feat(ri-050): bind next publication to exact-commit terminal verification (#1275)

Reviewed by scooby via git comms (terminal ACK 32d986). Merge directed by Jason 2026-08-16. Conflicts from #1229 and #1252 resolved on the branch by a pi seat; pre-merge gate verified: tools/install.sh=5d28f773, framework/install.sh=1578c33b, test:framework-shell=48 links with both #1252 and #1245 suites present.

.woodpecker/ci.yml

@@ -30,6 +30,19 @@ steps:
       # the baked pnpm store.
       - pnpm install --frozen-lockfile --prefer-offline
 
+  # ---------------------------------------------------------------------------
+  # The steps below (sanitization, upgrade-guard, typecheck, lint, format,
+  # test) are the COMPLETE mandatory verification set. SDLC-D-034 mirrors them
+  # one-for-one in the canonical terminal verification command — root
+  # `pnpm verify:release` (scripts/verify-release.mjs) — which the publish
+  # pipeline (.woodpecker/publish.yml `verify` step) runs before ANY publish
+  # effect. These lines stay direct (not routed through the runner) because the
+  # #1017 test-enumeration guard audits framework tool paths through THIS
+  # surface; scripts/verify-release.test.mjs enforces that the runner's stage
+  # table keeps matching these commands exactly, so the two cannot drift.
+  # ---------------------------------------------------------------------------
+
+  # Canonical verify:release stage `sanitization`.
   # Blocking gate: public framework package must contain no operator-specific
   # personal data or private $HOME defaults. Runs early (no node_modules needed).
   sanitization:
@@ -47,6 +60,7 @@ steps:
       # with everything it guards; this direct line keeps one instrument running.
       - bash packages/mosaic/framework/tools/quality/scripts/check-test-enumeration.sh
 
+  # Canonical verify:release stage `upgrade-guard`.
   # Blocking gate (#791): a framework upgrade must never write or delete an
   # operator-owned path. The HARD GATE proves an unanticipated operator sentinel
   # survives a keep-mode reseed byte-identical (with rsync present AND absent —
@@ -68,6 +82,8 @@ steps:
       - bash packages/mosaic/framework/tools/quality/scripts/test-upgrade-durable-snapshot.sh
       - bash packages/mosaic/framework/tools/quality/scripts/test-install-migration.sh
 
+  # Canonical verify:release stage `typecheck` — the same `pnpm typecheck`
+  # invocation (which runs the checkout preflight first, then turbo).
   typecheck:
     image: *node_image
     commands:
@@ -78,7 +94,8 @@ steps:
       - sanitization
       - upgrade-guard
 
-  # lint, format, and test are independent — run in parallel after typecheck
+  # lint, format, and test are independent — run in parallel after typecheck.
+  # Each runs exactly its canonical verify:release stage command.
   lint:
     image: *node_image
     commands:
@@ -95,6 +112,12 @@ steps:
     depends_on:
       - typecheck
 
+  # Canonical verify:release stage `test` — the `pnpm test` line below is the
+  # shared command; everything else in this step is PIPELINE-LEVEL
+  # prerequisite the canonical command expects its caller to provide (SDLC-D-034):
+  # the ci-postgres service + pg_isready wait + db:migrate (postgres path),
+  # `apk add openssl`, and the pinned pi install. None of those can move into
+  # the runner (it must also work locally on the PGlite path with no database).
   test:
     image: *node_image
     environment:

.woodpecker/publish.yml

@@ -1,5 +1,19 @@
 # Build, publish npm packages, and push Docker images
 # Runs on main for stable publishes and on next for integration-line prereleases/images
+#
+# SDLC-D-034 publish gate: every publish effect (publish-npm, publish-next-npm,
+# and every image build/push step) depends DIRECTLY on the `verify` step below.
+# `verify` (a) asserts the provider's commit identity matches the actual
+# checkout (CI_COMMIT_SHA == git rev-parse HEAD, fail closed on mismatch or
+# emptiness) and (b) runs the canonical terminal verification command
+# (`pnpm verify:release`), which mirrors the PR CI pipeline's complete
+# mandatory set (sanitization, upgrade-guard, preflight+typecheck, lint,
+# format:check, test, build) — see scripts/verify-release.mjs. A missing,
+# failed, skipped, cancelled, or inconclusive verification therefore skips the
+# dependent publish effects (fail closed). Path-filtered short-circuits may
+# skip publish EFFECTS (e.g. docs-only merges) but never bypass `verify` for a
+# publish that does run: `verify` itself carries no path filter.
+# scripts/verify-release.test.mjs enforces this DAG invariant at checkout time.
 
 variables:
   # Pre-baked CI base (see .woodpecker/ci-image.yml): node:24-alpine +
@@ -48,6 +62,45 @@ steps:
       # Resolve from the baked pnpm store instead of a cold network fetch.
       - pnpm install --frozen-lockfile --prefer-offline
 
+  # SDLC-D-034 exact-commit publish gate. No `when`/path filter on purpose: it
+  # runs for every event this pipeline serves so no publish effect can ever
+  # start without it. Fails closed on commit-identity mismatch (or either SHA
+  # being empty) and on any incomplete verification.
+  verify:
+    image: *node_image
+    commands:
+      - *enable_pnpm
+      # (a) Commit identity: the provider's claimed SHA must equal the actual
+      # checkout HEAD — verification of anything else must never authorize a
+      # publish of this commit.
+      - |
+        if [ -z "$CI_COMMIT_SHA" ]; then
+          echo "[verify] FATAL: CI_COMMIT_SHA is empty — cannot certify commit identity" >&2
+          exit 1
+        fi
+        CHECKOUT_SHA="$(git rev-parse HEAD 2>/dev/null || true)"
+        if [ -z "$CHECKOUT_SHA" ]; then
+          echo "[verify] FATAL: git rev-parse HEAD returned nothing — cannot certify commit identity" >&2
+          exit 1
+        fi
+        if [ "$CI_COMMIT_SHA" != "$CHECKOUT_SHA" ]; then
+          echo "[verify] FATAL: provider commit ($CI_COMMIT_SHA) != checkout HEAD ($CHECKOUT_SHA)" >&2
+          exit 1
+        fi
+        echo "[verify] commit identity confirmed: $CHECKOUT_SHA"
+      # (b) Canonical terminal verification. Caller-provided prerequisites the
+      # runner expects (see .woodpecker/ci.yml comments): bash/rsync for the
+      # guard stages, openssl + the pinned pi binary for the test stage. git is
+      # baked into ci-base but re-asserted here so the identity check above can
+      # never silently depend on a stale baked image. DATABASE_URL is
+      # deliberately NOT set: the canonical command must hold on the PGlite
+      # path too and never sets or requires a database itself.
+      - apk add --no-cache bash rsync openssl git
+      - npm install -g @earendil-works/[email protected]
+      - pnpm verify:release
+    depends_on:
+      - install
+
   build:
     image: *node_image
     commands:
@@ -55,6 +108,7 @@ steps:
       - pnpm build
     depends_on:
       - install
+      - verify
 
   publish-npm:
     image: *node_image
@@ -114,6 +168,7 @@ steps:
         exit 1
     depends_on:
       - build
+      - verify
 
   publish-next-npm:
     image: *node_image
@@ -192,6 +247,7 @@ steps:
         echo "[publish-next] @mosaicstack/mosaic@next resolves to $RESOLVED_VERSION"
     depends_on:
       - build
+      - verify
 
   # TODO: Uncomment when ready to publish to npmjs.org
   # publish-npmjs:
@@ -205,6 +261,7 @@ steps:
   #     - bash scripts/publish-npmjs.sh
   #   depends_on:
   #     - build
+  #     - verify
   #   when:
   #     - event: [tag]
 
@@ -242,6 +299,7 @@ steps:
         /kaniko/executor --context . --dockerfile docker/gateway.Dockerfile $DESTINATIONS
     depends_on:
       - build
+      - verify
 
   build-appservice:
     image: gcr.io/kaniko-project/executor:debug
@@ -268,6 +326,7 @@ steps:
         /kaniko/executor --context . --dockerfile docker/appservice.Dockerfile $DESTINATIONS
     depends_on:
       - build
+      - verify
 
   build-web:
     image: gcr.io/kaniko-project/executor:debug
@@ -294,3 +353,4 @@ steps:
         /kaniko/executor --context . --dockerfile docker/web.Dockerfile $DESTINATIONS
     depends_on:
       - build
+      - verify

package.json

@@ -9,6 +9,7 @@
     "preflight": "node scripts/preflight.mjs",
     "clean:generated": "node scripts/clean-generated.mjs",
     "typecheck": "pnpm preflight && turbo run typecheck",
+    "verify:release": "node scripts/verify-release.mjs",
     "test:checkout": "node --test scripts/*.test.mjs",
     "test": "pnpm test:checkout && turbo run test && pnpm run test:installer",
     "test:installer": "bash tools/install-next-lane.test.sh",

packages/mosaic/__tests__/platform/detect.test.ts

@@ -0,0 +1,74 @@
+import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
+
+// homedir/platform are read at call time, so they can be stubbed per case.
+vi.mock('node:os', async (importOriginal) => {
+  const actual = await importOriginal<typeof import('node:os')>();
+  return {
+    ...actual,
+    homedir: () => '/home/tester',
+    platform: () => mockPlatform,
+  };
+});
+
+let mockPlatform: NodeJS.Platform = 'linux';
+
+const { getShellProfilePath, detectShell } = await import('../../src/platform/detect.js');
+
+describe('getShellProfilePath', () => {
+  const originalShell = process.env['SHELL'];
+  const originalZdotdir = process.env['ZDOTDIR'];
+
+  beforeEach(() => {
+    mockPlatform = 'linux';
+    delete process.env['ZDOTDIR'];
+  });
+
+  afterEach(() => {
+    if (originalShell === undefined) delete process.env['SHELL'];
+    else process.env['SHELL'] = originalShell;
+    if (originalZdotdir === undefined) delete process.env['ZDOTDIR'];
+    else process.env['ZDOTDIR'] = originalZdotdir;
+  });
+
+  // The regression this guards: setupPath() in stages/finalize.ts appends the
+  // PATH export to whatever this returns. A line written to ~/.bashrc is
+  // unreachable to `bash -lc`, systemd units and agent seats, because Debian's
+  // default .bashrc returns early for non-interactive shells — so an install
+  // reported success and left `mosaic: command not found`. Same for .zshrc,
+  // which zsh only reads for interactive shells.
+  it('never targets an interactive-only rc file', () => {
+    for (const shell of ['/bin/bash', '/usr/bin/zsh']) {
+      process.env['SHELL'] = shell;
+      const profile = getShellProfilePath();
+      expect(profile).not.toMatch(/\.bashrc$/);
+      expect(profile).not.toMatch(/\.zshrc$/);
+    }
+  });
+
+  it('uses ~/.profile for bash', () => {
+    process.env['SHELL'] = '/bin/bash';
+    expect(getShellProfilePath()).toBe('/home/tester/.profile');
+  });
+
+  it('uses ~/.zshenv for zsh', () => {
+    process.env['SHELL'] = '/usr/bin/zsh';
+    expect(getShellProfilePath()).toBe('/home/tester/.zshenv');
+  });
+
+  it('honours ZDOTDIR for zsh', () => {
+    process.env['SHELL'] = '/usr/bin/zsh';
+    process.env['ZDOTDIR'] = '/custom/zdot';
+    expect(getShellProfilePath()).toBe('/custom/zdot/.zshenv');
+  });
+
+  it('falls back to ~/.profile for an unknown shell', () => {
+    process.env['SHELL'] = '/bin/somethingelse';
+    expect(detectShell()).toBe('unknown');
+    expect(getShellProfilePath()).toBe('/home/tester/.profile');
+  });
+
+  it('still routes fish to its own config', () => {
+    process.env['SHELL'] = '/usr/bin/fish';
+    expect(getShellProfilePath()).toBe('/home/tester/.config/fish/config.fish');
+  });
+});

packages/mosaic/framework/install.sh

@@ -35,6 +35,18 @@ SOURCE_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 TARGET_DIR="${MOSAIC_HOME:-$HOME/.config/mosaic}"
 INSTALL_MODE="${MOSAIC_INSTALL_MODE:-prompt}"
 
