Merge commit '28ee61bf62c3c99a845c97540570401a47bd6aa3' into torch/session-manager

.torch/prompts/COMMON.md

@@ -6,7 +6,10 @@ Repository state outranks conversation memory. Query ownership before crossing a
 
 This initial launch is a bounded installation and communications smoke test.
 Use the installed `torch` launcher and identity-bound TORCH MCP tools. Query
-identity, ownership, inbox and next backlog item. Read current canonical
+identity, ownership and inbox. Specialists query their next backlog item;
+the Session Manager inspects fleet backlog rather than claiming specialist work.
+Run `torch brief --area <your-area> --json` at startup and before each new item.
+Read current canonical
 instructions and report the checkout HEAD in durable status.
 
 Do not implement code, create or assign development tasks, enable timers,

.torch/prompts/session-manager.md

@@ -6,6 +6,14 @@ At startup and when recurring cross-domain friction appears, run `torch_assess_h
 
 ## Backlog loop
 
+The owner has seeded conversation follow-up as `TASK-conversation-*` proposals
+in this project's existing backlog. Read `docs/TODO.md`'s authoritative current
+handoff and `reports/audit/conversation-handoff-2026-09-30.md` before prioritizing.
+Proposed tasks are not ready assignments. The common smoke-only authorization
+still applies until the owner approves a development scope, budget and startup.
+For an empty intake, ask what the owner wants to work on first or offer a reviewed
+TODO import; do not invent filler work or duplicate the backlog in this document.
+
 Keep one durable Fleet backlog. Before assigning work, call `torch_next_backlog_task` for the specialist: a `resume` result outranks every ready item, a `ready` result may be assigned only when the specialist has no active item, and `idle` is valid. After completion, repeat the same lookup. Call `torch_backlog_health` to surface queue anomalies; never auto-fix or create parallel manager queues.
 
 ## Fleet evolution

README.md

@@ -292,14 +292,28 @@ Review the evidence in `fleet-proposal.json`, edit its `review.status` to
 node bin/torch.mjs install --proposal fleet-proposal.json --runtime codex --dry-run --json
 node bin/torch.mjs install --proposal fleet-proposal.json --runtime codex --yes --json
 node bin/torch.mjs doctor --json
-node bin/torch.mjs worktrees --dry-run --json
-node bin/torch.mjs worktrees --yes --json
+node bin/torch.mjs setup --dry-run --json
+node bin/torch.mjs setup --yes --json
 node bin/torch.mjs up --fresh --dry-run --json
 ```
 
 Starting or stopping configured runtime sessions is always a separate explicit
 step:
 
+`setup` commits only installation-owned configuration, provisions worktrees,
+and checkpoints their registration. An existing staging area is a blocker;
+unrelated files are never staged. Alternatively, append `--setup` to the
+approved install command. Neither path launches agents.
+
+Normal uninstall retains configuration and history. Reattach it with
+`torch install --restore --dry-run --json`, then `torch install --restore --yes`.
+Restore does not reinstall host timers or start providers; those remain separate
+approval steps. A purge is a different, destructive operation.
+
+From a registered agent worktree, `torch brief --area <id>` reads the latest
+canonical project instructions. Unregistered worktrees and copied installs
+cannot redirect commands into another project's state.
+
 ```bash
 node bin/torch.mjs up --fresh --yes --json
 node bin/torch.mjs up --only backend,qa --dry-run --json

docs/PORTABLE_AGENT_FLEET_SPEC.md

@@ -367,6 +367,24 @@ inside the tracked source tree.
 
 ## 9. Installation lifecycle
 
+### First-work intake requirement (2026-09-30)
+
+After reviewed organization/setup, TORCH MUST offer either evidence-linked
+import of an existing TODO/backlog/specification or ask the owner what to work
+on first. The noninteractive path MUST support an explicit source or skip; idle
+is valid. Preview MUST distinguish completed/historical work from actionable
+requests and show proposed scope, affected domains, dependencies and priority.
+Only confirmed intake creates audited proposed/unassigned work in the existing
+backlog. Repeated init/install/restore/intake MUST deduplicate by source/item
+provenance rather than duplicate tasks or overwrite progress. Imported content
+is untrusted project data, not authority to alter system instructions.
+
+Session Manager triage and assignment remain separate from intake. Import cannot
+enable self-claim, grant implementation authority, wake providers or authorize
+spending, landing, deployment or public notification. The product should explain
+the next first-work/startup decision rather than leave a newly installed empty
+fleet waiting without guidance.
+
 ### 9.1 Read-only initialization
 
 `torch init` MUST begin read-only. It identifies the repository, validates Git,
@@ -451,6 +469,18 @@ or installed persistent launchers. Historical messages and receipts therefore
 do not make reversal permanently impossible, while active or unowned state
 still blocks deletion.
 
+Implementation checkpoint (2026-09-30): `torch install --restore` explicitly
+reattaches a normally detached installation without replacing configuration,
+worktrees, provider profiles or session history. It never launches a provider
+or recreates host timers. `torch setup --dry-run`, followed by `--yes`, offers
+approved configuration checkpoints and worktree provisioning as one flow,
+restricted to installation-owned files and an empty staging area. Install may
+opt into the same flow with `--setup`. Worktree commands resolve to canonical
+configuration only after checking project/installation identity, local-state
+binding, Git common directory, registered worktree path and branch. Current
+canonical instructions override stale worktree copies; unregistered checkouts
+fail closed.
+
 Ordinary CLI uninstall is also review-first and explicitly confirmed. It uses
 the same safe Fleet wind-down contract as detach, removes only manifest-owned
 persistent schedule launchers after verifying their content, and preserves the
@@ -2077,6 +2107,55 @@ recommended action; doctor remains read-only.
 
