🤖 fix: accumulate output tokens across steps in cost tracking #811
Conversation
ethanndickson
force-pushed
the
fix-cost-tracking-increment
branch
from
b23d27d to
609fe22
Compare
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
ethanndickson
force-pushed
the
fix-cost-tracking-increment
branch
from
609fe22 to
b4940f6
Compare
|
@codex review |
|
Codex Review: Didn't find any major issues. Hooray! ℹ️ About Codex in GitHubCodex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback". |
ethanndickson
force-pushed
the
fix-cost-tracking-increment
branch
from
b4940f6 to
b98c08d
Compare
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
In multi-step mode (tool use), the AI SDK emits per-step usage where: - inputTokens: Current context window (grows each step) - outputTokens: Tokens generated in that step only The aggregator was replacing usage on each step, losing earlier output tokens. Now we accumulate output/reasoning tokens while keeping the latest input tokens (which correctly represent the growing context). This fixes the issue where costs appeared to increment by only ~2¢ at a time instead of reflecting cumulative output costs. _Generated with mux_
ethanndickson
force-pushed
the
fix-cost-tracking-increment
branch
from
b98c08d to
935f071
Compare
|
@codex review |
|
Codex Review: Didn't find any major issues. Hooray! ℹ️ About Codex in GitHubCodex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback". |
1 participant
In multi-step mode (tool use), the AI SDK emits per-step usage where:
inputTokens: Current context window (grows each step)outputTokens: Tokens generated in that step onlyThe aggregator was replacing usage on each step, losing earlier output tokens. Now we accumulate output/reasoning tokens while keeping the latest input tokens (which correctly represent the growing context).
This fixes the issue where costs appeared to increment by only ~2¢ at a time instead of reflecting cumulative output costs.
Generated with
mux