Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

test(sandbox-policy): refresh durable context snapshots

Browse Source
This commit is contained in:
NI0317
2026-07-30 23:17:33 +08:00
parent 7d8931fa8c
commit e61054c4d1
19 changed files with 198 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
apps/web/tests/queue-actions.e2e.ts
View File

@@ -111,7 +111,7 @@ describe('web e2e: queue row actions', () => {
const snapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd)
await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE)
expect(sessionEvents.filter(event => event.type === 'user/message')).toHaveLength(1)
expect(sessionEvents.filter(event => event.type === 'user/message' && event.data.source.kind === 'user')).toHaveLength(1)
expect(tripwire.pageErrors).toEqual([])
expect(tripwire.warnings).toEqual([])

8
apps/web/tests/snapshots/code-mode-round/ui.expected.md
View File

@@ -11,6 +11,14 @@
- img
- button "编辑":
- img
- button "上下文注入":
- img
- img
- text: 上下文注入
- button "上下文注入":
- img
- img
- text: 上下文注入
- 'button "Think The user wants me to write a single `run_code` program that:"':
- img
- img

8
apps/web/tests/snapshots/cordis-tool-round/ui.expected.md
View File

@@ -11,6 +11,14 @@
- img
- button "编辑":
- img
- button "上下文注入":
- img
- img
- text: 上下文注入
- button "上下文注入":
- img
- img
- text: 上下文注入
- button "Think The user wants me to:":
- img
- img

8
apps/web/tests/snapshots/fresh-round-trip/ui.expected.md
View File

@@ -11,6 +11,14 @@
- img
- button "编辑":
- img
- button "上下文注入":
- img
- img
- text: 上下文注入
- button "上下文注入":
- img
- img
- text: 上下文注入
- button "Think The user wants me to run a simple bash command and reply with \"DONE\".":
- img
- img

8
apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md
View File

@@ -11,6 +11,14 @@
- img
- button "编辑":
- img
- button "上下文注入":
- img
- img
- text: 上下文注入
- button "上下文注入":
- img
- img
- text: 上下文注入
- button "Think The user wants me to reply with a single word. Let me comply.":
- img
- img

8
apps/web/tests/snapshots/live-interactions/cancel.expected.md
View File

@@ -11,6 +11,14 @@
- img
- button "编辑":
- img
- button "上下文注入":
- img
- img
- text: 上下文注入
- button "上下文注入":
- img
- img
- text: 上下文注入
- paragraph: partial
- text: 已停止
- button "复制":

8
apps/web/tests/snapshots/live-interactions/error-auth.expected.md
View File

@@ -11,6 +11,14 @@
- img
- button "编辑":
- img
- button "上下文注入":
- img
- img
- text: 上下文注入
- button "上下文注入":
- img
- img
- text: 上下文注入
- textbox "Message the agent"
- button "Add attachment":
- img

8
apps/web/tests/snapshots/live-interactions/retry.expected.md
View File

@@ -11,6 +11,14 @@
- img
- button "编辑":
- img
- button "上下文注入":
- img
- img
- text: 上下文注入
- button "上下文注入":
- img
- img
- text: 上下文注入
- button "Think The user is asking for a one-sentence description of event sourcing. This is a straightforward knowledge question that doesn't require any skill loading or tool calls.":
- img
- img

8
apps/web/tests/snapshots/question-composer/answered.expected.md
View File

@@ -11,6 +11,14 @@
- img
- button "编辑":
- img
- button "上下文注入":
- img
- img
- text: 上下文注入
- button "上下文注入":
- img
- img
- text: 上下文注入
- button "Think The user wants me to use the ask_user_question tool with specific parameters. Let me do exactly that.":
- img
- img

8
apps/web/tests/snapshots/queue-actions/collapsed.expected.md
View File

@@ -11,6 +11,14 @@
- img
- button "编辑":
- img
- button "上下文注入":
- img
- img
- text: 上下文注入
- button "上下文注入":
- img
- img
- text: 上下文注入
- paragraph: partial
- button "2 条排队消息"
- textbox "Message the agent"

