Merge remote-tracking branch 'origin/master' into session-query-tool
# Conflicts: # docs/architecture.i18n.yaml
This commit is contained in:
@@ -147,11 +147,11 @@ const SCENARIOS: Scenario[] = [
|
||||
// Keyless, authored (like error-finish/cancel): deterministically forcing a
|
||||
// LIVE model to repeat one call three times is not a stable recording, so
|
||||
// the fixture scripts five identical todo_write calls and pins BOTH reminder
|
||||
// tiers (gentle at 3, detailed at 5) as context/message in transcript and log.
|
||||
// tiers (gentle at 3, detailed at 5) as injected user/message in transcript and log.
|
||||
{ name: 'repeat-tool-guard', hasModelTurn: true, recorded: false },
|
||||
// Authored replay: a root AGENTS.md pins the session prefix, then a read in
|
||||
// nested/ discovers its narrower AGENTS.md as a raw, metadata-bearing
|
||||
// context/message. Both AGENTS.md fixtures are symlinks to a sibling
|
||||
// injected user/message. Both AGENTS.md fixtures are symlinks to a sibling
|
||||
// AGENTS.canonical.md, so this scenario also guards that discovery follows a
|
||||
// symlinked instruction file to its target's content. The scenario-specific
|
||||
// config keeps home/root discovery hermetic, and the resulting prefix needs
|
||||
@@ -227,7 +227,7 @@ const SCENARIOS: Scenario[] = [
|
||||
// tool/code-dispatch events. Each overlay composes and pins its own header class.
|
||||
{ name: 'code-mode-turn', hasModelTurn: true, recorded: true, pinsHeader: true, headerClass: 'code', configPath: CODE_MODE_CONFIG },
|
||||
// A nested fs dispatch inside run_code discovers workspace instructions. The
|
||||
// context/message must follow the outer result while retaining workspace
|
||||
// injected user/message must follow the outer result while retaining workspace
|
||||
// provenance, which proves Code Mode carries deferred tool context end to end.
|
||||
{
|
||||
name: 'code-mode-workspace-context',
|
||||
|
||||
@@ -688,7 +688,7 @@
|
||||
{"type":"turn/start","seq":686,"time":1783421455801,"data":{"turn":4,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"approval/policy","seq":687,"time":1783421455801,"data":{"policy":"never"}}
|
||||
{"type":"user/message","seq":688,"time":1783421455801,"data":{"content":[{"type":"text","text":"帮我创建一个 c.md"}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"context/message","seq":689,"time":1783421455802,"data":{"content":[{"type":"text","text":"The approval policy changed from \"ask\" to \"never\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"approval"}},"surfaceOp":"append"}
|
||||
{"type":"user/message","seq":689,"time":1783421455802,"data":{"content":[{"type":"text","text":"The approval policy changed from \"ask\" to \"never\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"approval"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":690,"time":1783421455802,"data":{"turn":4,"step":1}}
|
||||
{"type":"request/header-delta","seq":691,"time":1783421455802,"data":{"system":{"keepStart":13,"keepEnd":0,"insert":["","Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation."]}}}
|
||||
{"type":"assistant/chunk","seq":692,"time":1783421456825,"data":{"turn":4,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
@@ -830,7 +830,7 @@
|
||||
{"type":"turn/start","seq":828,"time":1783421478599,"data":{"turn":5,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"bash/sandbox-mode","seq":829,"time":1783421478599,"data":{"mode":"workspace-write"}}
|
||||
{"type":"user/message","seq":830,"time":1783421478599,"data":{"content":[{"type":"text","text":"帮我创建一个 d.md"}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"context/message","seq":831,"time":1783421478600,"data":{"content":[{"type":"text","text":"The bash sandbox mode changed from \"read-only\" to \"workspace-write\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"tool-bash"}},"surfaceOp":"append"}
|
||||
{"type":"user/message","seq":831,"time":1783421478600,"data":{"content":[{"type":"text","text":"The bash sandbox mode changed from \"read-only\" to \"workspace-write\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"tool-bash"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":832,"time":1783421478600,"data":{"turn":5,"step":1}}
|
||||
{"type":"request/header-delta","seq":833,"time":1783421478600,"data":{"system":{"keepStart":12,"keepEnd":2,"insert":["Bash commands run under the \"workspace-write\" file sandbox."]}}}
|
||||
{"type":"assistant/chunk","seq":834,"time":1783421479489,"data":{"turn":5,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
@@ -1482,7 +1482,7 @@
|
||||
