pi-gauntlet 5.6.1 → 5.6.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -1,5 +1,9 @@
1
1
  # Changelog
2
2
 
3
+ ## v5.6.2 - 2026-09-17
4
+
5
+ - `brainstorming`: the lookup rule distinguishes current-state facts (looked up) from decisions about what should happen (asked, even when a ticket recorded one earlier); the `Recommendation:` suffix binds questionary questions only, not the skill's git-state, design-round, or spec-gate approvals; the premise note may be questionary question one. Follow-ups from the #32 post-ship assessment. (#32)
6
+
3
7
  ## v5.6.1 - 2026-09-17
4
8
 
5
9
  - `brainstorming`: the questionary looks up questions the code, docs, or issue tracker already answer instead of asking; every question it does ask ends with `Recommendation: <answer> - <why>` (including the ask to accept a corrected fact); before approaches, a plain-prose premise note in chat names which design-dependent claims the sources support, disprove (with the corrected fact and where), or leave unverified - a contradicted claim stops the flow until the user accepts the correction or explicitly overrides, with the outcome recorded in the draft. One checklist pointer, one Red Flags entry. (#32)
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "pi-gauntlet",
3
- "version": "5.6.1",
3
+ "version": "5.6.2",
4
4
  "description": "Opinionated, gated workflow skills, subagent personas, and runtime extensions for the pi coding agent.",
5
5
  "author": "Jacek Juraszek",
6
6
  "type": "module",
@@ -145,10 +145,12 @@ path.
145
145
  - Ask questions **one at a time** to refine the idea. Prefer multiple-choice; one
146
146
  question per message. Focus on: purpose, constraints, success criteria, who/what
147
147
  it touches. Before asking, check whether the code, the docs, or the issue tracker
148
- already answer it - if so, look it up instead of asking (dispatch a subagent when
149
- the lookup is costly), and ask only what no source can answer. Every question you
150
- ask, including asking the user to accept a corrected fact, ends with the line
151
- `Recommendation: <answer> - <why>` - the answer, then " - ", then the reason.
148
+ already answer it: a fact about the current state is looked up, not asked (dispatch
149
+ a subagent when the lookup is costly); a decision about what should happen is asked,
150
+ even when a ticket recorded one earlier. Every questionary question, including the
151
+ ask to accept a corrected fact, ends with the line `Recommendation: <answer> - <why>`
152
+ (the answer, then " - ", then the reason); approvals elsewhere in this skill (git
153
+ state, design rounds, the spec gate) keep their own wording.
152
154
  - **Append bar:** append to the draft's `## Appended during questionary` only
153
155
  findings the spec will cite — schema shapes, hard constraints, ticket-vs-code
154
156
  contradictions, user answers that changed scope. Not a log of every grep.
@@ -160,13 +162,14 @@ on, which of those claims the sources support and where you saw it (a file and l
160
162
  a doc, a ticket), which they disprove - give the corrected fact and where you found
161
163
  it - and which remain unverified, naming the lookup you tried. Write it as a note a
162
164
  person can act on: full sentences, no status-keyword lists, no template; when the
163
- design depends on no claims at all, one sentence saying so is enough. An unverified claim is not a stop - it enters the
164
- spec as an Open Question or a stated assumption. If a claim the design depends on was
165
- contradicted, the note is your next message and it ends by asking the user to accept
166
- the corrected fact or explicitly override it; nothing else continues - no other
167
- questions, no approaches - until they answer, and the outcome is recorded in the draft's
168
- `## Appended during questionary` so spec-writing carries it into `## Problem` or the relevant `## Design`
169
- decision.
165
+ design depends on no claims at all, one sentence saying so is enough. An unverified
166
+ claim is not a stop - it enters the spec as an Open Question or a stated assumption.
167
+ If a claim the design depends on was contradicted, the note is your next message -
168
+ even as questionary question one - and it ends by asking the user to accept the
169
+ corrected fact or explicitly override it; nothing else continues - no other questions,
170
+ no approaches - until they answer, and the outcome is recorded in the draft's
171
+ `## Appended during questionary` so spec-writing carries it into `## Problem` or the
172
+ relevant `## Design` decision.
170
173
 
171
174
  ### 4. Explore approaches
172
175