anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-24 12:15:51 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

[PR #10520] feat(app): add provider usage breakdown to session context #13469

New Issue
Open
opened 2026-02-16 18:18:19 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 18:18:19 -05:00
Owner
Copy Link
Copy Source

Original Pull Request: https://github.com/anomalyco/opencode/pull/10520

State: open
Merged: No

Summary

Add per-provider token usage breakdown to the session context usage tooltip, making it easier for users to understand their token consumption across different AI providers.

Changes

  • Enhanced SessionContextUsage component with provider breakdown:

    • Shows per-provider token counts with emoji indicators (🟣 Anthropic, 🔵 Google, 🟢 OpenAI, etc.)
    • Displays percentage breakdown for each provider
    • Formats token counts (e.g., 1.2M, 500K)
    • Separates provider usage from context window stats

  • Added SessionContextUsage to session header for better visibility

Screenshot

When hovering the usage indicator:

┌─────────────────────────────────┐
│ Provider Usage                   │
│ ─────────────────────────────── │
│ 🟣 Anthropic     1.2M      62%  │
│ 🔵 Google        500K      25%  │  
│ 🟢 OpenAI        250K      13%  │
│ ─────────────────────────────── │
│ Total            2.0M           │
├─────────────────────────────────┤
│ Context Tokens: 150,000         │
│ Window Usage: 45%               │
│ Total Cost: $2.50               │
└─────────────────────────────────┘

Why

Multi-model users often want to know which providers they're consuming the most tokens from. This helps with:

  • Cost optimization (knowing which provider is being used most)
  • Usage monitoring across different AI providers
  • Better transparency in multi-agent workflows (e.g., oh-my-opencode)
**Original Pull Request:** https://github.com/anomalyco/opencode/pull/10520 **State:** open **Merged:** No --- ## Summary Add per-provider token usage breakdown to the session context usage tooltip, making it easier for users to understand their token consumption across different AI providers. ## Changes - **Enhanced `SessionContextUsage` component** with provider breakdown: - Shows per-provider token counts with emoji indicators (🟣 Anthropic, 🔵 Google, 🟢 OpenAI, etc.) - Displays percentage breakdown for each provider - Formats token counts (e.g., 1.2M, 500K) - Separates provider usage from context window stats - **Added `SessionContextUsage` to session header** for better visibility ## Screenshot When hovering the usage indicator: ``` ┌─────────────────────────────────┐ │ Provider Usage │ │ ─────────────────────────────── │ │ 🟣 Anthropic 1.2M 62% │ │ 🔵 Google 500K 25% │ │ 🟢 OpenAI 250K 13% │ │ ─────────────────────────────── │ │ Total 2.0M │ ├─────────────────────────────────┤ │ Context Tokens: 150,000 │ │ Window Usage: 45% │ │ Total Cost: $2.50 │ └─────────────────────────────────┘ ``` ## Why Multi-model users often want to know which providers they're consuming the most tokens from. This helps with: - Cost optimization (knowing which provider is being used most) - Usage monitoring across different AI providers - Better transparency in multi-agent workflows (e.g., oh-my-opencode)
yindo added the pull-request label 2026-02-16 18:18:19 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
acp
bad
bug
discussion
docs
documentation
enhancement
extension
good first issue
growth
help-wanted
mcp
model-problem
needs:compliance
nix
opentui
perf
pull-request
Mirrored from GitHub Pull Request
 tui
web
windows
zen
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#13469
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?