fix(subagent): address background-first review

2026-08-29 04:26:38 +00:00 · 2026-08-11 21:52:59 +08:00
parent 98d4551597
commit c778b5b0db
56 changed files with 173 additions and 146 deletions
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-06-manager-owned-subagent-settlement-delivery.md
-2026-08-06-manager-owned-subagent-settlement-delivery.md: e06fe2b4ca7dd9a975f70524979de09d13cdcf79
-2026-08-06-manager-owned-subagent-settlement-delivery.zh.md: 77e8b5e4bae9b05e08bf2c4a4bf997b688cd1157
+2026-08-06-manager-owned-subagent-settlement-delivery.md: 11669d4603e658d1478557f81c2d2b4d5495bca7
+2026-08-06-manager-owned-subagent-settlement-delivery.zh.md: f3684777ccb3800226803e998438147ebc1dbf16
@@ -16,7 +16,7 @@ The signal already existed. `subagent/end` has carried `stopReason` and `lastAss

 The continuation manager delivers the account itself, from inside the disposal transaction that ends the Activation.

-When a resident Activation settles, `notifySettlement()` resolves the child's durable direct parent and sends it one user-role message: the epoch's outcome as a sentence the parent can act on, then the child's final assistant content, or a statement that it produced none. Delivery is unconditional for every child whose id a caller actually received. It does not consult whether the child reported, and it keeps no bookkeeping that could make the promise conditional — that unconditionality is what lets `tool-subagent` tell the model "you are told when it finishes, so never poll or wait on it" and have that be true. A materialization rolled back before its first accepted message stays silent, because the caller was told that child was not established.
+When a resident Activation settles, `notifySettlement()` resolves the child's durable direct parent and sends it one user-role message: the epoch's outcome as a sentence the parent can act on, then the child's final assistant content, or a statement that it produced none. Delivery is unconditional for every child whose id a caller actually received. It does not consult whether the child reported, and it keeps no bookkeeping that could make the promise conditional — that unconditionality is what lets `tool-subagent` promise a runtime notice containing the outcome and any final assistant message. A materialization rolled back before its first accepted message stays silent, because the caller was told that child was not established.

 ### Provenance

@@ -44,7 +44,7 @@ Delivery never blocks or fails teardown. A rejected send is logged and dropped,

 ### The epoch's own log is the whole account

-`epochStopReason()` reads the epoch's outcome from its own log, because teardown succeeding says nothing about whether the model errored, hit its ceiling, or was stopped. Reading turns alone got that wrong twice, in the same shape both times: a turn stopped before its first step leaves a `turn/end` indistinguishable from the balanced no-op turns a rejection or an emptied claim produces, so the filter that skipped those also skipped real endings and answered with the previous turn's clean completion. The durability checkpoint (`dsh-session-checkpoint-policy`, in every shipped profile) and prompt assembly both run at that boundary and both propagate, and `Inbox.claim()` has already taken the messages by then — so the parent was told a child finished while the delivery it was waiting on had been swallowed. Under a promise that says "you are told when it finishes, so never poll", that is the one failure a parent cannot detect and will not retry.
+`epochStopReason()` reads the epoch's outcome from its own log, because teardown succeeding says nothing about whether the model errored, hit its ceiling, or was stopped. Reading turns alone got that wrong twice, in the same shape both times: a turn stopped before its first step leaves a `turn/end` indistinguishable from the balanced no-op turns a rejection or an emptied claim produces, so the filter that skipped those also skipped real endings and answered with the previous turn's clean completion. The durability checkpoint (`dsh-session-checkpoint-policy`, in every shipped profile) and prompt assembly both run at that boundary and both propagate, and `Inbox.claim()` has already taken the messages by then — so the parent was told a child finished while the delivery it was waiting on had been swallowed. Under the advertised automatic settlement notice, that is the one failure a parent cannot detect and will not retry.

 The missing fact was never the turn's; it was the inbox's. `Inbox` logs every mutation with `removedCount` and marks a cancellation `outcome: 'canceled'`, which separates a turn claiming its input from work being dropped unrun. `foldConsumedWork()` in `dsh-agent` folds both vocabularies into one answer: the latest turn that accounts for consumed work — stepped, or claimed-then-failed, stopped, or rejected — and whether accepted work was cancelled after it with no turn opening over it. A `blocked` end over claimed input is an account too: the pre-step rejection that produced it — a hook deny, a policy plugin — discarded the messages the turn claimed, so the notice says the child declined rather than finished. Only a `blocked` turn that claimed nothing stays invisible.

@@ -60,7 +60,7 @@ Three assembled ACP scenarios cover the notice: a child that never reports, a ch

 `subagent-continuable` is the one that pins a failure. Its child's last turn dies on the forced durability checkpoint without entering a step, so that transcript is where the stop-reason rule above is visible end to end: the notice says the child *failed*, carries the earlier `SECOND_OK` as its last content rather than as a result, and the parent's own acknowledgement turn reaches the ACP client.

-A keyless headless Loader snapshot covers the user-visible path end to end. Its replay parent starts one continuable child with `run_in_background: true`, never calls `list_agents`, `send_message`, or Task tools, consumes the manager-authored `subagent-settled` notice, and produces its final answer. The child never calls `report`, so the transcript cannot pass through the cooperative report path. A test-only Loader fence holds the parent's post-spawn request until the real manager notice enters its inbox, removing platform scheduling from the transcript without synthesizing the notice.
+A keyless headless Loader snapshot covers the user-visible path end to end. Its replay parent omits `run_in_background` to exercise the continuable background default, never calls `list_agents`, `send_message`, or Task tools, consumes the manager-authored `subagent-settled` notice, and produces its final answer. The child never calls `report`, so the transcript cannot pass through the cooperative report path. A test-only Loader fence holds the parent's post-spawn request until the real manager notice enters its inbox, removing platform scheduling from the transcript without synthesizing the notice.

 `subagent-report` needed one more concession. With the shipped waking report default, that scenario has two independent parent wakes — the report and the settlement — and whether the second extends the first's turn or opens its own is a genuine coin flip that measured 50/50 across runs. No authored transcript can hold both orders. Its overlay therefore pins `reportDelivery: quiet`, leaving settlement as the only wake, and a snapshot-only pre-step fence holds the child until the parent's spawn turn ends so that wake opens one deterministic turn claiming both messages. The waking report default keeps its coverage in the report package's own tests.

@@ -16,7 +16,7 @@ Status: implemented

 继续执行管理器自己投递这份记账，就在结束 Activation 的那笔 dispose 事务内部完成。

-当驻留 Activation 结算时，`notifySettlement()` 解析该 child 持久化的直接父级，并向它发送一条用户角色消息：先是父级可据以行动的一句结果说明，然后是 child 的最终 assistant 内容，或一句说明它没有产出内容。对每个调用方真正拿到过 id 的 child，投递都是无条件的。它不查询 child 是否上报过，也不保留任何可能让这项承诺变成有条件的记账——正是这种无条件性，才让 `tool-subagent` 能够告诉模型「它结束时你会被告知，因此绝不要轮询或等待它」并且这句话为真。在第一条消息被接受之前就回滚的物化保持静默，因为调用方已被告知该 child 未建立。
+当驻留 Activation 结算时，`notifySettlement()` 解析该 child 持久化的直接父级，并向它发送一条用户角色消息：先是父级可据以行动的一句结果说明，然后是 child 的最终 assistant 内容，或一句说明它没有产出内容。对每个调用方真正拿到过 id 的 child，投递都是无条件的。它不查询 child 是否上报过，也不保留任何可能让这项承诺变成有条件的记账——正是这种无条件性，才让 `tool-subagent` 能够承诺一条包含结局与可能存在的最终 assistant 消息的运行时通知。在第一条消息被接受之前就回滚的物化保持静默，因为调用方已被告知该 child 未建立。

