omnilane 0.31.0 → 0.32.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude-plugin/marketplace.json +2 -2
- package/.claude-plugin/plugin.json +1 -1
- package/CHANGELOG.md +25 -1
- package/README.ja.md +51 -65
- package/README.ko.md +51 -64
- package/README.md +52 -66
- package/README.zh-CN.md +50 -61
- package/README.zh-TW.md +51 -62
- package/VERSION +1 -1
- package/package.json +1 -1
- package/plugin.json +1 -1
- package/routing.local.yaml.example +4 -4
- package/routing.yaml +22 -24
- package/scripts/configure.sh +3 -3
- package/scripts/runners/run-vote.sh +3 -3
- package/skills/omnilane/SKILL.md +40 -37
package/README.md
CHANGED
|
@@ -78,11 +78,11 @@ key with no extra CLI at all):
|
|
|
78
78
|
```mermaid
|
|
79
79
|
flowchart LR
|
|
80
80
|
M["main loop<br/><i>any CLI you drive</i>"] --> T{{"routing.yaml<br/>one shared table"}}
|
|
81
|
-
T -->|hardest-coding| C1["
|
|
82
|
-
T -->|bulk-mechanical| C2["Codex — GPT-5.6
|
|
83
|
-
|
|
84
|
-
T -->|long-context| C4["Gemini — 3.
|
|
85
|
-
T -->|live-search| C5["Grok — 4.
|
|
81
|
+
T -->|hardest-coding| C1["Claude — Fable 5.1"]
|
|
82
|
+
T -->|bulk-mechanical| C2["Codex — GPT-5.6 Sol"]
|
|
83
|
+
T -->|taste-final| C3["Claude — Fable 5.1"]
|
|
84
|
+
T -->|long-context| C4["Gemini — 3.7 Flash"]
|
|
85
|
+
T -->|live-search| C5["Grok — 4.6"]
|
|
86
86
|
T -->|"arbitrate (opt-in)"| C6["vote — 1-4 model panel"]
|
|
87
87
|
```
|
|
88
88
|
|
|
@@ -115,23 +115,25 @@ actually resolves.
|
|
|
115
115
|
|
|
116
116
|
| Lane | First choice | Backup | When |
|
|
117
117
|
|---|---|---|---|
|
|
118
|
-
| 🔥 hardest-coding |
|
|
119
|
-
| 🏗️ bulk-mechanical | GPT-5.6
|
|
120
|
-
| 🧹 triage | GPT-5.6 Luna (
|
|
121
|
-
| ⚖️ hard-judgment | Claude
|
|
122
|
-
| ✒️ taste-final | Claude
|
|
123
|
-
| 💬 consult |
|
|
124
|
-
| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude
|
|
125
|
-
| 📚 long-context | Gemini 3.
|
|
126
|
-
| ⚡ fast-agentic |
|
|
127
|
-
| 📡 live-search | Grok 4.
|
|
128
|
-
| 🚰 coding-overflow | Grok 4.
|
|
118
|
+
| 🔥 hardest-coding | Claude Fable 5.1 (xhigh) | GPT-5.6 Sol (xhigh) | Hardest implementation, deep root-cause debug, correctness-critical edits |
|
|
119
|
+
| 🏗️ bulk-mechanical | GPT-5.6 Sol (high) | Gemini 3.7 Flash (High) → Claude Sonnet 5 (high) | Refactors, migrations, tests, review sweeps — mechanical endurance |
|
|
120
|
+
| 🧹 triage | GPT-5.6 Luna (high) | Gemini 3.7 Flash (Low) → Claude Haiku 4.5 | High-volume scans, first-pass filtering |
|
|
121
|
+
| ⚖️ hard-judgment | Claude Fable 5.1 (xhigh) | GPT-5.6 Sol (max) → Grok 4.6 | Architecture arbitration, deep reasoning, second opinions |
|
|
122
|
+
| ✒️ taste-final | Claude Fable 5.1 (high) | GPT-5.6 Sol (max) | User-facing prose, prompt/doc polish, style arbitration |
|
|
123
|
+
| 💬 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 |
|
|
124
|
+
| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude Fable 5.1 (high) | UI drafts only WITH a design system / reference images |
|
|
125
|
+
| 📚 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 |
|
|
126
|
+
| ⚡ fast-agentic | Gemini 3.7 Flash (Medium) | GPT-5.6 Luna (high) | Fast multi-step agentic loops, multimodal checks |
|
|
127
|
+
| 📡 live-search | Grok 4.6 | — (off) | Realtime X/web search and social context |
|
|
128
|
+
| 🚰 coding-overflow | Grok 4.6 | Gemini 3.7 Flash (High) → Kimi K3 → Qwen3 Coder Plus → OpenCode | Codex-quota relief valve for mid-tier coding |
|
|
129
129
|
| 🗳️ 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 |
|
|
130
130
|
|
|
131
131
|
The **backup** is the next candidate in the lane's `routing.yaml` chain — what
|
|
132
132
|
dispatch falls back to when the first-choice vendor CLI is not installed. Every
|
|
133
133
|
lane is such a chain; when nothing in it is installed the lane degrades to `off`.
|
|
134
134
|
|
|
135
|
+
> **Fable 5.1 is in the defaults — and where Opus 5 still fits.** See the current three-way evidence and Opus override in the [FAQ](#-faq).
|
|
136
|
+
|
|
135
137
|
### Natural-language consultation
|
|
136
138
|
|
|
137
139
|
With the `omnilane` skill or `/route`, you can ask normally:
|
|
@@ -155,12 +157,12 @@ with who is driving. What changes is which lanes you **self-execute** (you
|
|
|
155
157
|
already are that model, so no second call) versus **dispatch**. Your harness's
|
|
156
158
|
`omnilane` skill applies the right row automatically; this is the human view.
|
|
157
159
|
|
|
158
|
-
- **Claude Code · Fable 5** — self-execute: hard-judgment, taste-final,
|
|
159
|
-
- **Claude Code · Opus 5** — self-execute: hard-judgment and taste-final. Dispatch
|
|
160
|
-
- **Codex · Sol** — self-execute: hardest-coding, hard-judgment, ui-draft. Dispatch taste-final → Claude, long-context → Gemini, live-search → Grok
|
|
161
|
-
- **Codex · Terra** — self-execute:
|
|
162
|
-
- **Grok Build · Grok 4.
|
|
163
|
-
- **Antigravity · Gemini** — self-execute: long-context and
|
|
160
|
+
- **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.
|
|
161
|
+
- **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.
|
|
162
|
+
- **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.
|
|
163
|
+
- **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.
|
|
164
|
+
- **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.
|
|
165
|
+
- **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.
|
|
164
166
|
|
|
165
167
|
</details>
|
|
166
168
|
|
|
@@ -489,52 +491,30 @@ with the key you set — those are advise-only and never edit files.
|
|
|
489
491
|
</details>
|
|
490
492
|
|
|
491
493
|
<details>
|
|
492
|
-
<summary><b>
|
|
494
|
+
<summary><b>Fable 5.1 is in the defaults — and where Opus 5 still fits</b></summary>
|
|
493
495
|
|
|
494
496
|
<br/>
|
|
495
497
|
|
|
496
|
-
|
|
497
|
-
|
|
498
|
-
|
|
499
|
-
just adds a second call for no gain — which is why the "pick your main model"
|
|
500
|
-
list above gives Fable 5 its own row as a **driver**, self-executing
|
|
501
|
-
hard-judgment, taste-final, and the hardest correctness-critical fixes.
|
|
502
|
-
|
|
503
|
-
**The measurements do not argue for it as a worker either.** On the Artificial
|
|
504
|
-
Analysis Intelligence Index (2026-07-24) Opus 5 (max) scores 61 and Fable 5 (max)
|
|
505
|
-
scores 60 — Artificial Analysis calls them "effectively tied", and Epoch AI's
|
|
506
|
-
Capability Index ranks them the other way (Fable 5 161, Opus 5 159). Call it a
|
|
507
|
-
draw on general intelligence. Where they are not tied is agentic professional
|
|
508
|
-
output, and Opus 5 leads by a wide margin:
|
|
509
|
-
|
|
510
|
-
| Benchmark | Claude Opus 5 (max) | Claude Fable 5 | |
|
|
511
|
-
|---|---:|---:|---|
|
|
512
|
-
| AA-Briefcase (agentic knowledge work, Elo) | 1720 | 1574 | **+146** |
|
|
513
|
-
| GDPval-AA v2 (Elo) | 1861 | 1747 | **+114** |
|
|
514
|
-
| Cost per AA-Briefcase task | $17.79 | $22.30 | **-20%** |
|
|
515
|
-
| API price, input / output per 1M | $5 / $25 | $10 / $50 | **half** |
|
|
516
|
-
|
|
517
|
-
Opus 5's max, xhigh and high tiers sweep the top three AA-Briefcase places, and
|
|
518
|
-
its `high` tier still beats Fable 5 at under half the cost per task. So Fable 5
|
|
519
|
-
costs twice as much without buying an advantage on any axis a lane is defined
|
|
520
|
-
around.
|
|
521
|
-
|
|
522
|
-
**What Fable 5 is genuinely better at**: factual breadth. It stays ahead of
|
|
523
|
-
Opus 5 on AA-Omniscience, as its size class suggests, and Opus 5 answers more
|
|
524
|
-
readily when uncertain — its hallucination rate is 50%, up 14 points from
|
|
525
|
-
Opus 4.8. If your task is recall-heavy rather than execution-heavy, name
|
|
526
|
-
Fable 5 explicitly:
|
|
498
|
+
Fable 5.1 now leads `hardest-coding`, `hard-judgment`, and `taste-final`.
|
|
499
|
+
At matched xhigh effort it leads Opus 5 on intelligence, agentic work, and
|
|
500
|
+
coding. Sol max remains the far cheaper cross-vendor judgment fallback.
|
|
527
501
|
|
|
528
|
-
|
|
529
|
-
|
|
530
|
-
|
|
502
|
+
| Benchmark (AA, retrieved 2026-09-02) | Claude Fable 5.1 (xhigh) | Claude Opus 5 (xhigh) | GPT-5.6 Sol (max) |
|
|
503
|
+
|---|---:|---:|---:|
|
|
504
|
+
| Intelligence | 64.8 | 62.5 | 60.9 |
|
|
505
|
+
| Agentic | 59.8 | 58.4 | 57.8 |
|
|
506
|
+
| Coding | 80.7 | 77.0 | 77.4 |
|
|
507
|
+
| Hallucination rate (lower is better) | .71 | **.60** | .92 |
|
|
508
|
+
| AA $/task | $2.65 | $1.80 | **$0.95** |
|
|
531
509
|
|
|
532
|
-
|
|
533
|
-
|
|
534
|
-
|
|
510
|
+
Fable 5.1 is not a bulk or triage default: it costs twice Opus 5 per token and
|
|
511
|
+
consumes the most Claude Code subscription quota per turn. Opus 5 remains the
|
|
512
|
+
lower-hallucination, lower-price Claude option, stays in `long-context` at
|
|
513
|
+
medium, and remains selectable everywhere through
|
|
514
|
+
`~/.omnilane/routing.local.yaml`:
|
|
535
515
|
|
|
536
516
|
```yaml
|
|
537
|
-
|
|
517
|
+
hard-judgment: claude claude-opus-5 xhigh
|
|
538
518
|
```
|
|
539
519
|
|
|
540
520
|
</details>
|
|
@@ -598,7 +578,7 @@ Default lane assignments follow Artificial Analysis coding/intelligence data
|
|
|
598
578
|
pages) plus published head-to-head reviews; they are opinions, not laws — the
|
|
599
579
|
configurator and `routing.local.yaml` exist so you can disagree. The full
|
|
600
580
|
working notes, including per-benchmark caveats, live in
|
|
601
|
-
[`docs/model-capabilities-2026-
|
|
581
|
+
[`docs/model-capabilities-2026-09.md`](docs/model-capabilities-2026-09.md).