+# Normalize the ambient umask so directory modes are a property of the installer
+# and not of whatever shell invoked it (#1236). Debian/Ubuntu ship umask 002, so
+# every `mkdir -p` below yielded 0775 — and the fleet env boundary rejects any
+# managed directory with `mode & 0o022`, which made `mosaic fleet init --write`
+# impossible on a stock install of those distros. Fedora/RHEL ship 022 and did
+# not trip it, so the product worked or did not depending on the operator's
+# login shell. 022 is what this script already assumes it produces: see the
+# umask note in make_durable_snapshot, which restores to the ambient value
+# precisely so "every later sync copy and new framework dir" gets 0644/0755.
+# Now that value is 022 rather than whatever was inherited.
+umask 022
+
 # Deliberately parsed from "$@" (a real, explicit, per-invocation argument) —
 # never an environment variable — so this opt-out can never sit silently
 # inherited in a shell profile. See #869 Point-1 C2.
@@ -696,6 +708,52 @@ sync_framework
 mkdir -p "$TARGET_DIR/memory"
 mkdir -p "$TARGET_DIR/credentials"
 
+# Three directories must be 0700, not merely not-group-writable (#1236).
+# The fleet code guards them with two different masks in two different
+# languages, and the strict one wins:
+#
+#   assertPrivateManagedDirectory (fleet-reconciler.js, `mode & 0o077`)
+#       -> MOSAIC_HOME and MOSAIC_HOME/fleet, checked before the roster lock is
+#          taken, so every mutating `mosaic fleet` command dies at 0755.
+#   assert_private_directory (tools/fleet/start-agent-session.sh, `mode & 077`)
+#       -> MOSAIC_HOME/fleet/agents, checked before a pane is ever spawned.
+#
+# Their laxer siblings (`mode & 0o022`) accept 0755, which is why normalizing
+# the umask above is necessary and not sufficient — a correct umask-022 install
+# still produces 0755 and still cannot run `mosaic fleet init --write`. Say the
+# strict modes outright rather than inferring them from a umask.
+#
+# Only these. The rest of the tree is content, stays 0755, and is only ever
+# reached by the 0o022 checks, which 0755 satisfies.
+chmod 700 "$TARGET_DIR" 2>/dev/null || \
+  warn "Could not set 0700 on $TARGET_DIR — 'mosaic fleet' mutations will fail as unsafe-permissions."
+if [[ -d "$TARGET_DIR/fleet" ]]; then
+  chmod 700 "$TARGET_DIR/fleet" 2>/dev/null || \
+    warn "Could not set 0700 on $TARGET_DIR/fleet — 'mosaic fleet' mutations will fail as unsafe-permissions."
+fi
+# fleet/agents does not exist on a first install — the CLI creates it 0700 on
+# demand. It is chmod'd here for the UPGRADE case: a tree built under umask 002
+# has it at 0775, and the repair sweep below cannot rescue it, because stripping
+# group/other write from 0755 leaves 0750 and `mode & 077` is still non-zero.
+if [[ -d "$TARGET_DIR/fleet/agents" ]]; then
+  chmod 700 "$TARGET_DIR/fleet/agents" 2>/dev/null || \
+    warn "Could not set 0700 on $TARGET_DIR/fleet/agents — agent sessions will fail to start as unsafe-permissions."
+fi
+# credentials/ holds secrets and was never meant to be group-readable either.
+# It is not on the fleet boundary, so a failure here breaks nothing — but it is
+# the one directory where a silently-failed chmod leaves secrets group-readable,
+# which is precisely the failure worth a line in the output.
+chmod 700 "$TARGET_DIR/credentials" 2>/dev/null || \
+  warn "Could not set 0700 on $TARGET_DIR/credentials — stored secrets may be readable by other users on this host."
+
+# Repair an existing tree. The umask above only governs directories this run
+# creates, so a host installed under umask 002 before this fix keeps its 0775
+# dirs through every upgrade and stays broken. Strips group/other WRITE only —
+# never read or execute — so it can repair the boundary violation without
+# changing who can traverse or read anything. Scoped to directories: file modes
+# are the manifest's business, not this fix's.
+find "$TARGET_DIR" -type d -perm /022 -exec chmod go-w {} + 2>/dev/null || true
+
 # Reconcile contract files from defaults/ into the framework root: framework-owned
 # files (CONSTITUTION/AGENTS/STANDARDS) are overwritten every upgrade (a divergent
 # copy is backed up once); user-seeded files (TOOLS) are written on first install only.

packages/mosaic/framework/systemd/user/test-fleet-units.sh

@@ -128,6 +128,14 @@ EOF
 sleep 30
 EOF
   chmod 700 "$AGENT_BIN/mosaic"
+  # The launcher resolves the roster's runtime against PANE_PATH before it
+  # spawns anything (#1241), so the runtime this projection names has to be
+  # present here even though the fake `mosaic` above never execs it.
+  cat > "$AGENT_BIN/pi" <<'EOF'
+#!/bin/sh
+sleep 30
+EOF
+  chmod 700 "$AGENT_BIN/pi"
   server_environment_before=$(tmux -L "$TEST_SOCKET" show-environment -g | sort)
   server_sessions_before=$(tmux -L "$TEST_SOCKET" list-sessions | sort)
   if /usr/bin/env -i HOME="$HOLDER_HOME" PATH=/usr/bin:/bin MOSAIC_HOME="$AGENT_HOME" \

packages/mosaic/framework/tools/_scripts/mosaic-doctor

@@ -225,6 +225,54 @@ else
   warn "mosaic-ensure-sequential-thinking helper missing"
 fi
 
+# Fleet transport binary (#1240).
+#
+# `mosaic fleet --help` reads "Manage the local Mosaic tmux fleet" and every
+# roster the CLI scaffolds sets `transport: tmux`, but nothing in the install
+# path provides tmux and, until now, nothing here noticed it was absent. On a
+# greenfield host that produced a fleet which installed clean, started clean,
+# and had no live seat; `mosaic fleet ps` was the operator's first and only
+# signal that anything was wrong.
+#
+# The roster's own `transport:` is read rather than assumed, so a host that
+# declares something other than tmux is told about the binary it actually
+# needs. Absent a roster the check still runs — `mosaic fleet init` will
+# scaffold a tmux fleet on this host, and finding out beforehand is the point.
+#
+# `tools/install.sh` carries a deliberately parallel check at the end of its
+# summary. The two are separate because the installer must be able to say this
+# before the framework's own scripts are guaranteed to be on disk; keep their
+# wording in step.
+fleet_declared_transport() {
+  local roster="$MOSAIC_HOME/fleet/roster.yaml"
+  local declared=""
+
+  if [[ -f "$roster" ]]; then
+    declared="$(sed -n 's/^[[:space:]]*transport:[[:space:]]*//p' "$roster" | head -1 |
+      tr -d '"'\''' | tr -d '\r' | awk '{print $1}')"
+  fi
+
+  printf '%s\n' "${declared:-tmux}"
+}
+
+check_fleet_transport() {
+  local transport
+  transport="$(fleet_declared_transport)"
+
+  if command -v "$transport" >/dev/null 2>&1; then
+    pass "Fleet transport available: $transport"
+    return
+  fi
+
+  if [[ -f "$MOSAIC_HOME/fleet/roster.yaml" ]]; then
+    warn "Fleet transport '$transport' is not installed — this host has a roster and no seat can launch. Install it (e.g. sudo apt-get install -y $transport), then 'mosaic fleet start'."
+  else
+    warn "Fleet transport '$transport' is not installed — 'mosaic fleet' cannot run seats here. Install it (e.g. sudo apt-get install -y $transport) before 'mosaic fleet init'."
+  fi
+}
+
+check_fleet_transport
+
 # Legacy migration surfaces should no longer contain symlink trees.
 legacy_paths=(
   "$HOME/.claude/agent-guides"

