anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-08-24 06:33:01 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

Feature Request: Batch Read #1632

New Issue
Closed
opened 2026-02-16 17:31:50 -05:00 by yindo · 2 comments
yindo commented 2026-02-16 17:31:50 -05:00
Owner
Copy Link
Copy Source

Originally created by @Sewer56 on GitHub (Sep 6, 2025).

There was a similar issue in Roo Code, that contains more-less all the required core details, so I'm going to link it here:

The short version of the request is:

A tool that can read multiple files at once, as opposed to reading a single file at a time.

Additional Context

With the advent of faster models running on beefier hardware, tool call overhead begins to dominate during codebase investigation/discovery phases- such as when using the PLAN agent, or creating your own plan via a /slash command.

As prompt processing tends to run at 10s of thousands of tokens per second, even the mainstream models (e.g. Claude) can become severely slown down by unnecessarily alternating between input and output during discovery. After reading a file, the LLM will often decide it wants to read 3-4 more files, to investigate how existing code interacts with a component that needs to be modified- however, there is currently no native way to describe this. So precious seconds wind up wasted, and costs- for users without prompt caching.

Some of the super fast, low latency models/providers also contain rate limits, such as requests per minute or tokens per second. Cerebras in particular comes to mind, with 400k TPM and 30 RPS on the 'Pro' plan. (Recently increased, but still heavily limiting). The output is instant at around 1.5k-2.2k tokens/second, but the tool call overhead completely dominates the discovery phase.

[On a positive note, Cerebras' completions API started returning prompt caching directives "prompt_tokens_details":{"cached_tokens":0} last night- presumably, more details will be announced on Monday]

Other

Since this is a core feature, no PR attempt was made, per the instructions in the README informing us not to do so.

Originally created by @Sewer56 on GitHub (Sep 6, 2025). There was a similar issue in Roo Code, that contains more-less all the required core details, so I'm going to link it here: - https://github.com/RooCodeInc/Roo-Code/issues/3453 The short version of the request is: ``` A tool that can read multiple files at once, as opposed to reading a single file at a time. ``` ## Additional Context With the advent of faster models running on beefier hardware, tool call overhead begins to dominate during codebase investigation/discovery phases- such as when using the `PLAN` agent, or creating your own plan via a `/slash` command. As prompt processing tends to run at 10s of thousands of tokens per second, even the mainstream models (e.g. Claude) can become severely slown down by unnecessarily alternating between `input` and `output` during discovery. After reading a file, the LLM will often decide it wants to read 3-4 more files, to investigate how existing code interacts with a component that needs to be modified- however, there is currently no native way to describe this. So precious seconds wind up wasted, and costs- for users without prompt caching. Some of the super fast, low latency models/providers also contain rate limits, such as `requests per minute` or `tokens per second`. Cerebras in particular comes to mind, with 400k TPM and 30 RPS on the 'Pro' plan. (Recently increased, but still heavily limiting). The output is instant at around 1.5k-2.2k tokens/second, but the tool call overhead completely dominates the discovery phase. [On a positive note, Cerebras' completions API started returning prompt caching directives `"prompt_tokens_details":{"cached_tokens":0}` last night- presumably, more details will be announced on Monday] ## Other Since this is a core feature, no PR attempt was made, per the instructions in the README informing us not to do so.
yindo closed this issue 2026-02-16 17:31:50 -05:00
yindo commented 2026-02-16 17:31:50 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Sep 6, 2025):

This issue might be a duplicate of existing issues. Please check:

  • #1900: This issue specifically requests adding a batch read tool that can read multiple files at once, which matches your request for reading multiple files simultaneously to reduce tool call overhead.

Feel free to ignore if none of these address your specific case.

@github-actions[bot] commented on GitHub (Sep 6, 2025): This issue might be a duplicate of existing issues. Please check: - #1900: This issue specifically requests adding a batch read tool that can read multiple files at once, which matches your request for reading multiple files simultaneously to reduce tool call overhead. Feel free to ignore if none of these address your specific case.
yindo commented 2026-02-16 17:31:50 -05:00
Author
Owner
Copy Link
Copy Source

@Sewer56 commented on GitHub (Sep 6, 2025):

Thanks bot, I didn't originally find the duplicate 😅

@Sewer56 commented on GitHub (Sep 6, 2025): Thanks bot, I didn't originally find the duplicate 😅
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
acp
bad
bug
discussion
docs
documentation
enhancement
extension
good first issue
growth
help-wanted
mcp
model-problem
needs:compliance
nix
opentui
perf
pull-request
Mirrored from GitHub Pull Request
 tui
web
windows
zen
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: anomalyco/opencode#1632
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?