@codetreker/daynight 0.24.1 → 0.24.5

package/README.md

@@ -152,13 +152,24 @@ records module ownership and the preserved data layout.
 
 The public `using-daynight` skill provides task creation, handoff review and
 execution of one specified task. Ordinary execution reads `run-task.md`.
-Worker-started agents use `execute-task-in-managed` only when their startup
+Worker-started agents use `autopilot-managed-task` only when their startup
 prompt explicitly names the `worker-managed` environment, the `using-daynight`
 skill and that mode, together with their assignment. `SKILL.md` routes to the
 selected instructions; ordinary execution does not load managed task rules.
 Shared task inputs, delivery and acceptance rules retain one owner in the bundle.
 The [foreground worker](#worker-configuration-and-startup) constructs that
 explicit assignment and loads the installed managed entry before launch.
+Managed execution follows one assignment through implementation, validation,
+focused PR delivery, CI and review repair, and merge. A valid worker-managed
+assignment already has sufficient authorization for that delivery and PR merge;
+merge as soon as the checks and review conditions are satisfied without asking
+for additional confirmation. Explicit user restrictions, pauses and revocation
+remain binding. Pending CI or
+review stays in execution; demonstrated external blockers return to the worker
+with a checkpoint. Merge requires current-head approval and required checks,
+and platform confirmation; mainline CI after merge is awaited only on explicit
+request. The mode preserves the assigned scope, the original claim and the
+controller's ownership of worktree, branch and workspace cleanup.
 
 Install the skill through an interactive terminal:
 
@@ -821,17 +832,19 @@ unchanged.
 Local diagnostics inspect tools and integration settings without starting Herdr
 or native agents. Missing prerequisites are reported together; selected-agent
 checks use effective retained native arguments in the setup launch directory.
-Missing native dependencies allow saving with a repair-needed result. Versions
-and hook configuration do not prove provider authentication, future task-directory
-trust, hook execution, live Herdr protocol, Git access or completed delivery.
+Missing native dependencies allow saving with a repair-needed result. Versions,
+fixed launch-argument capabilities and hook configuration do not prove provider
+authentication, hook execution, live Herdr protocol, Git access or completed
+delivery.
 Setup does not install tools, edit provider configuration, sign in, clone, open
 worker state or acquire tasks. Unconfirmed probe-process cleanup is a failure,
 including during cancellation.
 
 Install Git, Herdr 0.9.5 or newer with protocol 22 capabilities, and the selected
 native agent on PATH. Configure native/provider credentials and the current
-official Herdr SessionStart integration explicitly. Codex needs hooks and
-`--no-daemon`; Unix hooks need bash and python3, while Windows hooks need
+official Herdr SessionStart integration explicitly. Codex must be 0.135 or newer
+and support hooks, `--no-daemon` and the fixed full-access/hook-trust flags;
+Unix hooks need bash and python3, while Windows hooks need
 PowerShell. Inspect official integration with `herdr integration status`. Missing
 capabilities and native launch failures remain visible;
 the worker does not install or change global native configuration. Git transport
@@ -933,9 +946,11 @@ pollIntervalMs is a positive safe integer within the timer range.
 Repository agent settings override fields independently for the same type.
 Explicit null model or [] args clears that field; switching type clears omitted
 model/args, and args replaces the list. Worker owns cwd/session/model/mode
-arguments. Configuration loads at startup without hot reload. Each claim retains
-its recorded agent type and native session ID; a restarted agent uses the current
-settings appropriate to that type. Settings for another type are not applied to it.
+arguments and the fixed full-access policy; conflicting arguments are rejected
+before launch. Configuration loads at startup without hot reload. Each claim
+retains its recorded agent type and native session ID; a restarted agent uses the
+current settings appropriate to that type. Settings for another type are not
+applied to it.
 
 New tasks have automatic execution disabled. Enable it explicitly through the
 normal task update workflow after reading the current task and version. Worker
@@ -1015,6 +1030,23 @@ The saved SQLite session_id still selects resume or fresh startup; an inactive
 pane's retained reference is not saved as a newly observed session ID. A live
 agent keeps its current connection.
 
+Startup and recovery prompts identify the assignment as a background task: the
+agent asks no questions and makes decisions within the task scope and existing
+authorization. While waiting for review or CI, it waits, checks for results and
+continues delivery without ending its execution turn. Fixed native full access
+and folder trust apply to every fresh/resumed process; task delivery remains
+within its existing business authorization.
+
+For a still-owned active claim, each patrol observes the live agent. An
+interactive-ready agent that is not launching and has no first input pending
+receives a continuation ping when idle or done. Working, blocked, unknown and
+not-ready agents remain under observation. The ping preserves the original task,
+claim, worktree and authorization; idle or done does not complete the business
+task. The driver retains the last input observation in memory and suppresses
+repeated input while it is unchanged. Unknown submission results require
+observation before another decision, without blind replay. Terminal cleanup
+suppresses business pings.
+
 A non-NULL saved session ID remains the recovery identity. A different native
 ID reported during startup, live reconnection or before deferred input is an
 error: the saved ID is retained and that input is not sent. A genuine live
@@ -1039,16 +1071,35 @@ and does not start a replacement daemon. Detaching leaves worker and tasks
 running. Original task panes retain their native XDG and private HISTFILE;
 client routing comes from the existing attachment descriptor.
 
