@tekyzinc/gsd-t 2.10.3 → 2.11.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -2,6 +2,14 @@
2
2
 
3
3
  All notable changes to GSD-T are documented here. Updated with each release.
4
4
 
5
+ ## [2.11.0] - 2026-02-12
6
+
7
+ ### Added
8
+ - Autonomy-level-aware auto-advancing for all phase commands — at Level 3 (Full Auto), partition, plan, impact, execute, test-sync, integrate, verify, and complete-milestone auto-advance without waiting for user input
9
+ - Wave error recovery auto-remediates at Level 3 (up to 2 fix attempts before stopping)
10
+ - Discuss phase always pauses for user input regardless of autonomy level
11
+ - Autonomy levels documentation added to GSD-T-README Configuration section
12
+
5
13
  ## [2.10.3] - 2026-02-11
6
14
 
7
15
  ### Changed
@@ -123,6 +123,11 @@ When all tasks in all domains are complete:
123
123
  1. Update `.gsd-t/progress.md` — all tasks marked complete
124
124
  2. Set status to `EXECUTED`
125
125
  3. List any contract deviations or decisions made during execution
126
- 4. Recommend: proceed to integrate phase
126
+
127
+ ### Autonomy Behavior
128
+
129
+ **Level 3 (Full Auto)**: Log a brief status line (e.g., "✅ Execute complete — {N}/{N} tasks done") and auto-advance to the next phase. Do NOT wait for user input.
130
+
131
+ **Level 1–2**: Report completion summary and recommend proceeding to integrate phase. Wait for confirmation.
127
132
 
128
133
  $ARGUMENTS
@@ -211,9 +211,10 @@ Validate the test landscape before recommending proceed/block:
211
211
  ### If PROCEED WITH CAUTION:
212
212
  "⚠️ Impact analysis found {N} items requiring attention:"
213
213
  - List the yellow items
214
- - "These can be addressed during execution. Proceed?"
215
- - If user confirms, continue
216
- - If user declines, pause for remediation
214
+
215
+ **Level 3 (Full Auto)**: Log the caution items and auto-advance to execute. Do NOT wait for user input.
216
+
217
+ **Level 1–2**: "These can be addressed during execution. Proceed?" Wait for user confirmation. If user declines, pause for remediation.
217
218
 
218
219
  ### If BLOCK:
219
220
  "🛑 Impact analysis found breaking changes that must be addressed first:"
@@ -129,8 +129,13 @@ Update `.gsd-t/progress.md`:
129
129
  - Add contract audit results
130
130
  - Add smoke test results
131
131
  - List any new tasks created for gaps
132
- - Recommend: proceed to verify phase
133
132
 
134
133
  Commit: `[integration] Wire domains together — all contracts verified`
135
134
 
135
+ ### Autonomy Behavior
136
+
137
+ **Level 3 (Full Auto)**: Log a brief status line (e.g., "✅ Integrate complete — all domain boundaries wired, {N} contracts verified") and auto-advance to the next phase. Do NOT wait for user input.
138
+
139
+ **Level 1–2**: Report integration results and recommend proceeding to verify phase. Wait for confirmation.
140
+
136
141
  $ARGUMENTS
@@ -184,6 +184,10 @@ Before finishing, verify:
184
184
  - [ ] Every contract has an owner and at least one consumer
185
185
  - [ ] Integration checkpoints are identified for all cross-domain dependencies
186
186
 
187
- Report the partition to the user with a summary of domains, contracts, and any decisions that need input.
187
+ ### Autonomy Behavior
188
+
189
+ **Level 3 (Full Auto)**: Log a brief status line (e.g., "✅ Partition complete — {N} domains defined, {N} contracts written") and auto-advance to the next phase. Do NOT wait for user input.
190
+
191
+ **Level 1–2**: Report the partition to the user with a summary of domains, contracts, and any decisions that need input. Wait for confirmation before proceeding.
188
192
 
189
193
  $ARGUMENTS
@@ -127,7 +127,11 @@ Update `.gsd-t/progress.md`:
127
127
 
128
128
  ## Step 6: Report
129
129
 
130
- Present to the user:
130
+ ### Autonomy Behavior
131
+
132
+ **Level 3 (Full Auto)**: Log a brief status line (e.g., "✅ Plan complete — {N} tasks across {N} domains, {execution mode}") and auto-advance to the next phase. Do NOT wait for user input.
133
+
134
+ **Level 1–2**: Present to the user:
131
135
  1. Task count per domain
132
136
  2. Dependency graph (which domains block which)
133
137
  3. Recommended execution mode:
@@ -136,4 +140,6 @@ Present to the user:
136
140
  - **Team parallel**: 15+ tasks with 3+ independent starting points
137
141
  4. Any ambiguities found during planning that need user input
138
142
 
