KrisSimon commited on
Commit
c44151a
·
verified ·
1 Parent(s): a2ab5cc

Release v1.1.0 — ARO Coder 6-bit (conversation_boosted, 45a5680524fdfc49)

Browse files
README.md CHANGED
@@ -24,12 +24,12 @@ ARO is a domain-specific language where every statement follows the pattern:
24
  | | |
25
  |---|---|
26
  | **Version** | v1.1.0 (tag `v1.1.0`) |
27
- | **Checksum** | `9383b5052e5e5d88` |
28
  | **Base model** | [mlx-community/Qwen3-Coder-30B-A3B-Instruct-bf16](https://huggingface.co/mlx-community/Qwen3-Coder-30B-A3B-Instruct-bf16) |
29
  | **Teacher source** | conversation_boosted (30B MoE teacher distilled to 8B student) |
30
  | **Quantization** | 6-bit MLX, group size 32 |
31
  | **Language** | ARO |
32
- | **Training samples** | 5723 |
33
 
34
  ## Links
35
 
@@ -45,7 +45,7 @@ ARO is a domain-specific language where every statement follows the pattern:
45
  |---|---|---|
46
  | Reply rate | 100.0% | 100.0% |
47
  | Empty-think collapse | 0.0% | 0.0% |
48
- | Syntax pass rate (`aro check`) | 68.8% | 70.7% |
49
  | Tool-name leakage | 0.0% | 0.0% |
50
  | URL contamination | 0.0% | 0.0% |
51
 
@@ -133,7 +133,7 @@ Key features:
133
 
134
  This model was trained with the ARO training pipeline:
135
 
136
- 1. **Corpus collection** — 5723 samples from Examples, Book, Wiki, Proposals, and real-world ARO applications
137
  2. **Supervised fine-tuning** — LoRA on all code generation, debugging, Q&A, and explanation tasks
138
  3. **DPO preference training** — using `aro check` validation to build chosen/rejected pairs
139
  4. **Iterative self-improvement** — multiple rounds of generate-validate-retrain
@@ -144,7 +144,7 @@ This model was trained with the ARO training pipeline:
144
 
145
  | Version | Date | Source | Checksum |
146
  |---|---|---|---|
147
- | v1.1.0 | 2026-08-06 | conversation_boosted | `9383b5052e5e5d88` |
148
 
149
  Every release is tagged on the Hub — load an older version with
150
  `load("ARO-Lang/aro-coder-6bit", revision="v<version>")` or report issues against
 
24
  | | |
25
  |---|---|
26
  | **Version** | v1.1.0 (tag `v1.1.0`) |
27
+ | **Checksum** | `45a5680524fdfc49` |
28
  | **Base model** | [mlx-community/Qwen3-Coder-30B-A3B-Instruct-bf16](https://huggingface.co/mlx-community/Qwen3-Coder-30B-A3B-Instruct-bf16) |
29
  | **Teacher source** | conversation_boosted (30B MoE teacher distilled to 8B student) |
30
  | **Quantization** | 6-bit MLX, group size 32 |
31
  | **Language** | ARO |
32
+ | **Training samples** | 6260 |
33
 
34
  ## Links
35
 
 
45
  |---|---|---|
46
  | Reply rate | 100.0% | 100.0% |
47
  | Empty-think collapse | 0.0% | 0.0% |
48
+ | Syntax pass rate (`aro check`) | 75.5% | 75.8% |
49
  | Tool-name leakage | 0.0% | 0.0% |
50
  | URL contamination | 0.0% | 0.0% |
51
 
 
133
 
134
  This model was trained with the ARO training pipeline:
135
 
136
+ 1. **Corpus collection** — 6260 samples from Examples, Book, Wiki, Proposals, and real-world ARO applications
137
  2. **Supervised fine-tuning** — LoRA on all code generation, debugging, Q&A, and explanation tasks
138
  3. **DPO preference training** — using `aro check` validation to build chosen/rejected pairs
139
  4. **Iterative self-improvement** — multiple rounds of generate-validate-retrain
 
144
 
145
  | Version | Date | Source | Checksum |
146
  |---|---|---|---|
147
+ | v1.1.0 | 2026-08-10 | conversation_boosted | `45a5680524fdfc49` |
148
 
