@openrig/cli 0.6.8 → 0.6.10

package/daemon/context-packs/onboarding-width/public-what-you-can-do.md

@@ -11,7 +11,7 @@ not know exists.** So the point of what follows is not skill. It is recognition:
 lands, something rhymes, and you go check instead of building.
 
 Eighty-seven top-level verbs ship (capability canon refreshed through
-`capability-delta-v0.6.8`). This marker describes the pack's teaching, not publication or live
+`capability-delta-v0.6.10`). This marker describes the pack's teaching, not publication or live
 adoption. Read this once for shape, and let it make you suspicious that a thing already exists.
 Model-divergence proclamations are live product (trust them; pins use canonical
 model IDs).
@@ -28,8 +28,9 @@ one command away. Your memory of the fleet is a claim about the past.
 - **`rig ps`** — what rigs exist. **`rig ps --nodes -A`** — the state of every seat everywhere,
   *including the broken ones*. **The bare form is the question you usually want:** `--active`
   filters to running and **hides detached, exited and attention states** — which are exactly the
-  cells you were scanning for. **`rig ps --resources`** shows this host's load and transcript
-  capture cost.
+  cells you were scanning for. A seat whose tmux session is confirmed gone reads `detached`
+  (activity reason `session_missing`), and `rig ps --nodes` says to restore or relaunch it.
+  **`rig ps --resources`** shows this host's load and transcript capture cost.
 - **`rig ps --all-hosts --nodes -A`** — the same across every registered machine. Rollup-only
   unless you ask for nodes.
 - **`rig discover`** — what is running on this box that OpenRig is *not* managing.
@@ -89,6 +90,9 @@ unseen — which makes messages the one delivery channel that never gets skipped
   confirm by effect, never relaunch on it. A send or wake to a seat whose latest hook is a
   question waiting for a person is refused with `target_needs_input`, even when its screen
   can't be read: read it with `rig capture` and get the question answered instead of retrying.
+  Over `--host` to an http-registered host, a send that may have reached the remote reads
+  `remote-outcome-unknown` ("Delivery UNCONFIRMED"): check the target with `rig capture <session>
+  --host <id>` before any resend. Only a host that was never reached reads as unreachable.
 - **`rig send --raw`** — send exact text or keystrokes without the From/To envelope;
   the interactive-prompt guard still applies. To deliberately drive an interactive prompt,
   **`--dangerously-interact --reason "<why>"`** is the explicit override and implies raw text.
@@ -97,7 +101,9 @@ unseen — which makes messages the one delivery channel that never gets skipped
   the wording wrong on the fourth. **Blast radius is real** — on a large rig this lands in every
   seat's turn.
 - **`rig capture <seat>`** — read what is on their screen right now. **`--rig` / `--pod`** captures
-  every seat in one call.
+  every seat in one call. `--lines N` is the last N lines (stderr says how many earlier lines were
+  cut); `--history-plus-pane` gives the older N history lines plus the whole pane. A short capture
+  doesn't prove a seat is idle.
 - **`rig transcript <seat>`** — what has been *said* in a seat, and **seat-scoped rather than
   session-scoped**: one file spanning every agent generation that has occupied it, so it reaches
   back through handovers. Capped (`transcripts.lines`, default 1000 — raise it for depth), and
@@ -110,7 +116,9 @@ unseen — which makes messages the one delivery channel that never gets skipped
   runtime tokens.
 - **`rig chatroom wait`** — block until a peer actually says something, instead of polling
   `capture` in a loop. Also `history`, `watch`, `topic` for a named thread that stays retrievable.
-  Its `--timeout` is in seconds and ignores a suffix, so `2m` means 2 seconds.
+  Its `--timeout` is in seconds and ignores a suffix, so `2m` means 2 seconds. Poll timeouts,
+  connection refusals, and reset or closed connections are retried until that deadline; other errors,
+  including an error answer from the daemon such as a removed rig, still end the wait.
 - **`rig stream emit` / `list` / `watch` / `archive`** — drop an observation somewhere the *next*
   agent will find it. Emitting costs nothing and does not interrupt anyone; the value appears when
   someone lists the stream before starting.
@@ -126,7 +134,9 @@ unseen — which makes messages the one delivery channel that never gets skipped
   window, and only then say that clicking macOS's Allow is fine. Herdr is visible only in a
   terminal the person can see; switching the shared TUI to `:terminals` does not open one. Over
   SSH, in CI or with no display, the command returns a definite no-window result with the reason
-  and an attach command: relay that command exactly. Inspect the result and visible content, or
+  and an attach command: relay that command exactly. When the daemon runs on a non-default tmux
+  server, attach commands carry `-L <name>` or `-S <path>`; from inside tmux run them as
+  `env -u TMUX <tmuxAttachCommand>`. Inspect the result and visible content, or
   say what cannot be verified. On a desktop, do not finish by printing a command for the person to
   type. Only if the window cannot open, `rig tui --shared` is the dashboard-only fallback; explain
   the failure. `--provider herdr` or `--provider cmux` adds tiles inside a workspace that is
@@ -148,7 +158,10 @@ unseen — which makes messages the one delivery channel that never gets skipped
   readiness for the delivery decision and `queue create --verify` for its receipt; connector
   setup or verification is not an outbound human message. After a connection gap the daemon
   catches up on missed channel messages and marks them late; `rig slack status` shows the
-  connection and the catch-up state. **`rig slack channel-map list` / `set <match> <channel>` /
+  connection, the catch-up state, and the count of retained retry records for inbound messages,
+  reactions and click answers (kept across restarts, not a distinct-message count). A retained alert whose row closed before its retry isn't
+  posted; the row says why. Its `Delivery:` line says whether events are confirmed arriving;
+  "connected" alone is not delivery, and a connection that stops delivering is replaced. **`rig slack channel-map list` / `set <match> <channel>` /
   `remove <match>`** sends a rig's or seat's human-bound posts to its own channel (a seat match
   beats a rig match; the rest use the default channel). After a change, invite the app to each
   channel, run `rig slack verify`, and rewire the connector (`rig slack disable` then `enable`, or
@@ -169,7 +182,11 @@ your context, your compaction and your replacement — and it is the only thing
 
