omnilane 0.9.1 → 0.10.2

package/CHANGELOG.md

@@ -6,6 +6,57 @@ semantic version tags.
 
 ## [Unreleased]
 
+## [0.10.2] - 2026-07-26
+
+### Changed
+
+- Lowered the shipped Claude effort on `hardest-coding` and `hard-judgment`
+  from `max` to `xhigh`, matching Anthropic's documented guidance for Claude
+  Opus 5: start at `xhigh` for coding and agentic work, keep `high` as the
+  floor for other intelligence-sensitive work, and reserve `max` for cases
+  where correctness outweighs cost (it can show diminishing returns and
+  overthink simpler tasks). Raise it back per lane with
+  `omnilane configure set <lane> "<spec>"` if your workload needs it.
+
+### Fixed
+
+- Repaired two dead CHANGELOG compare links that pointed at a `v0.10.0` tag
+  which was never published. `0.10.1` now compares against `v0.9.1`, and
+  `0.10.0` points at its release commit.
+
+## [0.10.1] - 2026-07-26
+
+### Added
+
+- Added `claude-opus-5` to default routing as the first choice for
+  `hard-judgment` and `taste-final`, with a fallback position for the hardest
+  coding work.
+- Expanded `omnilane configure` across all 13 providers with 106 selectable
+  model entries. Codex, Claude Code, Grok Build, and Antigravity use their
+  current native catalogs; OpenRouter and OpenCode shortcuts were verified
+  against the live OpenRouter catalog. Custom model IDs remain available via
+  `c`.
+- Added the 2026-07-25 release summary to all five localized READMEs and
+  included `README.ja.md` in the NPM package.
+
+## [0.10.0] - 2026-07-22
+
+### Changed
+
+- Moved the default gemini candidates from Gemini 3.5 Flash to Gemini 3.6 Flash
+  (released 2026-07-21) in fast-agentic, triage, and bulk-mechanical, and
+  updated the Gemini Flash alias. Google reports 17% fewer output tokens at a
+  lower output price; Artificial Analysis measures Intelligence Index 50 and
+  the highest output speed on its leaderboard. The sibling releases are not
+  routable: 3.5 Flash-Lite is absent from the agy CLI and 3.5 Flash Cyber is a
+  restricted government/partner pilot. Refreshed the Gemini price table
+  (3.6 Flash $1.50/$7.50, 3.5 Flash $1.50/$9.00, 3.5 Flash-Lite $0.30/$2.50).
+- Re-audited model-routing evidence against current official sources, corrected
+  price/context facts for GPT-5.6, Claude 5, Gemini 3.x, Grok 4.5, and Kimi K3,
+  and aligned the canonical skill plus localized READMEs: Gemini 3.1 Pro is
+  agentic-capable, while Flash remains preferred for fast repeated loops.
+  Default route candidates and fallback order are unchanged.
+
 ## [0.9.1] - 2026-07-19
 
 ### Fixed
@@ -321,7 +372,10 @@ semantic version tags.
 - Initial shared routing table, cross-vendor dispatcher, runners, installer,
   and baseline lint fixes.
 
-[Unreleased]: https://github.com/Seraphim0916/omnilane/compare/v0.9.1...HEAD
+[Unreleased]: https://github.com/Seraphim0916/omnilane/compare/v0.10.2...HEAD
+[0.10.2]: https://github.com/Seraphim0916/omnilane/compare/v0.10.1...v0.10.2
+[0.10.1]: https://github.com/Seraphim0916/omnilane/compare/v0.9.1...v0.10.1
+[0.10.0]: https://github.com/Seraphim0916/omnilane/compare/v0.9.1...1ea55e5
 [0.9.1]: https://github.com/Seraphim0916/omnilane/compare/v0.9.0...v0.9.1
 [0.9.0]: https://github.com/Seraphim0916/omnilane/compare/v0.8.3...v0.9.0
 [0.8.3]: https://github.com/Seraphim0916/omnilane/compare/v0.8.2...v0.8.3

package/README.ja.md

@@ -21,6 +21,12 @@
 
 ---
 
+## 2026-07-25 更新
+
+- デフォルトルーティングに `claude-opus-5` を追加しました。`hard-judgment` と `taste-final` の第一候補となり、最難関のコーディング作業でもフォールバックとして利用できます。
+- `omnilane configure` を全 13 プロバイダーへ拡張しました。選択可能なモデルは 106 件で、Codex、Claude Code、Grok Build、Antigravity の最新カタログに加え、検証済みの OpenRouter／OpenCode ショートカットを収録しています。`c` によるカスタムモデル ID の入力も引き続き利用できます。
+
+---
 ## 👋 はじめての方へ
 
 すでに AI コーディングアシスタント——**Claude Code、Codex、Cursor、Gemini
@@ -36,6 +42,15 @@ CLI** など——を使っていますよね。どれも一度に一つの AI
 
 **[⬇ 60 秒クイックスタートへ](#-60-秒クイックスタート)**
 
+## v0.10.0 の新機能
+
+- **Gemini 3.6 Flash を既定に** — `fast-agentic`・`triage`・`bulk-mechanical`
+  の gemini 候補(および `Gemini Flash` エイリアス)を 2026-07-21 リリースの
+  Gemini 3.6 Flash に更新。出力トークンが減り、出力単価も下がり、Artificial
+  Analysis 計測の出力速度は首位です。
+- **エビデンス再監査** — ルーティングのコメント、モデル能力ノート、Gemini
+  価格表を公式ソースに合わせて更新(2026-07-21/22)。
+
 ## v0.9.1 の新機能
 
 - **修正**: `configure set` が `routing.local.yaml` の手書きコメントを削除しなく
@@ -83,7 +98,7 @@ flowchart LR
     M["メインループ<br/><i>任意の CLI</i>"] --> T{{"routing.yaml<br/>一枚の共有テーブル"}}
     T -->|hardest-coding| C1["Codex — GPT-5.6 Sol"]
     T -->|bulk-mechanical| C2["Codex — GPT-5.6 Terra"]
-    T -->|taste-final| C3["Claude — Opus 4.8"]
+    T -->|taste-final| C3["Claude — Opus 5"]
     T -->|long-context| C4["Gemini — 3.1 Pro"]
     T -->|live-search| C5["Grok — 4.5"]
     T -->|"arbitrate(オプトイン)"| C6["vote — 1-4 モデルパネル"]
@@ -115,15 +130,15 @@ flowchart LR
 
 | レーン | 第一候補 | バックアップ | 用途 |
 |---|---|---|---|
-| 🔥 hardest-coding | GPT-5.6 Sol (max) | Claude Opus 4.8 (xhigh) | 最難関の実装、根本原因デバッグ、正確性が要の変更 |
+| 🔥 hardest-coding | GPT-5.6 Sol (max) | Claude Opus 5 (xhigh) | 最難関の実装、根本原因デバッグ、正確性が要の変更 |
 | 🏗️ bulk-mechanical | GPT-5.6 Terra (max) | Claude Sonnet 5 (high) | リファクタ、移行、テスト、大規模スイープ |
-| 🧹 triage | GPT-5.6 Luna (medium) | Gemini 3.5 Flash (Low) | 大量の一次スクリーニング |
-| ⚖️ hard-judgment | GPT-5.6 Sol (max) | Claude Opus 4.8 (xhigh) | アーキテクチャ裁定、深い推論、セカンドオピニオン |
-| ✒️ taste-final | Claude Opus 4.8 (high) | GPT-5.6 Sol (max) | 対外文章、prompt/ドキュメント推敲、スタイル最終審 |
+| 🧹 triage | GPT-5.6 Luna (medium) | Gemini 3.6 Flash (Low) | 大量の一次スクリーニング |
+| ⚖️ hard-judgment | Claude Opus 5 (xhigh) | GPT-5.6 Sol (max) | アーキテクチャ裁定、深い推論、セカンドオピニオン |
+| ✒️ taste-final | Claude Opus 5 (high) | GPT-5.6 Sol (max) | 対外文章、prompt/ドキュメント推敲、スタイル最終審 |
 | 💬 consult | 明示指定したベンダー/モデル | —(フォールバックなし) | 自然言語で直接相談。`--vendor` を必ず維持 |
-| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude Opus 4.8 (high) | デザインシステム/参考画像がある場合の UI ドラフト |
-| 📚 long-context | Gemini 3.1 Pro (High) | Claude Opus 4.8 (high) | 100 万トークン級の長文統合——分析専用、agentic ループ禁止 |
-| ⚡ fast-agentic | Gemini 3.5 Flash (High) | GPT-5.6 Luna (high) | 高速なマルチステップ agentic ループ、マルチモーダル確認 |
+| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude Opus 5 (high) | デザインシステム/参考画像がある場合の UI ドラフト |
+| 📚 long-context | Gemini 3.1 Pro (High) | Claude Opus 5 (high) | 100 万トークン級の長文統合。Pro も agentic 対応、高速反復ループは Flash を優先 |
+| ⚡ fast-agentic | Gemini 3.6 Flash (High) | GPT-5.6 Luna (high) | 高速なマルチステップ agentic ループ、マルチモーダル確認 |
 | 📡 live-search | Grok 4.5 | —(off) | リアルタイム X/ウェブ検索とソーシャル文脈 |
 | 🚰 coding-overflow | Grok 4.5 | Kimi K3 → Qwen3 Coder Plus → OpenCode | Codex クォータ逼迫時の中級コーディング逃し弁 |
 | 🗳️ arbitrate | off(オプトイン) | — | 内蔵オピニオンパネル(重大な判断用)——デフォルト無効。`routing.local.yaml` で有効化;投票者×ラウンドごとに 1 コール消費 |
@@ -133,7 +148,9 @@ flowchart LR
 
 > **Claude Fable 5 はどこ?** 意図的にデフォルト表に入れていません:Claude の
 > 最上位ティアは通常*メインループ自身*であり、ディスパッチされるワーカーでは
-> ないため(価格も Opus より上)。設定メニューのモデル一覧には載っているので、
+> ないため(価格も Opus より上)。これはコスト/ガードレール/メインループ方針で
+> あり、能力評価ではありません。Anthropic は Fable 5 を Opus 5 より上位に
+> 位置付けています。設定メニューのモデル一覧には載っているので、
 > 使いたければ自分でルーティングできます(例:`routing.local.yaml` に
 > `taste-final: claude claude-fable-5 high`)。
 
@@ -162,11 +179,11 @@ flowchart LR
 該当行を自動適用します。これはその人間向けビューです。
 
 - **Claude Code · Fable 5** — 自分で実行:hard-judgment、taste-final、正確性が最重要の難修正。ディスパッチ:機械的コーディング量 → Codex、長文 → Gemini、リアルタイム検索 → Grok。
-- **Claude Code · Opus 4.8** — 自分で実行:taste-final。hard-judgment は Codex Sol へ(素の知能スコアが Opus より上)、コーディングは全て Codex レーン、長文 → Gemini、リアルタイム検索 → Grok。
+- **Claude Code · Opus 5** — 自分で実行：hard-judgment、taste-final。大量のコーディングは Codex レーン、長文 → Gemini、リアルタイム検索 → Grok。
 - **Codex · Sol** — 自分で実行:hardest-coding、hard-judgment、ui-draft。ディスパッチ:taste-final → Claude、長文 → Gemini、リアルタイム検索 → Grok、大量作業 → Codex Terra。
 - **Codex · Terra** — 自分で実行:bulk-mechanical。本当に最難関の部分は Sol へエスカレーション;taste → Claude、長文 → Gemini、リアルタイム検索 → Grok。
 - **Grok Build · Grok 4.5** — 自分で実行:live-search、coding-overflow(中級コーディング)。難しい作業は全て Codex/Claude/Gemini へ——先に全 API シグネチャと引用事実を検証。
-- **Antigravity · Gemini** — 自分で実行:long-context(3.1 Pro)、fast-agentic(Flash)。コーディング/判断/文章は Codex/Claude へ;リアルタイム検索 → Grok。3.1 Pro では agentic ツールループチェーンを決して受けない。
+- **Antigravity · Gemini** — 自分で実行:3.1 Pro で長文と重いコンテキストの agentic 作業、Flash で高速反復ループ。最難関のコーディング/判断/文章は Codex/Claude へ;リアルタイム検索 → Grok。
 
 </details>
 

package/README.ko.md

@@ -21,6 +21,12 @@
 
 ---
 
+## 2026-07-25 업데이트
+
+- 기본 라우팅에 `claude-opus-5`를 추가했습니다. `hard-judgment`와 `taste-final`의 첫 번째 선택이며, 가장 어려운 코딩 작업의 대체 경로로도 사용됩니다.
+- `omnilane configure`를 13개 전체 제공자로 확장했습니다. 선택 가능한 모델은 106개이며 Codex, Claude Code, Grok Build, Antigravity의 최신 카탈로그와 검증된 OpenRouter／OpenCode 바로가기를 포함합니다. `c`를 통한 사용자 지정 모델 ID 입력도 계속 지원합니다.
+
+---
 ## 👋 처음이신가요?
 
 이미 AI 코딩 어시스턴트——**Claude Code, Codex, Cursor, Gemini CLI** 같은——를 쓰고
@@ -35,6 +41,15 @@
 
 **[⬇ 60초 시작으로](#-60초-시작)**
 
+## v0.10.0 새 기능
+
+- **Gemini 3.6 Flash 기본 라우팅** — `fast-agentic`, `triage`,
+  `bulk-mechanical` 의 gemini 후보(그리고 `Gemini Flash` 별칭)를 2026-07-21
+  출시된 Gemini 3.6 Flash 로 변경: 출력 토큰 감소, 출력 단가 인하, Artificial
+  Analysis 측정 출력 속도 1위.
+- **근거 재감사** — 라우팅 주석, 모델 능력 노트, Gemini 가격표를 공식 소스에
+  맞춰 갱신 (2026-07-21/22).
+
 ## v0.9.1 새 기능
 
 - **수정**: `configure set` 이 더 이상 `routing.local.yaml` 의 수기 주석을
@@ -82,7 +97,7 @@ flowchart LR
     M["메인 루프<br/><i>아무 CLI</i>"] --> T{{"routing.yaml<br/>공유 테이블 하나"}}
     T -->|hardest-coding| C1["Codex — GPT-5.6 Sol"]
     T -->|bulk-mechanical| C2["Codex — GPT-5.6 Terra"]
-    T -->|taste-final| C3["Claude — Opus 4.8"]
+    T -->|taste-final| C3["Claude — Opus 5"]
     T -->|long-context| C4["Gemini — 3.1 Pro"]
     T -->|live-search| C5["Grok — 4.5"]
     T -->|"arbitrate(옵트인)"| C6["vote — 1-4 모델 패널"]
@@ -113,15 +128,15 @@ flowchart LR
 
 | 레인 | 1순위 모델 | 백업 | 용도 |
 |---|---|---|---|
-| 🔥 hardest-coding | GPT-5.6 Sol (max) | Claude Opus 4.8 (xhigh) | 가장 어려운 구현, 근본 원인 디버깅, 정확성이 핵심인 수정 |
+| 🔥 hardest-coding | GPT-5.6 Sol (max) | Claude Opus 5 (xhigh) | 가장 어려운 구현, 근본 원인 디버깅, 정확성이 핵심인 수정 |
 | 🏗️ bulk-mechanical | GPT-5.6 Terra (max) | Claude Sonnet 5 (high) | 리팩터링, 마이그레이션, 테스트, 대량 스윕 |
-| 🧹 triage | GPT-5.6 Luna (medium) | Gemini 3.5 Flash (Low) | 대량 1차 선별 |
-| ⚖️ hard-judgment | GPT-5.6 Sol (max) | Claude Opus 4.8 (xhigh) | 아키텍처 중재, 깊은 추론, 세컨드 오피니언 |
-| ✒️ taste-final | Claude Opus 4.8 (high) | GPT-5.6 Sol (max) | 대외 문장, prompt/문서 다듬기, 스타일 최종심 |
+| 🧹 triage | GPT-5.6 Luna (medium) | Gemini 3.6 Flash (Low) | 대량 1차 선별 |
+| ⚖️ hard-judgment | Claude Opus 5 (xhigh) | GPT-5.6 Sol (max) | 아키텍처 중재, 깊은 추론, 세컨드 오피니언 |
+| ✒️ taste-final | Claude Opus 5 (high) | GPT-5.6 Sol (max) | 대외 문장, prompt/문서 다듬기, 스타일 최종심 |
 | 💬 consult | 명시적으로 지정한 벤더/모델 | —(폴백 없음) | 자연어 직접 상담. `--vendor` 를 반드시 유지 |
-| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude Opus 4.8 (high) | 디자인 시스템/참고 이미지가 있을 때의 UI 초안 |
-| 📚 long-context | Gemini 3.1 Pro (High) | Claude Opus 4.8 (high) | 100만 토큰급 장문 통합——분석 전용, agentic 루프 금지 |
-| ⚡ fast-agentic | Gemini 3.5 Flash (High) | GPT-5.6 Luna (high) | 빠른 멀티스텝 agentic 루프, 멀티모달 확인 |
+| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude Opus 5 (high) | 디자인 시스템/참고 이미지가 있을 때의 UI 초안 |
+| 📚 long-context | Gemini 3.1 Pro (High) | Claude Opus 5 (high) | 100만 토큰급 장문 통합. Pro 도 agentic 지원, 빠른 반복 루프는 Flash 우선 |
+| ⚡ fast-agentic | Gemini 3.6 Flash (High) | GPT-5.6 Luna (high) | 빠른 멀티스텝 agentic 루프, 멀티모달 확인 |
 | 📡 live-search | Grok 4.5 | —(off) | 실시간 X/웹 검색과 소셜 맥락 |
 | 🚰 coding-overflow | Grok 4.5 | Kimi K3 → Qwen3 Coder Plus → OpenCode | Codex 쿼터 소진 시 중급 코딩 안전 밸브 |
 | 🗳️ arbitrate | off(옵트인) | — | 내장 의견 패널(중대한 결정용)——기본 비활성. `routing.local.yaml` 에서 활성화;투표자×라운드마다 1콜 소모 |
@@ -131,7 +146,9 @@ flowchart LR
 
 > **Claude Fable 5 는 어디에?** 의도적으로 기본 테이블에 넣지 않았습니다:
 > Claude 최상위 티어는 보통 *메인 루프 자신*이지 디스패치되는 워커가 아니며,
-> 가격도 Opus 보다 높습니다. 설정 메뉴의 모델 목록에는 있으니 원하면 직접
+> 가격도 Opus 보다 높습니다. 이는 비용/가드레일/메인 루프 정책이며 능력 평가가
+> 아닙니다. Anthropic 은 Fable 5 를 Opus 5 보다 상위에 둡니다. 설정 메뉴의
+> 모델 목록에는 있으니 원하면 직접
 > 라우팅하세요(예: `routing.local.yaml` 에
 > `taste-final: claude claude-fable-5 high`).
 
@@ -160,11 +177,11 @@ flowchart LR
 행을 자동 적용하며, 이것은 사람이 보는 버전입니다.
 
 - **Claude Code · Fable 5** — 직접 실행: hard-judgment, taste-final, 정확성이 최우선인 난이도 높은 수정. 디스패치: 기계적 코딩 물량 → Codex, 장문 → Gemini, 실시간 검색 → Grok.
-- **Claude Code · Opus 4.8** — 직접 실행: taste-final. hard-judgment 은 Codex Sol 로(순수 지능 점수가 Opus 보다 높음), 모든 코딩은 Codex 레인, 장문 → Gemini, 실시간 검색 → Grok.
+- **Claude Code · Opus 5** 직접 실행: hard-judgment, taste-final. 대량 코딩은 Codex 레인, 장문 → Gemini, 실시간 검색 → Grok.
 - **Codex · Sol** — 직접 실행: hardest-coding, hard-judgment, ui-draft. 디스패치: taste-final → Claude, 장문 → Gemini, 실시간 검색 → Grok, 대량 작업 → Codex Terra.
 - **Codex · Terra** — 직접 실행: bulk-mechanical. 정말 가장 어려운 부분은 Sol 로 에스컬레이션; taste → Claude, 장문 → Gemini, 실시간 검색 → Grok.
 - **Grok Build · Grok 4.5** — 직접 실행: live-search, coding-overflow(중급 코딩). 어려운 작업은 모두 Codex/Claude/Gemini 로——먼저 모든 API 시그니처와 인용 사실을 검증.
-- **Antigravity · Gemini** — 직접 실행: long-context(3.1 Pro), fast-agentic(Flash). 코딩/판단/문장은 Codex/Claude 로; 실시간 검색 → Grok. 3.1 Pro 에서는 agentic 툴 루프 체인을 절대 맡지 않음.
+- **Antigravity · Gemini** — 직접 실행: 3.1 Pro 로 장문과 무거운 컨텍스트의 agentic 작업, Flash 로 빠른 반복 루프. 가장 어려운 코딩/판단/문장은 Codex/Claude 로; 실시간 검색 → Grok.
 
 </details>
 

package/README.md

@@ -21,6 +21,12 @@ or any hosted model via OpenRouter — on the subscriptions you already pay for,
 
 ---
 
+## 2026-07-25 update
+
+- Added `claude-opus-5` to default routing: first choice for `hard-judgment` and `taste-final`, plus a fallback for the hardest coding work.
+- Expanded `omnilane configure` across all 13 providers: 106 selectable model entries, complete live catalogs for Codex, Claude Code, Grok Build, and Antigravity, plus verified OpenRouter/OpenCode shortcuts. Custom model IDs remain available through `c`.
+
+---
 ## 👋 New here?
 
 You already drive an AI coding assistant — **Claude Code, Codex, Cursor, Gemini
@@ -36,6 +42,15 @@ and `./install.sh --uninstall` removes it cleanly.
 
 **[⬇ Jump to the 60-second start](#-60-second-start)**
 
+## What's new in v0.10.0
+
+- **Gemini 3.6 Flash defaults** — the gemini candidates in `fast-agentic`,
+  `triage`, and `bulk-mechanical` (and the `Gemini Flash` alias) now run
+  Gemini 3.6 Flash (released 2026-07-21): fewer output tokens, a lower output
+  price, and the fastest output speed measured by Artificial Analysis.
+- **Evidence re-audit** — routing comments, model capability notes, and the
+  Gemini price table refreshed against official sources (2026-07-21/22).
+
 ## What's new in v0.9.1
 
 - **Fix:** `configure set` no longer deletes hand-written comments from
@@ -84,7 +99,7 @@ flowchart LR
     M["main loop<br/><i>any CLI you drive</i>"] --> T{{"routing.yaml<br/>one shared table"}}
     T -->|hardest-coding| C1["Codex — GPT-5.6 Sol"]
     T -->|bulk-mechanical| C2["Codex — GPT-5.6 Terra"]
-    T -->|taste-final| C3["Claude — Opus 4.8"]
+  T -->|taste-final| C3["Claude — Opus 5"]
     T -->|long-context| C4["Gemini — 3.1 Pro"]
     T -->|live-search| C5["Grok — 4.5"]
     T -->|"arbitrate (opt-in)"| C6["vote — 1-4 model panel"]
@@ -116,15 +131,15 @@ flowchart LR
 
 | Lane | First choice | Backup | When |
 |---|---|---|---|
-| 🔥 hardest-coding | GPT-5.6 Sol (max) | Claude Opus 4.8 (xhigh) | Hardest implementation, deep root-cause debug, correctness-critical edits |
+| 🔥 hardest-coding | GPT-5.6 Sol (max) | Claude Opus 5 (xhigh) | Hardest implementation, deep root-cause debug, correctness-critical edits |
 | 🏗️ bulk-mechanical | GPT-5.6 Terra (max) | Claude Sonnet 5 (high) | Refactors, migrations, tests, review sweeps — mechanical endurance |
-| 🧹 triage | GPT-5.6 Luna (medium) | Gemini 3.5 Flash (Low) | High-volume scans, first-pass filtering |
-| ⚖️ hard-judgment | GPT-5.6 Sol (max) | Claude Opus 4.8 (xhigh) | Architecture arbitration, deep reasoning, second opinions |
-| ✒️ taste-final | Claude Opus 4.8 (high) | GPT-5.6 Sol (max) | User-facing prose, prompt/doc polish, style arbitration |
+| 🧹 triage | GPT-5.6 Luna (medium) | Gemini 3.6 Flash (Low) | High-volume scans, first-pass filtering |
+| ⚖️ hard-judgment | Claude Opus 5 (xhigh) | GPT-5.6 Sol (max) | Architecture arbitration, deep reasoning, second opinions |
+| ✒️ taste-final | Claude Opus 5 (high) | GPT-5.6 Sol (max) | User-facing prose, prompt/doc polish, style arbitration |
 | 💬 consult | Explicit named vendor/model | — (no fallback) | Direct natural-language consultation; always keep `--vendor` |
-| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude Opus 4.8 (high) | UI drafts only WITH a design system / reference images |
-| 📚 long-context | Gemini 3.1 Pro (High) | Claude Opus 4.8 (high) | 1M-token synthesis — analysis only, never agentic loops |
-| ⚡ fast-agentic | Gemini 3.5 Flash (High) | GPT-5.6 Luna (high) | Fast multi-step agentic loops, multimodal checks |
+| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude Opus 5 (high) | UI drafts only WITH a design system / reference images |
+| 📚 long-context | Gemini 3.1 Pro (High) | Claude Opus 5 (high) | 1M-token synthesis; Pro is agentic-capable, while fast repeated loops prefer Flash |
+| ⚡ fast-agentic | Gemini 3.6 Flash (High) | GPT-5.6 Luna (high) | Fast multi-step agentic loops, multimodal checks |
 | 📡 live-search | Grok 4.5 | — (off) | Realtime X/web search and social context |
 | 🚰 coding-overflow | Grok 4.5 | Kimi K3 → Qwen3 Coder Plus → OpenCode | Codex-quota relief valve for mid-tier coding |
 | 🗳️ arbitrate | off (opt-in vote panel) | — | Built-in opinion panel for big calls — disabled by default; enable it in `routing.local.yaml`, one call per voter per round |
@@ -135,7 +150,9 @@ lane is such a chain; when nothing in it is installed the lane degrades to `off`
 
 > **Where is Claude Fable 5?** Deliberately not in the defaults: the top
 > Claude tier is usually the *main loop itself*, not a dispatched worker, and
-> it prices above Opus. It is offered in the configurator's model menu —
+> it prices above Opus. This is a cost / guardrail / main-loop policy choice,
+> not a capability verdict; Anthropic positions Fable 5 above Opus 5. It is
+> offered in the configurator's model menu —
 > route to it if you disagree (e.g. `taste-final: claude claude-fable-5 high`
 > in `routing.local.yaml`).
 
@@ -163,11 +180,11 @@ already are that model, so no second call) versus **dispatch**. Your harness's
 `omnilane` skill applies the right row automatically; this is the human view.
 
 - **Claude Code · Fable 5** — self-execute: hard-judgment, taste-final, the hardest correctness-critical fixes. Dispatch mechanical coding volume → Codex, long-context → Gemini, live-search → Grok.
-- **Claude Code · Opus 4.8** — self-execute: taste-final. Dispatch hard-judgment to Codex Sol (it out-scores Opus on raw intelligence), all coding to the Codex lanes, long-context → Gemini, live-search → Grok.
+- **Claude Code · Opus 5** — self-execute: hard-judgment and taste-final. Dispatch bulk coding to Codex lanes, long-context → Gemini, live-search → Grok.
 - **Codex · Sol** — self-execute: hardest-coding, hard-judgment, ui-draft. Dispatch taste-final → Claude, long-context → Gemini, live-search → Grok, bulk → Codex Terra.
 - **Codex · Terra** — self-execute: bulk-mechanical. Escalate the genuinely hardest pieces to Sol; dispatch taste → Claude, long-context → Gemini, live-search → Grok.
 - **Grok Build · Grok 4.5** — self-execute: live-search, coding-overflow (mid-tier coding). Dispatch everything hard to Codex/Claude/Gemini — and verify every API signature and cited fact first.
-- **Antigravity · Gemini** — self-execute: long-context (3.1 Pro) and fast-agentic (Flash). Dispatch coding/judgment/taste to Codex/Claude; live-search → Grok. Never take agentic tool-loop chains on 3.1 Pro.
+- **Antigravity · Gemini** — self-execute: long-context and context-heavy agentic work on 3.1 Pro, fast repeated loops on Flash. Dispatch hardest coding/judgment/taste to Codex/Claude; live-search → Grok.
 
 </details>
 

package/README.zh-CN.md

@@ -21,6 +21,12 @@
 
 ---
 
+## 2026-07-25 更新
+
+- 默认路由加入 `claude-opus-5`：成为 `hard-judgment`、`taste-final` 第一顺位，也纳入最高难度编程任务的备选。
+- `omnilane configure` 已扩展全部 13 个提供商：共 106 个可选模型，完整收录 Codex、Claude Code、Grok Build、Antigravity 实时列表，并加入已验证的 OpenRouter／OpenCode 快捷项；仍可用 `c` 输入自定义模型 ID。
+
+---
 ## 👋 第一次用?
 
 你已经在用某个 AI 写程式助手——**Claude Code、Codex、Cursor、Gemini
@@ -33,6 +39,14 @@ CLI** 之类。每个一次只接一个 AI 模型,而「每件工作该用哪个
 
 **[⬇ 直接跳到 60 秒上手](#-60-秒上手)**
 
+## v0.10.0 新功能
+
+- **Gemini 3.6 Flash 默认路由**——`fast-agentic`、`triage`、`bulk-mechanical`
+  的 gemini 候选(与 `Gemini Flash` 别名)改用 2026-07-21 发布的 Gemini 3.6
+  Flash:输出 token 更少、输出单价更低、Artificial Analysis 实测输出速度第一。
+- **证据重审计**——路由注释、模型能力笔记与 Gemini 价格表对官方来源刷新
+  (2026-07-21/22)。
+
 ## v0.9.1 新功能
 
 - **修复**:`configure set` 不再删除 `routing.local.yaml` 中手写的注释——
@@ -76,7 +90,7 @@ flowchart LR
     M["主循环<br/><i>你在用的任一 CLI</i>"] --> T{{"routing.yaml<br/>一张共用路由表"}}
     T -->|hardest-coding| C1["Codex — GPT-5.6 Sol"]
     T -->|bulk-mechanical| C2["Codex — GPT-5.6 Terra"]
-    T -->|taste-final| C3["Claude — Opus 4.8"]
+    T -->|taste-final| C3["Claude — Opus 5"]
     T -->|long-context| C4["Gemini — 3.1 Pro"]
     T -->|live-search| C5["Grok — 4.5"]
     T -->|"arbitrate(可选)"| C6["vote — 1-4 模型评审团"]
@@ -105,15 +119,15 @@ flowchart LR
 
 | 通道 | 首选模型 | 备选模型 | 用途 |
 |---|---|---|---|
-| 🔥 hardest-coding | GPT-5.6 Sol (max) | Claude Opus 4.8 (xhigh) | 最难的实现、深度调试、正确性攸关的修改 |
+| 🔥 hardest-coding | GPT-5.6 Sol (max) | Claude Opus 5 (xhigh) | 最难的实现、深度调试、正确性攸关的修改 |
 | 🏗️ bulk-mechanical | GPT-5.6 Terra (max) | Claude Sonnet 5 (high) | 重构、迁移、测试、大面积扫描——机械耐力活 |
-| 🧹 triage | GPT-5.6 Luna (medium) | Gemini 3.5 Flash (Low) | 高量初筛、第一轮过滤 |
-| ⚖️ hard-judgment | GPT-5.6 Sol (max) | Claude Opus 4.8 (xhigh) | 架构仲裁、深度推理、第二意见 |
-| ✒️ taste-final | Claude Opus 4.8 (high) | GPT-5.6 Sol (max) | 对外文字、prompt 与文档打磨、风格终审 |
+| 🧹 triage | GPT-5.6 Luna (medium) | Gemini 3.6 Flash (Low) | 高量初筛、第一轮过滤 |
+| ⚖️ hard-judgment | Claude Opus 5 (xhigh) | GPT-5.6 Sol (max) | 架构仲裁、深度推理、第二意见 |
+| ✒️ taste-final | Claude Opus 5 (high) | GPT-5.6 Sol (max) | 对外文字、prompt 与文档打磨、风格终审 |
 | 💬 consult | 明确指定的厂商/模型 | —(不降级) | 自然语言直接咨询;必须保留 `--vendor` |
-| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude Opus 4.8 (high) | 有设计规范/参考图时的 UI 出稿;开放式视觉品味交给 taste-final |
-| 📚 long-context | Gemini 3.1 Pro (High) | Claude Opus 4.8 (high) | 百万 token 长文整合——仅限分析,不派 agentic 长链 |
-| ⚡ fast-agentic | Gemini 3.5 Flash (High) | GPT-5.6 Luna (high) | 快速多步骤 agentic 循环、多模态检查 |
+| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude Opus 5 (high) | 有设计规范/参考图时的 UI 出稿;开放式视觉品味交给 taste-final |
+| 📚 long-context | Gemini 3.1 Pro (High) | Claude Opus 5 (high) | 百万 token 长文整合;Pro 可跑 agentic 工作,高速重复循环仍优先 Flash |
+| ⚡ fast-agentic | Gemini 3.6 Flash (High) | GPT-5.6 Luna (high) | 快速多步骤 agentic 循环、多模态检查 |
 | 📡 live-search | Grok 4.5 | —(off) | 实时 X/网络搜索与社群脉络 |
 | 🚰 coding-overflow | Grok 4.5 | Kimi K3 → Qwen3 Coder Plus → OpenCode | Codex 额度吃紧时的中量级编码溢流道;事实性声明须另行查证 |
 | 🗳️ arbitrate | off(可选评审团) | — | 内置意见评审团,重大决定用——默认关闭,要用在 `routing.local.yaml` 打开;每评审每轮烧一次额度 |
@@ -121,7 +135,8 @@ flowchart LR
 **备选模型**是候选链的下一位——首选那家的厂商 CLI 没装时,派发就降到它。
 
 > **Claude Fable 5 去哪了?** 默认表刻意不放:Claude 顶级档通常就是*主循环本人*,
-> 不是被派发的工人,且定价高于 Opus。设置菜单的模型清单里有它——
+> 不是被派发的工人,且定价高于 Opus。这是成本/护栏/主循环策略,不代表能力
+> 不如 Opus;Anthropic 将 Fable 5 定位在 Opus 5 之上。设置菜单的模型清单里有它——
 > 不同意就自己路由过去(例如在 `routing.local.yaml` 写
 > `taste-final: claude claude-fable-5 high`)。
 
@@ -145,11 +160,11 @@ flowchart LR
 的 `omnilane` 技能会自动套对的那一行,这里是给人看的版本。
 
 - **Claude Code · Fable 5** — 自己做:hard-judgment、taste-final、最吃正确性的硬修。派出去:机械编码量 → Codex、长文 → Gemini、实时搜索 → Grok。
-- **Claude Code · Opus 4.8** — 自己做:taste-final。hard-judgment 派给 Codex Sol(智力分高于 Opus)、所有编码走 Codex 通道、长文 → Gemini、实时搜索 → Grok。
+- **Claude Code · Opus 5** — 自己做：hard-judgment、taste-final。大量编码走 Codex 通道、长文 → Gemini、实时搜索 → Grok。
 - **Codex · Sol** — 自己做:hardest-coding、hard-judgment、ui-draft。派出去:taste-final → Claude、长文 → Gemini、实时搜索 → Grok、粗活 → Codex Terra。
 - **Codex · Terra** — 自己做:bulk-mechanical。真正最硬的往上升给 Sol;taste → Claude、长文 → Gemini、实时搜索 → Grok。
 - **Grok Build · Grok 4.5** — 自己做:live-search、coding-overflow(中量级编码)。所有硬活派给 Codex/Claude/Gemini——先验每个 API 签名与引用事实。
-- **Antigravity · Gemini** — 自己做:long-context(3.1 Pro)、fast-agentic(Flash)。编码/判断/文字派给 Codex/Claude;实时搜索 → Grok。3.1 Pro 绝不接 agentic 工具长链。
+- **Antigravity · Gemini** — 自己做:3.1 Pro 的长文与重上下文 agentic 工作、Flash 的高速重复循环。最难的编码/判断/文字派给 Codex/Claude;实时搜索 → Grok。
 
 </details>
 

package/README.zh-TW.md

@@ -21,6 +21,12 @@
 
 ---
 
+## 2026-07-25 更新
+
+- 預設路由加入 `claude-opus-5`：成為 `hard-judgment`、`taste-final` 第一順位，也納入最高難度程式任務的備援。
+- `omnilane configure` 已擴充全部 13 個供應商：共 106 個可選模型，完整收錄 Codex、Claude Code、Grok Build、Antigravity 即時清單，並加入已驗證的 OpenRouter／OpenCode 捷徑；仍可用 `c` 輸入自訂模型 ID。
+
+---
 ## 👋 第一次用?
 
 你已經在用某個 AI 寫程式助手——**Claude Code、Codex、Cursor、Gemini
@@ -33,6 +39,14 @@ CLI** 之類。每個一次只接一個 AI 模型,而「每件工作該用哪個
 
 **[⬇ 直接跳到 60 秒上手](#-60-秒上手)**
 
+## v0.10.0 新功能
+
+- **Gemini 3.6 Flash 預設路由**——`fast-agentic`、`triage`、`bulk-mechanical`
+  的 gemini 候選(與 `Gemini Flash` 別名)改用 2026-07-21 發布的 Gemini 3.6
+  Flash:輸出 token 更少、輸出單價更低、Artificial Analysis 實測輸出速度第一。
+- **證據重稽核**——路由註解、模型能力筆記與 Gemini 價格表對官方來源刷新
+  (2026-07-21/22)。
+
 ## v0.9.1 新功能
 
 - **修正**:`configure set` 不再刪掉 `routing.local.yaml` 裡手寫的註解——
@@ -79,7 +93,7 @@ flowchart LR
     M["主迴圈<br/><i>你在用的任一 CLI</i>"] --> T{{"routing.yaml<br/>一張共用路由表"}}
     T -->|hardest-coding| C1["Codex — GPT-5.6 Sol"]
     T -->|bulk-mechanical| C2["Codex — GPT-5.6 Terra"]
-    T -->|taste-final| C3["Claude — Opus 4.8"]
+  T -->|taste-final| C3["Claude — Opus 5"]
     T -->|long-context| C4["Gemini — 3.1 Pro"]
     T -->|live-search| C5["Grok — 4.5"]
     T -->|"arbitrate(選配)"| C6["vote — 1-4 模型評審團"]
@@ -108,15 +122,15 @@ flowchart LR
 
 | 通道 | 首選模型 | 備選模型 | 用途 |
 |---|---|---|---|
-| 🔥 hardest-coding | GPT-5.6 Sol (max) | Claude Opus 4.8 (xhigh) | 最難的實作、深度除錯、正確性攸關的修改 |
+| 🔥 hardest-coding | GPT-5.6 Sol (max) | Claude Opus 5 (xhigh) | 最難的實作、深度除錯、正確性攸關的修改 |
 | 🏗️ bulk-mechanical | GPT-5.6 Terra (max) | Claude Sonnet 5 (high) | 重構、搬遷、測試、大面積掃描——機械耐力活 |
-| 🧹 triage | GPT-5.6 Luna (medium) | Gemini 3.5 Flash (Low) | 高量初篩、第一輪過濾 |
-| ⚖️ hard-judgment | GPT-5.6 Sol (max) | Claude Opus 4.8 (xhigh) | 架構仲裁、深度推理、第二意見 |
-| ✒️ taste-final | Claude Opus 4.8 (high) | GPT-5.6 Sol (max) | 對外文字、prompt 與文件打磨、風格終審 |
+| 🧹 triage | GPT-5.6 Luna (medium) | Gemini 3.6 Flash (Low) | 高量初篩、第一輪過濾 |
+| ⚖️ hard-judgment | Claude Opus 5 (xhigh) | GPT-5.6 Sol (max) | 架構仲裁、深度推理、第二意見 |
+| ✒️ taste-final | Claude Opus 5 (high) | GPT-5.6 Sol (max) | 對外文字、prompt 與文件打磨、風格終審 |
 | 💬 consult | 明確點名的廠商/模型 | —(不降級) | 自然語言直接諮詢;必須保留 `--vendor` |
-| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude Opus 4.8 (high) | 有設計規範/參考圖時的 UI 出稿;開放式視覺品味交給 taste-final |
-| 📚 long-context | Gemini 3.1 Pro (High) | Claude Opus 4.8 (high) | 百萬 token 長文整合——僅限分析,不派 agentic 長鏈 |
-| ⚡ fast-agentic | Gemini 3.5 Flash (High) | GPT-5.6 Luna (high) | 快速多步驟 agentic 迴圈、多模態檢查 |
+| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude Opus 5 (high) | 有設計規範/參考圖時的 UI 出稿;開放式視覺品味交給 taste-final |
+| 📚 long-context | Gemini 3.1 Pro (High) | Claude Opus 5 (high) | 百萬 token 長文整合;Pro 可跑 agentic 工作,高速重複迴圈仍優先 Flash |
+| ⚡ fast-agentic | Gemini 3.6 Flash (High) | GPT-5.6 Luna (high) | 快速多步驟 agentic 迴圈、多模態檢查 |
 | 📡 live-search | Grok 4.5 | —(off) | 即時 X/網路搜尋與社群脈絡 |
 | 🚰 coding-overflow | Grok 4.5 | Kimi K3 → Qwen3 Coder Plus → OpenCode | Codex 額度吃緊時的中量級編碼溢流道;事實性宣稱須另行查證 |
 | 🗳️ arbitrate | off(選配評審團) | — | 內建意見評審團,重大決定用——預設關閉,要用在 `routing.local.yaml` 開;每評審每輪燒一次額度 |
@@ -124,7 +138,8 @@ flowchart LR
 **備選模型**是候選鏈的下一位——首選那家的廠商 CLI 沒裝時,派工就降到它。
 
 > **Claude Fable 5 去哪了?** 預設表刻意不放:Claude 頂級檔通常就是*主迴圈本人*,
-> 不是被派發的工人,而且定價高於 Opus。設定選單的模型清單有列它——
+> 不是被派發的工人,而且定價高於 Opus。這是成本/護欄/主迴圈策略,不代表能力
+> 不如 Opus;Anthropic 將 Fable 5 定位在 Opus 5 之上。設定選單的模型清單有列它——
 > 不同意就自己路由過去(例如在 `routing.local.yaml` 寫
 > `taste-final: claude claude-fable-5 high`)。
 
@@ -148,11 +163,11 @@ flowchart LR
 的 `omnilane` 技能會自動套對的那一列,這裡是給人看的版本。
 
 - **Claude Code · Fable 5** — 自己做:hard-judgment、taste-final、最吃正確性的硬修。派出去:機械編碼量 → Codex、長文 → Gemini、即時搜尋 → Grok。
-- **Claude Code · Opus 4.8** — 自己做:taste-final。hard-judgment 派給 Codex Sol(智力分高於 Opus)、所有編碼走 Codex 通道、長文 → Gemini、即時搜尋 → Grok。
+- **Claude Code · Opus 5** — 自己做：hard-judgment、taste-final。大量編碼走 Codex 通道、長文 → Gemini、即時搜尋 → Grok。
 - **Codex · Sol** — 自己做:hardest-coding、hard-judgment、ui-draft。派出去:taste-final → Claude、長文 → Gemini、即時搜尋 → Grok、粗活 → Codex Terra。
 - **Codex · Terra** — 自己做:bulk-mechanical。真正最硬的往上升給 Sol;taste → Claude、長文 → Gemini、即時搜尋 → Grok。
 - **Grok Build · Grok 4.5** — 自己做:live-search、coding-overflow(中量級編碼)。所有硬活派給 Codex/Claude/Gemini——先驗每個 API 簽章與引用事實。
-- **Antigravity · Gemini** — 自己做:long-context(3.1 Pro)、fast-agentic(Flash)。編碼/判斷/文字派給 Codex/Claude;即時搜尋 → Grok。3.1 Pro 絕不接 agentic 工具長鏈。
+- **Antigravity · Gemini** — 自己做:3.1 Pro 的長文與重脈絡 agentic 工作、Flash 的高速重複迴圈。最硬的編碼/判斷/文字派給 Codex/Claude;即時搜尋 → Grok。
 
 </details>
 

package/VERSION

@@ -1 +1 @@
-0.9.1
+0.10.2

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "omnilane",
-  "version": "0.9.1",
+  "version": "0.10.2",
   "description": "One routing table, every harness — classify subtasks into lanes and dispatch each lane to the best vendor's agentic CLI (Codex, Claude, Gemini, Grok) using your existing subscription logins.",
   "bin": {
     "omnilane": "bin/omnilane"

package/routing.yaml

@@ -7,30 +7,35 @@
 #   Fallback chain: the first candidate whose vendor CLI is installed wins, so the
 #   same table degrades gracefully when you only subscribe to one or two vendors.
 # Override any line in ~/.omnilane/routing.local.yaml (same format; local wins).
-# Provenance (audited 2026-07-12): defaults follow Artificial Analysis data, 2026-07
+# Provenance (audited 2026-07-12, re-audited 2026-07-25 vs official model cards;
+# Gemini Flash candidates moved 3.5 -> 3.6 on 2026-07-22; Claude Opus defaults moved
+# 4.8 -> 5 after the 2026-07-24 release — see docs/model-capabilities-2026-07.md):
+# defaults follow Artificial Analysis data, 2026-07
 # snapshot. Verified against AA site records + vendor pricing pages: Intelligence &
 # Coding indexes and 7:2:1 blended prices all match (AA field price1mBlended7To2To1);
 # coding cost-per-task is chart-only (not independently reconstructed). Prices are
 # standard short-context API tier — on subscription CLIs treat $ as relative ranking.
 # Your own job outcomes (~/.omnilane/jobs/) outrank these priors; edit lanes to match.
 
-hardest-coding:  codex gpt-5.6-sol max | claude claude-opus-4-8 xhigh  # AA Coding Agent Index v1.1: Sol (max) 80 = SOTA (2026-07-09, Codex harness); Claude xhigh per Anthropic guidance for difficult tasks
-bulk-mechanical: codex gpt-5.6-terra max | claude claude-sonnet-5 high | gemini "Gemini 3.5 Flash (High)" -  # Terra 76.66 ~= Fable-class at a fraction of the cost
-triage:          codex gpt-5.6-luna medium | gemini "Gemini 3.5 Flash (Low)" - | claude claude-haiku-4-5 -  # high-volume scans
-hard-judgment:   codex gpt-5.6-sol max | claude claude-opus-4-8 xhigh   # Sol max Intelligence 59 — second only to Fable 5 (2026-07-09 AA); Claude xhigh per Anthropic guidance for difficult tasks
-taste-final:     claude claude-opus-4-8 high | codex gpt-5.6-sol max    # user-facing prose, prompt/doc polish, Chinese phrasing, style arbitration
-consult:         codex gpt-5.6-sol max | claude claude-opus-4-8 high | grok grok-4.5 - | gemini "Gemini 3.1 Pro (High)" -  # direct named-model consultation; use --vendor to prevent fallback
-ui-draft:        codex gpt-5.6-sol xhigh | claude claude-opus-4-8 high  # only with a design system / reference images; open-ended visual taste -> taste-final
-long-context:    gemini "Gemini 3.1 Pro (High)" - | claude claude-opus-4-8 high | codex gpt-5.6-sol high  # 1M-token synthesis ONLY — never agentic loops (AA agentic 21.4)
-fast-agentic:    gemini "Gemini 3.5 Flash (High)" - | codex gpt-5.6-luna high  # speed + agentic tool loops
+hardest-coding:  codex gpt-5.6-sol max | claude claude-opus-5 xhigh  # Opus 5 xhigh is joint-first on AA Coding Agent Index (2026-07-24) and is Anthropic's documented starting point for coding/agentic work; max shows diminishing returns and can overthink. Keep Sol first for the established Codex harness lane.
+bulk-mechanical: codex gpt-5.6-terra max | claude claude-sonnet-5 high | gemini "Gemini 3.6 Flash (High)" -  # AA Coding Agent Index v1.1: Terra 77.4 ~= Fable 77.2 at a fraction of the cost
+triage:          codex gpt-5.6-luna medium | gemini "Gemini 3.6 Flash (Low)" - | claude claude-haiku-4-5 -  # high-volume scans
+hard-judgment:   claude claude-opus-5 xhigh | codex gpt-5.6-sol max   # AA Intelligence Index 2026-07-24: Opus 5 61, Sol max 59; Opus leads AA agentic knowledge-work benchmarks. xhigh per Anthropic guidance (high is the documented floor for intelligence-sensitive work; max is for correctness-over-cost only) — raise to max locally via `omnilane configure set` if your workload needs it.
+taste-final:     claude claude-opus-5 high | codex gpt-5.6-sol max    # user-facing prose, prompt/doc polish, Chinese phrasing, style arbitration
+consult:         codex gpt-5.6-sol max | claude claude-opus-5 high | grok grok-4.5 - | gemini "Gemini 3.1 Pro (High)" -  # direct named-model consultation; use --vendor to prevent fallback
+ui-draft:        codex gpt-5.6-sol xhigh | claude claude-opus-5 high  # only with a design system / reference images; open-ended visual taste -> taste-final
+long-context:    gemini "Gemini 3.1 Pro (High)" - | claude claude-opus-5 high | codex gpt-5.6-sol high  # all have 1M context; prefer Gemini for cost + long-doc synthesis, Flash for fast loops
+fast-agentic:    gemini "Gemini 3.6 Flash (High)" - | codex gpt-5.6-luna high  # speed + agentic tool loops; 3.6 Flash (released 2026-07-21): AA Intelligence 50, #1 output speed 303.6 tok/s, -17% output tokens vs 3.5 Flash per Google
 live-search:     grok grok-4.5 - | off          # native X/web search lane; no real substitute
-coding-overflow: grok grok-4.5 - | kimi kimi-k3 - | qwen qwen3-coder-plus - | opencode - - | off  # codex-quota relief valve: mid-tier coding; verify factual claims (grok hallucination-prone). kimi/qwen model fields are CLI aliases — adjust to your login. opencode "-" model = its own configured default.
+coding-overflow: grok grok-4.5 - | kimi kimi-k3 - | qwen qwen3-coder-plus - | opencode - - | off  # codex-quota relief valve: mid-tier coding; Grok 4.5 (GA 2026-07-16) Terminal-Bench 83.3 / SWE-Bench Pro 64.7, but AA hallucination 54% — verify factual claims. qwen3-coder-plus = 2025-09-23 snapshot alias (Qwen 3.6 Plus exists; re-evaluate before swapping). kimi/qwen model fields are CLI aliases — adjust to your login. opencode "-" model = its own configured default.
 arbitrate:       off - -                        # opinion panel is OPT-IN: it costs one call per voter per round.
                                                 # Enable: `arbitrate: vote codex,claude,grok -` (any 1-4 of codex/claude/grok/gemini)
                                                 # Debate round (each voter rebuts the others): set the effort field to 2.
                                                 # Custom gate: `arbitrate: exec /path/to/script -`
 # Claude Fable 5 (claude-fable-5) is deliberately absent from the defaults: the top Claude tier
-# is usually the MAIN LOOP itself, not a dispatched worker, and it prices above Opus. If you want
+# is usually the MAIN LOOP itself, not a dispatched worker, and it prices above Opus. This is a
+# cost / guardrail / main-loop policy choice, NOT a capability verdict — Anthropic positions
+# Fable 5 above Opus 4.8. If you want
 # to route to it anyway, pick it in the configurator or set e.g.
 #   taste-final: claude claude-fable-5 high
 # in ~/.omnilane/routing.local.yaml.

