@azure-id/orc 1.9.1 → 2.0.2

package/CHANGELOG.md

@@ -10,6 +10,396 @@ Format: `### v<version> — <title> _(<date>)_`.
 
 ---
 
+### v2.0.2 — the lanes record what you answered, and the reviewer always gets the card _(2026-09-28)_
+
+**Still on the unscoped `orc` package?** Do this once first - your `orc upgrade`
+is the pre-v0.56.0 one and cannot install itself. Full detail in the CAUTION at
+the top of this file.
+
+- **Step 1 - release the command from the old package:** `npm uninstall -g orc`
+- **Step 2 - install the current package:** `npm i -g @azure-id/orc`
+- **Step 3 - re-apply it to your project:** `orc update`
+
+**Do not use `npm i -g -f`.** Full detail in v0.56.0 below.
+
+A patch from the live evals of 2.0 (E1–E4 in the eval sandbox). The habits feature did
+not work in live use until this release: the lanes forgot to record answers, used their
+own option and question names, and recorded a follow-up decision as the same question.
+Each fix below is in the CLI or a hook, not in more lane prose.
+
+- **`orc trace write` checks every `ASK` as it arrives.** A wrong option id, an unknown
+  question id, or a repeat of the same question with no new executor dispatch (a
+  follow-up) is kept OUT of the trace and handed back with the real ids, first in the
+  answer. The rest of the packet is written.
+- **The FINISH packet names the questions nobody recorded.** With `habits` on, the answer
+  lists each registered question of the lane that has no `ASK` in the run, with its
+  option ids. A late packet with `run: <trace name>` still lands after `.current` is gone.
+- **Habit evidence is not split by context.** The "any context" row counts every answer;
+  a row with `kind`/`branch` is a refinement. A dispatch-gate answer may list a
+  third-party slot. The habit cache version changed, so a parser change clears it.
+- **The narration guard** (session hook, `Stop`). A run that dispatched agents and wrote
+  NO narration line is stopped ONCE, with the command that fixes it. Never twice, never
+  for a subagent.
+- **The reviewer always gets the gotcha card** (session hook, `SubagentStart`). A live
+  review got no card in 5 of 5 runs. Now every `orc-reviewer-*`, `orc-verifier-*` and
+  `orc-judge-*` receives the card for the files git sees as changed. `orc update` wires
+  the new event; `orc doctor` names it when it is missing.
+- **`/orc-quick` takes the undo snapshot.** Its own start step names
+  `orc run snapshot` (before: 3 of 8 runs took it; after: 6 of 6).
+- **`rules_card_compact` is `on` by default.** Eval E4 (12 runs) passed: no new
+  `unmet[]`, no new `rules_conflicts[]`, the smoke gate green on the first try in 6 of 6
+  runs with the compact card against 3 of 6 without. `off` gives the full card.
+
+**Eval results:** E1 (the trim broke nothing) passed · E2 (habits) passed — 6 answers →
+the offer "5 of 5" → accepted → the next run marks `→ usual` and still asks; with
+`habits: off` zero `ASK` lines · E3 (the gotcha card): E3 (the gotcha card): with the card the reviewer found all 3 recurring defects in 5 of 5 runs (without: 2.4 of 3; the float-money defect 5 of 5 against 2 of 5), ordinary recall was equal (3.0), false positives fell from 2.2 to 1.0 per run. The planned gap of 1.0 could not be reached: without the card the reviewer already finds 2 of the 3, so the most the card could add was 0.6, and it added all of it · E4 passed (above).
+
+**What you have to do:** `orc update`.
+
+---
+
+### v2.0.1 — the trace keeps the gate name, and the lanes find the habits rule _(2026-09-27)_
+
+**Still on the unscoped `orc` package?** Do this once first - your `orc upgrade`
+is the pre-v0.56.0 one and cannot install itself. Full detail in the CAUTION at
+the top of this file.
+
+- **Step 1 - release the command from the old package:** `npm uninstall -g orc`
+- **Step 2 - install the current package:** `npm i -g @azure-id/orc`
+- **Step 3 - re-apply it to your project:** `orc update`
+
+**Do not use `npm i -g -f`.** Full detail in v0.56.0 below.
+
+A patch. The first live runs of 2.0.0 in the eval sandbox found four defects. Nothing
+changes for a user who has `habits` off, except that traces are complete again.
+
+- **`orc trace write` keeps the gate name.** A lane often sent `verb: GATE` and put
+  the rest in the tail. The CLI then wrote `GATE :: …`, and the name and the
+  `pass|bounce|escalate` word were lost (`orc stats` and `/orc-retro` read them).
+  The CLI now puts each event into the shape of its own grammar in `TRACE_VERBS`:
+  - `note:`, `detail:` or `text:` is used as the tail when `tail` is missing
+    (before: an EMPTY `.txt` line);