 - **`rig queue create`** — a row with an owner, a body and a transition history. Its reply, like
   `handoff`'s, confirms the row was saved; the owner is woken after that. Before you say they were
-  told, read the row's transitions (or use `--verify` for a person's request).
+  told, read the row's transitions, or use `--verify`. For a seat it reports the wake's terminal
+  receipt and any claim separately: an unconfirmed receipt is not a failed handoff, and a claim is
+  pickup, not proof the body was read. For a row the seat already claimed, `outcome` can read
+  `indeterminate` while `claim` is accurate: read `claim`. It isn't a failed handoff, so don't
+  re-run the create.
 - **`rig queue show`** — what a row *actually says*. The header is not the body.
 - **`rig queue claim` / `unclaim`** — is this mine and running, or still pending where two agents
   might double-work it. Put it down honestly when it is not yours.
@@ -191,6 +208,11 @@ your context, your compaction and your replacement — and it is the only thing
   delivery, the row's transitions are the receipt ledger; `undelivered` does not answer whether a
   person received the escalation. **`overdue` and `undelivered` are the two halves of "is anything
   silently stuck", and a rig can be clean on one and rotten on the other.**
+- **`queue.wake_human_rung`** — when a seat can't be woken, the last escalation step posts to a
+  person. `rig config set queue.wake_human_rung explicit-only` (default `always`) keeps that post
+  for rows addressed to a person (an `@external` address or a registered human); the rest stop at
+  `rig view show escalations`. A seat stuck at a prompt only a person can clear still reaches one,
+  and an unreadable human registry posts everything.
 - **`rig queue inbox-drop` / `inbox-pending` / `inbox-absorb` / `inbox-deny`** — put something in
   front of a seat that it can *refuse*. Mail, not assignment.
 - **`rig queue outbox-record` / `outbox-list`** — what you dispatched, in a record that survives
@@ -335,19 +357,25 @@ not have to tear one down to change it, and you rarely have to start from nothin
   by name, a bundle someone handed you, a GitHub folder link (pinned to one commit), or a stopped
   rig. `rig up` with a pod-aware spec on a stopped team's name replaces that team (the earlier one
   is archived), so check `rig ps --nodes` first. Launch-created `AGENTS.md` or `CLAUDE` files now show in `git status`.
+  `rig up <rig> --existing` puts back the OpenRig guidance blocks `rig down` removed before a
+  resumed seat starts. A seat still missing one makes the rig `partially_restored` (its node lists
+  `guidanceGaps`) and `rig up` exits 1.
 - **`rig down`** — stop a rig's seats and take it out of the running set. It ends the agents'
   sessions and any work in progress; don't run it on a live team unless the person asked. In
   human mode it first prints one line with each agent's last known activity, or “unknown”: a
   best-effort snapshot, not a record of what was interrupted. With `--host`, a remote teardown
   that reports errors exits 2.
-- **`rig launch <rig> [seat]`** — one seat is down; start just that one, without disturbing the
-  rest. Add `--plan` to preview it first, locally or with `--host`; a plan is never sent to a
-  daemon older than 0.5.9, which would ignore it and launch.
+- **`rig launch <rigId> [seat]`** — one seat is down; start just that one, without disturbing the
+  rest. It takes the rig ID from `rig ps --json`; a rig name gives `rig_not_found`. Add `--plan` to preview it first, locally or with `--host`; a plan is never sent to a
+  daemon older than 0.5.9, which would ignore it and launch. A seat whose agent exited to a shell in
+  its kept pane reads `attention_required` (exit 1), not already running: resume it, or
+  `rig seat launch <session> --fresh --stop`.
 - **`rig seat launch <seat> --fresh --reason <why>`** — deliberately create a blank occupant for
   exactly one existing seat. It uses no resume, fork, rebuild, snapshot, or restore packet;
   siblings and durable work stay put, and unmanaged ambiguity refuses.
 - **`rig add`** / **`rig expand`** — graft one more member, or a whole new pod, onto a rig that is
-  already running. `rig grow --new-pod` and `rig expand` are one ingress; choose by input shape.
+  already running. `rig add` takes the rig's name or ID; a name two active rigs share is refused
+  with `rig_ambiguous` and the candidates. `rig grow --new-pod` and `rig expand` are one ingress; choose by input shape.
 - **`rig remove`** / **`rig shrink`** — take a seat, or an entire pod, out of a running topology.
