Jesse ZhangandClaude Opus 4.8 9b58bac621 Composer 2.5 Cursor "Fast": effort is Default, not a thinking budget ...

Cursor's Composer "Fast" is a serving tier (lower latency, higher cost, same
model intelligence) — not a reasoning-effort level. Drop the Fast/effort framing
entirely: effort is Default, notes just state a plain one-shot Composer 2.5 run.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-11 22:40:31 +01:00

..

claude-fable-5-cc.json

Rename Claude Code combination ids to the -cc suffix; refresh the Opus 4.8 mythos build

2026-06-10 23:07:51 +01:00

claude-fable-5-cursor.json

Register Claude Fable 5 × Cursor (High) (#7)

2026-06-11 20:24:48 +01:00

claude-fable-5.json

Contributor credits, SVG prefetch, integrate Xiaomi MiMo from PR #4

2026-06-10 13:03:01 +01:00

claude-opus-4-8-cc.json

Rename Claude Code combination ids to the -cc suffix; refresh the Opus 4.8 mythos build

2026-06-10 23:07:51 +01:00

composer-2-5-fast.json

Composer 2.5 Cursor "Fast": effort is Default, not a thinking budget

2026-06-11 22:40:31 +01:00

composer-2-5-grok-build.json

Set Composer 2.5 (Grok Build TUI) effort to Default, not blank

2026-06-11 16:00:39 +01:00

composer-2-5.json

Contributor credits, SVG prefetch, integrate Xiaomi MiMo from PR #4

2026-06-10 13:03:01 +01:00

deepseek-v4-pro.json

Contributor credits, SVG prefetch, integrate Xiaomi MiMo from PR #4

2026-06-10 13:03:01 +01:00

doubao-seed-2-0-mini.json

Contributor credits, SVG prefetch, integrate Xiaomi MiMo from PR #4

2026-06-10 13:03:01 +01:00

doubao-seed-2-0-pro.json

Contributor credits, SVG prefetch, integrate Xiaomi MiMo from PR #4

2026-06-10 13:03:01 +01:00

gemini-3-1-pro-aistudio.json

Split LpIuma's AI Studio Gemini runs into their own combinations; add PR template; register Kimi mythos run

2026-06-10 19:10:55 +01:00

gemini-3-1-pro.json

Split LpIuma's AI Studio Gemini runs into their own combinations; add PR template; register Kimi mythos run

2026-06-10 19:10:55 +01:00

gemini-3-5-flash-aistudio.json

Split LpIuma's AI Studio Gemini runs into their own combinations; add PR template; register Kimi mythos run

2026-06-10 19:10:55 +01:00

gemini-3-5-flash.json

Split LpIuma's AI Studio Gemini runs into their own combinations; add PR template; register Kimi mythos run

2026-06-10 19:10:55 +01:00

glm-5-1.json

Data-only contributions: per-model JSON registry, validation, PR CI

2026-06-10 11:48:18 +01:00

gpt-5-5-pro.json

Add GPT-5.5 Pro pelican run

2026-06-10 13:07:50 +01:00

gpt-5-5-xhigh.json

Rename the Codex CLI entry's model label back to GPT-5.5

2026-06-10 16:35:13 +01:00

grok-build.json

Add four pelican runs: Fable 5 (Claude Code), Grok Build, Kimi K2.6, MiniMax M3

2026-06-10 18:24:32 +01:00

kimi-k2-6.json

Correct Kimi Code effort to Thinking; standardize worker docs on bunx

2026-06-10 20:13:54 +01:00

minimax-m3.json

Add four pelican runs: Fable 5 (Claude Code), Grok Build, Kimi K2.6, MiniMax M3

2026-06-10 18:24:32 +01:00

mistral-medium-3-5.json

Data-only contributions: per-model JSON registry, validation, PR CI

2026-06-10 11:48:18 +01:00

qwen3-7-max.json

Data-only contributions: per-model JSON registry, validation, PR CI

2026-06-10 11:48:18 +01:00

xiaomi-mimo-v2-5-pro.json

Strip MiMo's embedded model name from its artifacts (blind-Arena identity leak)

2026-06-11 14:31:19 +01:00