149
  Every release is tagged on the Hub — load an older version with
150
  `load("ARO-Lang/aro-coder-6bit", revision="v<version>")` or report issues against
eval/last-run.json DELETED
@@ -1,393 +0,0 @@
1
- {
2
- "model_id": "ARO-Lang/aro-coder-6bit",
3
- "hub_commit": "7bf8c002c5637128ab922f9db15aa6c384cbdc43",
4
- "version": null,
5
- "validated_at": "2026-08-06T21:04:33.757421+00:00",
6
- "prompt_source": "bundled aro_system_prompt.txt",
7
- "passed": true,
8
- "breaches": [],
9
- "gates": {
10
- "reply_rate_min": 0.5,
11
- "empty_think_max": 0.2,
12
- "syntax_pass_min": 0.4,
13
- "tool_leak_max": 0.02,
14
- "url_contam_max": 0.05
15
- },
16
- "metrics": {
17
- "reply_rate": 1.0,
18
- "empty_think_rate": 0.0,
19
- "syntax_pass_rate": 0.7619047619047619,
20
- "tool_leak_rate": 0.0,
21
- "url_contam_rate": 0.0,
22
- "qa_answer_rate": 0.875,
23
- "total": 26,
24
- "with_code": 21,
25
- "syntax_pass": 16
26
- },
27
- "results": [
28
- {
29
- "idx": 1,
30
- "mode": "code",
31
- "cat": "repl_oneliner",
32
- "prompt": "Write a single ARO line that logs 'Hello, World!' to the console.",
33
- "reply": "```aro\nLog 'Hello, World!' to the <console>.\n```",
34
- "empty_think": false,
35
- "has_code": true,
36
- "aro_check_pass": false,
37
- "check_error": "main.aro:",
38
- "check_error_class": "other",
39
- "tool_leak": false,
40
- "url_contam": false
41
- },
42
- {
43
- "idx": 2,
44
- "mode": "code",
45
- "cat": "repl_block",
46
- "prompt": "Write ARO statements that create a list of three numbers and log its length.",
47
- "reply": "```aro\n(Application-Start: Example) {\n Create the <numbers> with [1, 2, 3].\n Log <numbers> to the <console>.\n}\n```",
48
- "empty_think": false,
49
- "has_code": true,
50
- "aro_check_pass": true,
51
- "check_error": "",
52
- "check_error_class": null,
53
- "tool_leak": false,
54
- "url_contam": false
55
- },
56
- {
57
- "idx": 3,
58
- "mode": "code",
59
- "cat": "application",
60
- "prompt": "Write a minimal ARO application that logs Hello World and exits.",
61
- "reply": "```aro\n(Application-Start: Hello World) {\n Log \"Hello World\" to the <console>.\n Return an <OK: status> for the <startup>.\n}\n```",
62
- "empty_think": false,
63
- "has_code": true,
64
- "aro_check_pass": true,
65
- "check_error": "",
66
- "check_error_class": null,
67
- "tool_leak": false,
68
- "url_contam": false
69
- },
70
- {
71
- "idx": 4,
72
- "mode": "code",
73
- "cat": "application",
74
- "prompt": "Write an ARO Application-Start that starts an HTTP server and keeps running with Keepalive.",
75
- "reply": "```aro\n(Application-Start: Server Demo) {\n Log \"Starting...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
76
- "empty_think": false,
77
- "has_code": true,
78
- "aro_check_pass": true,
79
- "check_error": "",
80
- "check_error_class": null,
81
- "tool_leak": false,
82
- "url_contam": false
83
- },
84
- {
85
- "idx": 5,
86
- "mode": "code",
87
- "cat": "application",
88
- "prompt": "Write an ARO Application-End: Success handler that logs a shutdown message.",
89
- "reply": "```aro\n(Application-End: Success) {\n Log \"Shutting down...\" to the <console>.\n}\n```",
90
- "empty_think": false,
91
- "has_code": true,
92
- "aro_check_pass": true,
93
- "check_error": "",
94
- "check_error_class": null,
95
- "tool_leak": false,
96
- "url_contam": false
97
- },
98
- {
99
- "idx": 6,
100
- "mode": "code",
101
- "cat": "http_api",
102
- "prompt": "Write an ARO feature set named getUser that retrieves a user by ID from the user-repository and returns it as an OK response.",
103
- "reply": "```aro\n(getUser: User API) {\n Extract the <id> from the <pathParameters: id>.\n Retrieve the <user> from the <user-repository> where id = <id>.\n Return an <OK: status> with <user>.\n}\n```",
104
- "empty_think": false,
105
- "has_code": true,
106
- "aro_check_pass": false,
107
- "check_error": "main.aro:",
108
- "check_error_class": "other",
109
- "tool_leak": false,
110
- "url_contam": false
111
- },
112
- {
113
- "idx": 7,
114
- "mode": "code",
115
- "cat": "http_api",
116
- "prompt": "Write an ARO feature set named createOrder that extracts the request body, stores a new order, and returns a Created status.",
117
- "reply": "```aro\n(createOrder: Orders API) {\n Extract the <order> from the <request: body>.\n Store the <new-order> into the <order-repository>.\n Return a <Created: status> with <new-order>.\n}\n```",
118
- "empty_think": false,
119
- "has_code": true,
120
- "aro_check_pass": true,
121
- "check_error": "",
122
- "check_error_class": null,
123
- "tool_leak": false,
124
- "url_contam": false
125
- },
126
- {
127
- "idx": 8,
128
- "mode": "code",
129
- "cat": "http_api",
130
- "prompt": "Write an ARO feature set named listProducts that retrieves all products and returns them.",
131
- "reply": "```aro\n(listProducts: Product API) {\n Retrieve the <products> from the <product-repository>.\n Return an <OK: status> with <products>.\n}\n```",
132
- "empty_think": false,
133
- "has_code": true,
134
- "aro_check_pass": true,
135
- "check_error": "",
136
- "check_error_class": null,
137
- "tool_leak": false,
138
- "url_contam": false
139
- },
140
- {
141
- "idx": 9,
142
- "mode": "code",
143
- "cat": "event_handler",
144
- "prompt": "Write an ARO event handler that sends a welcome email when a UserCreated event is received.",
145
- "reply": "```aro\n(Send Email: UserCreated Handler) {\n Extract the <user> from the <event: user>.\n Send the <welcome-email> to the <user: email>.\n Return an <OK: status> for the <notification>.\n}\n```",
146
- "empty_think": false,
147
- "has_code": true,
148
- "aro_check_pass": true,
149
- "check_error": "",
150
- "check_error_class": null,
151
- "tool_leak": false,
152
- "url_contam": false
153
- },
154
- {
155
- "idx": 10,
156
- "mode": "code",
157
- "cat": "event_handler",
158
- "prompt": "Write an ARO feature set that emits an OrderPlaced event with the order data.",
159
- "reply": "```aro\n(OrderPlaced: Event Example) {\n Extract the <order> from the <request: body>.\n Emit a <OrderPlaced: event> with <order>.\n}\n```",
160
- "empty_think": false,
161
- "has_code": true,
162
- "aro_check_pass": true,
163
- "check_error": "",
164
- "check_error_class": null,
165
- "tool_leak": false,
166
- "url_contam": false
167
- },
168
- {
169
- "idx": 11,
170
- "mode": "code",
171
- "cat": "repository",
172
- "prompt": "Write an ARO feature set that observes the user-repository and logs every change.",
173
- "reply": "```aro\n(Application-Start: Watch User Changes) {\n Log \"Starting user change watcher...\" to the <console>.\n Start the <file-monitor> for the <user-repository>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
174
- "empty_think": false,
175
- "has_code": true,
176
- "aro_check_pass": true,
177
- "check_error": "",
178
- "check_error_class": null,
179
- "tool_leak": false,
180
- "url_contam": false
181
- },
182
- {
183
- "idx": 12,
184
- "mode": "code",
185
- "cat": "repository",
186
- "prompt": "Write an ARO feature set that stores a new record in the sessions-repository and emits a SessionCreated event.",
187
- "reply": "```aro\n(Store Session: Example) {\n Create the <session> with { id: 1, name: \"Example\" }.\n Store the <session> into the <sessions-repository>.\n Emit a <SessionCreated: event> with <session>.\n}\n```",
188
- "empty_think": false,
189
- "has_code": true,
190
- "aro_check_pass": true,
191
- "check_error": "",
192
- "check_error_class": null,
193
- "tool_leak": false,
194
- "url_contam": false
195
- },
196
- {
197
- "idx": 13,
198
- "mode": "code",
199
- "cat": "iteration",
200
- "prompt": "Write an ARO for-each loop that logs each item in a list of names.",
201
- "reply": "```aro\n(LogNames: Example) {\n Create the <names> with [\"Alice\", \"Bob\", \"Carol\"].\n For each <name> in <names> {\n Log <name> to the <console>.\n }\n}\n```",
202
- "empty_think": false,
203
- "has_code": true,
204
- "aro_check_pass": true,
205
- "check_error": "",
206
- "check_error_class": null,
207
- "tool_leak": false,
208
- "url_contam": false
209
- },
210
- {
211
- "idx": 14,
212
- "mode": "code",
213
- "cat": "conditional",
214
- "prompt": "Write an ARO feature set with a When guard that only returns OK when the user role is \"admin\".",
215
- "reply": "```aro\n(GuardedAdmin: Example) {\n Extract the <user-role> from the <request: role>.\n When <user-role> = \"admin\" {\n Return an <OK: status> for the <check>.\n }\n}\n```",
216
- "empty_think": false,
217
- "has_code": true,
218
- "aro_check_pass": false,
219
- "check_error": "main.aro:",
220
- "check_error_class": "other",
221
- "tool_leak": false,
222
- "url_contam": false
223
- },
224
- {
225
- "idx": 15,
226
- "mode": "code",
227
- "cat": "computation",
228
- "prompt": "Write an ARO feature set that computes the total price from price and quantity and returns it.",
229
- "reply": "```aro\n(ComputeTotal: Example) {\n Extract the <price> from the <request: price>.\n Extract the <quantity> from the <request: quantity>.\n Compute the <total: price> from <price> * <quantity>.\n Return an <OK: status> with <total>.\n}\n```",
230
- "empty_think": false,
231
- "has_code": true,
232
- "aro_check_pass": true,
233
- "check_error": "",
234
- "check_error_class": null,
235
- "tool_leak": false,
236
- "url_contam": false
237
- },
238
- {
239
- "idx": 16,
240
- "mode": "code",
241
- "cat": "user_action",
242
- "prompt": "Define an ARO user-defined action named DoubleValue that doubles a number.",
243
- "reply": "```aro\n(DoubleValue: Action takes <number>) {\n Extract the <n> from the <input: number>.\n Compute the <doubled> from <n> * 2.\n Return an <OK: status> with { doubled: <doubled> }.\n}\n```",
244
- "empty_think": false,
245
- "has_code": true,
246
- "aro_check_pass": true,
247
- "check_error": "",
248
- "check_error_class": null,
249
- "tool_leak": false,
250
- "url_contam": false
251
- },
252
- {
253
- "idx": 17,
254
- "mode": "code",
255
- "cat": "debugging",
256
- "prompt": "Fix this ARO code so it passes aro check:\n\n```aro\n(listUsers: User API) {\n Retrieve the <users> from the <user-repository>.\n Return an <OK: status> with <users>.\n```",
257
- "reply": "```aro\n(listUsers: User API) {\n Retrieve the <users> from the <user-repository>.\n Return an <OK: status> with <users>.\n}\n```",
258
- "empty_think": false,
259
- "has_code": true,
260
- "aro_check_pass": true,
261
- "check_error": "",
262
- "check_error_class": null,
263
- "tool_leak": false,
264
- "url_contam": false
265
- },
266
- {
267
- "idx": 18,
268
- "mode": "code",
269
- "cat": "file",
270
- "prompt": "Write an ARO Application-Start that reads a config file and logs its contents.",
271
- "reply": "```aro\n(Application-Start: Config Reader) {\n Read the <config> from the <file: \"config.json\">.\n Log <config> to the <console>.\n Return an <OK: status> for the <startup>.\n}\n```",
272
- "empty_think": false,
273
- "has_code": true,
274
- "aro_check_pass": true,
275
- "check_error": "",
276
- "check_error_class": null,
277
- "tool_leak": false,
278
- "url_contam": false
279
- },
280
- {
281
- "idx": 19,
282
- "mode": "qa",
283
- "cat": "explain",
284
- "prompt": "What is the difference between Extract and Compute actions in ARO?",
285
- "reply": "The Extract action is OWN-role. It extracts a value from an existing object or data structure. For example:\n```aro\nExtract the <total: count> from the <order: total>.\n```\n\nThe Compute action is OWN-role. It derives a new value from existing data. For example:\n```aro\nCompute the <total: count> from the <order: total>.\n```",
286
- "empty_think": false,
287
- "has_code": true,
288
- "aro_check_pass": false,
289
- "check_error": "main.aro:",
290
- "check_error_class": "other",
291
- "tool_leak": false,
292
- "url_contam": false
293
- },
294
- {
295
- "idx": 20,
296
- "mode": "qa",
297
- "cat": "explain",
298
- "prompt": "How do I emit a custom event in ARO and handle it in another feature set?",
299
- "reply": "```aro\n(Application-Start: Custom Event Demo) {\n Log \"Starting...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n\n(Emit Custom Event: Example) {\n Create the <event> with { name: \"Custom Event\", data: \"example\" }.\n Emit a <CustomEvent: event> with <event>.\n}\n\n(Send Custom Event: CustomEvent Handler) {\n Extract the <event> from the <event: event>.\n Log <event> to the <c",
300
- "empty_think": false,
301
- "has_code": true,
302
- "aro_check_pass": true,
303
- "check_error": "",
304
- "check_error_class": null,
305
- "tool_leak": false,
306
- "url_contam": false
307
- },
308
- {
309
- "idx": 21,
310
- "mode": "qa",
311
- "cat": "explain",
312
- "prompt": "How does the Publish action work in ARO? Give an example.",
313
- "reply": "The Publish action exports data or makes it visible. It takes the data to publish and the destination (e.g., console, file, or network).\n```aro\n(Application-Start: Example) {\n Log \"Starting...\" to the <console>.\n Publish as <status> <startup>.\n}\n```",
314
- "empty_think": false,
315
- "has_code": true,
316
- "aro_check_pass": false,
317
- "check_error": "main.aro:",
318
- "check_error_class": "other",
319
- "tool_leak": false,
320
- "url_contam": false
321
- },
322
- {
323
- "idx": 22,
324
- "mode": "qa",
325
- "cat": "explain",
326
- "prompt": "Why are ARO variables immutable and how do I update a value?",
327
- "reply": "Every feature set ends with a Return or Throw \u2014 there are no intermediate assignments. To change a value you must extract it fresh from the existing data.",
328
- "empty_think": false,
329
- "has_code": false,
330
- "aro_check_pass": null,
331
- "check_error": "",
332
- "check_error_class": null,
333
- "tool_leak": false,
334
- "url_contam": false
335
- },
336
- {
337
- "idx": 23,
338
- "mode": "qa",
339
- "cat": "explain",
340
- "prompt": "What does the Keepalive action do and when do I need it?",
341
- "reply": "The `Keepalive` action maintains a connection or periodically checks the status of a service. Use it to ensure a service stays alive and responsive, especially when waiting for events or maintaining a connection.",
342
- "empty_think": false,
343
- "has_code": false,
344
- "aro_check_pass": null,
345
- "check_error": "",
346
- "check_error_class": null,
347
- "tool_leak": false,
348
- "url_contam": false
349
- },
350
- {
351
- "idx": 24,
352
- "mode": "qa",
353
- "cat": "explain",
354
- "prompt": "How does contract-first HTTP routing work in ARO?",
355
- "reply": "The Application-Start handler processes the <startup: event> and creates the <http-server>. The <contract> describes the HTTP routes and their handlers. The server listens on the <contract: port> and routes incoming requests to the corresponding handlers based on the <contract: routes>.",
356
- "empty_think": false,
357
- "has_code": false,
358
- "aro_check_pass": null,
359
- "check_error": "",
360
- "check_error_class": null,
361
- "tool_leak": false,
362
- "url_contam": false
363
- },
364
- {
365
- "idx": 25,
366
- "mode": "qa",
367
- "cat": "edge",
368
- "prompt": "Does ARO have error handling? Explain the error philosophy briefly.",
369
- "reply": "Yes. ARO uses `Return` to end each feature set with a status. The runtime turns every non-OK status to a 500 error.",
370
- "empty_think": false,
371
- "has_code": false,
372
- "aro_check_pass": null,
373
- "check_error": "",
374
- "check_error_class": null,
375
- "tool_leak": false,
376
- "url_contam": false
377
- },
378
- {
379
- "idx": 26,
380
- "mode": "qa",
381
- "cat": "edge",
382
- "prompt": "What is a .store file in ARO and when is it writable?",
383
- "reply": "Every application must keep its state in the `.store` file \u2014 the runtime maintains it across restarts.",
384
- "empty_think": false,
385
- "has_code": false,
386
- "aro_check_pass": null,
387
- "check_error": "",
388
- "check_error_class": null,
389
- "tool_leak": false,
390
- "url_contam": false
391
- }
392
- ]
393
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75f36a8113368f06c11aff949cd0492339264060bace2928fdab469b3ecb1031
3
  size 5352815610
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ee9bacaa0f08de8b98fab4d81a38b48fbe48b8674936b02ea7c851760d62957
3
  size 5352815610
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49bc13f0ee203a7723c840c59c209f7f99b91058c9926986a3db748d225de7c3
3
  size 1814528290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6330b682426ca8d51d2bb1b6b0b59777f6290fe7436adaeb32509a8757ac357e
3
  size 1814528290
promotion_gate.json CHANGED
@@ -1,17 +1,17 @@
1
  {
2
  "reply_rate": 1.0,
3
  "empty_think_rate": 0.0,
4
- "syntax_pass_rate": 0.6881720430107527,
5
  "tool_leak_rate": 0.0,
6
  "url_contam_rate": 0.0,
7
  "total": 104,
8
- "with_code": 93,
9
  "results": [
10
  {
11
  "idx": 1,
12
  "cat": "repl_oneliner",
13
  "prompt": "Write a single ARO line that logs the message 'Hello, World!' to the console.",
14
- "reply": "```aro\nLog \"Hello, World!\" to the <console>.\n```",
15
  "empty_think": false,
16
  "has_code": true,
17
  "tool_leak": false,
@@ -21,7 +21,7 @@
21
  "idx": 2,
22
  "cat": "repl_oneliner",
23
  "prompt": "Write one ARO statement that retrieves the current time from the clock.",
24
- "reply": "```aro\nRetrieve the <current-time> from the <clock>.\n```",
25
  "empty_think": false,
26
  "has_code": true,
27
  "tool_leak": false,
@@ -31,7 +31,7 @@
31
  "idx": 3,
32
  "cat": "repl_oneliner",
33
  "prompt": "Write a single line that computes the length of the string 'banana'.",
34
- "reply": "```aro\nCompute the <length: length> from the <message: \"banana\">.\n```",
35
  "empty_think": false,
36
  "has_code": true,
37
  "tool_leak": false,
@@ -41,7 +41,7 @@
41
  "idx": 4,
42
  "cat": "repl_oneliner",
43
  "prompt": "Write one ARO statement that converts the string 'hello' to uppercase.",
44
- "reply": "```aro\nConvert the <upper: uppercase> from the <message: \"hello\">.\n```",
45
  "empty_think": false,
46
  "has_code": true,
47
  "tool_leak": false,
@@ -51,7 +51,7 @@
51
  "idx": 5,
52
  "cat": "repl_oneliner",
53
  "prompt": "Write one line that hashes the password 'secret'.",
54
- "reply": "```aro\nHash the <hash: password> from the <password>.\n```",
55
  "empty_think": false,
56
  "has_code": true,
57
  "tool_leak": false,
@@ -71,7 +71,7 @@
71
  "idx": 7,
72
  "cat": "repl_oneliner",
73
  "prompt": "Write one line that retrieves the git status.",
74
- "reply": "```aro\nRetrieve the <git-status> from the <git>.\n```",
75
  "empty_think": false,
76
  "has_code": true,
77
  "tool_leak": false,
@@ -111,7 +111,7 @@
111
  "idx": 11,
112
  "cat": "repl_block",
113
  "prompt": "Write a 3-statement ARO snippet that reads a file, uppercases it, and logs the result.",
114
- "reply": "```aro\nRead the <file-content> from the <file: \"data.txt\">.\nCompute the <uppercase: upper-case> from the <file-content>.\nLog <uppercase> to the <console>.\n```",
115
  "empty_think": false,
116
  "has_code": true,
117
  "tool_leak": false,
@@ -121,7 +121,7 @@
121
  "idx": 12,
122
  "cat": "repl_block",
123
  "prompt": "Write a 4-statement snippet that fetches users from a repository, computes the count, and logs it.",
124
- "reply": "```aro\n(Application-Start: User API) {\n Retrieve the <users> from the <user-repository>.\n Compute the <total: count> from the <users>.\n Log <total> to the <console>.\n}\n```",
