diff --git a/apps/cli/tests/profiles/acp/tests/goal-expected/goal-round-driver/session.expected.jsonl b/apps/cli/tests/profiles/acp/tests/goal-expected/goal-round-driver/session.expected.jsonl
index 19495490be..33970cf5be 100644
--- a/apps/cli/tests/profiles/acp/tests/goal-expected/goal-round-driver/session.expected.jsonl
+++ b/apps/cli/tests/profiles/acp/tests/goal-expected/goal-round-driver/session.expected.jsonl
@@ -8,7 +8,7 @@
 {"type":"step/start","data":{"turn":1,"step":1}}
 {"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{sessionId}}"}},"surfaceOp":"append"}
 {"type":"user/message","data":{"content":[{"type":"text","text":"Create a durable two-round goal for the ACP snapshot, inspect it, then report readiness."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
-{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\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`)."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"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`)."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
+{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\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 the root agent named \"lead\".\n\nUse list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"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:identity","text":"You are the root agent named \"lead\"."},{"name":"subagent:communication","text":"Use list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
 {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial"}}
 {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
 {"type":"session/title","data":{"title":"Create a durable two-round goal","messageSeqs":[8],"source":{"kind":"fallback"}}}
diff --git a/apps/cli/tests/profiles/acp/tests/goal-expected/goal-wrapup/session.expected.jsonl b/apps/cli/tests/profiles/acp/tests/goal-expected/goal-wrapup/session.expected.jsonl
index 7e3a02fce9..777b13ba1f 100644
--- a/apps/cli/tests/profiles/acp/tests/goal-expected/goal-wrapup/session.expected.jsonl
+++ b/apps/cli/tests/profiles/acp/tests/goal-expected/goal-wrapup/session.expected.jsonl
@@ -8,7 +8,7 @@
 {"type":"step/start","data":{"turn":1,"step":1}}
 {"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{sessionId}}"}},"surfaceOp":"append"}
 {"type":"user/message","data":{"content":[{"type":"text","text":"Create a durable goal for the wrap-up snapshot, then report readiness."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
-{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\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`)."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"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`)."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
+{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\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 the root agent named \"lead\".\n\nUse list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"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:identity","text":"You are the root agent named \"lead\"."},{"name":"subagent:communication","text":"Use list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
 {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial"}}
 {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
 {"type":"session/title","data":{"title":"Create a durable goal for","messageSeqs":[8],"source":{"kind":"fallback"}}}
diff --git a/apps/cli/tests/profiles/acp/tests/image-offload.expected.e2e.ts b/apps/cli/tests/profiles/acp/tests/image-offload.expected.e2e.ts
index 41470ed5dd..be65126fb7 100644
--- a/apps/cli/tests/profiles/acp/tests/image-offload.expected.e2e.ts
+++ b/apps/cli/tests/profiles/acp/tests/image-offload.expected.e2e.ts
@@ -143,7 +143,10 @@ it('pins Messages Files offload and inline fallback in assembled requests', asyn
     const runtimeContext = (cwd: string): string => 'Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\n'
       + `Current working directory: ${JSON.stringify(cwd)}.\n\n`
       + 'Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\n'
-      + 'Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).'
+      + 'Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\n'
+      + 'You are the root agent named "lead".\n\n'
+      + 'Use list_agents({}) to find agents in your tree and their full names.\n'
+      + 'Use send_message({ name: "<full agent path>", message: "..." }) to message another agent.'
     const messages = requests[0]?.messages as { content?: unknown }[] | undefined
     const offloaded = messages?.find(message => JSON.stringify(message.content).includes('[image omitted'))
     expect(offloaded?.content).toEqual([
diff --git a/apps/cli/tests/profiles/headless/tests/expected/goal-tools/stream-json.expected.jsonl b/apps/cli/tests/profiles/headless/tests/expected/goal-tools/stream-json.expected.jsonl
index c54f84df0b..f3c01312f7 100644
--- a/apps/cli/tests/profiles/headless/tests/expected/goal-tools/stream-json.expected.jsonl
+++ b/apps/cli/tests/profiles/headless/tests/expected/goal-tools/stream-json.expected.jsonl
@@ -4,7 +4,7 @@
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":6,"time":0,"data":{"turn":1,"step":1}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"system/message","seq":7,"time":0,"data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{sessionId}}"}},"surfaceOp":"append"}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":8,"time":0,"data":{"content":[{"type":"text","text":"Probe strict-schema fillers against missing-goal revision 1, then create a durable goal to finish the snapshot proof and inspect it."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}
-{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":9,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":9,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed.\n\nYou are the root agent named \"lead\".\n\nUse list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."},{"name":"subagent:identity","text":"You are the root agent named \"lead\"."},{"name":"subagent:communication","text":"Use list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":10,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial"}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/context","seq":11,"time":0,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"session/title","seq":12,"time":0,"data":{"title":"Probe strict-schema fillers against miss","messageSeqs":[8],"source":{"kind":"fallback"}}}}
diff --git a/apps/cli/tests/profiles/headless/tests/expected/headless-profile/session.expected.jsonl b/apps/cli/tests/profiles/headless/tests/expected/headless-profile/session.expected.jsonl
index d45d98dfd0..575218eb96 100644
--- a/apps/cli/tests/profiles/headless/tests/expected/headless-profile/session.expected.jsonl
+++ b/apps/cli/tests/profiles/headless/tests/expected/headless-profile/session.expected.jsonl
@@ -8,7 +8,7 @@
 {"type":"step/start","data":{"turn":1,"step":1}}
 {"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{sessionId}}"}},"surfaceOp":"append"}
 {"type":"user/message","data":{"content":[{"type":"text","text":"Prove the product headless profile path with one real tool round trip."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
-{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\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`)."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"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`)."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
+{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\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 the root agent named \"lead\".\n\nUse list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"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:identity","text":"You are the root agent named \"lead\"."},{"name":"subagent:communication","text":"Use list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
 {"type":"request/header","data":{"header":{"config":{"provider":"cli-mock","model":"cli-mock","reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true},"tools":"{{tools}}"},"reason":"initial"}}
 {"type":"request/context","data":{"provider":"cli-mock","model":"cli-mock"}}
 {"type":"session/title","data":{"title":"Prove the product headless profile","messageSeqs":[8],"source":{"kind":"fallback"}}}
diff --git a/apps/cli/tests/profiles/headless/tests/expected/invalid-credential/stream-json.expected.jsonl b/apps/cli/tests/profiles/headless/tests/expected/invalid-credential/stream-json.expected.jsonl
index e747f996ad..6fa8b51ad0 100644
--- a/apps/cli/tests/profiles/headless/tests/expected/invalid-credential/stream-json.expected.jsonl
+++ b/apps/cli/tests/profiles/headless/tests/expected/invalid-credential/stream-json.expected.jsonl
@@ -4,7 +4,7 @@
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":6,"time":0,"data":{"turn":1,"step":1}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"system/message","seq":7,"time":0,"data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{sessionId}}"}},"surfaceOp":"append"}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":8,"time":0,"data":{"content":[{"type":"text","text":"say pong"}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}
-{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":9,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":9,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed.\n\nYou are the root agent named \"lead\".\n\nUse list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."},{"name":"subagent:identity","text":"You are the root agent named \"lead\"."},{"name":"subagent:communication","text":"Use list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":10,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":"{{tools}}"},"reason":"initial"}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/context","seq":11,"time":0,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash","contextWindow":1000000}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"session/title","seq":12,"time":0,"data":{"title":"say pong","messageSeqs":[8],"source":{"kind":"fallback"}}}}
diff --git a/apps/cli/tests/profiles/headless/tests/expected/missing-credential/stream-json.expected.jsonl b/apps/cli/tests/profiles/headless/tests/expected/missing-credential/stream-json.expected.jsonl
index bc7c728199..283b5eb388 100644
--- a/apps/cli/tests/profiles/headless/tests/expected/missing-credential/stream-json.expected.jsonl
+++ b/apps/cli/tests/profiles/headless/tests/expected/missing-credential/stream-json.expected.jsonl
@@ -4,7 +4,7 @@
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":6,"time":0,"data":{"turn":1,"step":1}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"system/message","seq":7,"time":0,"data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{sessionId}}"}},"surfaceOp":"append"}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":8,"time":0,"data":{"content":[{"type":"text","text":"say pong"}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}
-{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":9,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":9,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed.\n\nYou are the root agent named \"lead\".\n\nUse list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."},{"name":"subagent:identity","text":"You are the root agent named \"lead\"."},{"name":"subagent:communication","text":"Use list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":10,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":"{{tools}}"},"reason":"initial"}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/context","seq":11,"time":0,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash","contextWindow":1000000}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"session/title","seq":12,"time":0,"data":{"title":"say pong","messageSeqs":[8],"source":{"kind":"fallback"}}}}
diff --git a/apps/cli/tests/profiles/headless/tests/expected/provider-retry/stream-json.expected.jsonl b/apps/cli/tests/profiles/headless/tests/expected/provider-retry/stream-json.expected.jsonl
index 5792ae3774..ec7cf0ecc6 100644
--- a/apps/cli/tests/profiles/headless/tests/expected/provider-retry/stream-json.expected.jsonl
+++ b/apps/cli/tests/profiles/headless/tests/expected/provider-retry/stream-json.expected.jsonl
@@ -4,7 +4,7 @@
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":6,"time":0,"data":{"turn":1,"step":1}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"system/message","seq":7,"time":0,"data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{sessionId}}"}},"surfaceOp":"append"}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":8,"time":0,"data":{"content":[{"type":"text","text":"retry the transient provider failure"}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}
-{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":9,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":9,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed.\n\nYou are the root agent named \"lead\".\n\nUse list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."},{"name":"subagent:identity","text":"You are the root agent named \"lead\"."},{"name":"subagent:communication","text":"Use list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":10,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial"}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/context","seq":11,"time":0,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"session/title","seq":12,"time":0,"data":{"title":"retry the transient provider failure","messageSeqs":[8],"source":{"kind":"fallback"}}}}
diff --git a/apps/cli/tests/profiles/headless/tests/expected/semantic-checkpoint/session.expected.jsonl b/apps/cli/tests/profiles/headless/tests/expected/semantic-checkpoint/session.expected.jsonl
index 11ae2ec827..7a3301b193 100644
--- a/apps/cli/tests/profiles/headless/tests/expected/semantic-checkpoint/session.expected.jsonl
+++ b/apps/cli/tests/profiles/headless/tests/expected/semantic-checkpoint/session.expected.jsonl
@@ -18,7 +18,7 @@
 {"type":"step/start","data":{"turn":2,"step":1}}
 {"type":"system/message","data":{"turn":2,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{sessionId}}"}},"sourceEventSeqs":[2],"surfaceOp":{"op":"replace","startSeq":2,"endSeq":2}}
 {"type":"user/message","data":{"content":[{"type":"text","text":"Continue safely from the interrupted operation."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
-{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
+{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed.\n\nYou are the root agent named \"lead\".\n\nUse list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."},{"name":"subagent:identity","text":"You are the root agent named \"lead\"."},{"name":"subagent:communication","text":"Use list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
 {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial","startsSeries":true}}
 {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
 {"type":"session/title","data":{"title":"Perform one side-effecting remote mutati","messageSeqs":[3],"source":{"kind":"fallback"}}}
diff --git a/apps/cli/tests/profiles/headless/tests/expected/subagent-diagnostic/parent.expected.jsonl b/apps/cli/tests/profiles/headless/tests/expected/subagent-diagnostic/parent.expected.jsonl
index 36af85437a..9b77e6f599 100644
--- a/apps/cli/tests/profiles/headless/tests/expected/subagent-diagnostic/parent.expected.jsonl
+++ b/apps/cli/tests/profiles/headless/tests/expected/subagent-diagnostic/parent.expected.jsonl
@@ -16,7 +16,7 @@
 {"type":"step/start","data":{"turn":2,"step":1}}
 {"type":"system/message","data":{"turn":2,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{sessionId}}"}},"sourceEventSeqs":[2],"surfaceOp":{"op":"replace","startSeq":2,"endSeq":2}}
 {"type":"user/message","data":{"content":[{"type":"text","text":"Call list_agents once and report what it shows."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
-{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
+{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed.\n\nYou are the root agent named \"lead\".\n\nUse list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."},{"name":"subagent:identity","text":"You are the root agent named \"lead\"."},{"name":"subagent:communication","text":"Use list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
 {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial","startsSeries":true}}
 {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
 {"type":"session/title","data":{"title":"Start a background job.","messageSeqs":[3],"source":{"kind":"fallback"}}}
diff --git a/apps/cli/tests/profiles/headless/tests/expected/subagent-inheritance/child.expected.jsonl b/apps/cli/tests/profiles/headless/tests/expected/subagent-inheritance/child.expected.jsonl
index 6bf221bc38..b05ac771a1 100644
--- a/apps/cli/tests/profiles/headless/tests/expected/subagent-inheritance/child.expected.jsonl
+++ b/apps/cli/tests/profiles/headless/tests/expected/subagent-inheritance/child.expected.jsonl
@@ -8,7 +8,7 @@
 {"type":"step/start","data":{"turn":1,"step":1}}
 {"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{sessionId}}"}},"surfaceOp":"append"}
 {"type":"user/message","data":{"content":[{"type":"text","text":"Use the write tool exactly once with file_path set to exactly the relative path inherited.txt and content escaped. If the write is denied, reply with the single word CHILD_DENIED and the denial marker line; do not retry and do not request escalation. If it succeeds, reply CHILD_WROTE."},{"type":"text","text":"Your final answer is delivered automatically if your parent is still online. Include the result and relevant evidence in that answer; the parent does not receive your full transcript, tool output, or reasoning. If your last action is a message to your parent, the completion notice omits your final answer; include the result and relevant evidence in that message."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
-{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns.\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\nYour parent agent id is \"{{sessionId}}\". Use send_message({ name: \"{{sessionId}}\", message: \"<finding>\" }) when a finding changes what the parent should do next; sending a message does not end your turn.\n\nDelegation depth for `subagent`: current 1, maximum 1, remaining levels 0. Do not call `subagent` at this depth; carry out the work directly.\n\nDelegation depth for `subagent_fork`: current 1, maximum 1, remaining levels 0. Do not call `subagent_fork` at this depth; carry out the work directly.\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":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns."},{"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:communication","text":"Your parent agent id is \"{{sessionId}}\". Use send_message({ name: \"{{sessionId}}\", message: \"<finding>\" }) when a finding changes what the parent should do next; sending a message does not end your turn."},{"name":"tool:subagent:depth","text":"Delegation depth for `subagent`: current 1, maximum 1, remaining levels 0. Do not call `subagent` at this depth; carry out the work directly."},{"name":"tool:subagent_fork:depth","text":"Delegation depth for `subagent_fork`: current 1, maximum 1, remaining levels 0. Do not call `subagent_fork` at this depth; carry out the work directly."},{"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":"{{sessionId}}"},"surfaceOp":"append"}
+{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns.\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\nYour name is \"lead/agent-1\". Your parent agent is \"lead\". Your root agent is \"lead\".\n\nUse list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent.\nMessage your parent when a finding changes what it should do next; sending a message does not end your turn.\n\nDelegation depth for `subagent`: current 1, maximum 1, remaining levels 0. Do not call `subagent` at this depth; carry out the work directly.\n\nDelegation depth for `subagent_fork`: current 1, maximum 1, remaining levels 0. Do not call `subagent_fork` at this depth; carry out the work directly.\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":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns."},{"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:identity","text":"Your name is \"lead/agent-1\". Your parent agent is \"lead\". Your root agent is \"lead\"."},{"name":"subagent:communication","text":"Use list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent.\nMessage your parent when a finding changes what it should do next; sending a message does not end your turn."},{"name":"tool:subagent:depth","text":"Delegation depth for `subagent`: current 1, maximum 1, remaining levels 0. Do not call `subagent` at this depth; carry out the work directly."},{"name":"tool:subagent_fork:depth","text":"Delegation depth for `subagent_fork`: current 1, maximum 1, remaining levels 0. Do not call `subagent_fork` at this depth; carry out the work directly."},{"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":"{{sessionId}}"},"surfaceOp":"append"}
 {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","reasoningEffort":"low"},"tools":"{{tools}}"},"reason":"initial"}}
 {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
 {"type":"session/title","data":{"title":"Use the write tool exactly","messageSeqs":[8],"source":{"kind":"fallback"}}}
diff --git a/apps/cli/tests/profiles/headless/tests/expected/subagent-inheritance/parent.expected.jsonl b/apps/cli/tests/profiles/headless/tests/expected/subagent-inheritance/parent.expected.jsonl
index 9fe186399f..7e3f452238 100644
--- a/apps/cli/tests/profiles/headless/tests/expected/subagent-inheritance/parent.expected.jsonl
+++ b/apps/cli/tests/profiles/headless/tests/expected/subagent-inheritance/parent.expected.jsonl
@@ -16,7 +16,7 @@
 {"type":"step/start","data":{"turn":2,"step":1}}
 {"type":"system/message","data":{"turn":2,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{sessionId}}"}},"sourceEventSeqs":[2],"surfaceOp":{"op":"replace","startSeq":2,"endSeq":2}}
 {"type":"user/message","data":{"content":[{"type":"text","text":"Delegate the write probe to a subagent."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
-{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
+{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed.\n\nYou are the root agent named \"lead\".\n\nUse list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."},{"name":"subagent:identity","text":"You are the root agent named \"lead\"."},{"name":"subagent:communication","text":"Use list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
 {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","reasoningEffort":"low"},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","wait_agent","web_fetch","web_search","workflow","working_directory","write"]},"reason":"resume","startsSeries":true}}
 {"type":"developer/message","data":{"turn":2,"step":1,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"bash"},{"type":"tool-addition","toolName":"create_goal"},{"type":"tool-addition","toolName":"edit"},{"type":"tool-addition","toolName":"get_goal"},{"type":"tool-addition","toolName":"glob"},{"type":"tool-addition","toolName":"grep"},{"type":"tool-addition","toolName":"interrupt_agent"},{"type":"tool-addition","toolName":"job_kill"},{"type":"tool-addition","toolName":"job_list"},{"type":"tool-addition","toolName":"job_output"},{"type":"tool-addition","toolName":"list_agents"},{"type":"tool-addition","toolName":"read"},{"type":"tool-addition","toolName":"read_image"},{"type":"tool-addition","toolName":"send_message"},{"type":"tool-addition","toolName":"skill"},{"type":"tool-addition","toolName":"subagent"},{"type":"tool-addition","toolName":"subagent_fork"},{"type":"tool-addition","toolName":"todo_write"},{"type":"tool-addition","toolName":"update_goal"},{"type":"tool-addition","toolName":"wait_agent"},{"type":"tool-addition","toolName":"web_fetch"},{"type":"tool-addition","toolName":"web_search"},{"type":"tool-addition","toolName":"workflow"},{"type":"tool-addition","toolName":"working_directory"},{"type":"tool-addition","toolName":"write"}],"role":"developer","id":"{{sessionId}}"},"headerSeq":18},"surfaceOp":"append"}
 {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
@@ -25,12 +25,12 @@
 {"type":"tool/call","data":{"turn":2,"step":1,"callId":"delegate-write","name":"subagent","arguments":"{\"description\": \"Delegated write probe\", \"prompt\": \"Use the write tool exactly once with file_path set to exactly the relative path inherited.txt and content escaped. If the write is denied, reply with the single word CHILD_DENIED and the denial marker line; do not retry and do not request escalation. If it succeeds, reply CHILD_WROTE.\"}"}}
 {"type":"subagent/catalog","data":{"version":0,"childId":"{{sessionId}}","childCreatedAt":0,"mode":"continuable","label":"Delegated write probe"}}
 {"type":"subagent-name/bound","data":{"version":1,"childId":"{{sessionId}}","name":"lead/agent-1"}}
-{"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"Background subagent {{sessionId}} finished and will do no further work unless you send it more."},{"type":"text","text":"Its closing message:"},{"type":"text","text":"CHILD_DENIED [sandbox: file access denied under read-only mode]"}],"source":{"kind":"subagent-settled","form":"notice","summary":"Background subagent {{sessionId}} finished and will do no further work unless you send it more.","senderSessionId":"{{sessionId}}"},"role":"user","id":"{{sessionId}}"}]}}
+{"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"Background subagent {{sessionId}} finished and will do no further work unless you send it more."},{"type":"text","text":"Its closing message:"},{"type":"text","text":"CHILD_DENIED [sandbox: file access denied under read-only mode]"}],"source":{"kind":"subagent-settled","form":"notice","summary":"Background subagent {{sessionId}} finished and will do no further work unless you send it more.","senderSessionId":"{{sessionId}}","stopReason":"completed","description":"Delegated write probe"},"role":"user","id":"{{sessionId}}"}]}}
 {"type":"tool/result","data":{"turn":2,"step":1,"message":{"role":"tool","source":{"kind":"tool","callId":"delegate-write"},"toolCallId":"delegate-write","content":[{"type":"text","text":"started subagent {{sessionId}}\nname: lead/agent-1"}],"isError":false,"id":"{{sessionId}}"}},"sourceEventSeqs":[23],"surfaceOp":"append"}
 {"type":"step/end","data":{"turn":2,"step":1}}
 {"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"removedCount":1,"inserted":[]}}
 {"type":"step/start","data":{"turn":2,"step":2}}
-{"type":"user/message","data":{"content":[{"type":"text","text":"Background subagent {{sessionId}} finished and will do no further work unless you send it more."},{"type":"text","text":"Its closing message:"},{"type":"text","text":"CHILD_DENIED [sandbox: file access denied under read-only mode]"}],"source":{"kind":"subagent-settled","form":"notice","summary":"Background subagent {{sessionId}} finished and will do no further work unless you send it more.","senderSessionId":"{{sessionId}}"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
+{"type":"user/message","data":{"content":[{"type":"text","text":"Background subagent {{sessionId}} finished and will do no further work unless you send it more."},{"type":"text","text":"Its closing message:"},{"type":"text","text":"CHILD_DENIED [sandbox: file access denied under read-only mode]"}],"source":{"kind":"subagent-settled","form":"notice","summary":"Background subagent {{sessionId}} finished and will do no further work unless you send it more.","senderSessionId":"{{sessionId}}","stopReason":"completed","description":"Delegated write probe"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
 {"type":"assistant/message","data":{"turn":2,"step":2,"message":{"role":"assistant","content":[{"type":"text","text":"The delegated child was denied by the sandbox. PARENT_DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"usage":{"inputTokens":10,"outputTokens":5},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":0,"index":0,"dt":[],"texts":["The delegated child was denied by the sandbox. PARENT_DONE"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"The delegated child was denied by the sandbox. PARENT_DONE"}}},{"type":"chunk","time":0,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"}
 {"type":"step/end","data":{"turn":2,"step":2}}
 {"type":"turn/end","data":{"turn":2,"reason":{"kind":"completed"}}}
diff --git a/apps/cli/tests/profiles/headless/tests/expected/subagent-settlement/child.expected.jsonl b/apps/cli/tests/profiles/headless/tests/expected/subagent-settlement/child.expected.jsonl
index 196e82c256..b747683429 100644
--- a/apps/cli/tests/profiles/headless/tests/expected/subagent-settlement/child.expected.jsonl
+++ b/apps/cli/tests/profiles/headless/tests/expected/subagent-settlement/child.expected.jsonl
@@ -8,7 +8,7 @@
 {"type":"step/start","data":{"turn":1,"step":1}}
 {"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{sessionId}}"}},"surfaceOp":"append"}
 {"type":"user/message","data":{"content":[{"type":"text","text":"Reply with exactly CHILD_RESULT and nothing else. Do not call send_message."},{"type":"text","text":"Your final answer is delivered automatically if your parent is still online. Include the result and relevant evidence in that answer; the parent does not receive your full transcript, tool output, or reasoning. If your last action is a message to your parent, the completion notice omits your final answer; include the result and relevant evidence in that message."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
-{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\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\nYour parent agent id is \"{{sessionId}}\". Use send_message({ name: \"{{sessionId}}\", message: \"<finding>\" }) when a finding changes what the parent should do next; sending a message does not end your turn.\n\nDelegation depth for `subagent`: current 1, maximum 1, remaining levels 0. Do not call `subagent` at this depth; carry out the work directly.\n\nDelegation depth for `subagent_fork`: current 1, maximum 1, remaining levels 0. Do not call `subagent_fork` at this depth; carry out the work directly.\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":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"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:communication","text":"Your parent agent id is \"{{sessionId}}\". Use send_message({ name: \"{{sessionId}}\", message: \"<finding>\" }) when a finding changes what the parent should do next; sending a message does not end your turn."},{"name":"tool:subagent:depth","text":"Delegation depth for `subagent`: current 1, maximum 1, remaining levels 0. Do not call `subagent` at this depth; carry out the work directly."},{"name":"tool:subagent_fork:depth","text":"Delegation depth for `subagent_fork`: current 1, maximum 1, remaining levels 0. Do not call `subagent_fork` at this depth; carry out the work directly."},{"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":"{{sessionId}}"},"surfaceOp":"append"}
+{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\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\nYour name is \"lead/agent-1\". Your parent agent is \"lead\". Your root agent is \"lead\".\n\nUse list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent.\nMessage your parent when a finding changes what it should do next; sending a message does not end your turn.\n\nDelegation depth for `subagent`: current 1, maximum 1, remaining levels 0. Do not call `subagent` at this depth; carry out the work directly.\n\nDelegation depth for `subagent_fork`: current 1, maximum 1, remaining levels 0. Do not call `subagent_fork` at this depth; carry out the work directly.\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":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"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:identity","text":"Your name is \"lead/agent-1\". Your parent agent is \"lead\". Your root agent is \"lead\"."},{"name":"subagent:communication","text":"Use list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent.\nMessage your parent when a finding changes what it should do next; sending a message does not end your turn."},{"name":"tool:subagent:depth","text":"Delegation depth for `subagent`: current 1, maximum 1, remaining levels 0. Do not call `subagent` at this depth; carry out the work directly."},{"name":"tool:subagent_fork:depth","text":"Delegation depth for `subagent_fork`: current 1, maximum 1, remaining levels 0. Do not call `subagent_fork` at this depth; carry out the work directly."},{"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":"{{sessionId}}"},"surfaceOp":"append"}
 {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial"}}
 {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
 {"type":"session/title","data":{"title":"Reply with exactly CHILD_RESULT and","messageSeqs":[8],"source":{"kind":"fallback"}}}
diff --git a/apps/cli/tests/profiles/headless/tests/expected/subagent-settlement/stream-json.expected.jsonl b/apps/cli/tests/profiles/headless/tests/expected/subagent-settlement/stream-json.expected.jsonl
index 61bc45735b..309fd8085f 100644
--- a/apps/cli/tests/profiles/headless/tests/expected/subagent-settlement/stream-json.expected.jsonl
+++ b/apps/cli/tests/profiles/headless/tests/expected/subagent-settlement/stream-json.expected.jsonl
@@ -4,7 +4,7 @@
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":6,"time":0,"data":{"turn":1,"step":1}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"system/message","seq":7,"time":0,"data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{sessionId}}"}},"surfaceOp":"append"}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":8,"time":0,"data":{"content":[{"type":"text","text":"Start one continuable subagent and acknowledge its completion notice. Do not call list_agents or send_message."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}
-{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":9,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":9,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed.\n\nYou are the root agent named \"lead\".\n\nUse list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."},{"name":"subagent:identity","text":"You are the root agent named \"lead\"."},{"name":"subagent:communication","text":"Use list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":10,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial"}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/context","seq":11,"time":0,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"session/title","seq":12,"time":0,"data":{"title":"Start one continuable subagent and","messageSeqs":[8],"source":{"kind":"fallback"}}}}
@@ -16,13 +16,13 @@
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"subagent-name/bound","seq":18,"time":0,"data":{"version":1,"childId":"{{sessionId}}","name":"lead/agent-1"}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":19,"time":0,"data":{"turn":1,"step":1,"message":{"role":"tool","source":{"kind":"tool","callId":"start-child"},"toolCallId":"start-child","content":[{"type":"text","text":"started subagent {{sessionId}}\nname: lead/agent-1"}],"isError":false,"id":"{{sessionId}}"}},"sourceEventSeqs":[15],"surfaceOp":"append"}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":20,"time":0,"data":{"turn":1,"step":1}}}
-{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"agent/inbox/spliced","seq":21,"time":0,"data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"Background subagent {{sessionId}} finished and will do no further work unless you send it more."},{"type":"text","text":"Its closing message:"},{"type":"text","text":"CHILD_RESULT"}],"source":{"kind":"subagent-settled","form":"notice","summary":"Background subagent {{sessionId}} finished and will do no further work unless you send it more.","senderSessionId":"{{sessionId}}"},"role":"user","id":"{{sessionId}}"}]}}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"agent/inbox/spliced","seq":21,"time":0,"data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"Background subagent {{sessionId}} finished and will do no further work unless you send it more."},{"type":"text","text":"Its closing message:"},{"type":"text","text":"CHILD_RESULT"}],"source":{"kind":"subagent-settled","form":"notice","summary":"Background subagent {{sessionId}} finished and will do no further work unless you send it more.","senderSessionId":"{{sessionId}}","stopReason":"completed","description":"Return child result"},"role":"user","id":"{{sessionId}}"}]}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":22,"time":0,"data":{"turn":1,"step":2}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":23,"time":0,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"text","text":"STARTED"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"usage":{"inputTokens":10,"outputTokens":5},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":0,"index":0,"dt":[],"texts":["STARTED"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"STARTED"}}},{"type":"chunk","time":0,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":24,"time":0,"data":{"turn":1,"step":2}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"agent/inbox/spliced","seq":25,"time":0,"data":{"target":"next-step","start":0,"removedCount":1,"inserted":[]}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":26,"time":0,"data":{"turn":1,"step":3}}}
-{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":27,"time":0,"data":{"content":[{"type":"text","text":"Background subagent {{sessionId}} finished and will do no further work unless you send it more."},{"type":"text","text":"Its closing message:"},{"type":"text","text":"CHILD_RESULT"}],"source":{"kind":"subagent-settled","form":"notice","summary":"Background subagent {{sessionId}} finished and will do no further work unless you send it more.","senderSessionId":"{{sessionId}}"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":27,"time":0,"data":{"content":[{"type":"text","text":"Background subagent {{sessionId}} finished and will do no further work unless you send it more."},{"type":"text","text":"Its closing message:"},{"type":"text","text":"CHILD_RESULT"}],"source":{"kind":"subagent-settled","form":"notice","summary":"Background subagent {{sessionId}} finished and will do no further work unless you send it more.","senderSessionId":"{{sessionId}}","stopReason":"completed","description":"Return child result"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":28,"time":0,"data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"text","text":"PARENT_RECEIVED_SETTLEMENT_NOTICE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"usage":{"inputTokens":10,"outputTokens":5},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":0,"index":0,"dt":[],"texts":["PARENT_RECEIVED_SETTLEMENT_NOTICE"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"PARENT_RECEIVED_SETTLEMENT_NOTICE"}}},{"type":"chunk","time":0,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":29,"time":0,"data":{"turn":1,"step":3}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":30,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}}
diff --git a/apps/cli/tests/profiles/headless/tests/expected/workspace-context-resume/offline-edit/session.expected.jsonl b/apps/cli/tests/profiles/headless/tests/expected/workspace-context-resume/offline-edit/session.expected.jsonl
index cbb82cb603..1e205f3de3 100644
--- a/apps/cli/tests/profiles/headless/tests/expected/workspace-context-resume/offline-edit/session.expected.jsonl
+++ b/apps/cli/tests/profiles/headless/tests/expected/workspace-context-resume/offline-edit/session.expected.jsonl
@@ -17,7 +17,7 @@
 {"type":"system/message","data":{"turn":2,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{sessionId}}"}},"sourceEventSeqs":[2],"surfaceOp":{"op":"replace","startSeq":2,"endSeq":2}}
 {"type":"user/message","data":{"content":[{"type":"text","text":"Acknowledge the current workspace instruction."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
 {"type":"user/message","data":{"content":[{"type":"text","text":"<system-reminder>\nUpdated instructions from: AGENTS.md\n\nThis file changed after it was loaded. Use the following content instead of the previously loaded instructions from this file.\n\nNew workspace instruction after offline edit.\n\n</system-reminder>"}],"source":{"kind":"agent-instructions","form":"instructions","changes":[{"action":"replace","scope":".\u0000AGENTS.md","path":"AGENTS.md","digest":"d8375b516f158718bd3463bc8eb7ed42c011b29f"}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
-{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
+{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed.\n\nYou are the root agent named \"lead\".\n\nUse list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."},{"name":"subagent:identity","text":"You are the root agent named \"lead\"."},{"name":"subagent:communication","text":"Use list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
 {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial","startsSeries":true}}
 {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
 {"type":"session/title","data":{"title":"Remember the workspace instruction.","messageSeqs":[3],"source":{"kind":"fallback"}}}
diff --git a/apps/cli/tests/profiles/headless/tests/expected/workspace-context-resume/precedence-change/session.expected.jsonl b/apps/cli/tests/profiles/headless/tests/expected/workspace-context-resume/precedence-change/session.expected.jsonl
index 3bd9c55f95..6e7ad62ae7 100644
--- a/apps/cli/tests/profiles/headless/tests/expected/workspace-context-resume/precedence-change/session.expected.jsonl
+++ b/apps/cli/tests/profiles/headless/tests/expected/workspace-context-resume/precedence-change/session.expected.jsonl
@@ -17,7 +17,7 @@
 {"type":"system/message","data":{"turn":2,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{sessionId}}"}},"sourceEventSeqs":[2],"surfaceOp":{"op":"replace","startSeq":2,"endSeq":2}}
 {"type":"user/message","data":{"content":[{"type":"text","text":"Acknowledge the current workspace instruction."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
 {"type":"user/message","data":{"content":[{"type":"text","text":"<system-reminder>\nThis complete workspace instruction baseline replaces all earlier workspace instruction baselines. The following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nCurrent AGENTS rule.\n\n\nInstructions from: CLAUDE.md\n\nCurrent CLAUDE rule.\n\n</system-reminder>"}],"source":{"kind":"agent-instructions","form":"instructions","baseline":true,"baselineIdentity":"{\"projectRoot\":\"\",\"projectRootMarkers\":[\".git\"],\"maxBytes\":65536,\"maxSourceBytes\":1048576,\"instructionFileCandidates\":[\"AGENTS.md\",\"CLAUDE.md\"],\"localInstructionFileCandidates\":[\"AGENTS.local.md\",\"CLAUDE.local.md\"]}","changes":[{"action":"set","scope":".\u0000AGENTS.md","path":"AGENTS.md","digest":"7f53d2327837129750aef117f9754a001c46cf68"},{"action":"set","scope":".\u0000CLAUDE.md","path":"CLAUDE.md","digest":"5b1e9e3fd759eee6b43ceff899e47fb10c64701a"}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
-{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
+{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed.\n\nYou are the root agent named \"lead\".\n\nUse list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."},{"name":"subagent:identity","text":"You are the root agent named \"lead\"."},{"name":"subagent:communication","text":"Use list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
 {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial","startsSeries":true}}
 {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
 {"type":"session/title","data":{"title":"Remember the workspace instruction.","messageSeqs":[3],"source":{"kind":"fallback"}}}
diff --git a/docs/module-graph.md b/docs/module-graph.md
index 3bb12ea5b9..a7df2196d4 100644
--- a/docs/module-graph.md
+++ b/docs/module-graph.md
@@ -1386,12 +1386,12 @@ flowchart TD
   pkg_sdk_protocol --> pkg_subagent
   pkg_sdk_protocol --> pkg_user_questions
   pkg_agent_team --> pkg_agent
-  pkg_agent_team --> pkg_commands
   pkg_agent_team --> pkg_llm
   pkg_agent_team --> pkg_session
   pkg_agent_team --> pkg_session_persistence
   pkg_agent_team --> pkg_session_projection
   pkg_agent_team --> pkg_subagent
+  pkg_agent_team --> pkg_typert_protocol
   pkg_workflow_ptc --> pkg_agent
   pkg_workflow_ptc --> pkg_llm
   pkg_workflow_ptc --> pkg_ptc_runtime
@@ -1843,7 +1843,7 @@ flowchart TD
 | [`hooks-claude-code`](../packages/experimental/hooks-claude-code) | `experimental` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/experimental/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`working-directory`](../packages/session/working-directory) |
 | [`tool-ralph`](../packages/experimental/tool-ralph) | `experimental` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) |
 | [`sdk-protocol`](../packages/sdk/protocol) | `sdk` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`user-questions`](../packages/interaction/user-questions) |
-| [`agent-team`](../packages/team/agent-team) | `team` | [`agent`](../packages/core/agent), [`commands`](../packages/interaction/commands), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session/session-persistence), [`session-projection`](../packages/session/session-projection), [`subagent`](../packages/subagent/subagent) |
+| [`agent-team`](../packages/team/agent-team) | `team` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session/session-persistence), [`session-projection`](../packages/session/session-projection), [`subagent`](../packages/subagent/subagent), [`typert-protocol`](../packages/typert/protocol) |
 | [`workflow-ptc`](../packages/workflow/workflow-ptc) | `workflow` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`ptc-runtime`](../packages/ptc-runtime/ptc-runtime), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow), [`working-directory`](../packages/session/working-directory) |
 | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`agent-preset-registry`](../packages/preset/agent-preset-registry), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-projection`](../packages/session/session-projection), [`subagent`](../packages/subagent/subagent), [`subagent-names`](../packages/subagent/subagent-names), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
 | [`tool-subagent-control`](../packages/subagent/tool-subagent-control) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-names`](../packages/subagent/subagent-names), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
diff --git a/docs/module-graph.zh.md b/docs/module-graph.zh.md
index 2c4e269640..96110826c8 100644
--- a/docs/module-graph.zh.md
+++ b/docs/module-graph.zh.md
@@ -1388,12 +1388,12 @@ flowchart TD
   pkg_sdk_protocol --> pkg_subagent
   pkg_sdk_protocol --> pkg_user_questions
   pkg_agent_team --> pkg_agent
-  pkg_agent_team --> pkg_commands
   pkg_agent_team --> pkg_llm
   pkg_agent_team --> pkg_session
   pkg_agent_team --> pkg_session_persistence
   pkg_agent_team --> pkg_session_projection
   pkg_agent_team --> pkg_subagent
+  pkg_agent_team --> pkg_typert_protocol
   pkg_workflow_ptc --> pkg_agent
   pkg_workflow_ptc --> pkg_llm
   pkg_workflow_ptc --> pkg_ptc_runtime
@@ -1845,7 +1845,7 @@ flowchart TD
 | [`hooks-claude-code`](../packages/experimental/hooks-claude-code) | `experimental` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/experimental/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`working-directory`](../packages/session/working-directory) |
 | [`tool-ralph`](../packages/experimental/tool-ralph) | `experimental` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) |
 | [`sdk-protocol`](../packages/sdk/protocol) | `sdk` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`user-questions`](../packages/interaction/user-questions) |
-| [`agent-team`](../packages/team/agent-team) | `team` | [`agent`](../packages/core/agent), [`commands`](../packages/interaction/commands), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session/session-persistence), [`session-projection`](../packages/session/session-projection), [`subagent`](../packages/subagent/subagent) |
+| [`agent-team`](../packages/team/agent-team) | `team` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session/session-persistence), [`session-projection`](../packages/session/session-projection), [`subagent`](../packages/subagent/subagent), [`typert-protocol`](../packages/typert/protocol) |
 | [`workflow-ptc`](../packages/workflow/workflow-ptc) | `workflow` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`ptc-runtime`](../packages/ptc-runtime/ptc-runtime), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow), [`working-directory`](../packages/session/working-directory) |
 | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`agent-preset-registry`](../packages/preset/agent-preset-registry), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-projection`](../packages/session/session-projection), [`subagent`](../packages/subagent/subagent), [`subagent-names`](../packages/subagent/subagent-names), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
 | [`tool-subagent-control`](../packages/subagent/tool-subagent-control) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-names`](../packages/subagent/subagent-names), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
diff --git a/packages/client/ui-agent-team/tests/team-disable-confirmation-callbacks.client.spec.tsx b/packages/client/ui-agent-team/tests/team-disable-confirmation-callbacks.client.spec.tsx
new file mode 100644
index 0000000000..92fa679c4c
--- /dev/null
+++ b/packages/client/ui-agent-team/tests/team-disable-confirmation-callbacks.client.spec.tsx
@@ -0,0 +1,43 @@
+// @vitest-environment jsdom
+
+import type { ComponentProps } from 'react'
+import { afterEach, expect, it, onTestFinished, vi } from 'vitest'
+import { act, cleanup, fireEvent, render, screen } from '@testing-library/react'
+import { SessionId } from '@deepseek-ai/dsh-session'
+import { makeTranslate } from '@deepseek-ai/dsh-client-test-runtime'
+import type { Button } from '@deepseek-ai/dsh-client-ui-primitives'
+import { TeamDisableConfirmation, type TeamDisableConfirmationProps } from '../src/client/TeamDisableConfirmation.tsx'
+import { zh } from '../src/client/locales.ts'
+
+vi.mock('../src/client/TeamDisableConfirmation.module.css', () => ({ default: {} }))
+vi.mock('@deepseek-ai/dsh-client-ui-primitives', async (importOriginal) => {
+  const actual = await importOriginal<typeof import('@deepseek-ai/dsh-client-ui-primitives')>()
+  return {
+    ...actual,
+    // Deliver repeated activations to the form even while its native button would suppress them.
+    Button: (props: ComponentProps<typeof Button>) => <actual.Button {...props} disabled={false} aria-disabled={props.disabled} />,
+  }
+})
+
+afterEach(cleanup)
+
+it('keeps one disable operation pending despite repeated callbacks without optional stylesheet classes', async () => {
+  const pending = Promise.withResolvers<string | null>()
+  onTestFinished(async () => { await act(async () => { pending.resolve(null) }) })
+  const sessionId = SessionId('pending-disable-session')
+  const disableTeam = vi.fn<TeamDisableConfirmationProps['disableTeam']>(() => pending.promise)
+  const cancelDisable = vi.fn<TeamDisableConfirmationProps['cancelDisable']>()
+  const useDisableRequest: TeamDisableConfirmationProps['useDisableRequest'] = select => select({ sessionId })
+  const props = { useDisableRequest, disableTeam, cancelDisable, t: makeTranslate(zh) } as TeamDisableConfirmationProps
+  render(<TeamDisableConfirmation {...props} />)
+  const confirm = screen.getByRole('button', { name: zh['disable.confirm'] })
+  fireEvent.click(confirm)
+  expect(confirm.getAttribute('aria-disabled')).toBe('true')
+  fireEvent.click(confirm)
+  fireEvent.click(screen.getByRole('button', { name: zh['disable.cancel'] }))
+  expect(disableTeam).toHaveBeenCalledExactlyOnceWith(sessionId)
+  expect(cancelDisable).not.toHaveBeenCalled()
+  expect(screen.getByRole('dialog', { name: zh['disable.title'] })).toBeTruthy()
+  await act(async () => { pending.resolve(null) })
+  expect(cancelDisable).toHaveBeenCalledExactlyOnceWith(sessionId)
+})
diff --git a/scripts/snapshots/python-sdk-single-exe/authoring/model-visible.json b/scripts/snapshots/python-sdk-single-exe/authoring/model-visible.json
index 7bd408b309..9aecf7c302 100644
--- a/scripts/snapshots/python-sdk-single-exe/authoring/model-visible.json
+++ b/scripts/snapshots/python-sdk-single-exe/authoring/model-visible.json
@@ -8,7 +8,7 @@
     }
   },
   "catalogs": [
-    "Query the packaged Python environment for Office authoring.Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\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`).<system-reminder>\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n<available_skills>\n- `office`: Create, edit, inspect, or convert Office documents, spreadsheets, presentations, and PDFs. Load to choose the relevant workflow.\n- `office-docx`: Create, read, edit, and validate Word documents (.docx).\n- `office-export-pdf`: Convert an Office document to a requested PDF with LibreOffice Kit.\n- `office-pptx`: Create, read, edit, and validate PowerPoint presentations (.pptx).\n- `office-recalculate`: Refresh spreadsheet formula caches and verify calculated values with LibreOffice Kit.\n- `office-render`: Render requested document images or inspect visual layout with LibreOffice Kit.\n- `office-xlsx`: Read, create, edit, and validate Excel workbooks, data, and formulas (.xlsx).\n</available_skills>\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\nA user may also invoke a skill directly; its <skill_content> block then appears in this conversation. Follow it, and do not call the `skill` tool again for that skill.\n</system-reminder>Time sampled while preparing turn 1, step 1: 2026-10-16T00:00:00+00:00[UTC]\nBrowser time zone for this request: unavailable. Ask the user to clarify otherwise-unqualified dates and times.\nElapsed since the preceding model-visible message: unavailable."
+    "Query the packaged Python environment for Office authoring.Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\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 the root agent named \"lead\".\n\nUse list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent.<system-reminder>\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n<available_skills>\n- `office`: Create, edit, inspect, or convert Office documents, spreadsheets, presentations, and PDFs. Load to choose the relevant workflow.\n- `office-docx`: Create, read, edit, and validate Word documents (.docx).\n- `office-export-pdf`: Convert an Office document to a requested PDF with LibreOffice Kit.\n- `office-pptx`: Create, read, edit, and validate PowerPoint presentations (.pptx).\n- `office-recalculate`: Refresh spreadsheet formula caches and verify calculated values with LibreOffice Kit.\n- `office-render`: Render requested document images or inspect visual layout with LibreOffice Kit.\n- `office-xlsx`: Read, create, edit, and validate Excel workbooks, data, and formulas (.xlsx).\n</available_skills>\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\nA user may also invoke a skill directly; its <skill_content> block then appears in this conversation. Follow it, and do not call the `skill` tool again for that skill.\n</system-reminder>Time sampled while preparing turn 1, step 1: 2026-10-16T00:00:00+00:00[UTC]\nBrowser time zone for this request: unavailable. Ask the user to clarify otherwise-unqualified dates and times.\nElapsed since the preceding model-visible message: unavailable."
   ],
   "result": {
     "python": "{{python}}",
diff --git a/scripts/snapshots/python-sdk-single-exe/authoring/win-x64/model-visible.json b/scripts/snapshots/python-sdk-single-exe/authoring/win-x64/model-visible.json
index 9115819ea9..d9c09347db 100644
--- a/scripts/snapshots/python-sdk-single-exe/authoring/win-x64/model-visible.json
+++ b/scripts/snapshots/python-sdk-single-exe/authoring/win-x64/model-visible.json
@@ -8,7 +8,7 @@
     }
   },
   "catalogs": [
-    "Query the packaged Python environment for Office authoring.Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\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`).<system-reminder>\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n<available_skills>\n- `diagnose-windows-sandbox-acl`: Use on Windows for unexpected DSH sandbox access denials: workspace writes or listing fail, or an ordinarily readable path cannot be read. One bundled command inspects the path and every ancestor and repairs the ACL problems it proves in that same run. Expected confinement denials need no ACL repair.\n- `office`: Create, edit, inspect, or convert Office documents, spreadsheets, presentations, and PDFs. Load to choose the relevant workflow.\n- `office-docx`: Create, read, edit, and validate Word documents (.docx).\n- `office-export-pdf`: Convert an Office document to a requested PDF with LibreOffice Kit.\n- `office-pptx`: Create, read, edit, and validate PowerPoint presentations (.pptx).\n- `office-recalculate`: Refresh spreadsheet formula caches and verify calculated values with LibreOffice Kit.\n- `office-render`: Render requested document images or inspect visual layout with LibreOffice Kit.\n- `office-xlsx`: Read, create, edit, and validate Excel workbooks, data, and formulas (.xlsx).\n</available_skills>\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\nA user may also invoke a skill directly; its <skill_content> block then appears in this conversation. Follow it, and do not call the `skill` tool again for that skill.\n</system-reminder>Time sampled while preparing turn 1, step 1: 2026-10-16T00:00:00+00:00[UTC]\nBrowser time zone for this request: unavailable. Ask the user to clarify otherwise-unqualified dates and times.\nElapsed since the preceding model-visible message: unavailable."
+    "Query the packaged Python environment for Office authoring.Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\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 the root agent named \"lead\".\n\nUse list_agents({}) to find agents in your tree and their full names.\nUse send_message({ name: \"<full agent path>\", message: \"...\" }) to message another agent.<system-reminder>\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n<available_skills>\n- `diagnose-windows-sandbox-acl`: Use on Windows for unexpected DSH sandbox access denials: workspace writes or listing fail, or an ordinarily readable path cannot be read. One bundled command inspects the path and every ancestor and repairs the ACL problems it proves in that same run. Expected confinement denials need no ACL repair.\n- `office`: Create, edit, inspect, or convert Office documents, spreadsheets, presentations, and PDFs. Load to choose the relevant workflow.\n- `office-docx`: Create, read, edit, and validate Word documents (.docx).\n- `office-export-pdf`: Convert an Office document to a requested PDF with LibreOffice Kit.\n- `office-pptx`: Create, read, edit, and validate PowerPoint presentations (.pptx).\n- `office-recalculate`: Refresh spreadsheet formula caches and verify calculated values with LibreOffice Kit.\n- `office-render`: Render requested document images or inspect visual layout with LibreOffice Kit.\n- `office-xlsx`: Read, create, edit, and validate Excel workbooks, data, and formulas (.xlsx).\n</available_skills>\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\nA user may also invoke a skill directly; its <skill_content> block then appears in this conversation. Follow it, and do not call the `skill` tool again for that skill.\n</system-reminder>Time sampled while preparing turn 1, step 1: 2026-10-16T00:00:00+00:00[UTC]\nBrowser time zone for this request: unavailable. Ask the user to clarify otherwise-unqualified dates and times.\nElapsed since the preceding model-visible message: unavailable."
   ],
   "result": {
     "python": "{{python}}",