omnilane 0.8.3 → 0.9.0

package/CHANGELOG.md

@@ -6,6 +6,54 @@ semantic version tags.
 
 ## [Unreleased]
 
+## [0.9.0] - 2026-07-19
+
+### Added
+
+- `omnilane completion fish` prints a Fish completion script
+  (`completions/omnilane.fish`): static command, option, and enum completion for
+  every public command, including the direct-API vendors and `jobs cancel`/`rm`.
+  Load it with `omnilane completion fish | source`. Dynamic lane-name and job-id
+  completion remain Bash/Zsh-only for now.
+- Five OpenAI-compatible direct-API vendors — `deepseek`, `zai` (GLM),
+  `mistral`, `groq`, and `cerebras` — join `openrouter` as CLI-free inference
+  lanes (curl + a `<VENDOR>_API_KEY`, advise mode only). A single vendor registry
+  in `lib/common.sh` (endpoint, key env, and default model per vendor) now drives
+  every vendor-name check in `dispatch.sh` and `jobs.sh`, so adding another
+  OpenAI-compatible vendor is a one-line registry entry plus a thin runner
+  wrapper. `configure` lists them with suggested models. See
+  `docs/model-capabilities-2026-07.md` for the July 2026 model/benchmark snapshot
+  behind the routing defaults.
+- `omnilane doctor` now reports vendor-CLI availability: which of codex, claude,
+  grok, gemini (the `agy` CLI), kimi, qwen, and opencode are reachable, plus
+  the direct-API vendors openrouter, deepseek, zai, mistral, groq, and cerebras
+  (curl + each `<VENDOR>_API_KEY`). Shown in human and `--json` output;
+  the probe mirrors the runners' `*_BIN` overrides and `local.sh` in an isolated
+  subshell. It is a `PASS`/`WARN` check and never fails the report.
+- MCP server read-only introspection tools: `explain`, `validate`, `dry_run`,
+  `jobs_list`, `jobs_stats`, `jobs_audit`, and `doctor` join the existing
+  `route`, `list_lanes`, `jobs_status`, and `jobs_result`, so the MCP surface
+  mirrors the CLI's full offline read-only surface. All refuse provider calls and
+  create no job state; `dry_run` requires an explicit `workdir` only when `mode`
+  is `work`. `jobs_stats`/`jobs_audit` accept an optional `last` and `json`.
+- `configure set|get|unset|list|diff` non-interactive subcommands: script or
+  inspect `routing.local.yaml` without a tty. `set` validates the lane, refuses
+  unsafe specs, and rolls back on a structural FAIL; `diff` shows how local
+  overrides change the effective table versus the defaults. The interactive menu
+  is unchanged.
+- `jobs list` and `jobs stats` filters: `--lane` and `--vendor` (and, for
+  `list`, `--status running|done`) narrow the output in both human and `--json`
+  modes. `list` scans all jobs for up to 20 matches; `stats` filters within its
+  `--last` sample and recomputes the success rate and lane/vendor aggregates.
+  Invalid filter values exit 2; unfiltered behavior is unchanged.
+- `jobs cancel ID`: stop a running background job. Signals the worker's process
+  group (SIGTERM, then SIGKILL after a grace period) so the vendor CLI child
+  dies too, and leaves a terminal exit recorded — 143 on graceful stop, 137 if
+  force-killed. Idempotent on already-finished, dead, or never-backgrounded jobs.
+- `jobs rm ID`: delete one job's stored directory (task, output, exit, metadata).
+  Refuses a job whose worker is still alive — cancel it first — complementing
+  `jobs prune`, which only bulk-deletes completed jobs by count or age.
+
 ## [0.8.3] - 2026-07-18
 
 ### Added
@@ -259,7 +307,8 @@ semantic version tags.
 - Initial shared routing table, cross-vendor dispatcher, runners, installer,
   and baseline lint fixes.
 
-[Unreleased]: https://github.com/Seraphim0916/omnilane/compare/v0.8.3...HEAD
+[Unreleased]: https://github.com/Seraphim0916/omnilane/compare/v0.9.0...HEAD
+[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
 [0.8.2]: https://github.com/Seraphim0916/omnilane/compare/v0.8.1...v0.8.2
 

package/README.ja.md

@@ -21,6 +21,14 @@
 
 ---
 
+## v0.9.0 の新機能
+
+- **OpenAI 互換の direct-API ベンダーを 5 つ追加** — `deepseek`、`zai`(GLM)、
+  `mistral`、`groq`、`cerebras` が `openrouter` と同じく CLI 不要のレーンに
+  (curl と `<VENDOR>_API_KEY` だけ)。`lib/common.sh` のレジストリに 1 行で
+  追加でき、モデル能力の比較は [`docs/model-capabilities-2026-07.md`](docs/model-capabilities-2026-07.md) を参照。
+- **Fish シェル補完** — `omnilane completion fish | source`。
+
 ## v0.8.3 の新機能
 