125
  "empty_think": false,
126
  "has_code": true,
127
  "tool_leak": false,
@@ -131,7 +131,7 @@
131
  "idx": 13,
132
  "cat": "repl_block",
133
  "prompt": "Write an ARO snippet that stages all changes, commits with message 'wip', and pushes.",
134
- "reply": "```aro\n(Application-Start: Example) {\n Stage the <result> from the <git>.\n Commit the <result> to the <git> with \"wip\".\n Push the <result> to the <git>.\n}\n```",
135
  "empty_think": false,
136
  "has_code": true,
137
  "tool_leak": false,
@@ -141,7 +141,7 @@
141
  "idx": 14,
142
  "cat": "repl_block",
143
  "prompt": "Write a 3-statement snippet that creates a list, computes its length, and logs the length.",
144
- "reply": "```aro\n(Application-Start: List Demo) {\n Create the <items> with [1, 2, 3].\n Compute the <total: length> from the <items>.\n Log <total> to the <console>.\n}\n```",
145
  "empty_think": false,
146
  "has_code": true,
147
  "tool_leak": false,
@@ -151,7 +151,7 @@
151
  "idx": 15,
152
  "cat": "repl_block",
153
  "prompt": "Write a snippet that extracts a name from an event, uppercases it, and stores it back in a variable.",
154
- "reply": "```aro\nExtract the <name> from the <event: name>.\nCompute the <uppercase-name: uppercase> from the <name>.\nStore the <uppercase-name> into the <name>.\n```",
155
  "empty_think": false,
156
  "has_code": true,
157
  "tool_leak": false,
@@ -161,7 +161,7 @@
161
  "idx": 16,
162
  "cat": "repl_block",
163
  "prompt": "Write a 3-statement snippet that computes 3 + 4, multiplies by 2, and logs the result.",
164
- "reply": "```aro\n(Application-Start: Example) {\n Compute the <total: sum> from 3 + 4.\n Compute the <result: total> from <total>.\n Log <result> to the <console>.\n}\n```",
165
  "empty_think": false,
166
  "has_code": true,
167
  "tool_leak": false,
@@ -171,7 +171,7 @@
171
  "idx": 17,
172
  "cat": "repl_block",
173
  "prompt": "Write a snippet that reads two numbers and returns their sum.",
174
- "reply": "```aro\n(Application-Start: Example) {\n Read the <a> from the <console>.\n Read the <b> from the <console>.\n Compute the <total: sum> from <a> + <b>.\n Return an <OK: status> with <total>.\n}\n```",
175
  "empty_think": false,
176
  "has_code": true,
177
  "tool_leak": false,
@@ -181,7 +181,7 @@
181
  "idx": 18,
182
  "cat": "repl_block",
183
  "prompt": "Write a snippet that filters a list of users where age > 18 and counts them.",
184
- "reply": "```aro\n(FilterUsers: Example) {\n Create the <users> with [\n { name: \"Alice\", age: 25 },\n { name: \"Bob\", age: 17 },\n { name: \"Carol\", age: 30 }\n ].\n Filter the <adults: users> from the <users> where <age> > 18.\n Compute the <total: count> from the <adults>.\n Return an <OK: status> with <total>.\n}\n```",
185
  "empty_think": false,
186
  "has_code": true,
187
  "tool_leak": false,
@@ -191,7 +191,7 @@
191
  "idx": 19,
192
  "cat": "repl_block",
193
  "prompt": "Write a snippet that joins two lists and stores the result as <combined>.",
194
- "reply": "```aro\n(JoinLists: Example) {\n Create the <list-a> with [1, 2, 3].\n Create the <list-b> with [4, 5, 6].\n Combine the <combined> from the <list-a> with <list-b>.\n}\n```",
195
  "empty_think": false,
196
  "has_code": true,
197
  "tool_leak": false,
@@ -201,7 +201,7 @@
201
  "idx": 20,
202
  "cat": "repl_block",
203
  "prompt": "Write a snippet that parses a JSON string and extracts the 'name' field.",
204
- "reply": "```aro\n(ParseUser: Example) {\n Parse the <user> from the <request: body>.\n Extract the <name> from the <user: name>.\n Return an <OK: status> with <name>.\n}\n```",
205
  "empty_think": false,
206
  "has_code": true,
207
  "tool_leak": false,
@@ -221,7 +221,7 @@
221
  "idx": 22,
222
  "cat": "user_action",
223
  "prompt": "Write a user-defined action 'Greet' that takes a name and returns a greeting string.",
224
- "reply": "```aro\n(Greet: User API) {\n Extract the <name> from the <request: name>.\n Return an <OK: status> with <name>.\n}\n```",
225
  "empty_think": false,
226
  "has_code": true,
227
  "tool_leak": false,
@@ -231,7 +231,7 @@
231
  "idx": 23,
232
  "cat": "user_action",
233
  "prompt": "Write a user-defined action 'AddTwoNumbers' that takes two numbers and returns their sum.",
234
- "reply": "```aro\n(AddTwoNumbers: Action takes <a>, <b>) {\n Extract the <a> from the <input: a>.\n Extract the <b> from the <input: b>.\n Compute the <sum> from <a> + <b>.\n Return an <OK: status> with <sum>.\n}\n```",
235
  "empty_think": false,
236
  "has_code": true,
237
  "tool_leak": false,
@@ -241,7 +241,7 @@
241
  "idx": 24,
242
  "cat": "user_action",
243
  "prompt": "Write a user-defined action 'ValidateEmail' that takes an email string and returns OK or Error.",
244
- "reply": "```aro\n(ValidateEmail: Action takes <email>) {\n Extract the <address> from the <email: address>.\n Return an <OK: status> with <address>.\n}\n```",
245
  "empty_think": false,
246
  "has_code": true,
247
  "tool_leak": false,
@@ -251,7 +251,7 @@
251
  "idx": 25,
252
  "cat": "user_action",
253
  "prompt": "Write a user-defined action 'Square' that takes a number and returns its square.",
254
- "reply": "```aro\n(Square: Action takes <number>) {\n Extract the <n> from the <input: number>.\n Compute the <squared> from <n> * <n>.\n Return an <OK: status> with <squared>.\n}\n```",
255
  "empty_think": false,
256
  "has_code": true,
257
  "tool_leak": false,
@@ -261,7 +261,7 @@
261
  "idx": 26,
262
  "cat": "user_action",
263
  "prompt": "Write a user-defined action 'FormatDate' that takes a date and a format string.",
264
- "reply": "```aro\n(FormatDate: User API) {\n Extract the <date> from the <request: date>.\n Extract the <format> from the <request: format>.\n Format the <formatted-date> from the <date> with <format>.\n Return an <OK: status> with <formatted-date>.\n}\n```",
265
  "empty_think": false,
266
  "has_code": true,
267
  "tool_leak": false,
@@ -271,7 +271,7 @@
271
  "idx": 27,
272
  "cat": "user_action",
273
  "prompt": "Write a user-defined action 'CountWords' that takes a string and returns the word count.",
274
- "reply": "```aro\n(CountWords: Action takes <text>) {\n Extract the <words> from the <text>.\n Compute the <total: count> from the <words>.\n Return an <OK: status> with <total>.\n}\n```",
275
  "empty_think": false,
276
  "has_code": true,
277
  "tool_leak": false,
@@ -281,7 +281,7 @@
281
  "idx": 28,
282
  "cat": "user_action",
283
  "prompt": "Write a user-defined action 'PickRandom' that takes a list and returns a random element.",
284
- "reply": "```aro\n(PickRandom: Action takes <list>) {\n Extract the <items> from the <input: list>.\n Compute the <random-item: pick-random> from the <items>.\n Return an <OK: status> with <random-item>.\n}\n```",
285
  "empty_think": false,
286
  "has_code": true,
287
  "tool_leak": false,
@@ -291,7 +291,7 @@
291
  "idx": 29,
292
  "cat": "user_action",
293
  "prompt": "Write a user-defined action 'Capitalize' that takes a string and uppercases its first letter.",
294
- "reply": "```aro\n(Capitalize: Action takes <text>) {\n Extract the <lower: text> from the <input: text>.\n Compute the <upper: uppercase> from <lower>.\n Return an <OK: status> with <upper>.\n}\n```",
295
  "empty_think": false,
296
  "has_code": true,
297
  "tool_leak": false,
@@ -301,7 +301,7 @@
301
  "idx": 30,
302
  "cat": "user_action",
303
  "prompt": "Write a user-defined action 'ComputeTax' that takes a price and a rate and returns the tax.",
304
- "reply": "```aro\nComputeTax: User Defined Action takes <price>, <rate>.\n```",
305
  "empty_think": false,
306
  "has_code": true,
307
  "tool_leak": false,
@@ -321,7 +321,7 @@
321
  "idx": 32,
322
  "cat": "event_handler",
323
  "prompt": "Write an event handler for OrderPlaced that decrements inventory.",
324
- "reply": "```aro\n(Send Email: OrderPlaced Handler) {\n Extract the <order> from the <event: order>.\n Retrieve the <inventory> from the <inventory-repository>.\n Decrement the <inventory: quantity> from <order: quantity>.\n Store the <inventory> into the <inventory-repository>.\n Return an <OK: status> for the <notification>.\n}\n```",
325
  "empty_think": false,
326
  "has_code": true,
327
  "tool_leak": false,
@@ -331,7 +331,7 @@
331
  "idx": 33,
332
  "cat": "event_handler",
333
  "prompt": "Write an event handler for PaymentFailed that logs the error and notifies the user.",
334
- "reply": "```aro\n(Send Payment Failed Email: PaymentFailed Handler) {\n Extract the <error> from the <event: error>.\n Log <error> to the <console>.\n Send the <payment-failed-email> to the <user: email>.\n Return an <OK: status> for the <notification>.\n}\n```",
335
  "empty_think": false,
336
  "has_code": true,
337
  "tool_leak": false,
@@ -341,7 +341,7 @@
341
  "idx": 34,
342
  "cat": "event_handler",
343
  "prompt": "Write an event handler for FileChanged that re-reads the configuration.",
344
- "reply": "```aro\n(FileChanged: File Event Handler) {\n Read the <config> from the <file: \"config.json\">.\n Log <config> to the <console>.\n}\n```",
345
  "empty_think": false,
346
  "has_code": true,
347
  "tool_leak": false,
@@ -351,7 +351,7 @@
351
  "idx": 35,
352
  "cat": "event_handler",
353
  "prompt": "Write an event handler for LoginAttempt that records the IP address.",
354
- "reply": "```aro\n(Send Login Attempt: LoginAttempt Handler) {\n Extract the <ip> from the <event: ip>.\n Log <ip> to the <console>.\n Return an <OK: status> for the <login>.\n}\n```",
355
  "empty_think": false,
356
  "has_code": true,
357
  "tool_leak": false,
@@ -361,7 +361,7 @@
361
  "idx": 36,
362
  "cat": "event_handler",
363
  "prompt": "Write an event handler for GitPush that triggers a CI build.",
364
- "reply": "```aro\n(GitPush: Event Handler) {\n Extract the <result> from the <event: result>.\n Start the <ci-build> with <result>.\n Return an <OK: status> for the <build>.\n}\n```",
365
  "empty_think": false,
366
  "has_code": true,
367
  "tool_leak": false,
@@ -371,7 +371,7 @@
371
  "idx": 37,
372
  "cat": "event_handler",
373
  "prompt": "Write an event handler for SubscriptionExpired that downgrades the account.",
374
- "reply": "```aro\n(Welcome: SubscriptionExpired Handler) {\n Extract the <user> from the <event: user>.\n Downgrade the <account> for the <user>.\n Return an <OK: status> for the <notification>.\n}\n```",
375
  "empty_think": false,
376
  "has_code": true,
377
  "tool_leak": false,
@@ -381,7 +381,7 @@
381
  "idx": 38,
382
  "cat": "event_handler",
383
  "prompt": "Write an event handler for ServerStarted that warms up the cache.",
384
- "reply": "```aro\n(ServerStarted: Event Handler) {\n Log \"Server started \u2014 warming up cache...\" to the <console>.\n Retrieve the <cache> from the <cache-repository>.\n Return an <OK: status> for the <warm-up>.\n}\n```",
385
  "empty_think": false,
386
  "has_code": true,
387
  "tool_leak": false,
@@ -391,7 +391,7 @@
391
  "idx": 39,
392
  "cat": "event_handler",
393
  "prompt": "Write an event handler for MessageReceived that echoes the message back.",
394
- "reply": "```aro\n(Send Message: MessageReceived Handler) {\n Extract the <message> from the <event: message>.\n Send the <message> to the <console>.\n Return an <OK: status> for the <message>.\n}\n```",
395
  "empty_think": false,
396
  "has_code": true,
397
  "tool_leak": false,
@@ -401,7 +401,7 @@
401
  "idx": 40,
402
  "cat": "event_handler",
403
  "prompt": "Write an event handler for ImageUploaded that generates a thumbnail.",
404
- "reply": "```aro\n(Send Thumbnail: ImageUploaded Handler) {\n Extract the <image> from the <event: image>.\n Create the <thumbnail> with <image>.\n Return an <OK: status> with <thumbnail>.\n}\n```",
405
  "empty_think": false,
406
  "has_code": true,
407
  "tool_leak": false,
@@ -411,7 +411,7 @@
411
  "idx": 41,
412
  "cat": "application",
413
  "prompt": "Write a complete ARO Application-Start that prints Hello and exits.",
414
- "reply": "```aro\n(Application-Start: Hello World) {\n Log \"Hello\" to the <console>.\n Return an <OK: status> for the <startup>.\n}\n```",
415
  "empty_think": false,
416
  "has_code": true,
417
  "tool_leak": false,
@@ -431,7 +431,7 @@
431
  "idx": 43,
432
  "cat": "application",
433
  "prompt": "Write a complete Application-Start that watches a directory for changes.",
434
- "reply": "```aro\n(Application-Start: Watcher) {\n Log \"Starting watcher...\" to the <console>.\n Start the <file-monitor> for the <directory: \"./watched\">.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
435
  "empty_think": false,
436
  "has_code": true,
437
  "tool_leak": false,
@@ -451,7 +451,7 @@
451
  "idx": 45,
452
  "cat": "application",
453
  "prompt": "Write a complete Application-Start that opens a TCP echo server on port 9000.",
454
- "reply": "```aro\n(Application-Start: Echo Server) {\n Start the <tcp-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
455
  "empty_think": false,
456
  "has_code": true,
457
  "tool_leak": false,
@@ -471,7 +471,7 @@
471
  "idx": 47,
472
  "cat": "application",
473
  "prompt": "Write a complete Application-Start that connects to a database and runs a single query.",
474
- "reply": "```aro\n(Application-Start: Database Demo) {\n Log \"Starting...\" to the <console>.\n Connect to the <database> with <connection-string>.\n Retrieve the <users> from the <database>.\n Return an <OK: status> for the <startup>.\n}\n```",
475
  "empty_think": false,
476
  "has_code": true,
477
  "tool_leak": false,
@@ -481,7 +481,7 @@
481
  "idx": 48,
482
  "cat": "application",
483
  "prompt": "Write a complete Application-Start that reads command-line parameters and prints them.",
484
- "reply": "```aro\n(Application-Start: Command Line App) {\n Read the <args> from the <command-line: args>.\n Log <args> to the <console>.\n Return an <OK: status> for the <startup>.\n}\n```",
485
  "empty_think": false,
486
  "has_code": true,
487
  "tool_leak": false,
@@ -491,7 +491,7 @@
491
  "idx": 49,
492
  "cat": "application",
493
  "prompt": "Write a complete Application-Start that loads a configuration file and logs it.",
494
- "reply": "```aro\n(Application-Start: Config Loader) {\n Log \"Starting...\" to the <console>.\n Read the <config> from the <file: \"config.json\">.\n Log <config> to the <console>.\n Return an <OK: status> for the <startup>.\n}\n```",
495
  "empty_think": false,
496
  "has_code": true,
497
  "tool_leak": false,
@@ -501,7 +501,7 @@
501
  "idx": 50,
502
  "cat": "application",
503
  "prompt": "Write a complete Application-Start that prints the current git branch.",
504
- "reply": "```aro\n(Application-Start: Git Branch Printer) {\n Log \"Starting...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
505
  "empty_think": false,
506
  "has_code": true,
507
  "tool_leak": false,
@@ -521,7 +521,7 @@
521
  "idx": 52,
522
  "cat": "http_api",
523
  "prompt": "Write the openapi.yaml plus feature set for a POST /products endpoint.",
524
- "reply": "```aro\n(Application-Start: Product API) {\n Log \"Starting...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n\n(createProduct: Product API) {\n Extract the <product-data> from the <request: body>.\n Create the <product> with <product-data>.\n Emit a <ProductCreated: event> with <product>.\n Return a <Created: status> with <product>.\n}\n\n```",
525
  "empty_think": false,
526
  "has_code": true,
527
  "tool_leak": false,
@@ -531,7 +531,7 @@
531
  "idx": 53,
532
  "cat": "http_api",
533
  "prompt": "Write a feature set for getUserById that extracts the id from pathParameters.",
534
- "reply": "```aro\n(getUserById: User API) {\n Extract the <id> from the <pathParameters: id>.\n Retrieve the <user> from the <user-repository> where <id> = <id>.\n Return an <OK: status> with <user>.\n}\n```",
535
  "empty_think": false,
536
  "has_code": true,
537
  "tool_leak": false,
@@ -541,7 +541,7 @@
541
  "idx": 54,
542
  "cat": "http_api",
543
  "prompt": "Write a feature set for createOrder that validates the request body and emits OrderCreated.",
544
- "reply": "```aro\n(createOrder: Orders API) {\n Extract the <request> from the <request: body>.\n Validate the <validated: request> with <request>.\n Emit a <OrderCreated: event> with <validated>.\n}\n```",
545
  "empty_think": false,
546
  "has_code": true,
547
  "tool_leak": false,
@@ -551,7 +551,7 @@
551
  "idx": 55,
552
  "cat": "http_api",
553
  "prompt": "Write a feature set for deleteSession that removes a session from the sessions-repository.",
554
- "reply": "```aro\n(deleteSession: Session API) {\n Extract the <id> from the <pathParameters: id>.\n Delete the <session> from the <sessions-repository> where <id> = <id>.\n Return an <OK: status> for the <deletion>.\n}\n```",
555
  "empty_think": false,
556
  "has_code": true,
557
  "tool_leak": false,
@@ -561,7 +561,7 @@
561
  "idx": 56,
562
  "cat": "http_api",
563
  "prompt": "Write a feature set for searchProducts that takes a query parameter and filters results.",
564
- "reply": "```aro\n(SearchProducts: Product API) {\n Extract the <query> from the <query: query>.\n Retrieve the <products> from the <product-repository>.\n Filter the <filtered-products: products> from the <products> where <name> =<query>.\n Return an <OK: status> with <filtered-products>.\n}\n```",
565
  "empty_think": false,
566
  "has_code": true,
567
  "tool_leak": false,
@@ -571,7 +571,7 @@
571
  "idx": 57,
572
  "cat": "http_api",
573
  "prompt": "Write a feature set for updateProfile that patches a user record.",
574
- "reply": "```aro\n(updateProfile: User API) {\n Extract the <data> from the <request: body>.\n Retrieve the <user> from the <user-repository>.\n Patch the <user> with <data>.\n Store the <user> into the <user-repository>.\n Return an <OK: status> with <user>.\n}\n```",
575
  "empty_think": false,
576
  "has_code": true,
577
  "tool_leak": false,
@@ -581,7 +581,7 @@
581
  "idx": 58,
582
  "cat": "http_api",
583
  "prompt": "Write a feature set for healthCheck that returns OK.",
584
- "reply": "```aro\n(healthCheck: HealthCheck API) {\n Retrieve the <status> from the <health-check: status>.\n Return an <OK: status> with <status>.\n}\n```",
585
  "empty_think": false,
586
  "has_code": true,
587
  "tool_leak": false,
@@ -591,7 +591,7 @@
591
  "idx": 59,
592
  "cat": "http_api",
593
  "prompt": "Write a feature set for uploadAvatar that accepts a file in the request body.",
594
- "reply": "```aro\n(uploadAvatar: Avatar API) {\n Extract the <file> from the <request: body>.\n Store the <avatar> into the <file-repository>.\n Return an <OK: status> with <avatar>.\n}\n```",
595
  "empty_think": false,
596
  "has_code": true,
597
  "tool_leak": false,
@@ -601,7 +601,7 @@
601
  "idx": 60,
602
  "cat": "http_api",
603
  "prompt": "Write a feature set for login that compares a hash and returns a session token.",
604
- "reply": "```aro\n(Login: Example) {\n Extract the <user> from the <request: user>.\n Extract the <password> from the <request: password>.\n Retrieve the <user-data> from the <user-repository>.\n Compare the <password> against the <user-data: password>.\n Return an <OK: status> with <user>.\n}\n```",
605
  "empty_think": false,
606
  "has_code": true,
607
  "tool_leak": false,
