omnilane 0.32.0 → 0.34.0

package/.claude-plugin/marketplace.json

@@ -6,14 +6,14 @@
   },
   "metadata": {
     "description": "One routing table, cross-vendor dispatch, foreman completion inbox.",
-    "version": "0.32.0"
+    "version": "0.34.0"
   },
   "plugins": [
     {
       "name": "omnilane",
       "source": "./",
       "description": "Route each subtask to the model that fits, dispatch it to any vendor CLI, and have finished dispatches report back into the foreman's next prompt.",
-      "version": "0.32.0",
+      "version": "0.34.0",
       "category": "development",
       "keywords": [
         "routing",

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "omnilane",
-  "version": "0.32.0",
+  "version": "0.34.0",
   "description": "One routing table, every harness: classify subtasks into lanes and auto-dispatch each lane to the best vendor CLI (Codex, Claude Code, Grok Build, Antigravity) with background jobs, depth guard, and serialized codex dispatch.",
   "author": {
     "name": "Seraphim0916"

package/CHANGELOG.md

@@ -6,6 +6,64 @@ semantic version tags.
 
 ## [Unreleased]
 
+## [0.34.0] - 2026-09-03
+
+### Changed
+
+- `hard-judgment`'s Claude slot swaps from Fable 5.1 (xhigh) to Opus 5
+  (xhigh): Opus returns 97.7% of Fable's agentic score (58.4 vs 59.8) at 68%
+  of the cost ($1.801 vs $2.651/task) with a lower hallucination rate (.60 vs
+  .71).
+- A fallback-depth pass gives every active lane (`arbitrate` intentionally
+  excluded) at least three vendor candidates: `hardest-coding`,
+  `taste-final`, `ui-draft`, `fast-agentic`, and `live-search` each gain new
+  fallbacks; `live-search`'s added Gemini and Claude candidates use their own
+  web-search tools, not Grok's native X/web surface, so treat them as
+  best-effort only when Grok's CLI is unavailable.
+
+## [0.33.0] - 2026-09-03
+
+### Added
+
+- `dispatch.sh --thread NAME` continues named Claude, Codex, Grok, and Gemini
+  conversations through each vendor's native session/resume primitive. Thread
+  state is written atomically under the private `$OMNILANE_HOME/threads/`
+  store and pins vendor, model, effort, and physical workdir; direct-API
+  vendors and `exec` refuse threading visibly.
+- `jobs.sh threads`, `threads show NAME`, and `threads rm NAME` list, inspect,
+  and remove local thread state without deleting the vendor session.
+- Threaded jobs record `thread` and `thread_turn` in `meta.json` and completion
+  inbox records; completion notices include `thread=NAME turn=N`.
+- Three-turn live probes verified memory continuity for all four vendors and
+  verified cross-directory resume: Claude (`--session-id`/`--resume`), Codex
+  (`thread_id`/`exec resume`), Grok (`--session-id`/`--resume`), and Gemini
+  (`conversation_id`/`--conversation`). Workdir remains pinned because changing
+  trees mid-conversation is still an operator error worth catching.
+
+### Changed
+
+- The skill routing reminder and the persistent hook text now dispatch every task by default, withdrawing the read-only-verification and one-line-fix self-execute exceptions and naming the reserved commander actions (planning, task briefs, reading worker output, acceptance, replies to the operator, git commit/push, governance-file edits).
+
+### Fixed
+
+- A shared JSON escaper now fixes backslash handling for live prompts,
+  `jobs.sh send`, and completion inbox records; the standalone doctor,
+  provider-probe, and release-audit output paths use the same corrected behavior.
+  Backslashes, quotes, control characters, and multibyte text round-trip as valid
+  JSON everywhere.
+
+## [0.32.1] - 2026-09-02
+
+### Fixed
+
+- Foremen could miss a completion forever when byte-based tail truncation split a UTF-8 character and the hook silently skipped the undecodable inbox record; writers now sanitise truncated tails, readers retry after repairing invalid bytes, and irrecoverable records are consumed with a FAILED unreadable-record notice.
+- Claude Code Desktop foremen were never bound to their session because dispatch only searched process-tree records created for headless workers; dispatch now prefers a valid `CLAUDE_CODE_SESSION_ID`, preventing sessions that share a working directory, or use `/`, from taking each other's notices.
+
+### Changed
+
+- The skill and the routing reminder now state the implementation dispatch parameters (`--mode work --workdir DIR --timeout 3600` or more) and record that the advise default is a read-only worker under a 600 s per-call watchdog that yields no output on implementation tasks.
+- The skill gains a `Job lifecycle defaults` section covering the foreman completion inbox, the live mailbox (`jobs.sh send` / `jobs.sh close`), goal orchestration defaults (`omnilane goal`, unlimited budgets unless opted in), and read-only job hygiene commands.
+
 ## [0.32.0] - 2026-09-02
 
 ### Changed
@@ -713,7 +771,10 @@ work to the wrong model, and records the evidence behind the shipped defaults.
 - Initial shared routing table, cross-vendor dispatcher, runners, installer,
   and baseline lint fixes.
 
-[Unreleased]: https://github.com/Seraphim0916/omnilane/compare/v0.32.0...HEAD
+[Unreleased]: https://github.com/Seraphim0916/omnilane/compare/v0.34.0...HEAD
+[0.34.0]: https://github.com/Seraphim0916/omnilane/compare/v0.33.0...v0.34.0
+[0.33.0]: https://github.com/Seraphim0916/omnilane/compare/v0.32.1...v0.33.0
+[0.32.1]: https://github.com/Seraphim0916/omnilane/compare/v0.32.0...v0.32.1
 [0.32.0]: https://github.com/Seraphim0916/omnilane/compare/v0.31.0...v0.32.0
 
 [0.31.0]: https://github.com/Seraphim0916/omnilane/compare/v0.30.0...v0.31.0

package/README.ja.md

@@ -112,16 +112,16 @@ flowchart LR
 
 | レーン | 第一候補 | バックアップ | 用途 |
 |---|---|---|---|
-| 🔥 hardest-coding | Claude Fable 5.1 (xhigh) | GPT-5.6 Sol (xhigh) | 最難関の実装、深い根本原因調査、正確性が重要な修正 |
+| 🔥 hardest-coding | Claude Fable 5.1 (xhigh) | GPT-5.6 Sol (xhigh) → Grok 4.6 → Gemini 3.7 Flash (High) | 最難関の実装、深い根本原因調査、正確性が重要な修正 |
 | 🏗️ bulk-mechanical | GPT-5.6 Sol (high) | Gemini 3.7 Flash (High) → Claude Sonnet 5 (high) | リファクタリング、移行、テスト、大規模レビュー——機械的な持久作業 |
 | 🧹 triage | GPT-5.6 Luna (high) | Gemini 3.7 Flash (Low) → Claude Haiku 4.5 | 大量スキャン、一次選別 |
-| ⚖️ hard-judgment | Claude Fable 5.1 (xhigh) | GPT-5.6 Sol (max) → Grok 4.6 | アーキテクチャ判断、深い推論、セカンドオピニオン |
-| ✒️ taste-final | Claude Fable 5.1 (high) | GPT-5.6 Sol (max) | ユーザー向け文章、プロンプト／文書の仕上げ、文体判断 |
+| ⚖️ hard-judgment | Claude Opus 5 (xhigh) | GPT-5.6 Sol (max) → Grok 4.6 | アーキテクチャ判断、深い推論、セカンドオピニオン |
+| ✒️ taste-final | Claude Fable 5.1 (high) | GPT-5.6 Sol (max) → Grok 4.6 → Gemini 3.7 Flash (High) | ユーザー向け文章、プロンプト／文書の仕上げ、文体判断 |
 | 💬 consult | GPT-5.6 Sol (max) | Claude Fable 5.1 (high) → Grok 4.6 → Gemini 3.7 Flash (High) | 指名モデルへの直接相談。フォールバック防止のため `--vendor` を維持 |
-| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude Fable 5.1 (high) | デザインシステム／参照画像がある場合だけの UI ドラフト |
+| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude Fable 5.1 (high) → Gemini 3.7 Flash (High) | デザインシステム／参照画像がある場合だけの UI ドラフト |
 | 📚 long-context | Gemini 3.7 Flash (Medium) | GPT-5.6 Terra (max) → Claude Opus 5 (medium) | 長文書の抽出と統合。AA-LCR、コスト、スループット順 |
-| ⚡ fast-agentic | Gemini 3.7 Flash (Medium) | 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 4.6 | — (`off`) | リアルタイム X／Web 検索とソーシャル文脈 |
+| ⚡ fast-agentic | Gemini 3.7 Flash (Medium) | GPT-5.6 Luna (high) → Claude Haiku 4.5 | 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 4.6 | Gemini 3.7 Flash (High) → Claude Sonnet 5 (high) | リアルタイム X／Web 検索とソーシャル文脈 |
 | 🚰 coding-overflow | Grok 4.6 | Gemini 3.7 Flash (High) → Kimi K3 → Qwen3 Coder Plus → OpenCode | Codex クォータ不足時の中級コーディング逃がし弁 |
 | 🗳️ arbitrate | `off`（オプトイン） | — | 重大判断用の内蔵意見パネル。デフォルト無効、`routing.local.yaml` で有効化し、投票者・ラウンドごとに 1 コール |
 
@@ -155,12 +155,12 @@ flowchart LR
 なので追加コールなし)、どれを**ディスパッチ**するか。CLI の `omnilane` スキルが
 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 5.1**——自分で実行：hard-judgment、taste-final、hardest-coding。ディスパッチ：bulk → Codex Sol high、long-context／高速ループ → Gemini 3.7 Flash、live-search → Grok。
-- **Claude Code · Opus 5**——低いハルシネーション率や価格を優先するときは hard-judgment と taste-final を自分で実行。最難関コーディング → Fable 5.1 または Sol、bulk → Sol high、long-context／高速ループ → Gemini 3.7 Flash、live-search → Grok。
+- **Claude Code · Fable 5.1**——自分で実行：taste-final、hardest-coding。ディスパッチ：hard-judgment → Opus 5、bulk → Codex Sol high、long-context／高速ループ → Gemini 3.7 Flash、live-search → Grok。
+- **Claude Code · Opus 5**——自分で実行：hard-judgment(これがデフォルトのレーン)。低いハルシネーション率や価格を優先するときはローカル override で taste-final も担当。最難関コーディング → Fable 5.1 または Sol、bulk → Sol high、long-context／高速ループ → Gemini 3.7 Flash、live-search → Grok。
 - **Codex · Sol**——自分で実行：hardest-coding、bulk-mechanical、hard-judgment、ui-draft。ディスパッチ：taste-final → Claude、long-context／高速ループ → Gemini 3.7 Flash、live-search → Grok。
 - **Codex · Terra**——long-context の Codex フォールバックを自分で実行。bulk-mechanical のデフォルトは Sol high に移動。最難関は Sol xhigh、taste → Claude、高速ループ → Gemini 3.7 Flash、live-search → Grok。
-- **Grok Build · Grok 4.6**——live-search と coding-overflow を自分で実行。難しいコーディング／判断／文章は Codex、Claude、Gemini へ送り、API シグネチャと引用事実は検証します。
-- **Antigravity · Gemini 3.7 Flash**——Medium の long-context／高速ループ、High の bulk／overflow、Low の triage を自分で実行。最難関のコーディング／判断／文章は Codex、Claude、live-search は Grok へ。
+- **Grok Build · Grok 4.6**——live-search と coding-overflow を自分で実行し、hardest-coding・hard-judgment・taste-final のフォールバックも兼任。第一候補が使えるときは難しいコーディング／判断／文章を Codex、Claude、Gemini へ送り、API シグネチャと引用事実は検証します。
+- **Antigravity · Gemini 3.7 Flash**——Medium の long-context／高速ループ、High の bulk／overflow、Low の triage を自分で実行し、High で hardest-coding・taste-final・ui-draft・live-search のフォールバックも兼任。第一候補が使えるときは最難関のコーディング／判断／文章を Codex、Claude へ。
 
 </details>
 
@@ -290,7 +290,7 @@ omnilane ui status                             # Live UI の稼働状態を表
 omnilane ui url                                # 現在の認証済みローカル URL を表示
 omnilane ui stop                               # Live UI を停止
 omnilane doctor [--json]                       # ルーティングとローカル実行環境を読み取り専用で診断
-dispatch.sh [--background] [--dry-run] [--mode advise|work|sysops] [--workdir DIR]
+dispatch.sh [--background] [--dry-run] [--thread NAME] [--mode advise|work|sysops] [--workdir DIR]
             [--vendor V] [--model M] [--effort E] [--timeout SEC] [--job-timeout SEC]
             LANE "TASK"                              # "-" で stdin から読む
 dispatch.sh [--json] --list [--json]
@@ -308,6 +308,11 @@ configure.sh                                        # 対話式レーンメニ
 configure.sh set|get|unset|list|diff LANE [SPEC]    # routing.local.yaml を非対話で編集/確認
 ```
 
+`--thread NAME` は単発ディスパッチ間で名前付きの Claude、Codex、Grok、
+Gemini 会話を継続します。0.33.0 ではベンダー、モデル、effort、物理 workdir
+を固定します。ローカル状態は `jobs.sh threads`、`threads show NAME`、
+`threads rm NAME` で管理でき、削除してもベンダー側のセッションは残ります。
+
 終了コード:`2` 使い方エラー(無効なベンダー、または指定ベンダーがレーンに
 ない場合を含む)、`3` レーン無効(off)、`4` チェーン内に利用可能な CLI がない、
 または設定済みの指定ベンダー CLI が利用不可、`5` Round 1 の成功投票者不足、
@@ -432,9 +437,12 @@ advise 専用で、ファイルを編集しません。
 
 <br/>
 
-Fable 5.1 は現在 `hardest-coding`、`hard-judgment`、`taste-final` の
-第一候補です。同じ xhigh では知能、agentic 作業、コーディングで Opus 5 を
-上回ります。Sol max は、はるかに安価な別ベンダーの判断用フォールバックです。
+Fable 5.1 は現在 `hardest-coding`、`taste-final` の第一候補です。同じ xhigh
+では知能、agentic 作業、コーディングで Opus 5 を上回ります。Sol max は、
+はるかに安価な別ベンダーの判断用フォールバックです。`hard-judgment` 自体は
+現在 Opus 5 xhigh がデフォルトです:Fable の agentic スコアの 97.7% を
+コスト 68% で達成し、ハルシネーション率も低いため、このレーン自身の
+コスト基準では安い方が勝ちます。
 
 | 評価（AA、2026-09-02 取得） | Claude Fable 5.1 (xhigh) | Claude Opus 5 (xhigh) | GPT-5.6 Sol (max) |
 |---|---:|---:|---:|
@@ -446,12 +454,12 @@ Fable 5.1 は現在 `hardest-coding`、`hard-judgment`、`taste-final` の
 
 Fable 5.1 は bulk と triage のデフォルトではありません。トークン単価が
 Opus 5 の 2 倍で、Claude Code のサブスクリプションクォータも 1 ターン当たり
-最も多く消費するためです。Opus 5 は低ハルシネーション・低価格の Claude
-選択肢として medium で `long-context` に残り、次の
-`~/.omnilane/routing.local.yaml` で任意のレーンへ戻せます。
+最も多く消費するためです。Opus 5 は現在 `hard-judgment` のデフォルトを担い、
+medium で `long-context` にも残り、`~/.omnilane/routing.local.yaml` で
+任意のレーンへいつでも戻せます——例えば Fable を呼び戻すには:
 
 ```yaml
-hard-judgment: claude claude-opus-5 xhigh
+hard-judgment: claude claude-fable-5-1 xhigh
 ```
 
 </details>
@@ -530,6 +538,15 @@ scripts/dispatch.sh --dry-run hardest-coding "…"   # 解決済みプラン、
 
 ## 📜 リリース履歴
 
+## v0.33.0 の新機能
+
+- **4 ベンダー対応スレッドディスパッチ。** `--thread NAME` はベンダー、
+  モデル、effort、workdir を固定し、Claude、Codex、Grok、Gemini の会話を
+  フォアグラウンドまたはバックグラウンドの単発ジョブ間で継続します。
+  direct-API ベンダー、`exec`、ライブモード、固定値の不一致は終了コード 2 で停止します。
+- **スレッド状態の管理。** `jobs.sh threads`、`threads show NAME`、
+  `threads rm NAME` でローカル状態を一覧、表示、削除できます。
+
 ## v0.32.0 の新機能
 
 - **AA 2026-09 スナップショットで全ルーティングを再評価。** Fable 5.1 と Gemini 3.7 Flash がデフォルトに入り、数値は新しい日付付き文書に集約しました。

package/README.ko.md

@@ -110,16 +110,16 @@ flowchart LR
 
 | 레인 | 1순위 모델 | 백업 | 용도 |
 |---|---|---|---|
-| 🔥 hardest-coding | Claude Fable 5.1 (xhigh) | GPT-5.6 Sol (xhigh) | 가장 어려운 구현, 근본 원인 디버깅, 정확성이 핵심인 수정 |
+| 🔥 hardest-coding | Claude Fable 5.1 (xhigh) | GPT-5.6 Sol (xhigh) → Grok 4.6 → Gemini 3.7 Flash (High) | 가장 어려운 구현, 근본 원인 디버깅, 정확성이 핵심인 수정 |
 | 🏗️ bulk-mechanical | GPT-5.6 Sol (high) | Gemini 3.7 Flash (High) → Claude Sonnet 5 (high) | 리팩터링, 마이그레이션, 테스트, 대량 스윕——기계적 지구력 작업 |
 | 🧹 triage | GPT-5.6 Luna (high) | Gemini 3.7 Flash (Low) → Claude Haiku 4.5 | 대량 스캔과 1차 선별 |
-| ⚖️ hard-judgment | Claude Fable 5.1 (xhigh) | GPT-5.6 Sol (max) → Grok 4.6 | 아키텍처 판정, 심층 추론, 2차 의견 |
-| ✒️ taste-final | Claude Fable 5.1 (high) | GPT-5.6 Sol (max) | 사용자 대상 문장, 프롬프트／문서 다듬기, 스타일 판정 |
+| ⚖️ hard-judgment | Claude Opus 5 (xhigh) | GPT-5.6 Sol (max) → Grok 4.6 | 아키텍처 판정, 심층 추론, 2차 의견 |
+| ✒️ taste-final | Claude Fable 5.1 (high) | GPT-5.6 Sol (max) → Grok 4.6 → Gemini 3.7 Flash (High) | 사용자 대상 문장, 프롬프트／문서 다듬기, 스타일 판정 |
 | 💬 consult | GPT-5.6 Sol (max) | Claude Fable 5.1 (high) → Grok 4.6 → Gemini 3.7 Flash (High) | 지정 모델 직접 상담. 폴백 방지를 위해 `--vendor` 유지 |
-| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude Fable 5.1 (high) | 디자인 시스템／참조 이미지가 있을 때만 UI 초안 |
+| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude Fable 5.1 (high) → Gemini 3.7 Flash (High) | 디자인 시스템／참조 이미지가 있을 때만 UI 초안 |
 | 📚 long-context | Gemini 3.7 Flash (Medium) | GPT-5.6 Terra (max) → Claude Opus 5 (medium) | 장문 추출과 종합. AA-LCR, 비용, 처리량 순 |
-| ⚡ fast-agentic | Gemini 3.7 Flash (Medium) | GPT-5.6 Luna (high) | 빠른 멀티스텝 agentic 루프, 멀티모달 확인 |
-| 📡 live-search | Grok 4.6 | — (`off`) | 실시간 X／웹 검색과 소셜 맥락 |
+| ⚡ fast-agentic | Gemini 3.7 Flash (Medium) | GPT-5.6 Luna (high) → Claude Haiku 4.5 | 빠른 멀티스텝 agentic 루프, 멀티모달 확인 |
+| 📡 live-search | Grok 4.6 | Gemini 3.7 Flash (High) → Claude Sonnet 5 (high) | 실시간 X／웹 검색과 소셜 맥락 |
 | 🚰 coding-overflow | Grok 4.6 | Gemini 3.7 Flash (High) → Kimi K3 → Qwen3 Coder Plus → OpenCode | Codex 쿼터 소진 시 중급 코딩 안전 밸브 |
 | 🗳️ arbitrate | `off`(옵트인) | — | 중대한 판단을 위한 내장 의견 패널. 기본 비활성, `routing.local.yaml` 에서 활성화하며 투표자·라운드당 1회 호출 |
 
@@ -153,12 +153,12 @@ flowchart LR
 추가 호출 없음)와 **디스패치**하는지입니다. CLI 의 `omnilane` 스킬이 해당
 행을 자동 적용하며, 이것은 사람이 보는 버전입니다.
 
-- **Claude Code · Fable 5.1**——직접 실행: hard-judgment, taste-final, hardest-coding. 디스패치: bulk → Codex Sol high, long-context／빠른 루프 → Gemini 3.7 Flash, live-search → Grok.
-- **Claude Code · Opus 5**——더 낮은 환각률이나 가격이 중요할 때 hard-judgment 와 taste-final 을 직접 실행. 최고난도 코딩 → Fable 5.1 또는 Sol, bulk → Sol high, long-context／빠른 루프 → Gemini 3.7 Flash, live-search → Grok.
+- **Claude Code · Fable 5.1**——직접 실행: taste-final, hardest-coding. 디스패치: hard-judgment → Opus 5, bulk → Codex Sol high, long-context／빠른 루프 → Gemini 3.7 Flash, live-search → Grok.
+- **Claude Code · Opus 5**——직접 실행: hard-judgment(기본 레인). 더 낮은 환각률이나 가격이 중요할 때는 로컬 오버라이드로 taste-final 도 맡을 수 있습니다. 최고난도 코딩 → Fable 5.1 또는 Sol, bulk → Sol high, long-context／빠른 루프 → Gemini 3.7 Flash, live-search → Grok.
 - **Codex · Sol**——직접 실행: hardest-coding, bulk-mechanical, hard-judgment, ui-draft. 디스패치: taste-final → Claude, long-context／빠른 루프 → Gemini 3.7 Flash, live-search → Grok.
 - **Codex · Terra**——long-context 의 Codex 폴백을 직접 실행. bulk-mechanical 기본값은 Sol high 로 이동했습니다. 최고난도는 Sol xhigh, taste → Claude, 빠른 루프 → Gemini 3.7 Flash, live-search → Grok.
-- **Grok Build · Grok 4.6**——live-search 와 coding-overflow 를 직접 실행. 어려운 코딩／판단／문장은 Codex, Claude, Gemini 로 보내고 API 시그니처와 인용 사실을 검증합니다.
-- **Antigravity · Gemini 3.7 Flash**——Medium 의 long-context／빠른 루프, High 의 bulk／overflow, Low 의 triage 를 직접 실행. 최고난도 코딩／판단／문장은 Codex, Claude 로, live-search 는 Grok 으로 보냅니다.
+- **Grok Build · Grok 4.6**——live-search 와 coding-overflow 를 직접 실행하며, hardest-coding, hard-judgment, taste-final 의 폴백도 겸합니다. 1순위 후보를 쓸 수 있으면 어려운 코딩／판단／문장은 Codex, Claude, Gemini 로 보내고 API 시그니처와 인용 사실을 검증합니다.
+- **Antigravity · Gemini 3.7 Flash**——Medium 의 long-context／빠른 루프, High 의 bulk／overflow, Low 의 triage 를 직접 실행하며, High 로 hardest-coding, taste-final, ui-draft, live-search 의 폴백도 겸합니다. 1순위 후보를 쓸 수 있으면 최고난도 코딩／판단／문장은 Codex, Claude 로 보냅니다.
 
 </details>
 
@@ -282,7 +282,7 @@ omnilane ui status                             # Live UI 실행 상태 표시
 omnilane ui url                                # 현재 인증된 로컬 URL 표시
 omnilane ui stop                               # Live UI 중지
 omnilane doctor [--json]                       # 라우팅과 로컬 실행 환경을 읽기 전용으로 진단
-dispatch.sh [--background] [--dry-run] [--mode advise|work|sysops] [--workdir DIR]
+dispatch.sh [--background] [--dry-run] [--thread NAME] [--mode advise|work|sysops] [--workdir DIR]
             [--vendor V] [--model M] [--effort E] [--timeout SEC] [--job-timeout SEC]
             LANE "TASK"                              # "-" 는 stdin 에서 읽기
 dispatch.sh [--json] --list [--json]
@@ -300,6 +300,11 @@ configure.sh                                        # 대화형 레인 메뉴
 configure.sh set|get|unset|list|diff LANE [SPEC]    # routing.local.yaml 비대화식 편집/확인
 ```
 
+`--thread NAME`은 단발 디스패치 사이에서 이름이 있는 Claude, Codex, Grok,
+Gemini 대화를 이어갑니다. 0.33.0에서는 벤더, 모델, effort, 실제 workdir를
+고정합니다. 로컬 상태는 `jobs.sh threads`, `threads show NAME`,
+`threads rm NAME`으로 관리하며, 상태를 삭제해도 벤더 세션은 남습니다.
+
 종료 코드: `2` 사용법 오류(잘못된 벤더 또는 지정 벤더가 레인에 없는 경우 포함),
 `3` 레인 비활성(off), `4` 체인에 사용 가능한 CLI 가 없거나 설정된 지정 벤더
 CLI 를 사용할 수 없음, `5` 1라운드 성공 투표자 부족, `6` 2라운드 반박 전부 실패,
@@ -418,9 +423,12 @@ Codex 중심, Codex 없음)이 들어 있습니다.
 
 <br/>
 
-Fable 5.1 은 이제 `hardest-coding`, `hard-judgment`, `taste-final`의
-1순위입니다. 같은 xhigh 에서 지능, agentic 작업, 코딩 모두 Opus 5 를
-앞섭니다. Sol max 는 훨씬 저렴한 타 벤더 판단 폴백으로 남습니다.
+Fable 5.1 은 이제 `hardest-coding`, `taste-final`의 1순위입니다. 같은
+xhigh 에서 지능, agentic 작업, 코딩 모두 Opus 5 를 앞섭니다. Sol max 는
+훨씬 저렴한 타 벤더 판단 폴백으로 남습니다. `hard-judgment` 자체는 이제
+Opus 5 xhigh 가 기본값입니다: Fable 의 agentic 점수 97.7%를 비용 68%에
+얻으면서 환각률도 더 낮아, 이 레인 고유의 비용 기준으로는 더 저렴한
+구성이 승리합니다.
 
 | 평가(AA, 2026-09-02 수집) | Claude Fable 5.1 (xhigh) | Claude Opus 5 (xhigh) | GPT-5.6 Sol (max) |
 |---|---:|---:|---:|
@@ -432,12 +440,12 @@ Fable 5.1 은 이제 `hardest-coding`, `hard-judgment`, `taste-final`의
 
 Fable 5.1 은 bulk 나 triage 기본값이 아닙니다. 토큰 가격이 Opus 5 의
 2배이고 Claude Code 구독 쿼터도 턴당 가장 많이 소비하기 때문입니다.
-Opus 5 는 더 낮은 환각률과 가격의 Claude 선택지로 medium
-`long-context`에 남으며, 다음 `~/.omnilane/routing.local.yaml` 설정으로
-어느 레인에든 다시 넣을 수 있습니다.
+Opus 5 는 이제 `hard-judgment`의 기본값이며 medium 으로 `long-context`에도
+남아 있고, `~/.omnilane/routing.local.yaml` 설정으로 어느 레인에든
+언제든 다시 넣을 수 있습니다 — 예를 들어 Fable 을 되돌리려면:
 
 ```yaml
-hard-judgment: claude claude-opus-5 xhigh
+hard-judgment: claude claude-fable-5-1 xhigh
 ```
 
 </details>
@@ -514,6 +522,15 @@ scripts/dispatch.sh --dry-run hardest-coding "…"   # 완전히 해석된 계
 
 ## 📜 릴리스 기록
 
+## v0.33.0 새 기능
+
+- **4개 벤더 스레드 디스패치.** `--thread NAME`은 벤더, 모델, effort,
+  workdir를 고정하고 Claude, Codex, Grok, Gemini 대화를 포그라운드 또는
+  백그라운드 단발 작업 사이에서 이어갑니다. direct-API 벤더, `exec`, 라이브
+  모드, 고정값 불일치는 종료 코드 2로 중단됩니다.
+- **스레드 상태 관리.** `jobs.sh threads`, `threads show NAME`, `threads rm NAME`으로
+  로컬 상태를 나열하거나 확인하고 삭제할 수 있습니다.
+
 ## v0.32.0 새 기능
 
 - **AA 2026-09 스냅샷으로 전체 라우팅을 재평가했습니다.** Fable 5.1 과 Gemini 3.7 Flash 가 기본값에 들어가고 수치는 새 날짜별 문서에 모았습니다.

package/README.md

@@ -115,16 +115,16 @@ actually resolves.
 
 | Lane | First choice | Backup | When |
 |---|---|---|---|
-| 🔥 hardest-coding | Claude Fable 5.1 (xhigh) | GPT-5.6 Sol (xhigh) | Hardest implementation, deep root-cause debug, correctness-critical edits |
+| 🔥 hardest-coding | Claude Fable 5.1 (xhigh) | GPT-5.6 Sol (xhigh) → Grok 4.6 → Gemini 3.7 Flash (High) | Hardest implementation, deep root-cause debug, correctness-critical edits |
 | 🏗️ bulk-mechanical | GPT-5.6 Sol (high) | Gemini 3.7 Flash (High) → Claude Sonnet 5 (high) | Refactors, migrations, tests, review sweeps — mechanical endurance |
 | 🧹 triage | GPT-5.6 Luna (high) | Gemini 3.7 Flash (Low) → Claude Haiku 4.5 | High-volume scans, first-pass filtering |
-| ⚖️ hard-judgment | Claude Fable 5.1 (xhigh) | GPT-5.6 Sol (max) → Grok 4.6 | Architecture arbitration, deep reasoning, second opinions |
-| ✒️ taste-final | Claude Fable 5.1 (high) | GPT-5.6 Sol (max) | User-facing prose, prompt/doc polish, style arbitration |
+| ⚖️ hard-judgment | Claude Opus 5 (xhigh) | GPT-5.6 Sol (max) → Grok 4.6 | Architecture arbitration, deep reasoning, second opinions |
+| ✒️ taste-final | Claude Fable 5.1 (high) | GPT-5.6 Sol (max) → Grok 4.6 → Gemini 3.7 Flash (High) | User-facing prose, prompt/doc polish, style arbitration |
 | 💬 consult | GPT-5.6 Sol (max) | Claude Fable 5.1 (high) → Grok 4.6 → Gemini 3.7 Flash (High) | Direct named-model consultation; keep `--vendor` to prevent fallback |
-| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude Fable 5.1 (high) | UI drafts only WITH a design system / reference images |
+| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude Fable 5.1 (high) → Gemini 3.7 Flash (High) | UI drafts only WITH a design system / reference images |
 | 📚 long-context | Gemini 3.7 Flash (Medium) | GPT-5.6 Terra (max) → Claude Opus 5 (medium) | Long-document retrieval and synthesis, ordered on AA-LCR, cost, and throughput |
-| ⚡ fast-agentic | Gemini 3.7 Flash (Medium) | GPT-5.6 Luna (high) | Fast multi-step agentic loops, multimodal checks |
-| 📡 live-search | Grok 4.6 | — (off) | Realtime X/web search and social context |
+| ⚡ fast-agentic | Gemini 3.7 Flash (Medium) | GPT-5.6 Luna (high) → Claude Haiku 4.5 | Fast multi-step agentic loops, multimodal checks |
+| 📡 live-search | Grok 4.6 | Gemini 3.7 Flash (High) → Claude Sonnet 5 (high) | Realtime X/web search and social context |
 | 🚰 coding-overflow | Grok 4.6 | Gemini 3.7 Flash (High) → 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 |
 
@@ -157,12 +157,12 @@ with who is driving. What changes is which lanes you **self-execute** (you
 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 5.1** — self-execute: hard-judgment, taste-final, hardest-coding. Dispatch bulk → Codex Sol high; long-context and fast loops → Gemini 3.7 Flash; live-search → Grok.
-- **Claude Code · Opus 5** — self-execute: hard-judgment and taste-final when its lower hallucination rate or price is preferred. Dispatch hardest coding → Fable 5.1 or Sol, bulk → Sol high, long-context and fast loops → Gemini 3.7 Flash, live-search → Grok.
+- **Claude Code · Fable 5.1** — self-execute: taste-final, hardest-coding. Dispatch hard-judgment → Opus 5; bulk → Codex Sol high; long-context and fast loops → Gemini 3.7 Flash; live-search → Grok.
+- **Claude Code · Opus 5** — self-execute: hard-judgment, its default lane. Use a local override for taste-final when its lower hallucination rate or price is preferred. Dispatch hardest coding → Fable 5.1 or Sol, bulk → Sol high, long-context and fast loops → Gemini 3.7 Flash, live-search → Grok.
 - **Codex · Sol** — self-execute: hardest-coding, bulk-mechanical, hard-judgment, ui-draft. Dispatch taste-final → Claude, long-context and fast loops → Gemini 3.7 Flash, live-search → Grok.
 - **Codex · Terra** — self-execute: long-context as the Codex fallback. Bulk-mechanical now defaults to Sol high; escalate hardest pieces to Sol xhigh, taste → Claude, fast loops → Gemini 3.7 Flash, live-search → Grok.
-- **Grok Build · Grok 4.6** — self-execute: live-search and coding-overflow. Dispatch hard coding/judgment/taste to Codex/Claude/Gemini; verify API signatures and cited facts.
-- **Antigravity · Gemini 3.7 Flash** — self-execute: long-context and fast loops at Medium, bulk/overflow at High, triage at Low. Dispatch hardest coding/judgment/taste to Codex/Claude; live-search → Grok.
+- **Grok Build · Grok 4.6** — self-execute: live-search and coding-overflow, plus fallback duty in hardest-coding, hard-judgment, and taste-final. Dispatch primary hard coding/judgment/taste work to Codex/Claude/Gemini when available; verify API signatures and cited facts.
+- **Antigravity · Gemini 3.7 Flash** — self-execute: long-context and fast loops at Medium, bulk/overflow at High, triage at Low, plus fallback duty (High) in hardest-coding, taste-final, ui-draft, and live-search. Dispatch primary hardest coding/judgment/taste to Codex/Claude when available.
 
 </details>
 
@@ -321,7 +321,7 @@ omnilane ui url                                # print the current authenticated
 omnilane ui stop                               # stop the Live UI
 omnilane doctor [--json] [--strict] [--probe V] [--probe-timeout SEC]  # live probe is opt-in
 omnilane benchmark [--json] [--run] [--vendor V] [--cost-per-call V=USD] # dry-run by default
-dispatch.sh [--background] [--dry-run] [--mode advise|work|sysops] [--workdir DIR]
+dispatch.sh [--background] [--dry-run] [--thread NAME] [--mode advise|work|sysops] [--workdir DIR]
             [--vendor V] [--model M] [--effort E] [--timeout SEC] [--job-timeout SEC]
             LANE "TASK"                              # "-" reads task from stdin
 dispatch.sh [--json] --list [--json]
@@ -340,6 +340,11 @@ configure.sh                                        # interactive lane menu
 configure.sh set|get|unset|list|diff LANE [SPEC]    # script/inspect routing.local.yaml, no tty
 ```
 
+`--thread NAME` continues named Claude, Codex, Grok, or Gemini conversations across
+single-shot dispatches. In 0.33.0 it pins vendor, model, effort, and physical
+workdir; use `jobs.sh threads`, `threads show NAME`, or `threads rm NAME` to
+manage local state without deleting the vendor session.
+
 `jobs recommend` reads only validated public metadata and exit codes. It ranks
 eligible vendors by success rate, sample count, then name; the default minimum
 is three completed jobs. It never reads task/result bodies or changes routing.
@@ -471,7 +476,7 @@ whose CLI is actually installed. With one subscription the whole table collapses
 onto that vendor; lanes with nothing available turn off rather than failing.
 `omnilane doctor` shows exactly what your machine can reach today, and
 `routing.local.yaml.example` ships starter profiles for common situations
-(Claude-only, Codex-heavy, no-Codex).
+(Claude-focused, Codex-heavy, no-Codex).
 
 </details>
 
@@ -495,9 +500,12 @@ with the key you set — those are advise-only and never edit files.
 
 <br/>
 
-Fable 5.1 now leads `hardest-coding`, `hard-judgment`, and `taste-final`.
-At matched xhigh effort it leads Opus 5 on intelligence, agentic work, and
-coding. Sol max remains the far cheaper cross-vendor judgment fallback.
+Fable 5.1 now leads `hardest-coding` and `taste-final`. At matched xhigh
+effort it leads Opus 5 on intelligence, agentic work, and coding. Sol max
+remains the far cheaper cross-vendor judgment fallback. `hard-judgment`
+itself now defaults to Opus 5 xhigh: it returns 97.7% of Fable's agentic
+score at 68% of the cost and a lower hallucination rate, so on that lane's
+own per-cost criterion the cheaper configuration wins.
 
 | Benchmark (AA, retrieved 2026-09-02) | Claude Fable 5.1 (xhigh) | Claude Opus 5 (xhigh) | GPT-5.6 Sol (max) |
 |---|---:|---:|---:|
@@ -508,13 +516,13 @@ coding. Sol max remains the far cheaper cross-vendor judgment fallback.
 | AA $/task | $2.65 | $1.80 | **$0.95** |
 
 Fable 5.1 is not a bulk or triage default: it costs twice Opus 5 per token and
-consumes the most Claude Code subscription quota per turn. Opus 5 remains the
-lower-hallucination, lower-price Claude option, stays in `long-context` at
-medium, and remains selectable everywhere through
-`~/.omnilane/routing.local.yaml`:
+consumes the most Claude Code subscription quota per turn. Opus 5 now leads
+`hard-judgment` by default, stays in `long-context` at medium, and remains
+selectable everywhere through `~/.omnilane/routing.local.yaml` — for example,
+to bring Fable back:
 
 ```yaml
-hard-judgment: claude claude-opus-5 xhigh
+hard-judgment: claude claude-fable-5-1 xhigh
 ```
 
 </details>
@@ -594,6 +602,15 @@ working notes, including per-benchmark caveats, live in
 
 ## 📜 Release history
 
+## What's new in v0.33.0
+
+- **Four-vendor threaded dispatch.** `--thread NAME` continues pinned Claude,
+  Codex, Grok, or Gemini conversations across foreground or background
+  single-shot jobs; direct-API vendors, `exec`, live mode, and pin mismatches
+  stop with visible exit-2 notices.
+- **Thread inspection.** `jobs.sh threads`, `threads show NAME`, and
+  `threads rm NAME` list, inspect, or remove local thread state.
+
 ## What's new in v0.32.0
 
 - **Full 2026-09 routing re-evaluation.** Fable 5.1 and Gemini 3.7 Flash enter the defaults, backed by the dated Artificial Analysis snapshot.

package/README.zh-CN.md

@@ -103,16 +103,16 @@ flowchart LR
 
 | 通道 | 首选模型 | 备选模型 | 用途 |
 |---|---|---|---|
-| 🔥 hardest-coding | Claude Fable 5.1 (xhigh) | GPT-5.6 Sol (xhigh) | 最难的实现、深度调试、正确性关键的修改 |
+| 🔥 hardest-coding | Claude Fable 5.1 (xhigh) | GPT-5.6 Sol (xhigh) → Grok 4.6 → Gemini 3.7 Flash (High) | 最难的实现、深度调试、正确性关键的修改 |
 | 🏗️ bulk-mechanical | GPT-5.6 Sol (high) | Gemini 3.7 Flash (High) → Claude Sonnet 5 (high) | 重构、迁移、测试、大范围扫描——机械耐力活 |
 | 🧹 triage | GPT-5.6 Luna (high) | Gemini 3.7 Flash (Low) → Claude Haiku 4.5 | 大量扫描、第一轮筛选 |
-| ⚖️ hard-judgment | Claude Fable 5.1 (xhigh) | GPT-5.6 Sol (max) → Grok 4.6 | 架构裁决、深度推理、第二意见 |
-| ✒️ taste-final | Claude Fable 5.1 (high) | GPT-5.6 Sol (max) | 对外文字、提示词／文档润色、风格裁决 |
+| ⚖️ hard-judgment | Claude Opus 5 (xhigh) | GPT-5.6 Sol (max) → Grok 4.6 | 架构裁决、深度推理、第二意见 |
+| ✒️ taste-final | Claude Fable 5.1 (high) | GPT-5.6 Sol (max) → Grok 4.6 → Gemini 3.7 Flash (High) | 对外文字、提示词／文档润色、风格裁决 |
 | 💬 consult | GPT-5.6 Sol (max) | Claude Fable 5.1 (high) → Grok 4.6 → Gemini 3.7 Flash (High) | 直接指定模型咨询；保留 `--vendor` 避免降级 |
-| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude Fable 5.1 (high) | 仅在提供设计系统／参考图时生成 UI 草稿 |
+| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude Fable 5.1 (high) → Gemini 3.7 Flash (High) | 仅在提供设计系统／参考图时生成 UI 草稿 |
 | 📚 long-context | Gemini 3.7 Flash (Medium) | GPT-5.6 Terra (max) → Claude Opus 5 (medium) | 长文档提取与综合，按 AA-LCR、成本和吞吐排序 |
-| ⚡ fast-agentic | Gemini 3.7 Flash (Medium) | GPT-5.6 Luna (high) | 高速多步骤工具循环、多模态检查 |
-| 📡 live-search | Grok 4.6 | — (`off`) | 实时 X／网页搜索与社交上下文 |
+| ⚡ fast-agentic | Gemini 3.7 Flash (Medium) | GPT-5.6 Luna (high) → Claude Haiku 4.5 | 高速多步骤工具循环、多模态检查 |
+| 📡 live-search | Grok 4.6 | Gemini 3.7 Flash (High) → Claude Sonnet 5 (high) | 实时 X／网页搜索与社交上下文 |
 | 🚰 coding-overflow | Grok 4.6 | Gemini 3.7 Flash (High) → Kimi K3 → Qwen3 Coder Plus → OpenCode | Codex 配额耗尽时的中量级编码安全阀 |
 | 🗳️ arbitrate | `off`（可选模型评审团） | — | 重大决定的内置意见评审团；默认禁用，在 `routing.local.yaml` 启用，每位评审每轮调用一次 |
 
@@ -140,12 +140,12 @@ flowchart LR
 你哪些通道**自己做**(你本来就是那个模型,省一次调用)、哪些**派出去**。你 CLI 里
 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 5.1**——自己执行：hard-judgment、taste-final、hardest-coding。派发：bulk → Codex Sol high；long-context／高速循环 → Gemini 3.7 Flash；实时搜索 → Grok。
-- **Claude Code · Opus 5**——需要更低幻觉率或价格时，自己执行 hard-judgment、taste-final。最难编码 → Fable 5.1 或 Sol；bulk → Sol high；long-context／高速循环 → Gemini 3.7 Flash；实时搜索 → Grok。
+- **Claude Code · Fable 5.1**——自己执行：taste-final、hardest-coding。派发：hard-judgment → Opus 5；bulk → Codex Sol high；long-context／高速循环 → Gemini 3.7 Flash；实时搜索 → Grok。
+- **Claude Code · Opus 5**——自己执行：hard-judgment(默认车道)。需要更低幻觉率或价格时，用本地覆写让它接手 taste-final。最难编码 → Fable 5.1 或 Sol；bulk → Sol high；long-context／高速循环 → Gemini 3.7 Flash；实时搜索 → Grok。
 - **Codex · Sol**——自己执行：hardest-coding、bulk-mechanical、hard-judgment、ui-draft。派发：taste-final → Claude；long-context／高速循环 → Gemini 3.7 Flash；实时搜索 → Grok。
 - **Codex · Terra**——自己执行 long-context 的 Codex 备用任务；bulk-mechanical 现在默认由 Sol high 处理。最难部分升级到 Sol xhigh，taste → Claude，高速循环 → Gemini 3.7 Flash，实时搜索 → Grok。
-- **Grok Build · Grok 4.6**——自己执行 live-search、coding-overflow。最难的编码／判断／文字交给 Codex、Claude、Gemini；仍需验证 API 签名和引用事实。
-- **Antigravity · Gemini 3.7 Flash**——自己执行：Medium 的 long-context／高速循环、High 的 bulk／overflow、Low 的 triage。最难编码／判断／文字交给 Codex、Claude；实时搜索 → Grok。
+- **Grok Build · Grok 4.6**——自己执行 live-search、coding-overflow，并兼任 hardest-coding、hard-judgment、taste-final 的备用。首选可用时，最难的编码／判断／文字交给 Codex、Claude、Gemini；仍需验证 API 签名和引用事实。
+- **Antigravity · Gemini 3.7 Flash**——自己执行：Medium 的 long-context／高速循环、High 的 bulk／overflow、Low 的 triage，并以 High 兼任 hardest-coding、taste-final、ui-draft、live-search 的备用。首选可用时，最难编码／判断／文字交给 Codex、Claude。
 
 </details>
 
@@ -265,7 +265,7 @@ omnilane ui status                             # 查看 Live UI 是否正在运
 omnilane ui url                                # 输出当前通过认证的本地链接
 omnilane ui stop                               # 停止 Live UI
 omnilane doctor [--json]                       # 只读检查路由与本地运行环境
-dispatch.sh [--background] [--dry-run] [--mode advise|work|sysops] [--workdir 目录]
+dispatch.sh [--background] [--dry-run] [--thread NAME] [--mode advise|work|sysops] [--workdir 目录]
             [--vendor V] [--model M] [--effort E] [--timeout SEC] [--job-timeout SEC]
             通道 "任务"                              # "-" 表示从 stdin 读任务
 dispatch.sh [--json] --list [--json]
@@ -283,6 +283,11 @@ configure.sh                                        # 交互通道菜单
 configure.sh set|get|unset|list|diff LANE [SPEC]    # 非交互编辑/查看 routing.local.yaml
 ```
 
+`--thread NAME` 可在多次单次派发间延续命名的 Claude、Codex、Grok 或 Gemini
+对话。0.33.0 会固定厂商、模型、effort 与实际工作目录；使用
+`jobs.sh threads`、`threads show NAME`、`threads rm NAME` 管理本地状态，
+删除状态不会删除厂商端会话。
+
 退出码:`2` 用法错误(包括厂商值无效,或指定厂商不在该通道)、`3` 通道已关闭、
 `4` 候选链没有可用 CLI,或指定厂商已配置但其 CLI 不可用、
 `5` 第一轮成功评审太少、`6` 第二轮没有任何反驳成功、`86` 拒绝嵌套派发、
@@ -398,9 +403,11 @@ omnilane goal close "$GOAL_ID" --summary "结账集成已稳定"
 
 <br/>
 
-Fable 5.1 现在领跑 `hardest-coding`、`hard-judgment`、`taste-final`。
-同为 xhigh 时，它在智能、代理式工作和编码上都领先 Opus 5；Sol max 则保留为
-便宜得多的跨厂商判断备用项。
+Fable 5.1 现在领跑 `hardest-coding`、`taste-final`。同为 xhigh 时，它在
+智能、代理式工作和编码上都领先 Opus 5；Sol max 则保留为便宜得多的跨厂商
+判断备用项。`hard-judgment` 本身现在改为默认走 Opus 5 xhigh：它能拿到
+Fable 代理式分数的 97.7%，成本却只要 68%，幻觉率也更低——按这条车道
+自身的每成本准则，更便宜的配置胜出。
 
 | 评测（AA，抓取于 2026-09-02） | Claude Fable 5.1 (xhigh) | Claude Opus 5 (xhigh) | GPT-5.6 Sol (max) |
 |---|---:|---:|---:|
@@ -411,12 +418,12 @@ Fable 5.1 现在领跑 `hardest-coding`、`hard-judgment`、`taste-final`。
 | AA 每任务成本 | $2.65 | $1.80 | **$0.95** |
 
 Fable 5.1 没进入 bulk 或 triage：每 token 价格是 Opus 5 的两倍，而且每轮
-消耗最多 Claude Code 订阅配额。Opus 5 仍是幻觉率更低、价格更低的 Claude
-选项，并以 medium 保留在 `long-context`；也能通过
-`~/.omnilane/routing.local.yaml` 放回任意通道：
+消耗最多 Claude Code 订阅配额。Opus 5 现在默认领跑 `hard-judgment`，并以
+medium 保留在 `long-context`；也能通过 `~/.omnilane/routing.local.yaml`
+随时放回任意通道——例如把 Fable 换回来：
 
 ```yaml
-hard-judgment: claude claude-opus-5 xhigh
+hard-judgment: claude claude-fable-5-1 xhigh
 ```
 
 </details>
@@ -490,6 +497,14 @@ vendor 一律当成 `work`,而且它只能逐次明确指定,永远不是 lane
 
 ## 📜 版本历程
 
+## v0.33.0 新功能
+
+- **四厂商线程派发。** `--thread NAME` 可让固定厂商、模型、effort 与工作
+  目录的 Claude、Codex、Grok 或 Gemini 对话跨前台或后台单次作业延续；
+  direct-API 厂商、`exec`、实时模式与固定值冲突都会以清晰的退出码 2 提示停止。
+- **线程状态管理。** `jobs.sh threads`、`threads show NAME`、`threads rm NAME`
+  可列出、查看或删除本地线程状态。
+
 ## v0.32.0 新功能
 
 - **基于 AA 2026-09 快照全面重评路由。** Fable 5.1 和 Gemini 3.7 Flash 进入默认表，数据集中在新的日期化文档。