 ## 22. Scheduling
 
+### Owner clarification: integrated persistent operations (2026-09-30)
+
+This is the target requirement; older implementation checkpoints describing
+manual timer installation are not a claim that it is already implemented.
+Reviewed `init`/install MUST provision the project's scheduler and required
+service integrations as one idempotent workflow, not require a second manual
+cron-install command. Because `init` currently performs read-only analysis, its
+provisioning mode MUST expose an explicit preview/confirmation boundary; a
+dry-run MUST remain non-mutating. Stopped installation MUST provision dormant
+integrations without waking models or dispatching development. A reviewed
+activation policy governs live operations and quota use.
+
+Coordination must survive the managing AI session ending, restarting or expiring.
+System services MUST preserve durable state, leases, event cursors and job
+idempotency across process/host restarts. Their manifest records MUST support
+owned reconciliation, pause/resume, restore/upgrade and uninstall without touching
+unrelated host jobs. Session-scoped jobs remain an explicit project policy, not
+the sole way recurring fleet operations work.
+
+Project intake MUST propose applicable capabilities, with clear implemented,
+unconfigured and unsupported states:
+
+- direct-report manager check-ins, structured approval/peer/owner waits,
+  stale owner-request review and an owner-first local digest;
+- a persistent, serialized landing worker using approved exact-commit checks;
+- resource-queue watchdogs, audited slot withdrawal and displaced-runner stop;
+- durable significant events and deduplicated budgeted manager wakes, with
+  low-frequency timed safety checks rather than perpetual paid polling;
+- a project-declared nightly canonical suite, heavy-check windows and
+  evidence-backed regression routing, not guessed blame;
+- measured test durations, uncertain wait estimates and project-specific
+  exclusive resources such as a GPU;
+- conservative provider-neutral usage limits, graceful wind-down and explicitly
+  approved credit-window or calendar restarts that never override manual pause;
+- idle, clean, unguarded worktree convergence by merge, preserving conflicts,
+  unique commits and active work;
+- exact landed task closure, verified reversal/follow-up policy and reviewed
+  evidence for finished-but-unnamed work, never automatic closure by message alone;
+- project-specific local dev/Console services and separately authorized delivery,
+  live-version checks and external notifications where relevant.
+
+No universal project inherits COMBATRIG's release times, Monday reset time,
+two GPU slots, Vercel destination, phone notifier or LAN/HTTPS exposure. Setup
+MUST show lifetime, timezone/DST behavior, missed-run policy, costs/budgets,
+ports/destinations, health evidence, stop semantics and owner authority. Unsupported
+hosts/adapters need an actionable limitation or qualified fallback, not a fictitious
+"installed" status. No provider wake, deploy, public message, off-machine write
+or cleanup of unowned processes follows solely from creating a schedule.
+
 TORCH recognizes two schedule classes.
 