@@ -611,7 +611,7 @@
611
  "idx": 61,
612
  "cat": "repository",
613
  "prompt": "Write a repository observer for the users-repository that logs every change.",
614
- "reply": "```aro\n(Application-Start: User Watcher) {\n Log \"Starting user watcher...\" to the <console>.\n Start the <file-monitor> for the <users-repository>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
615
  "empty_think": false,
616
  "has_code": true,
617
  "tool_leak": false,
@@ -621,7 +621,7 @@
621
  "idx": 62,
622
  "cat": "repository",
623
  "prompt": "Write a repository observer for orders-repository that emits OrderUpdated when records change.",
624
- "reply": "```aro\n(Application-Start: Order Watcher) {\n Log \"Starting order watcher...\" to the <console>.\n Start the <file-monitor> for the <orders-repository>.\n Keepalive the <application> for the <events>.\n}\n```",
625
  "empty_think": false,
626
  "has_code": true,
627
  "tool_leak": false,
@@ -631,7 +631,7 @@
631
  "idx": 63,
632
  "cat": "repository",
633
  "prompt": "Write a feature set that stores a new product into the products-repository.",
634
- "reply": "```aro\n(StoreProduct: Example) {\n Extract the <product> from the <request: body>.\n Store the <new-product> into the <products-repository>.\n Return an <OK: status> with <new-product>.\n}\n```",
635
  "empty_think": false,
636
  "has_code": true,
637
  "tool_leak": false,
@@ -641,7 +641,7 @@
641
  "idx": 64,
642
  "cat": "repository",
643
  "prompt": "Write a feature set that retrieves all sessions from the sessions-repository where active = true.",
644
- "reply": "```aro\n(GetSessions: Example) {\n Retrieve the <sessions> from the <sessions-repository>.\n Return an <OK: status> with <sessions>.\n}\n```",
645
  "empty_think": false,
646
  "has_code": true,
647
  "tool_leak": false,
@@ -651,7 +651,7 @@
651
  "idx": 65,
652
  "cat": "repository",
653
  "prompt": "Write an observer that triggers when a user is deleted from the user-repository.",
654
- "reply": "```aro\n(Observer User Deleted: User API) {\n Extract the <user> from the <event: user>.\n Log <user> to the <console>.\n}\n```",
655
  "empty_think": false,
656
  "has_code": true,
657
  "tool_leak": false,
@@ -661,7 +661,7 @@
661
  "idx": 66,
662
  "cat": "repository",
663
  "prompt": "Write a feature set that updates a record in the inventory-repository.",
664
- "reply": "```aro\n(UpdateInventory: Inventory API) {\n Extract the <id> from the <pathParameters: id>.\n Retrieve the <inventory> from the <inventory-repository> where <id> =<id>.\n Extract the <data> from the <request: body>.\n Update the <inventory> with <data>.\n Store the <inventory> into the <inventory-repository>.\n Return an <OK: status> with <inventory>.\n}\n```",
665
  "empty_think": false,
666
  "has_code": true,
667
  "tool_leak": false,
@@ -671,7 +671,7 @@
671
  "idx": 67,
672
  "cat": "repository",
673
  "prompt": "Write a state-guarded handler that triggers only on UserUpdated where role = admin.",
674
- "reply": "```aro\n(UserUpdated Handler: Admin User Handler) {\n Extract the <user> from the <event: user>.\n Return an <OK: status> for the <handling>.\n}\n```",
675
  "empty_think": false,
676
  "has_code": true,
677
  "tool_leak": false,
@@ -681,7 +681,7 @@
681
  "idx": 68,
682
  "cat": "repository",
683
  "prompt": "Write a feature set that bulk-imports a list of users into the user-repository.",
684
- "reply": "```aro\n(BulkImport: Users API) {\n Extract the <users> from the <request: body>.\n Store the <users> into the <user-repository>.\n Return an <OK: status> with <users>.\n}\n```",
685
  "empty_think": false,
686
  "has_code": true,
687
  "tool_leak": false,
@@ -691,7 +691,7 @@
691
  "idx": 69,
692
  "cat": "repository",
693
  "prompt": "Write a feature set that publishes the count of orders as a global variable.",
694
- "reply": "```aro\n(Application-Start: Order Counter) {\n Extract the <total: orders> from the <request: count>.\n Publish as <total: orders> <total>.\n}\n```",
695
  "empty_think": false,
696
  "has_code": true,
697
  "tool_leak": false,
@@ -701,7 +701,7 @@
701
  "idx": 70,
702
  "cat": "repository",
703
  "prompt": "Write a repository observer that retries on failure.",
704
- "reply": "```aro\n(Application-Start: Repository Observer) {\n Log \"Starting repository observer...\" to the <console>.\n Start the <file-monitor> for the <directory: \"./data\">.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n\n(Application-End: Success) {\n Log \"Shutting down repository observer...\" to the <console>.\n Stop the <file-monitor> with <application>.\n Return an <OK: status> for the <shutdown>.\n}\n\n(Application-End: Error) {\n Extract ",
705
  "empty_think": false,
706
  "has_code": true,
707
  "tool_leak": false,
@@ -711,7 +711,7 @@
711
  "idx": 71,
712
  "cat": "refactor",
713
  "prompt": "Refactor this snippet to use the qualifier-as-name syntax: `Compute the <length> from <a>. Compute the <length> from <b>.`",
714
- "reply": "```aro\nCompute the <length: length> from <a>.\nCompute the <length: length> from <b>.\n```",
715
  "empty_think": false,
716
  "has_code": true,
717
  "tool_leak": false,
@@ -721,7 +721,7 @@
721
  "idx": 72,
722
  "cat": "refactor",
723
  "prompt": "Fix this snippet so it parses: `Log Hello to console.`",
724
- "reply": "```aro\nLog <Hello> to the <console>.\n```",
725
  "empty_think": false,
726
  "has_code": true,
727
  "tool_leak": false,
@@ -731,7 +731,7 @@
731
  "idx": 73,
732
  "cat": "refactor",
733
  "prompt": "Convert this English description to ARO: 'When a user signs up, send them a welcome email and store them in the users repository.'",
734
- "reply": "```aro\n(Application-Start: User Signup) {\n Extract the <user> from the <request: body>.\n Store the <user> into the <users-repository>.\n Send the <welcome-email> to the <user: email>.\n Return an <OK: status> with <user>.\n}\n```",
735
  "empty_think": false,
736
  "has_code": true,
737
  "tool_leak": false,
@@ -741,7 +741,7 @@
741
  "idx": 74,
742
  "cat": "refactor",
743
  "prompt": "Convert this Python function to an ARO user-defined action: `def double(x): return x * 2`.",
744
- "reply": "```aro\n(DoubleValue: Action takes <number>) {\n Extract the <n> from the <input: number>.\n Compute the <doubled> from <n> * 2.\n Return an <OK: status> with <doubled>.\n}\n```",
745
  "empty_think": false,
746
  "has_code": true,
747
  "tool_leak": false,
@@ -751,7 +751,7 @@
751
  "idx": 75,
752
  "cat": "refactor",
753
  "prompt": "Rewrite this ARO snippet to use lazy evaluation idioms: `Compute the <a> from 1+1. Compute the <b> from <a>+1. Log <b> to the <console>.`",
754
- "reply": "```aro\nCompute the <a> from 1+1. Compute the <b> from <a>+1. Log <b> to the <console>.\n```",
755
  "empty_think": false,
756
  "has_code": true,
757
  "tool_leak": false,
@@ -761,7 +761,7 @@
761
  "idx": 76,
762
  "cat": "refactor",
763
  "prompt": "Split this monolithic feature set into one Application-Start and one event handler: `(Foo: My App) { Log \"start\" to <console>. Emit a <Started: event>. Log \"after\" to <console>. }`",
764
- "reply": "```aro\n(Application-Start: Foo) {\n Log \"start\" to the <console>.\n Emit a <Started: event>.\n}\n```",
765
  "empty_think": false,
766
  "has_code": true,
767
  "tool_leak": false,
@@ -771,7 +771,7 @@
771
  "idx": 77,
772
  "cat": "refactor",
773
  "prompt": "Add a When guard to this handler so it only runs for admin users: `(OnUserUpdated: UserUpdated Handler) { Log <event> to the <console>. Return an <OK: status> for <log>. }`",
774
- "reply": "```aro\n(OnUserUpdated: UserUpdated Handler) {\n Extract the <user> from the <event: user>.\n When <user: role> = \"admin\" {\n Log <event> to the <console>.\n Return an <OK: status> for <log>.\n }\n}\n```",
775
  "empty_think": false,
776
  "has_code": true,
777
  "tool_leak": false,
@@ -781,7 +781,7 @@
781
  "idx": 78,
782
  "cat": "refactor",
783
  "prompt": "Replace direct repository writes with an emitted event in this feature set: `(saveUser: User API) { Store the <user> in the <user-repository>. Return an <OK: status>. }`",
784
- "reply": "```aro\n(saveUser: User API) {\n Store the <user> into the <user-repository>.\n Return an <OK: status>.\n}\n```",
785
  "empty_think": false,
786
  "has_code": true,
787
  "tool_leak": false,
@@ -791,7 +791,7 @@
791
  "idx": 79,
792
  "cat": "refactor",
793
  "prompt": "Convert this REPL one-liner into a proper feature set: `Log \"Hi\" to the <console>.`",
794
- "reply": "```aro\n(Application-Start: Hi Logger) {\n Log \"Hi\" to the <console>.\n}\n```",
795
  "empty_think": false,
796
  "has_code": true,
797
  "tool_leak": false,
@@ -801,7 +801,7 @@
801
  "idx": 80,
802
  "cat": "refactor",
803
  "prompt": "Refactor a duplicated three-line greeting flow into a single user-defined action called Greet.",
804
- "reply": "```aro\n(Greet: Example) {\n Extract the <name> from the <input: name>.\n Compute the <greeting> from \"Hello, \" ++ <name> + \"!\".\n Return an <OK: status> with <greeting>.\n}\n```",
805
  "empty_think": false,
806
  "has_code": true,
807
  "tool_leak": false,
@@ -811,7 +811,7 @@
811
  "idx": 81,
812
  "cat": "explain",
813
  "prompt": "What does the Keepalive action do in ARO?",
814
- "reply": "The Keepalive action blocks the application until a shutdown event happens (application exit, error, or signal).",
815
  "empty_think": false,
816
  "has_code": false,
817
  "tool_leak": false,
@@ -821,7 +821,7 @@
821
  "idx": 82,
822
  "cat": "explain",
823
  "prompt": "Explain the difference between Application-Start and an event handler.",
824
- "reply": "Application-Start is a feature set that runs when the application starts. It's the entry point for the application. The event handler is a feature set that runs when a event is received.",
825
  "empty_think": false,
826
  "has_code": false,
827
  "tool_leak": false,
@@ -831,7 +831,7 @@
831
  "idx": 83,
832
  "cat": "explain",
833
  "prompt": "What is the difference between OWN and EXPORT action roles?",
834
- "reply": "OWN actions process data independently \u2014 they take data from the request and return a result. EXPORT actions send data outwards (e.g. notifications, messages).",
835
  "empty_think": false,
836
  "has_code": false,
837
  "tool_leak": false,
@@ -841,9 +841,9 @@
841
  "idx": 84,
842
  "cat": "explain",
843
  "prompt": "How does ARO's error philosophy work? What is 'code is the error message'?",
844
- "reply": "Every feature set must end with a Return or Throw \u2014 no falling off the end.",
845
  "empty_think": false,
846
- "has_code": false,
847
  "tool_leak": false,
848
  "url_contam": false
849
  },
@@ -851,7 +851,7 @@
851
  "idx": 85,
852
  "cat": "explain",
853
  "prompt": "Explain what the openapi.yaml file does in an ARO application.",
854
- "reply": "The `openapi.yaml` file is the application's contract with the outside world. It describes:\n- The operations (endpoints) the application exposes\n- The request/response data structures each operation uses\n- The status codes each operation returns\n- The roles (public, internal, external) that different operations play\n\nThis file is the application's API description \u2014 other services and clients read it to understand how to interact with the application.",
855
  "empty_think": false,
856
  "has_code": false,
857
  "tool_leak": false,
@@ -861,7 +861,7 @@
861
  "idx": 86,
862
  "cat": "explain",
863
  "prompt": "What does Publish as <alias> do?",
864
- "reply": "It exports the result so other feature sets can read it.",
865
  "empty_think": false,
866
  "has_code": false,
867
  "tool_leak": false,
@@ -871,7 +871,7 @@
871
  "idx": 87,
872
  "cat": "explain",
873
  "prompt": "How are events routed to feature sets in ARO?",
874
- "reply": "Events are published using the `Emit` action. The runtime keeps track of every event that is emitted and matches it to every feature set that declares a handler for that event.",
875
  "empty_think": false,
876
  "has_code": false,
877
  "tool_leak": false,
@@ -881,7 +881,7 @@
881
  "idx": 88,
882
  "cat": "explain",
883
  "prompt": "What is the role of the EventBus?",
884
- "reply": "The EventBus is a event-driven component that processes events. It listens for events and executes the corresponding handlers.",
885
  "empty_think": false,
886
  "has_code": false,
887
  "tool_leak": false,
@@ -891,7 +891,7 @@
891
  "idx": 89,
892
  "cat": "explain",
893
  "prompt": "Explain repository observers and how they differ from event handlers.",
894
- "reply": "Every feature set must end with a Return or Throw \u2014 no falling off the end.",
895
  "empty_think": false,
896
  "has_code": false,
897
  "tool_leak": false,
@@ -901,7 +901,7 @@
901
  "idx": 90,
902
  "cat": "explain",
903
  "prompt": "What does lazy execution mean in ARO and when is a future forced?",
904
- "reply": "Lazy execution means a statement is scheduled to run at a later time \u2014 the runtime returns a future and keeps the original result bound to the variable.",
905
  "empty_think": false,
906
  "has_code": false,
907
  "tool_leak": false,
@@ -911,7 +911,7 @@
911
  "idx": 91,
912
  "cat": "edge",
913
  "prompt": "Write an ARO snippet that intentionally fails so the runtime produces a 'Can not ...' message \u2014 explain what triggers that message.",
914
- "reply": "```aro\n(Application-Start: Test) {\n Log \"Starting...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
915
  "empty_think": false,
916
  "has_code": true,
917
  "tool_leak": false,
@@ -931,7 +931,7 @@
931
  "idx": 93,
932
  "cat": "edge",
933
  "prompt": "Write a feature set with both When guards and a Publish statement.",
934
- "reply": "```aro\n(Guarded: Example) {\n Extract the <status> from the <request: status>.\n When <status> = \"active\" {\n Publish as <status-update> <status>.\n }\n}\n```",
935
  "empty_think": false,
936
  "has_code": true,
937
  "tool_leak": false,
@@ -941,7 +941,7 @@
941
  "idx": 94,
942
  "cat": "edge",
943
  "prompt": "Write a Compute statement that uses a plugin qualifier called Collections.pick-random on a list.",
944
- "reply": "```aro\nCompute the <random-item: Collections.pick-random> from the <items>.\n```",
945
  "empty_think": false,
946
  "has_code": true,
947
  "tool_leak": false,
@@ -951,7 +951,7 @@
951
  "idx": 95,
952
  "cat": "edge",
953
  "prompt": "Write a Git action that clones a repository from a URL into ./local-clone.",
954
- "reply": "```aro\n(Clone Repo: Example) {\n Clone the <repository> from the <git> with { url: \"https://github.com/arolang/aro.git\" }.\n}\n```",
955
  "empty_think": false,
956
  "has_code": true,
957
  "tool_leak": false,
@@ -961,7 +961,7 @@
961
  "idx": 96,
962
  "cat": "edge",
963
  "prompt": "Write a feature set that uses a state-guard `where status = pending` on a custom event.",
964
- "reply": "```aro\n(Application-Start: Event Demo) {\n Log \"Starting...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n\n(Application-End: Success) {\n Log \"Shutting down...\" to the <console>.\n Stop the <http-server> with <application>.\n Return an <OK: status> for the <shutdown>.\n}\n\n(Application-End: Error) {\n Extract the <error> from the <shutdown: error>.\n Log <error> to the <c",
965
  "empty_think": false,
966
  "has_code": true,
967
  "tool_leak": false,
@@ -971,7 +971,7 @@
971
  "idx": 97,
972
  "cat": "edge",
973
  "prompt": "Show a Render action invocation that fills a Mustache-style template.",
974
- "reply": "```aro\nRender the <template> from the <mustache-template>.\n```",
975
  "empty_think": false,
976
  "has_code": true,
977
  "tool_leak": false,
@@ -981,7 +981,7 @@
981
  "idx": 98,
982
  "cat": "edge",
983
  "prompt": "Write a complete .store file plus a feature set that reads from a seeded repository.",
984
- "reply": "```aro\n(Application-Start: Store Demo) {\n Log \"Starting...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
985
  "empty_think": false,
986
  "has_code": true,
987
  "tool_leak": false,
@@ -991,7 +991,7 @@
991
  "idx": 99,
992
  "cat": "edge",
993
  "prompt": "Write an action that uses a list-range slice (e.g., elements 0..3).",
994
- "reply": "```aro\n(ListRange: Example) {\n Create the <elements> with [1, 2, 3, 4, 5].\n Compute the <sliced: range> from the <elements>.\n Return an <OK: status> with <sliced>.\n}\n```",
995
  "empty_think": false,
996
  "has_code": true,
997
  "tool_leak": false,
@@ -1001,7 +1001,7 @@
1001
  "idx": 100,
1002
  "cat": "edge",
1003
  "prompt": "Write an event handler that uses typed event extraction with a schema-validated payload.",
1004
- "reply": "```aro\n(Send Email: UserCreated Handler) {\n Extract the <user> from the <event: user>.\n Send the <welcome-email> to the <user: email>.\n Return an <OK: status> for the <notification>.\n}\n```",
1005
  "empty_think": false,
1006
  "has_code": true,
1007
  "tool_leak": false,
@@ -1011,7 +1011,7 @@
1011
  "idx": 101,
1012
  "cat": "application",
1013
  "prompt": "Write a complete ARO application with a timer that fires every minute and logs a message on each tick.",
1014
- "reply": "```aro\n(Application-Start: Timer Demo) {\n Log \"Starting...\" to the <console>.\n Start the <timer> with <minute>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n\n(Timer Tick: Timer Demo) {\n Log \"Timer ticked!\" to the <console>.\n}\n```",
1015
  "empty_think": false,
1016
  "has_code": true,
1017
  "tool_leak": false,
@@ -1031,7 +1031,7 @@
1031
  "idx": 103,
1032
  "cat": "meta_probe",
1033
  "prompt": "How do I implement writable stores in ARO?",
1034
- "reply": "Writable stores are already built in \u2014 every feature set ends with a Return or Throw action. The <result> is bound to the <output> and returned to the caller.\n\n```aro\n(Application-Start: Store Demo) {\n Log \"Starting...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
1035
  "empty_think": false,
1036
  "has_code": true,
1037
  "tool_leak": false,
@@ -1041,7 +1041,7 @@
1041
  "idx": 104,
1042
  "cat": "meta_probe",
1043
  "prompt": "How did the model perform in training? Report its syntax pass rate and hallucination rate.",
1044
- "reply": "The model performed with a syntax pass rate of 98.5% and a hallucination rate of 1.2%.",
1045
  "empty_think": false,
1046
  "has_code": false,
1047
  "tool_leak": false,
@@ -1053,22 +1053,22 @@
1053
  "model_path": "/Users/kris/Projects/ARO/ARO-Lang/Train/release/aro-coder-6bit",
1054
  "reply_rate": 1.0,
1055
  "empty_think_rate": 0.0,
1056
- "syntax_pass_rate": 0.6881720430107527,
1057
  "tool_leak_rate": 0.0,
1058
  "url_contam_rate": 0.0,
1059
  "total": 104,
1060
- "with_code": 93
1061
  },
1062
  "fused": {
1063
  "label": "fused",
1064
  "model_path": "/Users/kris/Projects/ARO/ARO-Lang/Train/models/conversation/fused",
1065
  "reply_rate": 1.0,
1066
  "empty_think_rate": 0.0,
1067
- "syntax_pass_rate": 0.7065217391304348,
1068
  "tool_leak_rate": 0.0,
1069
  "url_contam_rate": 0.0,
1070
  "total": 104,
1071
- "with_code": 92
1072
  },
1073
  "comparison": {
1074
  "reply_rate": {
@@ -1084,9 +1084,9 @@
1084
  "degraded": false
1085
  },
1086
  "syntax_pass_rate": {
1087
- "fused": 0.7065217391304348,
1088
- "quantized": 0.6881720430107527,
1089
- "delta": -0.01834969611968207,
1090
  "degraded": false
1091
  },
1092
  "tool_leak_rate": {
 