 - **MCP サーバー** — `omnilane mcp` は依存ゼロの stdio MCP サーバーを起動し、
@@ -148,6 +156,8 @@ flowchart LR
   指定ベンダーに固定し、フォールバックしません。
 - **`skills/omnilane/SKILL.md`** — 四つのハーネス共通のスキル:
   自分のモデルを特定し、自分のレーンは自前で実行、残りはディスパッチ。
+- **`omnilane mcp`** — 同じルーティングを MCP stdio サーバーとして提供。
+  スキルではなく MCP で統合するホスト向け。
 
 <div align="center">
 
@@ -301,10 +311,13 @@ MCP 対応ホストがスキルの導入やルーティングリマインダー
 }
 ```
 
-サーバーは `route`、`jobs_status`、`jobs_result`、`list_lanes` を公開します。
+サーバーは `route` に加えて、読み取り専用の照会ツール `list_lanes`、`explain`、`validate`、`dry_run`、`jobs_list`、`jobs_status`、`jobs_result`、`jobs_stats`、`jobs_audit`、`doctor` を公開します。
 `route` のデフォルトは読み取り専用の `advise` モードで、`work` を選ぶ呼び
 出しには明示的な `workdir` が必須です。
 
+実行時に必要なのは Node.js のみ(npm パッケージは不要)。npm 派なら
+`npm install -g omnilane` で MCP サーバーごと CLI をインストールできます。
+
 ## ⚙️ カスタマイズ
 
 三層、すべて任意:
@@ -329,6 +342,8 @@ scripts/dispatch.sh --list     # 実効テーブル(フォールバック解決
 ```
 eval "$(omnilane completion bash)"             # 現在の Bash で補完を有効化
 source <(omnilane completion zsh)               # 現在の Zsh で補完を有効化
+omnilane completion fish | source              # 現在の Fish で補完を有効化
+omnilane mcp                                   # MCP stdio サーバー(Node.js が必要)
 omnilane release-audit [--target VERSION] [--json] # オフライン・読み取り専用のリリースゲート
 omnilane ui start                              # ローカル Live UI を起動または再利用し、URL を表示
 omnilane ui status                             # Live UI の稼働状態を表示
@@ -342,11 +357,15 @@ dispatch.sh [--json] --list [--json]
 dispatch.sh [--json] --explain LANE [--json]       # 候補ごとの決定理由をオフライン表示
 dispatch.sh [--json] --validate [--json]           # プロバイダーを呼ばず実効ルーティングを検証
 jobs.sh [--json] {list | status ID | result ID}    # JSON は本文を返さずメタデータのみ
+jobs.sh [--json] list [--lane L] [--vendor V] [--status running|done]  # 一覧を絞り込み
 jobs.sh wait ID [--timeout N]                     # ジョブ終了値。124 はタイムアウト、125 はワーカー消失
-jobs.sh [--json] stats [--last N]                  # ローカル成功率とルーティング集計
+jobs.sh cancel ID                                 # 実行中ジョブを停止:グループに SIGTERM、その後 SIGKILL
+jobs.sh rm ID                                     # 完了/停止ジョブを1件削除(実行中は拒否)
+jobs.sh [--json] stats [--last N] [--lane L] [--vendor V]  # ローカル成功率とルーティング集計
 jobs.sh audit [--last N] [--json]                  # 読み取り専用のジョブ整合性・プライバシー検査
 jobs.sh prune [--keep N] [--apply]                # 既定はプレビューのみ。完了ジョブだけを対象
 configure.sh                                        # 対話式レーンメニュー
+configure.sh set|get|unset|list|diff LANE [SPEC]    # routing.local.yaml を非対話で編集/確認
 ```
 
 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
@@ -419,11 +438,12 @@ configure.sh                                        # 対話式レーンメニ
 
 ## 🌱 ステータス
 
-v0.8.3 は 8 つのディスパッチベンダーを備えます——4 つのハーネスネイティブ
+omnilane は 13 のディスパッチベンダーを備えます——4 つのハーネスネイティブ
 (codex、claude、grok、gemini)、3 つの集約/オーバーフロー CLI(kimi、qwen、
-opencode)、そして CLI 不要の `openrouter` 直接 API ベンダー——すべて統一
-runner 契約と契約テスト付き。Claude Code の `SessionStart` 自動リマインダー
-も同梱。kimi、qwen、opencode、openrouter の runner はフェイクバイナリで
+opencode)、そして CLI 不要の OpenAI 互換 direct-API ベンダー 6 つ(openrouter、
+deepseek、zai、mistral、groq、cerebras)——すべて統一 runner 契約と契約テスト
+付き。Claude Code の `SessionStart` 自動リマインダーと MCP stdio サーバー
+(`omnilane mcp`)も同梱。direct-API と集約系の runner はフェイクバイナリで
 契約テスト済みです。実モデルでの報告を歓迎します。Grok/Antigravity の
 コマンドシェル挙動は CLI バージョンで変わる可能性があります。issue と PR を
 歓迎します。

package/README.ko.md

@@ -21,6 +21,14 @@
 
 ---
 
+## v0.9.0 새 기능
+
+- **OpenAI 호환 direct-API 벤더 5개 추가** — `deepseek`, `zai` (GLM), `mistral`,
+  `groq`, `cerebras` 가 `openrouter` 처럼 CLI 없는 레인으로 추가(curl 과
+  `<VENDOR>_API_KEY` 만 필요). `lib/common.sh` 레지스트리에 한 줄로 추가되며,
+  모델 능력 비교는 [`docs/model-capabilities-2026-07.md`](docs/model-capabilities-2026-07.md) 참고.
+- **Fish 셸 자동완성** — `omnilane completion fish | source`.
+
 ## v0.8.3 새 기능
 
 - **MCP 서버** — `omnilane mcp` 는 의존성 없는 stdio MCP 서버를 시작하여,
@@ -147,6 +155,8 @@ flowchart LR
   고정하며 폴백하지 않습니다.
 - **`skills/omnilane/SKILL.md`** — 네 하네스 공용 스킬: 자기 모델을 파악하고,
   자기 레인은 직접 수행, 나머지는 디스패치.
+- **`omnilane mcp`** — 같은 라우팅을 MCP stdio 서버로 제공.
+  스킬 대신 MCP 로 통합하는 호스트용.
 
 <div align="center">
 
@@ -294,10 +304,13 @@ MCP 지원 호스트가 스킬 설치나 라우팅 리마인더 없이 omnilane
 }
 ```
 