+  - a ` :: ` inside `verb` splits into head and tail, and a tail that starts with
+    `::` loses it (before: `GATE x :: :: …`);
+  - a verb with no ` :: ` in its grammar (`OUTCOME`, `FINDING`, `PHASE` …) that
+    has only a tail is joined to its head;
+  - a verb whose grammar needs head arguments (`GATE <name> pass|…`, `ASK <qid>`,
+    `DISPATCH <agent>`, `SCORE task=…`) is repaired from `args :: detail` in the
+    tail, or REFUSED by name (exit 2, nothing written) — the lane then uses the
+    writer agent.
+  `_shared/phases/trace.md` says it once: `verb` = the WHOLE head, `tail` = the detail.
+- **The lanes find the habits rule.** The `habits{}` pointer sat in each spine's
+  lane-contract block, far from the step that reads the answer, and a live
+  `/orc-quick` run with `habits: propose` never opened `_shared/habits.md` and
+  wrote no `ASK`. The rule now sits IN the step that reads `orc lane config`:
+  `/orc-quick` Q0 step 1, `/orc-mini` Phase 0, and `_shared/phases/preflight.md`
+  step 1 (orc, fast, test, pr-setup). The orc and fast spine copies were removed.
+
+**What you have to do:** `orc update`.
+
+---
+
+### v2.0.0 — the coding lanes remember what you fixed and how you work _(2026-09-27)_
+
+**Still on the unscoped `orc` package?** Do this once first - your `orc upgrade`
+is the pre-v0.56.0 one and cannot install itself. Full detail in the CAUTION at
+the top of this file.
+
+- **Step 1 - release the command from the old package:** `npm uninstall -g orc`
+- **Step 2 - install the current package:** `npm i -g @azure-id/orc`
+- **Step 3 - re-apply it to your project:** `orc update`
+
+**Do not use `npm i -g -f`.** Full detail in v0.56.0 below.
+
+This release does five things. The coding lanes load less than half the text
+they loaded before. ORC can learn the answers you give to its questions, but
+only when you turn that on, and it applies nothing without your yes. The repair
+memory (gotchas) learns from reviews, Sonar, SARIF, PR threads and closed
+defects. The reviewer returns more facts about each finding. And a set of small
+tools: `orc undo`, `orc pr threads`, `orc ci failed`, `orc ci flaky`, an
+end-of-run card, questions per run in `orc stats`, a terminal bell, and the run
+pointer after a compact.
+
+**BREAKING.** This is a major version because five contracts change in a way
+that a 1.9.x user or a fork can see:
+
+1. **`/orc-quick` now takes part in the review memory.** Before, quick did not
+   read gotchas and did not record them, and its dispatch gate said never to
+   remember an answer for the next entry. Now quick reads the gotcha card when
+   it offers a review, records the review outcome, and shows a habit
+   suggestion on its `→ suggested` line (only when `habits` is not `off`). The
+   gate is still asked every time.
+2. **The reviewer return has new REQUIRED fields**: `category` (a closed set of
+   11 values), `scenario` on every P0 and P1, and `pre_existing`. A forked or
+   hand-edited reviewer agent that does not return them fails the return
+   validation, and the orchestrator treats its return as malformed.
+3. **The closed trace verb set is larger**: `ASK` (one answered question),
+   `FINDING-OUTCOME` (what became of each finding at review close) and the
+   `GATE flaky` result. `FINDING` has optional tail fields
+   (`pre=` `suppressed=` `folded=`). A trace reader that treats the verb set as
+   closed must learn them. Old traces parse as before.
+4. **The lane spines have a new shape.** The shared lane contract text moved to
+   `_shared/lane-contract.md`, and worker instructions live in the agent files
+   only. `orc update` overwrites an installed spine as it always did, so a
+   hand patch on a spine is lost.
+5. **Config resolution has a new rank, `learned`,** below your config file and
+   above the shipped default, and a new state word `learned`. Both appear ONLY
+   when `habits` is not `off`.
+
+Nothing is removed: no config key is retired, no command is renamed, and no file
+that you own moves.
+
+**T — the lanes load less.** Each lane reads the same rules from fewer bytes.
+The trace protocol went from 36,089 to 7,885 bytes (the full verb table is now
+on demand, and each lane gets only its own verbs from `orc lane phases`). The
+file banners, history and repeated exit codes left the payload. The coding
+spines have a 16,384-byte cap. Worker instructions have one source, the agent
+file. The descriptions that load in every session went from 11,711 to 6,587
+characters, and three internal skills are hidden from the skill list.
+`orc lane config --json` now carries a `probes{}` block, so a preflight reads
