@azure-id/orc 1.9.2 → 2.1.0

package/README-id.md

@@ -7,13 +7,13 @@
 *Terima permintaan → pahami → rencanakan → beri nilai → kerjakan paralel → periksa → uji → kirim.*
 
 ![npm](https://img.shields.io/npm/v/%40azure-id%2Forc?style=for-the-badge&color=cb3837&logo=npm)
-![Version](https://img.shields.io/badge/version-1.9.2-blue.svg?style=for-the-badge)
+![Version](https://img.shields.io/badge/version-2.1.0-blue.svg?style=for-the-badge)
 ![License](https://img.shields.io/badge/license-MIT-green.svg?style=for-the-badge)
 ![Node](https://img.shields.io/badge/node-%3E%3D18-brightgreen.svg?style=for-the-badge)
 ![Claude Code](https://img.shields.io/badge/Claude_Code-Skills-purple.svg?style=for-the-badge)
 ![Dependencies](https://img.shields.io/badge/dependencies-zero-lightgrey.svg?style=for-the-badge)
 
-**Versi terbaru: v1.9.2** · diperbarui 23-09-2026 · [daftar perubahan lengkap](CHANGELOG.md)
+**Versi terbaru: v2.1.0** · diperbarui 02-10-2026 · [daftar perubahan lengkap](CHANGELOG.md)
 
 **Ada di npm: [`@azure-id/orc`](https://www.npmjs.com/package/@azure-id/orc)** — `npm i -g @azure-id/orc`
 
@@ -275,6 +275,7 @@ pemakaian 5 jam, pemakaian mingguan, dan beberapa hal lain.
 | **`/orc-mini`** | Satu agen Sonnet 5, satu pemeriksaan build + tes, lalu kirim. Melewati review penuh dan pengujian. Satu baris **pembacaan kompleksitas** berisi angka menawarkan lane penuh kalau perubahannya lebih luas dari satu area. Bisa pindah ke alur penuh di tengah jalan kalau diminta. | [lihat](templates/skills/orc-mini/examples/mini-run-mock.md) |
 | **`/orc-fast`** | Lane tercepat. Butuh wiki yang masih segar **dan** pola kode yang sudah tersimpan; kalau ada, ia melewati tahap analis dan perencana sepenuhnya. Kalau salah satu syarat tidak ada, ia mundur ke `/orc-mini` — obrolan tidak pernah berhenti. | [lihat](mock-run/orc-fast.md) |
 | **`/orc-quick`** | Minta apa saja: perbaikan kecil, pertanyaan, mencari bug, menaikkan versi dependensi, komentar PR. Lihat → tanya sekali → kerjakan. **Selalu bertanya agen mana yang mau dipakai**, dan tidak ada pengaturan yang bisa mengubah itu. Satu **defect direproduksi merah dulu sebelum diperbaiki**. | [lihat](mock-run/orc-quick.md) |
+| **`/orc-fix`** | Memperbaiki satu hal setelah review: isu Sonar, CI merah, atau bug yang ditemukan orang. Di dalam run yang sedang dijeda, ia hanya **mencatat** perbaikannya (satu observasi dan satu baris `FIX` di jejak run itu), jadi review yang melewatkannya ikut terhitung. Kalau tidak ada run yang terbuka, ia memperbaiki seperti `/orc-quick` dan bertanya agen mana yang dipakai. | [lihat](mock-run/orc-fix.md) |
 | **`/orc-diy`** | Lane racikan Anda sendiri, disusun di terminal dengan `orc diy` lalu dikompilasi. Kalau belum disetel atau sudah basi, ia menolak jalan dan menawarkan `/orc` biasa. | [lihat](mock-run/orc-diy.md) |
 
 ### Memikirkan apa yang mau dibuat
@@ -665,9 +666,19 @@ dipublikasikan mengubahnya jadi angka. Risiko yang dikutip memaksa nilai minimal
 model terkunci** — jadi apa yang benar-benar berjalan bisa diperiksa, bukan
 sekadar diminta lewat kalimat.
 
+Tabel bawaan (sejak v2.1.0):
+
+| Nilai | Agen | Model · effort |
+|---|---|---|
+| `[0,21)` | `orc-executor-sonnet-5-low` | Sonnet 5 · low |
+| `[21,31)` | `orc-executor-sonnet-5-med` | Sonnet 5 · medium |
+| `[31,41)` | `orc-executor-sonnet-5-high` | Sonnet 5 · high |
+| `[41,90)` | `orc-executor-opus-5-low` | Opus 5.5 · low |
+| `[90,100]` | `orc-executor-opus-5-med` | Opus 5.5 · medium |
+
 > **Aturan yang paling sering membuat orang bingung:** model sebuah subagen tidak
-> akan pernah lebih tinggi daripada model sesi utama Anda. Jalankan sesi Anda di
-> Opus 5.
+> akan pernah lebih tinggi daripada model sesi utama Anda. Setiap pita mulai nilai
+> 41 butuh sesi utama Opus 5.5.
 
 **Penjelasan lengkap — pita nilainya, `opus5_only`, dan penjaga tingkat yang
 dipasang `orc init`: [guides/model-selection.md](guides/model-selection.md).**
@@ -699,13 +710,13 @@ yang sama.