-서버는 `route`, `jobs_status`, `jobs_result`, `list_lanes` 를 제공합니다.
+서버는 `route` 와 함께 읽기 전용 조회 도구 `list_lanes`, `explain`, `validate`, `dry_run`, `jobs_list`, `jobs_status`, `jobs_result`, `jobs_stats`, `jobs_audit`, `doctor` 를 제공합니다.
 `route` 의 기본값은 읽기 전용 `advise` 모드이며, `work` 를 선택한 호출은
 명시적 `workdir` 을 함께 제공해야 합니다.
 
+실행에 필요한 것은 Node.js 뿐입니다(npm 패키지 없음). npm 을 선호하면
+`npm install -g omnilane` 으로 MCP 서버가 포함된 CLI 를 설치할 수 있습니다.
+
 ## ⚙️ 사용자 설정
 
 세 계층, 모두 선택 사항:
@@ -322,6 +335,8 @@ scripts/dispatch.sh --list     # 실효 테이블(폴백 해석 주석 포함)
 ```
 eval "$(omnilane completion bash)"             # 현재 Bash 에서 완성 활성화
 source <(omnilane completion zsh)               # 현재 Zsh 에서 완성 활성화
+omnilane completion fish | source              # 현재 Fish 에서 완성 활성화
+omnilane mcp                                   # MCP stdio 서버(Node.js 필요)
 omnilane release-audit [--target VERSION] [--json] # 오프라인 읽기 전용 릴리스 게이트
 omnilane ui start                              # 로컬 Live UI 를 시작하거나 재사용하고 URL 표시
 omnilane ui status                             # Live UI 실행 상태 표시
@@ -335,11 +350,15 @@ dispatch.sh [--json] --list [--json]
 dispatch.sh [--json] --explain LANE [--json]       # 후보별 라우팅 결정을 오프라인 설명
 dispatch.sh [--json] --validate [--json]           # 공급자 호출 없이 실효 라우팅 검사
 jobs.sh [--json] {list | status ID | result ID}    # JSON은 본문 없이 메타데이터만 반환
+jobs.sh [--json] list [--lane L] [--vendor V] [--status running|done]  # 목록 필터
 jobs.sh wait ID [--timeout N]                     # 작업 종료값, 124 시간 초과, 125 작업자 소실
-jobs.sh [--json] stats [--last N]                  # 로컬 성공률과 라우팅 집계
+jobs.sh cancel ID                                 # 실행 중 작업 중지: 그룹 SIGTERM 후 SIGKILL
+jobs.sh rm ID                                     # 완료/종료 작업 1건 삭제(실행 중이면 거부)
+jobs.sh [--json] stats [--last N] [--lane L] [--vendor V]  # 로컬 성공률과 라우팅 집계
 jobs.sh audit [--last N] [--json]                  # 읽기 전용 작업 무결성/개인정보 검사
 jobs.sh prune [--keep N] [--apply]                # 기본은 미리보기이며 완료된 작업만 정리
 configure.sh                                        # 대화형 레인 메뉴
+configure.sh set|get|unset|list|diff LANE [SPEC]    # routing.local.yaml 비대화식 편집/확인
 ```
 
