fix(core): clear tool output and attachments on compaction prune

[bil9148]

Issue for this PR

Closes #5700, #3013

Related: #9385, #9151, #7046, #5363, #13796, #12255, #10248, #9156, #9140, #10913

Type of change

• Bug fix
• New feature
• Refactor / code improvement
• Documentation

What does this PR do?

SessionCompaction.prune() marks old tool outputs as compacted by setting part.state.time.compacted = Date.now(), but it never clears the actual output string or attachments array from the part. Since toModelMessages already replaces compacted output with "[Old tool result content cleared]" (message-v2.ts:620), the stored data is dead weight after compaction.

The problem is that every prompt loop iteration reloads all parts from storage into memory. In a long session with many tool calls (file reads, grep results, bash output), these compacted-but-still-full parts accumulate significant data that gets loaded into RAM repeatedly for no reason.

This clears both output and attachments on the part when pruning, so subsequent reloads don't bring dead data back into memory.

How did you verify your code works?

I monitored RSS memory of the bun process over multiple long sessions using /proc/<pid>/status and /proc/<pid>/smaps. Before the fix, a session would climb to 14-22GB RSS over the course of extended use. After the fix, memory growth is noticeably slower because compacted parts no longer contribute to the reload size.

Also verified that toModelMessages already guards compacted parts at message-v2.ts:620-621 — it checks part.state.time.compacted and substitutes "[Old tool result content cleared]" regardless of what's in output, so clearing the field has no functional impact on the messages sent to the API.

Checklist

• I have tested my changes locally
• I have not included unrelated changes in this PR

[github-actions]

The following comment was made by an LLM, it may be inaccurate:

I found potentially related PRs:

⚠️ Potential Duplicates:

1. PR fix: clear tool output and attachments when pruning to prevent memory leak #7049: "fix: clear tool output and attachments when pruning to prevent memory leak"

   • fix: clear tool output and attachments when pruning to prevent memory leak #7049
   • This appears to be addressing the exact same issue as PR fix(core): clear tool output and attachments on compaction prune #14693 - clearing tool output and attachments during pruning to prevent memory leaks.

2. PR fix: resolve memory leak issues across multiple subsystems #14650: "fix: resolve memory leak issues across multiple subsystems"

   • fix: resolve memory leak issues across multiple subsystems #14650
   • This PR addresses memory leak issues broadly and may overlap with the SessionCompaction memory optimization work.

Recommendation: Check PR #7049 first, as it appears to be directly addressing the same bug fix. It may have already been merged or closed, making PR #14693 potentially redundant.

[bil9148]

Closing in favor of #7049, which addresses the same root cause (compacted tool outputs and attachments not being cleared during pruning) and includes tests.