+up to seven probe answers from one call. `orc trace write --packet -` writes
+the `.txt` and the `.jsonl` of a trace from one packet (the Haiku trace writer
+is now the fallback). 16 more agent files are generated from
+`agents-src/twins/`, and `node bin/build-agents.js --check` (part of
+`npm run verify`) covers them.
+
+Always-loaded bytes per lane (`spine + command + when: "always"` references):
+
+| Lane | 1.9.2 | after the trim | 2.0.0 | change |
+|---|---|---|---|---|
+| orc | 60,169 | 29,289 | 29,124 | −52 % |
+| orc-mini | 56,153 | 24,851 | 24,697 | −56 % |
+| orc-fast | 59,142 | 27,793 | 27,750 | −53 % |
+| orc-quick | 61,858 | 30,998 | 30,768 | −50 % |
+| orc-verify | 42,330 | 13,224 | 13,035 | −69 % |
+| orc-test | 61,566 | 28,295 | 27,994 | −55 % |
+| orc-pr-setup | 56,130 | 24,673 | 24,380 | −57 % |
+| orc-pr-driver | 48,456 | 18,071 | 17,882 | −63 % |
+| orc-analyze | 52,351 | 21,514 | 21,339 | −59 % |
+| orc-analyze-mini | 43,792 | 13,401 | 13,212 | −70 % |
+| orc-poly | 51,483 | 20,826 | 20,637 | −60 % |
+| orc-route | 47,454 | 16,923 | 16,734 | −65 % |
+| orc-wait | 7,082 | 6,696 | 6,693 | −5 % |
+| orc-diy | 8,098 | 5,292 | 5,278 | −35 % |
+| context-combiner | 13,193 | 11,472 | 11,472 | −13 % |
+| orc-pattern | 45,748 | 16,249 | 16,060 | −65 % |
+| orc-advisor | 2,916 | 2,605 | 2,605 | −11 % |
+| orc-judge | 4,679 | 4,280 | 4,280 | −9 % |
+| **sum** | **722,600** | **316,452** | **313,940** | **−57 %** |
+
+The habits, gotchas and review work that came after the trim added no byte to
+any lane above its trimmed value: the new text is read on demand.
+
+**H — habits (off by default).** New key `habits`: `off` · `observe` ·
+`propose`.
+
+- `off` (the default) costs zero tokens: `orc lane config --json` has no
+  habits field (with `--no-probes` it is byte-identical to 1.9.2), and no lane
+  writes an `ASK` line.
+- `observe`: each answered question writes one `ASK` line into the trace.
+  `orc habit show` computes your usual answers from those lines. It proposes
+  nothing.
+- `propose`: at the END of a run, at most once, ORC asks whether an answer you
+  keep giving should become your usual one. The rule is fixed in the CLI: at
+  least 5 full-weight answers, a Wilson lower bound of 0.55 or more, and the
+  last 3 answers the same.
+- Nothing is applied without your yes. There is no automatic level, and
+  `auto` is refused by name. An accepted habit is the `learned` rank, below
+  your config file: `orc config set` always wins. `orc habit forget <id>`
+  undoes it.
+- A habit can learn only toward the careful side: `review_before_push: on`,
+  `mini_tdd: on`, `quick_update_tests: on`. A habit to skip a review, to drop
+  TDD or to continue on a stale wiki is never applied. A dispatch gate is
+  asked every time; a habit only orders the offer.
+- 30 question points in the lanes carry an `(H <qid>)` mark.
+  `orc habit points` lists them.
+- Commands: `orc habit show | log | points | why | accept | decline | forget |
+  reset | doctor | export | purge`, and `orc habit repo` for the soft
+  preferences read from git history (commit, branch and test naming).
+- New keys: `review_before_push` (`ask`), `mini_tdd` (`ask`),
+  `quick_update_tests` (`ask`).
+
+**G — gotchas v2, importers and sync.** The repair memory learns from more
+sources, and the reviewer gets a card.
+
+- `orc gotcha add | match | card | filter | observe | accept | quality | why`,
+  `orc gotcha list --candidates` and `orc gotcha export --review-md`.
+- `orc gotcha card` is the reviewer card, sized by `gotcha_card_budget`
+  (600 tokens, minimum 200). It is always on: `gotcha_card_budget` is a size,
+  not an off switch. An entry that does not fit is counted in the card header.
+- Observations go to `.claude/orc/observations.jsonl`. A candidate becomes an
+  entry by a fixed rule: an in-lane red → green with a reproduction, a miss, a
+  security finding with a CWE tag or a HIGH impact, or 3 addressed cases in 2
+  PRs within 90 days. `orc gotcha accept <C-id>` promotes one by hand.
+- `orc gotcha filter` drops suppressed, folded and noisy advice. It never
+  removes a P0 or a P1.
+- Importers: `orc gotcha import sarif <file>`,
+  `orc gotcha import sonar` (the token comes from `SONAR_TOKEN` only),
+  `orc gotcha import pr <n>` (human threads only) and
+  `orc gotcha import issues`. `orc gotcha sync` runs every source that is
+  available, incremental and time-boxed. New keys: `gotcha_card_budget`,
+  `gotcha_sync_hours` (6), `sonar_url`, `sonar_project`, `sonar_org`.
+- A v1 `gotchas.md` stays valid, with no rewrite. The 1.9.2 parser still reads
+  a file that 2.0.0 wrote (a test copies its regex).
+- The status line gotcha count now shows a number. It was always empty.
+
+**R — the reviewer v2.** New `_shared/review-slice.md` names the slice fields
+once. The reviewer gets the diff ranges, the gotcha card, the rules card and
+the tool findings. It returns `category`, `cwe`, `scenario`, `pre_existing`,
+`group` and `confidence` on each finding. `/orc` and `/orc-ultra` can dispatch
+a disprove pass on a P0/P1. A re-review gets the previous findings. At review
+close the lane records each outcome, and `orc gotcha quality` measures the
+acceptance per category.
+
+**Q — quality of life.**
+
+- **`orc undo --run <slug>`** prints the commands that revert ONLY the files the
+  run changed, back to the snapshot taken at run start
+  (`orc run snapshot`). It changes nothing until you add `--apply`. An edit you
+  made before the run stays.
+- **`orc pr threads <n>`** lists the unresolved review threads.
+  **`orc ci failed`** lists the failing CI steps. Both are read-only.
+  `/orc-quick` takes a red CI, or Sonar and SARIF issues, as a request.
+- **`orc ci flaky`** tells a flaky local red from a real one. A flaky re-run
+  does not use a repair round, and the trace gets `GATE flaky`.
+- **The end-of-run card** names what changed and the undo command. Quick
+  prints it in place of `git checkout -- .`.
+- **`orc stats --json`** has `questions{}`: questions per run, per lane and per
+  point.
+- **`notify: bell`** rings the terminal bell once when a turn of an ORC run
+  ends. `off` is the default and is silent.
+- **After a compact**, the session hook prints the run pointer line again.
+- **`rules_card_compact`** (`off`) would give `/orc-mini` and `/orc-fast` the
+  compact rules card. It stays off until eval E4 passes.
+
+**U — `orc ui` ▸ Behaviour.** A new panel under Stats, key `u`. It shows the
+learning switch (Off · Observe · Propose), your habits with their evidence and
+the buttons the CLI allows, the rhythm of your runs, the gotchas and what the
+reviewer will see, review quality per category, and the answer log. It renders
+the CLI's lines and computes no habit. A `never` habit has no button. With
+`habits: off`, one card replaces the tabs. Reduced motion stops all motion.
+
+**Upgrade notes — what a 1.9.2 install keeps, and what changes.**
+
+- `.claude/orc.config.yaml` is read as it is. No key is renamed or retired. The
+  new keys resolve to their defaults: `habits: off`, `review_before_push: ask`,
+  `mini_tdd: ask`, `quick_update_tests: ask`, `gotcha_card_budget: 600`,
+  `gotcha_sync_hours: 6`, `notify: off`, `rules_card_compact: off`, and the
+  `sonar_*` keys empty.
+- `.claude/orc/gotchas.md` and its archive stay valid, with no rewrite. A
+  downgrade to 1.9.2 still parses the file.
+- `gotchas: off` no longer removes the reviewer card, because review learning is
+  always on. `orc config set gotchas off` says so. An old `gotchas: off` still
+  turns off the executor block (`orc gotcha match` exits 4).
+- Old traces are read as they are. They have no `ASK` lines, so the habits start
+  at `none yet`. Nothing is guessed from old `NOTE` lines.
+- Every existing field of `orc lane config --json` and `orc config list --json`
+  is unchanged (a test pins them). `probes{}` is added; `habits{}`, the
+  `learned` source and the `learned` state appear only when `habits` is on.
+- `orc gotcha status | list | show | prune` are unchanged, with the same exit
+  codes.
+- **A DIY flow compiled by 1.9.x is STALE after the update**, because the
+  version and the composed layers changed. Run `orc diy compile` after the
+  update. Until then `orc diy status` exits 1 and `/orc-diy` offers the compile
+  or plain `/orc`.
+- A forked or hand-edited reviewer agent fails the v2 return validation (see
+  BREAKING item 2). Hand-edited installed spines are overwritten, as always.
+- **`orc update` wires the new session hook** (`orc-session-hook.js`) into
+  `.claude/settings.json`: ONE `Stop` entry and ONE `SessionStart` entry with
+  the matcher `compact`. It is always wired. The `Stop` hook reads `notify` first
+  and stays silent unless `notify: bell`. `orc doctor` checks both entries, and
+  when one is missing it names `orc update` as the fix
+  (`session-hook-unwired`).
+- New files are user data: `habits-state.json`, `habits-cache.json`,
+  `observations.jsonl`, `gotchas-sync.json`. They are never in the install
+  manifest, and they survive `update`, `update --prune` and `doctor --fix`.
+- Node ≥ 18 and zero npm dependencies, as before.
+
+**Evals owed.** Four evals are prepared and NOT run. Each needs a live Claude
+Code session in the sandbox:
+