packages/mosaic/framework/tools/_scripts/test-fleet-transport-check.sh

@@ -0,0 +1,215 @@
+#!/usr/bin/env bash
+# Covers the #1240 fleet-transport checks in `mosaic-doctor` and in
+# `tools/install.sh`.
+#
+# Both checks answer the same question — "can a seat actually launch on this
+# host?" — from two different places, because the installer has to be able to
+# answer it before the framework's own scripts are guaranteed to be on disk.
+# Two implementations of one rule is exactly the shape that drifts, so this
+# harness drives BOTH, in one file, from the same table of cases.
+#
+# The functions are extracted from the shipped scripts rather than copied here.
+# A test that carries its own copy of the logic is a test that keeps passing
+# after the shipped copy changes — the failure mode this whole change is about.
+# Extraction is by exact function header and a closing brace in column one; if
+# either script is reshaped so that stops matching, the extraction yields
+# nothing and this fails loudly instead of silently measuring an empty string.
+set -euo pipefail
+
+SCRIPT_DIR=$(cd -- "$(dirname -- "$0")" && pwd)
+DOCTOR="$SCRIPT_DIR/mosaic-doctor"
+# framework/tools/_scripts -> framework/tools -> framework -> mosaic -> packages -> repo
+INSTALLER=$(cd -- "$SCRIPT_DIR/../../../../.." && pwd)/tools/install.sh
+
+fail() {
+  echo "FAIL: $*" >&2
+  exit 1
+}
+
+[ -f "$DOCTOR" ] || fail "missing mosaic-doctor at $DOCTOR"
+[ -f "$INSTALLER" ] || fail "missing install.sh at $INSTALLER"
+
+ROOT=$(mktemp -d)
+trap 'rm -rf "$ROOT"' EXIT
+
+# The cases below run with PATH set to a directory that deliberately does not
+# contain a shell, and a PATH assignment on a command also governs how that
+# command is looked up — so bash has to be named absolutely or it becomes the
+# thing that is missing.
+BASH_BIN=$(command -v bash) || fail "host is missing 'bash'"
+
+# A PATH containing exactly the utilities these functions use and nothing else.
+# The absent-transport cases are only meaningful on a PATH where the transport
+# is genuinely unresolvable, and this host (like most) has tmux in /usr/bin —
+# so the system path cannot be part of the path under test.
+FAKE_BIN="$ROOT/bin"
+mkdir -p "$FAKE_BIN"
+for utility in sed head tr awk; do
+  utility_path=$(command -v "$utility") || fail "host is missing '$utility'"
+  ln -s "$utility_path" "$FAKE_BIN/$utility"
+done
+
+if PATH="$FAKE_BIN" command -v tmux >/dev/null 2>&1; then
+  fail "'tmux' is resolvable on the minimal test path; absent-transport cases are not measurable"
+fi
+
+# Extract a function by its exact header, up to a closing brace in column one.
+extract_function() {
+  local source_file="$1"
+  local function_name="$2"
+  local destination="$3"
+
+  awk -v name="$function_name" '
+    $0 == name "() {" { collecting = 1 }
+    collecting { print }
+    collecting && $0 == "}" { exit }
+  ' "$source_file" > "$destination"
+
+  grep -qF "$function_name() {" "$destination" ||
+    fail "could not extract '$function_name' from $source_file — has it been renamed or reshaped?"
+  # An unterminated extraction would be a syntax error the moment it is sourced,
+  # but saying so here names the cause instead of leaving a bash parse error.
+  bash -n "$destination" ||
+    fail "extracted '$function_name' does not parse; the closing brace was probably not found"
+}
+
+extract_function "$DOCTOR" fleet_declared_transport "$ROOT/doctor-declared.sh"
+extract_function "$DOCTOR" check_fleet_transport "$ROOT/doctor-check.sh"
+extract_function "$INSTALLER" check_fleet_transport "$ROOT/installer-check.sh"
+
+# Build a MOSAIC_HOME, optionally with a roster declaring a transport.
+make_home() {
+  local home="$ROOT/$1"
+  local declared="${2-}"
+
+  rm -rf "$home"
+  mkdir -p "$home"
+  if [ -n "$declared" ]; then
+    mkdir -p "$home/fleet"
+    cat > "$home/fleet/roster.yaml" <<EOF
+version: 2
+generation: 1
+transport: $declared
+agents: []
+EOF
+  fi
+  printf '%s\n' "$home"
+}
+
+# Run the doctor's check against a given home and path, capturing which
+# reporter the check chose. The real `pass` prints only under `--verbose` and
+# the real `warn` always prints; these stubs make both unconditional on
+# purpose, because what is under test is the severity the check selects, not
+# whether the default verbosity happens to show it. A check that warned where
+# it should pass would otherwise be invisible here.
+run_doctor_check() {
+  local home="$1"
+  local path="$2"
+
+  MOSAIC_HOME="$home" PATH="$path" "$BASH_BIN" --noprofile --norc -c '
+    set -euo pipefail
+    warn() { echo "[WARN] $*"; }
+    pass() { echo "[OK] $*"; }
+    MOSAIC_HOME="$1"
+    source "$2"
+    source "$3"
+    check_fleet_transport
+  ' _ "$home" "$ROOT/doctor-declared.sh" "$ROOT/doctor-check.sh" 2>&1
+}
+
+run_installer_check() {
+  local home="$1"
+  local path="$2"
+
+  MOSAIC_HOME="$home" PATH="$path" "$BASH_BIN" --noprofile --norc -c '
+    set -euo pipefail
+    warn() { echo "[WARN] $*"; }
+    C="" RESET=""
+    MOSAIC_HOME="$1"
+    source "$2"
+    check_fleet_transport
+  ' _ "$home" "$ROOT/installer-check.sh" 2>&1
+}
+
+# A transport that exists. Named tmux because that is what the default roster
+# declares; the binary never runs, it only has to resolve.
+PRESENT_BIN="$ROOT/present-bin"
+mkdir -p "$PRESENT_BIN"
+printf '#!/usr/bin/env bash\nexit 0\n' > "$PRESENT_BIN/tmux"
+chmod +x "$PRESENT_BIN/tmux"
+PATH_WITH_TMUX="$PRESENT_BIN:$FAKE_BIN"
+
+# ── absent, no roster ────────────────────────────────────────────────────────
+# Nothing has been configured yet, so the honest thing to point at is `init`.
+home=$(make_home no-roster)
+
+output=$(run_doctor_check "$home" "$FAKE_BIN")
+echo "$output" | grep -qF '[WARN]' || fail "doctor did not warn when tmux was absent"
+echo "$output" | grep -qF 'tmux' || fail "doctor warning did not name the transport"
+echo "$output" | grep -qF 'mosaic fleet init' || fail "doctor did not point a rosterless host at init"
+
+output=$(run_installer_check "$home" "$FAKE_BIN")
+echo "$output" | grep -qF '[WARN]' || fail "installer did not warn when tmux was absent"
+echo "$output" | grep -qF 'reports success and no seat comes up' ||
+  fail "installer warning did not say what the missing transport actually breaks"
+
+# ── absent, roster present ───────────────────────────────────────────────────
+# A configured fleet that cannot launch is a stronger statement than a
+# hypothetical one, and the message says so.
+home=$(make_home with-roster tmux)
+
+output=$(run_doctor_check "$home" "$FAKE_BIN")
+echo "$output" | grep -qF '[WARN]' || fail "doctor did not warn with a roster present and tmux absent"
+echo "$output" | grep -qF 'roster' || fail "doctor did not mention the roster it found"
+echo "$output" | grep -qF 'mosaic fleet start' || fail "doctor did not point a configured host at start"
+
+# ── present ──────────────────────────────────────────────────────────────────
+# Silence from the installer, and a pass (not a warning) from the audit.
+for home_name in no-roster with-roster; do
+  home="$ROOT/$home_name"
+
+  output=$(run_doctor_check "$home" "$PATH_WITH_TMUX")
+  if echo "$output" | grep -qF '[WARN]'; then
+    fail "doctor warned about the transport while tmux was present ($home_name)"
+  fi
+  echo "$output" | grep -qF '[OK]' || fail "doctor did not record a pass with tmux present ($home_name)"
+
+  output=$(run_installer_check "$home" "$PATH_WITH_TMUX")
+  if [ -n "$output" ]; then
+    fail "installer was not silent with tmux present ($home_name): $output"
+  fi
+done
+
+# ── the roster declares something other than tmux ────────────────────────────
+# The roster is read, not assumed. A host that declares a different transport
+# is told about the binary it actually needs, and never about tmux — being sent
+# to install the wrong package is worse than no advice at all.
+home=$(make_home other-transport zellij)
+
+output=$(run_doctor_check "$home" "$PATH_WITH_TMUX")
+echo "$output" | grep -qF 'zellij' || fail "doctor ignored the roster's declared transport"
+if echo "$output" | grep -qF 'tmux'; then
+  fail "doctor named tmux for a host whose roster declares zellij"
+fi
+
+output=$(run_installer_check "$home" "$PATH_WITH_TMUX")
+echo "$output" | grep -qF 'zellij' || fail "installer ignored the roster's declared transport"
+if echo "$output" | grep -qF 'tmux'; then
+  fail "installer named tmux for a host whose roster declares zellij"
+fi
+
+# ── a quoted or trailing-comment transport value ─────────────────────────────
+# YAML permits both and neither is exotic; a check that installs `tmux"` or
+# reads `tmux # default` as a binary name would send the operator nowhere.
+home=$(make_home quoted-transport '"tmux"   # the only transport today')
+
+output=$(run_doctor_check "$home" "$PATH_WITH_TMUX")
+echo "$output" | grep -qF '[OK] Fleet transport available: tmux' ||
+  fail "doctor did not parse a quoted/commented transport value: $output"
+
+output=$(run_installer_check "$home" "$PATH_WITH_TMUX")
+if [ -n "$output" ]; then
+  fail "installer did not parse a quoted/commented transport value: $output"
+fi
+
+echo "ok - fleet transport checks (mosaic-doctor + install.sh)"

packages/mosaic/framework/tools/fleet/start-agent-session.sh

@@ -286,6 +286,36 @@ _build_runtime_bin_prefix() {
 MOSAIC_RUNTIME_BIN_PREFIX=$(_build_runtime_bin_prefix)
 PANE_PATH=${MOSAIC_RUNTIME_BIN_PREFIX:+${MOSAIC_RUNTIME_BIN_PREFIX}:}/usr/local/bin:/usr/bin:/bin
 
+# #1241. The pane runs `mosaic yolo <runtime>` under PANE_PATH with a cleared
+# environment. A binary missing from *that* path is a pane that dies in under a
+# second, inside a session nobody is attached to, with its diagnostic scrolled
+# into a pane tmux then destroys. Resolve both here, before any effect, where
+# the failure is still attributable to the thing that caused it.
+#
+# `mosaic yolo <runtime>` runs checkRuntime(runtime) and the binary it looks for
+# is named exactly like the runtime, so resolving the runtime name is the same
+# question the pane will ask a moment later — asked while an operator can still
+# see the answer.
+_resolve_in_pane_path() {
+  PATH="$PANE_PATH" command -v -- "$1" 2>/dev/null
+}
+
+# Exit 69 (EX_UNAVAILABLE): the seat cannot be provided. Distinguished from the
+# 64 (EX_USAGE) rejections above, which mean the projection itself was bad —
+# here the data is fine and the host is not ready. Callers tell the individual
+# cases apart by `code=`, the same way fail_env's many codes share exit 64.
+fail_launch() {
+  local code="$1"
+  shift
+  echo "ERROR: agent launch aborted: code=${code} agent=${AGENT_NAME} $*" >&2
+  exit 69
+}
+
+for required_binary in mosaic "$MOSAIC_AGENT_RUNTIME"; do
+  _resolve_in_pane_path "$required_binary" >/dev/null ||
+    fail_launch missing-binary "'${required_binary}' is not on the pane PATH (${PANE_PATH})"
+done
+
 _ensure_claude_workdir_trusted() {
   local workdir="$1"
   local resolved
@@ -384,6 +414,19 @@ if [ -n "$PANE_PID" ]; then
   _start_heartbeat_sidecar "$AGENT_NAME" "$PANE_PID" \
     "$MOSAIC_HEARTBEAT_RUN_DIR" "$MOSAIC_HEARTBEAT_INTERVAL" || \
     echo "WARNING: heartbeat sidecar could not be started for $AGENT_NAME" >&2
+elif _tmux has-session -t "=${AGENT_NAME}:0.0" 2>/dev/null; then
+  # #1241. Session present, no pane PID after a second of retries. Whatever this
+  # is, it is not a seat an operator can use, so it is not a success either.
+  fail_launch pane-pid-unresolved \
+    "tmux reports the session but no pane PID after 5 attempts"
 else
-  echo "WARNING: could not resolve pane PID for $AGENT_NAME — heartbeat sidecar not started" >&2
+  # #1241. This branch used to print a WARNING about the heartbeat sidecar and
+  # exit 0. It is not a heartbeat problem: tmux destroys a session when its pane
+  # command exits, so an absent session one second after new-session means the
+  # runtime died on startup. Reporting it as success is what let `fleet start`
+  # return 0 over three dead panes — the launcher knew, and said the wrong thing
+  # at the wrong severity to the wrong layer.
+  fail_launch pane-did-not-survive \
+    "the pane exited immediately and tmux destroyed the session;" \
+    "run 'mosaic yolo ${MOSAIC_AGENT_RUNTIME}' in ${MOSAIC_AGENT_WORKDIR} to see why"
 fi