|
|
602
582
|
|
|
603
583
|
## ⚠️ Known limitations
|
|
604
584
|
|
|
@@ -614,6 +594,12 @@ working notes, including per-benchmark caveats, live in
|
|
|
614
594
|
|
|
615
595
|
## 📜 Release history
|
|
616
596
|
|
|
597
|
+
## What's new in v0.32.0
|
|
598
|
+
|
|
599
|
+
- **Full 2026-09 routing re-evaluation.** Fable 5.1 and Gemini 3.7 Flash enter the defaults, backed by the dated Artificial Analysis snapshot.
|
|
600
|
+
- **Catalogs match live CLI surfaces.** Fable 5.1 is added and retired Gemini 3.5 Flash rows are removed.
|
|
601
|
+
- **Opus 5 remains available.** It stays in `long-context` and can override any lane through `routing.local.yaml`.
|
|
602
|
+
|
|
617
603
|
## What's new in v0.31.0
|
|
618
604
|
|
|
619
605
|
- **Unlimited goal budgets by default.** `budget_jobs` and `budget_seconds` now persist as JSON `null` and render as `unlimited`; the previous implicit 8-job and 900-second caps are gone. Use `--budget-jobs N` or `--budget-seconds S` to opt in to a hard cap. The repeat-failure fuse remains enabled by default.
|
|
@@ -715,7 +701,7 @@ working notes, including per-benchmark caveats, live in
|
|
|
715
701
|
latency-bound.
|
|
716
702
|
- **Lane comments no longer carry numbers.** `routing.yaml` now states why each
|
|
717
703
|
ordering holds; every score, price and throughput figure lives in
|
|
718
|
-
`docs/model-capabilities-2026-
|
|
704
|
+
`docs/model-capabilities-2026-09.md` with its retrieval date, so a stale
|
|
719
705
|
figure never requires a routing-table edit.
|
|
720
706
|
- **A value profile** in `routing.local.yaml.example` trades about one
|
|
721
707
|
Intelligence Index point for 30-40% off the cost per task.
|
|
@@ -774,7 +760,7 @@ working notes, including per-benchmark caveats, live in
|
|
|
774
760
|
profiles still pointed at `claude-opus-4-8` and Gemini 3.5 Flash; they now use
|
|
775
761
|
Claude Opus 5 (with lane-appropriate effort) and Gemini 3.6 Flash.
|
|
776
762
|
- **Corrected the Intelligence Index figures** in
|
|
777
|
-
`docs/model-capabilities-2026-
|
|
763
|
+
`docs/model-capabilities-2026-09.md` against the Artificial Analysis source
|
|
778
764
|
(index points, not percentages), added the AA-Briefcase / GDPval-AA v2
|
|
779
765
|
comparison, and recorded the two results that cut against the defaults:
|
|
780
766
|
Fable 5's lead on factual knowledge and Sol's lead on presentation quality.
|
|
@@ -822,7 +808,7 @@ working notes, including per-benchmark caveats, live in
|
|
|
822
808
|
- **Five OpenAI-compatible direct-API vendors** — `deepseek`, `zai` (GLM),
|
|
823
809
|
`mistral`, `groq`, and `cerebras` join `openrouter` as CLI-free lanes (curl +
|
|
824
810
|
a `<VENDOR>_API_KEY`). A one-line `lib/common.sh` registry entry adds each;
|
|
825
|
-
see [`docs/model-capabilities-2026-
|
|
811
|
+
see [`docs/model-capabilities-2026-09.md`](docs/model-capabilities-2026-09.md).
|
|
826
812
|
- **Fish shell completion** — `omnilane completion fish | source`.
|
|
827
813
|
|
|
828
814
|
## What's new in v0.8.3
|
|
@@ -846,7 +832,7 @@ working notes, including per-benchmark caveats, live in
|
|
|
846
832
|
DeepSeek, Z.ai GLM, Mistral, Groq, and Cerebras. Each needs only `curl` and
|
|
847
833
|
its `<VENDOR>_API_KEY`; advise/consult only. A one-line `lib/common.sh`
|
|
848
834
|
registry entry defines each endpoint, key env, and default model. See
|
|
849
|
-
[`docs/model-capabilities-2026-
|
|
835
|
+
[`docs/model-capabilities-2026-09.md`](docs/model-capabilities-2026-09.md).
|
|
850
836
|
- **`opencode` vendor** — headless dispatch through the OpenCode
|
|
851
837
|
multi-provider aggregator CLI (`opencode run`). Advise mode pins OpenCode's
|
|
852
838
|
built-in read-only `plan` agent; work mode uses `--auto`. Joins the default
|
package/README.zh-CN.md
CHANGED
|
@@ -72,11 +72,11 @@ omnilane 让**任何**一个 agentic CLI 的主循环把子任务分类到通道
|
|
|
72
72
|
```mermaid
|
|
73
73
|
flowchart LR
|
|
74
74
|
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"}}
|
|
75
|
-
T -->|hardest-coding| C1["
|
|
76
|
-
T -->|bulk-mechanical| C2["Codex — GPT-5.6
|
|
77
|
-
T -->|taste-final| C3["Claude —
|
|
78
|
-
T -->|long-context| C4["Gemini — 3.
|
|
79
|
-
T -->|live-search| C5["Grok — 4.
|
|
75
|
+
T -->|hardest-coding| C1["Claude — Fable 5.1"]
|
|
76
|
+
T -->|bulk-mechanical| C2["Codex — GPT-5.6 Sol"]
|
|
77
|
+
T -->|taste-final| C3["Claude — Fable 5.1"]
|
|
78
|
+
T -->|long-context| C4["Gemini — 3.7 Flash"]
|
|
79
|
+
T -->|live-search| C5["Grok — 4.6"]
|
|
80
80
|
T -->|"arbitrate(可选)"| C6["vote — 1-4 模型评审团"]
|
|
81
81
|
```
|
|
82
82
|
|
|
@@ -103,24 +103,23 @@ flowchart LR
|
|
|
103
103
|
|
|
104
104
|
| 通道 | 首选模型 | 备选模型 | 用途 |
|
|
105
105
|
|---|---|---|---|
|
|
106
|
-
| 🔥 hardest-coding |
|
|
107
|
-
| 🏗️ bulk-mechanical | GPT-5.6
|
|
108
|
-
| 🧹 triage | GPT-5.6 Luna (
|
|
109
|
-
| ⚖️ hard-judgment | Claude
|
|
110
|
-
| ✒️ taste-final | Claude
|
|
111
|
-
| 💬 consult |
|
|
112
|
-
| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude
|
|
113
|
-
| 📚 long-context | Gemini 3.
