Repository navigation
feat(opencode): Sol #low joins workhorse (cross-rung review) - #1247
Conversation
|
Warning Review limit reachedYou've used all free OSS reviews for now. Wait for the free limit to reset to keep reviewing this public repository. Next included review available in 3 minutes. View limit details
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
Adds
sol-plan#lowto workhorse, weight 2.Why (Drew, 2026-10-26 cross-rung review)
A higher family's low rung routinely beats the lower family's high rungs on intelligence and speed at once. Sol #low (AA v4.3.2: II 42, TTFT 2.9s, $0.13/task, the cheapest point on AA's cost frontier together with Sol #medium) dominates the pool's Luna #xhigh seat (35, 24.2s) on both axes. And per Drew: OpenAI is our largest quota — it will be spent regardless, so spend it on the family's elbow rung rather than its slow tail. In seats where multiple providers compete, DeepSeek Flash already covers Luna's cheap-fast niche.
Scope
luna-haiku-100kpool is untouched (its reason to exist is the sub-100k pricing band, not the seat quality).Validated: JSONC parses; target and weight asserted programmatically.
Need help on this PR? Tag
@codesmith-botwith what you need.