 
 ```
 templates/
-├── skills/       31 folder skill, 38 berkas SKILL.md (satu lane boleh membawa
+├── skills/       34 folder skill, 41 berkas SKILL.md (satu lane boleh membawa
 │                 sub-skill) — lane di atas, plus yang tidak punya perintah
 │                 sendiri: context-combiner, orc-advisor, orc-judge,
 │                 orc-analyze-mini, dan _shared/ (kesepakatan lintas lane)
-├── commands/     29 perintah garis miring
+├── commands/     33 perintah garis miring
 ├── hooks/        penjaga effort (PreToolUse) · peringatan statusline · catatan jejak
-└── agents/       48 subagen dengan model terkunci + MODEL-MAPPING.md
+└── agents/       50 subagen dengan model terkunci + MODEL-MAPPING.md
 bin/cli.js        pemasang, penyunting pengaturan, penyusun alur, pembaca status
                   pekerjaan, dan separuh pasti dari setiap lane. Setiap pembacaan
                   bisa menjawab --json
@@ -786,43 +797,46 @@ Bacalah sebagai catatan putaran itu, bukan sebagai audit terkini:
 **Riwayat lengkap: [CHANGELOG.md](CHANGELOG.md)** — atau `orc changelog`, yang
 hanya mencetak yang lebih baru dari versi yang Anda punya.
 
-### v1.9.2 - graf kode mendapat tab sendiri, dan Opus 5 menjadi Opus 5.5 _(23-09-2026)_
-
-**Graf kode punya tab sendiri.** `orc ui` ▸ Knowledge ▸ **Code graph**
-menggantikan satu kartu di tab Wiki. Tab ini menunjukkan, berurutan:
-
-- **Posisi graf Anda sekarang** — empat status (OFF · NONE · FRESH · DRIFTED)
-  sebagai tangga. Status saat ini menyala, dan satu tindakan yang dibutuhkan
-  ada di bawahnya.
-- **Cara kerja graf kode** — lima langkah beranimasi, dari file Anda sampai
-  kartu singkat yang dibaca agent. Tiga langkah pertama gratis.
-- **Seperti apa graf kode** — contoh graf (bukan kode Anda). Arahkan pointer ke
-  sebuah titik untuk melihat pemanggil dan yang dipanggilnya.
-- **Graf Anda, dalam angka** — file, simbol, kepadatan per bahasa, dan apa yang
-  berubah sejak pembuatan terakhir.
-- **Biaya graf, dan perkiraan hematnya** — dibayar (persis) dan dihindari
-  (perkiraan, digambar sebagai rentang) pada satu skala, dan pertanyaan yang
-  diajukan lane.
-- **Arti setiap kata** — setiap istilah di tab ini, dengan kata sederhana.
-
-Temuan DRIFTED di Overview sekarang membuka tab ini. Reduced motion menghapus
-semua animasi.
-
-**Setiap agent Opus 5 sekarang memakai Opus 5.5.** Model id-nya
-`claude-opus-5-5` (sebelumnya `claude-opus-5`): executor, scout, analis,
-planner, reviewer, verifier, judge, dan setiap agent Opus lainnya. Opus 5.5
-lebih murah: $4 input, $5 cache write, $0,20 cache read, dan $20 output per
-sejuta token. `bin/pricing.json` punya baris baru, dan `orc budget`
-memakainya.
-
-**Yang harus Anda lakukan:** jalankan `orc update` untuk memasang file agent
-yang baru. NAMA agent tidak berubah, jadi `rubric_bands_override`,
-`fixed_executor` dan `opus5_only` tetap berjalan. Config yang masih menyebut
-`claude-opus-5` tetap valid.
+### v2.1.0 - review terhitung, tabel nilai naik, dan log lama bisa dihapus _(02-10-2026)_
+
+- **Tabel nilai baru dengan lima pita.** Nilai 0–40 ke Sonnet 5 (low, medium,
+  high). Nilai 41–89 ke Opus 5.5 low, dan 90–100 ke Opus 5.5 medium. Haiku tidak
+  lagi ada di tabel. **Setiap pita mulai nilai 41 butuh sesi utama Opus 5.5.**
+- **Sonnet 5 berjalan di `claude-sonnet-5-5`.** Tabel harga kembali benar.
+- **Reviewer sekarang `orc-reviewer-opus-5-low`.** Di eval langsung, effort low
+  menemukan setiap cacat yang sengaja ditanam dan masih ada di diff.
+- **Pemindai wiki dan penulis CLAUDE.md memakai Opus 5.5 low** (dulu Opus 4.8).
+- **Review quality tidak lagi menulis "0 so far" setelah review sungguhan.** Ia
+  menghitung review dari jejak. Review yang bersih juga dihitung.
+- **Aturan review milik proyek Anda.** Kalau CLAUDE.md atau AGENTS.md meminta
+  review lain (misalnya `/code-review`), lane bertanya "review ORC, review itu,
+  atau lewati". `orc review policy` menunjukkan apa yang ORC temukan.
+- **Lane baru `/orc-fix`.** Ia mencatat perbaikan setelah review (Sonar, CI merah,
+  bug) dan siapa yang memasukkan bug itu. Kartu reviewer menampilkannya, dan panel
+  menampilkan "Fixes after review".
+- **`orc clear logs`** menampilkan jejak dan folder run yang lama. `--apply`
+  menghapusnya. Tidak ada yang dihapus otomatis kecuali Anda menyetel
+  `log_retention_auto: on`.
+- **Timer status line:** 1, 2, 3, 5 atau 10 detik. Di bawah 1 detik ditolak, karena
+  Claude Code tidak mendukungnya.
+- **Perbaikan tab Behaviour:** dengan `habits: off` Anda tetap melihat Review quality
+  dan Gotchas, `/orc-fast` mencatat jawaban Anda, dan log jawaban menampilkan
+  pertanyaannya.
+
+**Yang harus Anda lakukan:** `orc update`. Kalau Anda punya alur `orc diy` yang
+sudah dikompilasi, jalankan `orc diy compile`. Kalau ada skrip yang menyebut
+`orc-reviewer-opus-5-med`, ganti menjadi `orc-reviewer-opus-5-low`. Biayanya
+berubah: baca CHANGELOG.
 
 <details>
-<summary><strong>Rilis sebelumnya</strong> — 121 rilis, hanya judulnya. Teks lengkapnya (dalam bahasa Inggris) ada di <a href="CHANGELOG.md">CHANGELOG.md</a>.</summary>
-
+<summary><strong>Rilis sebelumnya</strong> — 127 rilis, hanya judulnya. Teks lengkapnya (dalam bahasa Inggris) ada di <a href="CHANGELOG.md">CHANGELOG.md</a>.</summary>
+
+- **v2.0.4** — design the status line to the last cell · _2026-09-30_
+- **v2.0.3** — the status line you designed is the status line you see · _2026-09-30_
+- **v2.0.2** — the lanes record what you answered, and the reviewer always gets the card · _2026-09-28_
+- **v2.0.1** — the trace keeps the gate name, and the lanes find the habits rule · _2026-09-27_
+- **v2.0.0** — the coding lanes remember what you fixed and how you work · _2026-09-27_
+- **v1.9.2** — the code graph gets its own tab, and Opus 5 becomes Opus 5.5 · _2026-09-23_
 - **v1.9.1** — the graph that was paid for and never asked · _2026-09-23_
 - **v1.9.0** — the lean lanes learn to look before they leap · _2026-09-21_
 - **v1.8.2** — the map that finds what a grep cannot · _2026-09-21_

package/README.md

@@ -7,14 +7,14 @@
 *Intake → analyze → plan → score → parallel subagents → review → verify → ship.*
 
 ![npm](https://img.shields.io/npm/v/%40azure-id%2Forc?style=for-the-badge&color=cb3837&logo=npm)
-![Version](https://img.shields.io/badge/version-1.9.2-blue.svg?style=for-the-badge)
+![Version](https://img.shields.io/badge/version-2.1.0-blue.svg?style=for-the-badge)
 ![License](https://img.shields.io/badge/license-MIT-green.svg?style=for-the-badge)
 ![Node](https://img.shields.io/badge/node-%3E%3D18-brightgreen.svg?style=for-the-badge)
 ![Claude Code](https://img.shields.io/badge/Claude_Code-Skills-purple.svg?style=for-the-badge)
 ![Dependencies](https://img.shields.io/badge/dependencies-zero-lightgrey.svg?style=for-the-badge)
 ![GitHub stars](https://img.shields.io/github/stars/azure-id/orc?style=for-the-badge&color=yellow)
 
-**Latest: v1.9.2** · updated 2026-09-23 · [full changelog](CHANGELOG.md)
+**Latest: v2.1.0** · updated 02-10-2026 · [full changelog](CHANGELOG.md)
 
 **On npm: [`@azure-id/orc`](https://www.npmjs.com/package/@azure-id/orc)** — `npm i -g @azure-id/orc`
 
@@ -255,6 +255,7 @@ ORC have terminal hook to see: Context Window %, 5 Hour usage %, Weekly usage %
 | **`/orc-fast`** | The fastest lane. Needs a fresh wiki **and** a cached code pattern; then it skips the analyst and planner entirely. A missing prerequisite falls back to `/orc-mini` — the chat never stops. | [see it](mock-run/orc-fast.md) |
 | **`/orc-quick`** | Ask for anything: a fix, a question, a defect hunt, a dependency bump, PR comments. Look → ask once → do. **It always asks which agent to dispatch**, and no setting can change that. A defect is **reproduced red before it is fixed**. | [see it](mock-run/orc-quick.md) |
 | **`/orc-wait`** | Wall-clock pause without losing the run. You see the window is nearly full, type `/orc-wait 30`, and ORC hands the run back to disk, waits in detached hops that **cost zero tokens**, and picks up where it stopped. Three modes decide how much finishes first: `safe` · `soft` (forces the checkpoint) · `hard` (fastest, can lose an in-flight return). `/orc-wait block <reason>` tells it not to stop you at all. | — |
+| **`/orc-fix`** | Fix one thing after a review: a Sonar issue, a red CI, a bug someone found. Inside a paused run it only **records** the fix (one observation and one `FIX` line in that run's trace), so the review that missed it is counted. With no run open, it fixes like `/orc-quick` and asks which agent to use. | [see it](mock-run/orc-fix.md) |
 | **`/orc-diy`** | Your own lane, composed in the terminal with `orc diy` and compiled. Unconfigured or stale → it refuses and offers plain `/orc`. | [see it](mock-run/orc-diy.md) |
 
 ### Work out what to build
@@ -505,7 +506,8 @@ orc ui --stop          # shut this project's server down
 | Settings | every config key, grouped, each with its own control | staged edits, applied together |
 | Runs | run history as an accordion: a row opens in place into state-of-play, resume prompt, checkpoint, trace tail | — |
 | **Knowledge** | **five tabs**: the wiki's tier AND its **contents** (every doc, what it covers, how often it is read), coverage against your tracked files, the code patterns with the conflicts the codifier flagged, repair memory with a **preview-then-apply** prune, and a read-only view of the linked repos | `wiki sync`, `gotcha prune` |
-| Stats | lane and agent usage, downgrades, and a **Cost** tab whose stacked bar keeps cache-read visible | — |
+| Stats | lane and agent usage, downgrades, questions per run, and a **Cost** tab whose stacked bar keeps cache-read visible | — |
+| **Behaviour** | the learning switch (Off · Observe · Propose), your habits with their evidence, the rhythm of your runs, the gotchas and the exact card the reviewer sees, review quality per category, and the answer log | `config set habits`, `habit accept` / `decline` / `forget`, `gotcha accept` |
 | Flow | the compiled DIY flow, its gate, and a stepper of every phase in order | `diy set`, `diy compile`, presets |
 | Crosslink | **Design** (the boundary as a graph) and **Settings** (each peer's freshness) | `crosslink add` / `remove` |
 | Promises · Boundary · Self-serve | the pact ledger, the boundary cards, and the surfaces a non-developer can change | `pact check`, `pact sync`, `handoff set` |
@@ -616,8 +618,18 @@ fixed published formula turns them into a number. A cited risk forces a floor of
 70. The score maps through a published table to a **named, model-pinned agent**,
 so what ran is inspectable rather than requested in prose.
 
+The default table (since v2.1.0):
+
+| Score | Agent | Model · effort |
+|---|---|---|
+| `[0,21)` | `orc-executor-sonnet-5-low` | Sonnet 5 · low |
+| `[21,31)` | `orc-executor-sonnet-5-med` | Sonnet 5 · medium |
+| `[31,41)` | `orc-executor-sonnet-5-high` | Sonnet 5 · high |
+| `[41,90)` | `orc-executor-opus-5-low` | Opus 5.5 · low |
+| `[90,100]` | `orc-executor-opus-5-med` | Opus 5.5 · medium |
+
 > **The rule that catches everyone:** a subagent's model can never be higher than
-> your main session's. Run your session on Opus 5.
+> your main session's. Every band from score 41 needs an Opus 5.5 main session.
 
 **Full detail — the bands, `opus5_only`, and the tier guard `orc init` installs:
 [guides/model-selection.md](guides/model-selection.md).**
@@ -648,13 +660,13 @@ clobbers. `orc ui` ▸ Settings edits the same keys through the same validators.
 
 ```
 templates/
-├── skills/       31 skill folders, 38 SKILL.md files (a lane may ship subskills) —
+├── skills/       34 skill folders, 41 SKILL.md files (a lane may ship subskills) —
 │                 the lanes above, plus the ones with no command of their own:
 │                 context-combiner, orc-advisor, orc-judge, orc-analyze-mini,
 │                 and _shared/ (cross-lane contract prose)
-├── commands/     29 slash commands
+├── commands/     33 slash commands
 ├── hooks/        effort guard (PreToolUse) · statusline warning · behavior trace
-└── agents/       48 model-pinned subagents + MODEL-MAPPING.md
+└── agents/       50 model-pinned subagents + MODEL-MAPPING.md
 bin/cli.js        installer, config editor, flow composer, run-state reader, and
                   the deterministic half of every lane. Every read speaks --json
 bin/graph*.js     the code graph: store, extraction, resolution + its cache and
@@ -663,7 +675,7 @@ bin/webui/        `orc ui` — the local control panel: css/ + js/ + i18n/<lang>
                   fixtures/, one file per layer and per panel. Zero deps, no build step
 bin/mockrun-catalog.js   the mocked-run catalogue (derived from the files on disk)
 mock-run/         the mocked runs themselves — start at INDEX.md
-guides/           configuration · model selection · documents · knowledge reads · other AI models
+guides/           configuration · model selection · documents · knowledge reads · other AI models · habits and gotchas
 ```
 
 The `orc` skill is a thin **spine**: it loads a reference or a subskill only when
@@ -685,6 +697,7 @@ Some lanes ship a full how-to next to the skill, in plain language:
 | [ORC-PR-DRIVER](templates/skills/orc-pr-driver/README.md) | you have a stack plan and want to build, submit and merge it |
 | [Rules](guides/rules.md) | you want the 65 anti-slop rules, the precedence ladder and the lint |
 | [Configuration](guides/configuration.md) · [Model selection](guides/model-selection.md) | you want every key, or the scoring bands |
+| [Habits and gotchas](guides/habits-and-gotchas.md) | you want to know how a habit is proposed, how to import Sonar, SARIF or PR history, and how to undo |
 | [Other AI models](guides/extra-models.md) | you want part of the ladder to run somewhere other than Claude |
 
 Every skill also ships its own `SKILL.md` and `references/`. The guides above are
@@ -728,41 +741,45 @@ a current audit: [EVAL-REPORT.md](EVAL-REPORT.md).
