Issue Station
Sign In
Tools hereToolbox

openclaw - 💡(How to fix) Fix [Bug]: LLM request failed: provider rejected the request schema or tool payload with xiaomi-coding/mimo-v2.5

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…

xiaomi-coding/mimo-v2.5 and mimo-v2.5-pro consistently fail with "LLM request failed: provider rejected the request schema or tool payload. rawError=400 Param Incorrect" on most messages.

Error Message

4.Observe error in logs and no reply from agent The model should process normal prompts and return a response instead of rejecting the request with schema/tool payload error. Agent fails with error LLM request failed: provider rejected the request schema or tool payload. rawError=400 Param Incorrect on most interactions. [agent/embedded] embedded run agent end: ... error=LLM request failed: provider rejected the request schema or tool payload. rawError=400 Param Incorrect Same error pattern seen in issues #68735 and #68957. Temporarily switching to other models may be needed as workaround.

Root Cause

xiaomi-coding/mimo-v2.5 and mimo-v2.5-pro consistently fail with "LLM request failed: provider rejected the request schema or tool payload. rawError=400 Param Incorrect" on most messages.

Fix Action

Fix / Workaround

Same error pattern seen in issues #68735 and #68957. Temporarily switching to other models may be needed as workaround.

Code Example

[agent/embedded] embedded run agent end: ... error=LLM request failed: provider rejected the request schema or tool payload. rawError=400 Param Incorrect
[model-fallback/decision] model fallback decision: decision=candidate_failed ... detail=400 Param Incorrect
RAW_BUFFERClick to expand / collapse

Bug type

Regression (worked before, now fails)

Beta release blocker

No

Summary

xiaomi-coding/mimo-v2.5 and mimo-v2.5-pro consistently fail with "LLM request failed: provider rejected the request schema or tool payload. rawError=400 Param Incorrect" on most messages.

Steps to reproduce

1.Configure provider xiaomi-coding with model mimo-v2.5 or mimo-v2.5-pro. 2.Start gateway and connect via Telegram. 3.Send normal messages to the bot. 4.Observe error in logs and no reply from agent

Expected behavior

The model should process normal prompts and return a response instead of rejecting the request with schema/tool payload error.

Actual behavior

Agent fails with error LLM request failed: provider rejected the request schema or tool payload. rawError=400 Param Incorrect on most interactions.

OpenClaw version

2026.5.12

Operating system

Ubuntu (running on VPS)

Install method

npm (global) + systemd user service

Model

xiaomi-coding/mimo-v2.5 (also tested with mimo-v2.5-pro)

Provider / routing chain

xiaomi-coding

Additional provider/model setup details

Using openai-completions compatibility mode. Ran openclaw doctor --fix multiple times. Tried compat.strictMessageKeys true.

Logs, screenshots, and evidence

[agent/embedded] embedded run agent end: ... error=LLM request failed: provider rejected the request schema or tool payload. rawError=400 Param Incorrect
[model-fallback/decision] model fallback decision: decision=candidate_failed ... detail=400 Param Incorrect

Impact and severity

Affects Telegram integration (main usage channel) Severity: Blocks normal usage Frequency: Almost every message after the first few Consequence: Agent cannot reply properly, making the bot mostly unusable with this model

Additional information

Same error pattern seen in issues #68735 and #68957. Temporarily switching to other models may be needed as workaround.

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

The model should process normal prompts and return a response instead of rejecting the request with schema/tool payload error.

#model loading#dependency error#configuration error#environment variable#network issue

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 [Bug]: LLM request failed: provider rejected the request schema or tool payload with xiaomi-coding/mimo-v2.5