fix(alibaba/qwen3.7-plus): correct max output to 64K and tier size to 256K#2090
Open
coder-wangbin wants to merge 1 commit into
Open
fix(alibaba/qwen3.7-plus): correct max output to 64K and tier size to 256K#2090coder-wangbin wants to merge 1 commit into
coder-wangbin wants to merge 1 commit into
Conversation
- output: 16,384 → 65,536 (official max output is 64K) - tier.size: 128,000 → 256,000 (matches qwen3.6-plus tier threshold) Verified against official spec: https://bailian.console.aliyun.com/cn-beijing/?tab=model#/model-market/detail/qwen3.7-plus Context: 1M | Max Output: 64K | Modalities: text + image + video
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Fix two remaining incorrect parameters for
alibaba/qwen3.7-plusthat are still wrong on dev (context and modalities were already fixed by 977e2f0).Changes
limit.outputcost.tiers[0].tier.sizeqwen3.6-plustier thresholdWhy this matters
OpenCode reads models.dev for model capabilities. When
outputis set to 16K instead of 64K, it causes:Verification
After this fix,
qwen3.7-plusis structurally identical toqwen3.6-plus(excluding name/dates/knowledge), confirming they share the same Plus-tier architecture.Note: This PR only modifies
providers/alibaba/— no opencode-go changes.