Issue Station
Sign In
Tools hereToolbox

openclaw - ✅(Solved) Fix [Bug]: Full Mode fails when Tool Profile is set to "Full" (Ollama + GLM/Qwen) [1 pull requests, 1 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#56297•Fetched 2026-04-08 01:42:38
View on GitHub
Comments
0
Participants
1
Timeline
6
Reactions
0
Author
xiyubudaifengxiyubudaifeng
Participants
xiyubudaifengxiyubudaifeng
Timeline (top)
referenced ×3labeled ×2cross-referenced ×1

Full Mode fails with "LLM request failed: network connection error." when using Ollama hosted GLM-4.7-flash/Qwen-3.5 models on remote Ubuntu server, while Messaging Mode works normally.

Error Message

Full Mode fails with "LLM request failed: network connection error." when using Ollama hosted GLM-4.7-flash/Qwen-3.5 models on remote Ubuntu server, while Messaging Mode works normally. 3. Observe the "LLM request failed" error and "400" by "/api/chat" from ollama output respon in 80ms. Error log: 08:54:57+00:00 warn agent/embedded {"subsystem":"agent/embedded"} {"event":"embedded_run_agent_end","tags":["error_handling","lifecycle","agent_end","assistant_error"],"runId":"c92461e8-2270-4953-a9cb-35843eabf2fe","isError":true,"error":"LLM request failed: network connection error.","failoverReason":"timeout","model":"glm-4.7-flash","provider":"ollama","rawErrorPreview":"fetch failed","rawErrorHash":"sha256:e2c73a8fd237"} embedded run agent end

Root Cause

Full Mode fails with "LLM request failed: network connection error." when using Ollama hosted GLM-4.7-flash/Qwen-3.5 models on remote Ubuntu server, while Messaging Mode works normally.

PR fix notes

PR #56332: delete

Description (problem / solution / changelog)

delete

Changed files

  • 2026-03-28.md (added, +384/-0)
  • AGENTS.md (modified, +21/-0)
  • src/agents/command/session.ts (modified, +11/-0)
  • src/config/sessions/store-validation.test.ts (added, +151/-0)
  • src/config/sessions/store-validation.ts (added, +81/-0)
  • src/config/sessions/store.ts (modified, +15/-1)

Code Example

Error log:

08:54:57+00:00 warn agent/embedded {"subsystem":"agent/embedded"} {"event":"embedded_run_agent_end","tags":["error_handling","lifecycle","agent_end","assistant_error"],"runId":"c92461e8-2270-4953-a9cb-35843eabf2fe","isError":true,"error":"LLM request failed: network connection error.","failoverReason":"timeout","model":"glm-4.7-flash","provider":"ollama","rawErrorPreview":"fetch failed","rawErrorHash":"sha256:e2c73a8fd237"} embedded run agent end

My config file:
{
  "meta": {
    "lastTouchedVersion": "2026.3.24",
    "lastTouchedAt": "2026-03-28T08:54:14.511Z"
  },
  "wizard": {
    "lastRunAt": "2026-03-28T08:11:39.317Z",
    "lastRunVersion": "2026.3.24",
    "lastRunCommand": "onboard",
    "lastRunMode": "local"
  },
  "auth": {
    "profiles": {
      "ollama:default": {
        "provider": "ollama",
        "mode": "api_key"
      }
    }
  },
  "models": {
    "mode": "merge",
    "providers": {
      "ollama": {
        "baseUrl": "http://192.168.65.219:11434",
        "apiKey": "OLLAMA_API_KEY",
        "api": "ollama",
        "models": [
          {
            "id": "glm-4.7-flash",
            "name": "glm-4.7-flash",
            "reasoning": false,
            "input": [
              "text"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 128000,
            "maxTokens": 8192
          },
          {
            "id": "qwen:32b",
            "name": "qwen:32b",
            "reasoning": false,
            "input": [
              "text"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 32768,
            "maxTokens": 8192
          },
          {
            "id": "qwen3.5:latest",
            "name": "qwen3.5:latest",
            "reasoning": false,
            "input": [
              "text"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 262144,
            "maxTokens": 8192
          },
          {
            "id": "glm-4.7-flash:latest",
            "name": "glm-4.7-flash:latest",
            "reasoning": false,
            "input": [
              "text"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 202752,
            "maxTokens": 8192
          },
          {
            "id": "qwen3-80b:latest",
            "name": "qwen3-80b:latest",
            "reasoning": false,
            "input": [
              "text"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 262144,
            "maxTokens": 8192
          }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "ollama/glm-4.7-flash"
      },
      "models": {
        "ollama/glm-4.7-flash": {}
      },
      "workspace": "/Users/***/.openclaw/workspace"
    }
  },
  "tools": {
    "profile": "full"
  },
  "commands": {
    "native": "auto",
    "nativeSkills": "auto",
    "restart": true,
    "ownerDisplay": "raw"
  },
  "session": {
    "dmScope": "per-channel-peer"
  },
  "gateway": {
    "port": 18789,
    "mode": "local",
    "bind": "loopback",
    "auth": {
      "mode": "token",
      "token": "***"
    },
    "tailscale": {
      "mode": "off",
      "resetOnExit": false
    },
    "nodes": {
      "denyCommands": [
        "camera.snap",
        "camera.clip",
        "screen.record",
        "contacts.add",
        "calendar.add",
        "reminders.add",
        "sms.send"
      ]
    }
  }
}
RAW_BUFFERClick to expand / collapse

Bug type

Regression (worked before, now fails)

Beta release blocker

No

Summary

Full Mode fails with "LLM request failed: network connection error." when using Ollama hosted GLM-4.7-flash/Qwen-3.5 models on remote Ubuntu server, while Messaging Mode works normally.

