Fix token estimation: include ToolUse arguments in text_length#881
Merged
jaberjaber23 merged 4 commits intoRightNow-AI:mainfrom Mar 30, 2026
Merged
Conversation
`MessageContent::text_length()` returned 0 for `ToolUse` blocks, ignoring the tool name and JSON input arguments. This caused the compactor's `estimate_token_count()` (which uses `text_length()`) to massively undercount tokens when conversations contained tool calls with large arguments (e.g. web_search results, page content). The result: compaction never triggered despite the session exceeding the context window, leading to "Token limit exceeded" errors. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
MessageContent::text_length()returned0forContentBlock::ToolUseblocks, completely ignoring the tool name and JSON input argumentsestimate_token_count()relies ontext_length(), so sessions with large tool call arguments (e.g.web_search,web_fetch) were massively undercountedToken limit exceedederrors at the LLM providerFix
Include
name.len() + input.to_string().len()forToolUseblocks, matching the existing pattern forToolResultandTextblocks.Test plan
text_length()returns non-zero for messages containingToolUseblockscargo test -p openfang-types🤖 Generated with Claude Code