feat: /usage

[GoodluckH]

Area.mp4

Currently, I'm basically reconstructing the FigConverationState output and that's gonna be hard to scale and maintain. It's a beta feature with rough est. Will follow up with a more accurate representation once #1175 is resolved.

Follow on ticket: #1178

[codecov-commenter]

Codecov Report

Attention: Patch coverage is 12.08791% with 80 lines in your changes missing coverage. Please review.

Project coverage is 14.12%. Comparing base (c633c9d) to head (d1ce4c0).
Report is 5 commits behind head on main.

Files with missing lines	Patch %	Lines
crates/q_cli/src/cli/chat/mod.rs	10.84%	74 Missing ⚠️
crates/q_cli/src/cli/chat/conversation_state.rs	0.00%	3 Missing ⚠️
crates/q_cli/src/util/token_counter.rs	50.00%	2 Missing ⚠️
crates/q_cli/src/cli/chat/command.rs	0.00%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1177      +/-   ##
==========================================
+ Coverage   14.03%   14.12%   +0.08%     
==========================================
  Files        2366     2366              
  Lines      205468   205778     +310     
  Branches   185832   186142     +310     
==========================================
+ Hits        28845    29065     +220     
- Misses     175198   175293      +95     
+ Partials     1425     1420       -5     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[brandonskiser]

We should have some shared behavior with summarization_state around here too, like have this be the window size and the summarization state MAX_CHARS constant be derived from this.

[GoodluckH]

yea moved this to summarization_state

[GoodluckH]

Which one is the source of the truth? The 200k tokens or 500k chars?

Rn I'm just dividing the char count by 3 to get tokens. With that logic, the new derived MAX_CHARS would be 600k, not 500k