Skip to content

[Bug]: Cron Job Output Not Saved in OpenClaw 2026.3.24 #56078

Description

@nobbywfc

Bug type

Regression (worked before, now fails)

Beta release blocker

No

Summary

Cron Job runs in OpenClaw 2026.3.24 do not save output files because no delivery channel is detected, even though the job executes successfully.

Steps to reproduce

1.Use OpenClaw 2026.3
2.Go to CONTROL → Cron Jobs
3.Create a new job
4.In the Prompt, specify a save path such as:
/home/nobby/stock/

5.Run the job manually
6.Check /home/nobby/stock/
7.Observe that no file is created
8.Check Web UI logs and see:
Channel is required (no configured channels detected)

Expected behavior

In OpenClaw 3.24, running a Cron Job with a prompt specifying a file path (e.g., “save the report to /home/nobby/stock as YYYY-MM-DD-tech-report.md”) successfully saved the generated report to that directory. The same behavior is expected in 2026.3.24

Actual behavior

In OpenClaw 2026.3.24, running the Cron Job (both manual “Run” and scheduled execution) produces no output file in /home/nobby/stock or anywhere under /home/nobby, even though the run is marked as successful. The Web UI log shows: “Channel is required (no configured channels detected).”

OpenClaw version

v2026.3.24

Operating system

ubuntu24.04 under WSL2

Install method

curl -fsSL https://openclaw.ai/install.sh | bash OpenClaw was initially installed via the official curl installer (3.22), and all subsequent updates were applied through the WebUI’s built‑in update mechanism.

Model

qwen3.5-4b of LLM in LMstudio

Provider / routing chain

full Local usage

Additional provider/model setup details

A single custom local provider is defined in providers.json, pointing to a local OpenAI‑compatible endpoint at http://192.168.11.29:1234/v1 (model: qwen3.5‑4b). The main agent uses this provider as its primary model with no per‑agent overrides, no cloud providers, no proxies, and no routing layers. All inference is fully local.

Logs, screenshots, and evidence

Channel is required (no configured channels detected).
Set delivery.channel explicitly or use a main session with a previous channel.

Impact and severity

No response

Additional information

No response

Metadata

Metadata

Assignees

No one assigned

    Labels

    P1High-priority user-facing bug, regression, or broken workflow.bugSomething isn't workingclawsweeper:linked-pr-openClawSweeper found an open linked pull request for this issue.clawsweeper:no-new-fix-prClawSweeper does not recommend queueing a new automated fix PR for this issue.clawsweeper:source-reproClawSweeper found a high-confidence source-level issue reproduction.impact:data-lossCan lose, corrupt, or silently drop user/session/config data.impact:message-lossChannel message delivery can be lost, duplicated, or misrouted.issue-rating: 🦞 diamond lobsterVery strong issue quality with high-confidence source-level or clear reproduction.regressionBehavior that previously worked and now fails

    Type

    No type

    Fields

    Priority

    None yet

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions