delegation-layer 0.1.37 → 0.1.39

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "delegation-layer",
-  "version": "0.1.37",
+  "version": "0.1.39",
   "description": "Multi-provider AI agent delegation CLI and Agent Skill for running bounded coding tasks across provider CLIs.",
   "keywords": [
     "ai-agents",

package/plugins/delegation-layer/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "delegation-layer",
   "displayName": "Delegation Layer",
-  "version": "0.1.37",
+  "version": "0.1.39",
   "description": "Consult external AI harnesses and CCR-configured models for reviews, research, implementation, and debate through the resumable Delegate CLI.",
   "author": {
     "name": "Hesham Karam",

package/plugins/delegation-layer/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "delegation-layer",
-  "version": "0.1.37",
+  "version": "0.1.39",
   "description": "Consult external AI harnesses and CCR-configured models for reviews, research, implementation, and debate through the resumable Delegate CLI.",
   "author": {
     "name": "Hesham Karam",

package/plugins/delegation-layer/skills/agent-integration/SKILL.md

@@ -128,8 +128,9 @@ tasks may proceed; the failed attempt must remain reported as failed or blocked.
     report delegate's evidence; do not assume the user's configuration is faulty
     or remove MCP servers, plugins, settings, or credentials to make it pass.
 11. The model chooses ordinary-task fan-out by issuing independent `dispatch`
-    commands concurrently. The private supervisor does not impose a task-count
-    or CPU-based limit. Use this for independent investigation, debate, review,
+    commands concurrently. There is no fixed task-count cap, but Delegate
+    refuses a new request while the host shows confirmed resource pressure (see
+    the `resource_pressure` row below). Use this for independent investigation, debate, review,
     or provider comparison. For independent parallel writes, choose
     `--isolation git-worktree` automatically unless the user explicitly chooses
     shared coordination; the model chooses fan-out and task scope. A read-only
@@ -313,10 +314,13 @@ for **each attempt**, including requests issued together:
 | `task_record: not_created`, `failure.code: supervisor_upgrade_required`, and `failure.next_action: run_supervisor_migrate` | Run `delegate --root "<the exact absolute state root used by the failed command>" supervisor migrate --json` once. Retry the exact original admission argv once only after `supervisor_control.state: migrated` and `supervisor_control.next_action: retry_dispatch`; otherwise stop and report the migration response. Preserve an explicit custom root exactly. A failed `continue` must be retried as the same `continue`; never replace it with a fresh `dispatch` or a direct provider call. |
 | `task_record: not_created` and `failure.next_action: correct_request` | Correct that request and retry it. |
 | `task_record: not_created`, `failure.code: workspace_provision_pending` or `workspace_busy`, and `failure.next_action: watch_workspace` | Follow [managed workspace recovery](references/result-handling.md#managed-workspace-results) using the same root and workspace. Once ready, retry the exact admission command and inputs. A failed `continue` remains that same `continue`, never a new dispatch. |
+| `task_record: not_created`, `failure.code: resource_pressure`, `failure.next_action: retry_later`, and `failure.retry_after_seconds: 30` | Delegate checked the host and confirmed resource pressure, so no ordinary task record was created and no provider task is running for this attempt. Do not poll or observe a task. Choose one: report the refusal and stop, or wait at least 30 seconds in the foreground and retry the exact original admission argv once. A `continue` stays that same `continue`. If the retry is refused again, report and stop. Never loop, retry in the background, schedule a retry, or run Pueue or process commands. The 30 seconds is advice, not a guarantee that the retry will pass. |
 | `task_record: not_created` with any other next action | Report that attempt's failure and stop it. Do not diagnose provider setup or substitute an integration. |
-| `task_record: created` | Use `status` before taking any other action. Do not dispatch again. |
+| `task_record: created` | Use `status` before taking any other action. Do not dispatch again. An optional `resource_admission` object with `status: unknown` and `warnings` only means a resource metric could not be read; the task was admitted. Keep the warning with your report, observe that same task with `status` and `collect`, and do not redispatch. |
 | `task_record: unknown` or an ambiguous response | Stop and report; do not retry an uncertain task creation. |
 
