specrails-core 4.11.1 → 4.11.2

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.
Files changed (2) hide show
  1. package/package.json +1 -1
  2. package/templates/commands/specrails/batch-implement.md +3 -2
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "specrails-core",
3
- "version": "4.11.1",
3
+ "version": "4.11.2",
4
4
  "description": "AI agent workflow system for Claude Code — installs 12 specialized agents, orchestration commands, and persona-driven product discovery into any repository",
5
5
  "type": "module",
6
6
  "bin": {
package/templates/commands/specrails/batch-implement.md CHANGED
@@ -12,7 +12,7 @@ Macro-orchestrator above `/specrails:implement`. Accepts a set of feature refere
12
12
  - **`--wave-size N`**: max features per wave regardless of concurrency (default: unlimited)
13
13
  - **`--dry-run` / `--preview`**: passed through to each `/specrails:implement` invocation; no git or backlog operations will run
14
14
 
15
- **IMPORTANT:** Before running, ensure Read/Write/Bash/Glob/Grep permissions are set to "allow" — background agents cannot request permissions interactively.
15
+ **IMPORTANT:** Before running, ensure Read/Write/Bash/Glob/Grep permissions are set to "allow" — subagents cannot request permissions interactively.
16
16
 
17
17
  ---
18
18
 
@@ -198,7 +198,8 @@ For each wave `W`:
198
198
  SPECRAILS_PROFILE_PATH=<resolved-per-rail-path> /specrails:implement <ref> [--dry-run]
199
199
  ```
200
200
  - Each ref in the batch spawns with its own resolved profile path — **distinct rails in the same batch MAY use distinct profiles concurrently**.
201
- - Run invocations in the batch in parallel (`run_in_background: true`).
201
+ - Run invocations in the batch **concurrently in the FOREGROUND**: emit every agent invocation for the batch in a single message with `run_in_background: false`. They still run in parallel, and your turn blocks until all of them return.
202
+ - **NEVER use `run_in_background: true`, and NEVER end your reply while a wave is still running.** In headless/pipeline execution (`claude -p`, specrails-desktop loops) the host tears the process down as soon as your turn ends — background agents are killed before they write a single file. Replies like "wave 1 is running in the background, I'll pick it up when it finishes" lose the entire wave.
202
203
  - Wait for all in the batch to complete before starting the next batch.
203
204
  3. For each completed invocation, record outcome in `WAVE_RESULTS`:
204
205
  - `{ref, wave, status: "done" | "failed", profile: "<name or empty>", error_summary: "..." | null}`