-Folder trust or authorization must be handled explicitly in the native tool or
-attached task pane. Worker retains input-readiness and supported Codex composer
-checks and does not auto-accept trust or alter global settings. Unknown layouts
-or launch errors remain visible. Reconnecting an already alive agent does not
-promise to resend an input lost across a process interruption.
-
-When the original claim is absent from a successful complete inventory, the
-worker asks its agent to release attributable temporary files, services and
-processes outside the worktree. It waits at most ten minutes for this cleanup
-attempt, stops the agent, closes its workspace, removes the matching worktree
+Every fresh or resumed native process uses fixed full access and task-folder
+trust. Copilot receives `--allow-all --no-ask-user --no-sandbox` and per-workspace
+`COPILOT_ALLOW_ALL=true`, `COPILOT_ASSISTED_APPROVAL=false`, overriding inherited
+values. Codex receives `--no-daemon`,
+`--dangerously-bypass-approvals-and-sandbox`,
+`--dangerously-bypass-hook-trust` and a final `-c` trusted-project override for
+the task's canonical path, using Codex's normalized Windows trust keys. These
+invocation settings require no native tool,
+folder or hook permission confirmation and are not optional configuration.
+
+Copilot arguments that enable assisted approval or sandboxing, deny tools/URLs,
+or restrict available tools are rejected. Codex approval/sandbox controls and
+duplicate worker-owned bypass flags are rejected. Ordinary model, reasoning,
+logging and additional configuration arguments remain supported. Setup and
+runtime use read-only native argument-capability probes; unsupported flags or
+versions fail explicitly.
+
+The policy applies only to native invocations and task workspaces. Global native
+configuration, credentials and organization/OS policies keep their existing
+owners; task delivery still follows its business authorization. Input-readiness
+and supported Codex composer checks remain. Unknown layouts, missing credentials,
+integration failures and launch errors stay visible. Use attach for business
+input. Reconnecting an already alive agent does not promise to resend an input
+lost across a process interruption.
+
+During normal reconciliation, when the original claim is absent from a
+successful complete inventory, the worker asks its agent to release attributable
+temporary files, services and processes outside the worktree. It waits at most
+ten minutes for this cleanup attempt, stops the agent, closes its workspace, removes the matching worktree
 and marks the local row done. Done, release and force withdrawal have the same terminal
 resource rule. Failed stop or deletion retains responsibility and the error.
 
@@ -1057,11 +1108,14 @@ worktree deletion validates only its target Git registration and directory.
 Unrelated repository or sibling-worktree registration errors are reported
 separately and do not prevent a healthy agent from stopping.
 
-Early cleanup completion uses only the successful cleanup-prompt receipt's
-idle, interactive-ready observation with both sequence counters present; later
-observations must advance both counters. A prior polling snapshot cannot supply
-that baseline. Busy, unknown, rejected or unattributable notification results
-retain the current bounded wait instead of counting an old task turn as cleanup.
+After the cleanup message is successfully submitted, a subsequent patrol that
+observes idle completes the cleanup turn and proceeds to stop the agent and
+close its workspace. Sequence counters and interactive readiness are not
+required. A pre-notification observation or the submission receipt itself
+cannot finish cleanup. Failed or unknown notification results retain their error
+and the current bounded wait, without automatic replay. Reaching the deadline
+still proceeds through actual stop confirmation. Idle in this terminal cleanup
+phase does not complete the business task.
 
 Cleanup timing and progress are in memory. Polls do not extend the current
 attempt's deadline; after a crash, the next successful reconciliation observes
@@ -1070,10 +1124,23 @@ may repeat. Separate tasks have independent bounded jobs, so one held RPC does
 not postpone another task's cleanup. A cleanup already selected in the current
 process can continue during later service-read failures.
 
-Ctrl+C stops acquisition and ordinary scheduling, then gives agents bounded
-outside-worktree cleanup, stops them and closes their workspaces. Valid claims,
-worktrees, session IDs and active/pending rows remain for the next run. The
-private instance stops last; exit failures remain visible.
+Ctrl+C stops acquisition and scheduling, cancels all running jobs including
+terminal cleanup, and joins them before directly stopping agents and closing
+their workspaces. Process exit sends no cleanup prompt and does not wait for a
+cleanup turn. It preserves claims, worktrees, native session IDs and all
+unfinished active/pending rows, including those whose ownership has ended. The
+next run uses normal inventory reconciliation to re-enter terminal cleanup for
+ended claims. External temporary resources may remain after direct interruption.
+Normal completion, release, withdrawal and manual-control cleanup retain their
+notification and removal sequence. Pending stop confirmations must settle before the private
+Herdr instance stops; stop errors remain visible, and uncertain stopping retains
+that instance and the affected resources. Before closing a verified orphan
+workspace with no local task row, cleanup and exit save its observed native
+agent and any live session ID in the existing pending claim index. Restart can
+then remove its retained worktree and unblock a later claim for the same task.
+An unknown original agent type retains the workspace with a visible error;
+current configuration does not establish that historical type. Unproven Git-only
+resources remain untouched.
 
 stderr and JSONL logs identify worker, platform, Project/task/claim, agent and
 known session ID. Startup prints the log location and attach guidance. Routine

package/config.example.yml

@@ -36,7 +36,9 @@ review:
 # choose a native agent and select existing Projects before worker run.
 # Omitted values use these defaults; an empty selection also makes interactive
 # worker run guide Project registration. Native credentials and the official
-# Herdr integration must be configured explicitly.
+# Herdr integration must be configured explicitly. Every fresh/resumed native
+# agent uses fixed full access and task-folder trust; args cannot lower that
+# policy or re-enable permission prompts. Global native configuration is unchanged.
 worker:
   # Used only for new worker repo registrations; independent of review's root.
   repositoryRoot: ~/daynights

package/dist/commands/skill/skills/using-daynight/SKILL.md

@@ -73,12 +73,17 @@ operations it requires. Do not load every mode by default.
 | `create-task <request>` | Preparing or registering persistent work explicitly requested by the user | [Create task](references/create-task.md) |
 | `run-task <task-id>` | Executing one specified ordinary task | [Run task](references/run-task.md) |
 | `handoff <task-id>` | Reviewing an explicitly requested task for handoff and enabling permission after it passes | [Handoff](references/handoff.md) |
-| `execute-task-in-managed <task-id>` | The worker startup prompt explicitly declares the `worker-managed` environment, this skill, and this mode | [Managed execution](references/execute-task-in-managed.md) |
+| `autopilot-managed-task <task-id>` | The worker startup prompt explicitly declares the `worker-managed` environment, this skill, and this mode | [Managed autopilot](references/autopilot-managed-task.md) |
 