packages/mosaic/framework/tools/fleet/test-start-agent-session.sh

@@ -23,8 +23,26 @@ index=0
 if [ "${args[0]:-}" = -L ]; then index=2; fi
 case "${args[$index]:-}" in
   has-session)
+    # The holder always answers. MOSAIC_TEST_HELD_SESSIONS lets a case add
+    # other targets that should answer too — without it there is no way to
+    # model "tmux still reports the session" for a non-holder agent, and the
+    # launcher's pane-pid-unresolved branch is unreachable from this harness.
+    #
+    # A listed target answers only AFTER new-session, because the launcher asks
+    # this question twice about the same name: once before launching, where a
+    # yes means "already running, nothing to do, exit 0", and once after, where
+    # a yes means "the session survived". A shim that answered yes to both
+    # would short-circuit at the first and never reach the branch under test —
+    # it would look like coverage and measure the idempotency path instead.
     for argument in "${args[@]}"; do
       [ "$argument" = '=_holder:0.0' ] && exit 0
+      case " ${MOSAIC_TEST_HELD_SESSIONS:-} " in
+        *" $argument "*)
+          if tr '\0' '\n' < "${MOSAIC_TEST_TMUX_CALLS:?}" | grep -qxF new-session; then
+            exit 0
+          fi
+          ;;
+      esac
     done
     exit 1
     ;;
@@ -62,6 +80,30 @@ env -0 > "${MOSAIC_HOME:?}/fleet/pane-environment"
 SHIM
 chmod +x "$FAKE_BIN/mosaic"
 
+# The runtime the rosters below name. The launcher resolves it against PANE_PATH
+# before spawning (#1241), so it has to exist somewhere the pane would find it —
+# not merely on the launcher's own PATH.
+printf '#!/usr/bin/env bash\nexit 0\n' > "$FAKE_BIN/pi"
+chmod +x "$FAKE_BIN/pi"
+
+# PANE_PATH is derived partly from `npm config get prefix`. Left to the real npm
+# it would splice whatever the host has installed into the path under test, and
+# the missing-binary cases below would pass or fail by accident of the machine.
+cat > "$FAKE_BIN/npm" <<'SHIM'
+#!/usr/bin/env bash
+printf '%s\n' "${MOSAIC_TEST_NPM_PREFIX:-/nonexistent}"
+SHIM
+chmod +x "$FAKE_BIN/npm"
+
+# PANE_PATH always ends in the system path. A host that installs these there can
+# not measure the missing-binary cases at all, and a green run would mean
+# nothing — so say so instead of passing.
+for host_binary in mosaic pi; do
+  if PATH=/usr/local/bin:/usr/bin:/bin command -v "$host_binary" >/dev/null 2>&1; then
+    fail "host provides '$host_binary' in the system path; missing-binary cases are not measurable here"
+  fi
+done
+
 write_generated() {
   local home="$1"
   local agent="$2"
@@ -81,6 +123,19 @@ MOSAIC_TMUX_SOCKET=mosaic-test
 EOF
   chmod 600 "$home/fleet/agents/$agent.env.generated"
   mkdir -p "$home/work"
+  install_pane_binaries "$home"
+}
+
+# `$PANE_HOME/.npm-global/bin` is one of the prefixes the launcher folds into
+# PANE_PATH, so this is the pane's own view of "installed", distinct from the
+# launcher's PATH. Tests that need a binary *absent* remove it from here.
+install_pane_binaries() {
+  local pane_home="$1"
+  mkdir -p "$pane_home/.npm-global/bin"
+  local binary
+  for binary in mosaic pi; do
+    ln -sf "$FAKE_BIN/$binary" "$pane_home/.npm-global/bin/$binary"
+  done
 }
 
 run_start() {
@@ -88,6 +143,7 @@ run_start() {
   local agent="$2"
   HOME="$home" PATH="$FAKE_BIN:$PATH" MOSAIC_TEST_TMUX_CALLS="$TMUX_CALLS" \
     MOSAIC_TEST_PANE_PID="${MOSAIC_TEST_PANE_PID:-}" \
+    MOSAIC_TEST_HELD_SESSIONS="${MOSAIC_TEST_HELD_SESSIONS:-}" \
     MOSAIC_TEST_HOME="$home" \
     MOSAIC_TEST_FLEET_OWNER=123e4567-e89b-12d3-a456-426614174000 \
     MOSAIC_HOME="$home" "$START" "$agent"
@@ -98,7 +154,10 @@ run_start() {
 HOME_VALID="$ROOT/valid"
 AGENT_VALID="coder0"
 write_generated "$HOME_VALID" "$AGENT_VALID"
-run_start "$HOME_VALID" "$AGENT_VALID"
+# A live pane PID is part of what "valid launch" means. Until #1241 this case
+# ran with none, so the suite's one success path was itself a dead pane the
+# launcher reported as fine.
+MOSAIC_TEST_PANE_PID=$$ run_start "$HOME_VALID" "$AGENT_VALID"
 valid_args=$(tr '\0' '\n' < "$TMUX_CALLS")
 echo "$valid_args" | grep -qF new-session || fail "valid generated projection did not reach tmux"
 echo "$valid_args" | grep -qF 'mosaic' || fail "fixed mosaic launcher command missing"
@@ -245,6 +304,13 @@ PANE_BASH_ENV="$ROOT/pane-boundary.bash-env"
 printf 'MOSAIC_RUNTIME_BIN=%s\n' "$FAKE_BIN" > \
   "$HOME_PANE_BOUNDARY/fleet/agents/coder-pane-boundary.env.local"
 chmod 600 "$HOME_PANE_BOUNDARY/fleet/agents/coder-pane-boundary.env.local"
+# This case does not go through run_start, so its pane binaries come from
+# MOSAIC_RUNTIME_BIN=$FAKE_BIN in the env.local written above — not from the
+# symlinks install_pane_binaries planted under the generated home, which this
+# launcher never consults because HOME here is the trusted parent. That is a
+# legitimate resolution path, but it means dropping MOSAIC_RUNTIME_BIN from
+# this case on the belief that the symlinks cover it would break the #1241
+# binary check rather than exercise it.
 LD_PRELOAD='/not/loaded/by-clean-bootstrap.so' \
 BASH_ENV="$PANE_BASH_ENV" \
 MOSAIC_UNTRUSTED_SENTINEL='must-not-reach-pane' \
@@ -258,6 +324,7 @@ PATH="$PANE_STALE_PATH" \
     "MOSAIC_TEST_HOME=$PANE_TRUSTED_HOME" \
     MOSAIC_TEST_FLEET_OWNER=123e4567-e89b-12d3-a456-426614174000 \
     MOSAIC_TEST_EXECUTE_PANE=1 \
+    "MOSAIC_TEST_PANE_PID=$$" \
     "$START" coder-pane-boundary
 pane_args=$(tr '\0' '\n' < "$TMUX_CALLS")
 echo "$pane_args" | grep -qxF "HOME=$PANE_TRUSTED_HOME" || \
@@ -392,6 +459,75 @@ echo "$interaction_policy_args" | grep -qF 'new-session' && \
 echo "$output" | grep -qF 'operator interaction service requires runtime pi' || \
   fail "interaction pinned-policy check did not follow strict parsing"
 
+# #1241. The pane runs `mosaic yolo <runtime>` against PANE_PATH. A binary
+# missing from that path is a launch failure, and it has to be named before the
+# session is created — after it, the diagnostic dies with the pane.
+assert_missing_pane_binary_rejected() {
+  local binary="$1"
+  local home="$ROOT/missing-$binary"
+  local agent="coder-missing-$binary"
+  write_generated "$home" "$agent"
+  rm -f "$home/.npm-global/bin/$binary"
+
+  : > "$TMUX_CALLS"
+  local output
+  if output=$(MOSAIC_TEST_PANE_PID=$$ run_start "$home" "$agent" 2>&1); then
+    fail "launch succeeded with '$binary' absent from the pane PATH"
+  fi
+  echo "$output" | grep -qF 'code=missing-binary' || fail "missing '$binary' diagnostic missing"
+  echo "$output" | grep -qF "'$binary'" || fail "missing-binary diagnostic did not name $binary"
+  if tr '\0' '\n' < "$TMUX_CALLS" | grep -qF new-session; then
+    fail "launcher created a session it knew would die ($binary absent)"
+  fi
+}
+
+assert_missing_pane_binary_rejected mosaic
+assert_missing_pane_binary_rejected pi
+
+# #1241. tmux destroys a session when its pane command exits, so no pane PID a
+# second after new-session means the runtime died on startup. This used to be a
+# WARNING about the heartbeat sidecar followed by exit 0 — three layers above it
+# then reported a fleet that was not running.
+: > "$TMUX_CALLS"
+HOME_DEAD_PANE="$ROOT/dead-pane"
+write_generated "$HOME_DEAD_PANE" "coder-dead-pane"
+if output=$(MOSAIC_TEST_PANE_PID='' run_start "$HOME_DEAD_PANE" coder-dead-pane 2>&1); then
+  fail "launcher reported success over a pane that did not survive"
+fi
+echo "$output" | grep -qF 'code=pane-did-not-survive' || fail "dead-pane diagnostic missing"
+if echo "$output" | grep -qiF 'heartbeat'; then
+  fail "dead pane is still being reported as a heartbeat-sidecar problem"
+fi
+tr '\0' '\n' < "$TMUX_CALLS" | grep -qF new-session || \
+  fail "dead-pane case did not reach the launch it is measuring"
+
+# #1241, the other way a pane fails. Above, tmux destroyed the session and
+# has-session said so. Here the session is still there and no PID comes back
+# after the retries — a different fault (the pane is alive but unusable, or
+# tmux is answering inconsistently) that an operator has to be told apart from
+# a runtime that died on startup.
+#
+# This case exists because the branch that handles it shipped with nothing able
+# to reach it: the shim answered has-session only for the holder, so every
+# non-holder agent landed in the session-is-gone branch no matter what. A
+# defensive branch nothing exercises is the same shape as the bug this whole
+# change is about, one layer down.
+: > "$TMUX_CALLS"
+HOME_NO_PID="$ROOT/pane-no-pid"
+write_generated "$HOME_NO_PID" "coder-no-pid"
+if output=$(MOSAIC_TEST_PANE_PID='' MOSAIC_TEST_HELD_SESSIONS='=coder-no-pid:0.0' \
+  run_start "$HOME_NO_PID" coder-no-pid 2>&1); then
+  fail "launcher reported success over a session with no resolvable pane PID"
+fi
+echo "$output" | grep -qF 'code=pane-pid-unresolved' || \
+  fail "session-present/no-PID was not reported as pane-pid-unresolved: $output"
+if echo "$output" | grep -qF 'code=pane-did-not-survive'; then
+  fail "a session tmux still reports was diagnosed as a destroyed session"
+fi
+if echo "$output" | grep -qiF 'heartbeat'; then
+  fail "an unresolvable pane PID is still being reported as a heartbeat-sidecar problem"
+fi
+
 # Exact stop derives the socket exclusively from the validated generated
 # projection and ignores an ambient socket supplied by the caller.
 : > "$TMUX_CALLS"

