fix: remove auto-proceed fake user message injection#255
Merged
ilblackdragon merged 2 commits intomainfrom Feb 20, 2026
Merged
Conversation
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
ilblackdragon
previously approved these changes
Feb 20, 2026
serrrfirat
force-pushed
the
fix/remove-auto-proceed-nudge
branch
from
b002f86 to
45d1c67
Compare
The agentic loop injected fake user messages ("Please proceed and use
the available tools to complete this task.") when the LLM responded
with text instead of tool calls. This caused hallucinated conversations
during casual chat, 3x wasted LLM calls, and trust issues.
Remove the `resume_after_tool` parameter and `tools_executed` tracking
entirely. Text responses now return immediately, trusting the LLM to
decide when tools are needed (consistent with ZeroClaw and OpenClaw).
Closes #145
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
serrrfirat
force-pushed
the
fix/remove-auto-proceed-nudge
branch
from
45d1c67 to
4810439
Compare
github-actions
Bot
added
size: S
ilblackdragon
approved these changes
Feb 20, 2026
Merged
Closed
26 tasks
jaswinder6991
pushed a commit
to jaswinder6991/ironclaw
that referenced
this pull request
Feb 26, 2026
…earai#255) The agentic loop injected fake user messages ("Please proceed and use the available tools to complete this task.") when the LLM responded with text instead of tool calls. This caused hallucinated conversations during casual chat, 3x wasted LLM calls, and trust issues. Remove the `resume_after_tool` parameter and `tools_executed` tracking entirely. Text responses now return immediately, trusting the LLM to decide when tools are needed (consistent with ZeroClaw and OpenClaw). Closes nearai#145 Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
bkutasi
pushed a commit
to bkutasi/ironclaw
that referenced
this pull request
Mar 28, 2026
…earai#255) The agentic loop injected fake user messages ("Please proceed and use the available tools to complete this task.") when the LLM responded with text instead of tool calls. This caused hallucinated conversations during casual chat, 3x wasted LLM calls, and trust issues. Remove the `resume_after_tool` parameter and `tools_executed` tracking entirely. Text responses now return immediately, trusting the LLM to decide when tools are needed (consistent with ZeroClaw and OpenClaw). Closes nearai#145 Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
resume_after_toolparameter andtools_executedtracking fromrun_agentic_loopMotivation
The nudge mechanism caused:
Both ZeroClaw and OpenClaw handle this by simply returning text responses immediately and relying on prompt engineering for tool use encouragement.
Closes #145
Test plan
cargo fmt— cleancargo clippy --all --benches --tests --examples --all-features— no warningscargo test— 882 tests passresume_after_tool,tools_executed, or "Please proceed" inagent_loop.rs🤖 Generated with Claude Code