   If it holds active work, pass `--fallback <live-seat>` to reroute before mutation; without a
   valid fallback the command refuses rather than strand the rows.
@@ -519,7 +547,8 @@ scheme, and nothing downstream can see it.
 - **`rig scope slice progress` / `mission progress`** — record that a step moved, in a form the
   progress view can parse.
 - **`rig scope slice approve`** — freeze a decision — *this is the plan* or *this is delivered* —
-  so the freeze is recorded rather than asserted in chat.
+  so the freeze is recorded rather than asserted in chat. With `--workspace`, approve stamps the
+  tree you named, and refuses one with no `missions/` folder.
 - **`rig scope slice close` / `ship` / `move`** — retire it with the reason attached, move it into
   the release it belongs to preserving git history, or re-file it under a different mission.
 - **`rig scope slice stage` / `verified`** — how mature is this, and *when was it last checked and
@@ -679,7 +708,8 @@ reaching them is ordinary work rather than an escalation.
   request, then boundedly inspect its transport receipt. Posted means posted, not read;
   pending, failed, or indeterminate delivery leaves the row intact. Inspect the same row's
   transitions before retrying. `rig send` remains agent-terminal delivery only.
-  `--human-questions-file` adds clickable decision questions.
+  `--human-questions-file` adds clickable decision questions. A typed Slack reply to one is kept
+  in `humanAnswers`, placed under the first unanswered question; closing isn't approval.
 - **When project policy calls for human judgment or an update, load `messaging-the-human`.**
   Use `rig context get skills/core/messaging-the-human/SKILL.md` for a complete decision brief,
   related supplemental detail and explicit quiet-update intent. An FYI creates no approval
@@ -764,7 +794,9 @@ your circumstances is configuration, and the ones that are not, another agent ca
 - **`rig provider accounts` / `bindings` / `signals` / `switch`** — which seats are bound to which
   accounts, what the usage signals say, and whether a seat can be moved without stranding the
   conversation it is in the middle of. **`provider signals` reports anomalies rather than a
-  listing** — unbound seats, accounts shared across several seats.
+  listing** — unbound seats, accounts shared across several seats. A Codex seat showing its
+  usage-limit banner reads activity `unknown` with reason `usage_limit`, and `provider signals` can
+  show a provider-event signal for that seat's account that allows a switch decision.
 - **Codex configuration fragments** — a `codex_config_fragment` must open with a table header and
   never overrides a user-declared table; see `docs/reference/agent-spec.md`.
 - **`rig env`** — the real services behind a rig: are they up, what are they saying, how do you
@@ -772,7 +804,8 @@ your circumstances is configuration, and the ones that are not, another agent ca
 - **`rig setup`** — what OpenRig would change about this machine, shown before it touches anything.
   It installs herdr by default on macOS and Linux (`--no-herdr` declines; if the install fails,
   views fall back to plain tmux) and on a Mac offers Ghostty once (`--ghostty` / `--no-ghostty`).
-  It no longer installs cmux; an existing cmux still works.
+  It no longer installs cmux; an existing cmux still works. `--providers claude`, `codex` or
+  `both` sets which harnesses it installs and checks; one not chosen reads `skipped`, never failed.
 - **`rig usage series`** — what a seat's token curve has looked like over time: climbing steadily,
   reset, or stopped reporting entirely. The last one is a signal, not a gap.
 - **`rig tui`** — the interactive view over rigs, pods, seats and specs. `rig` and `rig tui` open
@@ -858,6 +891,8 @@ database. It is one more set of primitives on a machine full of them.
 - **"Did that actually land?"** — `rig queue show <qitemId>` gives a bounded preview,
   original byte size and the exact expansion command. Read the complete original record with
   `rig queue show <qitemId> --full --json`; a preview or a compact list is not the whole body.
+  Compact `rig queue list` rows carry `summary`; the fields they leave out are absent, not empty,
+  and `fieldsElided` names them.
   Delivery status is separate from content: inspect its receipt before claiming it was consumed.
 - **"What am I waiting on?"** — the queue row's `waiting` view derives its owner, exact blocker
   and blocker owner, last meaningful change, activity confidence and next backstop from live