|
|
114
|
-
| ⚡ fast-agentic |
|
|
115
|
-
| 📡 live-search | Grok 4.
|
|
116
|
-
| 🚰 coding-overflow | Grok 4.
|
|
117
|
-
| 🗳️ arbitrate | off
|
|
106
|
+
| 🔥 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 |
|
|
107
|
+
| 🏗️ 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 |
|
|
108
|
+
| 🧹 triage | GPT-5.6 Luna (high) | Gemini 3.7 Flash (Low) → Claude Haiku 4.5 | 大量扫描、第一轮筛选 |
|
|
109
|
+
| ⚖️ 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 |
|
|
110
|
+
| ✒️ 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 |
|
|
111
|
+
| 💬 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 |
|
|
112
|
+
| 🎨 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 |
|
|
113
|
+
| 📚 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 |
|
|
114
|
+
| ⚡ 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 |
|
|
115
|
+
| 📡 live-search | Grok 4.6 | — (`off`) | 实时 X/网页搜索与社交上下文 |
|
|
116
|
+
| 🚰 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 |
|
|
117
|
+
| 🗳️ 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 |
|
|
118
118
|
|
|
119
119
|
**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。每条
|
|
120
120
|
通道都是这样一条链;整条都没装时,通道自动降为 `off`。
|
|
121
121
|
|
|
122
|
-
> **
|
|
123
|
-
> [常见问题](#-常见问题)。
|
|
122
|
+
> **Fable 5.1 已进入默认表——以及 Opus 5 仍适合放在哪里。** 三方数据与 Opus override 见[常见问题](#-常见问题)。
|
|
124
123
|
|
|
125
124
|
### 自然语言咨询
|
|
126
125
|
|
|
@@ -141,12 +140,12 @@ flowchart LR
|
|
|
141
140
|
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
|
|
142
141
|
的 `omnilane` 技能会自动套对的那一行,这里是给人看的版本。
|
|
143
142
|
|
|
144
|
-
- **Claude Code · Fable 5
|
|
145
|
-
- **Claude Code · Opus 5
|
|
146
|
-
- **Codex · Sol
|
|
147
|
-
- **Codex · Terra
|
|
148
|
-
- **Grok Build · Grok 4.
|
|
149
|
-
- **Antigravity · Gemini
|
|
143
|
+
- **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。
|
|
144
|
+
- **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。
|
|
145
|
+
- **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。
|
|
146
|
+
- **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。
|
|
147
|
+
- **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。
|
|
148
|
+
- **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。
|
|
150
149
|
|
|
151
150
|
</details>
|
|
152
151
|
|
|
@@ -395,45 +394,29 @@ omnilane goal close "$GOAL_ID" --summary "结账集成已稳定"
|
|
|
395
394
|
</details>
|
|
396
395
|
|
|
397
396
|
<details>
|
|
398
|
-
<summary><b>
|
|
397
|
+
<summary><b>Fable 5.1 已进入默认表——以及 Opus 5 仍适合放在哪里</b></summary>
|
|
399
398
|
|
|
400
399
|
<br/>
|
|
401
400
|
|
|
402
|
-
|
|
403
|
-
|
|
404
|
-
|
|
405
|
-
模型」清单里,Fable 5 有自己独立的一行,身份是**主控**:自己做 hard-judgment、
|
|
406
|
-
taste-final、最吃正确性的硬修。
|
|
401
|
+
Fable 5.1 现在领跑 `hardest-coding`、`hard-judgment`、`taste-final`。
|
|
402
|
+
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
|
|
403
|
+
便宜得多的跨厂商判断备用项。
|
|
407
404
|
|
|
408
|
-
|
|
409
|
-
|
|
410
|
-
|
|
411
|
-
|
|
405
|
+
| 评测(AA,抓取于 2026-09-02) | Claude Fable 5.1 (xhigh) | Claude Opus 5 (xhigh) | GPT-5.6 Sol (max) |
|
|
406
|
+
|---|---:|---:|---:|
|
|
407
|
+
| 智能 | 64.8 | 62.5 | 60.9 |
|
|
408
|
+
| 代理式 | 59.8 | 58.4 | 57.8 |
|
|
409
|
+
| 编码 | 80.7 | 77.0 | 77.4 |
|
|
410
|
+
| 幻觉率(越低越好) | .71 | **.60** | .92 |
|
|
411
|
+
| AA 每任务成本 | $2.65 | $1.80 | **$0.95** |
|
|
412
412
|
|
|
413
|
-
|
|
414
|
-
|
|
415
|
-
|
|
416
|
-
|
|
417
|
-
| AA-Briefcase 每任务成本 | $17.79 | $22.30 | **-20%** |
|
|
418
|
-
| API 单价,输入/输出 每 1M | $5 / $25 | $10 / $50 | **一半** |
|
|
419
|
-
|
|
420
|
-
Opus 5 的 max、xhigh、high 三个档位包揽 AA-Briefcase 前三名,连 `high` 档都在
|
|
421
|
-
不到一半的每任务成本下赢过 Fable 5。也就是说,Fable 5 贵一倍,却换不到任何一条
|
|
422
|
-
通道所在意的优势。
|
|
423
|
-
|
|
424
|
-
**Fable 5 真正更强的地方**:事实广度。它在 AA-Omniscience 上仍领先 Opus 5
|
|
425
|
-
(符合两者的规模差),而 Opus 5 在没把握时更倾向直接作答——幻觉率 50%,比
