@rse/ase 0.9.60 → 0.9.61

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json CHANGED
@@ -6,7 +6,7 @@
6
6
  "homepage": "https://ase.tools",
7
7
  "repository": { "url": "git+https://github.com/rse/ase.git", "type": "git" },
8
8
  "bugs": { "url": "https://github.com/rse/ase/issues" },
9
- "version": "0.9.60",
9
+ "version": "0.9.61",
10
10
  "license": "Apache-2.0",
11
11
  "author": {
12
12
  "name": "Dr. Ralf S. Engelschall",
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "ase",
3
- "version": "0.9.60",
3
+ "version": "0.9.61",
4
4
  "description": "Agentic Software Engineering (ASE)",
5
5
  "keywords": [ "agentic", "software", "engineering" ],
6
6
  "homepage": "https://ase.tools",
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "ase",
3
- "version": "0.9.60",
3
+ "version": "0.9.61",
4
4
  "description": "Agentic Software Engineering (ASE)",
5
5
  "keywords": [ "agentic", "software", "engineering" ],
6
6
  "homepage": "https://ase.tools",
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "ase",
3
- "version": "0.9.60",
3
+ "version": "0.9.61",
4
4
  "description": "Agentic Software Engineering (ASE)",
5
5
  "keywords": [ "agentic", "software", "engineering" ],
6
6
  "homepage": "https://ase.tools",
@@ -6,7 +6,7 @@
6
6
  "homepage": "https://ase.tools",
7
7
  "repository": { "url": "git+https://github.com/rse/ase.git", "type": "git" },
8
8
  "bugs": { "url": "https://github.com/rse/ase/issues" },
9
- "version": "0.9.60",
9
+ "version": "0.9.61",
10
10
  "license": "Apache-2.0",
11
11
  "author": {
12
12
  "name": "Dr. Ralf S. Engelschall",
@@ -50,12 +50,13 @@ which shows the established <todo-what/> and <todo-how/>, where a still
50
50
  empty <todo-what/> or <todo-how/> renders as `(none)`:
51
51
 
52
52
  <template>
53
- <ase-tpl-boxed title="EDIT TODO" subtitle="<arg1/>">
53
+ <ase-tpl-head title="EDIT TODO" subtitle="<arg1/>"/>
54
54
 
55
55
  **WHAT**: <todo-what/>
56
+
56
57
  **HOW**: <todo-how/>
57
58
 
58
- </ase-tpl-boxed>
59
+ <ase-tpl-foot title="EDIT TODO" subtitle="<arg1/>"/>
59
60
  </template>
60
61
 
61
62
  </define>
@@ -229,9 +230,10 @@ empty <todo-what/> or <todo-how/> renders as `(none)`:
229
230
  `GRILLING` otherwise (a single round needs no round
230
231
  numbering). Do not output anything.
231
232
 
232
- 2. Determine the questions <question-N/>, chosen to
233
- resolve the open points related to the above understanding
234
- of grilling, by focusing on the mentioned *Focus Areas*.
233
+ 2. Determine the very brief but precise questions <question-N/>,
234
+ chosen to resolve the open points related to the above
235
+ understanding of grilling, by focusing on the mentioned
236
+ *Focus Areas*.
235
237
 
236
238
  For each <question-N/> determine its <focus-area-N/> and a
237
239
  <topic-N/>, a 1-2 word hint describing what the question is
@@ -250,6 +252,10 @@ empty <todo-what/> or <todo-how/> renders as `(none)`:
250
252
  options, configuration keys, and literal values -- with
251
253
  backticks.
252
254
 
255
+ Keep every <question-N/> at most *200 characters* long, as a
256
+ longer question overflows its table cell and silently
257
+ degrades the entire table into a plain text rendering.
258
+
253
259
  3. Finally, *sort* the questions by descending
254
260
  focus area order -- first all `DOMAIN`, then all
255
261
  `INTERFACE`, then all `ARCHITECTURE`, and then all
@@ -259,14 +265,21 @@ empty <todo-what/> or <todo-how/> renders as `(none)`:
259
265
  anything.
260
266
 
