openclaw - 💡(How to fix) Fix [Bug]: extra_body overwriting request payload keys: thinking — framework-level thinking field collision affecting all providers [1 comments, 2 participants]

openclaw2026-04-30 11:06:17

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.

GitHub issue URL

Helpful · Quick feedback

GitHub stats

openclaw/openclaw#75040•Fetched 2026-05-01 05:38:52

View on GitHub

Comments

Participants

Timeline

Reactions

Author

kingkong9817

Participants

clawsweeper[bot]

kingkong9817

Timeline (top)

commented ×1mentioned ×1subscribed ×1

Every API request produces a WARN log: extra_body overwriting request payload keys: thinking. This is a framework-level issue that affects all providers (DeepSeek, Ollama, etc.), not just a single provider. The thinking parameter is being written in two separate locations within the request payload pipeline, causing a field collision on every request.

Error Message

Essentially every request triggers this WARN
No WARN about parameter overwriting should appear on requests where thinking is explicitly disabled

Root Cause

2. Ollama/Qwen3 (local model): This has severe consequences for local models:

[llm-idle-timeout] ollama/qwen3:32b-q4_K_M-16k produced no reply before the idle watchdog
Profile ollama:default timed out
Stuck sessions with state=processing age=141s
The root cause appears to be: OpenClaw sends "thinking" parameter, but Ollama native protocol uses "think" (top-level). When the thinking field state is unreliable due to the overwrite collision, the model may output to message.thinking instead of message.content, causing OpenClaw to see an empty reply → idle-timeout → stuck session → failover to surface_error.
Mitigation: Setting thinking: false, think: false, and reasoning: false for all local Ollama models resolves the issue, confirming the thinking field is the root cause.

Fix Action

Workaround

For Ollama/Qwen3: explicitly disable all thinking-related parameters in the model config (thinking: false, think: false, reasoning: false).

Code Example

extra_body overwriting request payload keys: thinking
[llm-idle-timeout] ollama/qwen3:32b-q4_K_M-16k produced no reply before the idle watchdog
Profile ollama:default timed out. Trying next account...
stuck session: sessionId=main state=processing age=141s

RAW_BUFFERClick to expand / collapse

Bug Report

Summary

Version

OpenClaw 2026.4.26 (be8c246)
Node.js v25.9.0
macOS (launchd managed gateway)

Reproduction

Always reproducible. Simply run the gateway with any model — the warning appears on every single API request.

Frequency

~384 occurrences/day (observed 2026-04-30, 18:56 CST)
271 occurrences/day (observed 2026-04-28)
Essentially every request triggers this WARN

Impact

1. DeepSeek (V4 Pro): When thinking is enabled, this parameter collision has caused:

Frequent API timeouts (10 consecutive timeouts observed between 04:03-04:20 UTC on 2026-04-28)
May be related to issue #74374 (400 "reasoning_content must be passed back")

2. Ollama/Qwen3 (local model): This has severe consequences for local models:

[llm-idle-timeout] ollama/qwen3:32b-q4_K_M-16k produced no reply before the idle watchdog
Profile ollama:default timed out
Stuck sessions with state=processing age=141s
The root cause appears to be: OpenClaw sends "thinking" parameter, but Ollama native protocol uses "think" (top-level). When the thinking field state is unreliable due to the overwrite collision, the model may output to message.thinking instead of message.content, causing OpenClaw to see an empty reply → idle-timeout → stuck session → failover to surface_error.
Mitigation: Setting thinking: false, think: false, and reasoning: false for all local Ollama models resolves the issue, confirming the thinking field is the root cause.

Relevant Source Location

Based on investigation, this appears to originate from createOpenAICompletionsExtraBodyWrapper in:

src/agents/pi-embedded-runner/extra-params.ts (around line 492)
The extra_body wrapper is applied after provider-specific wrappers, and Object.assign overwrites payload keys with a collision warning

Expected Behavior

The thinking parameter should be written to the request payload exactly once, in a single location
No WARN about parameter overwriting should appear on requests where thinking is explicitly disabled
Local Ollama models should work reliably whether thinking is enabled or disabled

Workaround

For Ollama/Qwen3: explicitly disable all thinking-related parameters in the model config (thinking: false, think: false, reasoning: false).

Log Evidence

extra_body overwriting request payload keys: thinking
[llm-idle-timeout] ollama/qwen3:32b-q4_K_M-16k produced no reply before the idle watchdog
Profile ollama:default timed out. Trying next account...
stuck session: sessionId=main state=processing age=141s

extent analysis

TL;DR

The most likely fix involves modifying the createOpenAICompletionsExtraBodyWrapper function in src/agents/pi-embedded-runner/extra-params.ts to avoid overwriting the thinking parameter in the request payload.

Guidance

Investigate the createOpenAICompletionsExtraBodyWrapper function to identify why the thinking parameter is being written twice, causing a field collision.
Verify that the thinking parameter is only written once by checking the request payload before and after the extra_body wrapper is applied.
Consider adding a check to prevent overwriting existing keys in the request payload, such as using Object.assign with a custom merge function.
Test the fix by running the gateway with a model and checking for the WARN log message.

Example

// Example of how to modify the createOpenAICompletionsExtraBodyWrapper function
// to avoid overwriting existing keys in the request payload
function createOpenAICompletionsExtraBodyWrapper(payload) {
  const extraBody = { thinking: true }; // or false, depending on the configuration
  // Use a custom merge function to avoid overwriting existing keys
  return { ...payload, ...extraBody };
}

Notes

The provided workaround for Ollama/Qwen3 models suggests that disabling thinking-related parameters resolves the issue, which supports the hypothesis that the thinking parameter collision is the root cause.

Recommendation

Apply a workaround by modifying the createOpenAICompletionsExtraBodyWrapper function to avoid overwriting the thinking parameter, as this is a more targeted fix than disabling thinking-related parameters for all models.

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?

#api #runtime error #dependency conflict #environment setup #docker error

Still need to ship something?

×6

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

Data

Security

Network

Code

UI/UX

Text

System

Multimedia

Protocol

API

Engineering

openclaw - 💡(How to fix) Fix [Bug]: extra_body overwriting request payload keys: thinking — framework-level thinking field collision affecting all providers [1 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Root Cause

Fix Action

Workaround

Code Example

Bug Report

Summary

Version

Reproduction

Frequency

Impact

Relevant Source Location

Expected Behavior

Workaround

Log Evidence

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

TRENDING

openclaw - 💡(How to fix) Fix [Bug]: extra_body overwriting request payload keys: thinking — framework-level thinking field collision affecting all providers [1 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Root Cause

Fix Action

Workaround

Code Example

Bug Report

Summary

Version

Reproduction

Frequency

Impact

Relevant Source Location

Expected Behavior

Workaround

Log Evidence

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

RELATED_DISCOVERY

TRENDING