{"type":"turn/start","seq":1480,"time":1783421524030,"data":{"turn":7,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"approval/policy","seq":1481,"time":1783421524030,"data":{"policy":"ask"}}
|
||||
{"type":"user/message","seq":1482,"time":1783421524030,"data":{"content":[{"type":"text","text":"帮我在 ~ 创建一个 f.md"}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"context/message","seq":1483,"time":1783421524030,"data":{"content":[{"type":"text","text":"The approval policy changed from \"never\" to \"ask\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"approval"}},"surfaceOp":"append"}
|
||||
{"type":"user/message","seq":1483,"time":1783421524030,"data":{"content":[{"type":"text","text":"The approval policy changed from \"never\" to \"ask\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"approval"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":1484,"time":1783421524030,"data":{"turn":7,"step":1}}
|
||||
{"type":"request/header-delta","seq":1485,"time":1783421524030,"data":{"system":{"keepStart":13,"keepEnd":0,"insert":[]}}}
|
||||
{"type":"assistant/chunk","seq":1486,"time":1783421524940,"data":{"turn":7,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
@@ -1946,7 +1946,7 @@
|
||||
{"type":"turn/start","seq":1944,"time":1783421552564,"data":{"turn":9,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"bash/sandbox-mode","seq":1945,"time":1783421552564,"data":{"mode":"danger-full-access"}}
|
||||
{"type":"user/message","seq":1946,"time":1783421552564,"data":{"content":[{"type":"text","text":"创建一个 h.md"}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"context/message","seq":1947,"time":1783421552564,"data":{"content":[{"type":"text","text":"The bash sandbox mode changed from \"workspace-write\" to \"danger-full-access\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"tool-bash"}},"surfaceOp":"append"}
|
||||
{"type":"user/message","seq":1947,"time":1783421552564,"data":{"content":[{"type":"text","text":"The bash sandbox mode changed from \"workspace-write\" to \"danger-full-access\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"tool-bash"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":1948,"time":1783421552564,"data":{"turn":9,"step":1}}
|
||||
{"type":"request/header-delta","seq":1949,"time":1783421552564,"data":{"system":{"keepStart":12,"keepEnd":0,"insert":["Bash commands run under the \"danger-full-access\" file sandbox."]}}}
|
||||
{"type":"assistant/chunk","seq":1950,"time":1783421553289,"data":{"turn":9,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
|
||||
@@ -12,7 +12,7 @@
|
||||
{"type":"assistant/message","seq":10,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"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,"callId":"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},"sourceEventSeqs":[11],"surfaceOp":"append"}
|
||||
{"type":"context/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},"meta":{"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}},"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},"meta":{"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}},"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"}}}
|
||||
@@ -49,6 +49,6 @@
|
||||
{"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":"context/message","seq":50,"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},"meta":{"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}},"surfaceOp":"append"}
|
||||
{"type":"user/message","seq":50,"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},"meta":{"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}},"surfaceOp":"append"}
|
||||
{"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"}}}
|
||||
|
||||
@@ -83,6 +83,7 @@ describe('ACP same-session goal snapshot', () => {
|
||||
const calls = events.filter(event => event.type === 'tool/call').map(event => event.data.name)
|
||||
expect(calls).toEqual(['create_goal', 'get_goal'])
|
||||
const rounds = events.flatMap(event => event.type === 'user/message' && event.data.source.kind === 'goal'
|
||||
&& event.data.source.round > 0
|
||||
? [event.data.source.round]
|
||||
: [])
|
||||
expect(rounds).toEqual([1, 2])
|
||||
|
||||
@@ -87,7 +87,7 @@
|
||||
{"type":"tool/call","seq":85,"time":1783921767208,"data":{"turn":1,"step":1,"callId":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","arguments":"{\"code\": \"const content = await tools.read({ file_path: \\\"nested/task.txt\\\" });\\nreturn content.lines.map(line => line.text).join(String.fromCharCode(10));\"}"}}
|
||||