 ### 来源信息

@@ -44,7 +44,7 @@ Status: implemented

 ### epoch 自己的日志就是全部交代

-`epochStopReason()` 从 epoch 自己的日志读取结局，因为拆卸成功与否，对「模型是否报错、是否撞到上限、是否被停下」什么也没说明。只读轮次这件事已经错了两次，而两次的形状相同：在第一个 step 之前被停下的轮次，其 `turn/end` 与「拒绝」或「被清空的认领」产生的平衡空转轮次长得一模一样，于是那道用来跳过后者的过滤，也把真实的结局一起跳过了，转而用上一个轮次的干净收尾作答。持久化检查点（`dsh-session-checkpoint-policy`，存在于每个随附 profile 中）与提示词组装都运行在这个边界上、且都会向外传播，而此时 `Inbox.claim()` 已经把消息取走了——于是父级被告知 child 已完成，而它正在等待的那条投递已被吞掉。在「你会在它完成时被告知，所以永远不要轮询」这一承诺之下，这恰恰是父级无法察觉、也不会重试的那一种失败。
+`epochStopReason()` 从 epoch 自己的日志读取结局，因为拆卸成功与否，对「模型是否报错、是否撞到上限、是否被停下」什么也没说明。只读轮次这件事已经错了两次，而两次的形状相同：在第一个 step 之前被停下的轮次，其 `turn/end` 与「拒绝」或「被清空的认领」产生的平衡空转轮次长得一模一样，于是那道用来跳过后者的过滤，也把真实的结局一起跳过了，转而用上一个轮次的干净收尾作答。持久化检查点（`dsh-session-checkpoint-policy`，存在于每个随附 profile 中）与提示词组装都运行在这个边界上、且都会向外传播，而此时 `Inbox.claim()` 已经把消息取走了——于是父级被告知 child 已完成，而它正在等待的那条投递已被吞掉。在已公布的自动结算通知约定下，这恰恰是父级无法察觉、也不会重试的那一种失败。

 缺失的事实从来不属于轮次，而属于 inbox。`Inbox` 会把每次改动连同 `removedCount` 一起记入日志，并给取消标记 `outcome: 'canceled'`，这就把「某个轮次认领了它的输入」与「工作被丢弃且从未运行」区分开来。`dsh-agent` 中的 `foldConsumedWork()` 把两套词汇折叠成一个答案：能为已消费工作作出交代的最新轮次——进入过 step 的，或认领后失败、被停下或被拒绝的——以及此后是否有已接受的工作被取消、而没有任何轮次为它开启过。认领过输入、以 `blocked` 结束的轮次同样是一份交代：产生它的 pre-step 拒绝——hook deny、策略插件——把该轮次认领的消息一并丢弃了，因此通知会说 child 拒绝了任务，而不是完成了任务。只有没认领任何输入的 `blocked` 轮次保持不可见。

@@ -60,7 +60,7 @@ Status: implemented

 `subagent-continuable` 是其中固定失败结局的那个。它的 child 最后一个轮次在被强制的持久化检查点上死亡，且未进入任何 step，因此该 transcript 正是上面那条终止原因规则的端到端可见之处：通知说该 child **失败**，把此前的 `SECOND_OK` 作为它最后产出的内容而非结果携带，而父级自己的确认轮次会到达 ACP 客户端。

-另有一个无密钥的 headless Loader 快照端到端覆盖用户可见路径。其重放父级通过 `run_in_background: true` 启动一个可继续 child，从不调用 `list_agents`、`send_message` 或 Task 工具，消费管理器写入的 `subagent-settled` 通知，并给出最终答案。child 从不调用 `report`，因此该 transcript 不可能经由协作式上报路径通过。一个仅用于测试的 Loader 栅栏会把父级启动后的请求保持到真实管理器通知进入其 inbox 为止，从 transcript 中排除平台调度差异，但不会伪造该通知。
+另有一个无密钥的 headless Loader 快照端到端覆盖用户可见路径。其重放父级省略 `run_in_background` 以覆盖可继续后台默认路径，从不调用 `list_agents`、`send_message` 或 Task 工具，消费管理器写入的 `subagent-settled` 通知，并给出最终答案。child 从不调用 `report`，因此该 transcript 不可能经由协作式上报路径通过。一个仅用于测试的 Loader 栅栏会把父级启动后的请求保持到真实管理器通知进入其 inbox 为止，从 transcript 中排除平台调度差异，但不会伪造该通知。

 `subagent-report` 还需要多做一步让步。在随附的唤醒上报默认值下，该场景有两个互相独立的父级唤醒——上报与结算——而第二个究竟是延长第一个的轮次还是另开一个轮次，是一枚真正的硬币，多次运行实测约为五五开。任何手写 transcript 都无法同时容纳两种顺序。因此它的 overlay 固定 `reportDelivery: quiet`，使结算成为唯一唤醒；另一个仅用于快照的 pre-step 栅栏会把 child 保持到父级启动轮次结束，使这次唤醒开启一个确定轮次并同时认领两条消息。唤醒上报默认值的覆盖则保留在 report 包自身的测试中。

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-11-background-first-continuable-delegation.md
-2026-08-11-background-first-continuable-delegation.md: a6393cc7f97e1447ad1eaec83325337e6385254e
-2026-08-11-background-first-continuable-delegation.zh.md: 4a14ca9c4f5189a44b69eb6fe8c2c4792f7fcb6c
+2026-08-11-background-first-continuable-delegation.md: e90b0a97cd5eeb273c8084d231ced003a661b978
+2026-08-11-background-first-continuable-delegation.zh.md: b8f14e0c40c341fc91b2fd0dc8c3f00fc2e14b66
@@ -18,7 +18,7 @@ The model-facing text divides responsibility by location:

 - the tool description states the call behavior, durable id, runtime settlement notice, follow-up through `send_message`, and the explicit foreground override;
 - the `run_in_background` parameter states the lifecycle-specific default and when to override it;
- a `tool:<toolName>` system-prompt section tells the model to start independent delegations together, continue useful work while they run, and choose foreground only when the next action depends on the result.
+- a `tool:<toolName>` system-prompt section tells the model to start independent delegations together, continue useful work while they run, and choose foreground only when the next action depends on the result. The section renders only when that tool remains visible in the assembly scope, so a child tool restriction removes the schema and its guidance together.

 The [continuable child report obligation](2026-08-06-continuable-child-report-obligation.md) remains unchanged: the child prompt requires one self-contained final report and earlier reports for findings that change the parent's next action. Manager-owned settlement remains unconditional and does not inspect whether a report arrived. The two messages may repeat final content, but they retain distinct authors and purposes: `report` is the child's explicit handoff, while settlement records how the run ended and preserves terminal output when the child cannot cooperate. `reportDelivery` remains deployment scheduling policy with `wakeup` as its default.

@@ -18,7 +18,7 @@ child 作用域的 `report` 提示词要求发送自包含的最终报告，而[

 - 工具描述说明调用行为、持久化 id、运行时结算通知、通过 `send_message` 继续对话，以及显式前台覆盖；
 - `run_in_background` 参数说明具体生命周期的默认值以及何时覆盖；
- `tool:<toolName>` 系统提示词 section 会告诉模型同时启动相互独立的委派、在它们运行时继续有用工作，并且仅当下一步动作依赖结果时选择前台。
+- `tool:<toolName>` 系统提示词 section 会告诉模型同时启动相互独立的委派、在它们运行时继续有用工作，并且仅当下一步动作依赖结果时选择前台。只有当该工具在组装作用域中仍可见时才会渲染这个 section，因此子级工具限制会同时移除 schema 与对应指引。

 [可继续 child 上报义务](2026-08-06-continuable-child-report-obligation.md)保持不变：child 提示词要求发送一份自包含的最终报告，并在发现会改变 parent 下一步动作的信息时提前报告。由管理器负责的结算仍然无条件执行，不检查报告是否已经到达。这两条消息可能重复最终内容，但作者和用途不同：`report` 是 child 的显式交接，结算则记录本次运行如何结束，并在 child 无法配合时保留终止输出。`reportDelivery` 仍是部署调度策略，默认值仍为 `wakeup`。

