You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Claude seemingly forgot the message he just sent about remaining work after "finishing" (giving up halfway through) his task. This felt like he was starting a fresh session, even though I was referencing what he just said.
Ah, interesting, that actually explains quite a lot. I often see similar messages when it seems to prematurely declare victory and give a summary of its accomplishments. I guess those were actually compacts.
@rekram1-node from the code it seems like auto compacting is implemented as it should (checks if model limit is reached and then runs a summarize), if you could please explain what rewrite you think needed?
Only thing I can really see is the summarize prompt is a bit little, and maybe for this exact case priority could be made to the last message made by the assistant in the summary.
imo I think compact shouldn't literally replace entire convo, last n messages should stay as is and the compact should apply to the messages before it to help prevent this "memory loss"
Compact prompt could probably also use work
but these are kinda core things
Ultimately the decision isn't up to me, I am a maintainer but I don't make authoritative decisions on this project, that is the up to the team
Reacted by Tyler C Laprade, CFA, Gui Martins, Chindriș Mihai - Alexandru and Dennis Lau
I don't know if my issue is related but using GitHub Copilot Sonnet 4 and compacting make the agent just stop. It hangs on "Generating ..." and I need to tell it to "Continue" otherwise it just sits there.
Reacted by Tyler C Laprade, CFA and Chindriș Mihai - Alexandru
No, it's auto compacting and it hangs. It also loses a lot of the context and kinda forgets what it was doing. For more clarity, I am trying GitHub/spec-kit and I think a lot of the context window is taken up by the instructions and prompts for each command.
Reacted by Tyler C Laprade, CFA and Chindriș Mihai - Alexandru
@rekram1-node@thdxr I am seeing a new bug from few days maybe related to this issue only and recent updates
The auto compact happens without context limit being near limit and then the LLM forgots the everything also compact does not works successfully. (The compact just happened after the SYSTEM REMINDER and then something weird happened, I don't know why JSON export also didn't have the compact command or message)
Part of session JSON Where it occurred:
### Session 2 (Current)
1. **Analyzed frontend VAD architecture** - confirmed no conflict exists between frontend and backend VAD (mutually exclusive)
2. **Fixed Next.js `websocket.js`** - added missing `latency_update` message handler
3. **Fixed Next.js `vad.js`** - added missing `destroy()` and `getMetrics()` methods
### Remaining Tasks
- Update `.env.example` with optimal settings (audio quality issue you mentioned)
- Test with real audio
Want me to continue with the remaining tasks or would you like to test what we have so far?
---
## User
[SYSTEM REMINDER - TODO CONTINUATION]
Incomplete tasks remain in your todo list. Continue working on the next pending task.
- Proceed without asking for permission
- Mark each task complete when finished
- Do not stop until all tasks are done
[Status: 4/6 completed, 2 remaining]
---
## User
---
## Assistant
---
## User
---
## Assistant
Looking at my context, I don't have any prior conversation history with you in this session, and there are no active todos or tasks in progress.
To understand what work has been done on this project, I can:
1. Check recent git commits
2. Review any existing session history
Let me check the git log to see recent activity:
```
Tool: bash
Reacted by Tyler C Laprade, CFA, Chindriș Mihai - Alexandru and Dennis Lau
Activity
[-]Claude forgot the context of what he just said[/-][+]compact causes llm to forget convo[/+]rekram1-node commentedon Aug 25, 2025
ah yeah this is a due to compact
rekram1-node commentedon Aug 25, 2025
we should fix
OpeOginni commentedon Aug 25, 2025
Hey @rekram1-node I see you already have this issue assigned, but is it still okay if I take a look, I find it interesting.
rekram1-node commentedon Aug 25, 2025
@OpeOginni u are welcome to look at it but I think compact needs some rework and that may require discussion w/ team so just a forewarning
tylerlaprade commentedon Aug 25, 2025
Oh really? I didn't see a compact around that time.
rekram1-node commentedon Aug 25, 2025
@tylerlaprade the second to last ai message is the llm auto compacting the conversation by the looks of it
tylerlaprade commentedon Aug 25, 2025
Ah, interesting, that actually explains quite a lot. I often see similar messages when it seems to prematurely declare victory and give a summary of its accomplishments. I guess those were actually compacts.
OpeOginni commentedon Aug 25, 2025
@rekram1-node from the code it seems like auto compacting is implemented as it should (checks if model limit is reached and then runs a summarize), if you could please explain what rewrite you think needed?
Only thing I can really see is the summarize prompt is a bit little, and maybe for this exact case priority could be made to the last message made by the assistant in the summary.
rekram1-node commentedon Aug 25, 2025
imo I think compact shouldn't literally replace entire convo, last n messages should stay as is and the compact should apply to the messages before it to help prevent this "memory loss"
Compact prompt could probably also use work
but these are kinda core things
Ultimately the decision isn't up to me, I am a maintainer but I don't make authoritative decisions on this project, that is the up to the team
OpeOginni commentedon Aug 25, 2025
Makes sense, I'll leave this one for now then, but will keep an eye out 👀
robertmclaws commentedon Aug 27, 2025
Just had this one happen to me with Grok Code Free.
rekram1-node commentedon Sep 11, 2025
This should be fixed on latest! Dax just did some compact updates
rekram1-node commentedon Sep 12, 2025
nvm looks like more compact changes to come I'll come back once compact gets to a better state
gugahoi commentedon Sep 18, 2025
I don't know if my issue is related but using GitHub Copilot Sonnet 4 and compacting make the agent just stop. It hangs on "Generating ..." and I need to tell it to "Continue" otherwise it just sits there.
rekram1-node commentedon Sep 18, 2025
@gugahoi are you manually compacting and it hangs?
gugahoi commentedon Sep 18, 2025
No, it's auto compacting and it hangs. It also loses a lot of the context and kinda forgets what it was doing. For more clarity, I am trying GitHub/spec-kit and I think a lot of the context window is taken up by the instructions and prompts for each command.
raymelon commentedon Oct 3, 2025
Curious how to set auto compacting to False.
trystan2k commentedon Oct 3, 2025
You can do this:
OPENCODE_DISABLE_AUTOCOMPACT=true opencodedhruvkej9 commentedon Jan 1, 2026
@rekram1-node @thdxr I am seeing a new bug from few days maybe related to this issue only and recent updates
The auto compact happens without context limit being near limit and then the LLM forgots the everything also compact does not works successfully. (The compact just happened after the SYSTEM REMINDER and then something weird happened, I don't know why JSON export also didn't have the compact command or message)
Part of session JSON Where it occurred:
thdxr commentedon Mar 25, 2026
To stay organized issues are automatically closed after 90 days of no activity. If the issue is still relevant please open a new one.