package/daemon/context-packs/reference/getting-started.md

@@ -137,7 +137,9 @@ The other provider's CLI/login is optional. Herdr is installed by default unless
 you decline it; cmux remains optional. Do not copy credentials
 or start repeated sign-in attempts. Recheck the selected login after the user
 completes it. `rig setup --dry-run` previews the broader setup; applying
-`rig setup` checks **both** harnesses and installs a missing one with npm; on
+`rig setup` checks **both** harnesses and installs a missing one with npm, unless
+you pass the person's choice: `rig setup --providers claude` (or `codex`) leaves
+the other out, so it reads not selected instead of failed. On
 macOS it uses an existing Homebrew (it does not install Homebrew) to install a
 missing tmux (elsewhere tmux is checked, not installed). Herdr installs on
 macOS and Linux; pass `--no-herdr` to decline it. Setup also
@@ -198,7 +200,7 @@ leaves existing cmux settings alone and does not open a view during setup.
 
 On a Mac, the installing agent also asks once, "Install Ghostty for the OpenRig
 view?" On Yes it reruns setup with `--ghostty`, preserving earlier choices such
-as `--no-herdr`. This installs the
+as `--no-herdr` and `--providers`. This installs the
 [documented Homebrew cask](https://ghostty.org/docs/install/binary) and checks for
 the app. On No it uses `--no-ghostty`; Terminal.app remains available. Plain setup
 reports this offer without installing Ghostty or waiting for input. The person
@@ -331,17 +333,19 @@ For the first desktop handoff, use `--window`. Only if the window cannot open,
 For an explicitly requested manual attachment, inspect the current bindings:
 
 ```sh
-rig ps --nodes --rig kernel --json
+rig ps --nodes --rig kernel --json --fields logicalId,canonicalSessionName,tmuxAttachCommand
 ```
 
-Find `logicalId: operator.agent` and use its `canonicalSessionName` in a new
+Find `logicalId: operator.agent` and run its `tmuxAttachCommand`, after `env -u TMUX`, in a new
 terminal on the same host and account:
 
 ```sh
-env -u TMUX tmux attach-session -t '=<canonicalSessionName>'
+env -u TMUX <tmuxAttachCommand>
 ```
 
-The installing agent fills in the actual session name. This optional manual route
+When the daemon was started inside tmux on a non-default socket, its sessions live on that
+server, and `tmuxAttachCommand` names it (`tmux -L <name> …` or `tmux -S <path> …`). The installing
+agent fills in the actual command. This optional manual route
 is separate from the first-install desktop action above.
 
 ### Plain terminal: a new viewing session

package/daemon/context-packs/reference/manifest.yaml

@@ -1,7 +1,7 @@
 # Reference guides the help pack links to, loaded one file or section at a time by address
 # (rig context get reference/<file>#<section>). Each file is a symlink to docs/reference/.
 name: reference
-version: "0.6.8"
+version: "0.6.10"
 taxonomy: world
 purpose: "Version-matched reference guides the help guide links to. Load a single file or section by address; don't load the whole pack."
 files:

package/daemon/context-packs/reference/whats-new.md

@@ -1,96 +1,167 @@
-# What changed in OpenRig 0.6.8
+# What changed in OpenRig 0.6.10
 
-This note is for an agent on an install that was just upgraded to 0.6.8. It lists only what behaves differently from
-0.6.7 and what to do about it. For everything OpenRig can do, read the capability map:
+This note is for an agent on an install that was just upgraded to 0.6.10. It lists only what behaves differently from
+0.6.9 and what to do about it. For everything OpenRig can do, read the capability map:
 `rig context get onboarding-width/public-what-you-can-do.md`. Each release replaces this file, so
 `rig context get reference/whats-new.md` describes the installed version once the upgraded daemon is running. Without
 a running daemon, read `$OPENRIG_HOME/reference/whats-new.md`. The daemon refreshes that copy when it starts, so right
 after an upgrade it can still hold the previous version's note.
 
