvider, getCachedResult, getDateOneMonthAgo, getDateOneWeekAgo, getEnvConfig, getHistoryDir, groupByDay, hashSystemPrompt, isFirstRun, listAvailableDates, loadAnalysisResult, loadProjectConfig, loadProjectConfigForCwd, mergeConfigs, parseDate, parseServices, readLogs, sanitize, sanitizePrompts, saveAnalysisResult, setCachedResult, validateSystemPrompt } from '../chunk-TGFHVZHY.js';
1
+ export { BATCH_STRATEGIES, CACHE_ANALYSIS_DIR, CACHE_DEFAULTS, CACHE_META_FILE, CLAUDE_PROJECTS_DIR, ENV_DEFAULTS, EXIT_CODES, HYNTX_CACHE_DIR, HYNTX_HISTORY_DIR, LAST_RUN_FILE, PROVIDER_LIMITS, analyzePrompts, claudeProjectsExist, cleanupExpiredEntries, clearCache, compareResults, createProvider, ensureHistoryDir, extractProjectName, generateCacheKey, getAllProviders, getAvailableProvider, getCachedResult, getDateOneMonthAgo, getDateOneWeekAgo, getEnvConfig, getHistoryDir, groupByDay, hashSystemPrompt, isFirstRun, listAvailableDates, loadAnalysisResult, loadProjectConfig, loadProjectConfigForCwd, mergeConfigs, parseDate, parseServices, readLogs, sanitize, sanitizePrompts, saveAnalysisResult, setCachedResult, validateSystemPrompt } from '../chunk-24U3LCZC.js';
@@ -447,7 +447,7 @@ var PROVIDER_LIMITS = {
447
447
  var ENV_DEFAULTS = {
448
448
  reminder: "7d",
449
449
  ollama: {
450
- model: "llama3.2",
450
+ model: "gemma3:4b",
451
451
  host: "http://localhost:11434"
452
452
  },
453
453
  anthropic: {
@@ -2159,6 +2159,17 @@ function convertMinimalToAnalysisResult(minimal, date, taxonomy, prompts) {
2159
2159
  }
2160
2160
 
2161
2161
  // src/providers/base.ts
2162
+ var PLACEHOLDER_PATTERNS = [
2163
+ "kebab-case-id",
2164
+ "Original problematic prompt",
2165
+ "Improved version addressing the issue",
2166
+ "<PLACEHOLDER_EXAMPLE>",
2167
+ "Human-Readable Issue Name"
2168
+ ];
2169
+ function containsPlaceholders(response) {
2170
+ const lower = response.toLowerCase();
2171
+ return PLACEHOLDER_PATTERNS.some((p) => lower.includes(p.toLowerCase()));
2172
+ }
2162
2173
  function buildUserPrompt(prompts, date, context) {
2163
2174
  if (prompts.length === 0) {
2164
2175
  throw new Error("Cannot build prompt from empty array");
@@ -2290,6 +2301,11 @@ function parseResponse(response, date, taxonomy = ISSUE_TAXONOMY, prompts) {
2290
2301
  );
2291
2302
  }
2292
2303
  }
2304
+ if (containsPlaceholders(response)) {
2305
+ throw new Error(
2306
+ "Response contains placeholder text - model did not provide real analysis"
2307
+ );
2308
+ }
2293
2309
  if (isValidMinimalResponse(parsed)) {
2294
2310
  const minimal = extractMinimalResult(parsed);
2295
2311
  return convertMinimalToAnalysisResult(minimal, date, taxonomy, prompts);
@@ -2324,6 +2340,8 @@ function parseResponse(response, date, taxonomy = ISSUE_TAXONOMY, prompts) {
2324
2340
  patterns: normalizedPatterns,
2325
2341
  stats: {
2326
2342
  ...parsed.stats,
2343
+ // Override totalPrompts with actual count if prompts provided
2344
+ totalPrompts: prompts?.length ?? parsed.stats.totalPrompts,
2327
2345
  overallScore: normalizeScore(parsed.stats.overallScore)
2328
2346
  },
2329
2347
  topSuggestion: parsed.topSuggestion
package/dist/cli.js CHANGED
@@ -335,7 +335,7 @@ var PROVIDER_LIMITS = {
335
335
  var ENV_DEFAULTS = {
336
336
  reminder: "7d",
337
337
  ollama: {
338
- model: "llama3.2",
338
+ model: "gemma3:4b",
339
339
  host: "http://localhost:11434"
340
340
  },
341
341
  anthropic: {
@@ -3541,14 +3541,14 @@ var HIGH_RAM_THRESHOLD = 8;
3541
3541
  var LOW_RAM_THRESHOLD = 4;
3542
3542
  function suggestBestModel(systemInfo, models) {
3543
3543
  if (systemInfo.ramGB < HIGH_RAM_THRESHOLD) {
3544
- if (isModelAvailable("llama3.2", models)) {
3544
+ if (isModelAvailable("gemma3:4b", models)) {
3545
3545
  return {
3546
- suggestedModel: "llama3.2",
