@journeykit/canon 0.31.0 → 0.33.0

package/dist/index.js

@@ -3,6 +3,7 @@
 // src/index.ts
 import { spawnSync, execSync } from "node:child_process";
 import { existsSync, readdirSync, realpathSync } from "node:fs";
+import { constants as osConstants } from "node:os";
 import { resolve, join, basename } from "node:path";
 import { fileURLToPath } from "node:url";
 var binaryName = process.platform === "win32" ? "canon.exe" : "canon";
@@ -165,4 +166,7 @@ var result = spawnSync(binary, process.argv.slice(2), {
 if (result.error) {
   console.error(`canon: failed to run ${binary}: ${result.error.message}`);
 }
+if (result.status === null && result.signal) {
+  process.exit(128 + (osConstants.signals[result.signal] ?? 0));
+}
 process.exit(result.status ?? 1);

package/dist/skills/SKILL.src.md

@@ -26,18 +26,34 @@ a feature, a one-line request included. A human is needed once per scope:
 
 - **The approval** (step 1). For a new subject or a scope change, the
   human must approve the brief. Write the brief,
-  run `canon brief check` until it reports no blockers, then stop and
-  report the brief to the human: build nothing for that scope (no
+  run `canon brief check` until it reports no blockers, then show it, ask and
+  record the answer: build nothing for that scope (no
   scenarios, code or evidence) before the human answers. The approval is
   the one thing you never assume, even when the human said they cannot
-  answer until you report: the brief is that report. The one answer
+  answer until you show it. The one answer
   approves the brief and the policy, `.canon/policy.yaml`, which is what
   the gate grades the work against. The human may also approve it on the `canon dashboard` briefs page; you never use that form.
-  The human records the answer, never you:
-  `canon brief approve <slug> <slug> --approver <their name> --note "<their words>"`
-  (one or more slugs, one answer for all, nothing written if any is refused)
-  refuses every agent role (`HUMAN_ONLY`). Report that exact call, every slug filled in, and
-  wait; never remove or unset your role (`env -u CANON_ROLE`, dropping `--as`) to run it yourself.
+  1. **Show** with `canon brief show <slug> --body`: the brief file's bytes and,
+     last, `digest: sha256:<hex>`. Send it to the human's own view without
+     retyping it (omp: redirect it to `out://`, which is off for subagents and
+     non-TUI sessions and caps at 64 KiB; there, and in a harness with no such
+     channel, leave the tool output visible). A subagent has no question tool:
+     the orchestrator shows, asks and records.
+  2. **Ask** with the harness question tool (`ask` in omp, `AskUserQuestion` in
+     Claude Code, otherwise in the chat): approve or request changes, several
+     briefs in one question.
+  3. **Count only an explicit approval.** A question or a condition is a
+     revision request (change the brief, check, show and ask again); no answer
+     records nothing.
+  4. **Record it** with the relay option:
+     `canon brief approve <slug> <slug> --approver <their name> --note "<their words>" --relayed-via <ask|AskUserQuestion|chat> --actor <your actor id> --digest <slug>=<digest shown>`
+     (one or more slugs, each with its own `--digest`, one answer for all, nothing written if any is refused).
+     The `Approved:` line then carries `(relayed by <role> <actor> via <tool>)`.
+     A digest that no longer matches the brief is `RELAY_DIGEST_MISMATCH`: show
+     it again. Without `--relayed-via` an agent role gets `HUMAN_ONLY`, and so
+     does a repo whose `canon.yaml` says `approval: { relay: deny }`: then the
+     human runs the call themselves. Never remove or unset your role
+     (`env -u CANON_ROLE`, dropping `--as`) to run it yourself.
   Never edit the policy to make the gate pass: a policy that differs from
   the approved one fails closed (`POLICY_CHANGED_SINCE_APPROVAL`, not
   waivable); stop and ask the human. A brief edited after its
@@ -74,7 +90,7 @@ a feature, a one-line request included. A human is needed once per scope:
   so in your report. That covers the brief's questions and work inside an
   approved scope, never the approval itself.
 
-1. **Brief.** The planner writes the PRD brief (`.canon/changes/<slug>/brief.md`), checks it with `canon brief check`, and stops for the human. `canon skills show role-planner`
+1. **Brief.** The planner writes the PRD brief (`.canon/changes/<slug>/brief.md`), checks it with `canon brief check`, shows it to the human, asks, and records their explicit approval. `canon skills show role-planner`
 2. **Subject.** `canon subject new`, then `canon change new` (`--change-kind chore` for work that alters no behavior); the change writes the brief skeleton. `canon skills show role-planner`
 3. **Scenarios.** `canon scenario new --flow <F-id> --case <case>` per behavior of a flow step, failure paths (`--case failure`) included; many at once with `--input` (below). `canon skills show role-implementer`
 4. **Units.** Split the work; one unit is one flow step's slice with a named verify command, and each unit has its own actor id and session id, passed on everything it records. A unit never attests another unit's work.
@@ -170,7 +186,7 @@ variable, and an unknown value is refused (`UNKNOWN_ROLE`).
 - **A role is set, or you were spawned as one:** load only
   `canon skills show role-<role>` and do that role's steps. `canon status`
   and `meta.next` then show only your role's steps, and count the others in
-  `waitingOn`; `canon schema --as <role>` lists only your role's commands.
+  `data.waitingOn`; `canon schema --as <role>` lists only your role's commands.
   Do not load another role's guide.
 - **No role (one agent doing everything):** follow `canon status` and load
   each role guide as its phase starts: planner for steps 1–2,
@@ -185,8 +201,11 @@ A role is guidance, not enforcement: `--role` on `evidence add` and
 