-## Skills from the managed catalog
-
-- **A skill with uncommitted changes in the catalog now blocks only itself.** Before, one edited skill made the whole
-  catalog unavailable to work-install, launch and restore preflight. Now that skill is skipped and named, and the
-  remaining clean skills stay available for projection.
-- **Read the warning, don't retry.** `catalog_skill_skipped` names a skill nobody selected; `selected_skill_skipped`
-  names the selector and the folder. The fix is to commit or restore that folder's content in the catalog, then run the
-  projection again.
-- **A selected skipped skill makes the inspection commands exit 1.** `rig context work-install --runtime <runtime>`
-  and `rig skill loadout --runtime <runtime>` inspect by default. Use `--apply-skills` with work-install or `--apply`
-  with skill loadout to project the remaining clean skills. Read the warnings and projection result; exit 1 alone does
-  not say whether files were changed. With `--json`, skipped skills are in `skillLoadout.skipped` or
-  `loadout.skipped`, respectively.
-- **A seat keeps the copy it already has** of a skipped skill, unchanged. After the catalog change is committed or
-  restored, the next applied projection can refresh it. No seat receives the skipped skill's uncommitted files, and
-  launch only warns about the skip.
-- **An uncommitted `catalog.yaml` still makes the whole catalog unavailable,** because it changes every selection.
-
-## Launch plans
-
-- **`rig launch <rig> <seat> --plan` previews one seat's launch** without launching it, locally or with `--host`. Use
-  it before starting a single seat, as `--seats … --plan` already allowed for several.
-- **A plan is never sent to a daemon older than 0.5.9,** which would ignore the flag and launch. If `rig launch --plan`
-  refuses for that reason, restart or upgrade that daemon. If it exits non-zero saying the daemon may have acted, check
-  `rig ps --nodes -A` before retrying.
+## After the upgrade
+
+- **Restart the daemon** (`rig daemon stop`, then `rig daemon start`). Two migrations run on the first start: `099`
+  adds one partial index to the queue table, and `101` adds four empty columns to `sessions`. Neither changes existing
+  data. There is no migration `100`. The bundled openrig-core plugin goes from 0.1.8 to 0.1.9.
+
+## Output that changed shape
+
+- **`rig capture --lines N` is the last N lines,** after blank rows at the bottom are dropped. When earlier lines are
+  cut, stderr says `[rig capture: <session>: N earlier lines not shown; last M shown]`. In `--json`, `lines` is then
+  the count returned, and `requestedLines` and `omittedLines` are new (per seat under `--rig` or `--pod`). For the old
+  output, N history lines plus the whole pane, add `--history-plus-pane`; it keeps the old JSON too, without
+  `requestedLines` or `omittedLines`. Without `--lines`, or with a non-numeric or zero `--lines`, nothing changed. A
+  short capture doesn't prove a seat is idle.
+- **Compact `rig queue list` rows carry `summary`,** and so do `overdue` and `undelivered`. The fields they leave out
+  (`body`, `evidenceRef`, `humanDetail`, `waiting`, `chainOfRecord`, `replyTo`, `humanQuestions`, `humanAnswers`) are
+  now absent, not `null` or `""`, and `fieldsElided` names them. A filter that tested those fields for null must test
+  for presence. Read a full row with `rig queue show <id> --full --json`.
+- **`lastNudgeResult` reads `claimed`** on a claimed row whose wake was recorded as `delivered-ack-pending` or
+  `indeterminate:…`. The recorded value is unchanged and shows in the new `lastNudgeWireResult`; unclaiming brings it
+  back. `claimed` is never promoted to `verified`.
+- **`rig chatroom history` returns the newest messages** when you give neither `--after` nor `--since`, still listed
+  oldest first. Before, a room longer than the limit returned its oldest messages. `--after` and `--since` still page
+  forward from that point, and `rig chatroom wait` is unchanged.
+
+## Seats and restore
+
+- **`rig launch <rigId> <seat>` no longer calls an exited agent running.** When a seat's kept pane is at an idle shell,
+  the launch returns `attention_required` (HTTP 409, exit 1) with `Session alive, agent not running for '<seat>'` and
+  the ways back: resume it with `--snapshot-id <id>` when a snapshot can, `rig seat launch <session> --fresh --stop`, or
+  restart the agent in the pane. The pane and its history are kept. This covers Claude Code, Codex, Pi and OMP seats.
+- **`rig up <rig> --existing` puts back the guidance `rig down` removed.** Before a resumed seat starts, the missing
+  OpenRig managed blocks go back into the rig's Claude file (`CLAUDE.md`, or `CLAUDE.local.md`) or `AGENTS.md` for
+  Codex. Existing blocks and the person's own text are untouched, and nothing is sent to the conversation. The
+  warnings say `Restore guidance: <seat>: put back missing blocks …`. A seat still missing a block keeps running, its
+  node lists `guidanceGaps`, the rig reads `partially_restored` instead of `fully_restored`, and `rig up` exits 1.
+- **A resumed Claude seat whose session ID changed can prove.** When Claude continues `--resume T1` under a new ID T2,
+  and the first SessionStart hook from the process OpenRig launched reports `source: "resume"`, OpenRig records T2. The
+  seat restores as `resumed`, `rig seat clear-attention` can clear it, and sends stop warning that the launch identity
+  differs. Resume commands now start with `OPENRIG_RESUME_LAUNCH='<T1>'`. It needs openrig-core 0.1.9; `/clear`, an
+  in-process `/resume`, or a hand-started process still keep the refusal.
+- **A restore no longer proves a seat from a launcher's token** when the launcher isn't Claude and the Claude it
+  started names a different conversation. That seat reads `mismatch` and the restore returns `attention_required`.
+- **A seat whose tmux session is confirmed gone reads `detached`,** with activity `unknown` and reason
+  `session_missing`. `rig ps --nodes` shows `tmux session missing; restore or relaunch the seat`, `rig seat status`
+  prints a `Reason:` line, and `--full --json` adds `storedSessionStatus`. The stored status isn't rewritten.
+- **A Codex seat at its usage limit reads `unknown` with reason `usage_limit`,** not idle, when its screen ends with
+  the `■ You've hit your usage limit` banner. For a seat bound to a known Codex account, `rig provider signals` can show
+  a provider-event signal for that account that allows a switch decision.
+- **`rig add <rig> …` takes the rig's name as well as its ID.** A name two active rigs share is refused with
+  `rig_ambiguous` and the candidates. `rig launch` still takes an ID only.
+- **`rig start` says why it skipped an existing kernel:** `Kernel auto-boot skipped (kernel rig already managed).` and,
+  if its seats aren't running, `rig up kernel --existing`.
+
+## Sends and wakes
+
+- **Codex seats behind a launcher receive sends.** When a seat's `codex` is a launcher that starts Codex as a child,
+  `rig send` and queue wakes used to refuse with "reports sh as the foreground command". The deepest `codex` on one
+  process chain now counts as the seat. Codex processes on separate branches, or naming different conversations, are
+  still refused.
+- **Claude's faint suggested prompt isn't a person's draft.** A send to an idle Claude seat whose empty input box shows
+  only that suggestion is no longer refused as `prompt_draft`. OpenRig takes one styled capture to tell; real typed or
+  pasted text is still refused, and a suggestion that wraps onto a second row still reads as a draft.
+- **`rig queue create --verify` reports a seat's wake and claim.** For an agent destination it returns as soon as a
+  wake result or a claim is recorded, bounded at 30 seconds, with `receiptSource: "terminal"`, `outcome`, `wakeResult`
+  and `claim {observed, claimedAt, pickup}`. An unconfirmed receipt is not a failed handoff. See the known gap below
+  for a row the seat already claimed.
+- **Keep agent-to-agent escalations off the person's Slack (off by default).** `rig config set queue.wake_human_rung
+  explicit-only` (or `OPENRIG_QUEUE_WAKE_HUMAN_RUNG`) stops the wake ladder's last step at `rig view show escalations`
+  unless the row is addressed to a person: an `@external` address or a registered human. A seat stuck at a prompt only
+  a person can clear still reaches one, and an unreadable human registry posts everything. The default, `always`,
+  changes nothing.
 