 **Full history: [CHANGELOG.md](CHANGELOG.md)** — or `orc changelog`, which prints
 only what is newer than the version you have.
 
-### v1.9.2 — the code graph gets its own tab, and Opus 5 becomes Opus 5.5 _(2026-09-23)_
-
-**The code graph has its own tab.** `orc ui` ▸ Knowledge ▸ **Code graph**
-replaces the one card on the Wiki tab. The tab shows, in this order:
-
-- **Where your graph is now** — the four states (OFF · NONE · FRESH · DRIFTED)
-  as a ladder. The current state is lit, and the one action it needs is below.
-- **How the code graph works** — five animated steps, from your files to the
-  short card an agent reads. The first three are free.
-- **What a code graph looks like** — an example graph (not your code). Put the
-  pointer on a dot to see its callers and callees.
-- **Your graph, in numbers** — files, symbols, density per language, and what
-  changed since the last build.
-- **What the graph cost, and what it probably saved** — paid (exact) and
-  avoided (an estimate, drawn as a range) on one scale, and which reads lanes
-  asked.
-- **What each word means** — every term on the tab, in plain words.
-
-A DRIFTED finding on Overview now opens this tab. Reduced motion removes every
-animation.
-
-**Every Opus 5 agent now runs Opus 5.5.** The model id is `claude-opus-5-5`
-(was `claude-opus-5`): executors, scouts, the analyst, the planner, the
-reviewer, the verifier, the judges and every other Opus agent. Opus 5.5 costs
-less: $4 input, $5 cache write, $0.20 cache read and $20 output per million
-tokens. `bin/pricing.json` has the new row, and `orc budget` uses it.
-
-**What you have to do:** run `orc update` to install the new agent files. The
-agent NAMES did not change, so `rubric_bands_override`, `fixed_executor` and
-`opus5_only` keep working. A config that still names `claude-opus-5` is still
-valid.
+### v2.1.0 — the review counts, the score table moves up, and old logs can go _(2026-10-02)_
+
+- **A new score table with five bands.** Scores 0–40 go to Sonnet 5 (low,
+  medium, high). Scores 41–89 go to Opus 5.5 low, and 90–100 to Opus 5.5 medium.
+  Haiku is no longer in the table. **Every band from 41 needs an Opus 5.5 main
+  session.**
+- **Sonnet 5 runs on `claude-sonnet-5-5`.** The price table is correct again.
+- **The reviewer is `orc-reviewer-opus-5-low`.** In the live eval, low effort
+  found every seeded defect that was still in the diff.
+- **The wiki scanner and the CLAUDE.md writer use Opus 5.5 low** (they used Opus
+  4.8).
+- **Review quality no longer says "0 so far" after real reviews.** It counts
+  reviews from the traces. A clean review counts too.
+- **Your project's own review rule.** When CLAUDE.md or AGENTS.md asks for a
+  different review (for example `/code-review`), the lanes ask "ORC review, that
+  review, or skip". `orc review policy` shows what ORC found.
+- **New lane `/orc-fix`.** It records a fix after a review (Sonar, a red CI, a
+  bug) and who added the bug. The reviewer card shows it, and the panel shows
+  "Fixes after review".
+- **`orc clear logs`** shows old traces and run folders. `--apply` deletes them.
+  Nothing is deleted automatically unless you set `log_retention_auto: on`.
+- **The status line timer:** 1, 2, 3, 5 or 10 seconds. Below 1 second is refused,
+  because Claude Code does not support it.
+- **Behaviour tab fixes:** with `habits: off` you still see Review quality and
+  Gotchas, `/orc-fast` records your answers, and the answer log shows the question.
+
+**What you have to do:** `orc update`. If you compiled an `orc diy` flow, run
+`orc diy compile`. If a script names `orc-reviewer-opus-5-med`, change it to
+`orc-reviewer-opus-5-low`. The cost changes: read the CHANGELOG.
 
 <details>
-<summary><strong>Earlier releases</strong> — 121 of them, titles only. Full text in <a href="CHANGELOG.md">CHANGELOG.md</a>.</summary>
-
+<summary><strong>Earlier releases</strong> — 127 of them, titles only. Full text in <a href="CHANGELOG.md">CHANGELOG.md</a>.</summary>
+
+- **v2.0.4** — design the status line to the last cell · _2026-09-30_
+- **v2.0.3** — the status line you designed is the status line you see · _2026-09-30_
+- **v2.0.2** — the lanes record what you answered, and the reviewer always gets the card · _2026-09-28_
+- **v2.0.1** — the trace keeps the gate name, and the lanes find the habits rule · _2026-09-27_
+- **v2.0.0** — the coding lanes remember what you fixed and how you work · _2026-09-27_
+- **v1.9.2** — the code graph gets its own tab, and Opus 5 becomes Opus 5.5 · _2026-09-23_
 - **v1.9.1** — the graph that was paid for and never asked · _2026-09-23_
 - **v1.9.0** — the lean lanes learn to look before they leap · _2026-09-21_
 - **v1.8.2** — the map that finds what a grep cannot · _2026-09-21_

package/bin/build-agents.js

@@ -1,18 +1,26 @@
 #!/usr/bin/env node
 "use strict";
 /**
- * Executor-agent generator. The 6 executor agent files differ ONLY in
- * frontmatter (name/model/effort + score band); their body is one shared
- * contract. This script is the single source of truth: edit
- * agents-src/executor.template.md (or the VARIANTS table), run
- * `npm run build:agents`, and every copy is stamped out identically.