|
|
426
|
-
Opus 4.8 高 14 个百分点。任务偏「回想」而非「执行」时,直接点名它:
|
|
427
|
-
|
|
428
|
-
```bash
|
|
429
|
-
dispatch.sh --vendor claude --model claude-fable-5 --effort high consult "…"
|
|
430
|
-
```
|
|
431
|
-
|
|
432
|
-
**这是成本与主循环策略的选择,不是能力判决。** 设置菜单的模型清单里有 Fable 5,
|
|
433
|
-
在 `routing.local.yaml` 写一行就能覆盖默认:
|
|
413
|
+
Fable 5.1 没进入 bulk 或 triage:每 token 价格是 Opus 5 的两倍,而且每轮
|
|
414
|
+
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
|
|
415
|
+
选项,并以 medium 保留在 `long-context`;也能通过
|
|
416
|
+
`~/.omnilane/routing.local.yaml` 放回任意通道:
|
|
434
417
|
|
|
435
418
|
```yaml
|
|
436
|
-
|
|
419
|
+
hard-judgment: claude claude-opus-5 xhigh
|
|
437
420
|
```
|
|
438
421
|
|
|
439
422
|
</details>
|
|
@@ -493,7 +476,7 @@ vendor 一律当成 `work`,而且它只能逐次明确指定,永远不是 lane
|
|
|
493
476
|
默认关闭;要用就在 `routing.local.yaml` 写
|
|
494
477
|
`arbitrate: vote codex,claude,grok -`(从四家里任选 1-4 个评审),
|
|
495
478
|
或改用 `exec` 厂商指向你自己的多模型审查闸脚本。完整工作笔记(含各评测的
|
|
496
|
-
但书)见 [`docs/model-capabilities-2026-
|
|
479
|
+
但书)见 [`docs/model-capabilities-2026-09.md`](docs/model-capabilities-2026-09.md)。
|
|
497
480
|
|
|
498
481
|
## ⚠️ 已知限制
|
|
499
482
|
|
|
@@ -507,6 +490,12 @@ vendor 一律当成 `work`,而且它只能逐次明确指定,永远不是 lane
|
|
|
507
490
|
|
|
508
491
|
## 📜 版本历程
|
|
509
492
|
|
|
493
|
+
## v0.32.0 新功能
|
|
494
|
+
|
|
495
|
+
- **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。
|
|
496
|
+
- **模型目录同步当前 CLI 接口。** 加入 Fable 5.1,移除 agy 已下架的 Gemini 3.5 Flash 项,并同步投票器。
|
|
497
|
+
- **Opus 5 仍可使用。** 它保留在 `long-context`,也能通过 `routing.local.yaml` 覆盖任意通道。
|
|
498
|
+
|
|
510
499
|
## v0.31.0 新功能
|
|
511
500
|
|
|
512
501
|
- **目标预算默认不设上限。** `budget_jobs` 和 `budget_seconds` 现在以 JSON `null` 保存并显示为 `unlimited`;此前隐含的 8 个任务和 900 秒上限已移除。只有使用 `--budget-jobs N` 或 `--budget-seconds S` 才会启用硬性上限;重复失败保险丝不是预算,默认仍然启用。
|
|
@@ -582,7 +571,7 @@ vendor 一律当成 `work`,而且它只能逐次明确指定,永远不是 lane
|
|
|
582
571
|
的 Agentic Index 上大幅领先 Flash,而且 2026-07-30 降价后每任务成本只剩零头。
|
|
583
572
|
Flash 只剩吞吐量优势——若你的循环受延迟限制,可在本机覆写把它调回第一。
|
|
584
573
|
- **lane 注释不再放数字。**`routing.yaml` 只说明每条排序「为什么」成立;所有分数、
|
|
585
|
-
价格与吞吐量连同取数日期,一律放在 `docs/model-capabilities-2026-
|
|
574
|
+
价格与吞吐量连同取数日期,一律放在 `docs/model-capabilities-2026-09.md`。数字过期
|
|
586
575
|
不再需要动路由表。
|
|
587
576
|
- **新增 value profile**(在 `routing.local.yaml.example`):用约一个 Intelligence
|
|
588
577
|
Index 分数,换每任务成本降三到四成。
|
|
@@ -628,7 +617,7 @@ vendor 一律当成 `work`,而且它只能逐次明确指定,永远不是 lane
|
|
|
628
617
|
- **修复:`routing.local.yaml.example` 还指着已退场的模型**——起手配置里的
|
|
629
618
|
`claude-opus-4-8` 全数改为 `claude-opus-5`(并按通道给对应档位),Gemini 3.5
|
|
630
619
|
Flash 候选改为 3.6 Flash,与 0.10.0 以来的默认值一致。
|
|
631
|
-
- **对照原始资料修正智能指数数字**(`docs/model-capabilities-2026-
|
|
620
|
+
- **对照原始资料修正智能指数数字**(`docs/model-capabilities-2026-09.md`):
|
|
632
621
|
那是指数点数不是百分比;补上 AA-Briefcase / GDPval-AA v2 对照,并记下两项与
|
|
633
622
|
默认值相反的结果:Fable 5 在事实知识领先、GPT-5.6 Sol 在呈现质量领先。
|
|
634
623
|
|
|
@@ -665,7 +654,7 @@ vendor 一律当成 `work`,而且它只能逐次明确指定,永远不是 lane
|
|
|
665
654
|
|
|
666
655
|
## v0.9.0 新功能
|
|
667
656
|
|
|
668
|
-
- **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-
|
|
657
|
+
- **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-2026-09.md`](docs/model-capabilities-2026-09.md)。
|
|
669
658
|
- **fish shell 补全** — `omnilane completion fish | source`。
|
|
670
659
|
|
|
671
660
|
## v0.8.3 新功能
|
package/README.zh-TW.md
CHANGED
|
@@ -72,11 +72,11 @@ omnilane 讓**任何**一個 agentic CLI 的主迴圈把子任務分類到通道
|
|
|
72
72
|
```mermaid
|
|
73
73
|
flowchart LR
|
|
74
74
|
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"}}
|
|
75
|
-
T -->|hardest-coding| C1["
|
|
76
|
-
T -->|bulk-mechanical| C2["Codex — GPT-5.6
|
|
77
|
-
|
|
78
|
-
T -->|long-context| C4["Gemini — 3.
|
|
79
|
-
T -->|live-search| C5["Grok — 4.