 종료 코드: `2` 사용법 오류(잘못된 벤더 또는 지정 벤더가 레인에 없는 경우 포함),
@@ -407,10 +426,11 @@ CLI 를 사용할 수 없음, `5` 1라운드 성공 투표자 부족, `6` 2라
 
 ## 🌱 상태
 
-v0.8.3 는 8개의 디스패치 벤더를 갖춥니다——4개의 하네스 네이티브(codex,
+omnilane 은 13개의 디스패치 벤더를 갖춥니다——4개의 하네스 네이티브(codex,
 claude, grok, gemini), 3개의 집합/오버플로 CLI(kimi, qwen, opencode), 그리고
-CLI 가 필요 없는 `openrouter` 직접 API 벤더——모두 통일 runner 계약과 계약
-테스트를 갖추었고, Claude Code `SessionStart` 자동 리마인더도 포함합니다.
+CLI 가 필요 없는 OpenAI 호환 direct-API 벤더 6개(openrouter, deepseek, zai,
+mistral, groq, cerebras)——모두 통일 runner 계약과 계약 테스트를 갖추었고,
+Claude Code `SessionStart` 자동 리마인더와 MCP stdio 서버(`omnilane mcp`)도 포함합니다.
 kimi, qwen, opencode, openrouter 의 runner 는 페이크 바이너리로 계약 테스트를
 마쳤습니다. 실제 모델 사용 보고를 환영합니다. Grok/Antigravity 커맨드 셸
 동작은 CLI 버전에 따라 달라질 수 있습니다. issue 와 PR 환영합니다.

package/README.md

@@ -21,6 +21,14 @@ or any hosted model via OpenRouter — on the subscriptions you already pay for,
 
 ---
 
+## What's new in v0.9.0
+
+- **Five OpenAI-compatible direct-API vendors** — `deepseek`, `zai` (GLM),
+  `mistral`, `groq`, and `cerebras` join `openrouter` as CLI-free lanes (curl +
+  a `<VENDOR>_API_KEY`). A one-line `lib/common.sh` registry entry adds each;
+  see [`docs/model-capabilities-2026-07.md`](docs/model-capabilities-2026-07.md).
+- **Fish shell completion** — `omnilane completion fish | source`.
+
 ## What's new in v0.8.3
 
 - **MCP server** — `omnilane mcp` starts a zero-dependency stdio MCP server,
@@ -37,6 +45,12 @@ or any hosted model via OpenRouter — on the subscriptions you already pay for,
   Advise/consult only (it cannot edit files; work mode fails with guidance)
   and the model slug is mandatory, e.g.
   `dispatch.sh --vendor openrouter --model anthropic/claude-sonnet-5 consult "..."`.
+- **`deepseek`, `zai`, `mistral`, `groq`, `cerebras` vendors** — the same
+  CLI-free direct-API path as `openrouter`, for OpenAI-compatible providers:
+  DeepSeek, Z.ai GLM, Mistral, Groq, and Cerebras. Each needs only `curl` and
+  its `<VENDOR>_API_KEY`; advise/consult only. A one-line `lib/common.sh`
+  registry entry defines each endpoint, key env, and default model. See
+  [`docs/model-capabilities-2026-07.md`](docs/model-capabilities-2026-07.md).
 - **`opencode` vendor** — headless dispatch through the OpenCode
   multi-provider aggregator CLI (`opencode run`). Advise mode pins OpenCode's
   built-in read-only `plan` agent; work mode uses `--auto`. Joins the default
@@ -149,6 +163,8 @@ flowchart LR
   vendor without fallback.
 - **`skills/omnilane/SKILL.md`** — a single skill every harness can load:
   identify your own model, self-execute your lane, dispatch the rest.
+- **`omnilane mcp`** — the same routing surface as an MCP stdio server,
+  for hosts that integrate via MCP instead of skills.
 
