abc/analysis_claude_code
1
0
Fork 0
mirror of https://github.com/shareAI-lab/analysis_claude_code.git synced 2026-09-21 21:03:38 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: preserve tool results during context compaction

Browse Source
This commit is contained in:
Haoran
2026-08-23 11:50:52 +08:00
parent 61c3e64595
commit 6d70d2e071
24 changed files with 843 additions and 497 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
s15_integrated_harness/README.md
View File

@@ -154,6 +154,8 @@ Before the LLM call, S15 runs the compaction pipeline:
tool_result_budget → snip_compact → micro_compact → compact_history
```
`snip_compact` archives the complete history before trimming its middle. `micro_compact` runs only above the context limit: it saves older consumed results before replacing them with recovery paths, keeps the latest 3 complete, and stops near 80% of the limit. If a new unseen result is itself too large, S15 keeps a preview and the full-output path before considering history summarization.
The model call is wrapped with recovery:
- 429: exponential backoff retry