Fix token counting: show only completion tokens, not cumulative prompt+completion

Fork: 0

root / navi-1

Browse code Fix token counting: show only completion tokens, not cumulative prompt+completion The token_count displayed next to assistant messages was summing prompt_tokens + completion_tokens across ALL tool-calling iterations, giving hundreds of thousands of tokens for multi-turn conversations. Now: - token_count (coins icon) = only completion tokens generated by the model - context_tokens (ContextBar) = only prompt tokens (context size sent to LLM) This gives users a realistic measure of how much the model actually generated. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> feature/navi-code master vmkdemo
1 parent 119776a commit e04b4ca8c8e9b585991f70ff66444babc5e5b535 Eugene Sukhodolskiy authored on 21 May

Browse code

The token_count displayed next to assistant messages was summing
prompt_tokens + completion_tokens across ALL tool-calling iterations,
giving hundreds of thousands of tokens for multi-turn conversations.

Now:
- token_count (coins icon) = only completion tokens generated by the model
- context_tokens (ContextBar) = only prompt tokens (context size sent to LLM)

This gives users a realistic measure of how much the model actually generated.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

feature/navi-code master vmkdemo

1 parent 119776a commit e04b4ca8c8e9b585991f70ff66444babc5e5b535

Eugene Sukhodolskiy authored on 21 May

Patch

Unified Split

Showing 4 changed files

Ignore Space Show notes View navi/core/agent.py

Ignore Space Show notes View navi/core/events.py

Ignore Space Show notes View navi/core/subagent_runner.py

Ignore Space Show notes View tests/unit/core/test_agent.py

Show line notes below