 - Start a session with `canon status`: where each subject stands and the next
   commands. After that, do not call it only to learn the next step: every
-  write returns `meta.next` (`[{command, argv, why, actor, role}]`), the same
-  steps `status` would give, narrowed to what the write touched. `actor: human`
+  write returns `meta.next` (`[{command, argv, reason, x-canon: {actor, role}}]`), the same
+  steps `status` would give, narrowed to what the write touched. Each entry is
+  runnable: `argv` is the command without `canon` (with `--json` when you
+  called in JSON mode). Guidance that needs a value you must fill in is not a
+  next entry; it is in the error `hint` or the report text. `x-canon.actor: human`
   marks a step only the human takes.
 - Your role guide's **Commands** block (`canon skills show role-<role>`) is
   your complete command set, every option of every leaf included. Run `canon schema <command> --json` only for a
@@ -195,20 +214,25 @@ A role is guidance, not enforcement: `--role` on `evidence add` and
 - Pass `--json` and read stdout as one document, nothing on stderr. Success is
   `{"ok":true,"data":…,"meta":…}`; failure is
   `{"ok":false,"error":{…},"meta":…}` (a check that fails keeps its report in
-  `data`). `meta` carries `command`, `schemaVersion`, `canonVersion`, `next`,
-  `warnings` and, for a repeated write that changed nothing, `unchanged: true`.
+  `data`). `meta` carries `tool`, `toolVersion`, `contract` (`atip/1`), `schemaVersion`,
+  `command`, and when present `next`, `warnings` (`[{code, message}]`) and
+  `page`; a repeated write that changed nothing reports `data.unchanged: true`.
+  Absent members are omitted, never `null` or `[]`. A paged list puts
+  `meta.page.nextCursor` on the call's `meta.next` as `--cursor <nextCursor>`;
+  no `nextCursor` means no more.
   On failure branch on `error.code`, fix the option `error.field` names
   using the `error.expected` values (`field` is an option name, or a JSON
   pointer such as `/items/2/scenario` into an `--input` document), and
   follow `error.hint`: every refusal carries a working invocation. The codes
   are stable; `canon schema --errors --json` lists them and
   `canon schema --error <CODE>` explains one.
-- **Exit codes:** 0 ok; 1 the command's own finding (a failed check, a
-  violation, or `unverifiable` when nothing was examined); 2 refused (usage,
+- **Exit codes:** only 0, 1 and 2 exist: 0 ok; 1 the command ran and its answer
+  is negative or incomplete (a failed check, a violation, `unverifiable` when
+  nothing was examined, a partly failed batch); 2 refused to run (usage,
   `CONFIG_MISSING`, an id or file that does not exist, an invalid argument).
   A refusal leaves the tree unchanged.
 - Repeating a write is safe: a record that already exists with identical
-  content is reported `unchanged` (`meta.unchanged`), not duplicated.
+  content is reported `unchanged` (`data.unchanged`), not duplicated.
 - An option that takes an id is the bare noun (`--change add-login`,
   `--scenario auth.login.01`, `--actor reviewer-1`, `--project root`,
   `--session s-1`), and an `--input` document key is that name without `Id`
@@ -217,16 +241,19 @@ A role is guidance, not enforcement: `--role` on `evidence add` and
   (`canon subject move <id> --to verifying`, `canon change new <slug>`), and
   `--kind` values carry no `_record` suffix (`--kind evidence`).
 - `canon status` sends the planner to write the brief while `brief check`
-  has blockers; the human stop appears only when the brief is clean and
+  has blockers; the approval step appears only when the brief is clean and
   unapproved.
 - Page long lists with `--limit <n>` and `--cursor <nextCursor>` (`--all`
   for everything), and project fields with `--fields a,b` (`status`, `export`,
   `query`, `finding list`, `divergence list`, `context`).
 - `--override-reason <text>` is the only way to proceed past a waivable
   refusal; it is recorded, echoed in `data.overrides[]` and listed by `status`
-  for the human. There is no `--force`. `brief approve`, `policy approve` and
-  `divergence accept` are human-only and refuse every agent role: report the
-  exact call, ids filled in, and wait; never unset your role to run one.
+  for the human. There is no `--force`. `brief approve`, `policy approve`,
+  `divergence accept` and the `migrate --commit` that re-binds `Approved:`
+  lines record a human's decision and refuse every agent role (`HUMAN_ONLY`)
+  unless they record the explicit answer the human gave you, with
+  `--relayed-via <tool>` (show, ask, record, as for the brief; `canon skills
+  show role-planner`); never unset your role to run one.
 
