@atlashub/smartstack-cli 4.46.0 → 4.47.0
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
|
@@ -149,6 +149,8 @@ When the user invokes `/business-analyse-develop`, they are giving you the instr
|
|
|
149
149
|
- Ask the user to choose between supervised/autonomous mode
|
|
150
150
|
- Wait for user input between modules
|
|
151
151
|
- Delegate the loop to sub-agents (except team mode and /apex delegation)
|
|
152
|
+
- Display a progress report then ask "shall I continue?" or present options (1/2/3)
|
|
153
|
+
- Pause because the scope is "large" or "ambitious" — execute ALL of it regardless of size
|
|
152
154
|
|
|
153
155
|
**The ONLY valid stop conditions are:**
|
|
154
156
|
- ALL objectives met / ALL tasks completed (→ report)
|
|
@@ -58,6 +58,8 @@ Ralph-loop is FULLY AUTONOMOUS by default. It executes ALL tasks from start to f
|
|
|
58
58
|
|
|
59
59
|
**DO NOT** ask the user to confirm, choose a mode, or approve execution.
|
|
60
60
|
**DO NOT** set max_iterations = 1 or any reduced value.
|
|
61
|
+
**DO NOT** display a progress report and then ask "shall I continue?" or present numbered options.
|
|
62
|
+
**DO NOT** pause because the scope seems large — 500+ files across 11 modules is NORMAL. Execute ALL of it.
|
|
61
63
|
|
|
62
64
|
The loop runs autonomously until:
|
|
63
65
|
- ALL tasks are completed (success)
|
|
@@ -7,6 +7,12 @@ next_step: steps/step-02-v4-verify.md
|
|
|
7
7
|
|
|
8
8
|
# Step 01-v4: Continuous Module Execution
|
|
9
9
|
|
|
10
|
+
## EXECUTION GUARANTEE — AUTONOMY RULES (MANDATORY)
|
|
11
|
+
|
|
12
|
+
> **NEVER stop between modules.** NEVER ask "shall I continue?". NEVER present options (1/2/3).
|
|
13
|
+
> **NEVER pause after a progress report.** Progress reports are LOG OUTPUT ONLY — print them and IMMEDIATELY continue to the next module.
|
|
14
|
+
> **The user invoked /business-analyse-develop to execute ALL modules to completion.** That is your mandate. Any stop that is not: all-complete, dead-end, or Ctrl+C is a **VIOLATION**.
|
|
15
|
+
|
|
10
16
|
## YOUR TASK
|
|
11
17
|
|
|
12
18
|
For each module in topological order, delegate the ENTIRE module implementation to `/apex -d` in a continuous session. Run quality gates at natural checkpoints. Let server-side compaction manage context.
|
|
@@ -102,12 +108,14 @@ grep -rn "Assert.True(true)\|Assert.Pass()\|// TODO\|throw new NotImplementedExc
|
|
|
102
108
|
|
|
103
109
|
If found → delegate fix to apex: "Replace stub tests with real implementations"
|
|
104
110
|
|
|
105
|
-
### 7. Module Complete
|
|
111
|
+
### 7. Module Complete — CONTINUE IMMEDIATELY
|
|
106
112
|
|
|
107
113
|
When ALL gates pass for a module:
|
|
108
114
|
1. Log checkpoint: `"Module {moduleCode}: ALL GATES PASS"`
|
|
109
115
|
2. Optionally append to progress.txt (human checkpoint)
|
|
110
|
-
3.
|
|
116
|
+
3. **IMMEDIATELY** advance to next module in queue — DO NOT pause, DO NOT ask user, DO NOT present options
|
|
117
|
+
|
|
118
|
+
> **ANTI-STOP GUARD:** After logging the progress report, your VERY NEXT action MUST be starting the next module delegation (`/apex -d`). If there are no more modules, go to step-02-v4-verify. Outputting a progress report and then waiting for user input is a **VIOLATION** of the execution guarantee.
|
|
111
119
|
|
|
112
120
|
---
|
|
113
121
|
|