 The managed execution reference is loaded only for that explicit worker launch;
 ordinary calls do not read it. Task properties, the working directory, and
 environment variables do not select the managed mode. An invocation presented
 as managed with an incomplete launch declaration waits for the missing context.
+A valid worker-managed assignment already carries sufficient authorization for
+its in-scope delivery, including PR merge; deliver it without additional permission
+requests once the required conditions are met. Explicit user restrictions, pause,
+and revocation still apply. The mode executes only that original assignment;
+reading its name does not authorize work or successor selection.
 
 For ordinary calls, honor the explicitly selected mode. For `using-daynight`
 without further input, infer the ordinary mode and target from the current

package/dist/commands/skill/skills/using-daynight/references/autopilot-managed-task.md

@@ -0,0 +1,205 @@
+# Autopilot one managed task
+
+Use this mode only when the worker's startup prompt explicitly declares the
+`worker-managed` environment, the `using-daynight` skill, and the
+`autopilot-managed-task` mode. It delivers one already-claimed assignment through
+its authorized implementation, validation, PR review, merge, and acceptance.
+Read [the handbook](handbook.md) for CLI operations and failure semantics.
+
+## Establish the assignment
+
+The startup prompt supplies `projectId`, `taskId`, the original `claimId`,
+`worktreeId`, the actual worktree path and branch, and the configuration selected
+for this invocation. Use that explicit assignment throughout execution and recovery.
+Task properties, the working directory, environment variables, and an ordinary
+conversation request do not establish this managed context.
+
+If a call is presented as managed but its launch declaration or assignment is
+missing, incomplete, or mismatched, return waiting without task or business
+writes. Do not infer replacement values or fall back to ordinary execution,
+claiming, starting, or selecting another task.
+
+A valid worker-managed assignment already carries sufficient authorization for
+its in-scope delivery, including PR merge. Do not request additional permission
+for those steps. Honor explicit user restrictions, pause requests, and
+revocation. The assignment does not authorize unrelated backlog work, production
+deployment, destructive data operations, or changes to permissions or protections.
+Reading, editing, or mentioning this mode does not establish a managed assignment
+or activate the separately installed `autopilot` skill, which is not a runtime
+dependency.
+
+The worker produces the launch prompt and decides subsequent scheduling. A new
+agent started to recover the same claim receives the original mode and
+assignment again. Reconnecting an existing live agent does not imply that the
+startup prompt should be submitted again.
+
+## Verify the existing execution
+
+Read the latest complete task using the supplied project and task IDs:
+
+```bash
+daynight task show <task-id> --project <project-id> --json
+```
+
+Verify its `projectId` and `id`, `status=in_progress`, and
+`properties.worker.state=active` with the supplied `claimId` and `worktreeId`.
+Verify the actual working directory and Git branch match the supplied worktree.
+Use the configuration supplied for this invocation. The controller selects the
+current settings appropriate to the recorded agent when it launches or resumes
+a native process; an executor does not independently replace that assignment.
+If the same claim is already `completed` and the task is `done`, report the
+existing completion and return without reexecuting it. Any other state or
+identity mismatch leaves execution waiting; an observed claim change stops
+business writes immediately.
+
+The worker has already claimed and started this task. Do not claim it, set it
+to `in_progress`, select candidates, or rerun automatic candidate qualification.
+Read and apply [shared task execution](task-execution.md) for the complete task
+and stage inputs, current prerequisites, authorized work, evidence, and
+acceptance. A missing required input or unmet prerequisite keeps this assignment
+waiting in `in_progress`; it does not authorize another task.
+
+Before resuming interrupted work or making task writes, refresh the complete
+task using the supplied project and task IDs and verify the same active claim.
+Retain the original claim ID through recovery and uncertain-write
+reconciliation; never substitute a claim read from the task.
+
+## Execute within controller-owned resources
+
+Use the supplied worktree and branch for authorized edits, commits, pushes, and
+merges. Do not create, switch, or remove the system-managed worktree or branch.
+Avoid merge options such as `gh pr merge --delete-branch` that may switch the
+checkout or delete its branch. The worker owns resource cleanup after execution;
+do not delete its worktree or close its workspace. Follow a cleanup request for
+attributable temporary resources outside the worktree within its stated scope.
+
+Use the Goal protocol for this task's required inputs and stage acceptance.
+This mode never advances a Goal stage or executes a successor. The shared
+execution and acceptance rules do not change that boundary.
+
+## Preserve execution continuity
+
+Keep a compact checkpoint in the host's session state or the project's existing
+local planning mechanism. Retain the original assignment identities, supplied
+worktree and branch, existing authorization, confirmed scope and acceptance,
+PR URLs and head SHA, validation and review state, blockers, attributable
+resources, and next action. Identify the invocation configuration without
+copying credentials or secrets into checkpoints, task evidence, or logs.
+
+Refresh the checkpoint before a long wait or session compaction. On recovery,
+restore it, verify the original active claim, and refresh remote PR state before
+resuming mutations. Reconcile interrupted business work and uncertain writes
+before deciding the next action. A status question does not cancel the assignment;
+honor explicit pause, stop, and authorization changes without discarding its work.
+
+## Deliver the assigned task
+
+1. **Implement and verify.** Read applicable repository instructions and existing
+   mechanisms. Reuse the confirmed task plan and acceptance criteria. Implement
+   the complete agreed behavior in the supplied worktree, synchronize affected
+   documents, and run relevant checks and behavioral verification. Collaborating
+   agents share this assignment and worktree. Use research and independent review
+   agents when available and authorized. Reassess the design when repeated
+   failures expose a structural problem.
+
+2. **Publish the focused change.** For a PR delivery, commit and push authorized
+   work promptly using repository conventions, default Git identity, and no AI
+   co-author attribution. Create or update the task's focused PR and preserve its
+   complete PR list as required by shared execution. Integrate necessary mainline
+   updates according to the repository's work-branch rules, resolve conflicts in
+   the supplied worktree, and revalidate.
+
+3. **Follow CI and review through repair.** Inspect the actual remote PR head,
+   checks, review requests, comments, and approvals. Request review through the
+   repository's established mechanism. Diagnose failed checks from their logs
+   and repair the cause without weakening acceptance. Rerun an
+   unchanged failure only after confirming a transient infrastructure cause.
+   Each push requires refreshed checks and review for the resulting head.
+
+   Assess findings against the original scope. Fix introduced Critical/Major
+   issues and defects that would make the agreed delivery incorrect. Defer smaller
+   or unrelated improvements under the project's tracking rules without executing
+   them or creating unauthorized tasks. Use fix, defer, and reject dispositions.
+   Reply in each finding's own thread, identify the agent, and resolve handled
+   threads according to repository rules. Repeat review and repair until the
+   final round has no new Critical/Major findings and remote review requirements
+   are satisfied.
+
+4. **Merge and confirm.** The assignment already authorizes its in-scope PR
+   merge. Immediately before merging, refresh the head SHA, required checks,
+   review threads, mergeability, and approvals. Require successful required
+   checks, handled blocking review threads, and actual reviewer approval for the
+   current head. When required checks, current-head approvals, blocking-thread
+   resolution, and mergeability all satisfy the repository's rules, merge
+   immediately without requesting additional permission. Never infer approval
+   from silence, approve your own PR, weaken checks or protections, or use an
+   administrative override. Use the repository's
+   permitted linear-history method and bind the merge to the verified head when
+   the platform supports it. A changed head or failed precondition requires a
+   fresh decision from current state.
+
+   Confirm the platform reports every necessary delivery PR as merged and record
+   each resulting merge commit. An accepted auto-merge request or merge-queue
+   entry is not completion. Do not wait for post-merge mainline CI unless the user
+   explicitly requires that verification. Continue with required task acceptance
+   and evidence after the platform confirms the merge.
+
+5. **Record acceptance and close this claim.** Complete the task's confirmed
+   acceptance and save readable evidence at its identified owner, including actual
+   validation and remaining limitations. Release attributable temporary services,
+   probes, and monitoring resources, including those left by failed collaborators,
+   while preserving controller-owned resources. Finish that cleanup before
+   [original-claim completion](#complete-the-original-claim), because confirmed
+   completion allows the worker to stop the agent and remove its workspace.
+
+For tasks without a PR delivery path, verify the actual artifact against their
+confirmed acceptance criteria. Do not invent a PR or reviewer gate for those
+tasks. Goal discussion confirmation gates remain mandatory; this assignment
+never authorizes execution of a later Goal stage.
+
+## Wait for delivery results
+
+Pending PR CI or review is ongoing execution, not external intervention. Use
+bounded watches or yielding polls at reasonable intervals, inspect new results,
+and act on failures and feedback. A polling timeout ends only that poll; keep
+waiting and inspecting results. Do not return merely because a required PR
+remains unmerged while its CI or review is pending. Use the worker's existing
+continuation mechanism; do not claim monitoring continues without one or start
+an independent scheduling service.
+
+Continue while useful authorized actions remain. A demonstrated blocker such as
+missing credentials, an unavailable required reviewer, a material unresolved
+decision, an unmet human confirmation gate, or an explicit user restriction or
+revocation that prevents delivery requires external intervention. This is a
+background task: do not ask the user questions. Preserve the concrete blocker, actual task and PR state,
+completed work, minimum needed intervention, and next action in the checkpoint,
+then return waiting to the controller. Preserve the assignment in `in_progress`;
+never treat a blocker or ordinary waiting as completion.
+
+## Complete the original claim
+
+When [shared acceptance readiness](task-execution.md#confirm-acceptance-readiness)
+is satisfied, all required evidence is readable, and attributable temporary
+resources have been released, reread the complete task, verify the same active
+claim, and finish with the original claim ID and the version observed for that
+decision:
+
+```bash
+daynight task set-status <task-id> done --project <project-id> --claim-id <claim-id> --if-version <observed-version>
+```
+
+This is the final task mutation. Confirm `done`,
+`properties.worker.state=completed`, and the original claim ID in the service
+result. A refused or unconfirmed write never falls back to ordinary completion
+or automatic replay: read the actual task using the supplied project and task
+IDs and reconcile only the original claim. An unreadable result remains
+unconfirmed; an observed claim change stops further business writes.
+
+## Return to the controller
+
+Return after this task completes or requires demonstrated external intervention.
+Preserve the assignment and waiting checkpoint when a human gate, an explicit
+user restriction or revocation, or unmet acceptance requires that intervention.
+A required PR with pending CI or review follows the ongoing wait above. The worker decides subsequent work
+and owns system-resource cleanup; this mode does not select a successor or advance
+a Goal stage.

package/dist/commands/skill/skills/using-daynight/references/handbook.md

@@ -89,9 +89,13 @@ completion operation: a real completion requires the current owner, active
 claim, in-progress task, and exact version, and retains worker history with
 `state=completed`. Omit `--claim-id` for ordinary status setting; refusal never
 causes fallback between these operations. Read the
-[managed execution reference](execute-task-in-managed.md) only when the worker
+[managed autopilot reference](autopilot-managed-task.md) only when the worker
 startup prompt explicitly selects that mode; ordinary status operations do not
-load its execution rules.
+load its execution rules. A valid worker-managed assignment already has sufficient
+authorization for its in-scope delivery and PR merge. Its executor merges once the
+required checks, current-head approvals, blocking-thread resolution, and
+mergeability conditions are met without requesting additional permission, while
+honoring explicit user restrictions, pause, and revocation.
 
