Release 1.6.3: review carry-over

README.md

@@ -297,6 +297,12 @@ Other things to know:
   stop the run for you instead. You can switch modes when the table is shown. A task the
   adjudicator parks is deferred, never counted as delivered; security tasks are never
   parked, and `allow_deferral: false` forbids parking altogether.
+- **Carry-over.** Rulings (pre-flight's, the adjudicator's, implementers') live in the ledger
+  and bind every agent that starts after them, a relaunch included; a relaunch's pre-flight
+  never re-rules work already built. Task minors an earlier launch left open reach the final
+  review, where one reviewer owns the checklist. A task that changes a file another lane or a
+  later task owns needs a ruling first; edits to earlier tasks' files are flagged. See
+  `reference.md` ("Carry-over").
 - **Transient failures** (agent errors, missing results) relaunch once automatically.
   Anything substantive stops the run and asks you.
 - **Where files go.** Manifests and ledgers are stored beside the plan, or under

SKILL.md

@@ -174,10 +174,8 @@ this. Say the table is the one required check, show it, and wait.
    token (keep it for relaunches). Exit 4: another session holds the run; stop and ask, and use
    `--takeover` only when the user confirms that session ended. Then run
    `<python> <skill_dir>/scripts/setup <manifest file> --owner <token>`. Its exit 4 naming another
-   run (`the checkout ... is in use by run ...`) means that run holds the checkout: setup changed
-   nothing, so release this run's own launch lock first (`active-run release <run_id> setup_failed
-   --owner <token>`, or `active-run release <run_id> --remove --owner <token>` for a new run that never
-   started), then stop and report it. It creates the feature branch and
+   run (`the checkout ... is in use by run ...`): reference.md "Active-run markers and stops"; then stop
+   and report it. It creates the feature branch and
    worktrees and discards edits in run-owned worktrees, so never before the yes. On failure
    wait 10 seconds and retry once; then `active-run release <run_id> setup_failed --owner <token>`, report,
    and stop. Put its output in `setup_result`
@@ -195,12 +193,12 @@ this. Say the table is the one required check, show it, and wait.
    never stops the run; keep the latest launch's refusal code for `tool-outcomes`.
 5. Record each launch's spend (reference.md "Budgets"), a relaunch included, never a dry run:
    `<python> <skill_dir>/scripts/ledger ended <ledger_dir> <status> <agents_spawned>
-   <rulings_spent>` (`<status>`: reference.md "Budgets").
-   After a launch that a transient relaunch follows, record only the spend (keep the lock
-   through the relaunch). At the end, record the spend and release the lock in one command
-   line, so the spend is never forgotten once the lock goes, and a refused record (exit 2)
-   keeps the lock until it is fixed: `<python> <skill_dir>/scripts/ledger ended <ledger_dir> <status>
-   <agents_spawned> <rulings_spent> && bash <skill_dir>/scripts/active-run release <run_id>
+   <rulings_spent>` (`<status>`: reference.md "Budgets"), then `<python> <skill_dir>/scripts/ledger
+   carry-launch <ledger_dir> <transcript dir>` (reference.md "Carry-over"; exit 3: say that launch
+   is not carried). Before a transient relaunch, keep the lock. At the end, in one command line
+   (reference.md "Budgets"): `<python> <skill_dir>/scripts/ledger ended <ledger_dir> <status>
+   <agents_spawned> <rulings_spent> && { <python> <skill_dir>/scripts/ledger carry-launch <ledger_dir>
+   <transcript dir> || true; } && bash <skill_dir>/scripts/active-run release <run_id>
    <release> --owner <token>`, where `<release>` is `--remove` only for `complete` when the hand-back gate
    passes: `acceptance.status` `accepted`, and `<python> <skill_dir>/scripts/check-verify <transcript dir>
    <manifest file>` exits 0 printing status `match` or `not_required`; otherwise `<status>` (`unaccepted` for
@@ -227,7 +225,8 @@ earlier snapshot belongs to the earlier launch.
 
 Relaunch once with the relaunch notice: carry budgets over (reference.md "Transient stops"). Set
 `repairs_spent` to the repairs in the stopped run's `final.repairs` plus the earlier value.
-First recompute `done`, `reviewed`, `deferred`, the `carry` notes and `backfill` as in Resume
+First recompute `done`, `reviewed`, `deferred`, the `carry` notes, `carried_minors`,
+`inputs_changed` and `backfill` as in Resume
 steps 2-3, then rerun `scripts/setup --owner <token>` and take `start_points`; if validation
 rejects its `setup_skipped`, rerun setup. Launch again. No second table. A second transient
 stop is a real stop, unless it is a usage-limit stop (reference.md "Usage limit").
@@ -288,10 +287,13 @@ first, show its plan, and add `--yes` only on the user's yes. Keep the manifest
 
 1. Invoked notice. Read the manifest (an `active-run list` marker names it); set `python` by
    Building step 0. No manifest (earlier work from a hand-run attempt): `<skill_dir>/adopt.md` first.
-2. `<python> <skill_dir>/scripts/ledger status <ledger_dir> --plan <plan> --manifest <manifest
+2. First `<python> <skill_dir>/scripts/ledger carry-launch <ledger_dir> <wf id>` for each earlier
+   launch not yet carried, in launch order (`doctor-<wf>.json` gives its `setup_event`). Then
+   `<python> <skill_dir>/scripts/ledger status <ledger_dir> --plan <plan> --manifest <manifest
    file> [--spec <spec>]`. Set `done`, `reviewed`, and `deferred` from it (taking a deferred
    task up: reference.md "Backfill"), and `repairs_spent` from earlier reports' `final.repairs`;
-   put each `carry` entry into `notes`. Tasks in `stale`
+   put each `carry` entry into `notes`; copy `minors` into `carried_minors`, and `inputs` into
+   `inputs_changed` as `{plan: plan_changed, spec: spec_changed}` (reference.md "Carry-over"). Tasks in `stale`
    (with their dependents) or `unbound` are left out of `reviewed`, so they are reviewed
    again: tell the user which and why, and say so when `inputs` reports a changed plan or
    spec. `<python> <skill_dir>/scripts/coverage <plan> <manifest file>` must exit 0 again

VERSION

@@ -1 +1 @@
-1.6.2
+1.6.3