 ## Slack
 
-- **Answer a person's thread reply in that thread.** When someone replies inside a thread OpenRig opened, answer with
-  `rig queue create --human-intent update --reply-to <the inbound reply's row>`, and the answer posts in that thread.
-  A top-level message is still answered top-level.
-- **A short rate limit is waited out.** When Slack asks for a pause of 10 seconds or less, OpenRig waits and retries the
-  post once. A longer pause is still left to the usual retry of retained messages.
-
-## Managed compaction
-
-- **A quiet seat is restored after `/compact`.** The turn boundary, the restore request and the read-depth
-  audit now reach a Claude seat that takes no turn after compacting. Before, they waited for the seat's next turn,
-  so a seat with nothing to do could sit unrestored. Each stage still waits until the seat's screen shows it idle.
-
-## Workflows
-
-- **Validate before you run.** `rig workflow validate` reports `step_cannot_finish` when no allowed exit can finish a
-  step or route onward, and such a workflow cannot be instantiated. Allow `done` or an exit with a route onward. In a
-  dependency graph, `handoff` can also finish a sink without a next step. A spec that validated on 0.6.7 may need a
-  correction.
-
-## The TUI
-
-- **Type whole commands on an empty command line.** The footer toggle is now `F`, and in a selected Scopes view the
-  mini-requirements and narrative keys are `M` and `N`, so `find`, `feed`, `mission`, `narrative` and `needs` reach the
-  command line intact.
-- **`j` and `k` move the selection down and up** when the command line is empty. With text on the line they're ordinary
-  letters.
-
-## Smaller changes
-
-- **A Claude seat launched with `--remote-control`** confirms its identity instead of staying "identity not confirmed".
-- **`rig down` still saves its recovery snapshot** when finding one seat's resume details fails.
-- **A wake for a handed-off task shows its summary** on one line, so read it to see what the task is for.
-- **`rig scope audit` accepts slice folders numbered 100 and above.** `rig proof add --file` keeps a leading UTF-8
-  byte-order mark.
-- **Building from source no longer needs POSIX shell tools** for the CLI and TUI output. It hasn't been run on Windows
-  yet; WSL2 is still the way to run OpenRig there.
-- **A topology naming reference** explains how to name a team's pods and seats: `rig context get
-  reference/topology-naming.md`.
+- **A decision click that isn't recorded gets one reply in the thread** saying why: the clicker isn't registered, the
+  decision was sent to someone else or is no longer waiting, the button no longer matches, or OpenRig can't find the
+  decision. Where it helps, the reply asks for an answer in words. A recorded click still gets its usual reply, and a
+  redelivered click gets no second one. It's best effort and needs the bot token. A successful press doesn't exercise
+  these replies.
+
+## Terminals and attach
+
+- **Attach commands name the daemon's tmux server.** When the daemon was started inside tmux on a non-default socket,
+  every attach command OpenRig prints carries `-L <name>` or `-S <path>`, including `tmuxAttachCommand` in `rig ps
+  --json`. From inside tmux, run it as `env -u TMUX <tmuxAttachCommand>`. On the default server nothing changed.
+- **When a caller of the daemon's terminal API names no provider, the daemon uses cmux if Herdr isn't available** and
+  cmux is, and says so. A named `--provider` is used as named. `rig terminal open` without `--provider`, and the TUI's
+  "Open terminals", open Herdr, or plain tmux when Herdr is missing, never cmux. The TUI's preview now asks for the
+  same provider as the window it opens, so it isn't refused when cmux is running.
+- **A tmux started inside a Herdr pane is recognised** by Herdr's markers (`HERDR_ENV`, `HERDR_PANE_ID`,
+  `HERDR_SOCKET_PATH`), so `rig terminal open --window` opens in that Herdr.
+
+## Setup
+
+- **`rig setup --providers claude|codex|both`** (or a comma list) sets which harnesses it installs and checks. One not
+  chosen reads `skipped` with `Not selected: …`, never failed. Without the flag, setup is unchanged. `rig doctor` still
+  checks both.
+- **A first `rig daemon start` after a timed-out probe goes ahead when the port is free,** as on WSL2. A port that's
+  really held is refused with `Address already in use (EADDRINUSE)` and the `--port` advice.
+
+## Teams
+
+- **Starter and factory teams run their own first steps and checks without stopping for approval** where they can:
+  plain `rig` commands, the file tool instead of a heredoc, the project's test command first. Their leads read the goal