 The service checks the exact version
 before a same-status no-op; it preserves all fields for a current-version no-op

package/dist/commands/worker/cleanup.js

@@ -9,7 +9,7 @@ export const createCleanupDriver = (deps) => {
             const identity = key(input.owner);
             let attempt = attempts.get(identity);
             if (attempt === undefined) {
-                attempt = { deadline: deps.now() + 600_000, notified: false, baseline: null };
+                attempt = { deadline: deps.now() + 600_000, notified: false, submitted: false };
                 attempts.set(identity, attempt);
                 deps.emit({ kind: "cleanup-started", ...(input.task === undefined ? {} : { task: input.task }), message: `Cleaning claim ${input.owner.claimId}; this attempt has a ten-minute deadline.` });
             }
@@ -26,20 +26,16 @@ export const createCleanupDriver = (deps) => {
                     if (liveAgent(pane) && !attempt.notified && deps.now() < attempt.deadline) {
                         attempt.notified = true;
                         try {
-                            const { observation } = await workerOperation((operation) => deps.herdr.tasks.submitPrompt(context, pane.binding, workerCleanupPrompt(input.owner, attempt.deadline), operation), signal, Math.max(1, Math.min(30_000, attempt.deadline - deps.now())));
-                            if (observation.status === "idle" && observation.interactiveReady
-                                && observation.stateChangeSeq !== null
-                                && observation.completionSeq !== null) {
-                                attempt.baseline = { stateChangeSeq: observation.stateChangeSeq, completionSeq: observation.completionSeq };
-                            }
+                            await workerOperation((operation) => deps.herdr.tasks.submitPrompt(context, pane.binding, workerCleanupPrompt(input.owner, attempt.deadline), operation), signal, Math.max(1, Math.min(30_000, attempt.deadline - deps.now())));
+                            attempt.submitted = true;
                         }
                         catch (error) {
                             deps.emit({ kind: "cleanup-notification-error", ...(input.task === undefined ? {} : { task: input.task }), message: "Cleanup notification failed; the current bounded cleanup attempt continues.", error });
                         }
+                        if (deps.now() < attempt.deadline)
+                            return false;
                     }
-                    const completed = attempt.baseline !== null && (pane.status === "idle" || pane.status === "done")
-                        && pane.stateChangeSeq !== null && pane.stateChangeSeq > attempt.baseline.stateChangeSeq
-                        && pane.completionSeq !== null && pane.completionSeq > attempt.baseline.completionSeq;
+                    const completed = attempt.submitted && pane.status === "idle";
                     if (liveAgent(pane) && !completed && deps.now() < attempt.deadline)
                         return false;
                     await workerOperation((operation) => deps.herdr.tasks.stopAndClose(context, pane.binding, operation), signal);