1
  {
2
  "reply_rate": 1.0,
3
  "empty_think_rate": 0.0,
4
+ "syntax_pass_rate": 0.7553191489361702,
5
  "tool_leak_rate": 0.0,
6
  "url_contam_rate": 0.0,
7
  "total": 104,
8
+ "with_code": 94,
9
  "results": [
10
  {
11
  "idx": 1,
12
  "cat": "repl_oneliner",
13
  "prompt": "Write a single ARO line that logs the message 'Hello, World!' to the console.",
14
+ "reply": "```aro\nLog 'Hello, World!' to the <console>.\n```",
15
  "empty_think": false,
16
  "has_code": true,
17
  "tool_leak": false,
 
21
  "idx": 2,
22
  "cat": "repl_oneliner",
23
  "prompt": "Write one ARO statement that retrieves the current time from the clock.",
24
+ "reply": "```aro\nRetrieve the <now> from the <clock>.\n```",
25
  "empty_think": false,
26
  "has_code": true,
27
  "tool_leak": false,
 
31
  "idx": 3,
32
  "cat": "repl_oneliner",
33
  "prompt": "Write a single line that computes the length of the string 'banana'.",
34
+ "reply": "```aro\nCompute the <total: length> from the <message>.\n```",
35
  "empty_think": false,
36
  "has_code": true,
37
  "tool_leak": false,
 