8
apps/web/tests/snapshots/queue-actions/editing.expected.md
View File

@@ -11,6 +11,14 @@
- img
- button "编辑":
- img
- button "上下文注入":
- img
- img
- text: 上下文注入
- button "上下文注入":
- img
- img
- text: 上下文注入
- paragraph: partial
- button "2 条排队消息" [disabled] [expanded]
- list:

8
apps/web/tests/snapshots/queue-actions/ui.expected.md
View File

@@ -11,6 +11,14 @@
- img
- button "编辑":
- img
- button "上下文注入":
- img
- img
- text: 上下文注入
- button "上下文注入":
- img
- img
- text: 上下文注入
- paragraph: partial
- list:
- listitem:

8
apps/web/tests/snapshots/steering/mid-steer.expected.md
View File

@@ -11,6 +11,14 @@
- img
- button "编辑":
- img
- button "上下文注入":
- img
- img
- text: 上下文注入
- button "上下文注入":
- img
- img
- text: 上下文注入
- button "Think The user wants me to use the ask_user_question tool to ask them a specific question with the given parameters. Let me do exactly that.":
- img
- img

8
apps/web/tests/snapshots/steering/settled.expected.md
View File

@@ -11,6 +11,14 @@
- img
- button "编辑":
- img
- button "上下文注入":
- img
- img
- text: 上下文注入
- button "上下文注入":
- img
- img
- text: 上下文注入
- button "Think The user wants me to use the ask_user_question tool to ask them a specific question with the given parameters. Let me do exactly that.":
- img
- img

1
examples/acp-agent/tests/acp.snapshot.ts
View File

@@ -111,6 +111,7 @@ const SCENARIOS: Scenario[] = [
name: 'session-query-spill',
hasModelTurn: true,
recorded: false,
overridden: true,
pinsHeader: true,
headerClass: 'session-query',
configPath: SESSION_QUERY_CONFIG,