+  from `rig queue show <id> --full`.
+- **The operator says what a team launch changes in the person's folder before asking** (`CLAUDE.md`, skills,
+  `.mcp.json`, `.openrig/`, and an accept-edits `.claude/settings.local.json`), and offers a separate copy such as a git
+  worktree. When a seat shows `needs_input`, the operator or lead tells the person which seat, what it asks, and its
+  attach command.
+
+## Smaller fixes
+
+- `_` and `%` in a `rig view show <lens> --rig <name>` rig name are no longer wildcards, in all seven lenses that
+  filter by rig.
+- `rig ask` matches chat keywords such as `config.json` or `C++` literally.
+- `rig heartbeat` reads CRLF queue files and reads a zone-less proof timestamp as UTC when picking the latest.
+- `rig usage top` reads every sample in its window; `rig usage top|series --json` prints the daemon's error as JSON.
+- A `?limit=` that isn't a number returns 400, not 500.
+- `rig workflow instantiate` and `project` print the instance and packet the daemon returned.
+- `rig transcript --tail` keeps a line ending in `%` and drops a repeated prompt.
+- `--json` after `--` no longer turns an error into JSON; `rig env` prints the daemon's error.
+- A file read over 1 MiB ends at a whole UTF-8 character, and `truncatedAtBytes` says where.
+- The TUI counts CR+LF as one Enter, keeps an emoji whole at a wrap, pages Local reading directories by 10, and skips
+  fenced examples when opening a file at a heading.
+- Scope progress rows go only under a matching `##` heading, frontmatter updates stay inside the exact `---`
+  delimiters, a capability delta expires only with a readable successor file, and fenced examples no longer count as
+  slice sections or progress tasks.
+- `rig package install` looks for a guidance block's closing marker only after its opening one.
+- A Codex seat keeps its last context reading across quota-only usage records, and a fresh Codex launch keeps git
+  metadata paths that end in whitespace.
 
 ## What to stop doing
 
-- **Stop treating a non-zero work-install exit as proof that nothing changed.** Read the skipped-skill warnings and
-  projection result. Inspection alone changes no skill files; an applied projection can update clean skills while
-  reporting a skipped one.
-- **Stop scripting around the TUI's single-letter keys.** Type the command whole.
-- **Stop assuming a workflow that validated on 0.6.7 can finish.** Validate it again on 0.6.8.
+- **Stop reading "already running" from `rig launch` as healthy** for a seat whose agent may have exited; 0.6.10 says
+  `attention_required`.
+- **Stop reading `rig capture --lines N` as N history lines plus the pane.** Add `--history-plus-pane` for that.
+- **Stop testing compact queue rows for null fields.** They're absent; check `fieldsElided`.
+- **Stop attaching to the default tmux server** when the printed command names `-L` or `-S`.
 
-## Known gaps in 0.6.8
+## Known gaps in 0.6.10
 
-- **Not yet checked on a real machine:** the full first install from nothing, on Mac, Linux and Windows.
+- **`rig queue create --verify` can report `outcome: "indeterminate"` for a row the seat already claimed,** with
+  "Terminal receipt unconfirmed (claimed)." Read `claim` for pickup: neither the claim nor this outcome shows the
+  message was displayed or read. It isn't a failed handoff, so don't re-run the create.
+- **The latest first-install check used 0.6.9 on Linux only.** macOS was last checked with 0.6.8, and native Windows
+  hasn't been checked.
 - **Only one selected lifecycle-help command has been checked in a live Claude session;** source and parser coverage
   is broader. If a help command still asks, report it.
 - **Codex team seats aren't asked before lifecycle commands yet.**
 - **The send gate trusts the most recently recorded hook.** If hooks are recorded out of order, it can hold a send for
   a question that's already answered, or miss one that's waiting. `rig capture` shows the real screen.
 - **A Codex seat whose permission request was approved automatically can still read "needs input".**
-- **A launched team still writes its skills into its working folder.**
+- **A launched team still writes into its working folder;** the operator now says what changes before you agree.
 - **After a restart, `rig status` shows `Kernel: skipped` whatever the kernel seats' state.** Read them with
   `rig ps --nodes --rig kernel --full`.
+- **`rig tui --shared` still attaches on the default tmux server,** so it can't find the dashboard when the daemon runs
+  on a non-default tmux socket. Use `rig tui` there instead.