+ * Agent generator. Two sets, one rule: a file that differs from its siblings
+ * ONLY in frontmatter and the "You are … (<model>, <effort>)" line is GENERATED.
+ *
+ *   1. The 10 executors — agents-src/executor.template.md × VARIANTS
+ *      (name/model/effort + score band).
+ *   2. The 8 model-twin pairs (v2.0.0 T15) — agents-src/twins/<family>.template.md
+ *      × TWINS (name/model/effort/description + the `who` line). One body per
+ *      family: before T15 each pair was two hand-kept copies that nothing
+ *      checked against each other.
+ *
+ * Edit the template (or the table), run `npm run build:agents`, and every copy
+ * is stamped out identically. A model change is still a RENAME: a new row, not
+ * an edited one.
  *
  * Modes:
- *   node bin/build-agents.js          write templates/agents/orc-executor-*.md
+ *   node bin/build-agents.js          write both sets into templates/agents/
  *   node bin/build-agents.js --check  fail if any generated file drifted from
- *                                     the template (runs in `npm run verify`
+ *                                     its template (runs in `npm run verify`
  *                                     and prepack — a hand-edit to a generated
- *                                     executor file fails the build)
+ *                                     agent file fails the build)
  */
 const fs = require("fs");
 const path = require("path");
@@ -26,8 +34,9 @@ const OUT_DIR = path.join(ROOT, "templates", "agents");
 // together). `effort: null` = a model with NO effort ladder (haiku): the
 // generator omits the `effort:` frontmatter line entirely.
 //
-// v1.0.0 W4 — the table is SIX bands, not eight, and the `opus5_only` ladder is
-// TWO, not three. Four of these agents are named by NO default row:
+// v1.0.0 W4 — the table was SIX bands, not eight, and the `opus5_only` ladder is
+// TWO, not three. v2.1.0 made the table FIVE bands (Sonnet 5 low/med/high, then
+// Opus 5.5 low/med). Seven of these agents are named by NO default row:
 // names them, and they ship anyway (D14). They stay reachable through
 // `rubric_bands_override`, `orc diy` `fixed_executor` and `extra_fallback_agent`,
 // and deleting a generated file that no row happens to name today would be a
@@ -36,19 +45,76 @@ const OUT_DIR = path.join(ROOT, "templates", "agents");
 // lies is worse than one that admits it is unreachable by default.
 const VARIANTS = [
   { name: "orc-executor-opus-5-med",     model: "claude-opus-5-5",     effort: "medium", band: "highest-complexity [90,100]" },
-  { name: "orc-executor-opus-5-low",     model: "claude-opus-5-5",     effort: "low",    band: "upper-complexity [65,90)" },
-  { name: "orc-executor-sonnet-5-high",  model: "claude-sonnet-5",  effort: "high",   band: "mid-complexity [55,65)" },
-  { name: "orc-executor-sonnet-4-6-high", model: "claude-sonnet-4-6", effort: "high",  band: "low-mid-complexity [40,55)" },
-  { name: "orc-executor-sonnet-4-6-med", model: "claude-sonnet-4-6", effort: "medium", band: "low-complexity [30,40)" },
-  { name: "orc-executor-haiku-4-5",      model: "claude-haiku-4-5",  effort: null,     band: "lowest-complexity [0,30)" },
-  // NAMED BY NO BAND since v1.0.0 W4 (D14) — kept on disk, dispatched only when a
-  // user names one explicitly.
-  { name: "orc-executor-opus-5-high",    model: "claude-opus-5-5",    effort: "high",   band: "no default band — reachable via rubric_bands_override, orc diy fixed_executor, or extra_fallback_agent" },
-  { name: "orc-executor-opus-4-8-high",  model: "claude-opus-4-8",  effort: "high",   band: "no default band — reachable via rubric_bands_override, orc diy fixed_executor, or extra_fallback_agent" },
-  { name: "orc-executor-opus-4-7-high",  model: "claude-opus-4-7",  effort: "high",   band: "no default band — reachable via rubric_bands_override, orc diy fixed_executor, or extra_fallback_agent" },
-  { name: "orc-executor-opus-4-7-med",   model: "claude-opus-4-7",  effort: "medium", band: "no default band — reachable via rubric_bands_override, orc diy fixed_executor, or extra_fallback_agent" },
+  { name: "orc-executor-opus-5-low",     model: "claude-opus-5-5",     effort: "low",    band: "upper-complexity [41,90)" },
+  { name: "orc-executor-sonnet-5-high",  model: "claude-sonnet-5-5",  effort: "high",   band: "mid-complexity [31,41)" },
+  { name: "orc-executor-sonnet-5-med",   model: "claude-sonnet-5-5",  effort: "medium", band: "low-complexity [21,31)" },
+  { name: "orc-executor-sonnet-5-low",   model: "claude-sonnet-5-5",  effort: "low",    band: "lowest-complexity [0,21)" },
+  // NAMED BY NO BAND since v1.0.0 W4 / v2.1.0 (D14) — kept on disk, dispatched
+  // only when a user names one explicitly.
