maestro-flow 0.3.30 → 0.3.31
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.
|
@@ -137,9 +137,9 @@ Display step banner:
|
|
|
137
137
|
{next.type == "decision" ? "Retry: " + JSON.parse(next.args).retry_count + "/" + JSON.parse(next.args).max_retries : ""}
|
|
138
138
|
```
|
|
139
139
|
|
|
140
|
-
**Context weight hint** (after 4+ completed steps):
|
|
140
|
+
**Context weight hint** (after 4+ completed steps, skip if auto):
|
|
141
141
|
```
|
|
142
|
-
If completed_count >= 4:
|
|
142
|
+
If completed_count >= 4 && !auto:
|
|
143
143
|
Display: ⚡ 已执行 {completed_count} 步，上下文较重。可 /maestro-ralph continue 在新上下文恢复。
|
|
144
144
|
```
|
|
145
145
|
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: maestro-ralph-execute
|
|
3
3
|
description: Single-step skill executor — spawned by maestro-ralph via CSV, reads ralph session context, executes one skill command, reports result
|
|
4
|
-
argument-hint: "<skill_call>"
|
|
4
|
+
argument-hint: "[-y] <skill_call>"
|
|
5
5
|
allowed-tools: Read, Write, Edit, Bash, Glob, Grep
|
|
6
6
|
---
|
|
7
7
|
|
|
@@ -62,6 +62,10 @@ Read-only for this agent. Provides:
|
|
|
62
62
|
## Step 1: Parse skill_call
|
|
63
63
|
|
|
64
64
|
```
|
|
65
|
+
Parse $ARGUMENTS:
|
|
66
|
+
Contains "-y" or "--yes" → auto = true, remove flag from remaining args
|
|
67
|
+
Remaining → skill_call
|
|
68
|
+
|
|
65
69
|
Extract from skill_call:
|
|
66
70
|
skill_name = text between $ and first space (e.g. "maestro-plan")
|
|
67
71
|
skill_args = remainder after first space (e.g. "1")
|
|
@@ -71,6 +75,8 @@ If skill_call is empty or malformed:
|
|
|
71
75
|
→ End.
|
|
72
76
|
```
|
|
73
77
|
|
|
78
|
+
Also read `session.auto` from ralph status.json — if `true`, treat as `-y` even if flag not passed.
|
|
79
|
+
|
|
74
80
|
## Step 2: Load ralph session context
|
|
75
81
|
|
|
76
82
|
```
|
|
@@ -134,6 +140,24 @@ maestro-verify, maestro-milestone-audit, maestro-milestone-complete:
|
|
|
134
140
|
|
|
135
141
|
## Step 4: Execute skill
|
|
136
142
|
|
|
143
|
+
**`-y` auto flag 传播：** 当 `auto == true` 时，按传播表附加 flag：
|
|
144
|
+
```
|
|
145
|
+
auto_flag_map = {
|
|
146
|
+
"maestro-init": "-y",
|
|
147
|
+
"maestro-analyze": "-y",
|
|
148
|
+
"maestro-brainstorm": "-y",
|
|
149
|
+
"maestro-roadmap": "-y",
|
|
150
|
+
"maestro-plan": "-y",
|
|
151
|
+
"maestro-execute": "-y",
|
|
152
|
+
"quality-business-test": "-y",
|
|
153
|
+
"quality-test": "-y --auto-fix",
|
|
154
|
+
"quality-retrospective": "-y",
|
|
155
|
+
"maestro-milestone-complete": "-y"
|
|
156
|
+
}
|
|
157
|
+
flag = auto_flag_map[skill_name] || ""
|
|
158
|
+
skill_args = flag ? `${skill_args} ${flag}` : skill_args
|
|
159
|
+
```
|
|
160
|
+
|
|
137
161
|
```
|
|
138
162
|
Read .codex/skills/{skill_name}/SKILL.md to understand the skill
|
|
139
163
|
Execute the skill with enriched skill_args as $ARGUMENTS
|