+- **E1** — trace parity before and after the trim.
+- **E2** — six `/orc-quick` requests under `habits: propose` give one proposal,
+  and the seventh shows `→ usual`.
+- **E3** — five reviews with the gotcha card and five without it. The card
+  stays on whatever the result is.
+- **E4** — the compact rules card on `/orc-mini` and `/orc-fast`.
+  `rules_card_compact` stays `off` until E4 passes.
+
+**What you have to do:** `orc update`. Then, if you use `/orc-diy`,
+`orc diy compile`. To try habits, `orc config set habits observe`.
+
+---
+
+### v1.9.2 — the code graph gets its own tab, and Opus 5 becomes Opus 5.5 _(2026-09-23)_
+
+**Still on the unscoped `orc` package?** Do this once first - your `orc upgrade`
+is the pre-v0.56.0 one and cannot install itself. Full detail in the CAUTION at
+the top of this file.
+
+- **Step 1 - release the command from the old package:** `npm uninstall -g orc`
+- **Step 2 - install the current package:** `npm i -g @azure-id/orc`
+- **Step 3 - re-apply it to your project:** `orc update`
+
+**Do not use `npm i -g -f`.** Full detail in v0.56.0 below.
+
+**The code graph has its own tab.** Before this release the graph was one card
+on the Knowledge ▸ Wiki tab: fourteen rows of exact numbers and no picture of
+what any of them meant. `orc ui` ▸ Knowledge now has a sixth tab, **Code
+graph**, and the card on the Wiki tab is gone. The tab reads top to bottom:
+
+- **Where your code graph is now.** The four states `OFF` · `NONE` · `FRESH`
+  · `DRIFTED` as a ladder, with the action that moves the graph from one to
+  the next on each connector. The current state is lit and sends a ring
+  outward. Below it is the ONE action that state needs: the config command for
+  OFF (copy-able, never a button), the free `orc graph update` button for NONE
+  and DRIFTED, nothing for FRESH. The line a lane prints into the chat
+  (`line`) is shown verbatim.
+- **How the code graph works.** Five stations — your code, the parser, the
+  map, the questions, the short card — with dots that run between them. The
+  first three are marked free; the card is marked as what costs context tokens.
+  The optional notes layer, the only part that can cost a model, is a separate
+  line with the current `code_graph_notes` value.
+- **What a code graph looks like (an example, not your code).** Four files from
+  a made-up shop drawn as an SVG: files, symbols, calls (a pulse runs caller to
+  callee), refs and imports. Point at a dot, or Tab to it, and its edges light
+  up while a caption says what `orc graph ctx` would answer. A legend names
+  every mark.
+- **Your graph, in numbers.** Files, symbols, symbols per file and generation
+  as tiles that count up to the CLI's own value; the added · changed · deleted
+  counts; and the density as a bar, per language when the CLI sent
+  `density.by_lang`.
+- **What the graph cost, and what it probably saved.** `paid` (four stacked
+  parts) and `avoided` (solid to its low end, striped to its high end) on ONE
+  scale. Every read in `read_set`, in the CLI's order, with its count and one
+  line on what it answers; a read never asked keeps its slot, muted.
+- **All the numbers, as the CLI sent them.** The old card, unchanged, minus the
+  chip and the button the ladder now carries.
+- **What each word means.** Every term on the tab in four groups.
+
+The pictures derive nothing: every number is `orc graph status --json` or
+`orc graph gain --json`, drawn to scale. `prefers-reduced-motion` removes all
+three new infinite animations with `display: none` and every finite one with
+`animation: none`, and the tiles skip their count-up. The `graph-drifted`
+doctor finding on Overview now opens the Code graph tab.
+
+**Every Opus 5 agent now runs Opus 5.5 (`claude-opus-5-5`).** Every agent and
+generated executor that shipped as `model: claude-opus-5` now ships as
+`model: claude-opus-5-5`, and the prose that named "Opus 5" now names
+"Opus 5.5". Opus 5.5 is cheaper than Opus 5, so the same pipeline costs less.
+`bin/pricing.json` gains the `claude-opus-5-5` row ($4 input · $5 cache write
+· $0.20 cache read · $20 output per million tokens, from the Claude pricing
+page), and `orc budget` prices its forecasts against it.
+
+What did NOT change: the agent NAMES (`orc-executor-opus-5-med` and the rest),
+the `opus5_only` key and its "Opus 5-only" mode name. `claude-opus-5` stays
+in the known-model list and keeps its price row, so an existing config and old
+traces still validate and still price.
+
+**What you have to do:** `orc update`, to install the new agent files.
+
+---
+
 ### v1.9.1 — the graph that was paid for and never asked _(2026-09-23)_
 
 **Still on the unscoped `orc` package?** Do this once first - your `orc upgrade`

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-1.9.1-blue.svg?style=for-the-badge)
+![Version](https://img.shields.io/badge/version-2.0.2-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: v1.9.1** · diperbarui 23-09-2026 · [daftar perubahan lengkap](CHANGELOG.md)
+**Versi terbaru: v2.0.2** · diperbarui 28-09-2026 · [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`
 
@@ -271,7 +271,7 @@ pemakaian 5 jam, pemakaian mingguan, dan beberapa hal lain.
 | Perintah | Kegunaannya | Contoh jalannya |
 |---|---|---|
 | **`/orc`** | Alur penuh: terima → rencana → gelombang paralel bernilai → periksa → uji → kirim. Rajin menyimpan titik simpan; bisa dilanjutkan di sesi baru. | [lihat](mock-run/orc.md) |
-| **`/orc-ultra`** | Sama, ditambah penasihat Opus 5 **xhigh** dan tiga gerbang penilaian. Analisis dalam, pola kode, tes, dan keamanan dipaksa menyala. Memang mahal. | [lihat](mock-run/orc-ultra.md) |
+| **`/orc-ultra`** | Sama, ditambah penasihat Opus 5.5 **xhigh** dan tiga gerbang penilaian. Analisis dalam, pola kode, tes, dan keamanan dipaksa menyala. Memang mahal. | [lihat](mock-run/orc-ultra.md) |
 | **`/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) |
@@ -786,45 +786,29 @@ 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.
 