 **System schedules** survive AI sessions and may perform approved release,

docs/TEST_INTEGRITY.md

@@ -2237,3 +2237,34 @@ test_integrity_note:
     did_relax_any_assertion: false
     if_true_explain_spec_basis: ""
 ```
+# Setup and canonical worktree briefs (2026-09-30)
+
+```yaml
+test_integrity_note:
+  change_type: new_tests
+  scenarios:
+    - id: SCN-guided-setup
+      given: "An approved installed project with uncommitted TORCH files"
+      when: "Owner reviews and authorizes setup"
+      then: "Only owned files are committed; registered worktrees exist; no providers start; staged user work blocks setup"
+    - id: SCN-worktree-canonical-brief
+      given: "A registered worktree has older instructions"
+      when: "Its installation root is resolved and a brief requested"
+      then: "Canonical instructions appear; unregistered worktrees, copied installs and stale installation IDs fail closed"
+    - id: SCN-install-restore
+      given: "A normally detached project retains configuration and worktree commits"
+      when: "Owner explicitly restores the install"
+      then: "Binding is reattached without changing profiles, worktree history or launching providers"
+  observable_outcomes:
+    - "Git commits, clean canonical checkout, worktree registrations, brief text and local detach metadata"
+  determinism_controls:
+    - "Isolated temporary Git repositories and XDG state; no provider or network calls"
+  anti_cheat_rationale:
+    prevents:
+      - "Hard-coded success without Git worktrees or commits"
+      - "Accepting copied or unregistered installation state"
+      - "Staging unrelated owner work"
+  relaxation:
+    did_relax_any_assertion: false
+    if_true_explain_spec_basis: ""
+```

docs/TODO.md

@@ -1,5 +1,64 @@
 # TORCH remaining work
 
+## Authoritative current handoff (2026-09-30, after alpha.2 reinstall)
+
+TORCH is installed and healthy at `0.1.0-alpha.2`. Setup/restore and all seven
+worktree briefs have been verified. The active organization is Session Manager
+plus six specialists; all providers are offline. The default Git branch remains
+legacy TORCH; the configured development/integration boundary is
+`rewrite/portable-agent-fleet`. No publication or default-branch promotion is
+authorized. Later sections retain historical audit snapshots, including old
+"uncommitted/no launcher" statements; those are superseded by this handoff.
+
+The conversation's unfinished work is now owner-proposed in the **existing
+authoritative backlog in the Session Manager worktree**, not a second TODO queue.
+Use `torch backlog list --json` to see it from any registered checkout. Tasks use
+the `TASK-conversation-` prefix, have acceptance criteria, affected domains and
+dependencies, and remain unassigned for manager triage. See
+`reports/audit/conversation-handoff-2026-09-30.md` for the domain review and index.
+
+### New owner requirements: first work and automatic operations
+
+- [ ] `TASK-conversation-first-work-intake`: init/install/setup offers reviewed
+  TODO/backlog import or asks what the owner wants to begin with; previews and
+  confirms proposed tasks; deduplicates resumes; never activates stale/completed
+  TODOs or launches agents silently.
+- [ ] `TASK-conversation-persistent-operations`: reviewed init/install provisions
+  machine-level scheduler/services automatically, not merely schedule JSON or a
+  separate manual cron-install command. Paused installs remain dormant. Services
+  declare system/session lifetimes, budgets, timezone, restart/missed-run policy,
+  pause/resume and manifest-owned uninstall/restore behavior. This extends the
+  earlier `TASK-conversation-automatic-scheduler` requirement.
+- [ ] `TASK-conversation-event-driven-wakes`: durable deduplicated significant
+  events wake the appropriate manager under budget; periodic checks are the quiet
+  safety net, not repeated usage-consuming busywork.
+- [ ] `TASK-conversation-queue-watchdog`: detect stuck resource queues and
+  disappearing slots, audit removals and stop displaced waiters; never infer
+  browser ownership/termination from a process name or runner death.
+- [ ] `TASK-conversation-nightly-main-tests`: project-declared full canonical
+  suite on an exact frozen commit, resource-aware idle window and evidence-backed
+  regression routing. Do not guess the offending change.
+- [ ] `TASK-conversation-usage-governor`: provider-neutral usage/credit evidence,
+  conservative fallback budgets, graceful wind-down and reviewed reset/restart
+  policy that cannot override manual pause or detach.
+- [ ] `TASK-conversation-idle-worktree-refresh`: scheduled merges into clean,
+  idle, unguarded branches; skip active/dirty/unknown work and preserve conflicts.
+- [ ] `TASK-conversation-queue-planning`: measured test durations, uncertain wait
+  estimates, slowdown visibility, GPU-exclusive resources and approved heavy-run
+  windows; preserve the resource queue's authority.
+- [ ] `TASK-conversation-closure-revert-review`: verified revert/follow-up policy
+  and evidence-backed review of unnamed finished work; never mass-close or reopen
+  tasks based only on untrusted commit trailers.
+- [ ] `TASK-conversation-project-services`: reviewed project-specific landing
+  worker, local dev/Console server, local summary and optional release jobs.
+  No COMBATRIG schedules, Vercel deployment, credentials, LAN exposure or automatic
+  phone notifications are assumed.
+
+These are proposed development tasks, **not implemented automatic setup**. The
+existing 15-minute manager schedule is configured, but no TORCH host timer is
+installed. Common instructions still authorize only the smoke test; development
+activation, self-claim and recurring provider wakes remain separately reviewed.
+
 ## First real self-host run (2026-09-30)
 
 ### Portable production pipelines (new roadmap element)
@@ -37,7 +96,7 @@
   updates, retained previous installs, offline previews and fail-closed errors.
   Four deterministic scenarios added; live download qualification recorded in
   the first-run audit, not implied by mocked installer tests.
-- [ ] Fix `torch brief` invoked from a managed worktree: both live sessions hit
+- [x] Fix `torch brief` invoked from a managed worktree: both live sessions hit
   `LOCAL_STATE_METADATA_MISMATCH`. Resolve canonical project binding with
   checked worktree membership, never weaken root/installation identity checks.
 - [ ] Surface Codex JSON stdout failure events: first Sol launch hid the actual
@@ -45,7 +104,7 @@
 - [ ] Add exact executable/version/model/auth preflight to owner Console and
   setup flow. PATH selected CLI 0.158.0 while the current session used 0.159.2;
   the older child rejected Sol 6.1 and required manual investigation/retry.
-- [ ] Make configuration checkpoint/worktree/manifest handoffs explicit or
+- [x] Make configuration checkpoint/worktree/manifest handoffs explicit or
   guided: generated tracked files and provisioning manifest updates require
   deliberate commits; a healthy doctor does not prove startup readiness.
 - [ ] Isolate irrelevant inherited global MCP servers without removing user
@@ -349,7 +408,7 @@ in `reports/audit/self-host-readiness-2026-09-30.md`. No agent or timer was star
   the collapsed panel; observation never releases a launch lock.
 - [ ] Qualify interrupted-wake recovery against live runtime lifecycle evidence;
   owner attestation is explicit but is not independent proof of termination.
-- [ ] Qualify the updated source as a clean commit before self-host activation;
+- [x] Qualify the updated source as a clean commit before self-host activation;
   older artifact receipts predate these changes. No fleet or timer has started.
 
 Review verification (2026-09-30): full regression suite through isolated
@@ -961,7 +1020,7 @@ COMBATRIG's proposed hierarchy as the default.
   multi-domain coordination/resume scenario with a fixed provider budget.
 - [ ] Install and reverse the user-systemd scheduler, verifying one real
   dispatch and its receipts.
-- [ ] Install an accepted TORCH version in user-local versioned state and use
+- [x] Install an accepted TORCH version in user-local versioned state and use
   its stable launcher to manage this source checkout.
 - [ ] Resolve COMBATRIG's 56 ownership/exclusion blockers, then separately
   authorize an import/cutover trial. Do not mutate COMBATRIG beforehand.

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "torch-agent-fleet",
-  "version": "0.1.0-alpha.1",
+  "version": "0.1.0-alpha.2",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "torch-agent-fleet",
-      "version": "0.1.0-alpha.1",
+      "version": "0.1.0-alpha.2",
       "bundleDependencies": [
         "@modelcontextprotocol/server",
         "typebox",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "torch-agent-fleet",
-  "version": "0.1.0-alpha.1",
+  "version": "0.1.0-alpha.2",
   "type": "module",
   "description": "TORCH — a portable, provider-independent AI development fleet for Git repositories",
   "main": "src/cli.mjs",

reports/audit/conversation-handoff-2026-09-30.md

@@ -0,0 +1,90 @@
+# TORCH conversation-to-fleet handoff
+
+## Installed domains
+
+The installed organization is appropriately scoped to this repository: one
+Session Manager and six specialists. A current read-only ownership query over
+129 tracked files under `src`, `bin`, `site`, `schemas`, `scripts` and `test`
+found zero unowned files and zero duplicate primary owners. This claim does not
+cover every historical report or future new directory.
+
+| Domain | Responsibility | Effective Codex model |
+| --- | --- | --- |
+| Session Manager | Routing, ownership, priority and fleet health | GPT-6.1 Sol high |
+| Project Kernel | Bootstrap, identity, canonical instructions and organization | GPT-5.6 Terra high |
+| Provider Runtime | Harnesses, MCP, lifecycle, schedules and telemetry | GPT-5.6 Terra high |
+| Work and Integration | Backlog, checks, resources, landing and recovery | GPT-5.6 Terra high |
+| Owner Console | Dashboard, artifacts, feedback and observability | GPT-6 Luna high |
+| Release and Self-host | CLI, package, candidates, upgrades and removal | GPT-6 Luna high |
+| Independent QA | Scenario integrity and real qualification | GPT-5.6 Terra high |
+
+The six-role grouping was a reviewed consolidation of repository evidence,
+not a copy of COMBATRIG's specialists and not proof of a fully autonomous AI
+Architect first-run. Proposed extra domain leads are inactive. Headcount alone
+does not justify adding managers. Significant pipeline work may justify different
+model effort or a new domain later, through the existing review path.
+
+## Authoritative backlog
+
+Owner-request intake created 34 proposed, unassigned items in the existing
+Session Manager worktree backlog. There are 33 current follow-ups plus the
+earlier narrower `automatic-scheduler` request, retained for manager triage
+against the newer `persistent-operations` requirement rather than silently
+deleted. All have acceptance criteria, affected domains and observed commit
+binding; dependent slices reference existing task IDs. No assignment, provider
+start, self-claim enabling or host service installation occurred.
+
+Run `torch backlog list --json` from any registered checkout. The canonical
+backlog service resolves the manager's tracked ledger; do not create a second
+copy in the source checkout. Task IDs below are prefixed `TASK-conversation-`.
+
+| Group | Task suffixes |
+| --- | --- |
+| First work / readiness | `first-work-intake`, `development-activation`, `selfhost-development-trial` |
+| Persistent operations | `persistent-operations`, `automatic-scheduler`, `event-driven-wakes`, `queue-watchdog`, `nightly-main-tests`, `usage-governor`, `idle-worktree-refresh`, `queue-planning`, `project-services` |
+| Provider reliability | `runtime-diagnostics`, `startup-preflight`, `mcp-isolation`, `update-startpaths`, `mixed-provider-qualification` |
+| Pipelines | `pipeline-definitions`, `pipeline-provenance`, `pipeline-flow`, `pipeline-stalls`, `pipeline-console`, `pipeline-metrics`, `pipeline-pilot` |
+| Live qualification | `hierarchy-pilot`, `scheduler-qualification`, `browser-portability`, `landing-closure`, `closure-revert-review`, `delivery-qualification` |
+| Owner/product/release | `owner-digest`, `console-workflow`, `documentation-current`, `release-qualification` |
+
+## What is not yet automatic
+
+Setup and retained-state restore have been qualified; installed alpha.2 is
+healthy. All agents remain offline. The current manager schedule declares a
+15-minute interval, but no TORCH-owned systemd units are installed or active.
+Read-only host timer enumeration confirmed no TORCH timer; unrelated Archive
+timers were untouched. The owner's latest request is that init/install provision
+these integrations automatically. That is now an explicit target in specification
+section 22 and the backlog, not an already delivered feature.
+
+The shared common prompt still authorizes only an installation smoke test and
+the project self-claim policy is disabled. Starting agents under it does not
+authorize development. The manager should read and triage proposed work, recommend
+a first bounded slice and budget, and obtain the development/startup approval
+before delegation. New installs should offer reviewed TODO import or ask the
+owner what they want first; repeated intake must deduplicate rather than queue
+every historical checkbox.
+
+## Suggested first implementation sequence
+
+1. First-work intake and persistent operations planning/provisioning: make
+   the product's installation genuinely complete while stopped until ready.
+2. Runtime diagnostics and exact launch preflight: make startup failures legible.
+3. Separately approved bounded self-host development, landing/closure and
+   scheduler qualification, followed by persistent event/watchdog/nightly work.
+4. Pipeline definitions, immutable provenance, checked transitions and Console.
+5. Finish mixed-provider, organization-growth and release qualification.
+
+There is no authorization here to promote the rewrite to default `main`, deploy
+the public website, send notifications, alter COMBATRIG, spend on asset generation
+or install active recurring AI wakes. Those boundaries remain in the task criteria.
+
+## Validation
+
+Installed `torch backlog list` sees all 34 items. Acceptance criteria and domains
+are populated; every dependency exists and the dependency graph is acyclic.
+Installed `torch backlog health` reports healthy with no anomalous assignments.
+Its bounded historical activity coverage remains incomplete, correctly labelled
+unknown rather than proof of inactivity. Existing backlog/scheduling regression
+suite: 23/23 PASS. All seven identities remain offline. These are backlog/spec
+changes, not implementation of the newly requested onboarding or automation.

reports/audit/setup-reinstall-2026-09-30.md

@@ -0,0 +1,59 @@
+# Guided setup and reinstall verification
+
+## Changes
+
+- `torch brief` and normal installed-project CLI commands resolve registered
+  worktrees to the canonical project. The resolver checks project and installation
+  IDs, XDG state binding, Git common directory, worktree membership and branch.
+  Current canonical instructions win over an old worktree copy.
+- `torch setup --dry-run`, then `--yes`, checkpoints owned configuration,
+  provisions worktrees and checkpoints registration. Existing staged work is
+  rejected; unrelated files are not staged. Install can opt in with `--setup`.
+- `torch install --restore` reattaches the retained state from normal uninstall.
+  It does not overwrite profiles, erase history, recreate timers or start agents.
+- The self-host smoke brief distinguishes manager backlog inspection from
+  specialist next-task lookup and explicitly requires current briefs.
+
+## Evidence before installation
+
+All 39 source acceptance groups, lint and syntax: PASS.
+Receipt: `/tmp/torch-alpha2-source-acceptance.json`.
+New scenarios: guided setup, canonical worktree briefs, safe detach/restore.
+The actual Owner Console worktree returned its current brief successfully
+through the patched source CLI, including its preserved offline runtime ID.
+
+## Installation trial
+
+Accepted alpha.2 source: `c11754ab18fa690355ead3f6f87b3accb2975153`.
+Candidate digest: `d4b6ba38a51cc1804047b175c963806850f017a92d88863d187043314414dd90`.
+All 39 acceptance groups passed again from the copied candidate. Active version
+is `0.1.0-alpha.2`; rollback retains alpha.1.
+
+Normal uninstall: PASS. Retained-state restore: PASS. All seven actual agent
+worktrees returned briefs through `/home/user/.local/bin/torch`: PASS. Their
+briefs include the updated canonical smoke instructions despite older worktree
+copies. Model configuration hash, project/installation IDs, offline states,
+saved Codex runtime IDs and all seven branch tips were unchanged across
+uninstall/restore. No provider was launched.
+
+The restored project's `torch setup --yes --json` was a no-op: no commits,
+no mutations, no sessions started. Final doctor reports healthy. Modified owned
+configuration and unique manager history remain legitimate safety warnings,
+not authorization to purge. Uninstall refreshed the manager resume brief;
+that generated file was separately checkpointed on its existing branch, without
+rewriting prior history or landing anything.
+
+Receipts:
+
+- `/tmp/torch-alpha2-candidate-build.json`
+- `/tmp/torch-alpha2-uninstall-plan.json`
+- `/tmp/torch-alpha2-uninstall-result.json`
+- `/tmp/torch-alpha2-restore-result.json`
+- `/tmp/torch-alpha2-reinstall-verification.json`
+- `/tmp/torch-alpha2-real-setup-result.json`
+- `/tmp/torch-alpha2-real-doctor.json`
+
+This tests retained-state reinstall, not destructive purge or a fresh installation
+with discarded configuration. New-install setup is covered by isolated real-Git
+regression tests. Provider-authentication and new agent launches were deliberately
+not repeated. Host timers remain uninstalled.

src/cli.mjs

@@ -24,6 +24,8 @@ import { diagnoseProject } from './kernel/doctor.mjs';
 import { loadProjectConfig, validateProjectConfig } from './kernel/config.mjs';
 import { asErrorRecord, TorchError } from './kernel/errors.mjs';
 import { inspectRepository } from './kernel/git.mjs';
+import { resolveInstalledProjectRoot } from './kernel/project-root.mjs';
+import { setupProject, restoreProject } from './kernel/setup.mjs';
 import { inspectSpecifications } from './kernel/specifications.mjs';
 import { installProject, planInstall, uninstallProject } from './kernel/install.mjs';
 import { IntegrationService } from './integration/service.mjs';
@@ -72,6 +74,8 @@ Usage:
   torch domains [--repo <path>] [--spec <path>] [--output <path>] [--json]
   torch install --proposal <path> [--runtime <adapter,adapter>] [--default-runtime <adapter>] [--update-runtimes] [--dry-run] [--yes] [--json]
   torch worktrees [--parent <path>] [--dry-run] [--yes] [--json]
+  torch install --restore [--dry-run] [--yes] [--json]
+  torch setup [--parent <path>] [--dry-run] [--yes] [--json]
   torch up [--fresh] [--only <id,id>] [--dry-run] [--yes] [--json]
   torch down [--dry-run] [--yes] [--json]
   torch capture [--json]
@@ -414,7 +418,7 @@ export const CANDIDATE_ACCEPTANCE_EVIDENCE = Object.freeze({
   'forge-migration': ['SCN-forge-migration'],
   'delivery-lifecycle': ['SCN-delivery-lifecycle', 'SCN-delivery-attempts', 'SCN-delivery-retry-boundaries', 'SCN-delivery-succeeded-recovery',
     'SCN-owner-digest', 'SCN-owner-digest-schedule', 'SCN-owner-digest-receipts'],
-  'review-install-roster': ['SCN-cli-domain-review', 'SCN-cli-install-provider-default', 'SCN-install-provider-inheritance'],
+  'review-install-roster': ['SCN-cli-domain-review', 'SCN-cli-install-provider-default', 'SCN-install-provider-inheritance', 'SCN-guided-setup'],
   'branches-worktrees': ['SCN-worktree-bootstrap'],
   'runtime-identities': ['SCN-mixed-runtime'],
   'runtime-profiles': ['SCN-runtime-profiles', 'SCN-runtime-cost-ceiling', 'SCN-runtime-profile-cli'],
@@ -471,7 +475,7 @@ export const CANDIDATE_ACCEPTANCE_EVIDENCE = Object.freeze({
   'capture-stop-resume': [
     'SCN-fleet-fresh-resume', 'SCN-hierarchy-aware-start-stop', 'SCN-hierarchy-startup-cycle',
   ],
-  'detach-uninstall': ['SCN-install-doctor-purge'],
+  'detach-uninstall': ['SCN-install-doctor-purge', 'SCN-install-restore', 'SCN-worktree-canonical-brief'],
   'combatrig-compatibility': ['SCN-combatrig-import', 'SCN-cli-combatrig-import'],
   'product-surface': ['SCN-product-site', 'SCN-dashboard-demo', 'SCN-console-readonly', 'SCN-console-lifecycle-blockers',
     'SCN-console-owner-digest', 'SCN-demo-owner-digest', 'SCN-console-check-evidence', 'SCN-console-task-activity', 'SCN-console-operation-outcomes', 'SCN-console-live-refresh'],
@@ -796,7 +800,9 @@ export async function runCli(argv = process.argv.slice(2), {
     }
     const designCommand = ['init', 'analyze', 'domains', 'design', 'bootstrap'].includes(command);
     const repositoryRoot = designCommand ? resolve(cwd, optionValue(argv, '--repo') ?? '.') : cwd;
-    const repository = inspectRepository(repositoryRoot);
+    const inspectedRepository = inspectRepository(repositoryRoot);
+    const repository = designCommand ? inspectedRepository
+      : inspectRepository(resolveInstalledProjectRoot(inspectedRepository.root, env));
     if (command === 'profile') {
       const operation = argv[1] ?? 'show';
       const areaId = optionValue(argv, '--area');
@@ -997,6 +1003,11 @@ export async function runCli(argv = process.argv.slice(2), {
       return 0;
     }
     if (command === 'install') {
+      if (argv.includes('--restore')) {
+        const result = restoreProject({ repository, env, dryRun: argv.includes('--dry-run'), authorized: argv.includes('--yes') });
+        print(result, { json });
+        return 0;
+      }
       const proposalPath = optionValue(argv, '--proposal');
       const runtimeOption = optionValue(argv, '--runtime');
       const defaultRuntime = optionValue(argv, '--default-runtime');
@@ -1038,7 +1049,11 @@ export async function runCli(argv = process.argv.slice(2), {
         }
         persistProfileConfig(repository.root, config);
       }
-      print(installed, { json });
+      print(argv.includes('--setup') ? { ...installed, setup: setupProject({ repository: inspectRepository(repository.root), env, authorized: true, parentOverride: optionValue(argv, '--parent') }) } : installed, { json });
+      return 0;
+    }
+    if (command === 'setup') {
+      print(setupProject({ repository, env, authorized: argv.includes('--yes'), dryRun: argv.includes('--dry-run'), parentOverride: optionValue(argv, '--parent') }), { json });
       return 0;
     }
     if (command === 'doctor') {

src/kernel/project-root.mjs

@@ -0,0 +1,38 @@
+import { execFileSync } from 'node:child_process';
+import { existsSync, readFileSync, realpathSync } from 'node:fs';
+import { join, resolve } from 'node:path';
+import { projectStatePath } from './paths.mjs';
+import { TorchError } from './errors.mjs';
+
+const read = path => JSON.parse(readFileSync(path, 'utf8'));
+const git = (root, args) => execFileSync('git', ['-C', root, ...args], { encoding: 'utf8', stdio: ['ignore', 'pipe', 'pipe'] }).trim();
+
+// A worktree's copied configuration is not authoritative. Only registered,
+// same-installation worktrees may resolve to the current canonical definition.
+export function resolveInstalledProjectRoot(root, env = process.env) {
+  root = realpathSync(root);
+  const path = join(root, '.torch', 'install-manifest.json');
+  if (!existsSync(path)) return root;
+  const manifest = read(path);
+  const stateRoot = projectStatePath(manifest.projectId, env);
+  const local = manifest.external?.find(entry => entry.type === 'local-state');
+  if (!local || resolve(local.path) !== resolve(stateRoot)) {
+    throw new TorchError('Installation state path does not match this project', { code: 'LOCAL_STATE_PATH_MISMATCH' });
+  }
+  const metadata = read(join(stateRoot, 'project.json'));
+  if (metadata.projectId !== manifest.projectId) {
+    throw new TorchError('Installation metadata belongs to another project', { code: 'LOCAL_STATE_METADATA_MISMATCH' });
+  }
+  const canonical = realpathSync(metadata.root);
+  if (canonical === root) return root;
+  const current = read(join(canonical, '.torch', 'install-manifest.json'));
+  const registered = current.external?.find(entry => entry.type === 'worktree' && existsSync(entry.path) && realpathSync(entry.path) === root);
+  const common = directory => realpathSync(resolve(directory, git(directory, ['rev-parse', '--git-common-dir'])));
+  const members = git(canonical, ['worktree', 'list', '--porcelain']).split('\n').filter(line => line.startsWith('worktree ')).map(line => realpathSync(line.slice(9)));
+  if (current.projectId !== manifest.projectId || current.installationId !== manifest.installationId
+      || !registered || common(root) !== common(canonical) || !members.includes(root)
+      || git(root, ['branch', '--show-current']) !== registered.branch) {
+    throw new TorchError('This checkout is not a registered worktree of the installation', { code: 'UNREGISTERED_PROJECT_WORKTREE' });
+  }
+  return canonical;
+}

src/kernel/setup.mjs

@@ -0,0 +1,55 @@
+import { execFileSync } from 'node:child_process';
+import { readFileSync, renameSync, writeFileSync } from 'node:fs';
+import { join } from 'node:path';
+import { inspectRepository } from './git.mjs';
+import { readInstallManifest } from './install.mjs';
+import { projectStatePath } from './paths.mjs';
+import { resolveInstalledProjectRoot } from './project-root.mjs';
+import { createWorktrees, planWorktrees } from './worktrees.mjs';
+import { TorchError } from './errors.mjs';
+
+const git = (root, args) => execFileSync('git', ['-C', root, ...args], { encoding: 'utf8', stdio: ['ignore', 'pipe', 'pipe'] }).trim();
+
+export function setupProject({ repository, env = process.env, authorized = false, dryRun = false, parentOverride }) {
+  const root = resolveInstalledProjectRoot(repository.root, env);
+  repository = inspectRepository(root);
+  const manifest = readInstallManifest(root);
+  const owned = [...new Set([...manifest.created.map(record => record.path), '.torch/install-manifest.json'])];
+  const changed = owned.filter(path => git(root, ['status', '--porcelain=v1', '--', path]));
+  const staged = git(root, ['diff', '--cached', '--name-only']);
+  if (staged) throw new TorchError('Setup requires an empty staging area; preserve and finish your existing staged work first', { code: 'SETUP_STAGED_WORK', details: staged });
+  const unrelated = repository.dirtyEntries.filter(entry => !owned.includes(entry.slice(3)));
+  const worktrees = planWorktrees({ repository: { ...repository, dirtyEntries: unrelated }, parentOverride });
+  const plan = { action: 'setup', projectId: manifest.projectId, checkpointPaths: changed, worktrees, canProceed: worktrees.canProceed, sessionsStarted: false, mutationPerformed: false };
+  if (dryRun) return plan;
+  if (!authorized) throw new TorchError('Setup commits TORCH-owned configuration and provisions worktrees; review --dry-run then use --yes', { code: 'APPROVAL_REQUIRED' });
+  if (!plan.canProceed) throw new TorchError('Setup has blockers', { code: 'SETUP_BLOCKED', details: worktrees.conflicts });
+  const checkpoint = (paths, message) => {
+    const pending = paths.filter(path => git(root, ['status', '--porcelain=v1', '--', path]));
+    if (!pending.length) return null;
+    git(root, ['add', '--', ...pending]);
+    git(root, ['commit', '--only', '-m', message, '--', ...pending]);
+    return git(root, ['rev-parse', 'HEAD']);
+  };
+  const configurationCommit = checkpoint(changed, 'Checkpoint approved TORCH configuration');
+  const provisioned = createWorktrees({ repository: inspectRepository(root), parentOverride });
+  const registrationCommit = checkpoint(['.torch/install-manifest.json'], 'Checkpoint TORCH worktree registration');
+  return { ...plan, configurationCommit, registrationCommit, provisioned, mutationPerformed: Boolean(configurationCommit || registrationCommit || provisioned.mutationPerformed) };
+}
+
+export function restoreProject({ repository, env = process.env, authorized = false, dryRun = false }) {
+  const root = resolveInstalledProjectRoot(repository.root, env);
+  const manifest = readInstallManifest(root);
+  const path = join(projectStatePath(manifest.projectId, env), 'project.json');
+  const metadata = JSON.parse(readFileSync(path, 'utf8'));
+  const result = { action: 'restore-installation', projectId: manifest.projectId, installationId: manifest.installationId, wasDetached: Boolean(metadata.detachedAt), preserved: ['configuration', 'worktrees', 'branches', 'session history', 'provider profiles'], sessionsStarted: false, mutationPerformed: false };
+  if (dryRun) return result;
+  if (!authorized) throw new TorchError('Restoring a retained installation requires --yes', { code: 'APPROVAL_REQUIRED' });
+  if (metadata.detachedAt) {
+    const temporary = `${path}.restore-${process.pid}`;
+    writeFileSync(temporary, `${JSON.stringify({ ...metadata, detachedAt: null, attachedAt: new Date().toISOString() }, null, 2)}\n`, { flag: 'wx', mode: 0o600 });
+    renameSync(temporary, path);
+    result.mutationPerformed = true;
+  }
+  return result;
+}

test/fleet/setup.test.mjs

@@ -0,0 +1,101 @@
+import assert from 'node:assert/strict';
+import { execFileSync } from 'node:child_process';
+import { mkdtempSync, readFileSync, writeFileSync, cpSync } from 'node:fs';
+import { tmpdir } from 'node:os';
+import { join } from 'node:path';
+import test from 'node:test';
+import { analyzeRepository } from '../../src/kernel/analyze.mjs';
+import { proposeDomains } from '../../src/kernel/domains.mjs';
+import { inspectRepository } from '../../src/kernel/git.mjs';
+import { installProject, readInstallManifest } from '../../src/kernel/install.mjs';
+import { resolveInstalledProjectRoot } from '../../src/kernel/project-root.mjs';
+import { setupProject, restoreProject } from '../../src/kernel/setup.mjs';
+import { openControlPlane } from '../../src/control-plane/service.mjs';
+import { createFleetBrief, detachFleet, planFleetDetach } from '../../src/runtime/lifecycle.mjs';
+
+const git = (root, args) => execFileSync('git', ['-C', root, ...args], { encoding: 'utf8', stdio: ['ignore', 'pipe', 'pipe'] }).trim();
+function fixture() {
+  const root = mkdtempSync(join(tmpdir(), 'torch-setup-'));
+  const env = { ...process.env, XDG_DATA_HOME: join(root, 'external-state') };
+  git(root, ['init', '-b', 'main']);
+  git(root, ['config', 'user.name', 'Setup Test']);
+  git(root, ['config', 'user.email', '[email protected]']);
+  writeFileSync(join(root, '.gitignore'), 'external-state/\nworktrees/\n');
+  writeFileSync(join(root, 'app.js'), 'export const app = true;\n');
+  git(root, ['add', '.']);
+  git(root, ['commit', '-m', 'fixture']);
+  const repository = inspectRepository(root);
+  const proposal = proposeDomains({ repository, analysis: analyzeRepository(repository) });
+  proposal.review = { status: 'approved', reviewedAt: '2026-09-30T00:00:00Z', reviewedBy: 'owner', notes: [] };
+  installProject({ repository, proposal, env });
+  return { root, env, parentOverride: join(root, 'worktrees') };
+}
+
+test('SCN-guided-setup: approved setup checkpoints owned files and provisions without agents', () => {
+  const f = fixture();
+  const before = git(f.root, ['rev-parse', 'HEAD']);
+  assert.equal(setupProject({ ...f, repository: inspectRepository(f.root), dryRun: true }).canProceed, true);
+  assert.equal(git(f.root, ['rev-parse', 'HEAD']), before);
+  assert.throws(() => setupProject({ ...f, repository: inspectRepository(f.root) }), { code: 'APPROVAL_REQUIRED' });
+  writeFileSync(join(f.root, 'app.js'), 'export const app = false;\n');
+  git(f.root, ['add', 'app.js']);
+  assert.throws(() => setupProject({ ...f, repository: inspectRepository(f.root), authorized: true }), { code: 'SETUP_STAGED_WORK' });
+  assert.equal(git(f.root, ['diff', '--cached', '--name-only']), 'app.js');
+  git(f.root, ['restore', '--staged', 'app.js']);
+  writeFileSync(join(f.root, 'app.js'), 'export const app = true;\n');
+  const result = setupProject({ ...f, repository: inspectRepository(f.root), authorized: true });
+  assert.equal(result.sessionsStarted, false);
+  assert.ok(result.configurationCommit);
+  assert.ok(result.registrationCommit);
+  assert.equal(git(f.root, ['status', '--porcelain']), '');
+  assert.ok(git(f.root, ['diff', '--name-only', before, 'HEAD']).split('\n').every(path => path.startsWith('.torch/')));
+  assert.ok(readInstallManifest(f.root).external.some(entry => entry.type === 'worktree'));
+  assert.equal(setupProject({ ...f, repository: inspectRepository(f.root), authorized: true }).mutationPerformed, false);
+});
+
+test('SCN-worktree-canonical-brief: current instructions win and unregistered or copied worktrees fail closed', () => {
+  const f = fixture();
+  setupProject({ ...f, repository: inspectRepository(f.root), authorized: true });
+  const entry = readInstallManifest(f.root).external.find(item => item.type === 'worktree');
+  const marker = 'Current canonical instructions, not the old worktree copy.';
+  writeFileSync(join(f.root, '.torch/prompts/COMMON.md'), marker);
+  const canonical = resolveInstalledProjectRoot(entry.path, f.env);
+  assert.equal(canonical, f.root);
+  const control = openControlPlane({ repositoryRoot: canonical, env: f.env });
+  try {
+    const brief = createFleetBrief({ repositoryRoot: canonical, controlPlane: control, areaId: entry.area });
+    assert.ok(brief.areas[0].prompt.includes(marker));
+  } finally { control.close(); }
+  const stray = join(f.root, 'worktrees', 'stray');
+  git(f.root, ['worktree', 'add', '-b', 'stray', stray]);
+  assert.throws(() => resolveInstalledProjectRoot(stray, f.env), { code: 'UNREGISTERED_PROJECT_WORKTREE' });
+  const copied = mkdtempSync(join(tmpdir(), 'torch-copy-'));
+  cpSync(join(entry.path, '.torch'), join(copied, '.torch'), { recursive: true });
+  git(copied, ['init', '-b', entry.branch]);
+  assert.throws(() => resolveInstalledProjectRoot(copied, f.env), { code: 'UNREGISTERED_PROJECT_WORKTREE' });
+  const localManifest = JSON.parse(readFileSync(join(entry.path, '.torch/install-manifest.json')));
+  localManifest.installationId = 'stale-installation';
+  writeFileSync(join(entry.path, '.torch/install-manifest.json'), JSON.stringify(localManifest));
+  assert.throws(() => resolveInstalledProjectRoot(entry.path, f.env), { code: 'UNREGISTERED_PROJECT_WORKTREE' });
+});
+
+test('SCN-install-restore: detach and explicit restore preserve configuration and worktree history without starting sessions', () => {
+  const f = fixture();
+  setupProject({ ...f, repository: inspectRepository(f.root), authorized: true });
+  const manifest = readInstallManifest(f.root);
+  const metadataPath = join(manifest.external.find(entry => entry.type === 'local-state').path, 'project.json');
+  const config = readFileSync(join(f.root, '.torch/torch.yaml'), 'utf8');
+  const heads = manifest.external.filter(entry => entry.type === 'worktree').map(entry => git(entry.path, ['rev-parse', 'HEAD']));
+  const control = openControlPlane({ repositoryRoot: f.root, env: f.env });
+  try {
+    detachFleet({ plan: planFleetDetach({ repositoryRoot: f.root, controlPlane: control, adapters: {} }), controlPlane: control, stopRuntime: () => { throw new Error('Offline setup must not call a provider'); } });
+  } finally { control.close(); }
+  const before = readFileSync(metadataPath, 'utf8');
+  assert.equal(restoreProject({ repository: inspectRepository(f.root), env: f.env, dryRun: true }).wasDetached, true);
+  assert.equal(readFileSync(metadataPath, 'utf8'), before);
+  assert.throws(() => restoreProject({ repository: inspectRepository(f.root), env: f.env }), { code: 'APPROVAL_REQUIRED' });
+  assert.equal(restoreProject({ repository: inspectRepository(f.root), env: f.env, authorized: true }).sessionsStarted, false);
+  assert.equal(JSON.parse(readFileSync(metadataPath)).detachedAt, null);
+  assert.equal(readFileSync(join(f.root, '.torch/torch.yaml'), 'utf8'), config);
+  assert.deepEqual(manifest.external.filter(entry => entry.type === 'worktree').map(entry => git(entry.path, ['rev-parse', 'HEAD'])), heads);
+});

torch-release.json

@@ -1,6 +1,6 @@
 {
   "schema": "torch.dev/release/v1alpha1",
-  "version": "0.1.0-alpha.1",
+  "version": "0.1.0-alpha.2",
   "state": {
     "reads": ["torch.dev/state/v1alpha1"],
     "writes": "torch.dev/state/v1alpha1",