@@ -6,7 +6,7 @@
 {"type":"subagent/descriptor","seq":4,"time":1786357538308,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Check direct child"}}
 {"type":"step/start","seq":5,"time":1786357538310,"data":{"turn":1,"step":1}}
 {"type":"user/message","seq":6,"time":1785730458555,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"ebe0cfa0-a909-47e0-8294-28ad84a8fe77"},"surfaceOp":"append"}
-{"type":"user/message","seq":7,"time":1786357538310,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"1f81ee1b-b08e-4fba-a075-426e41dd03d4"},"surfaceOp":"append"}
+{"type":"user/message","seq":7,"time":1786357538310,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"10c6c81d-85a2-4c50-a8c2-2f58f309f070"},"surfaceOp":"append"}
 {"type":"session/title","seq":8,"time":1786357538310,"data":{"title":"Reply with exactly DIRECT_CHILD_OK and","messageSeqs":[6],"source":{"kind":"fallback"}}}
 {"type":"request/header","seq":9,"time":1785730458555,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"request/context","seq":10,"time":1785730458555,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
@@ -6,7 +6,7 @@
 {"type":"subagent/descriptor","seq":4,"time":1786357538469,"data":{"version":2,"mode":"one-shot","provider":"spawn"}}
 {"type":"step/start","seq":5,"time":1786357538470,"data":{"turn":1,"step":1}}
 {"type":"user/message","seq":6,"time":1785730458703,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"2ac2cc54-9bce-4cfa-a569-a64f51bc30a7"},"surfaceOp":"append"}
-{"type":"user/message","seq":7,"time":1786357538471,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"dbf0fe20-f0e0-4700-b0fc-d192f5e7b1ca"},"surfaceOp":"append"}
+{"type":"user/message","seq":7,"time":1786357538471,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"5a8c5ad7-352c-475a-9356-87510cc6b1a8"},"surfaceOp":"append"}
 {"type":"session/title","seq":8,"time":1786357538471,"data":{"title":"Reply with exactly WORKFLOW_CHILD_OK and","messageSeqs":[6],"source":{"kind":"fallback"}}}
 {"type":"request/header","seq":9,"time":1785730458703,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"request/context","seq":10,"time":1785730458703,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
@@ -21,7 +21,7 @@ Use the workflow tool ONLY when the user explicitly asks for a workflow or for l

 Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.

-Use subagent's continuable background route by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when you cannot take your next action without that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.
+Use subagent in the background by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when your next action depends on that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.

 ## Writing code for run_code

@@ -134,13 +134,13 @@ interface ToolArgsMap {
    /** The exact skill name from the available skills list. */
    name: string;
  } & Record<string, JsonValue>;
-  /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool uses its continuable background route by default and immediately returns a durable subagent id. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` to use a foreground run only when you must receive its result before taking your next action. */
+  /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool runs in the background by default, immediately returns a durable subagent id, and keeps the child conversation available for later turns. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` only when your next action depends on receiving the result. */
  subagent: {
    /** A short (3-5 word) description of the delegated task, for display. */
    description: string;
    /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */
    prompt: string;
-    /** Whether to use the continuable background route. Defaults to true. Set false to run in the foreground and wait only when your next action depends on its result. */
+    /** Whether to run in the background and return a durable subagent id immediately. Defaults to true. Set false to wait for the result when your next action depends on it. */
    run_in_background?: boolean;
  } & Record<string, JsonValue>;
  /** Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn). Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive its result, not its intermediate steps. This call waits for the subagent and returns its result. */
@@ -309,7 +309,7 @@
    },
    {
      "name": "subagent",
-      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool uses its continuable background route by default and immediately returns a durable subagent id. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` to use a foreground run only when you must receive its result before taking your next action.",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool runs in the background by default, immediately returns a durable subagent id, and keeps the child conversation available for later turns. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` only when your next action depends on receiving the result.",
      "parameters": {
        "type": "object",
        "properties": {
@@ -323,7 +323,7 @@
          },
          "run_in_background": {
            "type": "boolean",
-            "description": "Whether to use the continuable background route. Defaults to true. Set false to run in the foreground and wait only when your next action depends on its result."
+            "description": "Whether to run in the background and return a durable subagent id immediately. Defaults to true. Set false to wait for the result when your next action depends on it."
          }
        },
        "required": [
@@ -252,7 +252,7 @@
    },
    {
      "name": "subagent",
-      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool uses its continuable background route by default and immediately returns a durable subagent id. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` to use a foreground run only when you must receive its result before taking your next action.",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool runs in the background by default, immediately returns a durable subagent id, and keeps the child conversation available for later turns. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` only when your next action depends on receiving the result.",
      "parameters": {
        "type": "object",
        "properties": {
@@ -266,7 +266,7 @@
          },
          "run_in_background": {
            "type": "boolean",
-            "description": "Whether to use the continuable background route. Defaults to true. Set false to run in the foreground and wait only when your next action depends on its result."
+            "description": "Whether to run in the background and return a durable subagent id immediately. Defaults to true. Set false to wait for the result when your next action depends on it."
          }
        },
        "required": [
@@ -21,7 +21,7 @@ Use the workflow tool ONLY when the user explicitly asks for a workflow or for l

 Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.

-Use subagent's continuable background route by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when you cannot take your next action without that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.
+Use subagent in the background by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when your next action depends on that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.

 ## Writing code for run_code

@@ -117,13 +117,13 @@ interface ToolArgsMap {
    /** The exact skill name from the available skills list. */
    name: string;
  } & Record<string, JsonValue>;
-  /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool uses its continuable background route by default and immediately returns a durable subagent id. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` to use a foreground run only when you must receive its result before taking your next action. */
+  /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool runs in the background by default, immediately returns a durable subagent id, and keeps the child conversation available for later turns. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` only when your next action depends on receiving the result. */
  subagent: {
    /** A short (3-5 word) description of the delegated task, for display. */
    description: string;
    /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */
    prompt: string;
-    /** Whether to use the continuable background route. Defaults to true. Set false to run in the foreground and wait only when your next action depends on its result. */
+    /** Whether to run in the background and return a durable subagent id immediately. Defaults to true. Set false to wait for the result when your next action depends on it. */
    run_in_background?: boolean;
  } & Record<string, JsonValue>;
  /** Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn). Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive its result, not its intermediate steps. This call waits for the subagent and returns its result. */
@@ -23,4 +23,4 @@ Use the workflow tool ONLY when the user explicitly asks for a workflow or for l

 Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.

-Use subagent's continuable background route by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when you cannot take your next action without that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.
+Use subagent in the background by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when your next action depends on that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.
@@ -268,7 +268,7 @@
    },
    {
      "name": "subagent",
-      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool uses its continuable background route by default and immediately returns a durable subagent id. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` to use a foreground run only when you must receive its result before taking your next action.",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool runs in the background by default, immediately returns a durable subagent id, and keeps the child conversation available for later turns. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` only when your next action depends on receiving the result.",
      "parameters": {
        "type": "object",
        "properties": {
@@ -282,7 +282,7 @@
          },
          "run_in_background": {
            "type": "boolean",
-            "description": "Whether to use the continuable background route. Defaults to true. Set false to run in the foreground and wait only when your next action depends on its result."
+            "description": "Whether to run in the background and return a durable subagent id immediately. Defaults to true. Set false to wait for the result when your next action depends on it."
          }
        },
        "required": [
@@ -231,7 +231,7 @@
    },
    {
      "name": "subagent",
-      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool uses its continuable background route by default and immediately returns a durable subagent id. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` to use a foreground run only when you must receive its result before taking your next action.",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool runs in the background by default, immediately returns a durable subagent id, and keeps the child conversation available for later turns. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` only when your next action depends on receiving the result.",
      "parameters": {
        "type": "object",
        "properties": {
@@ -245,7 +245,7 @@
          },
          "run_in_background": {
            "type": "boolean",
-            "description": "Whether to use the continuable background route. Defaults to true. Set false to run in the foreground and wait only when your next action depends on its result."
+            "description": "Whether to run in the background and return a durable subagent id immediately. Defaults to true. Set false to wait for the result when your next action depends on it."
          }
        },
        "required": [
@@ -21,4 +21,4 @@ Use the workflow tool ONLY when the user explicitly asks for a workflow or for l

 Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.