packages/mosaic/framework/tools/quality/test-enumeration-exclusions.txt

@@ -32,10 +32,6 @@ packages/mosaic/framework/tools/tmux/test-send-message-socket.sh | requires a re
 packages/mosaic/framework/tools/tmux/test-send-message-verdict.sh | requires real tmux-pane fixtures on a throwaway socket; CI image ships no tmux; #1017 burndown (same condition as its sibling)
 
 # --- single-suite directories: unmeasured in CI ---
-packages/mosaic/framework/tools/fleet/test-start-agent-session.sh | unmeasured in CI image; stubs tmux via a fake bin dir, likely CI-fit; #1017 burndown
-packages/mosaic/framework/tools/glpi/test-list-http-status.sh | unmeasured in CI image; stub-based (#807 regression harness), likely CI-fit; #1017 burndown
-packages/mosaic/framework/tools/orchestrator/test-board-roll.sh | unmeasured in CI image; file-fixture based, likely CI-fit; #1017 burndown
-packages/mosaic/framework/tools/woodpecker/test-ci-wait-exit-matrix.sh | unmeasured in CI image; drives ci-wait.sh against a stub pipeline-status.sh, likely CI-fit; #1017 burndown
 
 # --- naming-boundary files the strict test-*.sh prefix cannot even name ---
 # (#1017: three independent censuses handled the microtest file three different

packages/mosaic/package.json

@@ -25,7 +25,7 @@
     "lint": "eslint src",
     "typecheck": "tsc --noEmit",
     "test": "vitest run --passWithNoTests && pnpm run test:framework-shell",
-    "test:framework-shell": "bash framework/tools/quality/scripts/check-test-enumeration.sh && bash framework/tools/quality/scripts/test-check-test-enumeration.sh && python3 src/lease-broker/daemon_deadline_unittest.py && python3 src/lease-broker/normative_fragments_unittest.py && python3 src/lease-broker/promotion_binding_unittest.py && python3 src/lease-broker/promotion_trigger_unittest.py && python3 src/lease-broker/receipt_challenge_unittest.py && python3 src/lease-broker/context_recovery_unittest.py && python3 src/lease-broker/recovery_runtime_unittest.py && python3 src/lease-broker/recovery_b1_adversarial_unittest.py && python3 src/lease-broker/receipt_observer_client_unittest.py && python3 src/lease-broker/invariant_r_unittest.py && python3 src/lease-broker/framework_skill_portability_unittest.py && python3 src/mutator-gate/runtime_tools_unittest.py && python3 src/mutator-gate/runtime_launch_guard_unittest.py && python3 src/mutator-gate/version_coupling_unittest.py && python3 framework/tools/lease-broker/check-runtime-launches.py --root ../.. && bash framework/tools/codex/test-pr-diff-context.sh && bash framework/tools/qa/test-deps-preflight.sh && bash framework/tools/git/test-pr-review-gitea-comment.sh && bash framework/tools/git/test-pr-review-repo-host-override.sh && bash framework/tools/git/test-ci-queue-wait-branch-absent.sh && bash framework/tools/git/test-ci-queue-wait-tristate.sh && bash framework/tools/git/test-ci-queue-wait-github-checks.sh && bash framework/tools/git/test-pr-merge-queue-branch.sh && bash framework/tools/git/test-pr-merge-head-pin.sh && bash framework/tools/git/test-pr-merge-message-field.sh && bash framework/tools/git/test-git-credential-mosaic.sh && bash framework/tools/git/test-gitea-token-identity.sh && bash framework/tools/woodpecker/test-terminal-green-contract.sh && bash framework/tools/_scripts/test-install-ordering-guard.sh && bash framework/tools/_scripts/test-mosaic-init-rce.sh && bash framework/tools/tmux/agent-send.test.sh && bash framework/tools/wake/test-wake-store-ack.sh && bash framework/tools/wake/test-wake-store-enqueue-race.sh && bash framework/tools/wake/test-wake-digest-hmac.sh && bash framework/tools/wake/test-wake-digest-quarantine.sh && bash framework/tools/wake/test-wake-detector.sh && bash framework/tools/wake/test-wake-fn-oracle.sh && bash framework/tools/wake/test-wake-reconcile.sh && bash framework/tools/wake/test-wake-beacon.sh && bash framework/tools/wake/test-wake-preimage.sh && bash framework/tools/wake/test-wake-install.sh"
+    "test:framework-shell": "bash framework/tools/quality/scripts/check-test-enumeration.sh && bash framework/tools/quality/scripts/test-check-test-enumeration.sh && python3 src/lease-broker/daemon_deadline_unittest.py && python3 src/lease-broker/normative_fragments_unittest.py && python3 src/lease-broker/promotion_binding_unittest.py && python3 src/lease-broker/promotion_trigger_unittest.py && python3 src/lease-broker/receipt_challenge_unittest.py && python3 src/lease-broker/context_recovery_unittest.py && python3 src/lease-broker/recovery_runtime_unittest.py && python3 src/lease-broker/recovery_b1_adversarial_unittest.py && python3 src/lease-broker/receipt_observer_client_unittest.py && python3 src/lease-broker/invariant_r_unittest.py && python3 src/lease-broker/framework_skill_portability_unittest.py && python3 src/mutator-gate/runtime_tools_unittest.py && python3 src/mutator-gate/runtime_launch_guard_unittest.py && python3 src/mutator-gate/version_coupling_unittest.py && python3 framework/tools/lease-broker/check-runtime-launches.py --root ../.. && bash framework/tools/codex/test-pr-diff-context.sh && bash framework/tools/qa/test-deps-preflight.sh && bash framework/tools/git/test-pr-review-gitea-comment.sh && bash framework/tools/git/test-pr-review-repo-host-override.sh && bash framework/tools/git/test-ci-queue-wait-branch-absent.sh && bash framework/tools/git/test-ci-queue-wait-tristate.sh && bash framework/tools/git/test-ci-queue-wait-github-checks.sh && bash framework/tools/git/test-pr-merge-queue-branch.sh && bash framework/tools/git/test-pr-merge-head-pin.sh && bash framework/tools/git/test-pr-merge-message-field.sh && bash framework/tools/git/test-git-credential-mosaic.sh && bash framework/tools/git/test-gitea-token-identity.sh && bash framework/tools/woodpecker/test-terminal-green-contract.sh && bash framework/tools/_scripts/test-install-ordering-guard.sh && bash framework/tools/_scripts/test-mosaic-init-rce.sh && bash framework/tools/tmux/agent-send.test.sh && bash framework/tools/wake/test-wake-store-ack.sh && bash framework/tools/wake/test-wake-store-enqueue-race.sh && bash framework/tools/wake/test-wake-digest-hmac.sh && bash framework/tools/wake/test-wake-digest-quarantine.sh && bash framework/tools/wake/test-wake-detector.sh && bash framework/tools/wake/test-wake-fn-oracle.sh && bash framework/tools/wake/test-wake-reconcile.sh && bash framework/tools/wake/test-wake-beacon.sh && bash framework/tools/wake/test-wake-preimage.sh && bash framework/tools/wake/test-wake-install.sh && bash framework/tools/fleet/test-start-agent-session.sh && bash framework/tools/glpi/test-list-http-status.sh && bash framework/tools/orchestrator/test-board-roll.sh && bash framework/tools/woodpecker/test-ci-wait-exit-matrix.sh && bash framework/tools/_scripts/test-fleet-transport-check.sh"
   },
   "dependencies": {
     "@mosaicstack/brain": "workspace:*",

packages/mosaic/src/platform/detect.ts

@@ -1,4 +1,3 @@
-import { existsSync } from 'node:fs';
 import { join } from 'node:path';
 import { homedir, platform } from 'node:os';
 
@@ -22,15 +21,18 @@ export function getShellProfilePath(): string | null {
 
   const shell = detectShell();
   switch (shell) {
+    // Both of these deliberately avoid the interactive-only rc files.
+    // Debian's default .bashrc returns early for non-interactive shells, so a
+    // PATH line appended to it never runs for `bash -lc`, systemd units, or
+    // agent seats — an install could report success and still leave `mosaic`
+    // unreachable. .profile is read by login shells and sources .bashrc for
+    // interactive ones, so one line covers both; .zshenv is zsh's equivalent.
     case 'zsh': {
       const zdotdir = process.env['ZDOTDIR'] ?? home;
-      return join(zdotdir, '.zshrc');
+      return join(zdotdir, '.zshenv');
     }
-    case 'bash': {
+    case 'bash':
-      const bashrc = join(home, '.bashrc');
-      if (existsSync(bashrc)) return bashrc;
       return join(home, '.profile');
-    }
     case 'fish':
       return join(home, '.config', 'fish', 'config.fish');
     default:

scripts/verify-release.mjs

@@ -0,0 +1,166 @@
+#!/usr/bin/env node
+// verify-release.mjs — the ONE canonical terminal verification command
+// (SDLC-D-034, `pnpm verify:release`).
+//
+// Publication (.woodpecker/publish.yml `verify` step) is bound to terminal
+// verification of the exact commit through this command, which is composed
+// from the SAME commands the PR CI pipeline (.woodpecker/ci.yml) runs — CI and
+// publish share one semantic checklist:
+//
+//   stage         | mirrors ci.yml step | commands
+//   --------------|---------------------|------------------------------------------
+//   sanitization  | sanitization        | verify-sanitized.sh, check-resident-
+//                |                     | budget.sh (--self-test + run),
+//                |                     | check-test-enumeration.sh
+//   upgrade-guard | upgrade-guard       | test-upgrade-manifest-guard.sh,
+//                |                     | test-upgrade-rollback.sh,
+//                |                     | test-upgrade-durable-snapshot.sh,
+//                |                     | test-install-migration.sh
+//   typecheck     | typecheck           | pnpm typecheck (runs the checkout
+//                |                     | preflight, then turbo typecheck)
+//   lint          | lint                | pnpm lint
+//   format        | format              | pnpm format:check
+//   test          | test                | pnpm test
+//   build         | publish.yml build   | pnpm build
+//
+// Caller-provided prerequisites (kept at the pipeline level — see the comments
+// in .woodpecker/ci.yml): `bash` + `rsync` for the guard stages, `openssl` and
+// the pinned @earendil-works/pi-coding-agent for the test stage, and — on the
+// postgres path only — the ci-postgres service plus
+// `pnpm --filter @mosaicstack/db run db:migrate` before the test stage.
+//
+// This command works with DATABASE_URL set (CI postgres path) or unset (local
+// PGlite path); it never sets, exports, or requires a database itself.
+//
+// scripts/verify-release.test.mjs enforces that this stage table keeps
+// matching .woodpecker/ci.yml step-for-step, so the two surfaces cannot drift
+// apart silently.
+
+import { spawnSync } from 'node:child_process';
+import path from 'node:path';
+import { fileURLToPath } from 'node:url';
+
+export const STAGES = [
+  {
+    name: 'sanitization',
+    // Mirror of the .woodpecker/ci.yml `sanitization` step (minus its
+    // `apk add` environment prep). Kept as direct command strings here: the
+    // #1017 test-enumeration guard audits these paths through the ci.yml
+    // surface, so indirection from ci.yml into this file is not possible.
+    commands: [
+      'bash packages/mosaic/framework/tools/quality/scripts/verify-sanitized.sh',
+      'bash packages/mosaic/framework/tools/quality/scripts/check-resident-budget.sh --self-test',
+      'bash packages/mosaic/framework/tools/quality/scripts/check-resident-budget.sh',
+      'bash packages/mosaic/framework/tools/quality/scripts/check-test-enumeration.sh',
+    ],
+  },
+  {
+    name: 'upgrade-guard',
+    // Mirror of the .woodpecker/ci.yml `upgrade-guard` step (minus its
+    // `apk add` environment prep).
+    commands: [
+      'bash packages/mosaic/framework/tools/quality/scripts/test-upgrade-manifest-guard.sh',
+      'bash packages/mosaic/framework/tools/quality/scripts/test-upgrade-rollback.sh',
+      'bash packages/mosaic/framework/tools/quality/scripts/test-upgrade-durable-snapshot.sh',
+      'bash packages/mosaic/framework/tools/quality/scripts/test-install-migration.sh',
+    ],
+  },
+  {
+    // `pnpm typecheck` is `pnpm preflight && turbo run typecheck`, so the
+    // checkout preflight (scripts/preflight.mjs) is part of this stage exactly
+    // as it is part of the ci.yml `typecheck` step.
+    name: 'typecheck',
+    commands: ['pnpm typecheck'],
+  },
+  {
+    name: 'lint',
+    commands: ['pnpm lint'],
+  },
+  {
+    name: 'format',
+    commands: ['pnpm format:check'],
+  },
+  {
+    // Requires `openssl` and the pinned `pi` binary on the pipeline path; see
+    // the caller-provided prerequisites above.
+    name: 'test',
+    commands: ['pnpm test'],
+  },
+  {
+    name: 'build',
+    commands: ['pnpm build'],
+  },
+];
+
+export function stageByName(name) {
+  return STAGES.find((stage) => stage.name === name);
+}
+
+function missingBinaries(bins) {
+  return bins.filter(
+    (bin) => spawnSync('sh', ['-c', `command -v ${bin} >/dev/null 2>&1`]).status !== 0,
+  );
+}
+
+function runCommand(command) {
+  const result = spawnSync(command, { shell: true, stdio: 'inherit' });
+  if (result.error) {
+    console.error(`[verify:release] failed to launch '${command}': ${result.error.message}`);
+    return false;
+  }
+  if (result.status !== 0) {
+    const reason = result.signal ? `terminated by ${result.signal}` : `exited ${result.status}`;
+    console.error(`[verify:release] command '${command}' ${reason}`);
+    return false;
+  }
+  return true;
+}
+
+// Runs the complete mandatory verification set (or, with --stage <name>, the
+// single named stage — used for wiring/smoke-testing, not for gating: only a
+// run of every stage is a terminal verification). Fails fast: the first
+// failing command aborts with a non-zero exit code. Returns the exit code.
+export function verifyRelease({ stages = STAGES } = {}) {
+  const missing = missingBinaries(['bash', 'rsync']);
+  if (missing.length > 0) {
+    console.error(
+      `[verify:release] FATAL: required binaries missing from PATH: ${missing.join(', ')}. ` +
+        'The caller provides them (ci-base bakes bash; pipelines apk add rsync).',
+    );
+    return 1;
+  }
+  for (const stage of stages) {
+    console.log(`\n[verify:release] === stage: ${stage.name} ===`);
+    for (const command of stage.commands) {
+      console.log(`[verify:release] $ ${command}`);
+      if (!runCommand(command)) {
+        console.error(
+          `[verify:release] FATAL: stage '${stage.name}' failed — verification inconclusive`,
+        );
+        return 1;
+      }
+    }
+  }
+  console.log(`\n[verify:release] all ${stages.length} stage(s) passed`);
+  return 0;
+}
+
+function main(argv) {
+  const stageFlagIndex = argv.indexOf('--stage');
+  if (stageFlagIndex !== -1) {
+    const name = argv[stageFlagIndex + 1];
+    const stage = stageByName(name);
+    if (!stage) {
+      console.error(
+        `[verify:release] unknown stage '${name ?? ''}' — expected one of: ${STAGES.map((entry) => entry.name).join(', ')}`,
+      );
+      process.exit(2);
+    }
+    process.exit(verifyRelease({ stages: [stage] }));
+  }
+  process.exit(verifyRelease());
+}
+
+if (process.argv[1] && path.resolve(process.argv[1]) === fileURLToPath(import.meta.url)) {
+  main(process.argv.slice(2));
+}

