fix: register DeepSeek V4 Flash for Bonk - #33255
Conversation
|
This pull request requires reviews from CODEOWNERS as it changes files that match the following patterns:
|
🚀 Deploying Preview to Cloudflare 🚀Preview URL: https://fix-register-deepseek-bonk.previews.developers.cloudflare.com (commit 9fa7d75)This URL reflects your latest Preview deploymentPreview Deployments by commit
|
|
/bonk review |
Review💡 1 suggestion found in commit 👉 Fix in your agent 👈Fix the following review findings in PR #33255 (https://github.com/cloudflare/cloudflare-docs/pull/33255).
Before making changes, review each finding and present a brief summary table:
- For each finding, state whether you agree, disagree, or need clarification
- If you disagree (e.g. the fix requires disproportionate effort for minimal benefit,
or the finding is factually incorrect), explain why
- If you need clarification before deciding, ask those questions
- Then share your plan for which issues to tackle and in what order
After triaging, follow this order:
1. Post a comment on this PR for any findings you are skipping, with the finding ID and your reasoning.
2. Then commit the fixes for the legitimate findings.
The comment must come before the commit — the bot reads PR comments when a new
push triggers a review, so skip comments posted after the push will be missed.
---
## Code Review
### Suggestions (1)
#### CR-5aff35ec8288 · Output limit equals full context window
- **File:** `opencode.jsonc` line 43
- **Issue:** The added GLM-4.7-Flash entry sets `limit.output: 131072`, the same as `limit.context`. The other models in this file cap output well below context (DeepSeek: 64000 with 1048576 context; Kimi: 64000 with 256000 context), and an output limit equal to the whole context is never reachable once any input tokens are present. This looks like the context value was copied into `output` by mistake.
- **Fix:** Verify GLM-4.7-Flash's actual max output on Workers AI and set `limit.output` to a realistic value (e.g. 64000, matching the other entries); an overestimated output cap can cause OpenCode to request `max_tokens` values the API rejects or to misestimate available output tokens.
Code ReviewThis code review is in beta and may not always be helpful — use your judgment. Suggestions (1)
ConventionsNo convention issues found. Style Guide ReviewNo style-guide issues found. CommandsOnly codeowners can run commands. Post a comment with the command to trigger it.
|
|
Preview URL: https://ed81de01.preview.developers.cloudflare.com |
| "options": { | ||
| "parallel_tool_calls": true, | ||
| }, | ||
| }, |
There was a problem hiding this comment.
Do we also need to add glm 4.7 flash? https://github.com/cloudflare/cloudflare-docs/blob/production/.github/workflows/bonk.yml#L78
Co-authored-by: mvvmm <mvvmm@users.noreply.github.com>
|
Yes — I've added it. Registered To be precise on "need": OpenCode resolves the |
wth I didn't know bonk could respond to and act on comments like this? Oh is it because bonk in the URL lol |
Summary
Registers DeepSeek V4 Flash in the OpenCode configuration so Bonk can resolve the model already selected by its workflow.
PR #33193, merged in commit
660c3cfa95, switched Bonk from Kimi K2.6 to DeepSeek V4 Flash. Although DeepSeek V4 Flash is available through Workers AI and AI Gateway, it was not registered in OpenCode 1.17.7's Cloudflare AI Gateway model catalog or the repository'sopencode.jsonc.As a result, OpenCode could not resolve the configured model when Bonk sent its first prompt. The run failed before inference and surfaced the model lookup failure as
share subscriber failedfollowed by exit code 1.This change explicitly defines the model's capabilities and limits in
opencode.jsonc, allowing Bonk to continue using DeepSeek V4 Flash.