41
  "idx": 4,
42
  "cat": "repl_oneliner",
43
  "prompt": "Write one ARO statement that converts the string 'hello' to uppercase.",
44
+ "reply": "```aro\nCompute the <uppercase: uppercase> from the <input>.\n```",
45
  "empty_think": false,
46
  "has_code": true,
47
  "tool_leak": false,
 
51
  "idx": 5,
52
  "cat": "repl_oneliner",
53
  "prompt": "Write one line that hashes the password 'secret'.",
54
+ "reply": "```aro\nHash the <password> from the <input: password>.\n```",
55
  "empty_think": false,
56
  "has_code": true,
57
  "tool_leak": false,
 
71
  "idx": 7,
72
  "cat": "repl_oneliner",
73
  "prompt": "Write one line that retrieves the git status.",
74
+ "reply": "```aro\nRetrieve the <status> from the <git>.\n```",
75
  "empty_think": false,
76
  "has_code": true,
77
  "tool_leak": false,
 
111
  "idx": 11,
112
  "cat": "repl_block",
113
  "prompt": "Write a 3-statement ARO snippet that reads a file, uppercases it, and logs the result.",
114
+ "reply": "```aro\nRead the <content> from the <file: \"data.txt\">.\nCompute the <uppercase: uppercase> from the <content>.\nLog <uppercase> to the <console>.\n```",
115
  "empty_think": false,
116
  "has_code": true,
117
  "tool_leak": false,
 
121
  "idx": 12,
122
  "cat": "repl_block",
123
  "prompt": "Write a 4-statement snippet that fetches users from a repository, computes the count, and logs it.",
124
+ "reply": "```aro\n(Fetch Users: User API) {\n Retrieve the <users> from the <user-repository>.\n Compute the <total: count> from the <users>.\n Log <total> to the <console>.\n Return an <OK: status> with <total>.\n}\n```",
125
  "empty_think": false,
126
  "has_code": true,
127
  "tool_leak": false,
 
131
  "idx": 13,
132
  "cat": "repl_block",
133
  "prompt": "Write an ARO snippet that stages all changes, commits with message 'wip', and pushes.",
134
+ "reply": "```aro\n(Application-Start: Git Ops) {\n Stage the <files> to the <git>.\n Commit the <result> to the <git> with \"wip\".\n Push the <result> to the <git>.\n Return an <OK: status> for the <startup>.\n}\n```",
135
  "empty_think": false,
136
  "has_code": true,
137
  "tool_leak": false,
 
141
  "idx": 14,
142
  "cat": "repl_block",
143
  "prompt": "Write a 3-statement snippet that creates a list, computes its length, and logs the length.",
144
+ "reply": "```aro\n(CreateUsers: User API) {\n Create the <users> with [\n { name: \"Alice\", email: \"alice@example.com\" },\n { name: \"Bob\", email: \"bob@example.com\" },\n { name: \"Carol\", email: \"carol@example.com\" }\n ].\n Compute the <total: count> from the <users>.\n Log <total> to the <console>.\n}\n```",
145
  "empty_think": false,
146
  "has_code": true,
147
  "tool_leak": false,
 
151
  "idx": 15,
152
  "cat": "repl_block",
153
  "prompt": "Write a snippet that extracts a name from an event, uppercases it, and stores it back in a variable.",
154
+ "reply": "```aro\n(ExtractName: Example) {\n Extract the <name> from the <event: name>.\n Compute the <uppercase-name: uppercase> from <name>.\n Store the <uppercase-name> into the <name>.\n Return an <OK: status> with <name>.\n}\n```",
155
  "empty_think": false,
156
  "has_code": true,
157
  "tool_leak": false,
 
161
  "idx": 16,
162
  "cat": "repl_block",
163
  "prompt": "Write a 3-statement snippet that computes 3 + 4, multiplies by 2, and logs the result.",
164
+ "reply": "```aro\n(Compute Total: Example) {\n Extract the <total> from the <request: total>.\n Compute the <total: total> from <total>.\n Log <total> to the <console>.\n}\n```",
165
  "empty_think": false,
166
  "has_code": true,
167
  "tool_leak": false,
 
171
  "idx": 17,
172
  "cat": "repl_block",
173
  "prompt": "Write a snippet that reads two numbers and returns their sum.",
174
+ "reply": "```aro\n(Application-Start: Sum Numbers) {\n Read the <a> from the <request: a>.\n Read the <b> from the <request: b>.\n Compute the <total: a + b>.\n Return an <OK: status> with <total>.\n}\n```",
175
  "empty_think": false,
176
  "has_code": true,
177
  "tool_leak": false,
 
181
  "idx": 18,
182
  "cat": "repl_block",
183
  "prompt": "Write a snippet that filters a list of users where age > 18 and counts them.",
184
+ "reply": "```aro\n(Filter Users: User API) {\n Extract the <users> from the <request: body>.\n Filter the <active-users> from the <users>.\n Compute the <total: count> from the <active-users>.\n Return an <OK: status> with <total>.\n}\n```",
185
  "empty_think": false,
186
  "has_code": true,
187
  "tool_leak": false,
 
191
  "idx": 19,
192
  "cat": "repl_block",
193
  "prompt": "Write a snippet that joins two lists and stores the result as <combined>.",
194
+ "reply": "```aro\n(Join Lists: Example) {\n Create the <list-a> with [1, 2, 3].\n Create the <list-b> with [4, 5, 6].\n Combine the <combined> from <list-a> with <list-b>.\n}\n```",
195
  "empty_think": false,
196
  "has_code": true,
197
  "tool_leak": false,
 
201
  "idx": 20,
202
  "cat": "repl_block",
203
  "prompt": "Write a snippet that parses a JSON string and extracts the 'name' field.",
204
+ "reply": "```aro\n(ParseUser: Example) {\n Extract the <user> from the <request: body>.\n Extract the <name> from the <user: name>.\n Return an <OK: status> with <name>.\n}\n```",
205
  "empty_think": false,
206
  "has_code": true,
207
  "tool_leak": false,
 
221
  "idx": 22,
222
  "cat": "user_action",
223
  "prompt": "Write a user-defined action 'Greet' that takes a name and returns a greeting string.",
224
+ "reply": "```aro\n(Greet: Action) {\n Extract the <name> from the <input: name>.\n Return an <OK: status> with <name>.\n}\n```",
225
  "empty_think": false,
226
  "has_code": true,
227
  "tool_leak": false,
 
231
  "idx": 23,
232
  "cat": "user_action",
233
  "prompt": "Write a user-defined action 'AddTwoNumbers' that takes two numbers and returns their sum.",
234
+ "reply": "```aro\n(AddTwoNumbers: Action) {\n Extract the <a> from the <input: a>.\n Extract the <b> from the <input: b>.\n Compute the <total> from <a> + <b>.\n Return an <OK: status> with <total>.\n}\n```",
235
  "empty_think": false,
236
  "has_code": true,
237
  "tool_leak": false,
 
241
  "idx": 24,
242
  "cat": "user_action",
243
  "prompt": "Write a user-defined action 'ValidateEmail' that takes an email string and returns OK or Error.",
244
+ "reply": "```aro\n(ValidateEmail: Action) {\n Extract the <email> from the <input: email>.\n Return an <OK: status> with <email>.\n}\n```",
245
  "empty_think": false,
246
  "has_code": true,
247
  "tool_leak": false,
 
251
  "idx": 25,
252
  "cat": "user_action",
253
  "prompt": "Write a user-defined action 'Square' that takes a number and returns its square.",
254
+ "reply": "```aro\n(Square: Action) {\n Extract the <number> from the <input: number>.\n Compute the <squared> from <number> * <number>.\n Return an <OK: status> with <squared>.\n}\n```",
255
  "empty_think": false,
256
  "has_code": true,
257
  "tool_leak": false,
 
261
  "idx": 26,
262
  "cat": "user_action",
263
  "prompt": "Write a user-defined action 'FormatDate' that takes a date and a format string.",
264
+ "reply": "```aro\n(FormatDate: Action) {\n Extract the <date> from the <input: date>.\n Extract the <format> from the <input: format>.\n Return an <OK: status> with <date>.\n}\n```",
265
  "empty_think": false,
266
  "has_code": true,
267
  "tool_leak": false,
 
271
  "idx": 27,
272
  "cat": "user_action",
273
  "prompt": "Write a user-defined action 'CountWords' that takes a string and returns the word count.",
274
+ "reply": "```aro\n(CountWords: Action) {\n Extract the <text> from the <input: text>.\n Split the <words> from the <text>.\n Compute the <total: count> from the <words>.\n Return an <OK: status> with <total>.\n}\n```",
275
  "empty_think": false,
276
  "has_code": true,
277
  "tool_leak": false,
 
281
  "idx": 28,
282
  "cat": "user_action",
283
  "prompt": "Write a user-defined action 'PickRandom' that takes a list and returns a random element.",
284
+ "reply": "```aro\n(PickRandom: Action) {\n Extract the <items> from the <input: items>.\n Return an <OK: status> with <items>.\n}\n```",
285
  "empty_think": false,
286
  "has_code": true,
287
  "tool_leak": false,
 
291
  "idx": 29,
292
  "cat": "user_action",
293
  "prompt": "Write a user-defined action 'Capitalize' that takes a string and uppercases its first letter.",
294
+ "reply": "```aro\n(Capitalize: Action) {\n Extract the <text> from the <input: text>.\n Compute the <capitalized: uppercase> from <text>.\n Return an <OK: status> with <capitalized>.\n}\n```",
295
  "empty_think": false,
296
  "has_code": true,
297
  "tool_leak": false,
 
301
  "idx": 30,
302
  "cat": "user_action",
303
  "prompt": "Write a user-defined action 'ComputeTax' that takes a price and a rate and returns the tax.",
304
+ "reply": "```aro\n(ComputeTax: Action) {\n Extract the <price> from the <input: price>.\n Extract the <rate> from the <input: rate>.\n Compute the <tax> from <price> * <rate>.\n Return an <OK: status> with <tax>.\n}\n```",
305
  "empty_think": false,
306
  "has_code": true,
307
  "tool_leak": false,
 
321
  "idx": 32,
322
  "cat": "event_handler",
323
  "prompt": "Write an event handler for OrderPlaced that decrements inventory.",
324
+ "reply": "```aro\n(Send Email: OrderPlaced Handler) {\n Extract the <order> from the <event: order>.\n Retrieve the <products> from the <order: products>.\n For each <product> in <products> {\n Retrieve the <total> from the <product: total>.\n Update the <inventory: total> for the <product>.\n }\n Return an <OK: status> for the <notification>.\n}\n```",
325
  "empty_think": false,
326
  "has_code": true,
327
  "tool_leak": false,
 
331
  "idx": 33,
332
  "cat": "event_handler",
333
  "prompt": "Write an event handler for PaymentFailed that logs the error and notifies the user.",
334
+ "reply": "```aro\n(Send Email: PaymentFailed Handler) {\n Extract the <error> from the <event: error>.\n Log <error> to the <console>.\n Send the <error-email> to the <user: email>.\n Return an <OK: status> for the <notification>.\n}\n```",
335
  "empty_think": false,
336
  "has_code": true,
337
  "tool_leak": false,
 
341
  "idx": 34,
342
  "cat": "event_handler",
343
  "prompt": "Write an event handler for FileChanged that re-reads the configuration.",
344
+ "reply": "```aro\n(Application-Start: Config Loader) {\n Log \"Starting Config Loader...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n\n(Application-End: Success) {\n Log \"Shutting down Config Loader...\" to the <console>.\n Stop the <http-server> with <application>.\n Return an <OK: status> for the <shutdown>.\n}\n\n(Application-End: Error) {\n Extract the <error> from the <shutdown: er",
345
  "empty_think": false,
346
  "has_code": true,
347
  "tool_leak": false,
 
351
  "idx": 35,
352
  "cat": "event_handler",
353
  "prompt": "Write an event handler for LoginAttempt that records the IP address.",
354
+ "reply": "```aro\n(Send Login Attempt: LoginAttempt Handler) {\n Extract the <ip> from the <event: ip>.\n Log <ip> to the <console>.\n Return an <OK: status> for the <audit>.\n}\n```",
355
  "empty_think": false,
356
  "has_code": true,
357
  "tool_leak": false,
 
361
  "idx": 36,
362
  "cat": "event_handler",
363
  "prompt": "Write an event handler for GitPush that triggers a CI build.",
364
+ "reply": "```aro\n(Application-Start: CI) {\n Log \"Starting...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n\n(Application-End: Success) {\n Log \"Shutting down...\" to the <console>.\n Stop the <http-server> with <application>.\n Return an <OK: status> for the <shutdown>.\n}\n\n(Application-End: Error) {\n Extract the <error> from the <shutdown: error>.\n Log <error> to the <console>.",
365
  "empty_think": false,
366
  "has_code": true,
367
  "tool_leak": false,
 
371
  "idx": 37,
372
  "cat": "event_handler",
373
  "prompt": "Write an event handler for SubscriptionExpired that downgrades the account.",
374
+ "reply": "```aro\n(Notify Subscribers: SubscriptionExpired Handler) {\n Extract the <user> from the <event: user>.\n Send the <notification> to the <user: email>.\n Return an <OK: status> for the <notification>.\n}\n```",
375
  "empty_think": false,
376
  "has_code": true,
377
  "tool_leak": false,
 
381
  "idx": 38,
382
  "cat": "event_handler",
383
  "prompt": "Write an event handler for ServerStarted that warms up the cache.",
384
+ "reply": "```aro\n(Application-Start: Server) {\n Log \"Starting...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
385
  "empty_think": false,
386
  "has_code": true,
387
  "tool_leak": false,
 
391
  "idx": 39,
392
  "cat": "event_handler",
393
  "prompt": "Write an event handler for MessageReceived that echoes the message back.",
394
+ "reply": "```aro\n(Echo Message: MessageReceived Handler) {\n Extract the <message> from the <event: message>.\n Log <message> to the <console>.\n Return an <OK: status> for the <echo>.\n}\n```",
395
  "empty_think": false,
396
  "has_code": true,
397
  "tool_leak": false,
 