 <div align="center">
 
@@ -301,10 +317,15 @@ adding a routing reminder. Configure the host to launch the installed CLI:
 }
 ```
 
-The server exposes `route`, `jobs_status`, `jobs_result`, and `list_lanes`.
-`route` defaults to read-only `advise` mode. Calls that select `work` must also
+The server exposes `route` plus read-only introspection: `list_lanes`,
+`explain`, `validate`, `dry_run`, `jobs_list`, `jobs_status`, `jobs_result`,
+`jobs_stats`, `jobs_audit`, and `doctor`. `route` defaults to read-only `advise` mode. Calls that select `work` must also
 provide an explicit `workdir`.
 
+Node.js is the only runtime requirement (no npm packages). If you prefer
+npm, `npm install -g omnilane` installs the CLI with the MCP server
+included.
+
 ## ⚙️ Configure
 
 Three layers, all optional:
@@ -314,6 +335,9 @@ Three layers, all optional:
    future models), and writes the result to `~/.omnilane/routing.local.yaml`.
    It intentionally skips the multi-vendor `consult` lane; edit that one by
    hand if needed. `install.sh` offers to run the menu at the end of a normal install.
+   For scripting, `configure set|get|unset|list|diff LANE [SPEC]` edits or inspects the same file
+   without a tty — `set` validates the lane and rejects an unsafe or structurally
+   invalid spec, rolling back on failure.
 2. **`~/.omnilane/routing.local.yaml`** — hand-edited overrides, same format
    as `routing.yaml`; local lines win. See `routing.local.yaml.example`.
 3. **`~/.omnilane/local.sh`** — per-machine binaries, proxies, auth wrappers;
@@ -332,6 +356,8 @@ omnilane list | route … | jobs … | configure   # global wrapper, works anywh
                                                # (install.sh links it into ~/.local/bin)
 eval "$(omnilane completion bash)"             # enable Bash completion for this shell
 source <(omnilane completion zsh)               # enable Zsh completion for this shell
+omnilane completion fish | source              # enable Fish completion for this shell
+omnilane mcp                                   # MCP stdio server (needs Node.js)
 omnilane release-audit [--target VERSION] [--json] # offline, read-only release gate
 omnilane ui start                              # start/reuse the local Live UI; print its URL
 omnilane ui status                             # report whether the Live UI is running
@@ -345,11 +371,15 @@ dispatch.sh [--json] --list [--json]
 dispatch.sh [--json] --explain LANE [--json]       # offline candidate-by-candidate decision trace
 dispatch.sh [--json] --validate [--json]           # lint effective routing; no provider calls
 jobs.sh [--json] {list | status ID | result ID}    # JSON result reports metadata, never bodies
+jobs.sh [--json] list [--lane L] [--vendor V] [--status running|done]  # filter the listing
 jobs.sh wait ID [--timeout N]                     # job exit; 124 timeout; 125 dead worker
-jobs.sh [--json] stats [--last N]                  # local success and routing aggregates
+jobs.sh cancel ID                                 # stop a running job: group SIGTERM, then SIGKILL
+jobs.sh rm ID                                     # delete one finished/dead job (refuses a running job)
+jobs.sh [--json] stats [--last N] [--lane L] [--vendor V]  # local success and routing aggregates
 jobs.sh audit [--last N] [--json]                  # read-only job integrity/privacy check
 jobs.sh prune [--keep N] [--apply]                # preview by default; completed jobs only
 configure.sh                                        # interactive lane menu
+configure.sh set|get|unset|list|diff LANE [SPEC]    # script/inspect routing.local.yaml, no tty
 ```
 
 **Big decisions can get a panel, not a person.** The `arbitrate` lane ships
@@ -439,11 +469,13 @@ configurator and `routing.local.yaml` exist so you can disagree.
 
 ## 🌱 Status
 
-v0.8.3 spans eight dispatch vendors — four harness natives (codex, claude,
-grok, gemini), three aggregator/overflow CLIs (kimi, qwen, opencode), and the
-CLI-free `openrouter` direct-API vendor — on the uniform runner contract with
-contract tests, plus the Claude Code `SessionStart` auto-reminder. kimi, qwen,
-opencode, and openrouter runners are contract-tested against fake binaries;
+omnilane now spans thirteen dispatch vendors — four harness natives (codex,
+claude, grok, gemini), three aggregator/overflow CLIs (kimi, qwen, opencode),
+and six CLI-free OpenAI-compatible direct-API vendors (openrouter, deepseek,
+zai, mistral, groq, cerebras) — on the uniform runner contract with
+contract tests, plus the Claude Code `SessionStart`
+auto-reminder and an MCP stdio server surface (`omnilane mcp`). The direct-API
+and aggregator runners are contract-tested against fake binaries;
 real-model reports welcome. Grok/Antigravity command-shell behavior may still
 vary across CLI versions. Issues and PRs welcome.
 

