@claude-pw/framework 0.5.2 → 0.6.0

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/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@claude-pw/framework",
3
- "version": "0.5.2",
3
+ "version": "0.6.0",
4
4
  "description": "Structured Project Workflow for Claude Code — adaptive pipeline, context management, quality gates",
5
5
  "bin": {
6
6
  "claude-pw": "./install.js"
@@ -4,7 +4,7 @@ description: "Load context and execute the next pipeline stage"
4
4
 
5
5
  ## Arguments
6
6
  - No arguments: normal flow (respects `autoAdvance` from config)
7
- - `--phase`: auto-advance all steps in the current phase, pause at UAT. Overrides `autoAdvance` to `auto` for this invocation only. Does NOT cross to next phase.
7
+ - `--phase`: plan the entire phase first, then auto-advance all steps to UAT. Shows execution plan for approval before starting. Overrides `autoAdvance` to `auto` for this invocation only. Does NOT cross to next phase.
8
8
 
9
9
  ## 0. Health check (session start)
10
10
 
@@ -230,6 +230,50 @@ Pipeline for Step [X.Y]:
230
230
  - CLOSE: ok
231
231
  ```
232
232
 
233
+ ### 1.7 Phase planning (only with --phase flag)
234
+
235
+ This step runs ONLY when `--phase` flag is active AND this is the first step of the phase (or first invocation with --phase).
236
+
237
+ Read the complete sub-plan. For each pending step (Status: [ ]):
238
+
239
+ 1. Read the step's input, output, and done criterion
240
+ 2. Evaluate which pipeline stages apply (same logic as the adaptive pipeline above)
241
+ 3. Note dependencies (Requires field)
242
+
243
+ Present the execution plan:
244
+ ```
245
+ Phase N: [phase name] — Execution Plan
246
+
247
+ Steps remaining: X of Y
248
+
249
+ Step N.1: [name]
250
+ Pipeline: [stages that will run]
251
+ Skipping: [stages skipped + reason]
252
+ Input: [from sub-plan]
253
+ Output: [from sub-plan]
254
+
255
+ Step N.2: [name]
256
+ Requires: N.1
257
+ Pipeline: [stages that will run]
258
+ Skipping: [stages skipped + reason]
259
+ Input: [from sub-plan]
260
+ Output: [from sub-plan]
261
+
262
+ ...
263
+
264
+ After all steps: phase validation → UAT (interactive).
265
+ Estimated context resets: [N / based on step count, suggest /clear every 3 steps]
266
+ ```
267
+
268
+ Ask: "Execute this plan? (yes / adjust / cancel)"
269
+ - **yes**: proceed with auto-advance (normal --phase behavior)
270
+ - **adjust**: ask what to change (skip a step, reorder, modify pipeline). Update sub-plan if needed, re-present.
271
+ - **cancel**: exit --phase mode, continue as normal /cpw-next-step (step by step)
272
+
273
+ After approval, continue to pipeline execution.
274
+
275
+ ---
276
+
233
277
  Then execute the current stage (check docs/tooling.md for tools mapped to this stage):
234
278
  - **SPIKE:** Define question + timebox. Delegate to the spike-explorer agent:
235
279
  <files_to_read>