3546
+ suggestedModel: "gemma3:4b",
3547
3547
  reason: "Fast and lightweight model, optimal for your system"
3548
3548
  };
3549
3549
  }
3550
3550
  return {
3551
- suggestedModel: "llama3.2",
3551
+ suggestedModel: "gemma3:4b",
3552
3552
  reason: "Recommended default model (needs installation)"
3553
3553
  };
3554
3554
  }
@@ -3564,14 +3564,14 @@ function suggestBestModel(systemInfo, models) {
3564
3564
  reason: "Better analysis quality with Small Schema"
3565
3565
  };
3566
3566
  }
3567
- if (isModelAvailable("llama3.2", models)) {
3567
+ if (isModelAvailable("gemma3:4b", models)) {
3568
3568
  return {
3569
- suggestedModel: "llama3.2",
3569
+ suggestedModel: "gemma3:4b",
3570
3570
  reason: "Fast and reliable default model"
3571
3571
  };
3572
3572
  }
3573
3573
  return {
3574
- suggestedModel: "llama3.2",
3574
+ suggestedModel: "gemma3:4b",
3575
3575
  reason: "Recommended default model (needs installation)"
3576
3576
  };
3577
3577
  }
@@ -3591,10 +3591,10 @@ function getInstallationSuggestion(systemInfo, models) {
3591
3591
  }
3592
3592
  return null;
3593
3593
  }
3594
- const hasLlama = isModelAvailable("llama3.2", models);
3594
+ const hasLlama = isModelAvailable("gemma3:4b", models);
3595
3595
  if (!hasLlama) {
3596
3596
  return {
3597
- suggestedModel: "llama3.2",
3597
+ suggestedModel: "gemma3:4b",
3598
3598
  benefits: "Fast and lightweight model for your system",
3599
3599
  installCommand: "ollama pull llama3.2"
3600
3600
  };
@@ -4687,6 +4687,17 @@ function convertMinimalToAnalysisResult(minimal, date, taxonomy, prompts3) {
4687
4687
  }
4688
4688
 
4689
4689
  // src/providers/base.ts
4690
+ var PLACEHOLDER_PATTERNS = [
4691
+ "kebab-case-id",
4692
+ "Original problematic prompt",
4693
+ "Improved version addressing the issue",
4694
+ "<PLACEHOLDER_EXAMPLE>",
4695
+ "Human-Readable Issue Name"
4696
+ ];
4697
+ function containsPlaceholders(response) {
4698
+ const lower = response.toLowerCase();
4699
+ return PLACEHOLDER_PATTERNS.some((p) => lower.includes(p.toLowerCase()));
4700
+ }
4690
4701
  function buildUserPrompt(prompts3, date, context) {
4691
4702
  if (prompts3.length === 0) {
4692
4703
  throw new Error("Cannot build prompt from empty array");
@@ -4818,6 +4829,11 @@ function parseResponse(response, date, taxonomy = ISSUE_TAXONOMY, prompts3) {
4818
4829
  );
4819
4830
  }
4820
4831
  }
4832
+ if (containsPlaceholders(response)) {
4833
+ throw new Error(
4834
+ "Response contains placeholder text - model did not provide real analysis"
4835
+ );
4836
+ }
4821
4837
  if (isValidMinimalResponse(parsed)) {
4822
4838
  const minimal = extractMinimalResult(parsed);
4823
4839
  return convertMinimalToAnalysisResult(minimal, date, taxonomy, prompts3);
@@ -4852,6 +4868,8 @@ function parseResponse(response, date, taxonomy = ISSUE_TAXONOMY, prompts3) {
4852
4868
  patterns: normalizedPatterns,
4853
4869
  stats: {
4854
4870
  ...parsed.stats,
4871
+ // Override totalPrompts with actual count if prompts provided
4872
+ totalPrompts: prompts3?.length ?? parsed.stats.totalPrompts,
4855
4873
  overallScore: normalizeScore(parsed.stats.overallScore)
4856
4874
  },
4857
4875
  topSuggestion: parsed.topSuggestion
package/dist/index.js CHANGED
@@ -1 +1 @@
1
- export { BATCH_STRATEGIES, CACHE_ANALYSIS_DIR, CACHE_DEFAULTS, CACHE_META_FILE, CLAUDE_PROJECTS_DIR, ENV_DEFAULTS, EXIT_CODES, HYNTX_CACHE_DIR, HYNTX_HISTORY_DIR, LAST_RUN_FILE, PROVIDER_LIMITS, analyzePrompts, claudeProjectsExist, cleanupExpiredEntries, clearCache, compareResults, createProvider, ensureHistoryDir, extractProjectName, generateCacheKey, getAllProviders, getAvailableProvider, getCachedResult, getDateOneMonthAgo, getDateOneWeekAgo, getEnvConfig, getHistoryDir, groupByDay, hashSystemPrompt, isFirstRun, listAvailableDates, loadAnalysisResult, loadProjectConfig, loadProjectConfigForCwd, mergeConfigs, parseDate, parseServices, readLogs, sanitize, sanitizePrompts, saveAnalysisResult, setCachedResult, validateSystemPrompt } from './chunk-TGFHVZHY.js';
