Skip to content

Conversation

roomote[bot]
Copy link

@roomote roomote bot commented Jul 15, 2025

Summary

This PR fixes the max_tokens error for the moonshotai/kimi-k2-instruct model when using Groq as the provider.

Problem

Users were encountering the following error when using the moonshotai/kimi-k2-instruct model through Groq:

400 max_tokens must be less than or equal to 16384, the maximum value for max_tokens is less than the context_window for this model

Root Cause

The model configuration had maxTokens set to 8192, but Groq API allows up to 16,384 tokens for this specific model. The error occurred because Roo Code was setting max_tokens to a value that exceeded Groq's API limits for this model.

Solution

Updated the maxTokens value for moonshotai/kimi-k2-instruct from 8192 to 16384 in the Groq provider configuration to align with Groq's API limits.

Changes

  • Updated packages/types/src/providers/groq.ts:
    • Changed maxTokens from 8192 to 16384 for moonshotai/kimi-k2-instruct

Testing

  • ✅ All existing Groq provider tests pass
  • ✅ Type checking passes
  • ✅ Linting passes

Verification

The fix ensures that the max_tokens parameter sent to Groq API will be within the allowed limit of 16,384 tokens for the moonshotai/kimi-k2-instruct model.

Fixes #5739


Important

Fixes max_tokens error for moonshotai/kimi-k2-instruct on Groq by updating maxTokens to 16384 in groq.ts.

  • Behavior:
    • Fixes max_tokens error for moonshotai/kimi-k2-instruct model on Groq by updating maxTokens to 16384.
  • Configuration:
    • Updated maxTokens from 8192 to 16384 in groq.ts for moonshotai/kimi-k2-instruct.
  • Testing:
    • All existing Groq provider tests pass.
    • Type checking and linting pass.

This description was created by Ellipsis for ea4860a. You can customize this summary. It will automatically update as commits are pushed.

…6384

- Updated maxTokens from 8192 to 16384 for moonshotai/kimi-k2-instruct model
- Fixes Groq API error: "max_tokens must be less than or equal to 16384"
- Aligns with Groq API limits for this specific model

Fixes #5739
@roomote roomote bot requested review from mrubens, cte and jr as code owners July 15, 2025 12:53
@dosubot dosubot bot added size:XS This PR changes 0-9 lines, ignoring generated files. bug Something isn't working labels Jul 15, 2025
@dosubot dosubot bot added the lgtm This PR has been approved by a maintainer label Jul 15, 2025
@mrubens mrubens merged commit 29b7d06 into main Jul 15, 2025
22 checks passed
@mrubens mrubens deleted the fix/groq-kimi-k2-max-tokens branch July 15, 2025 12:56
@github-project-automation github-project-automation bot moved this from New to Done in Roo Code Roadmap Jul 15, 2025
@github-project-automation github-project-automation bot moved this from Triage to Done in Roo Code Roadmap Jul 15, 2025
fxcl added a commit to tameslabs/Roo-Cline that referenced this pull request Jul 16, 2025
* main:
  fix: Resolve confusing auto-approve checkbox states (RooCodeInc#5602)
  fix: prevent empty mode names from being saved (RooCodeInc#5766) (RooCodeInc#5794)
  Format time in ISO 8601 (RooCodeInc#5793)
  fix: resolve DirectoryScanner memory leak and improve file limit handling (RooCodeInc#5785)
  Fix settings dirty check (RooCodeInc#5779)
  feat: increase Ollama API timeout values and extract as constants (RooCodeInc#5778)
  fix: Exclude Terraform and Terragrunt cache directories from checkpoints (RooCodeInc#4601) (RooCodeInc#5750)
  Move less commonly used provider settings into an advanced dropdown (RooCodeInc#5762)
  feat: Add configurable error & repetition limit with unified control (RooCodeInc#5654) (RooCodeInc#5752)
  list-files must include at least the first-level directory contents (RooCodeInc#5303)
  Update evals repo link (RooCodeInc#5758)
  Feature/vertex ai model name conversion (RooCodeInc#5728)
  fix(litellm): handle baseurl with paths correctly (RooCodeInc#5697)
  Add telemetry for todos (RooCodeInc#5746)
  feat: add undo functionality for enhance prompt feature (fixes RooCodeInc#5741) (RooCodeInc#5742)
  Fix max_tokens limit for moonshotai/kimi-k2-instruct on Groq (RooCodeInc#5740)
  Changeset version bump (RooCodeInc#5735)
  Add changeset for v3.23.12 patch release (RooCodeInc#5734)
  Update the max-token calculation in model-params to use the shared logic (RooCodeInc#5720)
  Changeset version bump (RooCodeInc#5719)
  chore: add changeset for v3.23.11 patch release (RooCodeInc#5718)
  Add Kimi K2 model and better support (RooCodeInc#5717)
  Fix: Remove invalid skip-checkout parameter from GitHub Actions workflows (RooCodeInc#5676)
  feat: add Cmd+Shift+. keyboard shortcut for previous mode switching (RooCodeInc#5695)
  Changeset version bump (RooCodeInc#5708)
  chore: add changeset for v3.23.10 patch release (RooCodeInc#5707)
  Add padding to the index model options (RooCodeInc#5706)
  fix: prioritize built-in model dimensions over custom dimensions (RooCodeInc#5705)
  Update CHANGELOG.md
  Changeset version bump (RooCodeInc#5702)
  chore: add changeset for v3.23.9 patch release (RooCodeInc#5701)
  Tweaks to command timeout error (RooCodeInc#5700)
  Update contributors list (RooCodeInc#5639)
  feat: enable Claude Code provider to run natively on Windows (RooCodeInc#5615)
  feat: Add configurable timeout for command execution (RooCodeInc#5668)
  feat: add gemini-embedding-001 model to code-index service (RooCodeInc#5698)
  fix: resolve vector dimension mismatch error when switching embedding models (RooCodeInc#5616) (RooCodeInc#5617)
  fix: [5424] return the cwd in the exec tool's response so that the model is not lost after subsequent calls (RooCodeInc#5667)
  Changeset version bump (RooCodeInc#5670)
  chore: add changeset for v3.23.8 patch release (RooCodeInc#5669)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working lgtm This PR has been approved by a maintainer size:XS This PR changes 0-9 lines, ignoring generated files.
Projects
Status: Done
Development

Successfully merging this pull request may close these issues.

roocode with groq gives max_tokens error for kimi k2
1 participant