101
examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl
View File

@@ -2,53 +2,54 @@
{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
{"type":"user/message","seq":1,"time":0,"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":"session/title","seq":2,"time":0,"data":{"title":"Create a durable two-round goal","messageSeqs":[1],"source":{"kind":"fallback"}}}
{"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":4,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_create","name":"create_goal","argumentsDelta":"{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}}}
{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}}}}
{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":20,"outputTokens":8}}}}
{"type":"assistant/chunk","seq":9,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":10,"time":0,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"usage":{"inputTokens":20,"outputTokens":8}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"}
{"type":"tool/call","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}}
{"type":"tool/result","seq":12,"time":0,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_goal_create"},"content":[{"type":"tool-result","toolCallId":"call_goal_create","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":2},\"activation\":\"armed\"}"}],"isError":false}],"role":"user","id":"{{sessionId}}"}},"sourceEventSeqs":[11],"surfaceOp":"append"}
{"type":"user/message","seq":13,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":2},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":0,"change":{"kind":"goal/change","version":1,"operation":"create","goal":{"id":"goal-{{sessionId}}","revision":1,"objective":"Finish the ACP goal-session snapshot proof","phase":"active","maxGoalRounds":2},"roundsStarted":0,"createdAt":0,"updatedAt":0}},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"step/end","seq":14,"time":0,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":15,"time":0,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_get","name":"get_goal","argumentsDelta":"{}"}}}
{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_get","name":"get_goal","arguments":"{}"}}}}
{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":30,"outputTokens":4}}}}
{"type":"assistant/chunk","seq":20,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":21,"time":0,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_goal_get","name":"get_goal","arguments":"{}"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"usage":{"inputTokens":30,"outputTokens":4}},"sourceEventSeqs":[16,17,18,19,20],"surfaceOp":"append"}
{"type":"tool/call","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_get","name":"get_goal","arguments":"{}"}}
{"type":"tool/result","seq":23,"time":0,"data":{"turn":1,"step":2,"message":{"source":{"kind":"tool","callId":"call_goal_get"},"content":[{"type":"tool-result","toolCallId":"call_goal_get","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":2},\"activation\":\"armed\"}"}],"isError":false}],"role":"user","id":"{{sessionId}}"}},"sourceEventSeqs":[22],"surfaceOp":"append"}
{"type":"step/end","seq":24,"time":0,"data":{"turn":1,"step":2}}
{"type":"step/start","seq":25,"time":0,"data":{"turn":1,"step":3}}
{"type":"assistant/chunk","seq":26,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":27,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":0,"text":"GOAL READY"}}}
{"type":"assistant/chunk","seq":28,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GOAL READY"}}}}
{"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":35,"outputTokens":2}}}}
{"type":"assistant/chunk","seq":30,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":31,"time":0,"data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"text","text":"GOAL READY"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"usage":{"inputTokens":35,"outputTokens":2}},"sourceEventSeqs":[26,27,28,29,30],"surfaceOp":"append"}
{"type":"step/end","seq":32,"time":0,"data":{"turn":1,"step":3}}
{"type":"turn/end","seq":33,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}
{"type":"turn/start","seq":34,"time":0,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":1}}}}
{"type":"user/message","seq":35,"time":0,"data":{"content":[{"type":"text","text":"<goal_round>\nObjective: \"Finish the ACP goal-session snapshot proof\"\nRound: 1/2\n\nContinue working toward the objective in this same session. Treat the current workspace, tool results, and durable session state as authoritative; inspect them instead of assuming earlier narration is still current. Make concrete progress and verify the result. Before claiming completion, gather evidence that the whole objective is achieved, read the current goal, and mark it complete. If work remains, leave the goal active for the next round. Follow the configured goal-tool policy before reporting a blocker.\n</goal_round>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":1},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"step/start","seq":36,"time":0,"data":{"turn":2,"step":1}}
{"type":"assistant/chunk","seq":37,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":38,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":0,"text":"GOAL ROUND ONE"}}}