package/README.zh-CN.md

@@ -21,6 +21,11 @@
 
 ---
 
+## v0.9.0 新功能
+
+- **新增 5 个 OpenAI-compatible direct-API vendor** — `deepseek`、`zai`(GLM)、`mistral`、`groq`、`cerebras`,与 `openrouter` 同为免 CLI 通道(curl 加一把 `<VENDOR>_API_KEY`);`lib/common.sh` registry 一行即加一个。详见 [`docs/model-capabilities-2026-07.md`](docs/model-capabilities-2026-07.md)。
+- **fish shell 补全** — `omnilane completion fish | source`。
+
 ## v0.8.3 新功能
 
 - **MCP server** — `omnilane mcp` 启动零依赖的 stdio MCP server,任何支持
@@ -131,6 +136,8 @@ flowchart LR
   调用对应厂商的 CLI。`--vendor` 会锁定指定厂商，不做降级。
 - **`skills/omnilane/SKILL.md`** — 一份技能四个框架都能加载:
   先认出自己是哪个模型,自己通道的活自己干,其余派出去。
+- **`omnilane mcp`** — 同一套路由改以 MCP stdio server 提供,
+  给走 MCP 而非 skill 集成的宿主。
 
 <div align="center">
 
@@ -267,10 +274,13 @@ Esc。服务器发送事件(SSE)会实时更新，又不会重建当前聚焦的
 }
 ```
 
-Server 提供 `route`、`jobs_status`、`jobs_result`、`list_lanes` 四个工具。
+Server 提供 `route`,以及一组只读查询工具:`list_lanes`、`explain`、`validate`、`dry_run`、`jobs_list`、`jobs_status`、`jobs_result`、`jobs_stats`、`jobs_audit`、`doctor`。
 `route` 默认只读 `advise` 模式;选择 `work` 的调用必须同时提供明确的
 `workdir`。
 
+唯一的运行需求是 Node.js(不装任何 npm 包);也可以直接
+`npm install -g omnilane`,CLI 连同 MCP server 一起装好。
+
 ## ⚙️ 自定义设置
 
 三层,全部可选:
@@ -295,6 +305,8 @@ scripts/dispatch.sh --list     # 生效表,标出候选链降级与关闭的通
 ```
 eval "$(omnilane completion bash)"             # 在当前 Bash 启用补全
 source <(omnilane completion zsh)               # 在当前 Zsh 启用补全
+omnilane completion fish | source
+omnilane mcp                                   # MCP stdio server(需 Node.js)
 omnilane release-audit [--target 版本] [--json]     # 离线、只读的发布闸门
 omnilane ui start                              # 启动或复用本地 Live UI,输出链接
 omnilane ui status                             # 查看 Live UI 是否正在运行
@@ -308,11 +320,15 @@ dispatch.sh [--json] --list [--json]
 dispatch.sh [--json] --explain 通道 [--json]       # 离线逐候选解释路由决策
 dispatch.sh [--json] --validate [--json]           # 离线检查生效路由，不调用模型
 jobs.sh [--json] {list | status 作业ID | result 作业ID} # JSON 结果只回元数据，不回正文
+jobs.sh [--json] list [--lane L] [--vendor V] [--status running|done]  # 过滤列表
 jobs.sh wait 作业ID [--timeout N]                  # 作业退出码；124 超时；125 工作进程消失
-jobs.sh [--json] stats [--last N]                  # 本机成功率与路由汇总
+jobs.sh cancel 作业ID                              # 停止运行中的作业:整组 SIGTERM,再 SIGKILL
+jobs.sh rm 作业ID                                  # 删除单个已完成/已死作业(运行中会被拒绝)
+jobs.sh [--json] stats [--last N] [--lane L] [--vendor V]  # 本机成功率与路由汇总
 jobs.sh audit [--last N] [--json]                  # 只读检查作业完整性与隐私
 jobs.sh prune [--keep N] [--apply]                # 默认仅预览；只清理已完成作业
 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
 ```
 
 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、