|
|
75
|
+
T -->|hardest-coding| C1["Claude — Fable 5.1"]
|
|
76
|
+
T -->|bulk-mechanical| C2["Codex — GPT-5.6 Sol"]
|
|
77
|
+
T -->|taste-final| C3["Claude — Fable 5.1"]
|
|
78
|
+
T -->|long-context| C4["Gemini — 3.7 Flash"]
|
|
79
|
+
T -->|live-search| C5["Grok — 4.6"]
|
|
80
80
|
T -->|"arbitrate(選配)"| C6["vote — 1-4 模型評審團"]
|
|
81
81
|
```
|
|
82
82
|
|
|
@@ -103,24 +103,23 @@ flowchart LR
|
|
|
103
103
|
|
|
104
104
|
| 通道 | 首選模型 | 備選模型 | 用途 |
|
|
105
105
|
|---|---|---|---|
|
|
106
|
-
| 🔥 hardest-coding |
|
|
107
|
-
| 🏗️ bulk-mechanical | GPT-5.6
|
|
108
|
-
| 🧹 triage | GPT-5.6 Luna (
|
|
109
|
-
| ⚖️ hard-judgment | Claude
|
|
110
|
-
| ✒️ taste-final | Claude
|
|
111
|
-
| 💬 consult |
|
|
112
|
-
| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude
|
|
113
|
-
| 📚 long-context | Gemini 3.
|
|
114
|
-
| ⚡ fast-agentic |
|
|
115
|
-
| 📡 live-search | Grok 4.
|
|
116
|
-
| 🚰 coding-overflow | Grok 4.
|
|
117
|
-
| 🗳️ arbitrate | off
|
|
106
|
+
| 🔥 hardest-coding | Claude Fable 5.1 (xhigh) | GPT-5.6 Sol (xhigh) | 最難的實作、深度除錯、正確性攸關的修改 |
|
|
107
|
+
| 🏗️ bulk-mechanical | GPT-5.6 Sol (high) | Gemini 3.7 Flash (High) → Claude Sonnet 5 (high) | 重構、搬遷、測試、大面積掃描——機械耐力活 |
|
|
108
|
+
| 🧹 triage | GPT-5.6 Luna (high) | Gemini 3.7 Flash (Low) → Claude Haiku 4.5 | 大量掃描、第一輪篩選 |
|
|
109
|
+
| ⚖️ hard-judgment | Claude Fable 5.1 (xhigh) | GPT-5.6 Sol (max) → Grok 4.6 | 架構裁決、深度推理、第二意見 |
|
|
110
|
+
| ✒️ taste-final | Claude Fable 5.1 (high) | GPT-5.6 Sol (max) | 對外文字、提示詞/文件潤飾、風格裁決 |
|
|
111
|
+
| 💬 consult | GPT-5.6 Sol (max) | Claude Fable 5.1 (high) → Grok 4.6 → Gemini 3.7 Flash (High) | 直接點名模型諮詢;保留 `--vendor` 避免降級 |
|
|
112
|
+
| 🎨 ui-draft | GPT-5.6 Sol (xhigh) | Claude Fable 5.1 (high) | 只有在附設計系統/參考圖時才做 UI 草稿 |
|
|
113
|
+
| 📚 long-context | Gemini 3.7 Flash (Medium) | GPT-5.6 Terra (max) → Claude Opus 5 (medium) | 長文件擷取與整合,依 AA-LCR、成本與吞吐排序 |
|
|
114
|
+
| ⚡ fast-agentic | Gemini 3.7 Flash (Medium) | GPT-5.6 Luna (high) | 高速多步驟工具迴圈、多模態檢查 |
|
|
115
|
+
| 📡 live-search | Grok 4.6 | — (`off`) | 即時 X/網頁搜尋與社群脈絡 |
|
|
116
|
+
| 🚰 coding-overflow | Grok 4.6 | Gemini 3.7 Flash (High) → Kimi K3 → Qwen3 Coder Plus → OpenCode | Codex 額度用完時的中量級編碼安全閥 |
|
|
117
|
+
| 🗳️ arbitrate | `off`(選配模型評審團) | — | 重大決定的內建意見評審團;預設停用,在 `routing.local.yaml` 啟用,每位評審每輪一次呼叫 |
|
|
118
118
|
|
|
119
119
|
**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。每條
|
|
120
120
|
通道都是這樣一條鏈;整條都沒裝時,通道自動降為 `off`。
|
|
121
121
|
|
|
122
|
-
> **
|
|
123
|
-
> [常見問題](#-常見問題)。
|
|
122
|
+
> **Fable 5.1 已進入預設——以及 Opus 5 仍適合放在哪裡。** 三方數據與 Opus override 寫在[常見問題](#-常見問題)。
|
|
124
123
|
|
|
125
124
|
### 自然語言諮詢
|
|
126
125
|
|
|
@@ -141,12 +140,12 @@ flowchart LR
|
|
|
141
140
|
你哪些通道**自己做**(你本來就是那個模型,省一次呼叫)、哪些**派出去**。你 CLI 裡
|
|
142
141
|
的 `omnilane` 技能會自動套對的那一列,這裡是給人看的版本。
|
|
143
142
|
|
|
144
|
-
- **Claude Code · Fable 5
|
|
145
|
-
- **Claude Code · Opus 5
|
|
146
|
-
- **Codex · Sol
|
|
147
|
-
- **Codex · Terra
|
|
148
|
-
- **Grok Build · Grok 4.