143
+ Wait for confirmation before proceeding.
144
+
139
145
  $ARGUMENTS
@@ -296,4 +296,10 @@ Action Required:
296
296
  Generated 5 test tasks → added to current domain
297
297
  ```
298
298
 
299
+ ### Autonomy Behavior
300
+
301
+ **Level 3 (Full Auto)**: Log the summary and auto-advance to the next phase. If there are failing tests, attempt auto-fix (up to 2 attempts) before continuing. Do NOT wait for user input.
302
+
303
+ **Level 1–2**: Present the full report and wait for user input before proceeding.
304
+
299
305
  $ARGUMENTS
@@ -137,7 +137,14 @@ Update `.gsd-t/progress.md`:
137
137
  - If FAIL: Set status to `VERIFY-FAILED`, list required remediations
138
138
  - Record verification date and summary
139
139
 
140
- Recommend next step:
140
+ ### Autonomy Behavior
141
+
142
+ **Level 3 (Full Auto)**:
143
+ - VERIFIED → Log "✅ Verify complete — all quality gates passed" and auto-advance to complete-milestone. Do NOT wait for user input.
144
+ - CONDITIONAL PASS → Log warnings, treat as VERIFIED, and auto-advance. Do NOT wait for user input.
145
+ - FAIL → Auto-execute remediation tasks (up to 2 fix attempts). If still failing after 2 attempts, STOP and report to user.
146
+
147
+ **Level 1–2**:
141
148
  - VERIFIED → Milestone complete, proceed to next milestone or ship
142
149
  - CONDITIONAL PASS → User decides if warnings are acceptable
143
150
  - FAIL → Return to execute phase for remediation tasks
@@ -91,8 +91,16 @@ Work through each phase that hasn't been completed:
91
91
  Between each phase:
92
92
  1. Update `.gsd-t/progress.md`
93
93
  2. Report brief status to user
94
- 3. If any phase produces findings that need user input, STOP and ask
95
- 4. If all clear, continue to next phase
94
+
95
+ ### Autonomy Behavior
96
+
97
+ **Level 3 (Full Auto)**: Auto-advance to the next phase after logging status. Only STOP for:
98
+ - Destructive Action Guard violations (always)
99
+ - Impact analysis BLOCK verdict (always)
100
+ - Unrecoverable errors after 2 fix attempts
101
+ - The Discuss phase (always pauses for user input, even at Level 3)
102
+
103
+ **Level 1–2**: If any phase produces findings that need user input, STOP and ask. If all clear, continue to next phase.
96
104
 
97
105
  Status messages:
98
106
  ```
@@ -147,25 +155,28 @@ If the user interrupts or the session needs to end:
147
155
  - Report blocking issues
148
156
  - Generate remediation tasks
149
157
  - Add to appropriate domain
150
- - Ask: "Address blockers now, or pause?"
151
- - If address: execute remediation tasks, re-run impact
152
- - If pause: save state, exit
158
+
159
+ **Level 3 (Full Auto)**: Auto-execute remediation tasks, then re-run impact analysis. Only STOP if remediation fails after 2 attempts.
160
+
161
+ **Level 1–2**: Ask: "Address blockers now, or pause?" If address: execute remediation tasks, re-run impact. If pause: save state, exit.
153
162
 
154
163
  ### If tests fail during execute:
155
164
  - Pause execution
156
165
  - Report failing tests
157
166
  - Generate fix tasks
158
- - Ask: "Fix now or continue?"
159
- - If fix: execute fix tasks, re-run tests
160
- - If continue: note failures, proceed (will catch in verify)
167
+
168
+ **Level 3 (Full Auto)**: Auto-execute fix tasks and re-run tests (up to 2 fix attempts). If still failing, STOP and report to user.
169
+
170
+ **Level 1–2**: Ask: "Fix now or continue?" If fix: execute fix tasks, re-run tests. If continue: note failures, proceed (will catch in verify).
161
171
 
162
172
  ### If verify fails:
163
173
  - Report failures
164
174
  - Generate remediation tasks
165
175
  - Do NOT run complete-milestone
166
- - Ask: "Address issues now?"
167
- - If yes: execute remediation, re-run verify
168
- - If no: save state with VERIFY_FAILED status
176
+
177
+ **Level 3 (Full Auto)**: Auto-execute remediation tasks and re-run verify (up to 2 attempts). If still failing, STOP and report to user.
178
+
179
+ **Level 1–2**: Ask: "Address issues now?" If yes: execute remediation, re-run verify. If no: save state with VERIFY_FAILED status.
169
180
 
170
181
  ## Workflow Visualization
171
182
 
@@ -250,6 +250,16 @@ Verify with: `/user:gsd-t-help`
250
250
 
251
251
  GSD-T respects your project's `CLAUDE.md` for conventions and autonomy level.
252
252
 
253
+ ### Autonomy Levels
254
+
255
+ | Level | Phase Behavior |
256
+ |-------|---------------|
257
+ | **Level 1: Supervised** | Pauses at each phase for confirmation |
258
+ | **Level 2: Standard** | Pauses at milestones |
259
+ | **Level 3: Full Auto** (default) | Auto-advances through all phases. Only stops for: Destructive Action Guard, impact BLOCK verdicts, unrecoverable errors (after 2 fix attempts), and the Discuss phase |
260
+
261
+ Set in your project's `CLAUDE.md` under `## Autonomy Level`.
262
+
253
263
  Recommended `.gsd-t/config.json`:
254
264
 
255
265
  ```json
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@tekyzinc/gsd-t",
3
- "version": "2.10.3",
3
+ "version": "2.11.0",
4
4
  "description": "GSD-T: Contract-Driven Development for Claude Code — 35 slash commands with backlog management, impact analysis, test sync, and milestone archival",
5
5
  "author": "Tekyz, Inc.",
6
6
  "license": "MIT",