+  { name: "orc-executor-sonnet-4-6-high", model: "claude-sonnet-4-6", effort: "high",  band: "none (opt-in only, see MODEL-MAPPING.md)" },
+  { name: "orc-executor-sonnet-4-6-med", model: "claude-sonnet-4-6", effort: "medium", band: "none (opt-in only, see MODEL-MAPPING.md)" },
+  { name: "orc-executor-haiku-4-5",      model: "claude-haiku-4-5",  effort: null,     band: "none (opt-in only, see MODEL-MAPPING.md)" },
+  { name: "orc-executor-opus-5-high",    model: "claude-opus-5-5",    effort: "high",   band: "none (opt-in only, see MODEL-MAPPING.md)" },
+  { name: "orc-executor-opus-4-8-high",  model: "claude-opus-4-8",  effort: "high",   band: "none (opt-in only, see MODEL-MAPPING.md)" },
+  { name: "orc-executor-opus-4-7-high",  model: "claude-opus-4-7",  effort: "high",   band: "none (opt-in only, see MODEL-MAPPING.md)" },
+  { name: "orc-executor-opus-4-7-med",   model: "claude-opus-4-7",  effort: "medium", band: "none (opt-in only, see MODEL-MAPPING.md)" },
 ];
 
+// v2.0.0 T15 — the model twins. Each family is one template under
+// agents-src/twins/; a row fills five placeholders: {{NAME}}, {{MODEL}},
+// {{EFFORT}}, {{DESC}} (the one-line frontmatter description) and {{WHO}} (the
+// "(Sonnet 5, high)" part of the "You are …" line — absent for a family whose
+// body never names its own model). The pair is a runtime choice (`opus5_only`,
+// the recon gate, the wiki tier ladder), so both halves always ship.
+const TWIN_DIR = path.join(ROOT, "agents-src", "twins");
+const TWINS = [
+  { family: "analyze-mini", variants: [
+    { name: "orc-analyze-mini-sonnet-5-high", model: "claude-sonnet-5-5", effort: "high", who: "Sonnet 5, high",
+      desc: "ORC mini System Analyst — claude-sonnet-5-5, high effort. Dispatched by /orc-mini and /orc-analyze-mini at analysis: single pass, no deep mode, no scouts." },
+    { name: "orc-analyze-mini-opus-5-med", model: "claude-opus-5-5", effort: "medium", who: "Opus 5.5, medium",
+      desc: "ORC mini System Analyst — claude-opus-5-5, medium effort. Dispatched by /orc-mini and /orc-analyze-mini, instead of orc-analyze-mini-sonnet-5-high when `opus5_only: true`." },
+  ] },
+  { family: "planner-mini", variants: [
+    { name: "orc-planner-mini-sonnet-5-high", model: "claude-sonnet-5-5", effort: "high", who: "Sonnet 5, high",
+      desc: "ORC mini Requirement Planner — claude-sonnet-5-5, high effort. Dispatched by /orc-mini at planning." },
+    { name: "orc-planner-mini-opus-5-med", model: "claude-opus-5-5", effort: "medium", who: "Opus 5.5, medium",
+      desc: "ORC mini Requirement Planner — claude-opus-5-5, medium effort. Dispatched by /orc-mini at planning, instead of orc-planner-mini-sonnet-5-high when `opus5_only: true`." },
+  ] },
+  { family: "pattern-codifier", variants: [
+    { name: "orc-pattern-codifier-sonnet-5-high", model: "claude-sonnet-5-5", effort: "high",
+      desc: "ORC Pattern Codifier — claude-sonnet-5-5, high effort. Dispatched by orc-pattern (lazy /orc miss, eager orc-wiki, or manual /orc-pattern) for ONE language." },
+    { name: "orc-pattern-codifier-opus-5-med", model: "claude-opus-5-5", effort: "medium",
+      desc: "ORC Pattern Codifier — claude-opus-5-5, medium effort. Dispatched by orc-pattern, instead of orc-pattern-codifier-sonnet-5-high when `opus5_only: true`." },
+  ] },
+  { family: "recon", variants: [
+    { name: "orc-recon-sonnet-4-6-med", model: "claude-sonnet-4-6", effort: "medium", who: "Sonnet 4.6, medium",
+      desc: "ORC Recon — claude-sonnet-4-6, medium effort. Dispatched by /orc-quick at the dispatch gate, for a read-only question. It never edits." },
+    { name: "orc-recon-opus-5-low", model: "claude-opus-5-5", effort: "low", who: "Opus 5.5, low",
+      desc: "ORC Recon — claude-opus-5-5, low effort. Dispatched by /orc-quick at the dispatch gate, for a WIDE or SUBTLE read-only question. It never edits." },
+  ] },
+  { family: "retro", variants: [
+    { name: "orc-retro-sonnet-5-high", model: "claude-sonnet-5-5", effort: "high", who: "Sonnet 5, high",
+      desc: "ORC Retro miner — claude-sonnet-5-5, high effort. Dispatched by /orc-retro to mine the behavior traces. Read-only, report-only." },
+    { name: "orc-retro-opus-5-med", model: "claude-opus-5-5", effort: "medium", who: "Opus 5.5, medium",
+      desc: "ORC Retro miner — claude-opus-5-5, medium effort. Dispatched by /orc-retro, instead of orc-retro-sonnet-5-high when `opus5_only: true`. Read-only." },
+  ] },
+  { family: "scout", variants: [