1
+ export { BATCH_STRATEGIES, CACHE_ANALYSIS_DIR, CACHE_DEFAULTS, CACHE_META_FILE, CLAUDE_PROJECTS_DIR, ENV_DEFAULTS, EXIT_CODES, HYNTX_CACHE_DIR, HYNTX_HISTORY_DIR, LAST_RUN_FILE, PROVIDER_LIMITS, analyzePrompts, claudeProjectsExist, cleanupExpiredEntries, clearCache, compareResults, createProvider, ensureHistoryDir, extractProjectName, generateCacheKey, getAllProviders, getAvailableProvider, getCachedResult, getDateOneMonthAgo, getDateOneWeekAgo, getEnvConfig, getHistoryDir, groupByDay, hashSystemPrompt, isFirstRun, listAvailableDates, loadAnalysisResult, loadProjectConfig, loadProjectConfigForCwd, mergeConfigs, parseDate, parseServices, readLogs, sanitize, sanitizePrompts, saveAnalysisResult, setCachedResult, validateSystemPrompt } from './chunk-24U3LCZC.js';
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "hyntx",
3
- "version": "2.7.0",
3
+ "version": "3.0.0",
4
4
  "description": "CLI that analyzes Claude Code prompts and generates improvement suggestions",
5
5
  "type": "module",
6
6
  "packageManager": "pnpm@9.15.4",
@@ -46,17 +46,17 @@
46
46
  "url": "https://github.com/jmlweb/hyntx"
47
47
  },
48
48
  "devDependencies": {
49
- "@commitlint/cli": "^20.2.0",
50
- "@commitlint/config-conventional": "^20.2.0",
51
- "@eslint/js": "^9.17.0",
52
- "@jmlweb/commitlint-config": "^2.0.0",
53
- "@jmlweb/eslint-config-base": "^2.0.1",
54
- "@jmlweb/prettier-config-base": "^1.0.0",
55
- "@jmlweb/tsconfig-base": "^1.0.0",
56
- "@jmlweb/tsup-config-base": "^1.1.0",
57
- "@jmlweb/vitest-config": "^1.0.0",
49
+ "@commitlint/cli": "^20.3.0",
50
+ "@commitlint/config-conventional": "^20.3.0",
51
+ "@eslint/js": "^9.39.2",
52
+ "@jmlweb/commitlint-config": "^3.0.1",
53
+ "@jmlweb/eslint-config-base": "^2.0.8",
54
+ "@jmlweb/prettier-config-base": "^1.0.6",
55
+ "@jmlweb/tsconfig-base": "^1.0.5",
56
+ "@jmlweb/tsup-config-base": "^1.1.4",
57
+ "@jmlweb/vitest-config": "^2.0.0",
58
58
  "@semantic-release/changelog": "^6.0.3",
59
- "@semantic-release/exec": "^6.0.3",
59
+ "@semantic-release/exec": "^7.1.0",
60
60
  "@semantic-release/git": "^10.0.1",
61
61
  "@types/asciichart": "^1.5.8",
62
62
  "@types/figlet": "^1.7.0",
@@ -64,16 +64,16 @@
64
64
  "@types/prompts": "^2.4.9",
65
65
  "@vitest/coverage-v8": "^4.0.16",
66
66
  "conventional-changelog-conventionalcommits": "^9.1.0",
67
- "eslint": "^9.17.0",
68
- "eslint-config-prettier": "^9.1.0",
67
+ "eslint": "^9.39.2",
68
+ "eslint-config-prettier": "^10.1.8",
69
69
  "eslint-plugin-simple-import-sort": "^12.1.1",
70
70
  "husky": "^9.1.7",
71
71
  "lint-staged": "^16.2.7",
72
- "prettier": "^3.4.2",
72
+ "prettier": "^3.7.4",
73
73
  "semantic-release": "^25.0.2",
74
- "tsup": "^8.3.5",
75
- "typescript": "^5.7.2",
76
- "typescript-eslint": "^8.19.0",
74
+ "tsup": "^8.5.1",
75
+ "typescript": "^5.9.3",
76
+ "typescript-eslint": "^8.51.0",
77
77
  "vitest": "^4.0.16"
78
78
  },
79
79
  "bin": {
@@ -112,7 +112,7 @@
112
112
  ]
113
113
  },
114
114
  "dependencies": {
115
- "@modelcontextprotocol/sdk": "^1.25.1",
115
+ "@modelcontextprotocol/sdk": "^1.25.3",
116
116
  "asciichart": "^1.5.25",
117
117
  "boxen": "^8.0.1",
118
118
  "chalk": "^5.6.2",
@@ -125,6 +125,14 @@
125
125
  "ora": "^9.0.0",
126
126
  "prompts": "^2.4.2",
127
127
  "simple-statistics": "^7.8.8",
128
- "zod": "^4.2.1"
128
+ "zod": "^4.3.4"
129
+ },
130
+ "pnpm": {
131
+ "overrides": {
132
+ "hono": ">=4.11.4",
133
+ "lodash": ">=4.17.23",
134
+ "lodash-es": ">=4.17.23",
135
+ "undici": ">=7.18.2"
136
+ }
129
137
  }
130
138
  }