anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-21 17:56:33 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

Feature: Configurable compaction threshold and model (global + per-model) #8411

New Issue
Open
opened 2026-02-16 18:09:54 -05:00 by yindo · 1 comment
yindo commented 2026-02-16 18:09:54 -05:00
Owner
Copy Link
Copy Source

Originally created by @tobiastornros on GitHub (Feb 3, 2026).

Originally assigned to: @thdxr on GitHub.

Add configurable compaction settings at both global and per-model levels:

  • Threshold: Trigger compaction at a percentage of context usage (not just at 100%)
  • Model: Use a different (cheaper/faster) model for compaction

Motivation

  1. Different models degrade at different context levels - Claude Opus quality drops around 50-60% context, while other models may handle more. Users should be able to tune this per-model.

  2. Compaction can use cheaper models - The compaction summary doesn't need the most expensive model. Users (especially Copilot users) want to use a cheaper model for compaction to save quota/costs.

Proposed Solution

Global config

{
  "compaction": {
    "auto": true,
    "prune": true,
    "threshold": 80,
    "model": "anthropic/claude-haiku-3-5-20241022"
  }
}

Per-model config

{
  "provider": {
    "anthropic": {
      "models": {
        "claude-opus-4-20250514": {
          "compaction_threshold": 50,
          "compaction_model": "zhipu/glm-4-plus"
        }
      }
    }
  }
}

Priority hierarchy

  1. Per-model compaction_threshold / compaction_model (highest)
  2. Global compaction.threshold / compaction.model
  3. Default: 100% threshold, same model as session

Related Issues

  • #11314 - Configurable Context Compaction Threshold
  • #8140 - Configurable context limit and auto-compaction threshold
  • #10017 - Custom compaction threshold to trigger earlier
  • #8629 - Model settings for automatic compaction (use cheaper model)
Originally created by @tobiastornros on GitHub (Feb 3, 2026). Originally assigned to: @thdxr on GitHub. Add configurable compaction settings at both global and per-model levels: - **Threshold**: Trigger compaction at a percentage of context usage (not just at 100%) - **Model**: Use a different (cheaper/faster) model for compaction ## Motivation 1. **Different models degrade at different context levels** - Claude Opus quality drops around 50-60% context, while other models may handle more. Users should be able to tune this per-model. 2. **Compaction can use cheaper models** - The compaction summary doesn't need the most expensive model. Users (especially Copilot users) want to use a cheaper model for compaction to save quota/costs. ## Proposed Solution ### Global config ```json { "compaction": { "auto": true, "prune": true, "threshold": 80, "model": "anthropic/claude-haiku-3-5-20241022" } } ``` ### Per-model config ```json { "provider": { "anthropic": { "models": { "claude-opus-4-20250514": { "compaction_threshold": 50, "compaction_model": "zhipu/glm-4-plus" } } } } } ``` ### Priority hierarchy 1. Per-model `compaction_threshold` / `compaction_model` (highest) 2. Global `compaction.threshold` / `compaction.model` 3. Default: 100% threshold, same model as session ## Related Issues - #11314 - Configurable Context Compaction Threshold - #8140 - Configurable context limit and auto-compaction threshold - #10017 - Custom compaction threshold to trigger earlier - #8629 - Model settings for automatic compaction (use cheaper model)
yindo commented 2026-02-16 18:09:54 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Feb 3, 2026):

This issue consolidates several related feature requests about compaction configuration. The issues listed are highly relevant and should be reviewed:

  • #11314: Configurable Context Compaction Threshold - Requests exposing threshold as user-configurable setting (currently hardcoded at 75%)
  • #8140: Configurable context limit and auto-compaction threshold - Proposes both threshold percentage and maxContext options
  • #10017: Custom compaction threshold to trigger earlier - Focuses on absolute token threshold (e.g., 50K tokens) to trigger compaction
  • #8629: Model settings for automatic compaction - Requests ability to use a cheaper model for compaction

This current issue (#11930) appears to be a comprehensive feature proposal that builds upon and consolidates these requests. It may be worth reviewing whether to close the older issues as duplicates of this one once it's implemented, or keeping them open for discussion if they represent specific use cases.

@github-actions[bot] commented on GitHub (Feb 3, 2026): This issue consolidates several related feature requests about compaction configuration. The issues listed are highly relevant and should be reviewed: - #11314: Configurable Context Compaction Threshold - Requests exposing threshold as user-configurable setting (currently hardcoded at 75%) - #8140: Configurable context limit and auto-compaction threshold - Proposes both threshold percentage and maxContext options - #10017: Custom compaction threshold to trigger earlier - Focuses on absolute token threshold (e.g., 50K tokens) to trigger compaction - #8629: Model settings for automatic compaction - Requests ability to use a cheaper model for compaction This current issue (#11930) appears to be a comprehensive feature proposal that builds upon and consolidates these requests. It may be worth reviewing whether to close the older issues as duplicates of this one once it's implemented, or keeping them open for discussion if they represent specific use cases.
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
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#8411
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?