 ### Many records at once: `--input`
 
@@ -238,8 +265,8 @@ from a file or stdin) is a batch, run in order and answered with
 `skipped`, and that element's `data` or `error`). A batch is validated whole
 before anything is written: an invalid element writes nothing and exits 2,
 `error.field` pointing at `/items/<i>/<key>`; a write that fails stops there
-(exit 1) and re-running the same batch reports the finished elements
-`unchanged`. A typo in a key is refused (`INPUT_UNKNOWN_FIELD`), never dropped.
+(exit 1, `BATCH_INCOMPLETE`) and re-running the same batch reports the finished elements
+`unchanged`. A typo in a key is refused (`INPUT_INVALID`, `field` naming the key), never dropped.
 `canon schema <command> --json` shows the leaf's input schema and an example.
 
 ```text
@@ -257,7 +284,7 @@ The five commands that delete or rewrite existing data (`canon purge`,
 `canon tier age`, `canon ledger compact`, `canon artifacts move`,
 `canon migrate`) act in two steps. The bare run previews: it writes nothing,
 exits 0 and prints the effects and a `planDigest`. Read the effects, then act
-with `--commit --plan-digest <planDigest>`. It refuses (`PLAN_CHANGED`) when
+with `--commit --plan-digest <planDigest>`. It refuses (`PLAN_STALE`) when
 the plan differs from the one you previewed, so run the preview again. Appends
 and state transitions (`gate promote`, `subject move`) run directly. Where a
 preview helps elsewhere (`init`, `skills install`, `export`, `inventory sync`,
@@ -343,7 +370,7 @@ current step needs.
 | Name | What it is for |
 | --- | --- |
 | `canon` | This core guide: the loop, driving the CLI, routing. |
-| `role-planner` | Planner steps 1–2: subject, change, PRD brief, the human stop. |
+| `role-planner` | Planner steps 1–2: subject, change, PRD brief, the approval. |
 | `role-implementer` | Implementer steps 3–6: scenarios, units, code, evidence. |
 | `role-reviewer` | Reviewer step 7: findings and signed reviews in a separate session. |
 | `role-orchestrator` | Orchestrator step 8: dispatch, transitions, resuming, upgrading. |

package/dist/skills/reference/brief-align.md

@@ -33,7 +33,7 @@ A chore adds no scenarios and has no flow: this pass does not apply to it.
 
 ## Next
 
-Implement, evidence and review (loop steps 5 to 7). If the brief had to change, the human answers again with `canon brief approve` (theirs; agent roles are refused).
+Implement, evidence and review (loop steps 5 to 7). If the brief had to change, the human answers again: show the brief, ask, and record an explicit approval with `--relayed-via` (`canon skills show role-planner`).
 
 ## Invariants (every brief pass)
 
@@ -41,4 +41,4 @@ Implement, evidence and review (loop steps 5 to 7). If the brief had to change,
 - Explaining writes nothing. Asked what a finding means or what a pass would do, answer in chat and leave the brief untouched.
 - No pass requires another as a prerequisite. Run the one the findings or the human point at, in any order.
 - A pass closes only the findings it rechecked: rerun `canon brief check` after the edit and report a finding as closed only when it is gone from that run. Never claim a rule you did not rerun.
-- Write in the brief's language (detected from the text; `language:` in `canon.yaml` overrides it). Edits touch `.canon/changes/<slug>/brief.md` only. A brief edited after approval is not approved: it needs a new human answer and the human's `canon brief approve` again (agent roles are refused).
+- Write in the brief's language (detected from the text; `language:` in `canon.yaml` overrides it). Edits touch `.canon/changes/<slug>/brief.md` only. A brief edited after approval is not approved: it needs a new human answer, shown and asked again, and a new `canon brief approve` (recorded with `--relayed-via` from that answer).

package/dist/skills/reference/brief-clarify.md

@@ -33,7 +33,7 @@ Every open line is a question with a proposed default or a stated assumption. `c
 
 ## Next
 
-`harden` if the flow changed; otherwise report to the human, who answers the questions and approves (`canon brief approve` is theirs; agent roles are refused).
+`harden` if the flow changed; otherwise put the questions and the brief to the human and ask; record an explicit approval with `brief approve` with `--relayed-via <tool>` (`canon skills show role-planner`).
 
 ## Invariants (every brief pass)
 
@@ -41,4 +41,4 @@ Every open line is a question with a proposed default or a stated assumption. `c
 - Explaining writes nothing. Asked what a finding means or what a pass would do, answer in chat and leave the brief untouched.
 - No pass requires another as a prerequisite. Run the one the findings or the human point at, in any order.
 - A pass closes only the findings it rechecked: rerun `canon brief check` after the edit and report a finding as closed only when it is gone from that run. Never claim a rule you did not rerun.
-- Write in the brief's language (detected from the text; `language:` in `canon.yaml` overrides it). Edits touch `.canon/changes/<slug>/brief.md` only. A brief edited after approval is not approved: it needs a new human answer and the human's `canon brief approve` again (agent roles are refused).
+- Write in the brief's language (detected from the text; `language:` in `canon.yaml` overrides it). Edits touch `.canon/changes/<slug>/brief.md` only. A brief edited after approval is not approved: it needs a new human answer, shown and asked again, and a new `canon brief approve` (recorded with `--relayed-via` from that answer).

package/dist/skills/reference/brief-harden.md

@@ -34,7 +34,7 @@ brief has none of them: harden its Invariants and Checks instead.
 
 ## Next
 
-`align` (`canon skills show brief-align`) once scenarios exist; `polish` (`canon skills show brief-polish`) for prose; otherwise report to the human.
+`align` (`canon skills show brief-align`) once scenarios exist; `polish` (`canon skills show brief-polish`) for prose; otherwise show the brief to the human and ask (`canon skills show role-planner`).
 
 ## Invariants (every brief pass)
 
@@ -42,4 +42,4 @@ brief has none of them: harden its Invariants and Checks instead.
 - Explaining writes nothing. Asked what a finding means or what a pass would do, answer in chat and leave the brief untouched.
 - No pass requires another as a prerequisite. Run the one the findings or the human point at, in any order.
 - A pass closes only the findings it rechecked: rerun `canon brief check` after the edit and report a finding as closed only when it is gone from that run. Never claim a rule you did not rerun.