@@ -380,12 +396,7 @@ configure.sh                                        # 交互通道菜单
 
 ## 🌱 状态
 
-v0.8.3 共有八个派发 vendor——四个框架原生(codex、claude、grok、gemini)、
-三个聚合/溢流 CLI(kimi、qwen、opencode),加上免 CLI 的 `openrouter` 直连
-API vendor——全部走统一 runner 契约并附 contract 测试,另有 Claude Code
-`SessionStart` 自动提醒。kimi、qwen、opencode、openrouter 的 runner 以假
-可执行文件做过契约测试;欢迎反馈真实模型使用经验。Grok/Antigravity 命令壳
-行为仍可能随 CLI 版本变动。欢迎提交 issue 与 PR。
+omnilane 现有 13 个派工 vendor——4 个框架原生(codex、claude、grok、gemini)、3 个聚合/溢流 CLI(kimi、qwen、opencode),加上 6 个免 CLI 的 OpenAI-compatible direct-API vendor(openrouter、deepseek、zai、mistral、groq、cerebras)——全部走统一 runner 契约并附 contract 测试,另有 Claude Code `SessionStart` 自动提醒与 MCP stdio server 介面(`omnilane mcp`)。direct-API 与聚合 runner 皆以假可执行档做过契约测试;欢迎反馈真实模型使用经验。Grok/Antigravity 命令壳行为仍可能随 CLI 版本变动。欢迎提交 issue 与 PR。
 
 项目文档：[贡献指南](CONTRIBUTING.md) · [安全政策](SECURITY.md) ·
 [变更记录](CHANGELOG.md)

package/README.zh-TW.md

@@ -21,6 +21,14 @@
 
 ---
 
+## v0.9.0 新功能
+
+- **五個 OpenAI-compatible direct-API vendor** — `deepseek`、`zai`(GLM)、
+  `mistral`、`groq`、`cerebras`,與 `openrouter` 同為免 CLI 通道(curl 加一把
+  `<VENDOR>_API_KEY`);`lib/common.sh` registry 一行即加一個。詳見
+  [`docs/model-capabilities-2026-07.md`](docs/model-capabilities-2026-07.md)。
+- **fish shell 補全** — `omnilane completion fish | source`。
+
 ## v0.8.3 新功能
 
 - **MCP server** — `omnilane mcp` 啟動零依賴的 stdio MCP server,任何支援
@@ -36,6 +44,11 @@
   託管模型,不必再裝任何代理 CLI。僅限 advise/consult(不能改檔,
   work 模式會明確報錯指路),模型 slug 必填,例如
   `dispatch.sh --vendor openrouter --model anthropic/claude-sonnet-5 consult "..."`。
+- **`deepseek`、`zai`、`mistral`、`groq`、`cerebras` vendor** — 與 `openrouter`
+  同一條免 CLI 直連 API 路徑,對應 OpenAI-compatible 供應商:DeepSeek、Z.ai GLM、
+  Mistral、Groq、Cerebras。各只要 `curl` 加自己那把 `<VENDOR>_API_KEY`;僅限
+  advise/consult。端點、金鑰、預設模型由 `lib/common.sh` 一行 registry 定義。
+  詳見 [`docs/model-capabilities-2026-07.md`](docs/model-capabilities-2026-07.md)。
 - **`opencode` vendor** — 透過 OpenCode 多供應商聚合 CLI 無頭派工
   (`opencode run`)。advise 模式鎖定內建唯讀 `plan` agent;work 模式
   用 `--auto`。加入預設 `coding-overflow` 鏈作為最後備援。
@@ -131,6 +144,8 @@ flowchart LR
   呼叫對應廠商的 CLI。`--vendor` 會鎖定點名廠商，不做降級。
 - **`skills/omnilane/SKILL.md`** — 一份技能四個框架都能載入:
   先認出自己是哪個模型,自己通道的活自己做,其餘派出去。
+- **`omnilane mcp`** — 同一套路由改以 MCP stdio server 提供,
+  給走 MCP 而非 skill 整合的宿主。
 
 <div align="center">
 
@@ -268,10 +283,13 @@ omnilane ui stop     # 正常停止
 }
 ```
 
-Server 提供 `route`、`jobs_status`、`jobs_result`、`list_lanes` 四個工具。
+Server 提供 `route`,以及一組唯讀查詢工具:`list_lanes`、`explain`、`validate`、`dry_run`、`jobs_list`、`jobs_status`、`jobs_result`、`jobs_stats`、`jobs_audit`、`doctor`。
 `route` 預設唯讀 `advise` 模式;選 `work` 的呼叫必須同時提供明確的
 `workdir`。
 
+唯一的執行需求是 Node.js(不裝任何 npm 套件);也可以直接
+`npm install -g omnilane`,CLI 連同 MCP server 一起裝好。
+
 ## ⚙️ 自訂設定
 