package/daemon/context-packs/skills/agent-operated-software/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "agent-operated-software"
-version: "0.6.8"
+version: "0.6.10"
 taxonomy: "skills"
 purpose: "Use when designing, building, operating, or diagnosing an ongoing application whose live backend or control loop includes OpenRig agents, including applications with a Markdown, YAML, or JSON agent control plane or a thin surface over specialist agent roles."
 files:

package/daemon/context-packs/skills/agent-operated-workflows/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "agent-operated-workflows"
-version: "0.6.8"
+version: "0.6.10"
 taxonomy: "skills"
 purpose: "Use when a bounded real-world procedure has a deterministic happy path but brownfield, variable, or partially knowable state; when an operation must resume from verified evidence; or when deciding whether agent judgment or ordinary code should own a procedure's control loop."
 files:

package/daemon/context-packs/skills/applying-a-permission-policy/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "applying-a-permission-policy"
-version: "0.6.8"
+version: "0.6.10"
 taxonomy: "skills"
 purpose: "Use before launching a team during agent-guided setup, or when a user asks to configure OpenRig command permissions, reduce repeated native approval prompts, or apply a selected rig/seat permission policy."
 files:

package/daemon/context-packs/skills/claude-compaction-restore/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "claude-compaction-restore"
-version: "0.6.8"
+version: "0.6.10"
 taxonomy: "skills"
 purpose: "Use when a Claude Code session is about to compact, has just compacted, reached its context limit, resumed after /compact, or must rebuild its working picture of a long-running seat from its own restore map, its JSONL transcript and the files it touched."
 files:

package/daemon/context-packs/skills/core/agent-starters/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "agent-starters"
-version: "0.6.8"
+version: "0.6.10"
 taxonomy: "skills"
 purpose: "Use when creating, refreshing, packaging, inspecting, promoting, or deprecating a named per-seat starting point — Agent Starter manifest authoring, the 6-state lifecycle (captured → named → inspectable → used → promoted → deprecated), provenance honesty, and refusal rules. NOT a VM image; a managed starting point composed from agent role + startup context + optional native session source + provenance."
 files:

package/daemon/context-packs/skills/core/agent-startup-and-context-ingestion/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "agent-startup-and-context-ingestion"
-version: "0.6.8"
+version: "0.6.10"
 taxonomy: "skills"
 purpose: "Use when designing or auditing how an agent becomes useful after launch — AGENTS.md overlays, role files, skills, rig specs, workflow specs, startup checklists, refocus messages, \"rig context\" surface. Covers the 4 failure modes that make startup context fail (old rig spec misses current operating mode; current agents never told about new guidance; startup file as dumping ground; orchestrator transmits implementation without preserving product intent)."
 files:

package/daemon/context-packs/skills/core/cross-host-rig-commands/SKILL.md

@@ -85,6 +85,7 @@ A local success message alone does not establish remote persistence or pickup.
 | ssh-unreachable | SSH connection, target and transport diagnostics |
 | permission-gate | The configured SSH or HTTP credentials and target policy |
 | remote-daemon-unreachable | Target listener and actual running daemon identity |
+| remote-outcome-unknown | The request may have arrived (timeout, dropped connection, unreadable reply): check its effect, for a send the target pane, before any retry |
 | remote-command-not-found | Remote CLI installation and executable lookup |
 | remote-command-failed | The remote operation's own status and error |
 

package/daemon/context-packs/skills/core/cross-host-rig-commands/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "cross-host-rig-commands"
-version: "0.6.8"
+version: "0.6.10"
 taxonomy: "skills"
 purpose: "Use when addressing a registered remote OpenRig host, choosing its transport, or interpreting a cross-host result."
 files:

package/daemon/context-packs/skills/core/human-in-the-loop/manifest.yaml

@@ -1,7 +1,7 @@
 # GENERATED by scripts/generate-context-packs.mjs — DO NOT EDIT.
 # Package-time projection of a canonical skill; regenerated every build.
 name: "human-in-the-loop"
-version: "0.6.8"
+version: "0.6.10"
 taxonomy: "skills"
 purpose: "Use when classifying a slice closeout (auto-continue / human gate / park), routing a real decision to a human, or designing a human queue/dashboard surface. Treats humans as durable network participants with attention surfaces, queues, and decision records — escalation lands as a durable attention item, not a chat message. Approval is NOT required for every clean closeout; the default RSI conveyor continues unless an explicit human gate is reached."
 files: