openclaw - 💡(How to fix) Fix Feature: config flag to disable shouldFailClosedInterpreterPreflight (complex interpreter invocation check) [2 comments, 3 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
openclaw/openclaw#60476Fetched 2026-04-08 02:50:37
View on GitHub
Comments
2
Participants
3
Timeline
3
Reactions
0
Timeline (top)
commented ×2subscribed ×1

Error Message

with error: exec preflight: complex interpreter invocation detected

Fix Action

Workaround

Added explicit 'never use cd/&&' instructions to 49+ cron payloads to prevent LLMs from generating chained commands.

Code Example

cd /path && node script.js
source ~/.zshrc && node script.js  
node script.js 2>&1 | tail -30
RAW_BUFFERClick to expand / collapse

Problem

The shouldFailClosedInterpreterPreflight() check in the exec subsystem is hardcoded with no config gate. It blocks commands like:

cd /path && node script.js
source ~/.zshrc && node script.js  
node script.js 2>&1 | tail -30

with error: exec preflight: complex interpreter invocation detected

Current behavior

  • strictInlineEval: false only controls inline eval (-c/-e flags), NOT the complex invocation check
  • tools.exec.security: full + tools.exec.ask: off does not bypass it
  • The check runs unconditionally in pi-embedded-*.js

Impact

Isolated cron sessions running LLM agents (e.g., Codex gpt-5.1/5.4) sometimes generate cd && node commands even when instructions specify absolute paths. This causes silent cron failures with no way to configure around it.

Requested fix

Add a config flag like tools.exec.skipInterpreterPreflight: true or tools.exec.allowChainedCommands: true that gates the shouldFailClosedInterpreterPreflight check, similar to how strictInlineEval gates inline eval detection.

Workaround

Added explicit 'never use cd/&&' instructions to 49+ cron payloads to prevent LLMs from generating chained commands.

Version

OpenClaw 2026.4.2 (d74a122)

extent analysis

TL;DR

Add a configuration flag to gate the shouldFailClosedInterpreterPreflight check, allowing chained commands like cd && node script.js to execute without errors.

Guidance

  • Identify the specific use cases where the shouldFailClosedInterpreterPreflight check is blocking necessary commands, such as cron sessions running LLM agents.
  • Consider adding a configuration flag like tools.exec.skipInterpreterPreflight or tools.exec.allowChainedCommands to gate this check, similar to strictInlineEval.
  • Verify that the proposed flag does not introduce security vulnerabilities by reviewing the code and testing it thoroughly.
  • In the meantime, apply the existing workaround of adding explicit instructions to avoid generating chained commands in cron payloads.

Example

No code snippet is provided as it is not clearly supported by the issue, but an example of the proposed configuration flag could be:

// proposed config flag
tools: {
  exec: {
    skipInterpreterPreflight: true
  }
}

Notes

The proposed solution assumes that adding a configuration flag to gate the shouldFailClosedInterpreterPreflight check is feasible and does not introduce security risks. Further review and testing are necessary to confirm this.

Recommendation

Apply the workaround of adding explicit instructions to avoid generating chained commands in cron payloads until a configuration flag is implemented to gate the shouldFailClosedInterpreterPreflight check.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

openclaw - 💡(How to fix) Fix Feature: config flag to disable shouldFailClosedInterpreterPreflight (complex interpreter invocation check) [2 comments, 3 participants]