Uh oh!
There was an error while loading. Please reload this page.
feat: implement smart pruning - #7215
Conversation
The following comment was made by an LLM, it may be inaccurate: Based on my search results, I found one potentially related PR: Related PR Found:PR #7049: "fix: clear tool output and attachments when pruning to prevent memory leak" Why it's related: This PR deals with pruning mechanism and memory management, which is closely related to the context management improvements in PR #7215. While PR #7049 appears to be a bug fix for clearing outputs during pruning, your new smart pruning system likely supersedes or enhances this approach with the tiered priority system and LLM summarization. The other results (PR #5422 on cache configuration and #1407 on autocompaction) are tangentially related to context optimization but don't appear to be direct duplicates of the smart pruning feature. |
f0df7bb to
1b7f011CompareThanks for your contribution! This PR doesn't have a linked issue. All PRs must reference an existing issue. Please:
See CONTRIBUTING.md for details. |
1b7f011 to
bd16d00Compareprocesstrader
commented
Jan 9, 2026
@rekram1-node I linked this to the feature request #7459, but somehow the label is still there 'needs:issue', just pinging in case you guys are using a filter for that, to not even look at PRs that could have that label. |
f1ae801 to
08fa7f7CompareClosing this pull request because it has had no updates for more than 60 days. If you plan to continue working on it, feel free to reopen or open a new PR. |
Summary
This PR implements Smart Pruning, a new context management system that replaces the basic FIFO approach with a tiered priority system to preserve critical information longer.
Key Changes
read,webfetch) - Summarized when prunedls,grep) - Compressed when prunededit,write) - Never prunedgrepkeeps first 5 matches,bashkeeps exit code + last 10 lines).opencode.jsonfor budgets, custom tool classification, and summarization settings.Fixes#7459