|
|
149
|
-
- **Antigravity · Gemini
|
|
143
|
+
- **Claude Code · Fable 5.1**——自己做:hard-judgment、taste-final、hardest-coding。派出去:bulk → Codex Sol high;long-context/高速迴圈 → Gemini 3.7 Flash;即時搜尋 → Grok。
|
|
144
|
+
- **Claude Code · Opus 5**——需要較低幻覺率或價格時,自己做 hard-judgment、taste-final。最難編碼 → Fable 5.1 或 Sol;bulk → Sol high;long-context/高速迴圈 → Gemini 3.7 Flash;即時搜尋 → Grok。
|
|
145
|
+
- **Codex · Sol**——自己做:hardest-coding、bulk-mechanical、hard-judgment、ui-draft。派出去:taste-final → Claude;long-context/高速迴圈 → Gemini 3.7 Flash;即時搜尋 → Grok。
|
|
146
|
+
- **Codex · Terra**——自己做 long-context 的 Codex 備援;bulk-mechanical 已改由 Sol high 預設處理。最難處升級 Sol xhigh,taste → Claude,高速迴圈 → Gemini 3.7 Flash,即時搜尋 → Grok。
|
|
147
|
+
- **Grok Build · Grok 4.6**——自己做 live-search、coding-overflow。最難的編碼/判斷/文字交給 Codex、Claude、Gemini;仍要驗證 API 簽章與引用事實。
|
|
148
|
+
- **Antigravity · Gemini 3.7 Flash**——自己做:Medium 的 long-context/高速迴圈、High 的 bulk/overflow、Low 的 triage。最難編碼/判斷/文字交給 Codex、Claude;即時搜尋 → Grok。
|
|
150
149
|
|
|
151
150
|
</details>
|
|
152
151
|
|
|
@@ -422,45 +421,29 @@ omnilane goal close "$GOAL_ID" --summary "結帳整合已穩定"
|
|
|
422
421
|
</details>
|
|
423
422
|
|
|
424
423
|
<details>
|
|
425
|
-
<summary><b>
|
|
424
|
+
<summary><b>Fable 5.1 已進入預設——以及 Opus 5 仍適合放在哪裡</b></summary>
|
|
426
425
|
|
|
427
426
|
<br/>
|
|
428
427
|
|
|
429
|
-
|
|
430
|
-
|
|
431
|
-
|
|
432
|
-
模型」清單裡,Fable 5 有自己獨立的一列,身分是**主控**:自己做 hard-judgment、
|
|
433
|
-
taste-final、最吃正確性的硬修。
|
|
428
|
+
Fable 5.1 現在領頭 `hardest-coding`、`hard-judgment`、`taste-final`。
|
|
429
|
+
同為 xhigh 時,它在智慧、代理式工作與編碼都領先 Opus 5;Sol max 則保留為
|
|
430
|
+
便宜許多的跨廠商判斷備援。
|
|
434
431
|
|
|
435
|
-
|
|
436
|
-
|
|
437
|
-
|
|
438
|
-
|
|
432
|
+
| 評測(AA,擷取於 2026-09-02) | Claude Fable 5.1 (xhigh) | Claude Opus 5 (xhigh) | GPT-5.6 Sol (max) |
|
|
433
|
+
|---|---:|---:|---:|
|
|
434
|
+
| 智慧 | 64.8 | 62.5 | 60.9 |
|
|
435
|
+
| 代理式 | 59.8 | 58.4 | 57.8 |
|
|
436
|
+
| 編碼 | 80.7 | 77.0 | 77.4 |
|
|
437
|
+
| 幻覺率(越低越好) | .71 | **.60** | .92 |
|
|
438
|
+
| AA 每任務成本 | $2.65 | $1.80 | **$0.95** |
|
|
439
439
|
|
|
440
|
-
|
|
441
|
-
|
|
442
|
-
|
|
443
|
-
|
|
444
|
-
| AA-Briefcase 每任務成本 | $17.79 | $22.30 | **-20%** |
|
|
445
|
-
| API 單價,輸入/輸出 每 1M | $5 / $25 | $10 / $50 | **一半** |
|
|
446
|
-
|
|
447
|
-
Opus 5 的 max、xhigh、high 三個檔位包辦 AA-Briefcase 前三名,連 `high` 檔都在
|
|
448
|
-
不到一半的每任務成本下贏過 Fable 5。也就是說,Fable 5 貴一倍,卻換不到任何一條
|
|
449
|
-
通道所在意的優勢。
|
|
450
|
-
|
|
451
|
-
**Fable 5 真正比較強的地方**:事實廣度。它在 AA-Omniscience 上仍領先 Opus 5
|
|
452
|
-
(符合兩者的規模差),而 Opus 5 在沒把握時更傾向直接作答——幻覺率 50%,比
|
|
453
|
-
Opus 4.8 高 14 個百分點。任務偏「回想」而非「執行」時,直接點名它:
|
|
454
|
-
|
|
455
|
-
```bash
|
|
456
|
-
dispatch.sh --vendor claude --model claude-fable-5 --effort high consult "…"
|
|
457
|
-
```
|
|
458
|
-
|
|
459
|
-
**這是成本與主迴圈策略的選擇,不是能力判決。** 設定選單的模型清單有列 Fable 5,
|
|
460
|
-
在 `routing.local.yaml` 寫一行就能覆寫預設:
|
|
440
|
+
Fable 5.1 沒進 bulk 或 triage:每 token 價格是 Opus 5 的兩倍,而且每回合
|
|
441
|
+
消耗最多 Claude Code 訂閱額度。Opus 5 仍是較低幻覺率、較低價格的 Claude
|
|
442
|
+
選項,並以 medium 留在 `long-context`;也能透過
|
|
443
|
+
`~/.omnilane/routing.local.yaml` 放回任何通道:
|
|
461
444
|
|
|
462
445
|
```yaml
|
|
463
|
-
|
|
446
|
+
hard-judgment: claude claude-opus-5 xhigh
|
|
464
447
|
```
|
|
465
448
|
|
|
466
449
|
</details>
|
|
@@ -517,7 +500,7 @@ vendor 一律當成 `work`,而且它只能逐次明確指定,永遠不是 lane
|
|
|
517
500
|
預設通道配置依據 Artificial Analysis 2026-07 快照(已對 AA 站上原始紀錄與
|
|
518
501
|
各廠官方定價頁交叉核對)加上公開對比評測;這些是意見不是定律——
|
|
519
502
|
設定選單和 `routing.local.yaml` 就是讓你不同意用的。完整工作筆記(含各評測的
|
|
520
|
-
但書)見 [`docs/model-capabilities-2026-
|
|
503
|
+
但書)見 [`docs/model-capabilities-2026-09.md`](docs/model-capabilities-2026-09.md)。