-### v1.9.1 - graf yang dibayar tetapi tidak pernah ditanya _(23-09-2026)_
+### v2.0.2 - lane mencatat jawaban Anda, dan reviewer selalu mendapat kartunya _(28-09-2026)_
 
-Graf kode lebih sering dirawat daripada ditanya, dan bagian yang ditanya lebih
-mahal daripada yang dicatat meterannya. Di satu proyek Vue nyata, 416 dari 429
-berkas `.vue` tidak punya simbol, dan panel menulis `0 hook updates` setelah 35.
+**Patch dari eval langsung.** Habits sekarang benar-benar bekerja di run langsung, dan
+reviewer selalu mendapat kartunya:
 
-**Jawaban lebih kecil.** `--brief` menyimpan kartu, baris dan setiap hitungan,
-lalu membuang baris yang tidak pernah dicetak lane: 74 % sampai 87 % lebih
-kecil, dan setiap panggilan lane memakainya. CLI sekarang menghitung baris
-blast-radius `/orc-quick` dan baris kompleksitas `/orc-mini` dalam satu
-panggilan, bukan lane yang menghitung baris-barisnya.
+- **Jawaban Anda dicatat dengan benar.** `orc trace write` memeriksa setiap jawaban saat
+  masuk dan mengembalikan jawaban yang salah bersama id yang benar. Di akhir run, ia
+  menyebut pertanyaan yang belum dicatat.
+- **Reviewer selalu mendapat kartu gotcha.** Sebuah hook memberikannya ke setiap
+  reviewer, verifier dan judge.
+- **Run yang tidak menulis trace dihentikan sekali** dan diberi tahu cara memperbaikinya.
+- **`/orc-quick` selalu mengambil snapshot undo.**
+- **Kartu aturan ringkas menyala secara default untuk `/orc-mini` dan `/orc-fast`** (eval E4 lulus).
 
-**Meterannya jujur.** Pembaruan oleh hook selalu tercatat 0, dan `paid`
-menghitung kartu padahal lane menerima 4 sampai 8 kali lebih banyak. Keduanya
-diperbaiki: baris `hook-update`, dan `paid.envelope` di samping kartu.
-Meterannya juga menulis pembacaan yang belum pernah dilakukan proyek ini.
-
-**Peta memberi tahu kapan ia tipis, dan kenapa** — `THIN` di `orc graph
-status`, dan `orc graph audit` baru yang menulis berkas kosong per bahasa,
-yang terpanjang lebih dulu.
-
-**Parser membaca Vue Options API** (mesin `graph@6`). Komponen, mixin dan modul
-Vuex menjadi class dengan method; `mixins` menjadi basisnya; konstanta yang
-diekspor dan komponen `<script setup>` diberi nama. Store 1.9.0 memperbarui
-dirinya sendiri satu kali, di preflight berikutnya. Tidak ada yang perlu
-dilakukan.
-
-**Pembacaan berbayar membawa isinya:** `ctx --callers-source` (enam baris di
-sekitar setiap titik panggil yang pasti), `lsp_at` untuk language server jika
-kartu menulis `AMBIGUOUS`, dan hitungan pembacaan berkas lebar yang tidak
-diberi petunjuk.
-
-**Tidak diukur di sini:** evaluasi sesi langsung tidak dijalankan, dan gerbang
-Vue (di bawah 20 % berkas `.vue` kosong) diukur di proyek Anda sendiri.
-CHANGELOG menyebut setiap batasnya.
+**Yang harus Anda lakukan:** `orc update`.
 
 <details>
-<summary><strong>Rilis sebelumnya</strong> — 120 rilis, hanya judulnya. Teks lengkapnya (dalam bahasa Inggris) ada di <a href="CHANGELOG.md">CHANGELOG.md</a>.</summary>
+<summary><strong>Rilis sebelumnya</strong> — 124 rilis, hanya judulnya. Teks lengkapnya (dalam bahasa Inggris) ada di <a href="CHANGELOG.md">CHANGELOG.md</a>.</summary>
 
+- **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_
 - **v1.8.1** — the guard that only failed on Windows · _2026-09-16_

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-1.9.1-blue.svg?style=for-the-badge)
+![Version](https://img.shields.io/badge/version-2.0.2-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: v1.9.1** · updated 2026-09-23 · [full changelog](CHANGELOG.md)
+**Latest: v2.0.2** · updated 28-09-2026 · [full changelog](CHANGELOG.md)
 