{"type":"tool/code-dispatch","seq":86,"time":1783921767270,"data":{"parentCallId":"call_00_6APApmaKLRDlXKMdIcWL5139","subCallId":"call_00_6APApmaKLRDlXKMdIcWL5139:code:1","name":"read","arguments":{"file_path":"nested/task.txt"},"isError":false,"resultSummary":"<path>./nested/task.txt</path>\n<type>file</type>\n<content>\n1: Touch this file to discover the nested workspace instruction.\n\n(End of file - total 1 lines)\n</content>"}}
|
||||
{"type":"tool/result","seq":87,"time":1783921767271,"data":{"turn":1,"step":1,"callId":"call_00_6APApmaKLRDlXKMdIcWL5139","content":[{"type":"text","text":"Touch this file to discover the nested workspace instruction."}],"isError":false},"sourceEventSeqs":[85],"surfaceOp":"append"}
|
||||
{"type":"context/message","seq":88,"time":1783921767272,"data":{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nThese instructions apply to work under `nested`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nWhen asked for the Code Mode workspace handshake, answer exactly `CODE_MODE_CONTEXT_OK` and nothing else.\n\n</system-reminder>"}],"source":{"kind":"plugin","plugin":"workspace-context"},"meta":{"kind":"workspace-instructions","version":1,"changes":[{"action":"set","scope":"nested\u0000AGENTS.md","path":"nested/AGENTS.md","digest":"ae22936ed26dc76b7107005ed6d5e2482a88668a"}]}},"surfaceOp":"append"}
|
||||
{"type":"user/message","seq":88,"time":1784811336862,"data":{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nThese instructions apply to work under `nested`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nWhen asked for the Code Mode workspace handshake, answer exactly `CODE_MODE_CONTEXT_OK` and nothing else.\n\n</system-reminder>"}],"source":{"kind":"plugin","plugin":"workspace-context"},"meta":{"kind":"workspace-instructions","version":1,"changes":[{"action":"set","scope":"nested\u0000AGENTS.md","path":"nested/AGENTS.md","digest":"ae22936ed26dc76b7107005ed6d5e2482a88668a"}]}},"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":89,"time":1783921767272,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":90,"time":1783921767272,"data":{"turn":1,"step":2}}
|
||||
{"type":"assistant/chunk","seq":91,"time":1783921768339,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -63,7 +63,7 @@
|
||||
{"type":"hook/invoked","seq":61,"time":1783352197968,"data":{"turn":1,"point":"PostToolUse","dialect":"claude","handlerId":"claude:PostToolUse:1","matcher":"bash"}}
|
||||
{"type":"hook/result","seq":62,"time":1783352197976,"data":{"turn":1,"point":"PostToolUse","handlerId":"claude:PostToolUse:1","decision":"pass","exitCode":0,"durationMs":7.404540999999881}}
|
||||
{"type":"tool/result","seq":63,"time":1783352197976,"data":{"turn":1,"step":1,"callId":"call_00_HbCMzTslWBZTSphWN0z97382","content":[{"type":"text","text":"HELLO\n"}],"isError":false},"sourceEventSeqs":[60],"surfaceOp":"append"}
|
||||
{"type":"context/message","seq":64,"time":1783352197976,"data":{"content":[{"type":"text","text":"Note: command output has been verified against the audit log."}],"source":{"kind":"plugin","plugin":"hooks-claude"}},"surfaceOp":"append"}
|
||||
{"type":"user/message","seq":64,"time":1783352197976,"data":{"content":[{"type":"text","text":"Note: command output has been verified against the audit log."}],"source":{"kind":"plugin","plugin":"hooks-claude"}},"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":65,"time":1783352197977,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":66,"time":1783352197977,"data":{"turn":1,"step":2}}
|
||||
{"type":"assistant/chunk","seq":67,"time":1783352198981,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
{"type":"hook/invoked","seq":1,"time":1783352160546,"data":{"turn":1,"point":"UserPromptSubmit","dialect":"claude","handlerId":"claude:UserPromptSubmit:1"}}
|
||||
{"type":"hook/result","seq":2,"time":1783352160564,"data":{"turn":1,"point":"UserPromptSubmit","handlerId":"claude:UserPromptSubmit:1","decision":"pass","exitCode":0,"durationMs":17.45639600000004}}
|
||||
{"type":"user/message","seq":3,"time":1783352160564,"data":{"content":[{"type":"text","text":"What is my favorite color? Reply with just the color and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"context/message","seq":4,"time":1783352160564,"data":{"content":[{"type":"text","text":"The user has previously stated their favorite color is teal."}],"source":{"kind":"plugin","plugin":"hooks-claude"}},"surfaceOp":"append"}
|
||||
{"type":"user/message","seq":4,"time":1783352160564,"data":{"content":[{"type":"text","text":"The user has previously stated their favorite color is teal."}],"source":{"kind":"plugin","plugin":"hooks-claude"}},"surfaceOp":"append"}
|
||||
{"type":"session/title","seq":5,"time":1783352160564,"data":{"title":"What is my favorite color?","messageSeqs":[3],"source":{"kind":"fallback"}}}