-Use subagent's continuable background route by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when you cannot take your next action without that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.
+Use subagent in the background by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when your next action depends on that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.
@@ -231,7 +231,7 @@
    },
    {
      "name": "subagent",
-      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool uses its continuable background route by default and immediately returns a durable subagent id. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` to use a foreground run only when you must receive its result before taking your next action.",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool runs in the background by default, immediately returns a durable subagent id, and keeps the child conversation available for later turns. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` only when your next action depends on receiving the result.",
      "parameters": {
        "type": "object",
        "properties": {
@@ -245,7 +245,7 @@
          },
          "run_in_background": {
            "type": "boolean",
-            "description": "Whether to use the continuable background route. Defaults to true. Set false to run in the foreground and wait only when your next action depends on its result."
+            "description": "Whether to run in the background and return a durable subagent id immediately. Defaults to true. Set false to wait for the result when your next action depends on it."
          }
        },
        "required": [
@@ -23,4 +23,4 @@ Use the workflow tool ONLY when the user explicitly asks for a workflow or for l

 Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.

-Use subagent's continuable background route by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when you cannot take your next action without that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.
+Use subagent in the background by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when your next action depends on that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.
@@ -231,7 +231,7 @@
    },
    {
      "name": "subagent",
-      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool uses its continuable background route by default and immediately returns a durable subagent id. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` to use a foreground run only when you must receive its result before taking your next action.",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool runs in the background by default, immediately returns a durable subagent id, and keeps the child conversation available for later turns. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` only when your next action depends on receiving the result.",
      "parameters": {
        "type": "object",
        "properties": {
@@ -245,7 +245,7 @@
          },
          "run_in_background": {
            "type": "boolean",
-            "description": "Whether to use the continuable background route. Defaults to true. Set false to run in the foreground and wait only when your next action depends on its result."
+            "description": "Whether to run in the background and return a durable subagent id immediately. Defaults to true. Set false to wait for the result when your next action depends on it."
          }
        },
        "required": [
@@ -247,7 +247,7 @@
    },
    {
      "name": "subagent",
-      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool uses its continuable background route by default and immediately returns a durable subagent id. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` to use a foreground run only when you must receive its result before taking your next action.",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool runs in the background by default, immediately returns a durable subagent id, and keeps the child conversation available for later turns. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` only when your next action depends on receiving the result.",
      "parameters": {
        "type": "object",
        "properties": {
@@ -261,7 +261,7 @@
          },
          "run_in_background": {
            "type": "boolean",
-            "description": "Whether to use the continuable background route. Defaults to true. Set false to run in the foreground and wait only when your next action depends on its result."
+            "description": "Whether to run in the background and return a durable subagent id immediately. Defaults to true. Set false to wait for the result when your next action depends on it."
          }
        },
        "required": [
@@ -23,4 +23,4 @@ Use the workflow tool ONLY when the user explicitly asks for a workflow or for l

 Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.

-Use subagent's continuable background route by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when you cannot take your next action without that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.
+Use subagent in the background by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when your next action depends on that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.
@@ -435,7 +435,7 @@
    },
    {
      "name": "subagent",
-      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool uses its continuable background route by default and immediately returns a durable subagent id. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` to use a foreground run only when you must receive its result before taking your next action.",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool runs in the background by default, immediately returns a durable subagent id, and keeps the child conversation available for later turns. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` only when your next action depends on receiving the result.",
      "parameters": {
        "type": "object",
        "properties": {
@@ -449,7 +449,7 @@
          },
          "run_in_background": {
            "type": "boolean",
-            "description": "Whether to use the continuable background route. Defaults to true. Set false to run in the foreground and wait only when your next action depends on its result."
+            "description": "Whether to run in the background and return a durable subagent id immediately. Defaults to true. Set false to wait for the result when your next action depends on it."
          }
        },
        "required": [
@@ -294,7 +294,7 @@
    },
    {
      "name": "subagent",
-      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool uses its continuable background route by default and immediately returns a durable subagent id. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` to use a foreground run only when you must receive its result before taking your next action.",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool runs in the background by default, immediately returns a durable subagent id, and keeps the child conversation available for later turns. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` only when your next action depends on receiving the result.",
      "parameters": {
        "type": "object",
        "properties": {
@@ -308,7 +308,7 @@
          },
          "run_in_background": {
            "type": "boolean",
-            "description": "Whether to use the continuable background route. Defaults to true. Set false to run in the foreground and wait only when your next action depends on its result."
+            "description": "Whether to run in the background and return a durable subagent id immediately. Defaults to true. Set false to wait for the result when your next action depends on it."
          }
        },
        "required": [
@@ -21,6 +21,6 @@ Use the workflow tool ONLY when the user explicitly asks for a workflow or for l

 Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.

-Use subagent's continuable background route by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when you cannot take your next action without that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.
+Use subagent in the background by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when your next action depends on that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.

 Deliver your result with the report tool before you finish: call it once with a self-contained answer. The agent that started you shares your workspace but does not automatically receive your transcript, tool output, or reasoning, so a closing remark such as "done" leaves it nothing it can use. Report earlier as well whenever a partial finding changes what that agent should do next; reporting never ends your turn.
@@ -247,7 +247,7 @@
    },
    {
      "name": "subagent",
-      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool uses its continuable background route by default and immediately returns a durable subagent id. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` to use a foreground run only when you must receive its result before taking your next action.",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool runs in the background by default, immediately returns a durable subagent id, and keeps the child conversation available for later turns. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` only when your next action depends on receiving the result.",
      "parameters": {
        "type": "object",
        "properties": {
@@ -261,7 +261,7 @@
          },
          "run_in_background": {
            "type": "boolean",
-            "description": "Whether to use the continuable background route. Defaults to true. Set false to run in the foreground and wait only when your next action depends on its result."
+            "description": "Whether to run in the background and return a durable subagent id immediately. Defaults to true. Set false to wait for the result when your next action depends on it."
          }
        },
        "required": [
@@ -21,6 +21,6 @@ Use the workflow tool ONLY when the user explicitly asks for a workflow or for l

 Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.

-Use subagent's continuable background route by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when you cannot take your next action without that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.
+Use subagent in the background by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when your next action depends on that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.

 Deliver your result with the report tool before you finish: call it once with a self-contained answer. The agent that started you shares your workspace but does not automatically receive your transcript, tool output, or reasoning, so a closing remark such as "done" leaves it nothing it can use. Report earlier as well whenever a partial finding changes what that agent should do next; reporting never ends your turn.
@@ -247,7 +247,7 @@
    },
    {
      "name": "subagent",
-      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool uses its continuable background route by default and immediately returns a durable subagent id. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` to use a foreground run only when you must receive its result before taking your next action.",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool runs in the background by default, immediately returns a durable subagent id, and keeps the child conversation available for later turns. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` only when your next action depends on receiving the result.",
      "parameters": {
        "type": "object",
        "properties": {
@@ -261,7 +261,7 @@
          },
          "run_in_background": {
            "type": "boolean",
-            "description": "Whether to use the continuable background route. Defaults to true. Set false to run in the foreground and wait only when your next action depends on its result."
+            "description": "Whether to run in the background and return a durable subagent id immediately. Defaults to true. Set false to wait for the result when your next action depends on it."
          }
        },
        "required": [
@@ -6,7 +6,7 @@
 {"type":"subagent/descriptor","seq":4,"time":1786357533600,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Start depth one"}}
 {"type":"step/start","seq":5,"time":1786357533602,"data":{"turn":1,"step":1}}
 {"type":"user/message","seq":6,"time":1785730456014,"data":{"content":[{"type":"text","text":"Call subagent once. Ask that child to attempt one further subagent call, then report the result."}],"source":{"kind":"user"},"role":"user","id":"a8129357-1bde-4cbd-90b4-6b8ad51d52e1"},"surfaceOp":"append"}
-{"type":"user/message","seq":7,"time":1786357533602,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"212db1ef-823c-46f6-8a3b-ccc4f5e92bc5"},"surfaceOp":"append"}
+{"type":"user/message","seq":7,"time":1786357533602,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"837ea332-428c-4e4a-b3f1-df24dd20c93a"},"surfaceOp":"append"}
 {"type":"session/title","seq":8,"time":1786357533602,"data":{"title":"Call subagent once. Ask that","messageSeqs":[6],"source":{"kind":"fallback"}}}
 {"type":"request/header","seq":9,"time":1785730456014,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"request/context","seq":10,"time":1785730456014,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
@@ -6,7 +6,7 @@
 {"type":"subagent/descriptor","seq":4,"time":1786357533628,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Start depth two"}}
 {"type":"step/start","seq":5,"time":1786357533630,"data":{"turn":1,"step":1}}
 {"type":"user/message","seq":6,"time":1785730456041,"data":{"content":[{"type":"text","text":"Attempt one subagent call beyond the configured cap, then report the rejection."}],"source":{"kind":"user"},"role":"user","id":"d4dc5a16-e542-4dd9-8e82-e6b7829cfc4b"},"surfaceOp":"append"}
-{"type":"user/message","seq":7,"time":1786357533630,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"db7bb37e-3447-4ac8-82cd-2566300acea1"},"surfaceOp":"append"}
+{"type":"user/message","seq":7,"time":1786357533630,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"a62cf283-f87f-4f6f-be16-a00978557f99"},"surfaceOp":"append"}
 {"type":"session/title","seq":8,"time":1786357533630,"data":{"title":"Attempt one subagent call beyond","messageSeqs":[6],"source":{"kind":"fallback"}}}
 {"type":"request/header","seq":9,"time":1785730456041,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"request/context","seq":10,"time":1785730456042,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
@@ -21,6 +21,6 @@ Use the workflow tool ONLY when the user explicitly asks for a workflow or for l

 Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.

-Use subagent's continuable background route by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when you cannot take your next action without that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.
+Use subagent in the background by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when your next action depends on that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.

 Deliver your result with the report tool before you finish: call it once with a self-contained answer. The agent that started you shares your workspace but does not automatically receive your transcript, tool output, or reasoning, so a closing remark such as "done" leaves it nothing it can use. Report earlier as well whenever a partial finding changes what that agent should do next; reporting never ends your turn.
@@ -247,7 +247,7 @@
    },
    {
      "name": "subagent",
-      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool uses its continuable background route by default and immediately returns a durable subagent id. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` to use a foreground run only when you must receive its result before taking your next action.",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool runs in the background by default, immediately returns a durable subagent id, and keeps the child conversation available for later turns. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` only when your next action depends on receiving the result.",
      "parameters": {
        "type": "object",
        "properties": {
@@ -261,7 +261,7 @@
          },
          "run_in_background": {
            "type": "boolean",
-            "description": "Whether to use the continuable background route. Defaults to true. Set false to run in the foreground and wait only when your next action depends on its result."
+            "description": "Whether to run in the background and return a durable subagent id immediately. Defaults to true. Set false to wait for the result when your next action depends on it."
          }
        },
        "required": [
@@ -6,7 +6,7 @@
 {"type":"subagent/descriptor","seq":4,"time":1786443013990,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Reply ALPHA only"}}
 {"type":"step/start","seq":5,"time":1786443013993,"data":{"turn":1,"step":1}}
 {"type":"user/message","seq":6,"time":1786443013993,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"73ce401a-faaf-408a-879e-7485380d537d"},"surfaceOp":"append"}
-{"type":"user/message","seq":7,"time":1786357524755,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"64e0fe5e-a3a5-44f1-bf43-b7dc74fad046"},"surfaceOp":"append"}
+{"type":"user/message","seq":7,"time":1786357524755,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"b5f31276-8b68-4182-8f90-32a3eb710968"},"surfaceOp":"append"}
 {"type":"session/title","seq":8,"time":1786357524755,"data":{"title":"Reply with exactly the word","messageSeqs":[6],"source":{"kind":"fallback"}}}
 {"type":"request/header","seq":9,"time":1786443013994,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"request/context","seq":10,"time":1786443013994,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
@@ -27,7 +27,7 @@
 {"type":"subagent/descriptor","seq":41,"time":1786357524800,"data":{"version":2,"mode":"one-shot","provider":"fork","label":"Recall project codeword"}}
 {"type":"step/start","seq":42,"time":1786357524803,"data":{"turn":2,"step":1}}
 {"type":"user/message","seq":43,"time":1786357524803,"data":{"content":[{"type":"text","text":"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else."}],"source":{"kind":"user"},"role":"user","id":"86e9f144-764f-460d-b72b-262cffe43d77"},"surfaceOp":"append"}
-{"type":"user/message","seq":44,"time":1786358036899,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"822cdf7d-2a4d-4e51-9a7b-212db77f8b94"},"surfaceOp":"append"}
+{"type":"user/message","seq":44,"time":1786358036899,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"3cf7eb4d-7ce0-4021-b477-ecb16b62ba60"},"surfaceOp":"append"}
 {"type":"request/header","seq":45,"time":1786358036900,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"resume"}}
 {"type":"assistant/chunk","seq":46,"time":1783352148077,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
 {"type":"reasoning-chunks","seq0":47,"time0":1783352148077,"data":{"turn":2,"step":1,"index":0,"dt":[0,0,29,0,0,0,35,0,0,0,0,26,29,31,0,30,0,0,27,1,27,0,1,0,0,31,1,0,0,1790157964],"texts":["The"," user"," is"," asking"," me"," to"," recall"," the"," project"," cod","ew","ord"," that"," was"," mentioned"," earlier"," in"," the"," conversation","."," I"," was"," told"," to"," remember"," it",":"," SA","FF","RON","."]}}
@@ -50,8 +50,8 @@
 {"type":"tool/result","seq":214,"time":1786443014049,"data":{"turn":2,"step":2,"message":{"source":{"kind":"tool","callId":"call_00_JSr5rhREq23wSmwSkCP77184"},"content":[{"type":"tool-result","toolCallId":"call_00_JSr5rhREq23wSmwSkCP77184","content":[{"type":"text","text":"SAFFRON"}],"isError":false}],"role":"user","id":"4e5624d0-b633-4df7-ad19-db764e298422"}},"sourceEventSeqs":[213],"surfaceOp":"append"}
 {"type":"step/end","seq":215,"time":1786443014050,"data":{"turn":2,"step":2}}
 {"type":"step/start","seq":216,"time":1786443014055,"data":{"turn":2,"step":3}}
-{"type":"assistant/chunk","seq":217,"time":1786443014060,"data":{"turn":2,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
-{"type":"reasoning-chunks","seq0":218,"time0":1786437123085,"data":{"turn":2,"step":3,"index":0,"dt":[1,-3084973840,0,0,27,1,31,1,24,1,0,0,0,0,28,0,1,0,0,28,0,0,28,1,0,28,0,29,29,0,33,0,23,29,31,31,0,0,0,27,0,0,0,0,0,29,0,0,1,27,1,0,0,0,27,1,0,28,1,0,0,0,0],"texts":["Both"," sub","agents"," returned",":\n","1","."," First"," (","fresh"," child","):"," \"","AL","P","HA","\"\n","2","."," Second"," (","fork","ed"," child","):"," \"","SA","FF","RON","\""," -"," correctly"," inherited"," the"," conversation"," context"," where"," I"," was"," asked"," to"," remember"," the"," cod","ew","ord"," \"","SA","FF","RON","\".\n\n","Now"," I"," reply"," with"," \"","PAR","ENT","_D","ONE","\""," as"," instructed","."]}}
+{"type":"assistant/chunk","seq":217,"time":1783352149217,"data":{"turn":2,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
+{"type":"reasoning-chunks","seq0":218,"time0":1783352149246,"data":{"turn":2,"step":3,"index":0,"dt":[0,0,0,0,27,1,31,1,24,1,0,0,0,0,28,0,1,0,0,28,0,0,28,1,0,28,0,29,29,0,33,0,23,29,31,31,0,0,0,27,0,0,0,0,0,29,0,0,1,27,1,0,0,0,27,1,0,28,1,0,0,0,0],"texts":["Both"," sub","agents"," returned",":\n","1","."," First"," (","fresh"," child","):"," \"","AL","P","HA","\"\n","2","."," Second"," (","fork","ed"," child","):"," \"","SA","FF","RON","\""," -"," correctly"," inherited"," the"," conversation"," context"," where"," I"," was"," asked"," to"," remember"," the"," cod","ew","ord"," \"","SA","FF","RON","\".\n\n","Now"," I"," reply"," with"," \"","PAR","ENT","_D","ONE","\""," as"," instructed","."]}}
 {"type":"assistant/chunk","seq":282,"time":1783352149821,"data":{"turn":2,"step":3,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
 {"type":"text-chunks","seq0":283,"time0":1783352149821,"data":{"turn":2,"step":3,"index":1,"dt":[0,0,0],"texts":["PAR","ENT","_D","ONE"]}}
 {"type":"assistant/chunk","seq":287,"time":1785498797528,"data":{"turn":2,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"Both subagents returned:\n1. First (fresh child): \"ALPHA\"\n2. Second (forked child): \"SAFFRON\" - correctly inherited the conversation context where I was asked to remember the codeword \"SAFFRON\".\n\nNow I reply with \"PARENT_DONE\" as instructed."}}}}
@@ -6,7 +6,7 @@
 {"type":"subagent/descriptor","seq":4,"time":1786357521754,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Return ALPHA only"}}
 {"type":"step/start","seq":5,"time":1786357521756,"data":{"turn":1,"step":1}}
 {"type":"user/message","seq":6,"time":1785730447828,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"a287f842-f6f2-4a17-ab4c-820e41f498d5"},"surfaceOp":"append"}
-{"type":"user/message","seq":7,"time":1786357521756,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"a9ee240c-e856-4a1a-8b21-7540309c45d4"},"surfaceOp":"append"}