 三層,全部選用:
@@ -298,6 +316,7 @@ omnilane list | route … | jobs … | configure   # 全域指令,任何目錄
                                                # (install.sh 會連結進 ~/.local/bin)
 eval "$(omnilane completion bash)"             # 在目前 Bash 啟用補全
 source <(omnilane completion zsh)               # 在目前 Zsh 啟用補全
+omnilane completion fish | source              # 在目前 Fish 啟用補全
 omnilane ui start                              # 啟動或沿用本機 Live UI,印出網址
 omnilane ui status                             # 查看 Live UI 是否運作中
 omnilane ui url                                # 印出目前通過驗證的本機網址
@@ -310,12 +329,17 @@ dispatch.sh [--json] --list [--json]
 dispatch.sh [--json] --explain 通道 [--json]       # 離線逐候選解釋路由決策
 dispatch.sh [--json] --validate [--json]           # 離線檢查生效路由，不呼叫模型
 jobs.sh [--json] {list | status 工作ID | result 工作ID} # JSON 結果只回中繼資料，不回本文
+jobs.sh [--json] list [--lane L] [--vendor V] [--status running|done]  # 過濾清單
 jobs.sh wait 工作ID [--timeout N]                  # 工作結束碼；124 逾時；125 工作者消失
-jobs.sh [--json] stats [--last N]                  # 本機成功率與路由彙整
+jobs.sh cancel 工作ID                              # 停止執行中的工作:整組 SIGTERM,再 SIGKILL
+jobs.sh rm 工作ID                                  # 刪除單一已完成/已死工作(執行中會被拒絕)
+jobs.sh [--json] stats [--last N] [--lane L] [--vendor V]  # 本機成功率與路由彙整
 jobs.sh audit [--last N] [--json]                  # 唯讀檢查工作完整性與隱私
 jobs.sh prune [--keep N] [--apply]                # 預設只預覽；只清理已完成工作
+omnilane mcp                                   # MCP stdio server(需 Node.js)
 omnilane release-audit [--target 版本] [--json]     # 離線、唯讀的發布閘門
 configure.sh                                        # 互動通道選單
+configure.sh set|get|unset|list|diff LANE [SPEC]    # 非互動編輯/檢視 routing.local.yaml
 ```
 
 **重大決定可以開評審團,不是問一個人。**`arbitrate` 通道**預設關閉**——
@@ -390,10 +414,11 @@ codex/claude/grok/gemini 自選 1-4 個評審。開了之後,同一個問題丟
 
 ## 🌱 狀態
 
-v0.8.3 共有八個派工 vendor——四個框架原生(codex、claude、grok、gemini)、
-三個聚合/溢流 CLI(kimi、qwen、opencode),加上免 CLI 的 `openrouter` 直連
-API vendor——全部走統一 runner 契約並附 contract 測試,另有 Claude Code
-`SessionStart` 自動提醒。kimi、qwen、opencode、openrouter 的 runner 以假
+omnilane 現有十三個派工 vendor——四個框架原生(codex、claude、grok、gemini)、
+三個聚合/溢流 CLI(kimi、qwen、opencode),加上六個免 CLI 的 OpenAI-compatible
+直連 API vendor(openrouter、deepseek、zai、mistral、groq、cerebras)——全部走
+統一 runner 契約並附 contract 測試,另有 Claude Code `SessionStart` 自動提醒與
+MCP stdio server 介面(`omnilane mcp`)。直連 API 與聚合 runner 皆以假
 執行檔做過契約測試;歡迎回報真實模型使用經驗。Grok/Antigravity 指令殼行為
 仍可能隨 CLI 版本變動。歡迎回報 issue 與 PR。
 

package/VERSION

@@ -1 +1 @@
-0.8.3
+0.9.0

package/bin/omnilane

@@ -40,13 +40,14 @@ case "$cmd" in
     ;;
   completion)
     [[ $# -eq 1 ]] || {
-      echo "usage: omnilane completion bash|zsh" >&2
+      echo "usage: omnilane completion bash|zsh|fish" >&2
       exit 2
     }
     case "$1" in
       bash) cat "$REPO/completions/omnilane.bash" ;;
       zsh)  cat "$REPO/completions/_omnilane" ;;
-      *) echo "usage: omnilane completion bash|zsh" >&2; exit 2 ;;
+      fish) cat "$REPO/completions/omnilane.fish" ;;
+      *) echo "usage: omnilane completion bash|zsh|fish" >&2; exit 2 ;;
     esac
     ;;
   release-audit) exec bash "$REPO/scripts/release-audit.sh" "$@" ;;
@@ -69,7 +70,7 @@ omnilane — one routing table, every harness
                                         dispatch or consult a model
   omnilane jobs  [--json] COMMAND [ARGS]  list, status, result, stats, wait, or audit
   omnilane mcp                          start the MCP stdio server
-  omnilane completion bash|zsh           print a shell completion script
+  omnilane completion bash|zsh|fish      print a shell completion script
   omnilane release-audit [flags]          offline, read-only release gate
   omnilane doctor [--json]              read-only local health report
   omnilane ui    start|status|url|stop