package/dist/commands/worker/cleanup.js.map

@@ -1 +1 @@
-{"version":3,"file":"cleanup.js","sourceRoot":"","sources":["../../../src/commands/worker/cleanup.ts"],"names":[],"mappings":"AAAA,OAAO,IAAI,MAAM,WAAW,CAAC;AAG7B,OAAO,EAAE,cAAc,EAAE,gBAAgB,EAAE,SAAS,EAAE,iBAAiB,EAAE,eAAe,EAAE,MAAM,gBAAgB,CAAC;AAEjH,OAAO,EAAE,mBAAmB,EAAE,MAAM,cAAc,CAAC;AAKnD,MAAM,GAAG,GAAG,CAAC,KAAoB,EAAU,EAAE,CAAC,GAAG,KAAK,CAAC,SAAS,IAAI,KAAK,CAAC,MAAM,IAAI,KAAK,CAAC,OAAO,EAAE,CAAC;AAEpG,MAAM,CAAC,MAAM,mBAAmB,GAAG,CAAC,IAA2B,EAAE,EAAE;IACjE,MAAM,QAAQ,GAAG,IAAI,GAAG,EAA0B,CAAC;IACnD,OAAO;QACL,OAAO,EAAE,KAAK,EAAE,KAAmB,EAAE,SAAyC,EAAE,cAAuB,EAAE,MAAoB,EAAoB,EAAE;YACjJ,MAAM,QAAQ,GAAG,GAAG,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC;YAClC,IAAI,OAAO,GAAG,QAAQ,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAC;YACrC,IAAI,OAAO,KAAK,SAAS,EAAE,CAAC;gBAC1B,OAAO,GAAG,EAAE,QAAQ,EAAE,IAAI,CAAC,GAAG,EAAE,GAAG,OAAO,EAAE,QAAQ,EAAE,KAAK,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC;gBAC9E,QAAQ,CAAC,GAAG,CAAC,QAAQ,EAAE,OAAO,CAAC,CAAC;gBAChC,IAAI,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,iBAAiB,EAAE,GAAG,CAAC,KAAK,CAAC,IAAI,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE,KAAK,CAAC,IAAI,EAAE,CAAC,EAAE,OAAO,EAAE,kBAAkB,KAAK,CAAC,KAAK,CAAC,OAAO,2CAA2C,EAAE,CAAC,CAAC;YAC/L,CAAC;YACD,MAAM,WAAW,GAAG,EAAE,GAAG,KAAK,CAAC,KAAK,EAAE,GAAG,EAAE,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,SAAS,EAAE,YAAY,EAAE,UAAU,EAAE,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,EAAE,CAAC;YAC9H,MAAM,OAAO,GAAG,MAAM,iBAAiB,CAAC,IAAI,EAAE,KAAK,CAAC,KAAK,EAAE,MAAM,CAAC,CAAC;YACnE,MAAM,IAAI,GAAG,OAAO,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,cAAc,CAAC,KAAK,CAAC,KAAK,EAAE,SAAS,CAAC,CAAC;YAC1E,IAAI,IAAI,KAAK,SAAS,EAAE,CAAC;gBACvB,MAAM,KAAK,GAA4B,KAAK,CAAC,IAAI,EAAE,KAAK,IAAI,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,aAAa,EAAE,KAAK,CAAC;gBACnG,IAAI,KAAK,KAAK,SAAS,EAAE,CAAC;oBACxB,MAAM,eAAe,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,YAAY,CAAC,WAAW,EAAE,IAAI,CAAC,OAAO,EAAE,SAAS,CAAC,EAAE,MAAM,CAAC,CAAC;gBACpH,CAAC;qBAAM,CAAC;oBACN,MAAM,OAAO,GAAG,gBAAgB,CAAC,EAAE,GAAG,KAAK,EAAE,IAAI,EAAE,EAAE,KAAK,EAAE,EAAE,CAAC,CAAC;oBAChE,IAAI,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC,OAAO,CAAC,QAAQ,IAAI,IAAI,CAAC,GAAG,EAAE,GAAG,OAAO,CAAC,QAAQ,EAAE,CAAC;wBAC1E,OAAO,CAAC,QAAQ,GAAG,IAAI,CAAC;wBACxB,IAAI,CAAC;4BACH,MAAM,EAAE,WAAW,EAAE,GAAG,MAAM,eAAe,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,YAAY,CAAC,OAAO,EAAE,IAAI,CAAC,OAAO,EAAE,mBAAmB,CAAC,KAAK,CAAC,KAAK,EAAE,OAAQ,CAAC,QAAQ,CAAC,EAAE,SAAS,CAAC,EAAE,MAAM,EAAE,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,IAAI,CAAC,GAAG,CAAC,MAAM,EAAE,OAAO,CAAC,QAAQ,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC,CAAC,CAAC,CAAC;4BACzP,IAAI,WAAW,CAAC,MAAM,KAAK,MAAM,IAAI,WAAW,CAAC,gBAAgB;mCAC5D,WAAW,CAAC,cAAc,KAAK,IAAI;mCACnC,WAAW,CAAC,aAAa,KAAK,IAAI,EAAE,CAAC;gCACxC,OAAO,CAAC,QAAQ,GAAG,EAAE,cAAc,EAAE,WAAW,CAAC,cAAc,EAAE,aAAa,EAAE,WAAW,CAAC,aAAa,EAAE,CAAC;4BAC9G,CAAC;wBACH,CAAC;wBAAC,OAAO,KAAK,EAAE,CAAC;4BACf,IAAI,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,4BAA4B,EAAE,GAAG,CAAC,KAAK,CAAC,IAAI,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE,KAAK,CAAC,IAAI,EAAE,CAAC,EAAE,OAAO,EAAE,6EAA6E,EAAE,KAAK,EAAE,CAAC,CAAC;wBAC9M,CAAC;oBACH,CAAC;oBACD,MAAM,SAAS,GAAG,OAAO,CAAC,QAAQ,KAAK,IAAI,IAAI,CAAC,IAAI,CAAC,MAAM,KAAK,MAAM,IAAI,IAAI,CAAC,MAAM,KAAK,MAAM,CAAC;2BAC5F,IAAI,CAAC,cAAc,KAAK,IAAI,IAAI,IAAI,CAAC,cAAc,GAAG,OAAO,CAAC,QAAQ,CAAC,cAAc;2BACrF,IAAI,CAAC,aAAa,KAAK,IAAI,IAAI,IAAI,CAAC,aAAa,GAAG,OAAO,CAAC,QAAQ,CAAC,aAAa,CAAC;oBACxF,IAAI,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC,SAAS,IAAI,IAAI,CAAC,GAAG,EAAE,GAAG,OAAO,CAAC,QAAQ;wBAAE,OAAO,KAAK,CAAC;oBACjF,MAAM,eAAe,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,YAAY,CAAC,OAAO,EAAE,IAAI,CAAC,OAAO,EAAE,SAAS,CAAC,EAAE,MAAM,CAAC,CAAC;gBAChH,CAAC;YACH,CAAC;YACD,IAAI,cAAc;gBAAE,MAAM,eAAe,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,IAAI,CAAC,GAAG,CAAC,cAAc,CAAC,KAAK,CAAC,OAAO,EAAE,KAAK,CAAC,KAAK,EAAE,SAAS,CAAC,EAAE,MAAM,EAAE,OAAO,CAAC,CAAC;YAC1I,QAAQ,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAC;YAC1B,IAAI,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,cAAc,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,eAAe,EAAE,GAAG,CAAC,KAAK,CAAC,IAAI,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE,KAAK,CAAC,IAAI,EAAE,CAAC,EAAE,OAAO,EAAE,cAAc,CAAC,CAAC,CAAC,0EAA0E,CAAC,CAAC,CAAC,wDAAwD,EAAE,CAAC,CAAC;YAC9R,OAAO,IAAI,CAAC;QACd,CAAC;QACD,SAAS,EAAE,CAAC,KAAoB,EAAU,EAAE,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,QAAQ,CAAC,GAAG,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,EAAE,QAAQ,IAAI,IAAI,CAAC,GAAG,EAAE,CAAC,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC;KAC1H,CAAC;AACJ,CAAC,CAAC"}