|
||||
{"type":"step/start","seq":6,"time":1783352160565,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":7,"time":1783352160566,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
|
||||
@@ -63,7 +63,7 @@
|
||||
{"type":"hook/invoked","seq":61,"time":1783352229622,"data":{"turn":1,"point":"PostToolUse","dialect":"codex","handlerId":"codex:PostToolUse:1","matcher":"bash"}}
|
||||
{"type":"hook/result","seq":62,"time":1783352229632,"data":{"turn":1,"point":"PostToolUse","handlerId":"codex:PostToolUse:1","decision":"pass","exitCode":0,"durationMs":9.27664199999981}}
|
||||
{"type":"tool/result","seq":63,"time":1783352229632,"data":{"turn":1,"step":1,"callId":"call_00_Q6wHtakaip2QNfIXaVJY5458","content":[{"type":"text","text":"HELLO\n"}],"isError":false},"sourceEventSeqs":[60],"surfaceOp":"append"}
|
||||
{"type":"context/message","seq":64,"time":1783352229633,"data":{"content":[{"type":"text","text":"Note: command output has been verified against the audit log."}],"source":{"kind":"plugin","plugin":"hooks-codex"}},"surfaceOp":"append"}
|
||||
{"type":"user/message","seq":64,"time":1783352229633,"data":{"content":[{"type":"text","text":"Note: command output has been verified against the audit log."}],"source":{"kind":"plugin","plugin":"hooks-codex"}},"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":65,"time":1783352229633,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":66,"time":1783352229633,"data":{"turn":1,"step":2}}
|
||||
{"type":"assistant/chunk","seq":67,"time":1783352230757,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
{"type":"hook/invoked","seq":1,"time":1783352209687,"data":{"turn":1,"point":"UserPromptSubmit","dialect":"codex","handlerId":"codex:UserPromptSubmit:1"}}
|
||||
{"type":"hook/result","seq":2,"time":1783352209706,"data":{"turn":1,"point":"UserPromptSubmit","handlerId":"codex:UserPromptSubmit:1","decision":"pass","exitCode":0,"durationMs":19.49695100000008}}
|
||||
{"type":"user/message","seq":3,"time":1783352209707,"data":{"content":[{"type":"text","text":"What is my favorite color? Reply with just the color and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"context/message","seq":4,"time":1783352209707,"data":{"content":[{"type":"text","text":"The user has previously stated their favorite color is teal."}],"source":{"kind":"plugin","plugin":"hooks-codex"}},"surfaceOp":"append"}
|
||||
{"type":"user/message","seq":4,"time":1783352209707,"data":{"content":[{"type":"text","text":"The user has previously stated their favorite color is teal."}],"source":{"kind":"plugin","plugin":"hooks-codex"}},"surfaceOp":"append"}
|
||||
{"type":"session/title","seq":5,"time":1783352209707,"data":{"title":"What is my favorite color?","messageSeqs":[3],"source":{"kind":"fallback"}}}
|
||||
{"type":"step/start","seq":6,"time":1783352209709,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":7,"time":1783352209710,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
|
||||
@@ -106,7 +106,7 @@
|
||||
{"type":"sandbox/mode","seq":104,"time":1784518115842,"data":{"mode":"danger-full-access"}}
|
||||
{"type":"approval/policy","seq":105,"time":1783962244624,"data":{"policy":"never"}}
|
||||
{"type":"user/message","seq":106,"time":1783962244624,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: cat out.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"context/message","seq":107,"time":1783962244624,"data":{"content":[{"type":"text","text":"The approval policy changed from \"ask\" to \"never\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"user-approval"}},"surfaceOp":"append"}
|
||||
{"type":"user/message","seq":107,"time":1783962244624,"data":{"content":[{"type":"text","text":"The approval policy changed from \"ask\" to \"never\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"user-approval"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":108,"time":1783962244624,"data":{"turn":2,"step":1}}
|
||||
{"type":"request/header","seq":109,"time":1784000791271,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"change"}}
|
||||
{"type":"assistant/chunk","seq":110,"time":1783860671025,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
|
||||
@@ -35,7 +35,7 @@
|
||||
{"type":"tool/call","seq":33,"time":0,"data":{"turn":1,"step":3,"callId":"call_3","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}}
|
||||
{"type":"todo/write","seq":34,"time":0,"data":{"todos":[{"content":"watch the kettle boil","status":"in_progress"}]}}
|
||||