+`resource_admission` is optional. Its `status` is `clear`, `pressure`, or `unknown`, and `warnings` is a short list of bounded entries with `code`, optional `metric`, `reason_code`, and `message`. An unknown metric adds a warning and never refuses by itself, but confirmed pressure on an independent metric still refuses. The check runs only for a new dispatch or `continue`; `status`, `collect`, `cancel`, and the recovery of an existing task are not checked or refused.
+
 One attempt's `stop_and_report` does not prevent correcting another independent
 request's usage error. Keep the failed attempt reported as failed. With an
 explicit task ID, absence can race another dispatch creating the same ID;

package/plugins/delegation-layer/skills/agent-integration/references/collaboration.md

@@ -3,7 +3,9 @@
 For independent parallel write work, choose `--isolation git-worktree`
 automatically unless the user explicitly chooses shared coordination. The
 model chooses fan-out and task scope; the supervisor has no fixed task-count
-cap or TTL eviction. A read-only review may attach a retained workspace with
+cap or TTL eviction. Delegate still refuses a new request while the host shows
+confirmed resource pressure: read each response separately, and handle a
+`resource_pressure` refusal as in [result handling](result-handling.md). A read-only review may attach a retained workspace with
 `--workspace ID`. The single managed-workspace policy, capture boundary, and
 release rules live in [managed workspace guidance](workspaces.md); do not
 restate them in each collaboration brief.
@@ -72,7 +74,8 @@ Keep the request-to-label mapping alongside those files. Include any exact
 requested model/effort in its invocation. Read both exit codes, stderr, and JSON
 responses independently; shell `wait` is not proof that either dispatch succeeded.
 Poll only tasks with `task_record: created`. A returned task ID with
-`task_record: not_created` does not identify an observable task.
+`task_record: not_created` does not identify an observable task. One request's
+`resource_pressure` refusal does not change another request's response.
 
 ## Wait within the current turn
 

package/plugins/delegation-layer/skills/agent-integration/references/continuation.md

@@ -40,13 +40,27 @@ but it does not authorize a fresh dispatch. Apply the remaining `task_record`
 error rules in [result handling](result-handling.md) before retrying or
 observing.
 
+Run `continue` with the same state root as the predecessor. The new turn uses
+the environment of the process that calls `continue`, not an environment saved
+by the predecessor, so the exact recorded session must be available there. If
+`continue` fails because it is not, report the failure and stop. Do not copy
+credentials or settings from another environment, choose a fresh session or
+another provider, or dispatch again to repair the failure.
+
 When the predecessor is bound to a managed workspace, `continue --task` carries
-the recorded workspace, working directory, provider session, and environment
-to the new task ID. It does not mutate the predecessor's immutable request or
+the recorded workspace, working directory, and provider session to the new task
+ID. The new turn runs in the calling environment. It does not mutate the predecessor's immutable request or
 reservation. A changed provider request is a new turn and must pass the normal
 workspace-use reservation. Read [managed workspace guidance](workspaces.md)
 before attaching another provider, review, or verification operation.
 
+A new `continue` is checked for host resource pressure before the successor is
+created. If it returns `resource_pressure` with `task_record: "not_created"` and
+`next_action: "retry_later"`, follow the bounded choice in
+[result handling](result-handling.md): report and stop, or wait 30 seconds and
+retry the exact `continue --task PREDECESSOR_ID` once. Never replace it with a
+fresh dispatch. A predecessor that is already running is not affected.
+
 If `continue` returns `workspace_busy` with `task_record: "not_created"` and
 `next_action: "watch_workspace"`, observe that workspace with the same root.
 Then retry the exact `continue --task PREDECESSOR_ID` after it becomes retained.