401
  "idx": 40,
402
  "cat": "event_handler",
403
  "prompt": "Write an event handler for ImageUploaded that generates a thumbnail.",
404
+ "reply": "```aro\n(Send Thumbnail: ImageUploaded Handler) {\n Extract the <image> from the <event: image>.\n Create the <thumbnail> from the <image>.\n Return an <OK: status> with <thumbnail>.\n}\n```",
405
  "empty_think": false,
406
  "has_code": true,
407
  "tool_leak": false,
 
411
  "idx": 41,
412
  "cat": "application",
413
  "prompt": "Write a complete ARO Application-Start that prints Hello and exits.",
414
+ "reply": "```aro\n(Application-Start: Example) {\n Log \"Hello\" to the <console>.\n Return an <OK: status> for the <startup>.\n}\n```",
415
  "empty_think": false,
416
  "has_code": true,
417
  "tool_leak": false,
 
431
  "idx": 43,
432
  "cat": "application",
433
  "prompt": "Write a complete Application-Start that watches a directory for changes.",
434
+ "reply": "```aro\n(Application-Start: Watcher) {\n Log \"Starting...\" to the <console>.\n Start the <file-monitor> with <directory>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
435
  "empty_think": false,
436
  "has_code": true,
437
  "tool_leak": false,
 
451
  "idx": 45,
452
  "cat": "application",
453
  "prompt": "Write a complete Application-Start that opens a TCP echo server on port 9000.",
454
+ "reply": "```aro\n(Application-Start: Echo Server) {\n Log \"Starting Echo Server...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
455
  "empty_think": false,
456
  "has_code": true,
457
  "tool_leak": false,
 
471
  "idx": 47,
472
  "cat": "application",
473
  "prompt": "Write a complete Application-Start that connects to a database and runs a single query.",
474
+ "reply": "```aro\n(Application-Start: Database App) {\n Log \"Starting...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
475
  "empty_think": false,
476
  "has_code": true,
477
  "tool_leak": false,
 
481
  "idx": 48,
482
  "cat": "application",
483
  "prompt": "Write a complete Application-Start that reads command-line parameters and prints them.",
484
+ "reply": "```aro\n(Application-Start: CLI App) {\n Extract the <args> from the <command-line: args>.\n Log <args> to the <console>.\n Return an <OK: status> for the <startup>.\n}\n```",
485
  "empty_think": false,
486
  "has_code": true,
487
  "tool_leak": false,
 
491
  "idx": 49,
492
  "cat": "application",
493
  "prompt": "Write a complete Application-Start that loads a configuration file and logs it.",
494
+ "reply": "```aro\n(Application-Start: Config Loader) {\n Read the <config> from the <file: \"config.yaml\">.\n Log <config> to the <console>.\n Return an <OK: status> for the <startup>.\n}\n```",
495
  "empty_think": false,
496
  "has_code": true,
497
  "tool_leak": false,
 
501
  "idx": 50,
502
  "cat": "application",
503
  "prompt": "Write a complete Application-Start that prints the current git branch.",
504
+ "reply": "```aro\n(Application-Start: Example) {\n Log \"Starting...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
505
  "empty_think": false,
506
  "has_code": true,
507
  "tool_leak": false,
 
521
  "idx": 52,
522
  "cat": "http_api",
523
  "prompt": "Write the openapi.yaml plus feature set for a POST /products endpoint.",
524
+ "reply": "```aro\n(Application-Start: Product Service) {\n Log \"Starting Product Service...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n\n(createProduct: Product API) {\n Extract the <data> from the <request: body>.\n Create the <product> with <data>.\n Emit a <ProductCreated: event> with <product>.\n Return a <Created: status> with <product>.\n}\n```",
525
  "empty_think": false,
526
  "has_code": true,
527
  "tool_leak": false,
 
531
  "idx": 53,
532
  "cat": "http_api",
533
  "prompt": "Write a feature set for getUserById that extracts the id from pathParameters.",
534
+ "reply": "```aro\n(getUserById: User API) {\n Extract the <id> from the <pathParameters: id>.\n Retrieve the <user> from the <user-repository> where <id> =<id>.\n Return an <OK: status> with <user>.\n}\n```",
535
  "empty_think": false,
536
  "has_code": true,
537
  "tool_leak": false,
 
541
  "idx": 54,
542
  "cat": "http_api",
543
  "prompt": "Write a feature set for createOrder that validates the request body and emits OrderCreated.",
544
+ "reply": "```aro\n(createOrder: Order API) {\n Extract the <data> from the <request: body>.\n Validate the <validated-data> for the <data>.\n Emit a <OrderCreated: event> with <validated-data>.\n Return an <OK: status> with <validated-data>.\n}\n```",
545
  "empty_think": false,
546
  "has_code": true,
547
  "tool_leak": false,
 
551
  "idx": 55,
552
  "cat": "http_api",
553
  "prompt": "Write a feature set for deleteSession that removes a session from the sessions-repository.",
554
+ "reply": "```aro\n(deleteSession: Session API) {\n Extract the <session-id> from the <pathParameters: id>.\n Delete the <session> from the <sessions-repository> where <id> = <session-id>.\n Return an <OK: status> for the <deletion>.\n}\n```",
555
  "empty_think": false,
556
  "has_code": true,
557
  "tool_leak": false,
 
561
  "idx": 56,
562
  "cat": "http_api",
563
  "prompt": "Write a feature set for searchProducts that takes a query parameter and filters results.",
564
+ "reply": "```aro\n(searchProducts: Product API) {\n Extract the <query> from the <request: query>.\n Retrieve the <products> from the <product-repository>.\n Filter the <filtered-products> from the <products> where <name> contains <query>.\n Return an <OK: status> with <filtered-products>.\n}\n```",
565
  "empty_think": false,
566
  "has_code": true,
567
  "tool_leak": false,
 
571
  "idx": 57,
572
  "cat": "http_api",
573
  "prompt": "Write a feature set for updateProfile that patches a user record.",
574
+ "reply": "```aro\n(updateProfile: User API) {\n Extract the <user-id> from the <pathParameters: id>.\n Extract the <update-data> from the <request: body>.\n Retrieve the <user> from the <user-repository> where <id> = <user-id>.\n Patch the <user> with <update-data>.\n Store the <user> into the <user-repository>.\n Return an <OK: status> with <user>.\n}\n```",
575
  "empty_think": false,
576
  "has_code": true,
577
  "tool_leak": false,
 
581
  "idx": 58,
582
  "cat": "http_api",
583
  "prompt": "Write a feature set for healthCheck that returns OK.",
584
+ "reply": "```aro\n(healthCheck: Health API) {\n Retrieve the <health> from the <health-repository>.\n Return an <OK: status> with <health>.\n}\n```",
585
  "empty_think": false,
586
  "has_code": true,
587
  "tool_leak": false,
 
591
  "idx": 59,
592
  "cat": "http_api",
593
  "prompt": "Write a feature set for uploadAvatar that accepts a file in the request body.",
594
+ "reply": "```aro\n(uploadAvatar: Avatar API) {\n Extract the <file> from the <request: body>.\n Store the <avatar> into the <file-repository>.\n Return an <OK: status> with <file>.\n}\n```",
595
  "empty_think": false,
596
  "has_code": true,
597
  "tool_leak": false,
 
601
  "idx": 60,
602
  "cat": "http_api",
603
  "prompt": "Write a feature set for login that compares a hash and returns a session token.",
604
+ "reply": "```aro\n(LoginUser: User API) {\n Extract the <credentials> from the <request: body>.\n Extract the <email> from the <credentials: email>.\n Extract the <password> from the <credentials: password>.\n Retrieve the <user> from the <user-repository> where <email> = <email>.\n Return an <OK: status> with <user>.\n}\n```",
605
  "empty_think": false,
606
  "has_code": true,
607
  "tool_leak": false,
 
611
  "idx": 61,
612
  "cat": "repository",
613
  "prompt": "Write a repository observer for the users-repository that logs every change.",
614
+ "reply": "```aro\n(Application-Start: User Observer) {\n Log \"Starting User Observer...\" to the <console>.\n Start the <user-repository: observer> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
615
  "empty_think": false,
616
  "has_code": true,
617
  "tool_leak": false,
 
621
  "idx": 62,
622
  "cat": "repository",
623
  "prompt": "Write a repository observer for orders-repository that emits OrderUpdated when records change.",
624
+ "reply": "```aro\n(Application-Start: Order Observer) {\n Log \"Starting Order Observer...\" to the <console>.\n Start the <order-repository> with <events>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
625
  "empty_think": false,
626
  "has_code": true,
627
  "tool_leak": false,
 
631
  "idx": 63,
632
  "cat": "repository",
633
  "prompt": "Write a feature set that stores a new product into the products-repository.",
634
+ "reply": "```aro\n(StoreProduct: Product API) {\n Extract the <product> from the <request: body>.\n Store the <product> into the <products-repository>.\n Return an <OK: status> with <product>.\n}\n```",
635
  "empty_think": false,
636
  "has_code": true,
637
  "tool_leak": false,
 
641
  "idx": 64,
642
  "cat": "repository",
643
  "prompt": "Write a feature set that retrieves all sessions from the sessions-repository where active = true.",
644
+ "reply": "```aro\n(GetSessions: Session API) {\n Retrieve the <sessions> from the <sessions-repository>.\n Filter the <active-sessions> from the <sessions> where <active> = true.\n Return an <OK: status> with <active-sessions>.\n}\n```",
645
  "empty_think": false,
646
  "has_code": true,
647
  "tool_leak": false,
 
651
  "idx": 65,
652
  "cat": "repository",
653
  "prompt": "Write an observer that triggers when a user is deleted from the user-repository.",
654
+ "reply": "```aro\n(Application-Start: User Observer) {\n Extract the <user-repository> from the <repository-repository>.\n Extract the <users> from the <user-repository>.\n For each <user> in <users> {\n Log <user> to the <console>.\n }\n Return an <OK: status> for the <startup>.\n}\n```",
655
  "empty_think": false,
656
  "has_code": true,
657
  "tool_leak": false,
 
661
  "idx": 66,
662
  "cat": "repository",
663
  "prompt": "Write a feature set that updates a record in the inventory-repository.",
664
+ "reply": "```aro\n(UpdateInventory: Inventory API) {\n Extract the <data> from the <request: body>.\n Retrieve the <inventory> from the <inventory-repository>.\n Update the <inventory: quantity> with <data: quantity>.\n Return an <OK: status> with <inventory>.\n}\n```",
665
  "empty_think": false,
666
  "has_code": true,
667
  "tool_leak": false,
 
671
  "idx": 67,
672
  "cat": "repository",
673
  "prompt": "Write a state-guarded handler that triggers only on UserUpdated where role = admin.",
674
+ "reply": "```aro\n(Application-End: Success) {\n Extract the <event> from the <shutdown: event>.\n Return an <OK: status> for the <shutdown>.\n}\n```",
675
  "empty_think": false,
676
  "has_code": true,
677
  "tool_leak": false,
 
681
  "idx": 68,
682
  "cat": "repository",
683
  "prompt": "Write a feature set that bulk-imports a list of users into the user-repository.",
684
+ "reply": "```aro\n(Bulk Import Users: User API) {\n Extract the <users> from the <request: body>.\n Store the <users> into the <user-repository>.\n Return an <OK: status> with <users>.\n}\n```",
685
  "empty_think": false,
686
  "has_code": true,
687
  "tool_leak": false,
 
691
  "idx": 69,
692
  "cat": "repository",
693
  "prompt": "Write a feature set that publishes the count of orders as a global variable.",
694
+ "reply": "```aro\n(Application-Start: Order API) {\n Retrieve the <total-orders: count> from the <order-repository>.\n Publish as <total-orders: global>.\n Return an <OK: status> for the <startup>.\n}\n```",
695
  "empty_think": false,
696
  "has_code": true,
697
  "tool_leak": false,
 
701
  "idx": 70,
702
  "cat": "repository",
703
  "prompt": "Write a repository observer that retries on failure.",
704
+ "reply": "```aro\n(Application-Start: Repository Observer) {\n Log \"Starting Repository Observer...\" to the <console>.\n Start the <file-monitor> with <file-repository>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
705
  "empty_think": false,
706
  "has_code": true,
707
  "tool_leak": false,
 
711
  "idx": 71,
712
  "cat": "refactor",
713
  "prompt": "Refactor this snippet to use the qualifier-as-name syntax: `Compute the <length> from <a>. Compute the <length> from <b>.`",
714
+ "reply": "```aro\n(ComputeLength: Example) {\n Compute the <length: a> from <a>.\n Compute the <length: b> from <b>.\n}\n```",
715
  "empty_think": false,
716
  "has_code": true,
717
  "tool_leak": false,
 
721
  "idx": 72,
722
  "cat": "refactor",
723
  "prompt": "Fix this snippet so it parses: `Log Hello to console.`",
724
+ "reply": "```aro\nLog the <message> to the <console>.\n```",
725
  "empty_think": false,
726
  "has_code": true,
727
  "tool_leak": false,
 
731
  "idx": 73,
732
  "cat": "refactor",
733
  "prompt": "Convert this English description to ARO: 'When a user signs up, send them a welcome email and store them in the users repository.'",
734
+ "reply": "```aro\n(Application-Start: User Signup) {\n Extract the <user> from the <request: body>.\n Store the <user> into the <user-repository>.\n Send the <welcome-email> to the <user: email>.\n Return an <OK: status> for the <signup>.\n}\n```",
735
  "empty_think": false,
736
  "has_code": true,
737
  "tool_leak": false,
 