package/scripts/configure.sh

@@ -147,25 +147,26 @@ case "${1:-}" in
   -h|--help|help) cfg_usage; exit 0 ;;
 esac
 
-# Curated suggestions only — "c" always allows free text so new models work.
-CODEX_MODELS=("gpt-5.6-sol" "gpt-5.6-terra" "gpt-5.6-luna")
+# Native CLI catalogs are pinned from each installed CLI's live model surface.
+# Dynamic/API catalogs stay curated — "c" always accepts an exact model ID.
+CODEX_MODELS=("gpt-5.6" "gpt-5.6-sol" "gpt-5.6-terra" "gpt-5.6-luna" "gpt-5.5" "gpt-5.4" "gpt-5.4-mini" "gpt-5.3-codex-spark")
 CODEX_EFFORTS=("xhigh" "max" "ultra" "high" "medium" "low" "minimal" "none")
-CLAUDE_MODELS=("claude-opus-4-8" "claude-fable-5" "claude-sonnet-5" "claude-haiku-4-5")
+CLAUDE_MODELS=("default" "best" "fable" "opus" "sonnet" "haiku" "opus[1m]" "sonnet[1m]" "opusplan" "claude-fable-5" "claude-opus-5" "claude-sonnet-5" "claude-opus-4-8" "claude-opus-4-7" "claude-opus-4-6" "claude-opus-4-5-20251101" "claude-sonnet-4-6" "claude-sonnet-4-5-20250929" "claude-haiku-4-5" "claude-haiku-4-5-20251001")
 CLAUDE_EFFORTS=("max" "xhigh" "high" "medium" "low" "-")
-GEMINI_MODELS=("Gemini 3.1 Pro (High)" "Gemini 3.1 Pro (Low)" "Gemini 3.5 Flash (High)" "Gemini 3.5 Flash (Medium)" "Gemini 3.5 Flash (Low)")
-GROK_MODELS=("grok-4.5" "grok-4.3")
-KIMI_MODELS=("kimi-k3" "kimi-k2.7-code")
-QWEN_MODELS=("qwen3-coder-plus" "qwen3-coder-flash")
-# OpenCode models use provider/model form; OpenRouter models are catalog slugs.
-OPENCODE_MODELS=("openrouter/anthropic/claude-sonnet-5" "openrouter/openai/gpt-5.6-sol" "opencode/default (leave model to opencode)")
-OPENROUTER_MODELS=("anthropic/claude-sonnet-5" "openai/gpt-5.6-sol" "moonshotai/kimi-k3" "qwen/qwen3-coder-plus")
+GEMINI_MODELS=("gemini-3.6-flash-high" "gemini-3.6-flash-medium" "gemini-3.6-flash-low" "gemini-3.5-flash-high" "gemini-3.5-flash-medium" "gemini-3.5-flash-low" "gemini-3.1-pro-high" "gemini-3.1-pro-low" "claude-sonnet-4-6" "claude-opus-4-6-thinking" "gpt-oss-120b-medium")
+GROK_MODELS=("grok-4.5" "headroom-grok-build" "grok-4.3-official")
+KIMI_MODELS=("kimi-k3" "kimi-k2.7-code" "kimi-k2.5")
+QWEN_MODELS=("qwen3.7-max" "qwen3.7-plus" "qwen3.6-plus" "qwen3.5-plus" "qwen3-max-2026-01-23" "qwen3-coder-next" "qwen3-coder-plus" "qwen3-coder-flash")
+# OpenCode models use provider/model form; OpenRouter models use catalog slugs.
+OPENCODE_MODELS=("openrouter/anthropic/claude-opus-5" "openrouter/anthropic/claude-fable-5" "openrouter/anthropic/claude-sonnet-5" "openrouter/openai/gpt-5.6-sol" "openrouter/openai/gpt-5.6-terra" "openrouter/openai/gpt-5.6-luna" "openrouter/x-ai/grok-4.5" "openrouter/google/gemini-3.6-flash" "openrouter/moonshotai/kimi-k3" "openrouter/moonshotai/kimi-k2.7-code" "openrouter/qwen/qwen3.7-max" "openrouter/qwen/qwen3.7-plus" "openrouter/qwen/qwen3-coder-plus" "opencode/default (leave model to opencode)")
+OPENROUTER_MODELS=("anthropic/claude-opus-5" "anthropic/claude-fable-5" "anthropic/claude-sonnet-5" "openai/gpt-5.6-sol" "openai/gpt-5.6-terra" "openai/gpt-5.6-luna" "x-ai/grok-4.5" "google/gemini-3.6-flash" "moonshotai/kimi-k3" "moonshotai/kimi-k2.7-code" "qwen/qwen3.7-max" "qwen/qwen3.7-plus" "qwen/qwen3-coder-plus")
 # Direct-API OpenAI-compatible vendors (curl + <VENDOR>_API_KEY); slugs are
 # suggestions — "c" free text covers anything each provider's /models lists.
-DEEPSEEK_MODELS=("deepseek-chat" "deepseek-reasoner" "deepseek-v4-flash")
-ZAI_MODELS=("glm-4.6")
-MISTRAL_MODELS=("devstral-latest" "codestral-latest" "mistral-medium-latest")
-GROQ_MODELS=("openai/gpt-oss-120b" "qwen/qwen3.6-27b" "openai/gpt-oss-20b")
-CEREBRAS_MODELS=("gpt-oss-120b" "qwen-3-32b" "llama-3.3-70b")
+DEEPSEEK_MODELS=("deepseek-v4-pro" "deepseek-v4-flash")
+ZAI_MODELS=("glm-5.1" "glm-5" "glm-5-turbo" "glm-4.7" "glm-4.7-flashx" "glm-4.7-flash" "glm-4.6")
+MISTRAL_MODELS=("devstral-latest" "devstral-small-latest" "codestral-latest" "mistral-medium-latest" "mistral-large-latest")
+GROQ_MODELS=("groq/compound" "groq/compound-mini" "openai/gpt-oss-120b" "openai/gpt-oss-20b" "qwen/qwen3.6-27b" "llama-3.3-70b-versatile" "llama-3.1-8b-instant")
+CEREBRAS_MODELS=("zai-glm-4.7" "gpt-oss-120b" "qwen-3-235b-a22b-instruct-2507" "qwen-3-32b" "llama3.1-8b")
 
 custom_value_is_safe() {
   case "$1" in

package/scripts/runners/run-vote.sh

@@ -31,7 +31,7 @@ trap cleanup_temp_files EXIT
 voter_spec() { # vendor -> "model<TAB>effort"
   case "$1" in
     codex)  printf 'gpt-5.6-sol\thigh' ;;
-    claude) printf 'claude-opus-4-8\thigh' ;;
+    claude) printf 'claude-opus-5\thigh' ;;
     gemini) printf 'Gemini 3.1 Pro (High)\t-' ;;
     grok)   printf 'grok-4.5\t-' ;;
     *)      return 1 ;;