|
|
521
504
|
|
|
522
505
|
## ⚠️ 已知限制
|
|
523
506
|
|
|
@@ -531,6 +514,12 @@ vendor 一律當成 `work`,而且它只能逐次明確指定,永遠不是 lane
|
|
|
531
514
|
|
|
532
515
|
## 📜 版本歷程
|
|
533
516
|
|
|
517
|
+
## v0.32.0
|
|
518
|
+
|
|
519
|
+
- **依 AA 2026-09 快照全面重評路由。** Fable 5.1 與 Gemini 3.7 Flash 進入預設,數據集中在新的日期化文件。
|
|
520
|
+
- **模型目錄同步實際 CLI 軟體介面。** 加入 Fable 5.1,移除 agy 已下架的 Gemini 3.5 Flash 項目,並同步投票程式。
|
|
521
|
+
- **Opus 5 仍可使用。** 它留在 `long-context`,也能透過 `routing.local.yaml` 覆寫任何通道。
|
|
522
|
+
|
|
534
523
|
## v0.31.0 新功能
|
|
535
524
|
|
|
536
525
|
- **目標預算預設無上限。** `budget_jobs` 與 `budget_seconds` 現在會以 JSON `null` 儲存並顯示為 `unlimited`;原先隱含的 8 個工作與 900 秒上限已移除。使用 `--budget-jobs N` 或 `--budget-seconds S` 才會啟用硬性上限;重複失敗保險絲不是預算,預設仍會啟用。
|
|
@@ -611,7 +600,7 @@ vendor 一律當成 `work`,而且它只能逐次明確指定,永遠不是 lane
|
|
|
611
600
|
的 Agentic Index 上大幅領先 Flash,而且 2026-07-30 砍價後每任務成本只剩零頭。
|
|
612
601
|
Flash 只剩吞吐量優勢——若你的迴圈受延遲限制,可在本機覆寫把它調回第一。
|
|
613
602
|
- **lane 註解不再放數字。**`routing.yaml` 只說明每條排序「為什麼」成立;所有分數、
|
|
614
|
-
價格與吞吐量連同取數日期,一律住在 `docs/model-capabilities-2026-
|
|
603
|
+
價格與吞吐量連同取數日期,一律住在 `docs/model-capabilities-2026-09.md`。數字過期
|
|
615
604
|
不再需要動路由表。
|
|
616
605
|
- **新增 value profile**(在 `routing.local.yaml.example`):用約一個 Intelligence
|
|
617
606
|
Index 分數,換每任務成本降三到四成。
|
|
@@ -657,7 +646,7 @@ vendor 一律當成 `work`,而且它只能逐次明確指定,永遠不是 lane
|
|
|
657
646
|
- **修正:`routing.local.yaml.example` 還指著已退場的模型**——起手設定檔裡的
|
|
658
647
|
`claude-opus-4-8` 全數改為 `claude-opus-5`(並依通道給對應檔位),Gemini 3.5
|
|
659
648
|
Flash 候選改為 3.6 Flash,與 0.10.0 以來的預設值一致。
|
|
660
|
-
- **對照原始資料修正智慧指數數字**(`docs/model-capabilities-2026-
|
|
649
|
+
- **對照原始資料修正智慧指數數字**(`docs/model-capabilities-2026-09.md`):
|
|
661
650
|
那是指數點數不是百分比;補上 AA-Briefcase / GDPval-AA v2 對照,並記下兩項與
|
|
662
651
|
預設值相反的結果:Fable 5 在事實知識領先、GPT-5.6 Sol 在呈現品質領先。
|
|
663
652
|
|
|
@@ -697,7 +686,7 @@ vendor 一律當成 `work`,而且它只能逐次明確指定,永遠不是 lane
|
|
|
697
686
|
- **五個 OpenAI-compatible direct-API vendor** — `deepseek`、`zai`(GLM)、
|
|
698
687
|
`mistral`、`groq`、`cerebras`,與 `openrouter` 同為免 CLI 通道(curl 加一把
|
|
699
688
|
`<VENDOR>_API_KEY`);`lib/common.sh` registry 一行即加一個。詳見
|
|
700
|
-
[`docs/model-capabilities-2026-
|
|
689
|
+
[`docs/model-capabilities-2026-09.md`](docs/model-capabilities-2026-09.md)。
|
|
701
690
|
- **fish shell 補全** — `omnilane completion fish | source`。
|
|
702
691
|
|
|
703
692
|
## v0.8.3 新功能
|
|
@@ -719,7 +708,7 @@ vendor 一律當成 `work`,而且它只能逐次明確指定,永遠不是 lane
|
|
|
719
708
|
同一條免 CLI 直連 API 路徑,對應 OpenAI-compatible 供應商:DeepSeek、Z.ai GLM、
|
|
720
709
|
Mistral、Groq、Cerebras。各只要 `curl` 加自己那把 `<VENDOR>_API_KEY`;僅限
|
|
721
710
|
advise/consult。端點、金鑰、預設模型由 `lib/common.sh` 一行 registry 定義。
|
|
722
|
-
詳見 [`docs/model-capabilities-2026-
|
|
711
|
+
詳見 [`docs/model-capabilities-2026-09.md`](docs/model-capabilities-2026-09.md)。
|
|
723
712
|
- **`opencode` vendor** — 透過 OpenCode 多供應商聚合 CLI 無頭派工
|
|
724
713
|
(`opencode run`)。advise 模式鎖定內建唯讀 `plan` agent;work 模式
|
|
725
714
|
用 `--auto`。加入預設 `coding-overflow` 鏈作為最後備援。
|
package/VERSION
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
0.
|
|
1
|
+
0.32.0
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "omnilane",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.32.0",
|
|
4
4
|
"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.",
|
|
5
5
|
"bin": {
|
|
6
6
|
"omnilane": "bin/omnilane"
|
package/plugin.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"$schema": "https://antigravity.google/schemas/v1/plugin.json",
|
|
3
3
|
"name": "omnilane",
|
|
4
|
-
"version": "0.
|
|
4
|
+
"version": "0.32.0",
|
|
5
5
|
"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."
|
|
6
6
|
}
|