Steps to reproduce

  1. Set the Tool Profile to Full.
  2. Send a chat message.
  3. Observe the "LLM request failed" error and "400" by "/api/chat" from ollama output respon in 80ms.
  4. Switching the Tool Profile back to Messaging .
  5. Send a chat message.
  6. Reply after a while.
  7. Observe the output sucessfully and "200" by "/api/chat" from ollama output respon in 35s.

Expected behavior

NOT_ENOUGH_INFO

Actual behavior

NOT_ENOUGH_INFO

OpenClaw version

OpenClaw 2026.3.24

Operating system

macOS26.4

Install method

npm

Model

glm-4.7-flash/qwen:32b

Provider / routing chain

openclaw (Mac Mini M4) -> Ollama (Ubuntu Server, internal network)

Additional provider/model setup details

Success when Tool Profile is set to "Messaging" <img width="2422" height="1240" alt="Image" src="https://github.com/user-attachments/assets/871e5bf7-9fff-44ca-ae47-6895de7e3e9e" />

This is what happen when Tool Profile is set to "Full" <img width="2433" height="1247" alt="Image" src="https://github.com/user-attachments/assets/071b2045-4656-49f1-8638-8fd6cfc10634" />

Logs, screenshots, and evidence

Error log:

08:54:57+00:00 warn agent/embedded {"subsystem":"agent/embedded"} {"event":"embedded_run_agent_end","tags":["error_handling","lifecycle","agent_end","assistant_error"],"runId":"c92461e8-2270-4953-a9cb-35843eabf2fe","isError":true,"error":"LLM request failed: network connection error.","failoverReason":"timeout","model":"glm-4.7-flash","provider":"ollama","rawErrorPreview":"fetch failed","rawErrorHash":"sha256:e2c73a8fd237"} embedded run agent end

My config file:
{
  "meta": {
    "lastTouchedVersion": "2026.3.24",
    "lastTouchedAt": "2026-03-28T08:54:14.511Z"
  },
  "wizard": {
    "lastRunAt": "2026-03-28T08:11:39.317Z",
    "lastRunVersion": "2026.3.24",
    "lastRunCommand": "onboard",
    "lastRunMode": "local"
  },
  "auth": {
    "profiles": {
      "ollama:default": {
        "provider": "ollama",
        "mode": "api_key"
      }
    }
  },
  "models": {
    "mode": "merge",
    "providers": {
      "ollama": {
        "baseUrl": "http://192.168.65.219:11434",
        "apiKey": "OLLAMA_API_KEY",
        "api": "ollama",
        "models": [
          {
            "id": "glm-4.7-flash",
            "name": "glm-4.7-flash",
            "reasoning": false,
            "input": [
              "text"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 128000,
            "maxTokens": 8192
          },
          {
            "id": "qwen:32b",
            "name": "qwen:32b",
            "reasoning": false,
            "input": [
              "text"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 32768,
            "maxTokens": 8192
          },
          {
            "id": "qwen3.5:latest",
            "name": "qwen3.5:latest",
            "reasoning": false,
            "input": [
              "text"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 262144,
            "maxTokens": 8192
          },
          {
            "id": "glm-4.7-flash:latest",
            "name": "glm-4.7-flash:latest",
            "reasoning": false,
            "input": [
              "text"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 202752,
            "maxTokens": 8192
          },
          {
            "id": "qwen3-80b:latest",
            "name": "qwen3-80b:latest",
            "reasoning": false,
            "input": [
              "text"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 262144,
            "maxTokens": 8192
          }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "ollama/glm-4.7-flash"
      },
      "models": {
        "ollama/glm-4.7-flash": {}
      },
      "workspace": "/Users/***/.openclaw/workspace"
    }
  },
  "tools": {
    "profile": "full"
  },
  "commands": {
    "native": "auto",
    "nativeSkills": "auto",
    "restart": true,
    "ownerDisplay": "raw"
  },
  "session": {
    "dmScope": "per-channel-peer"
  },
  "gateway": {
    "port": 18789,
    "mode": "local",
    "bind": "loopback",
    "auth": {
      "mode": "token",
      "token": "***"
    },
    "tailscale": {
      "mode": "off",
      "resetOnExit": false
    },
    "nodes": {
      "denyCommands": [
        "camera.snap",
        "camera.clip",
        "screen.record",
        "contacts.add",
        "calendar.add",
        "reminders.add",
        "sms.send"
      ]
    }
  }
}

Impact and severity

No response

Additional information

No response

extent analysis

Fix Plan

The fix involves updating the baseUrl in the config file to use https instead of http and ensuring the Ollama server is configured to handle HTTPS requests.

  • Update the baseUrl in the config file:
"baseUrl": "https://192.168.65.219:11434",
  • Ensure the Ollama server is configured to handle HTTPS requests. This may involve generating a self-signed certificate or obtaining a trusted certificate from a certificate authority.

Verification

To verify the fix, repeat the steps to reproduce the issue:

  1. Set the Tool Profile to Full.
  2. Send a chat message.
  3. Observe the response from the Ollama server.

If the issue is resolved, the response should be successful, and the error message "LLM request failed: network connection error" should not appear.

Extra Tips

  • Ensure the Ollama server is configured to handle HTTPS requests and that the certificate is trusted by the client.
  • If using a self-signed certificate, ensure it is properly configured and trusted by the client.
  • Consider implementing additional error handling and logging to help diagnose any future issues.

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…

FAQ

Expected behavior

NOT_ENOUGH_INFO

#api#SSR setup#ISR setup#authentication setup#request error

Still need to ship something?

×6

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

Back to top recommendations

TRENDING