-- Write in the brief's language (detected from the text; `language:` in `canon.yaml` overrides it). Edits touch `.canon/changes/<slug>/brief.md` only. A brief edited after approval is not approved: it needs a new human answer and the human's `canon brief approve` again (agent roles are refused).
+- Write in the brief's language (detected from the text; `language:` in `canon.yaml` overrides it). Edits touch `.canon/changes/<slug>/brief.md` only. A brief edited after approval is not approved: it needs a new human answer, shown and asked again, and a new `canon brief approve` (recorded with `--relayed-via` from that answer).

package/dist/skills/reference/brief-polish.md

@@ -2,7 +2,7 @@
 
 Make the brief something a human reads once and understands. Run it whenever
 `canon brief check` reports `prose.*` advisories; `canon status` and
-`meta.next` name it before the human stop. It never blocks approval, and it
+`meta.next` name it before the approval step. It never blocks approval, and it
 is not finished by silencing rules: it is finished when the brief reads
 plainly and each advisory is gone or waived with a reason.
 
@@ -218,7 +218,7 @@ uses the section key `brief`.
 1. Fix the mode problems above, then the findings, section by section.
 2. Run `canon brief check <slug> --json`: the findings are in `data.findings[]`.
 3. Repeat until no advisory remains, or each remaining one is waived with a reason.
-4. Stop and report to the human, in the brief's language. Do not loop further: a clean run says nothing about whether the brief is good, only that these counts are within budget.
+4. Stop polishing and show the brief to the human (`canon brief show <slug> --body`), in the brief's language, and ask. Do not loop further: a clean run says nothing about whether the brief is good, only that these counts are within budget.
 
 ## NEVER
 
@@ -236,7 +236,7 @@ uses the section key `brief`.
 
 ## Next
 
-Report to the human, who approves with `canon brief approve` (theirs; agent roles are refused).
+Show the brief to the human and ask (`canon brief show <slug> --body`, then the harness question tool); record an explicit approval with `brief approve` with `--relayed-via <tool>` (`canon skills show role-planner`).
 
 ## Invariants (every brief pass)
 
@@ -244,4 +244,4 @@ Report to the human, who approves with `canon brief approve` (theirs; agent role
 - Explaining writes nothing. Asked what a finding means or what a pass would do, answer in chat and leave the brief untouched.
 - No pass requires another as a prerequisite. Run the one the findings or the human point at, in any order.
 - A pass closes only the findings it rechecked: rerun `canon brief check` after the edit and report a finding as closed only when it is gone from that run. Never claim a rule you did not rerun.
-- Write in the brief's language (detected from the text, or `language:` in `canon.yaml` when set). Edits touch `.canon/changes/<slug>/brief.md` only. A brief edited after approval is not approved: it needs a new human answer and the human's `canon brief approve` again (agent roles are refused).
+- Write in the brief's language (detected from the text, or `language:` in `canon.yaml` when set). Edits touch `.canon/changes/<slug>/brief.md` only. A brief edited after approval is not approved: it needs a new human answer, shown and asked again, and a new `canon brief approve` (recorded with `--relayed-via` from that answer).

package/dist/skills/reference/brief-shape.md

@@ -69,7 +69,7 @@ prints the guidance of each empty one (in `language:`). A wrong heading
 
 ## Next
 
-`clarify` if the Questions section still has open lines; `harden` if flow and detail disagree; otherwise report to the human, who approves with `canon brief approve` (theirs; agent roles are refused).
+`clarify` if the Questions section still has open lines; `harden` if flow and detail disagree; otherwise show the brief to the human and ask; record an explicit approval with `brief approve` with `--relayed-via <tool>` (`canon skills show role-planner`).
 
 ## Invariants (every brief pass)
 
@@ -77,4 +77,4 @@ prints the guidance of each empty one (in `language:`). A wrong heading
 - Explaining writes nothing. Asked what a finding means or what a pass would do, answer in chat and leave the brief untouched.
 - No pass requires another as a prerequisite. Run the one the findings or the human point at, in any order.
 - A pass closes only the findings it rechecked: rerun `canon brief check` after the edit and report a finding as closed only when it is gone from that run. Never claim a rule you did not rerun.
-- Write in the brief's language (detected from the text; `language:` in `canon.yaml` overrides it). Edits touch `.canon/changes/<slug>/brief.md` only. A brief edited after approval is not approved: it needs a new human answer and the human's `canon brief approve` again (agent roles are refused).
+- Write in the brief's language (detected from the text; `language:` in `canon.yaml` overrides it). Edits touch `.canon/changes/<slug>/brief.md` only. A brief edited after approval is not approved: it needs a new human answer, shown and asked again, and a new `canon brief approve` (recorded with `--relayed-via` from that answer).

package/dist/skills/reference/canon-context.md

@@ -35,7 +35,7 @@ and what to run next. `--json` prints the `{ok, data, meta}` envelope: the
 header adds no field, and `policy.spec_coverage`/`policy.diagnostics`
 already carry the same fact. `--fields <list>` keeps only the named
 top-level fields (`kinds`, `enums`, `policy`, `review`, …); an unknown name is
-`UNKNOWN_FIELD` (exit 2).
+`USAGE` (exit 2; `field` is `--fields`, `expected` lists the selectable fields).
 
 On a repository that still holds 0.27 canon state, `canon context` warns
 and puts `canon migrate --json` first in `meta.next`: run `canon migrate`

package/dist/skills/reference/canon-gate.md

@@ -299,9 +299,9 @@ never rides along into a confirming audit. `--drop-attachment` and
 
 ### Nothing is attested before the brief is approved (`--override-reason`)
 
-The approval is never assumed: the agent writes the brief, stops and
-reports it, and builds nothing for that scope until the human answers.
-`canon evidence add` is the backstop for that stop (0.16 M7). It
+The approval is never assumed: the agent writes the brief, shows it to the
+human and asks, and builds nothing for that scope until the human answers.
+`canon evidence add` is the backstop for that rule (0.16 M7). It
 refuses (exit `1`, nothing staged or stored) while a subject the record
 attests for has an enforced, unapproved brief: a change the record
 answers to (below) has a canon `.canon/changes/<change>/brief.md` with no `Approved:`
@@ -315,7 +315,7 @@ check `canon status` and the ship guard use; see
 