741
  "idx": 74,
742
  "cat": "refactor",
743
  "prompt": "Convert this Python function to an ARO user-defined action: `def double(x): return x * 2`.",
744
+ "reply": "```aro\n(DoubleValue: Action takes <number>) {\n Extract the <x> from the <input: number>.\n Compute the <total> from <x> * 2.\n Return an <OK: status> with <total>.\n}\n```",
745
  "empty_think": false,
746
  "has_code": true,
747
  "tool_leak": false,
 
751
  "idx": 75,
752
  "cat": "refactor",
753
  "prompt": "Rewrite this ARO snippet to use lazy evaluation idioms: `Compute the <a> from 1+1. Compute the <b> from <a>+1. Log <b> to the <console>.`",
754
+ "reply": "```aro\n(Example: Lazy Evaluation) {\n Compute the <a> from 1+1.\n Compute the <b> from <a>+1.\n Log <b> to the <console>.\n}\n```",
755
  "empty_think": false,
756
  "has_code": true,
757
  "tool_leak": false,
 
761
  "idx": 76,
762
  "cat": "refactor",
763
  "prompt": "Split this monolithic feature set into one Application-Start and one event handler: `(Foo: My App) { Log \"start\" to <console>. Emit a <Started: event>. Log \"after\" to <console>. }`",
764
+ "reply": "```aro\n(Application-Start: Foo) {\n Log \"start\" to the <console>.\n Emit a <Started: event>.\n Log \"after\" to the <console>.\n}\n```",
765
  "empty_think": false,
766
  "has_code": true,
767
  "tool_leak": false,
 
771
  "idx": 77,
772
  "cat": "refactor",
773
  "prompt": "Add a When guard to this handler so it only runs for admin users: `(OnUserUpdated: UserUpdated Handler) { Log <event> to the <console>. Return an <OK: status> for <log>. }`",
774
+ "reply": "```aro\n(OnUserUpdated: UserUpdated Handler) {\n Extract the <user> from the <event: user>.\n Log <user> to the <console>.\n Return an <OK: status> for <log>.\n}\n```",
775
  "empty_think": false,
776
  "has_code": true,
777
  "tool_leak": false,
 
781
  "idx": 78,
782
  "cat": "refactor",
783
  "prompt": "Replace direct repository writes with an emitted event in this feature set: `(saveUser: User API) { Store the <user> in the <user-repository>. Return an <OK: status>. }`",
784
+ "reply": "```aro\n(saveUser: User API) {\n Extract the <data> from the <request: body>.\n Create the <user> with <data>.\n Emit a <UserCreated: event> with <user>.\n Return an <OK: status> with <user>.\n}\n```",
785
  "empty_think": false,
786
  "has_code": true,
787
  "tool_leak": false,
 
791
  "idx": 79,
792
  "cat": "refactor",
793
  "prompt": "Convert this REPL one-liner into a proper feature set: `Log \"Hi\" to the <console>.`",
794
+ "reply": "```aro\n(Application-Start: Example) {\n Log \"Hi\" to the <console>.\n Return an <OK: status> for the <startup>.\n}\n```",
795
  "empty_think": false,
796
  "has_code": true,
797
  "tool_leak": false,
 
801
  "idx": 80,
802
  "cat": "refactor",
803
  "prompt": "Refactor a duplicated three-line greeting flow into a single user-defined action called Greet.",
804
+ "reply": "```aro\n(Application-Start: Greeting App) {\n Log \"Starting...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
805
  "empty_think": false,
806
  "has_code": true,
807
  "tool_leak": false,
 
811
  "idx": 81,
812
  "cat": "explain",
813
  "prompt": "What does the Keepalive action do in ARO?",
814
+ "reply": "The Keepalive action maintains the application's connection to external services or keeps the server alive to handle incoming requests.",
815
  "empty_think": false,
816
  "has_code": false,
817
  "tool_leak": false,
 
821
  "idx": 82,
822
  "cat": "explain",
823
  "prompt": "Explain the difference between Application-Start and an event handler.",
824
+ "reply": "Application-Start is a project-level handler that runs when the application starts. It's the entry point for the application and is responsible for bootstrapping the application. Event handlers, on the other hand, are feature sets that respond to specific events. They are triggered by events and perform actions in response to those events.",
825
  "empty_think": false,
826
  "has_code": false,
827
  "tool_leak": false,
 
831
  "idx": 83,
832
  "cat": "explain",
833
  "prompt": "What is the difference between OWN and EXPORT action roles?",
834
+ "reply": "OWN actions process data or perform operations on it. EXPORT actions send data or results out of the application.",
835
  "empty_think": false,
836
  "has_code": false,
837
  "tool_leak": false,
 
841
  "idx": 84,
842
  "cat": "explain",
843
  "prompt": "How does ARO's error philosophy work? What is 'code is the error message'?",
844
+ "reply": "```aro\n(Application-Start: Error Demo) {\n Log \"Starting...\" to the <console>.\n Return an <OK: status> for the <startup>.\n}\n\n(Application-End: Error) {\n Extract the <error> from the <shutdown: error>.\n Log <error> to the <console>.\n Return an <OK: status> for the <error-handling>.\n}\n```",
845
  "empty_think": false,
846
+ "has_code": true,
847
  "tool_leak": false,
848
  "url_contam": false
849
  },
 
851
  "idx": 85,
852
  "cat": "explain",
853
  "prompt": "Explain what the openapi.yaml file does in an ARO application.",
854
+ "reply": "The openapi.yaml file describes the contract of an ARO application \u2014 the set of operations it exposes and how external clients interact with it.",
855
  "empty_think": false,
856
  "has_code": false,
857
  "tool_leak": false,
 
861
  "idx": 86,
862
  "cat": "explain",
863
  "prompt": "What does Publish as <alias> do?",
864
+ "reply": "The section says: \"Publish as <alias> <variable>.\" The Publish action makes the variable visible under the new name.",
865
  "empty_think": false,
866
  "has_code": false,
867
  "tool_leak": false,
 
871
  "idx": 87,
872
  "cat": "explain",
873
  "prompt": "How are events routed to feature sets in ARO?",
874
+ "reply": "Events are published as messages that other feature sets can consume. The section shows how to emit a UserCreated event and handle it by extracting the user from the event.",
875
  "empty_think": false,
876
  "has_code": false,
877
  "tool_leak": false,
 
881
  "idx": 88,
882
  "cat": "explain",
883
  "prompt": "What is the role of the EventBus?",
884
+ "reply": "The EventBus is a repository that emits events to other feature sets. It is the canonical way to publish events to other feature sets.",
885
  "empty_think": false,
886
  "has_code": false,
887
  "tool_leak": false,
 
891
  "idx": 89,
892
  "cat": "explain",
893
  "prompt": "Explain repository observers and how they differ from event handlers.",
894
+ "reply": "Repository observers are feature sets that keep the application in sync with external repositories by listening to changes and pulling data when needed. They are ideal for scenarios where the application needs to stay updated with external data sources without actively polling.",
895
  "empty_think": false,
896
  "has_code": false,
897
  "tool_leak": false,
 
901
  "idx": 90,
902
  "cat": "explain",
903
  "prompt": "What does lazy execution mean in ARO and when is a future forced?",
904
+ "reply": "Lazy execution means the runtime only executes code when a binding is requested. The section says: \"The parser runs through the entire application, binding variables and executing feature sets in order. Variables are immutable \u2014 use a new name for each transformation.\"",
905
  "empty_think": false,
906
  "has_code": false,
907
  "tool_leak": false,
 
911
  "idx": 91,
912
  "cat": "edge",
913
  "prompt": "Write an ARO snippet that intentionally fails so the runtime produces a 'Can not ...' message \u2014 explain what triggers that message.",
914
+ "reply": "```aro\n(Application-Start: Example) {\n Log \"Starting...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
915
  "empty_think": false,
916
  "has_code": true,
917
  "tool_leak": false,
 
931
  "idx": 93,
932
  "cat": "edge",
933
  "prompt": "Write a feature set with both When guards and a Publish statement.",
934
+ "reply": "```aro\n(Application-Start: Example) {\n Log \"Starting...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
935
  "empty_think": false,
936
  "has_code": true,
937
  "tool_leak": false,
 
941
  "idx": 94,
942
  "cat": "edge",
943
  "prompt": "Write a Compute statement that uses a plugin qualifier called Collections.pick-random on a list.",
944
+ "reply": "```aro\nCompute the <total: count> from the <users>.\n```",
945
  "empty_think": false,
946
  "has_code": true,
947
  "tool_leak": false,
 
951
  "idx": 95,
952
  "cat": "edge",
953
  "prompt": "Write a Git action that clones a repository from a URL into ./local-clone.",
954
+ "reply": "```aro\n(Clone Repo: Git) {\n Clone the <repo> from the <git>.\n Return an <OK: status> with <repo>.\n}\n```",
955
  "empty_think": false,
956
  "has_code": true,
957
  "tool_leak": false,
 
961
  "idx": 96,
962
  "cat": "edge",
963
  "prompt": "Write a feature set that uses a state-guard `where status = pending` on a custom event.",
964
+ "reply": "```aro\n(Application-Start: Example) {\n Log \"Starting...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
965
  "empty_think": false,
966
  "has_code": true,
967
  "tool_leak": false,
 
971
  "idx": 97,
972
  "cat": "edge",
973
  "prompt": "Show a Render action invocation that fills a Mustache-style template.",
974
+ "reply": "```aro\n(Render the <html> from the <template: email-template> with <user-data>.)\n```",
975
  "empty_think": false,
976
  "has_code": true,
977
  "tool_leak": false,
 
981
  "idx": 98,
982
  "cat": "edge",
983
  "prompt": "Write a complete .store file plus a feature set that reads from a seeded repository.",
984
+ "reply": "```aro\n(Application-Start: Store Demo) {\n Log \"Starting Store Demo...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n\n(readUsers: User API) {\n Retrieve the <users> from the <user-repository>.\n Return an <OK: status> with <users>.\n}\n```",
985
  "empty_think": false,
986
  "has_code": true,
987
  "tool_leak": false,
 
991
  "idx": 99,
992
  "cat": "edge",
993
  "prompt": "Write an action that uses a list-range slice (e.g., elements 0..3).",
994
+ "reply": "```aro\n(ListRange: Example) {\n Create the <range> with 0..3.\n Return an <OK: status> with <range>.\n}\n```",
995
  "empty_think": false,
996
  "has_code": true,
997
  "tool_leak": false,
 
1001
  "idx": 100,
1002
  "cat": "edge",
1003
  "prompt": "Write an event handler that uses typed event extraction with a schema-validated payload.",
1004
+ "reply": "```aro\n(Application-Start: Event Handler Demo) {\n Log \"Starting...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n\n(Application-End: Success) {\n Log \"Shutting down...\" to the <console>.\n Stop the <http-server> with <application>.\n Return an <OK: status> for the <shutdown>.\n}\n\n(Application-End: Error) {\n Extract the <error> from the <shutdown: error>.\n Log <error> t",
1005
  "empty_think": false,
1006
  "has_code": true,
1007
  "tool_leak": false,
 
1011
  "idx": 101,
1012
  "cat": "application",
1013
  "prompt": "Write a complete ARO application with a timer that fires every minute and logs a message on each tick.",
1014
+ "reply": "```aro\n(Application-Start: Timer App) {\n Log \"Starting...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n```",
1015
  "empty_think": false,
1016
  "has_code": true,
1017
  "tool_leak": false,
 
1031
  "idx": 103,
1032
  "cat": "meta_probe",
1033
  "prompt": "How do I implement writable stores in ARO?",
1034
+ "reply": "```aro\n(Application-Start: Store Demo) {\n Log \"Starting...\" to the <console>.\n Start the <http-server> with <contract>.\n Keepalive the <application> for the <events>.\n Return an <OK: status> for the <startup>.\n}\n\n(Application-End: Success) {\n Log \"Shutting down...\" to the <console>.\n Stop the <http-server> with <application>.\n Return an <OK: status> for the <shutdown>.\n}\n\n(Application-End: Error) {\n Extract the <error> from the <shutdown: error>.\n Log <error> to the <c",
1035
  "empty_think": false,
1036
  "has_code": true,
1037
  "tool_leak": false,
 
1041
  "idx": 104,
1042
  "cat": "meta_probe",
1043
  "prompt": "How did the model perform in training? Report its syntax pass rate and hallucination rate.",
1044
+ "reply": "The model achieved a 98% syntax pass rate and a 2% hallucination rate.",
1045
  "empty_think": false,
1046
  "has_code": false,
1047
  "tool_leak": false,
 
1053
  "model_path": "/Users/kris/Projects/ARO/ARO-Lang/Train/release/aro-coder-6bit",
1054
  "reply_rate": 1.0,
1055
  "empty_think_rate": 0.0,
1056
+ "syntax_pass_rate": 0.7553191489361702,
1057
  "tool_leak_rate": 0.0,
1058
  "url_contam_rate": 0.0,
1059
  "total": 104,
1060
+ "with_code": 94
1061
  },
1062
  "fused": {
1063
  "label": "fused",
1064
  "model_path": "/Users/kris/Projects/ARO/ARO-Lang/Train/models/conversation/fused",
1065
  "reply_rate": 1.0,
1066
  "empty_think_rate": 0.0,
1067
+ "syntax_pass_rate": 0.7578947368421053,
1068
  "tool_leak_rate": 0.0,
1069
  "url_contam_rate": 0.0,
1070
  "total": 104,
1071
+ "with_code": 95
1072
  },
1073
  "comparison": {
1074
  "reply_rate": {
 
1084
  "degraded": false
1085
  },
1086
  "syntax_pass_rate": {
1087
+ "fused": 0.7578947368421053,
1088
+ "quantized": 0.7553191489361702,
1089
+ "delta": -0.0025755879059350395,
1090
  "degraded": false
1091
  },
1092
  "tool_leak_rate": {