261
267
  4. For all remaining <question-N/>, check the code base
262
- and your world knowledge to find *two to four*
268
+ and your world knowledge to find *two to three*
263
269
  grounded answer alternatives <answer-N-K/> with a
264
- brief label <answer-N-K-label/> and a description
265
- <answer-N-K-description/> which reflects the current
266
- <todo-what/>/<todo-how/> understanding by prefixing its
270
+ 1-3 word label <answer-N-K-label/> and an ultra brief description
271
+ <answer-N-K-description/> of at most *10 words*. For the answer
272
+ which reflects the current
273
+ <todo-what/>/<todo-how/> understanding prefixing its
267
274
  description with `✻ **CURRENT** ✻`. Assemble a <answer-N/>
268
- out of `**<answer-N-1-label/>**: <answer-N-1-description/> ─◇─
269
- **<answer-N-2-label/>**: <answer-N-2-description/> ─◇─ [...]`.
275
+ out of `**A1**: **<answer-N-1-label/>**: <answer-N-1-description/> ─◇─
276
+ **A2**: **<answer-N-2-label/>**: <answer-N-2-description/> ─◇─ [...]`.
277
+
278
+ Keep every assembled <answer-N/> at most *240 characters*
279
+ long -- drop the least relevant alternative and compact the
280
+ descriptions until it fits -- as a longer answer overflows
281
+ its table cell and silently degrades the entire table into a
282
+ plain text rendering.
270
283
 
271
284
  5. In the following, you *MUST* *NOT* use your built-in
272
285
  <user-dialog-tool/> tool! Instead, you *MUST* just show a
@@ -294,16 +307,23 @@ empty <todo-what/> or <todo-how/> renders as `(none)`:
294
307
  aspect, so the subsequent dialog only has to ask for the
295
308
  combined answer. Align all column edges of the table. If
296
309
  <getopt-option-grill-rounds/> is equal `1`, *omit* the
297
- leading `<round-id/>` line:
310
+ leading `<round-id/>` line.
311
+
312
+ In every table cell you *MUST* escape each literal pipe
313
+ character outside a code span as `\|` and you *MUST*
314
+ open *and* close every backtick code span within the
315
+ *same* cell -- an unescaped pipe or an unbalanced
316
+ backtick run splits the cell and silently degrades the
317
+ entire table into a plain text rendering:
298
318
 
299
319
  <template>
300
320
  ⧉ **ASE**: <round-id/>:
301
321
 
302
- | ASPECT | FOCUS AREA | TOPIC | **QUESTION** ┈─▶ **ANSWERS** |
303
- | -------- | --------------- | ----------- | --------------------------------- |
304
- | 1/<n/> | <focus-area-1/> | <topic-1/> | **<question-1/>** ┈─▶ <answer-1/> |
305
- | 2/<n/> | <focus-area-2/> | <topic-2/> | **<question-2/>** ┈─▶ <answer-2/> |
306
- | [...] | [...] | [...] | [...] |
322
+ | # | FOCUS TOPIC | **QUESTION** | **ANSWERS** |
323
+ | :----: | ----------------------------- | ----------------- | ----------- |
324
+ | **Q1** | <focus-area-1/> <topic-1/> | **<question-1/>** | <answer-1/> |
325
+ | **Q2** | <focus-area-2/> <topic-2/> | **<question-2/>** | <answer-2/> |
326
+ | [..] | [...] | [...] | [...] |
307
327
  </template>
308
328
 
309
329
  2. Show a custom dialog. Its only answer options are the
@@ -55,7 +55,7 @@ implementation until it passes). The *querying* state and every
55
55
  All questions of a round are announced together below a
56
56
  `GRILLING ROUND K/L` line (the announcement line and round numbering
57
57
  are omitted when only a single round is performed) as an
58
- `ASPECT`/`FOCUS AREA`/`TOPIC`/`QUESTION` table with one row per
58
+ `#`/`FOCUS TOPIC`/`QUESTION` table with one row per
59
59
  question, each row carrying two to four grounded answer alternatives
60
60
  (with the alternative reflecting the current understanding marked as
61
61
  `CURRENT`). They are then asked in *one* batch via a single