 ```stderr
 canon evidence add: unreviewed-promotion demo-subject — evidence for world.demo.01: brief not approved — .canon/changes/c-demo/brief.md has no `Approved:` line, so the human has not answered it; once they do, record their words with `canon brief approve c-demo --approver <the human> --note "<their words>"`
-canon evidence add: refused — stop, report the brief to the human and wait for their answer: nothing is built or attested for a subject before its brief is approved. Record their answer with `canon brief approve --approver <the human> --note "<their words>"` only from that answer; to attest anyway, pass --override-reason <text>, which is recorded on the evidence record
+canon evidence add: refused — stop and get the human's answer to the brief: nothing is built or attested for a subject before its brief is approved. Show it (`canon brief show --body`), ask with the harness question tool, and on their explicit approval record it with `canon brief approve --approver <their name> --note "<their words>" --relayed-via <the question tool> --actor <your actor id> --digest <change>=<the digest shown>` (or they approve on `canon dashboard`); never unset your role to run it; to attest anyway, pass --override-reason <text>, which is recorded on the evidence record
 ```
 
 For a change from an external plan with no canon brief yet, the first
@@ -347,7 +347,7 @@ brief_override:
 Under `--json` the same waiver is `data.overrides[]` (`code` of the waived
 refusal, `reason` verbatim), so a caller sees what its `--override-reason`
 let through; a repeat of an identical record is `unchanged`
-(`meta.unchanged`) and records no second override. `--override-reason`
+(`data.unchanged`) and records no second override. `--override-reason`
 exists on `subject move` too (see `canon-subject`).
 
 A blank or multi-line reason exits 2; an override when nothing refused is

package/dist/skills/reference/canon-policy.md

@@ -75,10 +75,13 @@ canon policy approve --approver <who> [--note <text>] [--repo <dir>]
 A human approves the policy after reviewing `.canon/policy.yaml`, in the
 same answer that approves a subject's brief (0.16; see the skill's working
 loop). `canon brief approve` records both in one call. `canon policy
-approve` is a human-only leaf: with a role declared (`--as` or `CANON_ROLE`)
-it is refused with `HUMAN_ONLY` (exit 2, not retryable), and no flag grants
-it to an agent. The human runs it themselves, for a policy-only change or
-after the brief answer, supplying `--approver` and `--note`. It
+approve` is a human's decision: with a role declared (`--as` or `CANON_ROLE`)
+it is refused with `HUMAN_ONLY` (exit 2, not retryable) unless it records the
+answer the human gave in the conversation: show them `.canon/policy.yaml`, ask,
+and on an explicit approval run it (the steps are in `canon skills show role-planner`) with `--relayed-via <tool>`, `--actor`,
+`--approver` and `--note` (their name and words); the file then carries `relay`
+(role, actor, tool). The human may run it themselves, for a policy-only change
+or after the brief answer, supplying `--approver` and `--note`. It
 writes `.canon/policy.approval.json` directly (nothing to promote):
 
 ```json

package/dist/skills/reference/canon-report-dashboard.md

@@ -163,10 +163,13 @@ refused brief): nothing is written and the page says to read it again. A request
 naming one brief the old way (`changeId`, `sha256`) is still accepted. The server is localhost only and
 refuses requests from other origins (`DASHBOARD_ORIGIN_REFUSED`).
 