{"type":"assistant/chunk","seq":39,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GOAL ROUND ONE"}}}}
{"type":"assistant/chunk","seq":40,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":40,"outputTokens":3}}}}
{"type":"assistant/chunk","seq":41,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":42,"time":0,"data":{"turn":2,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"GOAL ROUND ONE"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"usage":{"inputTokens":40,"outputTokens":3}},"sourceEventSeqs":[37,38,39,40,41],"surfaceOp":"append"}
{"type":"step/end","seq":43,"time":0,"data":{"turn":2,"step":1}}
{"type":"turn/end","seq":44,"time":0,"data":{"turn":2,"reason":{"kind":"completed"}}}
{"type":"turn/start","seq":45,"time":0,"data":{"turn":3,"trigger":{"kind":"message","source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":2}}}}
{"type":"user/message","seq":46,"time":0,"data":{"content":[{"type":"text","text":"<goal_round>\nObjective: \"Finish the ACP goal-session snapshot proof\"\nRound: 2/2\n\nContinue working toward the objective in this same session. Treat the current workspace, tool results, and durable session state as authoritative; inspect them instead of assuming earlier narration is still current. Make concrete progress and verify the result. Before claiming completion, gather evidence that the whole objective is achieved, read the current goal, and mark it complete. If work remains, leave the goal active for the next round. Follow the configured goal-tool policy before reporting a blocker.\n</goal_round>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":2},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"step/start","seq":47,"time":0,"data":{"turn":3,"step":1}}
{"type":"assistant/chunk","seq":48,"time":0,"data":{"turn":3,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":49,"time":0,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":0,"text":"partial"}}}
{"type":"step/end","seq":50,"time":0,"data":{"turn":3,"step":1}}
{"type":"turn/end","seq":51,"time":0,"data":{"turn":3,"reason":{"kind":"aborted"}}}
{"type":"user/message","seq":52,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":2,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"paused\",\"maxGoalRounds\":2},\"roundsStarted\":2,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":2,"round":0,"change":{"kind":"goal/change","version":1,"operation":"pause","goal":{"id":"goal-{{sessionId}}","revision":2,"objective":"Finish the ACP goal-session snapshot proof","phase":"paused","maxGoalRounds":2},"roundsStarted":2,"createdAt":0,"updatedAt":0}},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"user/message","seq":3,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict the write and edit tools or one-shot bash commands.\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":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"step/start","seq":4,"time":0,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":5,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_create","name":"create_goal","argumentsDelta":"{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}}}
{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}}}}
{"type":"assistant/chunk","seq":9,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":20,"outputTokens":8}}}}
{"type":"assistant/chunk","seq":10,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":11,"time":0,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"usage":{"inputTokens":20,"outputTokens":8}},"sourceEventSeqs":[6,7,8,9,10],"surfaceOp":"append"}
{"type":"tool/call","seq":12,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}}
{"type":"tool/result","seq":13,"time":0,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_goal_create"},"content":[{"type":"tool-result","toolCallId":"call_goal_create","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":2},\"activation\":\"armed\"}"}],"isError":false}],"role":"user","id":"{{sessionId}}"}},"sourceEventSeqs":[12],"surfaceOp":"append"}
{"type":"user/message","seq":14,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":2},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":0,"change":{"kind":"goal/change","version":1,"operation":"create","goal":{"id":"goal-{{sessionId}}","revision":1,"objective":"Finish the ACP goal-session snapshot proof","phase":"active","maxGoalRounds":2},"roundsStarted":0,"createdAt":0,"updatedAt":0}},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"step/end","seq":15,"time":0,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":16,"time":0,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_get","name":"get_goal","argumentsDelta":"{}"}}}
{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_get","name":"get_goal","arguments":"{}"}}}}
{"type":"assistant/chunk","seq":20,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":30,"outputTokens":4}}}}
{"type":"assistant/chunk","seq":21,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":22,"time":0,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_goal_get","name":"get_goal","arguments":"{}"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"usage":{"inputTokens":30,"outputTokens":4}},"sourceEventSeqs":[17,18,19,20,21],"surfaceOp":"append"}