+{"version":3,"file":"cleanup.js","sourceRoot":"","sources":["../../../src/commands/worker/cleanup.ts"],"names":[],"mappings":"AAAA,OAAO,IAAI,MAAM,WAAW,CAAC;AAG7B,OAAO,EAAE,cAAc,EAAE,gBAAgB,EAAE,SAAS,EAAE,iBAAiB,EAAE,eAAe,EAAE,MAAM,gBAAgB,CAAC;AAEjH,OAAO,EAAE,mBAAmB,EAAE,MAAM,cAAc,CAAC;AAKnD,MAAM,GAAG,GAAG,CAAC,KAAoB,EAAU,EAAE,CAAC,GAAG,KAAK,CAAC,SAAS,IAAI,KAAK,CAAC,MAAM,IAAI,KAAK,CAAC,OAAO,EAAE,CAAC;AAEpG,MAAM,CAAC,MAAM,mBAAmB,GAAG,CAAC,IAA2B,EAAE,EAAE;IACjE,MAAM,QAAQ,GAAG,IAAI,GAAG,EAA0B,CAAC;IACnD,OAAO;QACL,OAAO,EAAE,KAAK,EAAE,KAAmB,EAAE,SAAyC,EAAE,cAAuB,EAAE,MAAoB,EAAoB,EAAE;YACjJ,MAAM,QAAQ,GAAG,GAAG,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC;YAClC,IAAI,OAAO,GAAG,QAAQ,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAC;YACrC,IAAI,OAAO,KAAK,SAAS,EAAE,CAAC;gBAC1B,OAAO,GAAG,EAAE,QAAQ,EAAE,IAAI,CAAC,GAAG,EAAE,GAAG,OAAO,EAAE,QAAQ,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,CAAC;gBAChF,QAAQ,CAAC,GAAG,CAAC,QAAQ,EAAE,OAAO,CAAC,CAAC;gBAChC,IAAI,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,iBAAiB,EAAE,GAAG,CAAC,KAAK,CAAC,IAAI,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE,KAAK,CAAC,IAAI,EAAE,CAAC,EAAE,OAAO,EAAE,kBAAkB,KAAK,CAAC,KAAK,CAAC,OAAO,2CAA2C,EAAE,CAAC,CAAC;YAC/L,CAAC;YACD,MAAM,WAAW,GAAG,EAAE,GAAG,KAAK,CAAC,KAAK,EAAE,GAAG,EAAE,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,SAAS,EAAE,YAAY,EAAE,UAAU,EAAE,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,EAAE,CAAC;YAC9H,MAAM,OAAO,GAAG,MAAM,iBAAiB,CAAC,IAAI,EAAE,KAAK,CAAC,KAAK,EAAE,MAAM,CAAC,CAAC;YACnE,MAAM,IAAI,GAAG,OAAO,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,cAAc,CAAC,KAAK,CAAC,KAAK,EAAE,SAAS,CAAC,CAAC;YAC1E,IAAI,IAAI,KAAK,SAAS,EAAE,CAAC;gBACvB,MAAM,KAAK,GAA4B,KAAK,CAAC,IAAI,EAAE,KAAK,IAAI,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,aAAa,EAAE,KAAK,CAAC;gBACnG,IAAI,KAAK,KAAK,SAAS,EAAE,CAAC;oBACxB,MAAM,eAAe,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,YAAY,CAAC,WAAW,EAAE,IAAI,CAAC,OAAO,EAAE,SAAS,CAAC,EAAE,MAAM,CAAC,CAAC;gBACpH,CAAC;qBAAM,CAAC;oBACN,MAAM,OAAO,GAAG,gBAAgB,CAAC,EAAE,GAAG,KAAK,EAAE,IAAI,EAAE,EAAE,KAAK,EAAE,EAAE,CAAC,CAAC;oBAChE,IAAI,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC,OAAO,CAAC,QAAQ,IAAI,IAAI,CAAC,GAAG,EAAE,GAAG,OAAO,CAAC,QAAQ,EAAE,CAAC;wBAC1E,OAAO,CAAC,QAAQ,GAAG,IAAI,CAAC;wBACxB,IAAI,CAAC;4BACH,MAAM,eAAe,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,YAAY,CAAC,OAAO,EAAE,IAAI,CAAC,OAAO,EAAE,mBAAmB,CAAC,KAAK,CAAC,KAAK,EAAE,OAAQ,CAAC,QAAQ,CAAC,EAAE,SAAS,CAAC,EAAE,MAAM,EAAE,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,IAAI,CAAC,GAAG,CAAC,MAAM,EAAE,OAAO,CAAC,QAAQ,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC,CAAC,CAAC,CAAC;4BACjO,OAAO,CAAC,SAAS,GAAG,IAAI,CAAC;wBAC3B,CAAC;wBAAC,OAAO,KAAK,EAAE,CAAC;4BACf,IAAI,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,4BAA4B,EAAE,GAAG,CAAC,KAAK,CAAC,IAAI,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE,KAAK,CAAC,IAAI,EAAE,CAAC,EAAE,OAAO,EAAE,6EAA6E,EAAE,KAAK,EAAE,CAAC,CAAC;wBAC9M,CAAC;wBACD,IAAI,IAAI,CAAC,GAAG,EAAE,GAAG,OAAO,CAAC,QAAQ;4BAAE,OAAO,KAAK,CAAC;oBAClD,CAAC;oBACD,MAAM,SAAS,GAAG,OAAO,CAAC,SAAS,IAAI,IAAI,CAAC,MAAM,KAAK,MAAM,CAAC;oBAC9D,IAAI,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC,SAAS,IAAI,IAAI,CAAC,GAAG,EAAE,GAAG,OAAO,CAAC,QAAQ;wBAAE,OAAO,KAAK,CAAC;oBACjF,MAAM,eAAe,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,YAAY,CAAC,OAAO,EAAE,IAAI,CAAC,OAAO,EAAE,SAAS,CAAC,EAAE,MAAM,CAAC,CAAC;gBAChH,CAAC;YACH,CAAC;YACD,IAAI,cAAc;gBAAE,MAAM,eAAe,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,IAAI,CAAC,GAAG,CAAC,cAAc,CAAC,KAAK,CAAC,OAAO,EAAE,KAAK,CAAC,KAAK,EAAE,SAAS,CAAC,EAAE,MAAM,EAAE,OAAO,CAAC,CAAC;YAC1I,QAAQ,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAC;YAC1B,IAAI,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,cAAc,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,eAAe,EAAE,GAAG,CAAC,KAAK,CAAC,IAAI,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE,KAAK,CAAC,IAAI,EAAE,CAAC,EAAE,OAAO,EAAE,cAAc,CAAC,CAAC,CAAC,0EAA0E,CAAC,CAAC,CAAC,wDAAwD,EAAE,CAAC,CAAC;YAC9R,OAAO,IAAI,CAAC;QACd,CAAC;QACD,SAAS,EAAE,CAAC,KAAoB,EAAU,EAAE,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,QAAQ,CAAC,GAAG,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,EAAE,QAAQ,IAAI,IAAI,CAAC,GAAG,EAAE,CAAC,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC;KAC1H,CAAC;AACJ,CAAC,CAAC"}