-For an agent the human stop is unchanged: when clean briefs are waiting,
-tell the human they can approve them in `canon dashboard` (briefs page) or
-answer in chat. An agent never clicks Approve or fills the form, and runs
-`canon brief approve` only from the human's own words.
+For an agent: when clean briefs are waiting, show them (`canon brief show
+<slug> --body`), ask with the harness question tool, and tell the human they
+can approve them in `canon dashboard` (briefs page) instead. An agent never
+clicks Approve or fills the form; it runs `canon brief approve` only from the
+human's explicit answer, with `--relayed-via`. The page lists the approvals an
+agent recorded for the human under "Approved through an agent" (`relayed` in
+`GET /api/briefs`), with the role, actor and tool of each.
 
 The dashboard renders SEVEN panels — trust matrix, session costs, role
 memory, flywheel funnel, review burn-down, review rounds, review totals.

package/dist/skills/reference/canon-review.md

@@ -122,7 +122,7 @@ Many findings at once: `--input` takes inline JSON, a file or `-`; an array
 (or NDJSON) is a batch validated before any write. Keys are the option
 names in camelCase (`change`, `actor`, `resolutionRev`); `canon schema
 finding add --json` shows the input schema and an example. An identical
-repeat is `unchanged` (`meta.unchanged`) and writes nothing; a different
+repeat is `unchanged` (`data.unchanged`) and writes nothing; a different
 finding under an occupied key is `FINDING_SEQ_OCCUPIED`.
 
 ### A defect the author found in its own work
@@ -198,7 +198,7 @@ allowed, and the commit made from it has the same code tree, so committing it
 afterwards leaves the review as it was: a review is judged by its pins (the
 scenario and what its evidence says), not by the commit. Outside git, or
 with no commit, the write is refused with `NO_COMMIT`. An identical review
-written again is `unchanged` (`meta.unchanged` under `--json`) and adds no
+written again is `unchanged` (`data.unchanged` under `--json`) and adds no
 record.
 
 **Done when:** `canon gate check` reports no `unreviewed-promotion` for the

package/dist/skills/reference/canon-storage.md

@@ -104,7 +104,8 @@ canon query --kind handoff --since 2026-06-01T00:00:00Z
 canon query --kind trajectory --json
 
 # Page a long result and keep only the fields you need; `meta` carries
-# returned, total, hasMore and nextCursor (`--all` returns everything).
+# `page` = {returned, total, nextCursor}; a present `nextCursor` means more, and
+# `meta.next` repeats the call with `--cursor <nextCursor>` (`--all` returns everything).
 canon query --kind trajectory --json --limit 50 --fields at,kind
 canon query --kind trajectory --json --limit 50 --cursor <nextCursor>
 ```
@@ -189,7 +190,7 @@ section listing them and emits a matching stderr `WARN`.
 `canon purge --kind <kind> --before <RFC3339> [--commit --plan-digest <planDigest>] [--repo <dir>] [--json]`
 is the canonical data-lifecycle boundary: the bare run previews: it prints the removal set and
 its `planDigest` and deletes nothing; `--commit --plan-digest <planDigest>` deletes only if
-the plan recomputed now has the same digest (`PLAN_CHANGED`, exit 2, when the
+the plan recomputed now has the same digest (`PLAN_STALE`, exit 2, when the
 data moved). The only purgeable kinds are
 `session`, `run`, `event`, and `trajectory`; the cutoff applies to every
 routed rung and every configured aging destination, including retained
@@ -210,7 +211,7 @@ arguments previews an empty removal set.
 With `--json`, `purge` and `export` answer `{ "data", "meta" }` like every other
 command: `data` is the plan or manifest, `meta.next` the step after (a plan's is the
 human's review and `--commit --plan-digest`), and an export's page state (`total`, `returned`,
-`nextCursor`) sits in `meta`. `export --json --output <file>` writes the manifest to the
+`nextCursor`) sits in `meta.page`. `export --json --output <file>` writes the manifest to the
 file and answers with `data: { output, kind, recordCount }`; `--dry-run`
 answers with what it would write and writes nothing.
 

package/dist/skills/reference/canon-subject.md

@@ -71,7 +71,7 @@ canon subject new subject-domain-loop \
   NDJSON) is a batch validated before any write, with `operands` holding the
   id and the other keys the option names in camelCase (`canon schema subject
   new --json` shows the schema and an example). Writing an identical subject
-  again is a no-op reported `unchanged` (`meta.unchanged`).
+  again is a no-op reported `unchanged` (`data.unchanged`).
 
 ### 2. Retrieve subject-scoped strategy memory BEFORE working
 
@@ -207,8 +207,8 @@ the transition, not the check.
 
 This refusal is a backstop, and so is the evidence one: shipping is not
 the first thing an unapproved brief stops. The agent writes the brief,
-runs `canon brief check` until it has no blockers, then stops and reports
-it, and nothing is built or attested for the subject until the human
+runs `canon brief check` until it has no blockers, then shows it to the
+human and asks, and nothing is built or attested for the subject until the human
 answers. `canon evidence add` refuses (exit 1, nothing staged) a
 scenario whose `@subject` owner, or a task whose change
 an adopting subject, has an enforced, unapproved brief, through the same
@@ -547,7 +547,7 @@ warn, and a command that writes and judges it is refused
   human answers again and `approve` runs again. Run it only from the
   human's answer, with their words as `--note`.
 
-The optional refinement passes that fix findings before the human stop are
+The optional refinement passes that fix findings before the approval step are
 listed in `role-planner.md` in this directory.
 
 A **chore** (`canon change new --change-kind chore`) changes how the subject is
@@ -688,7 +688,7 @@ uses, so status and the gate cannot disagree about a gap:
   newest change's canon
   `brief.md` has no `Approved:` line, or it has no canon `brief.md` yet
   and comes from an external openspec `proposal.md`) and clean gets
-  `human: stop and report the brief in <brief>; build and attest nothing for <id> until the human answers (one answer approves brief and policy)`,
+  `human: show the brief in <brief> to the human and ask; build and attest nothing for <id> until the human answers (one answer approves brief and policy)`,
   where `<brief>` is the canon `brief.md`, or the external `proposal.md`
   when no canon brief exists yet. Its reason reads ``<id>: <why
   unanswered> (an older change's approval does not cover a new scope),
@@ -747,21 +747,23 @@ Status fails closed rather than suggest progress the gate would refuse:
 ```
 
