openclaw - ✅(Solved) Fix Thinking-only LLM responses silently dropped (kimi-k2.5-thinking) [2 pull requests, 1 comments, 2 participants]

openclaw2026-04-11 01:14:43

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#64570•Fetched 2026-04-11 06:14:22

View on GitHub

Comments

Participants

Timeline

Reactions

Author

OpenCodeEngineer

Participants

neeravmakwana

OpenCodeEngineer

Timeline (top)

referenced ×6cross-referenced ×2commented ×1

Error Message

resolveIncompleteTurnPayloadText — only triggers on stopReason: "toolUse" | "error", misses stopReason: "stop" with empty assistant text

Root Cause

Two detection gates in src/agents/pi-embedded-runner/run/incomplete-turn.ts fail to catch this:

resolveIncompleteTurnPayloadText — only triggers on stopReason: "toolUse" | "error", misses stopReason: "stop" with empty assistant text
resolvePlanningOnlyRetryInstruction — only applies to openai/gpt-5 models

RAW_BUFFERClick to expand / collapse

Problem

When kimi-k2.5-thinking (or potentially other thinking models) returns a response containing only thinking content with stopReason: "stop", the agent treats this as a successful completion with 0 payloads — no text, no tool calls, no retry. The user's message gets silently dropped.

Root Cause

Two detection gates in src/agents/pi-embedded-runner/run/incomplete-turn.ts fail to catch this:

resolveIncompleteTurnPayloadText — only triggers on stopReason: "toolUse" | "error", misses stopReason: "stop" with empty assistant text
resolvePlanningOnlyRetryInstruction — only applies to openai/gpt-5 models

Proposed Fix

Extend resolveIncompleteTurnPayloadText to detect stopReason: "stop" with 0 assistant text blocks AND 0 tool calls. Extend resolvePlanningOnlyRetryInstruction to cover all thinking models.

Impact

Any user message triggering a thinking-only response is silently lost. Particularly likely on high-context sessions.

#724

extent analysis

TL;DR

Extend the resolveIncompleteTurnPayloadText and resolvePlanningOnlyRetryInstruction functions to handle stopReason: "stop" with empty responses from thinking models like kimi-k2.5-thinking.

Guidance

Review the src/agents/pi-embedded-runner/run/incomplete-turn.ts file to understand the current implementation of resolveIncompleteTurnPayloadText and resolvePlanningOnlyRetryInstruction.
Modify resolveIncompleteTurnPayloadText to trigger on stopReason: "stop" when there are 0 assistant text blocks and 0 tool calls.
Update resolvePlanningOnlyRetryInstruction to apply to all thinking models, not just openai/gpt-5.
Test the changes with different thinking models and edge cases to ensure the fix works as expected.

Example

// Example of how resolveIncompleteTurnPayloadText could be extended
function resolveIncompleteTurnPayloadText(turn) {
  if (turn.stopReason === "stop" && turn.assistant.text_blocks.length === 0 && turn.tool_calls.length === 0) {
    // Handle the case where stopReason is "stop" with empty response
  }
  // Existing logic for other stopReason cases
}

Notes

The proposed fix assumes that the issue is solely due to the two detection gates missing the stopReason: "stop" case. Additional testing and verification may be necessary to ensure the fix works correctly in all scenarios.

Recommendation

Apply the workaround by extending the resolveIncompleteTurnPayloadText and resolvePlanningOnlyRetryInstruction functions as described, to prevent user messages from being silently dropped when a thinking model returns an empty response.

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?

#retrieval issue #search optimization #API routing #API middleware #SSR setup

Still need to ship something?

×6

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

openclaw - ✅(Solved) Fix Thinking-only LLM responses silently dropped (kimi-k2.5-thinking) [2 pull requests, 1 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Root Cause

Fix Action

Fixed

PR fix notes

PR #64576: fix(agents): surface incomplete embedded Pi turn when stop leaves no visible reply

Description (problem / solution / changelog)

Summary

Change Type (select all)

Scope (select all touched areas)

Linked Issue/PR

Root Cause (if applicable)

Regression Test Plan (if applicable)

User-visible / Behavior Changes

Diagram (if applicable)

Security Impact (required)

Changed files

PR #64589: fix(agents): incomplete turn + Codex prepareArguments (#64570)

Description (problem / solution / changelog)

Summary

Changes

Issue

Supersedes

Changed files

Problem

Root Cause

Proposed Fix

Impact

Related

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

RELATED_DISCOVERY

TRENDING