package/plugins/delegation-layer/skills/agent-integration/references/result-handling.md

@@ -20,12 +20,21 @@ the same as a successful provider result.
    or call a provider directly to replace a failed continuation. Also handle
    `workspace_provision_pending` or `workspace_busy` with `watch_workspace`
    using [managed workspace recovery](#managed-workspace-results) before the
-   generic stop rule. For every other `not_created` response, do not poll;
+   generic stop rule. A `resource_pressure` refusal (`failure.next_action:
+   "retry_later"`, `failure.retry_after_seconds: 30`, `task_record: "not_created"`) is
+   a bounded caller choice: report and stop, or wait at least 30 seconds in the
+   foreground and retry the exact original admission once; `continue` remains
+   `continue`. Never loop, retry in the background, or poll. For every other
+   `not_created` response, do not poll;
    correct the request only if
    `failure.next_action` is `correct_request`, otherwise report and stop. When
    `task_record` is `unknown`, stop and report without polling or retrying.
    Status and collect can report `admission: "unknown"` alongside valid terminal
-   evidence for an existing task.
+   evidence for an existing task. An admitted task can carry
+   `resource_admission` with `status: "unknown"` and bounded `warnings`
+   (for example `resource_observation_unavailable`). That is a warning about
+   an unreadable host metric, not a failure: observe that same task with
+   `status` and `collect`, and do not redispatch.
 3. If `status` is `timed_out`, follow the continuation procedure before treating
    pending publication as a reason to wait. `continuation.resumable: true`
    permits a linked successor even when no outcome has been published. An

package/plugins/delegation-layer/skills/agent-integration/references/workspaces.md

@@ -102,9 +102,11 @@ flag. This auxiliary budget is separate from and does not renew the provider
 task budget. The existing `codex:review` default remains 1 hour.
 