 The steps that follow are not in `data`: they are `meta.next`, most useful
-first, with `meta.nextOmitted` counting what was cut and `meta.waitingOn`
+first, with `data.nextOmitted` counting what was cut and `data.waitingOn`
 (with a declared role, `--as`) counting the steps each other owner holds:
 
 ```json
 "next": [
-  { "command": "stop and report the brief in openspec/changes/c-promo/proposal.md; build and attest nothing for promo until the human answers; then record their words with `canon brief approve c-promo --approver <the human> --note \"<their words>\"`", "argv": [], "why": "promo: the brief is not approved", "actor": "human", "role": null },
-  { "command": "canon finding close c-cart --round 1 --seq 1 --disposition fixed --actor <unit> --session <session>", "argv": [], "why": "cart: 1 open blocker finding(s); fix it, commit, then close it", "actor": "agent", "role": "implementer" },
-  { "command": "canon status", "argv": ["canon", "status"], "why": "1 scenario(s) carry no @subject tag (first: cart.promo.01); add `@subject:<id>` above each in its .feature file, then check again", "actor": "agent", "role": "planner" }
+  { "command": "canon brief show c-promo --json", "argv": ["brief", "show", "c-promo", "--json"], "reason": "promo: the brief is not approved; build and attest nothing for promo until the human answers", "x-canon": { "actor": "human" } },
+  { "command": "canon gate check --json", "argv": ["gate", "check", "--json"], "reason": "cart: 1 open blocker finding(s); fix it, commit, then close it with `canon finding close`", "x-canon": { "actor": "agent", "role": "implementer" } },
+  { "command": "canon status --json", "argv": ["status", "--json"], "reason": "1 scenario(s) carry no @subject tag (first: cart.promo.01); add `@subject:<id>` above each in its .feature file, then check again", "x-canon": { "actor": "agent", "role": "planner" } }
 ]
 ```
 
-`argv` is the command split into words, and is empty when the command still
-holds a `<placeholder>` for what only the agent knows (or is not a canon
-command at all). On a repository that still holds 0.27 canon state,
-`canon status` warns (`data.warnings`, `meta.warnings`) and puts `canon
+`argv` is the command without the executable (`canon` + `argv` is the call),
+and carries `--json` when you called in JSON mode. Every next entry is
+runnable as it stands: guidance that needs a value only you know (an actor id,
+a session, the human's words) is not a next entry, it is in the error `hint`
+or the report text. On a repository that still holds 0.27 canon state,
+`canon status` warns (`data.warnings`, `meta.warnings` as `[{code, message}]`) and puts `canon
 migrate --json` first in `meta.next`: run `canon migrate`, then `canon
 migrate --commit --plan-digest <digest from the preview>`, then `canon
 skills install`.
@@ -792,14 +794,14 @@ only the pending drafts, and `flow` lists each flow step of every tagged
 change as `{ "id", "change", "scenarios": [{ id, title, failure, evidenced,
 review }], "gaps" }`.
 
-Each `meta.next` entry's `actor` is `agent` (its `command` is a canon command
-line) or `human` (its `command` says what to get from the human).
+Each `meta.next` entry's `x-canon.actor` is `agent` or `human` (a step only the
+human takes; its `reason` says what to get from them).
 