{"type":"tool/call","seq":23,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_get","name":"get_goal","arguments":"{}"}}
{"type":"tool/result","seq":24,"time":0,"data":{"turn":1,"step":2,"message":{"source":{"kind":"tool","callId":"call_goal_get"},"content":[{"type":"tool-result","toolCallId":"call_goal_get","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":2},\"activation\":\"armed\"}"}],"isError":false}],"role":"user","id":"{{sessionId}}"}},"sourceEventSeqs":[23],"surfaceOp":"append"}
{"type":"step/end","seq":25,"time":0,"data":{"turn":1,"step":2}}
{"type":"step/start","seq":26,"time":0,"data":{"turn":1,"step":3}}
{"type":"assistant/chunk","seq":27,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":28,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":0,"text":"GOAL READY"}}}
{"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GOAL READY"}}}}
{"type":"assistant/chunk","seq":30,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":35,"outputTokens":2}}}}
{"type":"assistant/chunk","seq":31,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":32,"time":0,"data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"text","text":"GOAL READY"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"usage":{"inputTokens":35,"outputTokens":2}},"sourceEventSeqs":[27,28,29,30,31],"surfaceOp":"append"}
{"type":"step/end","seq":33,"time":0,"data":{"turn":1,"step":3}}
{"type":"turn/end","seq":34,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}
{"type":"turn/start","seq":35,"time":0,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":1}}}}
{"type":"user/message","seq":36,"time":0,"data":{"content":[{"type":"text","text":"<goal_round>\nObjective: \"Finish the ACP goal-session snapshot proof\"\nRound: 1/2\n\nContinue working toward the objective in this same session. Treat the current workspace, tool results, and durable session state as authoritative; inspect them instead of assuming earlier narration is still current. Make concrete progress and verify the result. Before claiming completion, gather evidence that the whole objective is achieved, read the current goal, and mark it complete. If work remains, leave the goal active for the next round. Follow the configured goal-tool policy before reporting a blocker.\n</goal_round>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":1},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"step/start","seq":37,"time":0,"data":{"turn":2,"step":1}}
{"type":"assistant/chunk","seq":38,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":39,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":0,"text":"GOAL ROUND ONE"}}}
{"type":"assistant/chunk","seq":40,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GOAL ROUND ONE"}}}}
{"type":"assistant/chunk","seq":41,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":40,"outputTokens":3}}}}
{"type":"assistant/chunk","seq":42,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":43,"time":0,"data":{"turn":2,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"GOAL ROUND ONE"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"usage":{"inputTokens":40,"outputTokens":3}},"sourceEventSeqs":[38,39,40,41,42],"surfaceOp":"append"}
{"type":"step/end","seq":44,"time":0,"data":{"turn":2,"step":1}}
{"type":"turn/end","seq":45,"time":0,"data":{"turn":2,"reason":{"kind":"completed"}}}
{"type":"turn/start","seq":46,"time":0,"data":{"turn":3,"trigger":{"kind":"message","source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":2}}}}
{"type":"user/message","seq":47,"time":0,"data":{"content":[{"type":"text","text":"<goal_round>\nObjective: \"Finish the ACP goal-session snapshot proof\"\nRound: 2/2\n\nContinue working toward the objective in this same session. Treat the current workspace, tool results, and durable session state as authoritative; inspect them instead of assuming earlier narration is still current. Make concrete progress and verify the result. Before claiming completion, gather evidence that the whole objective is achieved, read the current goal, and mark it complete. If work remains, leave the goal active for the next round. Follow the configured goal-tool policy before reporting a blocker.\n</goal_round>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":2},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"step/start","seq":48,"time":0,"data":{"turn":3,"step":1}}
{"type":"assistant/chunk","seq":49,"time":0,"data":{"turn":3,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":50,"time":0,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":0,"text":"partial"}}}
{"type":"step/end","seq":51,"time":0,"data":{"turn":3,"step":1}}
{"type":"turn/end","seq":52,"time":0,"data":{"turn":3,"reason":{"kind":"aborted"}}}
{"type":"user/message","seq":53,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":2,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"paused\",\"maxGoalRounds\":2},\"roundsStarted\":2,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":2,"round":0,"change":{"kind":"goal/change","version":1,"operation":"pause","goal":{"id":"goal-{{sessionId}}","revision":2,"objective":"Finish the ACP goal-session snapshot proof","phase":"paused","maxGoalRounds":2},"roundsStarted":2,"createdAt":0,"updatedAt":0}},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}