 `continue --task PREDECESSOR_ID` inherits the predecessor's managed workspace,
-working directory, provider session, and recorded environment, while creating
-a new task ID. A changed provider request is a new turn; it must not mutate the
-predecessor's immutable records. A retained workspace can be used by a
+working directory, and provider session, while creating a new task ID. The new
+turn runs in the calling environment, so the exact recorded session must be
+available there; see [continuation](continuation.md). The predecessor's
+admitted records stay unchanged. A changed provider request is a new turn; it
+must not mutate the predecessor's immutable records. A retained workspace can be used by a
 read-only review by attaching its ID, for example:
 
 ```text

package/skills/agent-integration/SKILL.md

@@ -128,8 +128,9 @@ tasks may proceed; the failed attempt must remain reported as failed or blocked.
     report delegate's evidence; do not assume the user's configuration is faulty
     or remove MCP servers, plugins, settings, or credentials to make it pass.
 11. The model chooses ordinary-task fan-out by issuing independent `dispatch`
-    commands concurrently. The private supervisor does not impose a task-count
-    or CPU-based limit. Use this for independent investigation, debate, review,
+    commands concurrently. There is no fixed task-count cap, but Delegate
+    refuses a new request while the host shows confirmed resource pressure (see
+    the `resource_pressure` row below). Use this for independent investigation, debate, review,
     or provider comparison. For independent parallel writes, choose
     `--isolation git-worktree` automatically unless the user explicitly chooses
     shared coordination; the model chooses fan-out and task scope. A read-only
@@ -313,10 +314,13 @@ for **each attempt**, including requests issued together:
 | `task_record: not_created`, `failure.code: supervisor_upgrade_required`, and `failure.next_action: run_supervisor_migrate` | Run `delegate --root "<the exact absolute state root used by the failed command>" supervisor migrate --json` once. Retry the exact original admission argv once only after `supervisor_control.state: migrated` and `supervisor_control.next_action: retry_dispatch`; otherwise stop and report the migration response. Preserve an explicit custom root exactly. A failed `continue` must be retried as the same `continue`; never replace it with a fresh `dispatch` or a direct provider call. |
 | `task_record: not_created` and `failure.next_action: correct_request` | Correct that request and retry it. |
 | `task_record: not_created`, `failure.code: workspace_provision_pending` or `workspace_busy`, and `failure.next_action: watch_workspace` | Follow [managed workspace recovery](references/result-handling.md#managed-workspace-results) using the same root and workspace. Once ready, retry the exact admission command and inputs. A failed `continue` remains that same `continue`, never a new dispatch. |
+| `task_record: not_created`, `failure.code: resource_pressure`, `failure.next_action: retry_later`, and `failure.retry_after_seconds: 30` | Delegate checked the host and confirmed resource pressure, so no ordinary task record was created and no provider task is running for this attempt. Do not poll or observe a task. Choose one: report the refusal and stop, or wait at least 30 seconds in the foreground and retry the exact original admission argv once. A `continue` stays that same `continue`. If the retry is refused again, report and stop. Never loop, retry in the background, schedule a retry, or run Pueue or process commands. The 30 seconds is advice, not a guarantee that the retry will pass. |
 | `task_record: not_created` with any other next action | Report that attempt's failure and stop it. Do not diagnose provider setup or substitute an integration. |
-| `task_record: created` | Use `status` before taking any other action. Do not dispatch again. |
+| `task_record: created` | Use `status` before taking any other action. Do not dispatch again. An optional `resource_admission` object with `status: unknown` and `warnings` only means a resource metric could not be read; the task was admitted. Keep the warning with your report, observe that same task with `status` and `collect`, and do not redispatch. |
 | `task_record: unknown` or an ambiguous response | Stop and report; do not retry an uncertain task creation. |
 
+`resource_admission` is optional. Its `status` is `clear`, `pressure`, or `unknown`, and `warnings` is a short list of bounded entries with `code`, optional `metric`, `reason_code`, and `message`. An unknown metric adds a warning and never refuses by itself, but confirmed pressure on an independent metric still refuses. The check runs only for a new dispatch or `continue`; `status`, `collect`, `cancel`, and the recovery of an existing task are not checked or refused.
+
 One attempt's `stop_and_report` does not prevent correcting another independent
 request's usage error. Keep the failed attempt reported as failed. With an
 explicit task ID, absence can race another dispatch creating the same ID;

package/skills/agent-integration/references/collaboration.md

@@ -3,7 +3,9 @@
 For independent parallel write work, choose `--isolation git-worktree`
 automatically unless the user explicitly chooses shared coordination. The
 model chooses fan-out and task scope; the supervisor has no fixed task-count
-cap or TTL eviction. A read-only review may attach a retained workspace with
+cap or TTL eviction. Delegate still refuses a new request while the host shows
+confirmed resource pressure: read each response separately, and handle a