scripts/verify-release.test.mjs

@@ -0,0 +1,277 @@
+import assert from 'node:assert/strict';
+import { readFile } from 'node:fs/promises';
+import { createRequire } from 'node:module';
+import path from 'node:path';
+import test from 'node:test';
+
+import { STAGES } from './verify-release.mjs';
+
+// SDLC-D-034 checkout invariant: publication in .woodpecker/publish.yml is
+// bound to exact-commit terminal verification. This suite parses the real
+// pipeline files and fails red when the gate is bypassed, weakened, or drifts
+// out of sync with the canonical `pnpm verify:release` command.
+
+// Reuse the monorepo's existing YAML parser (@mosaicstack/mosaic's direct
+// dependency) instead of adding a root dependency or vendoring a parser.
+const mosaicRequire = createRequire(
+  path.resolve(process.cwd(), 'packages', 'mosaic', 'package.json'),
+);
+const { parse: parseYaml } = mosaicRequire('yaml');
+
+const publishYmlPath = path.join(process.cwd(), '.woodpecker', 'publish.yml');
+const ciYmlPath = path.join(process.cwd(), '.woodpecker', 'ci.yml');
+
+async function readPublishPipeline() {
+  return parseYaml(await readFile(publishYmlPath, 'utf8'));
+}
+
+// A step has an external publication effect when its name starts with
+// `publish` or when any command pushes an image to a registry.
+function pushesImage(step) {
+  return (step.commands ?? []).some((command) =>
+    /(^|\s)(\/kaniko\/executor|docker push)\b|--destination/.test(command),
+  );
+}
+
+function publishEffectSteps(pipeline) {
+  return Object.entries(pipeline.steps ?? {})
+    .filter(([name, step]) => name.startsWith('publish') || pushesImage(step))
+    .map(([name]) => name);
+}
+
+// Transitive closure of a step's depends_on graph.
+function dependencyClosure(pipeline, stepName, seen = new Set()) {
+  const dependencies = pipeline.steps?.[stepName]?.depends_on ?? [];
+  for (const dependency of dependencies) {
+    if (seen.has(dependency)) continue;
+    seen.add(dependency);
+    dependencyClosure(pipeline, dependency, seen);
+  }
+  return seen;
+}
+
+function verifyCommands(pipeline) {
+  const verify = pipeline.steps?.verify;
+  assert.ok(verify, 'publish pipeline must define a `verify` step');
+  assert.ok(Array.isArray(verify.commands), '`verify` step must have commands');
+  return verify.commands;
+}
+
+function assertCommitIdentityAssertion(commands) {
+  const text = commands.join('\n');
+  assert.match(
+    text,
+    /CI_COMMIT_SHA/,
+    '`verify` must compare the provider commit identity (CI_COMMIT_SHA)',
+  );
+  assert.match(text, /git rev-parse HEAD/, '`verify` must compare against git rev-parse HEAD');
+  assert.match(
+    text,
+    /exit 1/,
+    '`verify` must fail closed (exit 1) on identity mismatch or emptiness',
+  );
+}
+
+function assertCanonicalCommand(commands) {
+  assert.ok(
+    commands.some((command) => /^pnpm verify:release\b/.test(command.trim())),
+    '`verify` must run the canonical terminal verification command `pnpm verify:release`',
+  );
+}
+
+function assertPublishGate(pipeline) {
+  assert.ok(pipeline.steps, 'publish pipeline must define steps');
+
+  const commands = verifyCommands(pipeline);
+  assertCommitIdentityAssertion(commands);
+  assertCanonicalCommand(commands);
+
+  const effects = publishEffectSteps(pipeline);
+  assert.ok(effects.length > 0, 'publish pipeline must contain publish effect steps to guard');
+
+  for (const stepName of effects) {
+    const step = pipeline.steps[stepName];
+    assert.ok(
+      Array.isArray(step.depends_on) && step.depends_on.includes('verify'),
+      `publish effect '${stepName}' must depend DIRECTLY on the verify step (SDLC-D-034: transitively through build is not enough)`,
+    );
+    assert.ok(
+      dependencyClosure(pipeline, stepName).has('verify'),
+      `publish effect '${stepName}' must depend on a chain that includes verify`,
+    );
+  }
+  return effects;
+}
+
+test('the publish pipeline gates every publish effect behind exact-commit verification', async () => {
+  const pipeline = await readPublishPipeline();
+  const effects = assertPublishGate(pipeline);
+  assert.deepEqual(effects.sort(), [
+    'build-appservice',
+    'build-gateway',
+    'build-web',
+    'publish-next-npm',
+    'publish-npm',
+  ]);
+});
+
+test('the verify step carries no path/event short-circuit of its own', async () => {
+  const pipeline = await readPublishPipeline();
+  // A `when` filter on `verify` would let a publish effect fire on an event
+  // class that skipped verification — the gate must be unconditional.
+  assert.equal(pipeline.steps.verify.when, undefined);
+});
+
+test('a publish step that bypasses verify fails the gate checker', () => {
+  // Negative fixture: a plausible publish pipeline where `publish-npm` hangs
+  // off `build` only and `build` never chains to `verify` — the exact bypass
+  // class SDLC-D-034 closes. The checker must go red on it.
+  const bypassingPipeline = `
+steps:
+  install:
+    image: node:24-alpine
+    commands:
+      - pnpm install --frozen-lockfile
+  verify:
+    image: node:24-alpine
+    commands:
+      - |
+        if [ -z "$CI_COMMIT_SHA" ] || [ "$CI_COMMIT_SHA" != "$(git rev-parse HEAD)" ]; then
+          echo "identity mismatch" >&2
+          exit 1
+        fi
+      - pnpm verify:release
+    depends_on:
+      - install
+  build:
+    image: node:24-alpine
+    commands:
+      - pnpm build
+    depends_on:
+      - install
+  publish-npm:
+    image: node:24-alpine
+    commands:
+      - pnpm publish
+    depends_on:
+      - build
+`;
+  assert.throws(
+    () => assertPublishGate(parseYaml(bypassingPipeline)),
+    /publish-npm.*DIRECTLY.*verify/s,
+  );
+});
+
+test('a publish step chained to verify only transitively fails the gate checker', () => {
+  // Negative fixture: `build` depends on verify but `publish-npm` does not
+  // carry the direct edge — weaker than SDLC-D-034 requires of the real DAG.
+  const transitiveOnlyPipeline = `
+steps:
+  install:
+    image: node:24-alpine
+    commands:
+      - pnpm install --frozen-lockfile
+  verify:
+    image: node:24-alpine
+    commands:
+      - |
+        if [ -z "$CI_COMMIT_SHA" ] || [ "$CI_COMMIT_SHA" != "$(git rev-parse HEAD)" ]; then
+          echo "identity mismatch" >&2
+          exit 1
+        fi
+      - pnpm verify:release
+    depends_on:
+      - install
+  build:
+    image: node:24-alpine
+    commands:
+      - pnpm build
+    depends_on:
+      - install
+      - verify
+  publish-npm:
+    image: node:24-alpine
+    commands:
+      - pnpm publish
+    depends_on:
+      - build
+`;
+  assert.throws(
+    () => assertPublishGate(parseYaml(transitiveOnlyPipeline)),
+    /publish-npm.*DIRECTLY.*verify/s,
+  );
+});
+
+test('a verify step without the commit-identity assertion fails the gate checker', () => {
+  const noIdentityPipeline = `
+steps:
+  verify:
+    image: node:24-alpine
+    commands:
+      - pnpm verify:release
+  publish-npm:
+    image: node:24-alpine
+    commands:
+      - pnpm publish
+    depends_on:
+      - verify
+`;
+  assert.throws(() => assertPublishGate(parseYaml(noIdentityPipeline)), /CI_COMMIT_SHA/);
+});
+
+test('the canonical verify:release stages mirror the PR CI pipeline one-for-one', async () => {
+  const ci = parseYaml(await readFile(ciYmlPath, 'utf8'));
+  const canonical = Object.fromEntries(STAGES.map((stage) => [stage.name, stage.commands]));
+
+  // The complete mandatory set, in gate order.
+  assert.deepEqual(
+    STAGES.map((stage) => stage.name),
+    ['sanitization', 'upgrade-guard', 'typecheck', 'lint', 'format', 'test', 'build'],
+  );
+
+  // Guard stages: ci.yml commands minus its `apk add` environment prep must be
+  // exactly the canonical stage commands (order included).
+  for (const stageName of ['sanitization', 'upgrade-guard']) {
+    assert.deepEqual(
+      ci.steps[stageName].commands.filter((command) => !command.startsWith('apk add')),
+      canonical[stageName],
+      `canonical '${stageName}' stage must match the ci.yml step`,
+    );
+  }
+
+  // pnpm stages: ci.yml commands minus `corepack enable` must be exactly the
+  // canonical stage commands.
+  for (const stepName of ['typecheck', 'lint', 'format']) {
+    assert.deepEqual(
+      ci.steps[stepName].commands.filter((command) => command !== 'corepack enable'),
+      canonical[stepName],
+      `canonical '${stepName}' stage must match the ci.yml step`,
+    );
+  }
+
+  // The test stage is shared, but ci.yml wraps it in pipeline-level
+  // prerequisites the canonical command expects its caller to provide
+  // (SDLC-D-034): the postgres service + readiness wait + db:migrate, openssl,
+  // and the pinned pi runtime. None of those may be dropped silently.
+  for (const command of canonical.test) {
+    assert.ok(
+      ci.steps.test.commands.includes(command),
+      `ci.yml test step must run the canonical test stage command '${command}'`,
+    );
+  }
+  for (const fragment of [
+    'pg_isready -h ci-postgres',
+    'pnpm --filter @mosaicstack/db run db:migrate',
+    'npm install -g @earendil-works/[email protected]',
+  ]) {
+    assert.ok(
+      ci.steps.test.commands.some((command) => command.includes(fragment)),
+      `ci.yml test step must keep its pipeline-level prerequisite '${fragment}'`,
+    );
+  }
+});
+
+test('the root package.json exposes verify:release as the canonical command', async () => {
+  const packageJson = JSON.parse(await readFile(path.join(process.cwd(), 'package.json'), 'utf8'));
+  assert.match(packageJson.scripts['verify:release'], /scripts\/verify-release\.mjs/);
+});

tools/install.sh

@@ -309,6 +309,124 @@ require_cmd() {
   fi
 }
 
+# True if any shell rc file already puts $1 on PATH.
+#
+# Each file is tested for existence first and grepped one at a time, rather than
+# handed to a single `grep -qs ... "${rc_files[@]}"`. Handing grep a missing file
+# makes the exit status implementation-defined: GNU grep 3.11 returns 0 when -q
+# matched an earlier file, ugrep 7.5 returns 2 for the missing one regardless.
+# On the 2 path the caller reads "not present yet" and appends a duplicate PATH
+# line on every single install.
+path_entry_exists() {
+  local dir="$1" rc_file
+  for rc_file in "$HOME/.profile" "$HOME/.zshenv" "$HOME/.zshrc" "$HOME/.bashrc"; do
+    if [[ -f "$rc_file" ]] && grep -qF "$dir" "$rc_file"; then
+      return 0
+    fi
+  done
+  return 1
+}
+
+# Append `export PATH="$1:$PATH"` to the shell profile so $1 survives this
+# process. An `export` here reaches only the installer; every directory the
+# install leaves behind has to be written down somewhere a later shell reads.
+#
+# Deliberately NOT ~/.bashrc: Debian's default .bashrc returns early for
+# non-interactive shells, so a PATH line appended to the bottom of it is
+# unreachable to `bash -lc`, to systemd units, and to every agent seat — the
+# exact consumers that need these binaries. ~/.profile is read by login shells
+# and Debian's .profile sources .bashrc for interactive ones, so a single line
+# there reaches both. For zsh the always-sourced file is .zshenv, not .zshrc.
+#
+# $1 = directory to add, $2 = label for the comment line.
+# Returns 1 (having warned) if the profile could not be written.
+persist_on_path() {
+  local dir="$1" label="$2" profile
+
+  if path_entry_exists "$dir"; then
+    return 0
+  fi
+
+  if [[ -n "${ZSH_VERSION:-}" ]] || [[ "$(basename "${SHELL:-}")" == "zsh" ]]; then
+    profile="$HOME/.zshenv"
+  else
+    profile="$HOME/.profile"
+  fi
+
+  # Probe writability in a subshell. A redirection failure on a special built-in
+  # aborts the shell it runs in, so it has to be a child; and the redirection on
+  # the subshell is what silences the "Permission denied" the shell would
+  # otherwise print ahead of our own message.
+  if ! ( : >>"$profile" ) 2>/dev/null; then
+    warn "$dir is not on your PATH and $profile could not be written"
+    dim "  Add to your shell rc:  export PATH=\"$dir:\$PATH\""
+    return 1
+  fi
+
+  {
+    echo ""
+    echo "# $label"
+    echo "export PATH=\"$dir:\$PATH\""
+  } >>"$profile"
+  ok "Added $dir to PATH in $profile"
+  return 0
+}
+
+# Persist $PREFIX/bin on PATH instead of only warning about it.
+#
+# The warning it replaces was the last step of an otherwise successful install,
+# so the installer reported success and left `mosaic: command not found` — an
+# unattended install had no operator to read the advice and act on it.
+ensure_prefix_on_path() {
+  if [[ ":$PATH:" == *":$PREFIX/bin:"* ]]; then
+    return
+  fi
+
+  if path_entry_exists "$PREFIX/bin"; then
+    warn "$PREFIX/bin is in your shell profile but not in this shell"
+  elif ! persist_on_path "$PREFIX/bin" "Mosaic CLI"; then
+    return
+  fi
+  dim "  Run:  export PATH=\"$PREFIX/bin:\$PATH\"   (or start a new login shell)"
+}
+
+# Fleet transport binary (#1240).
+#
+# `mosaic fleet --help` reads "Manage the local Mosaic tmux fleet" and every
+# roster the CLI scaffolds sets `transport: tmux`, but nothing in this script
+# provides tmux and, until now, nothing in it mentioned tmux at all. A
+# greenfield host came out of this installer able to install a fleet, start a
+# fleet, and run no seat — the operator's first signal was `mosaic fleet ps`.
+#
+# Not a `require_cmd`: tmux is required by the fleet, not by mosaic. Plenty of
+# hosts install this to run `mosaic claude` and will never scaffold a roster,
+# and failing their install over a binary they do not need would be wrong. It
+# is a warning that names precisely what it blocks.
+#
+# `tools/_scripts/mosaic-doctor` carries a deliberately parallel check, so the
+# same host state gets the same answer from an audit as from an install. They
+# are separate implementations because this one has to work before the
+# framework's scripts are guaranteed to be on disk; keep their wording in step.
+check_fleet_transport() {
+  local transport=tmux
+  local roster="$MOSAIC_HOME/fleet/roster.yaml"
+  local declared=""
+
+  if [[ -f "$roster" ]]; then
+    declared="$(sed -n 's/^[[:space:]]*transport:[[:space:]]*//p' "$roster" | head -1 |
+      tr -d '"'\''' | tr -d '\r' | awk '{print $1}')"
+    [[ -n "$declared" ]] && transport="$declared"
+  fi
+
+  command -v "$transport" &>/dev/null && return 0
+
+  warn "Fleet transport '$transport' is not installed."
+  echo "  The Mosaic fleet runs its agent seats inside $transport. Without it,"
+  echo "  ${C}mosaic fleet start${RESET} reports success and no seat comes up."
+  echo "  Install it before using the fleet, e.g. ${C}sudo apt-get install -y $transport${RESET}"
+  echo "  (this does not affect ${C}mosaic claude${RESET} or the other single-runtime commands)."
+}
+
 installed_cli_version() {
   local json
   json="$(npm ls -g --depth=0 --json --prefix="$PREFIX" 2>/dev/null)" || true
@@ -516,8 +634,175 @@ install_next_cli_from_registry() {
   ok "Installed @next packages: CLI ${installed_cli}, gateway ${installed_gateway}"
 }
 