package/dist/commands/worker/coordinator.js

@@ -1,7 +1,8 @@
 import { randomUUID } from "node:crypto";
+import path from "node:path";
 import { setTimeout as delay } from "node:timers/promises";
 import { createCleanupDriver } from "./cleanup.js";
-import { createExecutionDriver, isWorkerCancellation, sameClaim, workerOperation } from "./execution.js";
+import { actualTaskPane, createExecutionDriver, isWorkerCancellation, liveAgent, sameClaim, settleWorkerStops, workerOperation } from "./execution.js";
 const key = (identity) => `${identity.projectId}/${identity.taskId}/${identity.claimId}`;
 const taskKey = (identity) => `${identity.projectId}/${identity.taskId}`;
 const remoteOwner = (origin, task) => {
@@ -148,10 +149,22 @@ export const createWorkerCoordinator = (options) => {
         } });
         jobs.set(identityKey, job);
     };
+    const recordMissingClaim = (owner, pane) => {
+        const task = options.store.getTask(owner);
+        if (task !== null)
+            return task;
+        if (pane === undefined && !options.herdr.tasks.pendingStops().some((stop) => sameClaim(stop.context, owner) && stop.context.serverOrigin === owner.serverOrigin))
+            return null;
+        const agent = pane?.kind ?? pane?.nativeSession?.agent;
+        if (agent === undefined)
+            throw new Error(`Cannot preserve ownership of ${key(owner)} without an observed native agent type; retain its Herdr resources and private instance.`);
+        // Persist ownership before a stop can close the only workspace proving it.
+        return options.store.registerPending({ ...owner, agent, sessionId: pane !== undefined && liveAgent(pane) && pane.nativeSession !== null ? pane.nativeSession.sessionId : null });
+    };
     const runCleanup = async (owner, deleteWorktree, signal) => {
         while (true) {
             const resources = await workerOperation((operation) => options.herdr.tasks.listResources(operation), signal);
-            const task = options.store.getTask(owner);
+            const task = recordMissingClaim(owner, actualTaskPane(owner, resources));
             const completed = await cleanup.advance({ owner, project: projectFor(owner), ...(task === null ? {} : { task }) }, resources, deleteWorktree, signal);
             if (completed) {
                 if (deleteWorktree && task !== null && task.status !== "done")
@@ -344,8 +357,7 @@ export const createWorkerCoordinator = (options) => {
         shutdown: async () => {
             shuttingDown = true;
             for (const running of controllers.values())
-                if (!running.terminal)
-                    running.controller.abort(new Error("Worker shutdown requested."));
+                running.controller.abort(new Error("Worker shutdown requested."));
             await Promise.all(jobs.values());
             let complete = true;
             const owners = new Map(ending);
@@ -386,7 +398,19 @@ export const createWorkerCoordinator = (options) => {
             }));
             await Promise.all([...owners.values()].map(async (owner) => {
                 try {
-                    await serialize(owner, () => runCleanup(owner, ending.has(key(owner))));
+                    await serialize(owner, async () => {
+                        if (options.store.getTask(owner) === null) {
+                            const observed = await workerOperation((operation) => options.herdr.tasks.listResources(operation));
+                            recordMissingClaim(owner, actualTaskPane(owner, observed));
+                        }
+                        await settleWorkerStops(deps, owner);
+                        const resources = await workerOperation((operation) => options.herdr.tasks.listResources(operation));
+                        const pane = actualTaskPane(owner, resources);
+                        if (pane === undefined)
+                            return;
+                        const context = { ...owner, cwd: path.join(projectFor(owner).localPath, ".worktrees", "daynight", owner.taskId) };
+                        await workerOperation((operation) => options.herdr.tasks.stopAndClose(context, pane.binding, operation));
+                    });
                 }
                 catch (error) {
                     complete = false;