 **On npm: [`@azure-id/orc`](https://www.npmjs.com/package/@azure-id/orc)** — `npm i -g @azure-id/orc`
 
@@ -250,7 +250,7 @@ ORC have terminal hook to see: Context Window %, 5 Hour usage %, Weekly usage %
 | Command | What it does | Mocked run |
 |---|---|---|
 | **`/orc`** | The full pipeline: intake → plan → scored parallel waves → review → verify → ship. Checkpoints eagerly; resumes in a fresh session. | [see it](mock-run/orc.md) |
-| **`/orc-ultra`** | The same, plus an Opus 5 **xhigh** advisor and three judgment gates. Deep analysis, patterns, tests and security forced on. Costly by design. | [see it](mock-run/orc-ultra.md) |
+| **`/orc-ultra`** | The same, plus an Opus 5.5 **xhigh** advisor and three judgment gates. Deep analysis, patterns, tests and security forced on. Costly by design. | [see it](mock-run/orc-ultra.md) |
 | **`/orc-mini`** | One Sonnet 5 executor, a build + test smoke gate, ship. Skips full review and verify. A one-line **complexity read** with counts behind it offers the full lane when the change is wider than one area. Switches to the full flow mid-run on request. | [see it](templates/skills/orc-mini/examples/mini-run-mock.md) |
 | **`/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) |
@@ -505,7 +505,8 @@ 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` |
@@ -663,7 +664,7 @@ 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 +686,7 @@ 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 +730,29 @@ 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.
 
-### v1.9.1 — the graph that was paid for and never asked _(2026-09-23)_
+### v2.0.2 — the lanes record what you answered, and the reviewer always gets the card _(2026-09-28)_
 
-The code graph was maintained far more than it was consulted, and the part that
-was consulted cost more than the meter said. On one real Vue project, 416 of
-429 `.vue` files had no symbol, and the panel said `0 hook updates` after 35.
+**A patch from the live evals.** Habits now really work in a live run, and the reviewer
+always gets its card:
 
-**Answers are smaller.** `--brief` keeps the card, the line and every count and
-drops the rows a lane never prints: 74 % to 87 % smaller, and every lane call
-uses it. The CLI now computes `/orc-quick`'s blast-radius line and
-`/orc-mini`'s complexity line in one call, instead of the lane counting rows.
+- **Your answers are recorded correctly.** `orc trace write` checks every answer as it
+  arrives and hands a wrong one back with the right ids. At the end of a run it names
+  any question nobody recorded.
+- **The reviewer always gets the gotcha card.** A hook hands it to every reviewer,
+  verifier and judge, so a lane that forgets it cannot lose it.
+- **A run that writes no trace is stopped once** and told how to fix it.
+- **`/orc-quick` always takes the undo snapshot.**
+- **The compact rules card is on by default for `/orc-mini` and `/orc-fast`** (eval E4 passed).
 
-**The meter tells the truth.** Hook updates were always counted as 0, and
-`paid` counted the card while the lane received 4 to 8 times more. Both are
-fixed: a `hook-update` row, and `paid.envelope` beside the cards. The meter
-also lists the reads this project has never made.
-
-**The map says when it is thin, and why** — `THIN` on `orc graph status`, and
-a new `orc graph audit` that lists the empty files by language, longest first.
-
-**The parser reads the Vue Options API** (engine `graph@6`). A component, a
-mixin and a Vuex module are a class with methods; `mixins` are its bases;
-exported constants and `<script setup>` components are named. A 1.9.0 store
-upgrades itself once, at the next preflight. Nothing to do.
-
-**The paid reads carry what they were paid for:** `ctx --callers-source` (six
-lines around each confident call site), `lsp_at` for a language server when a
-card says `AMBIGUOUS`, and a count of the wide whole-file reads no hint named.
-
-**Not measured here:** the live-session evaluation did not run, and the Vue gate
-(under 20 % empty `.vue` files) is measured on your own project. The CHANGELOG
-names every limit.
+**What you have to do:** `orc update`.
 
 <details>
-<summary><strong>Earlier releases</strong> — 120 of them, titles only. Full text in <a href="CHANGELOG.md">CHANGELOG.md</a>.</summary>
+<summary><strong>Earlier releases</strong> — 124 of them, titles only. Full text in <a href="CHANGELOG.md">CHANGELOG.md</a>.</summary>
 
+- **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_
 - **v1.8.1** — the guard that only failed on Windows · _2026-09-16_