2
examples/acp-agent/tests/snapshots/session-query-spill/input.json
View File

@@ -2,6 +2,6 @@
"steps": [
{ "op": "initialize" },
{ "op": "newSession" },
{ "op": "prompt", "text": "Read request event 4 with session_event_read, verify the complete spill was retained, then reply DONE." }
{ "op": "prompt", "text": "Read request event 5 with session_event_read, verify the complete spill was retained, then reply DONE." }
]
}

32
examples/acp-agent/tests/snapshots/session-query-spill/replay.override.json Normal file
View File

@@ -0,0 +1,32 @@
[
{
"kind": "chunks",
"chunks": [
{ "type": "block-start", "index": 0, "blockType": "tool-call" },
{ "type": "tool-call-delta", "index": 0, "id": "call_session_query_spill", "name": "session_event_read", "argumentsDelta": "{\"seq\":5}" },
{ "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_session_query_spill", "name": "session_event_read", "arguments": "{\"seq\":5}" } },
{ "type": "usage", "usage": { "inputTokens": 10, "outputTokens": 5 } },
{ "type": "finish", "reason": { "kind": "tool-calls" } }
]
},
{
"kind": "chunks",
"chunks": [
{ "type": "block-start", "index": 0, "blockType": "tool-call" },
{ "type": "tool-call-delta", "index": 0, "id": "call_verify_session_query_spill", "name": "bash", "argumentsDelta": "{\"command\":\"file=$(find /tmp/dsh-acp-snap-035d1d054 -name '*-session_event_read.txt' -type f); grep -q request/header \\\"$file\\\" && grep -q session_event_search \\\"$file\\\" && echo SPILL_CANONICAL_OK\",\"description\":\"Verify complete session query spill\"}" },
{ "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_verify_session_query_spill", "name": "bash", "arguments": "{\"command\":\"file=$(find /tmp/dsh-acp-snap-035d1d054 -name '*-session_event_read.txt' -type f); grep -q request/header \\\"$file\\\" && grep -q session_event_search \\\"$file\\\" && echo SPILL_CANONICAL_OK\",\"description\":\"Verify complete session query spill\"}" } },
{ "type": "usage", "usage": { "inputTokens": 10, "outputTokens": 5 } },
{ "type": "finish", "reason": { "kind": "tool-calls" } }
]
},
{
"kind": "chunks",
"chunks": [
{ "type": "block-start", "index": 0, "blockType": "text" },
{ "type": "text-delta", "index": 0, "text": "DONE" },
{ "type": "block-end", "index": 0, "block": { "type": "text", "text": "DONE" } },
{ "type": "usage", "usage": { "inputTokens": 10, "outputTokens": 2 } },
{ "type": "finish", "reason": { "kind": "stop" } }
]
}
]

16
examples/acp-agent/tests/snapshots/session-query-spill/session.jsonl
View File

@@ -1,18 +1,18 @@
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}","delegationDepth":0}
{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Read request event 4 with session_event_read, verify the complete spill was retained, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"e4951ffb-95c6-4539-b905-e9ce632f0b6e"},"surfaceOp":"append"}
{"type":"session/title","seq":2,"time":0,"data":{"title":"Read request event 4 with","messageSeqs":[1],"source":{"kind":"fallback"}}}
{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Read request event 5 with session_event_read, verify the complete spill was retained, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"e4951ffb-95c6-4539-b905-e9ce632f0b6e"},"surfaceOp":"append"}
{"type":"session/title","seq":2,"time":0,"data":{"title":"Read request event 5 with","messageSeqs":[1],"source":{"kind":"fallback"}}}
{"type":"user/message","seq":3,"time":1785417661483,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict the write and edit tools or one-shot bash commands.\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":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"role":"user","id":"3ed2a64d-9876-4b36-bce3-d625096df43f"},"surfaceOp":"append"}
{"type":"step/start","seq":4,"time":1785417661483,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":5,"time":1785417661484,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_session_query_spill","name":"session_event_read","argumentsDelta":"{\"seq\":4}"}}}
{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_session_query_spill","name":"session_event_read","arguments":"{\"seq\":4}"}}}}
{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_session_query_spill","name":"session_event_read","argumentsDelta":"{\"seq\":5}"}}}
{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_session_query_spill","name":"session_event_read","arguments":"{\"seq\":5}"}}}}
{"type":"assistant/chunk","seq":9,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
{"type":"assistant/chunk","seq":10,"time":1785417661492,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":11,"time":1785417661492,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_session_query_spill","name":"session_event_read","arguments":"{\"seq\":4}"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-flash"},"id":"987f0e82-c12c-4aa6-8d8f-15cbbe80c321"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[6,7,8,9,10],"surfaceOp":"append"}
{"type":"tool/call","seq":12,"time":1785417661493,"data":{"turn":1,"step":1,"callId":"call_session_query_spill","name":"session_event_read","arguments":"{\"seq\":4}"}}
{"type":"tool/result","seq":13,"time":1785417661502,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_session_query_spill"},"content":[{"type":"tool-result","toolCallId":"call_session_query_spill","content":[{"type":"text","text":"Session {{sessionId}} — Read request event 4 with\nTarget event seq 4:\n```json\n{\n \"type\": \"step/start\",\n \"seq\": 4,\n \"time\": 1785417661483,\n \"data\": {\n \"turn\": 1,\n \"step\": 1\n }\n}\n```"}],"isError":false}],"role":"user","id":"4b6e307a-b405-44f2-b53f-383e508ad96e"}},"sourceEventSeqs":[12],"surfaceOp":"append"}
{"type":"assistant/message","seq":11,"time":1785417661492,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_session_query_spill","name":"session_event_read","arguments":"{\"seq\":5}"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-flash"},"id":"987f0e82-c12c-4aa6-8d8f-15cbbe80c321"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[6,7,8,9,10],"surfaceOp":"append"}
{"type":"tool/call","seq":12,"time":1785417661493,"data":{"turn":1,"step":1,"callId":"call_session_query_spill","name":"session_event_read","arguments":"{\"seq\":5}"}}
{"type":"tool/result","seq":13,"time":1785417661502,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_session_query_spill"},"content":[{"type":"tool-result","toolCallId":"call_session_query_spill","content":[{"type":"text","text":"Session {{sessionId}} — Read request event 5 with\nTarget event seq 5:\n```json\n{\n \"type\": \"request/header\",\n \"seq\": 5,\n \"time\": 1785423916061,\n \"data\": {\n \"header\": {\n \"config\": {\n \"provider\": \"deepseek\",\n \"model\": \"deepseek-v4-flash\"\n },\n rmissions: one sentence for the user explaining why this exact file operation needs the wider access.\"\n }\n },\n \"required\": [\n \"file_path\",\n \"content\"\n ]\n }\n }\n ]\n },\n \"reason\": \"initial\"\n }\n}\n```\n\n(Omitted 35785 bytes. Full formatted result stored at: /tmp/dsh-acp-snap-035d1d054/session-ca0adefdb246/87abfab171fb-session_event_read.txt. Use read with offset/limit, or grep this path to search within it.)"}],"isError":false}],"role":"user","id":"4b6e307a-b405-44f2-b53f-383e508ad96e"}},"sourceEventSeqs":[12],"surfaceOp":"append"}
{"type":"step/end","seq":14,"time":1785417661502,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":15,"time":1785417661510,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
@@ -22,7 +22,7 @@
{"type":"assistant/chunk","seq":20,"time":1785417661515,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":21,"time":1785417661515,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_verify_session_query_spill","name":"bash","arguments":"{\"command\":\"file=$(find /tmp/dsh-acp-snap-035d1d054 -name '*-session_event_read.txt' -type f); grep -q request/header \\\"$file\\\" && grep -q session_event_search \\\"$file\\\" && echo SPILL_CANONICAL_OK\",\"description\":\"Verify complete session query spill\"}"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-flash"},"id":"043fb25e-b70e-4013-9a03-0c66dbfa4156"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[16,17,18,19,20],"surfaceOp":"append"}
{"type":"tool/call","seq":22,"time":1785417661515,"data":{"turn":1,"step":2,"callId":"call_verify_session_query_spill","name":"bash","arguments":"{\"command\":\"file=$(find /tmp/dsh-acp-snap-035d1d054 -name '*-session_event_read.txt' -type f); grep -q request/header \\\"$file\\\" && grep -q session_event_search \\\"$file\\\" && echo SPILL_CANONICAL_OK\",\"description\":\"Verify complete session query spill\"}"}}
{"type":"tool/result","seq":23,"time":1785417661535,"data":{"turn":1,"step":2,"message":{"source":{"kind":"tool","callId":"call_verify_session_query_spill"},"content":[{"type":"tool-result","toolCallId":"call_verify_session_query_spill","content":[{"type":"text","text":"[stderr]\nfind: /tmp/dsh-acp-snap-035d1d054: No such file or directory\ngrep: : No such file or directory\n[exit code: 2]"}],"isError":false}],"role":"user","id":"d3048cac-2c66-43dc-92c6-f73a3f7a277a"}},"sourceEventSeqs":[22],"surfaceOp":"append"}
{"type":"tool/result","seq":23,"time":1785417661535,"data":{"turn":1,"step":2,"message":{"source":{"kind":"tool","callId":"call_verify_session_query_spill"},"content":[{"type":"tool-result","toolCallId":"call_verify_session_query_spill","content":[{"type":"text","text":"SPILL_CANONICAL_OK\n"}],"isError":false}],"role":"user","id":"d3048cac-2c66-43dc-92c6-f73a3f7a277a"}},"sourceEventSeqs":[22],"surfaceOp":"append"}
{"type":"step/end","seq":24,"time":1785417661535,"data":{"turn":1,"step":2}}
{"type":"step/start","seq":25,"time":1785417661544,"data":{"turn":1,"step":3}}
{"type":"assistant/chunk","seq":26,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}