+{"type":"user/message","seq":7,"time":1786357521756,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"59d87d55-736f-4836-be4e-084a9f5cc7b1"},"surfaceOp":"append"}
 {"type":"session/title","seq":8,"time":1786357521756,"data":{"title":"Reply with exactly the word","messageSeqs":[6],"source":{"kind":"fallback"}}}
 {"type":"request/header","seq":9,"time":1785730447828,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"request/context","seq":10,"time":1785730447828,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
@@ -6,7 +6,7 @@
 {"type":"subagent/descriptor","seq":4,"time":1786357521799,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Return BETA only"}}
 {"type":"step/start","seq":5,"time":1786357521801,"data":{"turn":1,"step":1}}
 {"type":"user/message","seq":6,"time":1785730447881,"data":{"content":[{"type":"text","text":"Reply with exactly the word BETA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"53f6419d-8ddc-4eee-8803-5b68411336f9"},"surfaceOp":"append"}
-{"type":"user/message","seq":7,"time":1786357521802,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"92e19923-3254-41fb-8f0f-af86432de7e2"},"surfaceOp":"append"}
+{"type":"user/message","seq":7,"time":1786357521802,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"1cc862ff-09a2-496d-817a-c4281b4540d7"},"surfaceOp":"append"}
 {"type":"session/title","seq":8,"time":1786357521802,"data":{"title":"Reply with exactly the word","messageSeqs":[6],"source":{"kind":"fallback"}}}
 {"type":"request/header","seq":9,"time":1785730447881,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"request/context","seq":10,"time":1785730447881,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
@@ -1,18 +1,18 @@
 {"type":"session","version":0,"id":"bbbbbbbb-0000-4000-8000-000000000002","createdAt":1783352127000,"cwd":"{{cwd}}","parentSession":"aaaaaaaa-0000-4000-8000-000000000001","origin":"subagent","delegationDepth":1}
 {"type":"approval/policy","seq":0,"time":1786373947132,"data":{"policy":"never","source":"delegation"}}
-{"type":"agent/inbox/spliced","seq":1,"time":1786373947134,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"e706be76-fc34-43dd-bea8-932a44ab7296"}]}}
+{"type":"agent/inbox/spliced","seq":1,"time":1786373947134,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"fcb407e0-2c85-4875-81cf-ad18fd96e3dc"}]}}
 {"type":"turn/start","seq":2,"time":1786373947134,"data":{"turn":1}}
 {"type":"agent/inbox/spliced","seq":3,"time":1786373947134,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
 {"type":"subagent/descriptor","seq":4,"time":1786373947165,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Say the word ALPHA"}}
 {"type":"step/start","seq":5,"time":1786373947168,"data":{"turn":1,"step":1}}
-{"type":"user/message","seq":6,"time":1786338530759,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"e706be76-fc34-43dd-bea8-932a44ab7296"},"surfaceOp":"append"}
-{"type":"user/message","seq":7,"time":1786373947168,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"258b6b8c-c0ef-4157-9cf5-77ac13dc9202"},"surfaceOp":"append"}
+{"type":"user/message","seq":6,"time":1786338530759,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"fcb407e0-2c85-4875-81cf-ad18fd96e3dc"},"surfaceOp":"append"}
+{"type":"user/message","seq":7,"time":1786373947168,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"43134073-e26c-4314-a019-95f39d40ab19"},"surfaceOp":"append"}
 {"type":"session/title","seq":8,"time":1786373947168,"data":{"title":"Reply with exactly the word","messageSeqs":[6],"source":{"kind":"fallback"}}}
 {"type":"request/header","seq":9,"time":1786338530759,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"request/context","seq":10,"time":1786338530759,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
 {"type":"assistant/chunk","seq":11,"time":1786338530769,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
 {"type":"assistant/chunk","seq":12,"time":1786338530769,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ALPHA"}}}}
 {"type":"assistant/chunk","seq":13,"time":1786338530769,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
-{"type":"assistant/message","seq":14,"time":1786338530769,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"ALPHA"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"237c74c5-2a50-4200-80e4-711e2d8fbd18"}},"sourceEventSeqs":[11,12,13],"surfaceOp":"append"}
+{"type":"assistant/message","seq":14,"time":1786338530769,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"ALPHA"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"4923daf1-fb8a-4278-b173-477ff3e36df0"}},"sourceEventSeqs":[11,12,13],"surfaceOp":"append"}
 {"type":"step/end","seq":15,"time":1786338530769,"data":{"turn":1,"step":1}}
 {"type":"turn/end","seq":16,"time":1786338530769,"data":{"turn":1,"reason":{"kind":"completed"}}}
@@ -1,18 +1,18 @@
 {"type":"session","version":0,"id":"cccccccc-0000-4000-8000-000000000003","createdAt":1783352127001,"cwd":"{{cwd}}","parentSession":"aaaaaaaa-0000-4000-8000-000000000001","origin":"subagent","delegationDepth":1}
 {"type":"approval/policy","seq":0,"time":1786373947132,"data":{"policy":"never","source":"delegation"}}
-{"type":"agent/inbox/spliced","seq":1,"time":1786373947133,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"61226d6c-a359-4cdd-9eab-734557314ce9"}]}}
+{"type":"agent/inbox/spliced","seq":1,"time":1786373947133,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"f768a0a8-04f9-4dbe-baf0-a55a2be33866"}]}}
 {"type":"turn/start","seq":2,"time":1786373947133,"data":{"turn":1}}
 {"type":"agent/inbox/spliced","seq":3,"time":1786373947134,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
 {"type":"subagent/descriptor","seq":4,"time":1786373947170,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Say the word ALPHA"}}
 {"type":"step/start","seq":5,"time":1786373947173,"data":{"turn":1,"step":1}}
-{"type":"user/message","seq":6,"time":1786338530749,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"61226d6c-a359-4cdd-9eab-734557314ce9"},"surfaceOp":"append"}
-{"type":"user/message","seq":7,"time":1786373947174,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"cf708e7a-d3c3-477a-91ed-f25605439130"},"surfaceOp":"append"}
+{"type":"user/message","seq":6,"time":1786338530749,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"},"role":"user","id":"f768a0a8-04f9-4dbe-baf0-a55a2be33866"},"surfaceOp":"append"}
+{"type":"user/message","seq":7,"time":1786373947174,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"2934ee83-26a7-4262-8517-e4fe8f97312a"},"surfaceOp":"append"}
 {"type":"session/title","seq":8,"time":1786373947174,"data":{"title":"Reply with exactly the word","messageSeqs":[6],"source":{"kind":"fallback"}}}
 {"type":"request/header","seq":9,"time":1786338530749,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"request/context","seq":10,"time":1786338530749,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
 {"type":"assistant/chunk","seq":11,"time":1786338530759,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
 {"type":"assistant/chunk","seq":12,"time":1786338530759,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ALPHA"}}}}
 {"type":"assistant/chunk","seq":13,"time":1786338530759,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
-{"type":"assistant/message","seq":14,"time":1786338530759,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"ALPHA"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"ed8a19d2-6095-44db-990c-9f1f9309c824"}},"sourceEventSeqs":[11,12,13],"surfaceOp":"append"}
+{"type":"assistant/message","seq":14,"time":1786338530759,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"ALPHA"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"013bb4a7-f401-4d39-8552-15232d042d26"}},"sourceEventSeqs":[11,12,13],"surfaceOp":"append"}
 {"type":"step/end","seq":15,"time":1786338530760,"data":{"turn":1,"step":1}}
 {"type":"turn/end","seq":16,"time":1786338530760,"data":{"turn":1,"reason":{"kind":"completed"}}}
@@ -21,6 +21,6 @@ Use the workflow tool ONLY when the user explicitly asks for a workflow or for l

 Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.

-Use subagent's continuable background route by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when you cannot take your next action without that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.
+Use subagent in the background by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when your next action depends on that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.

 Deliver your result with the report tool before you finish: call it once with a self-contained answer. The agent that started you shares your workspace but does not automatically receive your transcript, tool output, or reasoning, so a closing remark such as "done" leaves it nothing it can use. Report earlier as well whenever a partial finding changes what that agent should do next; reporting never ends your turn.
@@ -247,7 +247,7 @@
    },
    {
      "name": "subagent",
-      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool uses its continuable background route by default and immediately returns a durable subagent id. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` to use a foreground run only when you must receive its result before taking your next action.",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool runs in the background by default, immediately returns a durable subagent id, and keeps the child conversation available for later turns. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` only when your next action depends on receiving the result.",
      "parameters": {
        "type": "object",
        "properties": {
@@ -261,7 +261,7 @@
          },
          "run_in_background": {
            "type": "boolean",
-            "description": "Whether to use the continuable background route. Defaults to true. Set false to run in the foreground and wait only when your next action depends on its result."
+            "description": "Whether to run in the background and return a durable subagent id immediately. Defaults to true. Set false to wait for the result when your next action depends on it."
          }
        },
        "required": [
@@ -21,4 +21,4 @@ Use the workflow tool ONLY when the user explicitly asks for a workflow or for l

 Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.

-Use subagent's continuable background route by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when you cannot take your next action without that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.
+Use subagent in the background by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when your next action depends on that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.
@@ -231,7 +231,7 @@
    },
    {
      "name": "subagent",
-      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool uses its continuable background route by default and immediately returns a durable subagent id. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` to use a foreground run only when you must receive its result before taking your next action.",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool runs in the background by default, immediately returns a durable subagent id, and keeps the child conversation available for later turns. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` only when your next action depends on receiving the result.",
      "parameters": {
        "type": "object",
        "properties": {
@@ -245,7 +245,7 @@
          },
          "run_in_background": {
            "type": "boolean",
-            "description": "Whether to use the continuable background route. Defaults to true. Set false to run in the foreground and wait only when your next action depends on its result."
+            "description": "Whether to run in the background and return a durable subagent id immediately. Defaults to true. Set false to wait for the result when your next action depends on it."
          }
        },
        "required": [
@@ -23,4 +23,4 @@ Use the workflow tool ONLY when the user explicitly asks for a workflow or for l

 Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.

-Use subagent's continuable background route by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when you cannot take your next action without that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.
+Use subagent in the background by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when your next action depends on that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.
@@ -231,7 +231,7 @@
    },
    {
      "name": "subagent",
-      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool uses its continuable background route by default and immediately returns a durable subagent id. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` to use a foreground run only when you must receive its result before taking your next action.",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. This tool runs in the background by default, immediately returns a durable subagent id, and keeps the child conversation available for later turns. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` only when your next action depends on receiving the result.",
      "parameters": {
        "type": "object",
        "properties": {
@@ -245,7 +245,7 @@
          },
          "run_in_background": {
            "type": "boolean",
-            "description": "Whether to use the continuable background route. Defaults to true. Set false to run in the foreground and wait only when your next action depends on its result."
+            "description": "Whether to run in the background and return a durable subagent id immediately. Defaults to true. Set false to wait for the result when your next action depends on it."
          }
        },
        "required": [
@@ -21,4 +21,4 @@ Use the workflow tool ONLY when the user explicitly asks for a workflow or for l

 Use the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.

-Use subagent's continuable background route by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when you cannot take your next action without that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.
+Use subagent in the background by default. Start independent delegations together in one assistant message and continue useful work while they run. Set `run_in_background: false` only when your next action depends on that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/subagent/tool-subagent/README.md
-README.md: 40ece8bbd6f0f8929b3cb112c0b9b0de20299b8b
-README.zh.md: 3f19740ef7abe961d6528e24a5063b3975fc1452
+README.md: cc872f3decc4c85f26bd997293c8dc4140eb221c
+README.zh.md: f7616dc677d10c141b1be606dae36d7dc7bb23ac
@@ -37,7 +37,7 @@ Foreground and background calls are concurrency-safe: sibling delegations in one

 #### What the model sees

-The generated default [`subagent` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-subagent) under this instance's configured name while its provider exists. Provider context inheritance changes the tool and prompt descriptions. Enabled background mode adds `run_in_background`: continuable mode documents its `true` default, runtime settlement notice, and explicit foreground override, while one-shot mode documents its `false` default and the task id collected with `task_output` or stopped with `task_kill`. A `tool:<toolName>` system-prompt section tells the model to start independent continuable delegations together, keep working while they run, and choose foreground only when its next action depends on the result.
+The generated default [`subagent` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-subagent) under this instance's configured name while its provider exists. Provider context inheritance changes the tool and prompt descriptions. Enabled background mode adds `run_in_background`: continuable mode documents its `true` default, runtime settlement notice, and explicit foreground override, while one-shot mode documents its `false` default and the task id collected with `task_output` or stopped with `task_kill`. While the tool is visible in an assembly's scope, a `tool:<toolName>` system-prompt section tells the model to start independent continuable delegations together, keep working while they run, and choose foreground only when its next action depends on the result; a tool restriction removes both its schema and this guidance.

 #### Token effect

@@ -78,5 +78,5 @@ Append-only; newly visible content follows the reusable request prefix and does
 ## Known Limitations and Deferred Work

 - **Background runs expose no result through this tool** — a one-shot task's final output is collected through the generic task surface, and a continuable child's output stays in its own session, read by its subagent id. The settlement notice states how that child ended and carries any final assistant message, but it is not this call's return value and cannot be awaited here.
- **Duplicate names across waiting instances are detected late** (`TODO(subagent-dup-toolname)`) — preventing provider-registration rollback requires a registry of intended names.
+- **Duplicate names across waiting one-shot instances are detected late** (`TODO(subagent-dup-toolname)`) — continuable instances reserve their prompt-section name during plugin application, but preventing provider-registration rollback for waiting one-shot instances requires a registry of intended names.
 - **Child policy is fixed per instance** — another model, persona, tool filter, or depth cap requires another distinctly named tool.
@@ -37,7 +37,7 @@

 #### 模型看到的内容

-当提供方存在时，以当前实例配置的名称公开已生成的默认 [`subagent` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-subagent)。提供方是否继承上下文会改变工具描述和提示词描述。启用后台模式会添加 `run_in_background`：可继续模式会记录其默认值为 `true`、运行时结算通知与显式前台覆盖；一次性模式会记录其默认值为 `false`，以及用 `task_output` 收集或用 `task_kill` 停止的 task id。一个 `tool:<toolName>` 系统提示词 section 会指示模型同时启动相互独立的可继续委派、在它们运行时继续工作，并且仅当下一步动作依赖结果时选择前台。
+当提供方存在时，以当前实例配置的名称公开已生成的默认 [`subagent` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-subagent)。提供方是否继承上下文会改变工具描述和提示词描述。启用后台模式会添加 `run_in_background`：可继续模式会记录其默认值为 `true`、运行时结算通知与显式前台覆盖；一次性模式会记录其默认值为 `false`，以及用 `task_output` 收集或用 `task_kill` 停止的 task id。当工具在本次组装的作用域中可见时，一个 `tool:<toolName>` 系统提示词 section 会指示模型同时启动相互独立的可继续委派、在它们运行时继续工作，并且仅当下一步动作依赖结果时选择前台；工具限制会同时移除其 schema 和这段指引。

 #### Token 影响

@@ -78,5 +78,5 @@
 ## 已知限制与暂缓事项

 - **后台运行不通过本工具公开结果**：一次性任务的最终输出通过通用 Task 接口收集，可继续子 agent 的输出留在其自身会话中，按其 subagent id 读取。结算通知会说明该子 agent 如何结束，并携带可能存在的最终 assistant 消息，但它不是本次调用的返回值，也无法在此等待。
- **等待中实例的重复名称发现较晚**（`TODO(subagent-dup-toolname)`）：若要阻止提供方注册回滚，需要一份预期名称注册表。
+- **等待中的一次性实例较晚才发现重复名称**（`TODO(subagent-dup-toolname)`）：可继续实例会在插件应用期间预留提示词 section 名称，但若要阻止等待中的一次性实例回滚提供方注册，仍需要一份预期名称注册表。
 - **每个实例的子 agent 策略固定**：其他模型、persona、工具过滤器或深度上限都需要另一个名称不同的工具。
@@ -23,7 +23,7 @@ export const name = 'tool-subagent'
 export const inject = ['tools', 'subagents', 'systemPrompt']

 /** Prompt order after bounded delegation policy and before child reporting. */
-const SUBAGENT_SECTION_ORDER = 116
+const SUBAGENT_SECTION_ORDER = 116.5

 /** Config: which registered provider this tool delegates to, plus child defaults. */
 export interface Config {
@@ -301,7 +301,7 @@ export function apply(ctx: Context, config: Config): void {
        // a separately installed capability, so this promise holds whenever the
        // continuable background path is reachable at all.
        ? continuable
-          ? ' This tool uses its continuable background route by default and immediately returns a durable subagent id. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` to use a foreground run only when you must receive its result before taking your next action.'
+          ? ' This tool runs in the background by default, immediately returns a durable subagent id, and keeps the child conversation available for later turns. When that run settles, the runtime sends the parent a notice containing its outcome and any final assistant message; `send_message` starts a later turn in the same child conversation. Set `run_in_background: false` only when your next action depends on receiving the result.'
          : ' This call waits for the result by default. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.'
        : ' This call waits for the subagent and returns its result.'),
      parameters: {
@@ -319,7 +319,7 @@ export function apply(ctx: Context, config: Config): void {
          run_in_background: {
            type: 'boolean' as const,
            description: continuable
-              ? 'Whether to use the continuable background route. Defaults to true. Set false to run in the foreground and wait only when your next action depends on its result.'
+              ? 'Whether to run in the background and return a durable subagent id immediately. Defaults to true. Set false to wait for the result when your next action depends on it.'
              : 'Whether to run as a background task and return its id. Defaults to false; collect with task_output or stop with task_kill.',
          },
        } : {},
@@ -432,9 +432,11 @@ export function apply(ctx: Context, config: Config): void {
  }

  // Register listeners before checking presence so no synchronous change is missed.
-  // TODO(subagent-dup-toolname): two WAITING fibers configured with the same
-  // toolName collide when their provider appears, and the duplicate-name throw
-  // rolls back the provider registration. Add an intent registry if this occurs.
+  // TODO(subagent-dup-toolname): two waiting one-shot fibers configured with the
+  // same toolName collide when their provider appears, and the duplicate-name
+  // throw rolls back the provider registration. Continuable instances reserve
+  // their prompt-section name during apply() and fail earlier. Add an intent
+  // registry if the late one-shot collision occurs in a shipped composition.
  ctx.on('subagent/provider-added', (provider) => {
    if (provider.name === config.provider && disposeTool === undefined) mount(provider)
  })
@@ -457,9 +459,9 @@ export function apply(ctx: Context, config: Config): void {
    ctx.systemPrompt.section({
      name: `tool:${toolName}`,
      order: SUBAGENT_SECTION_ORDER,
-      text: () => ctx.subagents.getProvider(config.provider) === undefined
+      text: context => disposeTool === undefined || ctx.tools.get(toolName, context.scope) === undefined
        ? ''
-        : `Use ${toolName}'s continuable background route by default. Start independent delegations together in one assistant message and continue useful work while they run. Set \`run_in_background: false\` only when you cannot take your next action without that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.`,
+        : `Use ${toolName} in the background by default. Start independent delegations together in one assistant message and continue useful work while they run. Set \`run_in_background: false\` only when your next action depends on that subagent's result. When a background run settles, the runtime sends you a notice containing its outcome and any final assistant message.`,
    })
  }
 }
@@ -354,13 +354,26 @@ describe('dsh-tool-subagent', () => {
    await ctx.plugin(ToolRegistry)
    await ctx.plugin(SubagentService)

-    // Arm 1: a mounted tool dies with its plugin fiber; the provider survives.
-    await mock.mountScriptedProvider(ctx, { name: 'mock' })
-    const mounted = await ctx.plugin(tool, { provider: 'mock' })
+    // Arm 1: a mounted tool and its prompt section die with the plugin fiber;
+    // the provider survives.
+    ctx.subagents.registerProvider({
+      name: 'continuable',
+      capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false },
+      inheritsParentContext: false,
+      start: async () => { throw new Error('lifecycle test does not start a child') },
+      prepareContinuable: async () => ({}),
+    })
+    const mounted = await ctx.plugin(tool, {
+      provider: 'continuable',
+      backgroundMode: 'continuable',
+      maxDepth: 'provider-managed',
+    })
    expect(ctx.tools.schemas().some(s => s.name === 'subagent')).toBe(true)
+    expect((await ctx.systemPrompt.assemble()).sections.some(s => s.name === 'tool:subagent')).toBe(true)
    await mounted.dispose()
    expect(ctx.tools.schemas().some(s => s.name === 'subagent')).toBe(false)
-    expect(ctx.subagents.getProvider('mock')).toBeDefined()
+    expect((await ctx.systemPrompt.assemble()).sections.some(s => s.name === 'tool:subagent')).toBe(false)
+    expect(ctx.subagents.getProvider('continuable')).toBeDefined()

    // Arm 2: a fiber disposed while WAITING must not react to the provider
    // arriving later — a surviving listener would re-register a tool that no
@@ -1012,16 +1025,16 @@ describe('dsh-tool-subagent continuable background mode', () => {
    expect(schema.description).not.toContain('task_output')
    expect(schema.description).not.toContain('task_kill')
    expect(schema.description).toContain('send_message')
-    expect(schema.description).toContain('continuable background route by default')
+    expect(schema.description).toContain('runs in the background by default')
+    expect(schema.description).not.toContain('never poll or wait on it')
    const properties = (schema.parameters as {
      properties: Record<string, { description?: string }>
    }).properties
    expect(properties.run_in_background?.description).toContain('Defaults to true')
    const assembly = await ctx.systemPrompt.assemble(assembleContextFor(parent))
    const guidance = assembly.sections.find(section => section.name === 'tool:subagent')
-    expect(guidance?.text).toContain("Use subagent's continuable background route by default")
+    expect(guidance?.text).toContain('Use subagent in the background by default')
    expect(guidance?.text).toContain('runtime sends you a notice containing its outcome')
-    expect(guidance?.text).not.toContain('do not poll')

    const started = await callSubagent(
      ctx,
@@ -1044,6 +1057,15 @@ describe('dsh-tool-subagent continuable background mode', () => {
    expect(loaded.events.some(event => event.type === 'assistant/message')).toBe(true)
  })

+  it('hides continuable guidance when the current agent cannot see the tool', async () => {
+    const { ctx, parent } = await continuableSetup()
+    parent.ctx.tools.restrict({ deny: ['subagent'] })
+
+    expect(ctx.tools.get('subagent', parent)).toBeUndefined()
+    const assembly = await ctx.systemPrompt.assemble(assembleContextFor(parent))
+    expect(assembly.sections.find(section => section.name === 'tool:subagent')?.text).toBe('')
+  })
+
  it('waits for a continuable provider only when run_in_background is explicitly false', async () => {
    const { ctx, parent } = await continuableSetup()
    const result = await callSubagent(
@@ -26,6 +26,9 @@
    {
      "path": "../../core/tools"
    },
+    {
+      "path": "../../core/system-prompt"
+    },
    {
      "path": "../subagent"
    },