+`resource_pressure` refusal as in [result handling](result-handling.md). A read-only review may attach a retained workspace with
 `--workspace ID`. The single managed-workspace policy, capture boundary, and
 release rules live in [managed workspace guidance](workspaces.md); do not
 restate them in each collaboration brief.
@@ -72,7 +74,8 @@ Keep the request-to-label mapping alongside those files. Include any exact
 requested model/effort in its invocation. Read both exit codes, stderr, and JSON
 responses independently; shell `wait` is not proof that either dispatch succeeded.
 Poll only tasks with `task_record: created`. A returned task ID with
-`task_record: not_created` does not identify an observable task.
+`task_record: not_created` does not identify an observable task. One request's
+`resource_pressure` refusal does not change another request's response.
 
 ## Wait within the current turn
 

package/skills/agent-integration/references/continuation.md

@@ -40,13 +40,27 @@ but it does not authorize a fresh dispatch. Apply the remaining `task_record`
 error rules in [result handling](result-handling.md) before retrying or
 observing.
 
+Run `continue` with the same state root as the predecessor. The new turn uses
+the environment of the process that calls `continue`, not an environment saved
+by the predecessor, so the exact recorded session must be available there. If
+`continue` fails because it is not, report the failure and stop. Do not copy
+credentials or settings from another environment, choose a fresh session or
+another provider, or dispatch again to repair the failure.
+
 When the predecessor is bound to a managed workspace, `continue --task` carries
-the recorded workspace, working directory, provider session, and environment
-to the new task ID. It does not mutate the predecessor's immutable request or
+the recorded workspace, working directory, and provider session to the new task
+ID. The new turn runs in the calling environment. It does not mutate the predecessor's immutable request or
 reservation. A changed provider request is a new turn and must pass the normal
 workspace-use reservation. Read [managed workspace guidance](workspaces.md)
 before attaching another provider, review, or verification operation.
 
+A new `continue` is checked for host resource pressure before the successor is
+created. If it returns `resource_pressure` with `task_record: "not_created"` and
+`next_action: "retry_later"`, follow the bounded choice in
+[result handling](result-handling.md): report and stop, or wait 30 seconds and
+retry the exact `continue --task PREDECESSOR_ID` once. Never replace it with a
+fresh dispatch. A predecessor that is already running is not affected.
+
 If `continue` returns `workspace_busy` with `task_record: "not_created"` and
 `next_action: "watch_workspace"`, observe that workspace with the same root.
 Then retry the exact `continue --task PREDECESSOR_ID` after it becomes retained.

package/skills/agent-integration/references/result-handling.md

@@ -20,12 +20,21 @@ the same as a successful provider result.
    or call a provider directly to replace a failed continuation. Also handle
    `workspace_provision_pending` or `workspace_busy` with `watch_workspace`
    using [managed workspace recovery](#managed-workspace-results) before the
-   generic stop rule. For every other `not_created` response, do not poll;
+   generic stop rule. A `resource_pressure` refusal (`failure.next_action:
+   "retry_later"`, `failure.retry_after_seconds: 30`, `task_record: "not_created"`) is
+   a bounded caller choice: report and stop, or wait at least 30 seconds in the
+   foreground and retry the exact original admission once; `continue` remains
+   `continue`. Never loop, retry in the background, or poll. For every other
+   `not_created` response, do not poll;
    correct the request only if
    `failure.next_action` is `correct_request`, otherwise report and stop. When
    `task_record` is `unknown`, stop and report without polling or retrying.
    Status and collect can report `admission: "unknown"` alongside valid terminal
-   evidence for an existing task.
+   evidence for an existing task. An admitted task can carry
+   `resource_admission` with `status: "unknown"` and bounded `warnings`
+   (for example `resource_observation_unavailable`). That is a warning about
+   an unreadable host metric, not a failure: observe that same task with
+   `status` and `collect`, and do not redispatch.
 3. If `status` is `timed_out`, follow the continuation procedure before treating
    pending publication as a reason to wait. `continuation.resumable: true`
    permits a linked successor even when no outcome has been published. An

package/skills/agent-integration/references/workspaces.md

@@ -102,9 +102,11 @@ flag. This auxiliary budget is separate from and does not renew the provider
 task budget. The existing `codex:review` default remains 1 hour.
 
 `continue --task PREDECESSOR_ID` inherits the predecessor's managed workspace,
-working directory, provider session, and recorded environment, while creating
-a new task ID. A changed provider request is a new turn; it must not mutate the
-predecessor's immutable records. A retained workspace can be used by a
+working directory, and provider session, while creating a new task ID. The new
+turn runs in the calling environment, so the exact recorded session must be
+available there; see [continuation](continuation.md). The predecessor's
+admitted records stay unchanged. A changed provider request is a new turn; it
+must not mutate the predecessor's immutable records. A retained workspace can be used by a
 read-only review by attaching its ID, for example:
 
 ```text