+    { name: "orc-scout-sonnet-4-6-high", model: "claude-sonnet-4-6", effort: "high", who: "Sonnet 4.6, high",
+      desc: "ORC Code Scout — claude-sonnet-4-6, high effort. Dispatched by orc in the analyst's DEEP mode (≤max_scouts in parallel), ONE coverage area each." },
+    { name: "orc-scout-opus-5-low", model: "claude-opus-5-5", effort: "low", who: "Opus 5.5, low",
+      desc: "ORC Code Scout — claude-opus-5-5, low effort. Dispatched by orc in the analyst's DEEP mode, instead of orc-scout-sonnet-4-6-high when `opus5_only: true`." },
+  ] },
+  { family: "claude-writer", variants: [
+    { name: "orc-claude-writer-opus-5-low", model: "claude-opus-5-5", effort: "low", who: "Opus 5.5, low",
+      desc: "ORC CLAUDE.md Writer — claude-opus-5-5, low effort. Dispatched by /orc-claude to create, update or refresh the repo-root CLAUDE.md." },
+  ] },
+  { family: "wiki-scanner", variants: [
+    { name: "orc-wiki-scanner-opus-5-low", model: "claude-opus-5-5", effort: "low",
+      desc: "ORC Wiki Scanner — claude-opus-5-5, low effort. Dispatched by orc-wiki per scan-task (DEEP tier), ONE coverage area each." },
+  ] },
+];
+
+
 // Line endings are NOT content here: .gitattributes stores these files with LF
 // and checks them out native, so a Windows worktree is CRLF and a Linux one LF.
 // The injected frontmatter line therefore borrows the TEMPLATE's own ending, and
@@ -68,17 +134,44 @@ function render(template, v) {
     .replace(/\{\{BAND\}\}/g, v.band);
 }
 
-function main() {
-  const checkMode = process.argv.includes("--check");
+function renderTwin(template, v) {
+  return template
+    .replace(/\{\{NAME\}\}/g, v.name)
+    .replace(/\{\{MODEL\}\}/g, v.model)
+    .replace(/\{\{EFFORT\}\}/g, v.effort)
+    .replace(/\{\{DESC\}\}/g, v.desc)
+    .replace(/\{\{WHO\}\}/g, v.who || "");
+}
+
+// Every [template, row, renderer] the generator owns, executors first.
+function jobs() {
   const template = fs.readFileSync(TEMPLATE, "utf8");
   if (/\{\{(?!NAME|MODEL|EFFORT_DESC|EFFORT_FM|BAND)\w/.test(template)) {
     console.error("❌ build-agents: unknown {{placeholder}} in executor.template.md");
     process.exit(1);
   }
+  const out = VARIANTS.map((v) => ({ v, out: render(template, v), src: "agents-src/executor.template.md" }));
+  for (const fam of TWINS) {
+    const src = "agents-src/twins/" + fam.family + ".template.md";
+    const t = fs.readFileSync(path.join(TWIN_DIR, fam.family + ".template.md"), "utf8");
+    if (/\{\{(?!(?:NAME|MODEL|EFFORT|DESC|WHO)\}\})\w/.test(t)) {
+      console.error("❌ build-agents: unknown {{placeholder}} in " + src);
+      process.exit(1);
+    }
+    if (/\{\{WHO\}\}/.test(t) !==fam.variants.every((v) => v.who)) {
+      console.error("❌ build-agents: " + src + " and its TWINS rows disagree about {{WHO}}");
+      process.exit(1);
+    }
+    for (const v of fam.variants) out.push({ v, out: renderTwin(t, v), src });
+  }
+  return out;
+}
 
+function main() {
+  const checkMode = process.argv.includes("--check");
+  const all = jobs();
   let drifted = 0;
-  for (const v of VARIANTS) {
-    const out = render(template, v);
+  for (const { v, out, src } of all) {
     const dest = path.join(OUT_DIR, v.name + ".md");
     if (checkMode) {
       const current = fs.existsSync(dest) ? fs.readFileSync(dest, "utf8") : null;
@@ -86,8 +179,8 @@ function main() {
         drifted++;
         console.error(
           `❌ generated agent drifted: templates/agents/${v.name}.md\n` +
-            `   Executor agents are GENERATED — edit agents-src/executor.template.md\n` +
-            `   (or bin/build-agents.js VARIANTS) and run: npm run build:agents`
+            `   This agent is GENERATED — edit ${src}\n` +
+            `   (or the VARIANTS / TWINS table in bin/build-agents.js) and run: npm run build:agents`
         );
       }
     } else {
@@ -98,12 +191,15 @@ function main() {
 
   if (checkMode) {
     if (drifted) process.exit(1);
-    console.log(`✅ ORC executor agents OK — ${VARIANTS.length} files match the template.`);
+    const twins = all.length - VARIANTS.length;
+    console.log(
+      `✅ ORC executor agents OK — ${VARIANTS.length} files match the template; ${twins} model twins match agents-src/twins/.`
+    );
   }
 }
 
 // Required by test/payload.test.js, which checks the line-ending rule above
 // without writing to templates/agents/.
-module.exports = { VARIANTS, render, lf, eolOf };
+module.exports = { VARIANTS, TWINS, render, renderTwin, lf, eolOf };
 
 if (require.main === module) main();