fix: improve context overflow error messages and docs#18997
Closed
realhoratiobot wants to merge 1 commit intoopenclaw:mainfrom
Closed
fix: improve context overflow error messages and docs#18997realhoratiobot wants to merge 1 commit intoopenclaw:mainfrom
realhoratiobot wants to merge 1 commit intoopenclaw:mainfrom
Conversation
- Include context window size, source, and message count in overflow error - Add actionable suggestions: reduce workspace files, lower bootstrapMaxChars - Document compaction config keys with examples in docs - Add troubleshooting section for context overflow - Clarify that autoCompact is not a config key (common user confusion) - Improve diagnostic logging with contextWindow and contextSource fields Closes openclaw#5771
|
@greptileai please review |
Comment on lines
543
to
+544
| const fallbackText = isContextOverflow | ||
| ? "⚠️ Context overflow — prompt too large for this model. Try a shorter message or a larger-context model." | ||
| ? "⚠️ Context overflow — prompt too large for this model. Try /reset or /new for a fresh session, reduce workspace files, or switch to a larger-context model." |
Contributor
There was a problem hiding this comment.
E2e test expects the old message string
The test in reply.triggers.trigger-handling.ignores-inline-elevated-directive-unapproved-sender.e2e.test.ts (line 140-142) uses toBe() (exact match) against the previous message:
"⚠️ Context overflow — prompt too large for this model. Try a shorter message or a larger-context model."
But this line now returns:
"⚠️ Context overflow — prompt too large for this model. Try /reset or /new for a fresh session, reduce workspace files, or switch to a larger-context model."
That test needs to be updated to match the new message, otherwise it will fail.
Prompt To Fix With AI
This is a comment left during a code review.
Path: src/auto-reply/reply/agent-runner-execution.ts
Line: 543:544
Comment:
**E2e test expects the old message string**
The test in `reply.triggers.trigger-handling.ignores-inline-elevated-directive-unapproved-sender.e2e.test.ts` (line 140-142) uses `toBe()` (exact match) against the previous message:
```
"⚠️ Context overflow — prompt too large for this model. Try a shorter message or a larger-context model."
```
But this line now returns:
```
"⚠️ Context overflow — prompt too large for this model. Try /reset or /new for a fresh session, reduce workspace files, or switch to a larger-context model."
```
That test needs to be updated to match the new message, otherwise it will fail.
How can I resolve this? If you propose a fix, please make it concise.
This was referenced Feb 17, 2026
Contributor
|
Closing as AI-assisted stale-fix triage. Linked issue #5771 ("[Bug]: Context overflow error") is CLOSED and was closed on 2026-02-23T16:33:28Z with state reason COMPLETED. If the behavior is still reproducible on current main, reopen #18997 (or open a new focused fix PR) and reference #5771. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Improves the user experience when hitting context overflow errors (#5771).
Changes
Error messages (src)
bootstrapMaxChars, use/resetcontextWindowandcontextSourcefieldsDocumentation (docs)
agents.defaults.compactionconfig with full example (mode, reserveTokensFloor, memoryFlush)contextTokens,bootstrapMaxChars,bootstrapTotalMaxCharsautoCompactis NOT a config key (common user confusion from the issue)Before
After
Testing
pnpm buildpassesrun.overflow-compaction.test.ts,config.compaction-settings.test.ts)Closes #5771
Greptile Summary
Improves context overflow error messages with actionable diagnostic information (context window size, source, message count) and adds comprehensive compaction documentation including config examples, related settings, and a troubleshooting section.
run.ts: Error message now includes dynamic context info (window size, source, message count) and specific remediation stepsagent-runner-execution.ts: Catch-all fallback message updated with consistent suggestions (/reset, reduce workspace files, switch model)compaction.md: Added YAML config example, related settings table,autoCompactclarification, and troubleshooting section — all verified against source codereply.triggers.trigger-handling.ignores-inline-elevated-directive-unapproved-sender.e2e.test.ts(line 140-142) usestoBe()exact match against the old fallback message fromagent-runner-execution.tsand was not updated in this PR — this test will failConfidence Score: 3/5
reply.triggers.trigger-handling.ignores-inline-elevated-directive-unapproved-sender.e2e.test.tsexpects the old message string viatoBe()and was not updated, which will cause a test failure. Score of 3 reflects that the functional changes are sound but the PR is not merge-ready until the test is fixed.src/auto-reply/reply/agent-runner-execution.ts— the updated error message at line 544 breaks an e2e test that was not included in this PR's changes.Last reviewed commit: 1eef057
(2/5) Greptile learns from your feedback when you react with thumbs up/down!