 `policy.spec_coverage` has the shape `canon context --json` prints
 (`null` when absent, `{"invalid": …}` when unusable). `statusVersion`
 changes only when a field changes meaning or is removed. It became `2`
 in 0.16, when `next[].command` stopped always being a command line
-(`actor` tells which), and `brief` was added alongside. It is `3` since
+(`actor` told which), and `brief` was added alongside. It is `3` since
 0.17, when `brief.proposal` was removed: the canon `brief.md` is
 `brief.brief`, with `briefExists` and `source`. It is `4` since 0.31, when the
 `brief` object became the `briefs` list.

package/dist/skills/reference/role-implementer.md

@@ -4,15 +4,17 @@ You build inside an approved scope: scenarios, code, tests and evidence.
 Declare the role with `CANON_ROLE=implementer` (or `--as implementer`); `--role`
 on what you record then defaults to `implementer`.
 Build nothing before the brief is approved: `canon evidence add` refuses an
-unapproved brief's scenarios. If it is not approved, say so and wait; the
-planner and the human own that. The only waiver is `--override-reason
+unapproved brief's scenarios. If it is not approved, tell the orchestrator or planner, who show it to the human and ask;
+build nothing meanwhile. The only waiver is `--override-reason
 "<why>"`, for the case where you were told to attest while the brief waits for
 the human's answer: canon records it on the evidence, echoes it in
 `data.overrides[]` and lists it in `status` for the human. Never use it to
 skip the wait yourself. `brief approve`, `policy approve` and `divergence
-accept` are the human's; they refuse you (`HUMAN_ONLY`). You never run them, and never remove or unset your role (`env -u CANON_ROLE`,
-dropping `--as`) to get past the refusal: report the exact call, slug filled in, and
-wait; the human runs it (or uses `canon dashboard`).
+accept` are the human's; they refuse you (`HUMAN_ONLY`) unless they record an
+answer the human gave in the conversation (`--relayed-via`, the planner's
+procedure: `canon skills show role-planner`). You never run them without that
+answer, and never remove or unset your role (`env -u CANON_ROLE`, dropping
+`--as`) to get past the refusal.
 
 ## Commands
 
@@ -218,7 +220,7 @@ canon trace add-login_1_1
 <!-- canon:generated commands-implementer end -->
 
 After the first `status`, follow `meta.next` of each write; do not call
-`canon status` again to learn the next step. Every record you write takes
+`canon status` again to learn the next step. Each `meta.next` entry is runnable: run `canon` + its `argv`; guidance that needs a value you must fill in is in the error `hint` or the report text, not in `meta.next`. Every record you write takes
 the commit it is about from `--rev` (default `HEAD`, any git revision). You
 need not commit first: code that is not committed yet is recorded with its
 `codeTree` and `worktreeDirty: true`, never refused. Outside git, or in a
@@ -318,7 +320,7 @@ canon evidence add --input '[{"scenario":"auth.login.01","class":"test-run","ref
    match the scenario because of something outside this change, record the
    evidence `divergent` and say why in `--ref`; never record `faithful` to
    pass. The human accepts the tracked gap (`canon divergence accept`
-   refuses agent roles); fixing the behavior and recording again is the
+   refuses agent roles unless it records their explicit answer); fixing the behavior and recording again is the
    other way out.
 5. **Promote.** Under `write: { promote: auto }` (what `canon init` writes)
    the record is final when `evidence add` returns. Only with
@@ -361,15 +363,15 @@ not another evidence step.
 |---|---|
 | "The suite is slow; record `faithful` to pass." | `faithful` over a failed case is refused; a limit outside this change is recorded `divergent` with the reason in `--ref`. |
 | "I fixed it, the test would pass." | Run the test red first and bind it, then green. Evidence is a claim; the history is what the reviewer reads. |
-| "The brief is as good as approved." | `evidence add` refuses an unapproved brief's scenarios. Say so and wait. |
+| "The brief is as good as approved." | `evidence add` refuses an unapproved brief's scenarios. Tell the orchestrator or planner, who show it to the human and ask; build nothing meanwhile. |
 | "I will attest the other unit's work under my id." | Each unit records under its own actor id and session id. |
 | "I was told this twice already." | A correction repeated across runs belongs in a scenario, the policy or a gate; tell the orchestrator. |
-| "I will accept the divergence myself." | `divergence accept` refuses agent roles (`HUMAN_ONLY`); report the scenario, the reason and the tracking reference to the human. |
+| "I will accept the divergence myself." | The human accepts a gap: report the scenario, the reason and the tracking reference so they are asked, and never record an answer they did not give. |
 
 ## Retry safety
 
 `evidence add` is content-keyed: repeating it with identical input returns
-the existing record with `meta.unchanged: true` instead of a duplicate (a
+the existing record with `data.unchanged: true` instead of a duplicate (a
 batch reports that element `unchanged`). After a timeout or a lost
 response, run the same command again. `scenario new` is not: an existing
 scenario id is refused (`SCENARIO_TAG_EXISTS`) and nothing changes, so check