langchain-ai/deepagentsjs
1
0
Fork 0
mirror of https://github.com/langchain-ai/deepagentsjs.git synced 2026-07-19 08:26:01 -04:00
Code Issues 42 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #221] Code generation frequently stops mid-way due to output token limits #46

New Issue
Closed
opened 2026-02-16 06:16:58 -05:00 by yindo · 7 comments
yindo commented 2026-02-16 06:16:58 -05:00
Owner
Copy Link
Copy Source

Originally created by @enteve on GitHub (Feb 11, 2026).
Original GitHub issue: https://github.com/langchain-ai/deepagentsjs/issues/221

Originally assigned to: @christian-bromann on GitHub.

Description:

When using DeepAgent to generate code, I frequently encounter an issue where the generation process stops abruptly due to the LLM's output token limit. This often happens before the code is complete, leaving partial or unusable results.

I've tried adding prompts instructing the agent to generate code in segments/batches, but the issue persists.

Has anyone experienced this or found a workaround? Some potential solutions I'm considering:

  1. Automatic resumption when output is truncated - detect incomplete code and continue generation
  2. Built-in chunking strategy for large code generation tasks
  3. Configurable token limit awareness in the agent

Questions:

  • Is there a recommended way to handle long code generation?
  • Are there any built-in features I might be missing to mitigate this?
  • Would it be possible to add support for streaming/chunked code generation?

Any guidance would be appreciated!

Originally created by @enteve on GitHub (Feb 11, 2026). Original GitHub issue: https://github.com/langchain-ai/deepagentsjs/issues/221 Originally assigned to: @christian-bromann on GitHub. ## Description: When using DeepAgent to generate code, I frequently encounter an issue where the generation process stops abruptly due to the LLM's output token limit. This often happens before the code is complete, leaving partial or unusable results. I've tried adding prompts instructing the agent to generate code in segments/batches, but the issue persists. Has anyone experienced this or found a workaround? Some potential solutions I'm considering: 1. Automatic resumption when output is truncated - detect incomplete code and continue generation 2. Built-in chunking strategy for large code generation tasks 3. Configurable token limit awareness in the agent ## Questions: - Is there a recommended way to handle long code generation? - Are there any built-in features I might be missing to mitigate this? - Would it be possible to add support for streaming/chunked code generation? Any guidance would be appreciated!
yindo commented 2026-02-16 06:16:58 -05:00
Author
Owner
Copy Link
Copy Source

@christian-bromann commented on GitHub (Feb 11, 2026):

@enteve thanks for reporting, I experienced the same and will take a look.

@christian-bromann commented on GitHub (Feb 11, 2026): @enteve thanks for reporting, I experienced the same and will take a look.
yindo commented 2026-02-16 06:16:58 -05:00
Author
Owner
Copy Link
Copy Source

@christian-bromann commented on GitHub (Feb 11, 2026):

@enteve which deepagents version are you using?

@christian-bromann commented on GitHub (Feb 11, 2026): @enteve which `deepagents` version are you using?
yindo commented 2026-02-16 06:16:58 -05:00
Author
Owner
Copy Link
Copy Source

@christian-bromann commented on GitHub (Feb 11, 2026):

Also, mind sharing the exact error message? I am getting this:

{"type":"error","error":{"type":"invalid_request_error","message":"prompt is too long: 219536 tokens > 200000 maximum"},"request_id":"req_011CY2kPwWtNt2aoncRPXh3B"}
@christian-bromann commented on GitHub (Feb 11, 2026): Also, mind sharing the exact error message? I am getting this: ``` {"type":"error","error":{"type":"invalid_request_error","message":"prompt is too long: 219536 tokens > 200000 maximum"},"request_id":"req_011CY2kPwWtNt2aoncRPXh3B"} ```
yindo commented 2026-02-16 06:16:59 -05:00
Author
Owner
Copy Link
Copy Source

@enteve commented on GitHub (Feb 11, 2026):

"deepagents": "^1.7.3"

i didn't keep the error message, i'll share the next time. it's not the prompt that exceeds the length. it's the output token. the error message contains something like

{"finish_reason": "length"}
@enteve commented on GitHub (Feb 11, 2026): "deepagents": "^1.7.3" i didn't keep the error message, i'll share the next time. it's not the prompt that exceeds the length. it's the output token. the error message contains something like ```json {"finish_reason": "length"} ```
yindo commented 2026-02-16 06:16:59 -05:00
Author
Owner
Copy Link
Copy Source

@arielb-oasis commented on GitHub (Feb 16, 2026):

Is there any solution? I dropped deepagents and went to Claude Claude because of limits I got each time even with file system middleware

@arielb-oasis commented on GitHub (Feb 16, 2026): Is there any solution? I dropped deepagents and went to Claude Claude because of limits I got each time even with file system middleware
yindo changed title from Code generation frequently stops mid-way due to output token limits to [GH-ISSUE #221] Code generation frequently stops mid-way due to output token limits 2026-06-05 17:21:10 -04:00
yindo closed this issue 2026-06-05 17:21:11 -04:00
yindo commented 2026-06-05 17:21:11 -04:00
Author
Owner
Copy Link
Copy Source

@christian-bromann commented on GitHub (Feb 18, 2026):

Yes @arielb-oasis we have a solution in #234 which we will ship tomorrow

<!-- gh-comment-id:3919071174 --> @christian-bromann commented on GitHub (Feb 18, 2026): Yes @arielb-oasis we have a solution in #234 which we will ship tomorrow
yindo commented 2026-06-05 17:21:11 -04:00
Author
Owner
Copy Link
Copy Source

@christian-bromann commented on GitHub (Feb 23, 2026):

We have shipped multiple improvements to the summarization middleware and our compaction process. This should hopefully resolve this issue, please let me know if it doesn't and I am happy to re-open. Thanks for all the input here!

<!-- gh-comment-id:3947382431 --> @christian-bromann commented on GitHub (Feb 23, 2026): We have shipped multiple improvements to the summarization middleware and our compaction process. This should hopefully resolve this issue, please let me know if it doesn't and I am happy to re-open. Thanks for all the input here!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
enhancement
help wanted
needs-response
pull-request
Mirrored from GitHub Pull Request
 stale
triage: high-impact
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/deepagentsjs#46
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?