+# ─── node bootstrap ───────────────────────────────────────────────────────────
+#
+# Nothing on a greenfield host installs Node.js, yet this installer and the CLI
+# it installs both hard-require it. Measured on a clean Debian 13 image: the
+# installer stopped at `require_cmd node` with "Required command not found" and
+# nothing was installed, with no hint of how to proceed.
+#
+# Inlined rather than factored into a sibling file on purpose: this script is
+# fetched standalone by curl and has nothing to source.
+#
+# No-op when a suitable node is already on PATH, so it never fights an
+# operator's nvm/fnm/distro node.
+
+NODE_ROOT="${MOSAIC_NODE_ROOT:-$HOME/.mosaic/node}"
+NODE_BOOTSTRAP_VERSION="${MOSAIC_NODE_VERSION:-v22.23.2}"
+NODE_MIN_MAJOR="${MOSAIC_NODE_MIN_MAJOR:-20}"
+NODE_DIST_BASE="${MOSAIC_NODE_DIST_BASE:-https://nodejs.org/dist}"
+
+# Major version of the node at $1, or empty if it will not run.
+node_major_of() {
+  local candidate="$1" version
+  version="$("$candidate" -e 'process.stdout.write(process.versions.node)' 2>/dev/null)" || return 0
+  printf '%s' "${version%%.*}"
+}
+
+node_is_suitable() {
+  local major
+  major="$(node_major_of "$1")"
+  [[ -n "$major" ]] && [[ "$major" -ge "$NODE_MIN_MAJOR" ]]
+}
+
+install_node() {
+  local node_os node_arch tarball release_url work_dir extracted target node_bin
+
+  case "$(uname -s)" in
+    Linux)  node_os="linux" ;;
+    Darwin) node_os="darwin" ;;
+    *) fail "Unsupported OS '$(uname -s)'. Install Node.js >= $NODE_MIN_MAJOR manually."; return 1 ;;
+  esac
+
+  # Linux here means glibc. Node's official linux-x64 build is dynamically
+  # linked against glibc, so on musl (Alpine) the binary will not exec — but it
+  # fails visibly: node_is_suitable rejects it and ensure_node exits with
+  # "install Node.js manually". No silent breakage, just a wasted download.
+  # A musl host needs the unofficial build, which is out of scope here.
+  case "$(uname -m)" in
+    x86_64|amd64)  node_arch="x64" ;;
+    aarch64|arm64) node_arch="arm64" ;;
+    armv7l)        node_arch="armv7l" ;;
+    *) fail "Unsupported architecture '$(uname -m)'. Install Node.js >= $NODE_MIN_MAJOR manually."; return 1 ;;
+  esac
+
+  # .tar.gz rather than the smaller .tar.xz: gzip is universally present, xz is
+  # not, and a minimal image is exactly the case this exists to handle.
+  tarball="node-${NODE_BOOTSTRAP_VERSION}-${node_os}-${node_arch}.tar.gz"
+  release_url="${NODE_DIST_BASE}/${NODE_BOOTSTRAP_VERSION}"
+
+  work_dir="$(mktemp -d "${TMPDIR:-/tmp}/mosaic-node-XXXXXX")"
+
+  info "Installing Node.js $NODE_BOOTSTRAP_VERSION ($node_os-$node_arch) to $NODE_ROOT…"
+
+  if ! curl -fsSL "${release_url}/${tarball}" -o "$work_dir/$tarball"; then
+    fail "Download failed: ${release_url}/${tarball}"
+    rm -rf "$work_dir"; return 1
+  fi
+
+  # Trust assumption, stated so nobody has to infer it: this verifies INTEGRITY
+  # (the tarball matches the manifest), not AUTHENTICITY (the manifest is
+  # genuinely Node's). The only thing establishing that is TLS to
+  # $NODE_DIST_BASE. Node publishes SHASUMS256.txt.sig signed by its release
+  # keys and we do not check it, which is on par with nvm but means pointing
+  # MOSAIC_NODE_DIST_BASE at an untrusted mirror has no signature backstop.
+  # Tracked as a hardening follow-up (raised by scooby in the #1229 review).
+  if ! curl -fsSL "${release_url}/SHASUMS256.txt" -o "$work_dir/SHASUMS256.txt"; then
+    fail "Could not fetch SHASUMS256.txt; refusing to install an unverified runtime."
+    rm -rf "$work_dir"; return 1
+  fi
+
+  # Keep only our artifact's line, so a missing entry is an error not a pass.
+  if ! grep " ${tarball}\$" "$work_dir/SHASUMS256.txt" >"$work_dir/expected.sha256"; then
+    fail "$tarball has no entry in SHASUMS256.txt; refusing to install."
+    rm -rf "$work_dir"; return 1
+  fi
+
+  if ! (cd "$work_dir" && verify_sha256 expected.sha256); then
+    fail "Checksum mismatch for $tarball; refusing to install."
+    rm -rf "$work_dir"; return 1
+  fi
+  ok "Checksum verified"
+
+  tar xzf "$work_dir/$tarball" -C "$work_dir"
+  extracted="$work_dir/node-${NODE_BOOTSTRAP_VERSION}-${node_os}-${node_arch}"
+  if [[ ! -x "$extracted/bin/node" ]]; then
+    fail "Extracted archive has no bin/node"
+    rm -rf "$work_dir"; return 1
+  fi
+
+  mkdir -p "$NODE_ROOT"
+  target="$NODE_ROOT/$NODE_BOOTSTRAP_VERSION"
+  rm -rf "$target.incoming"
+  mv "$extracted" "$target.incoming"
+  rm -rf "$target"
+  mv "$target.incoming" "$target"
+  ln -sfn "$NODE_BOOTSTRAP_VERSION" "$NODE_ROOT/current"
+  rm -rf "$work_dir"
+
+  node_bin="$NODE_ROOT/current/bin"
+  if ! node_is_suitable "$node_bin/node"; then
+    fail "Installed node at $node_bin/node did not run"
+    return 1
+  fi
+
+  export PATH="$node_bin:$PATH"
+  ok "Node.js $(node -v) installed with npm $(npm -v 2>/dev/null || echo '?')"
+  return 0
+}
+
+# Make the Mosaic-managed Node reachable from the next shell as well as this
+# one. Measured on a greenfield canary run: without this the install finished
+# rc=0, wrote $PREFIX/bin to ~/.profile, and the next login shell found `mosaic`
+# and then died on `env: 'node': No such file or directory` — the CLI is a Node
+# script, so a CLI on PATH without its runtime is a successful install that
+# produces a broken command.
+persist_node_on_path() {
+  persist_on_path "$NODE_ROOT/current/bin" "Mosaic-managed Node.js" || true
+}
+
+ensure_node() {
+  if command -v node &>/dev/null && node_is_suitable node; then
+    return 0
+  fi
+
+  # A previous run may have installed one that is not on this shell's PATH.
+  if node_is_suitable "$NODE_ROOT/current/bin/node"; then
+    export PATH="$NODE_ROOT/current/bin:$PATH"
+    persist_node_on_path
+    return 0
+  fi
+
+  if [[ "${MOSAIC_SKIP_NODE_BOOTSTRAP:-0}" == "1" ]]; then
+    fail "No suitable Node.js and MOSAIC_SKIP_NODE_BOOTSTRAP=1; refusing to download."
+    echo "  Install Node.js >= $NODE_MIN_MAJOR yourself, then re-run this script."
+    exit 1
+  fi
+
+  require_cmd curl
+  require_cmd tar
+
+  # sha256sum on Linux, shasum on macOS. Verification is not optional: without a
+  # checksum this would install an unauthenticated runtime.
+  if command -v sha256sum &>/dev/null; then
+    verify_sha256() { sha256sum -c --status "$1"; }
+  elif command -v shasum &>/dev/null; then
+    verify_sha256() { shasum -a 256 -c --status "$1"; }
+  else
+    fail "sha256sum or shasum required to verify the Node.js download"
+    exit 1
+  fi
+
+  if ! install_node; then
+    fail "Could not bootstrap Node.js. Install Node.js >= $NODE_MIN_MAJOR and re-run."
+    exit 1
+  fi
+  persist_node_on_path
+}
+
 # ─── preflight ────────────────────────────────────────────────────────────────
 
+ensure_node
 require_cmd node
 require_cmd npm
 
@@ -682,11 +967,7 @@ if [[ "$FLAG_CLI" == "true" ]]; then
     ensure_monorepo
     install_cli_from_source
 
-    # PATH check for npm prefix
+    ensure_prefix_on_path
-    if [[ ":$PATH:" != *":$PREFIX/bin:"* ]]; then
-      warn "$PREFIX/bin is not on your PATH"
-      dim "  Add to your shell rc:  export PATH=\"$PREFIX/bin:\$PATH\""
-    fi
   elif is_next_registry_lane; then
     info "Next mode — trying fast npm @next install from ${REGISTRY}…"
     if install_next_cli_from_registry; then
@@ -699,11 +980,7 @@ if [[ "$FLAG_CLI" == "true" ]]; then
       export MOSAIC_GATEWAY_SKIP_NPM_INSTALL=1
     fi
 
-    # PATH check for npm prefix
+    ensure_prefix_on_path
-    if [[ ":$PATH:" != *":$PREFIX/bin:"* ]]; then
-      warn "$PREFIX/bin is not on your PATH"
-      dim "  Add to your shell rc:  export PATH=\"$PREFIX/bin:\$PATH\""
-    fi
   else
     if [[ -z "$LATEST" ]]; then
       warn "Could not reach registry at $REGISTRY — skipping npm CLI."
@@ -721,11 +998,7 @@ if [[ "$FLAG_CLI" == "true" ]]; then
       ok "CLI is at or ahead of registry ($CURRENT ≥ $LATEST)."
     fi
 
-    # PATH check for npm prefix
+    ensure_prefix_on_path
-    if [[ ":$PATH:" != *":$PREFIX/bin:"* ]]; then
-      warn "$PREFIX/bin is not on your PATH"
-      dim "  Add to your shell rc:  export PATH=\"$PREFIX/bin:\$PATH\""
-    fi
   fi
 fi
 
@@ -870,6 +1143,11 @@ if [[ "$FLAG_CHECK" == "false" ]]; then
   ok "Done."
 fi
 
+# Fleet readiness (#1240). Runs in both normal and --check mode: "what is the
+# state of this host" is exactly the question --check is asked, and a host that
+# cannot run a seat should not have to discover it from `fleet ps`.
+check_fleet_transport
+
 } # end main
 
 main "$@"