nhcarrigan/hikari-desktop
9
0
Fork 0
generated from nhcarrigan/template
Code Issues 9 Pull Requests 36 Actions Releases 22 Activity

fix: review cost estimation accuracy after v2.1.75 token overcounting fix #228

New Issue
Closed
opened 2026-03-20 08:26:11 -07:00 by hikari · 0 comments
hikari commented 2026-03-20 08:26:11 -07:00
Owner
Copy Link
Copy Source

Background

CLI v2.1.75 fixed token estimation over-counting for thinking and tool_use blocks that was causing premature context compaction. This means the actual token counts reported for these block types are now lower than before.

Why It Matters for Hikari Desktop

Hikari Desktop performs its own cost estimation in wsl_bridge.rs when a session is interrupted (before the final result message arrives with accurate usage). The estimation logic uses character-to-token ratios. If the CLI was previously over-counting these blocks, our estimation may have been calibrated against inflated numbers.

We should:

  1. Review the estimation logic for thinking and tool_use blocks in wsl_bridge.rs
  2. Check whether our conservative chars/token ratio and safety margin still produce reasonable estimates against real post-v2.1.75 usage data
  3. Update the ratio/margin if testing shows systematic over-estimation

This is a low-urgency calibration task, but worth tracking as part of the v2.1.75 audit.

Acceptance Criteria

  • Cost estimation accuracy reviewed against real sessions on CLI ≥ 2.1.75
  • Estimation constants updated if materially off
  • Tests updated to reflect any changed constants

✨ This issue was created with help from Hikari~ 🌸

## Background CLI v2.1.75 fixed token estimation over-counting for `thinking` and `tool_use` blocks that was causing premature context compaction. This means the actual token counts reported for these block types are now lower than before. ## Why It Matters for Hikari Desktop Hikari Desktop performs its own cost estimation in `wsl_bridge.rs` when a session is interrupted (before the final `result` message arrives with accurate usage). The estimation logic uses character-to-token ratios. If the CLI was previously over-counting these blocks, our estimation may have been calibrated against inflated numbers. We should: 1. Review the estimation logic for `thinking` and `tool_use` blocks in `wsl_bridge.rs` 2. Check whether our conservative chars/token ratio and safety margin still produce reasonable estimates against real post-v2.1.75 usage data 3. Update the ratio/margin if testing shows systematic over-estimation This is a low-urgency calibration task, but worth tracking as part of the v2.1.75 audit. ## Acceptance Criteria - [ ] Cost estimation accuracy reviewed against real sessions on CLI ≥ 2.1.75 - [ ] Estimation constants updated if materially off - [ ] Tests updated to reflect any changed constants ✨ This issue was created with help from Hikari~ 🌸
naomi closed this issue 2026-03-23 14:28:09 -07:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
aspect
code
Concerns the software code in the repository
aspect
dx
Concerns developers' experience with the codebase
aspect
interface
Concerns end-users' experience with the software
aspect
text
Concerns the documentation material in the repository
contribute
good first issue
A great opportunity for a team member to learn a new codebase
contribute
help wanted
Open for anyone on our team to grab.
contribute
staff only
Restricted to our executive leadership.
goal
addition
Addition of new feature
goal
fix
Bug fix
goal
improvement
Improvement to an existing feature
points
1
Very simple issue requiring minimal effort and complexity.
points
13
Extremely complex issue representing major undertakings. Should be broken down into smaller pieces.
points
2
Simple issue that requires a bit more thought or investigation.
points
3
Moderate complexity issue requiring more substantial work.
points
5
Complex issue requiring significant effort and expertise.
points
8
Very complex issue requiring extensive work and deep expertise.
priority
critical
1
Must be fixed ASAP
priority
high
2
Stalls work on the project or its dependents
priority
low
4
Low priority and doesn't need to be rushed
priority
medium
3
Not blocking but should be fixed soon
priority
none
5
No priority, should only be performed when a developer is available
status
awaiting triage
Has not been triaged & therefore, not ready for work
status
blocked
Blocked and therefore not ready for work
status
discarded
Will not be worked on
status
discontinued
Not suitable for work as repo is in maintenance
status
label work required
Needs proper labelling before it can be worked on
status
ready for dev
Ready for work
status
ticket work required
Needs more details before it can be worked on
talk
discussion
Open for discussions and feedback
talk
question
Can be resolved with an answer
time
1 day
Approximately one full day of development work.
time
1-2 weeks
One to two weeks of focused development effort.
time
2-3 days
Two to three days of development effort.
time
4-5 days
Approximately one week of development work.
time
<1 day
Less than one day of focused work. Quick fixes or simple tasks.
time
>2 weeks
More than two weeks of development work. Must be broken down into smaller pieces.
No Label
Milestone
No items
No Milestone
Assignees
Clear assignees
gurkirat hanna (Hanna Rose) hikari (Hikari) minori (Minori) naomi (Naomi Carrigan) rain teklu tim
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: nhcarrigan/hikari-desktop#228
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?