{"type":"tool/result","seq":35,"time":0,"data":{"turn":1,"step":3,"callId":"call_3","content":[{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}],"isError":false},"sourceEventSeqs":[33],"surfaceOp":"append"}
|
||||
{"type":"context/message","seq":36,"time":0,"data":{"content":[{"type":"text","text":"You are repeating the exact same tool call with identical arguments. Carefully analyze the previous result before calling again: if the task is not complete, try a different approach or different arguments instead of repeating the call."}],"source":{"kind":"plugin","plugin":"repeat-tool-guard"}},"surfaceOp":"append"}
|
||||
{"type":"user/message","seq":36,"time":0,"data":{"content":[{"type":"text","text":"You are repeating the exact same tool call with identical arguments. Carefully analyze the previous result before calling again: if the task is not complete, try a different approach or different arguments instead of repeating the call."}],"source":{"kind":"plugin","plugin":"repeat-tool-guard"}},"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":37,"time":0,"data":{"turn":1,"step":3}}
|
||||
{"type":"step/start","seq":38,"time":0,"data":{"turn":1,"step":4}}
|
||||
{"type":"assistant/chunk","seq":39,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
|
||||
@@ -58,7 +58,7 @@
|
||||
{"type":"tool/call","seq":56,"time":0,"data":{"turn":1,"step":5,"callId":"call_5","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}}
|
||||
{"type":"todo/write","seq":57,"time":0,"data":{"todos":[{"content":"watch the kettle boil","status":"in_progress"}]}}
|
||||
{"type":"tool/result","seq":58,"time":0,"data":{"turn":1,"step":5,"callId":"call_5","content":[{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}],"isError":false},"sourceEventSeqs":[56],"surfaceOp":"append"}
|
||||
{"type":"context/message","seq":59,"time":0,"data":{"content":[{"type":"text","text":"Repeated tool call detected:\n- tool: todo_write\n- consecutive_calls: 5\n- arguments: {\"todos\":[{\"content\":\"watch the kettle boil\",\"status\":\"in_progress\"}]}\nThe repeated calls are not making progress. Do not call this tool with these exact arguments again. Inspect the latest result and choose a different action, different arguments, or finish the task if enough evidence has been gathered."}],"source":{"kind":"plugin","plugin":"repeat-tool-guard"}},"surfaceOp":"append"}
|
||||
{"type":"user/message","seq":59,"time":0,"data":{"content":[{"type":"text","text":"Repeated tool call detected:\n- tool: todo_write\n- consecutive_calls: 5\n- arguments: {\"todos\":[{\"content\":\"watch the kettle boil\",\"status\":\"in_progress\"}]}\nThe repeated calls are not making progress. Do not call this tool with these exact arguments again. Inspect the latest result and choose a different action, different arguments, or finish the task if enough evidence has been gathered."}],"source":{"kind":"plugin","plugin":"repeat-tool-guard"}},"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":60,"time":0,"data":{"turn":1,"step":5}}
|
||||
{"type":"step/start","seq":61,"time":0,"data":{"turn":1,"step":6}}
|
||||
{"type":"assistant/chunk","seq":62,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
|
||||
|
||||
@@ -12,7 +12,7 @@
|
||||
{"type":"assistant/message","seq":10,"time":1783778297070,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":11,"time":1783778297070,"data":{"turn":1,"step":1,"callId":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}}
|
||||
{"type":"tool/result","seq":12,"time":1783778297072,"data":{"turn":1,"step":1,"callId":"call_workspace_read","content":[{"type":"text","text":"<path>{{cwd}}/nested/task.txt</path>\n<type>file</type>\n<content>\n1: snapshot task\n\n(End of file - total 1 lines)\n</content>"}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"}
|
||||
{"type":"context/message","seq":13,"time":1783778297072,"data":{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nThese instructions apply to work under `nested`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nNested snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"plugin","plugin":"workspace-context"},"meta":{"kind":"workspace-instructions","version":1,"changes":[{"action":"set","scope":"nested\u0000AGENTS.md","path":"nested/AGENTS.md","digest":"c446df9a85c7e73a3055f394a4822a19ac9ead5a"}]}},"surfaceOp":"append"}
|
||||
{"type":"user/message","seq":13,"time":1783778297072,"data":{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nThese instructions apply to work under `nested`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nNested snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"plugin","plugin":"workspace-context"},"meta":{"kind":"workspace-instructions","version":1,"changes":[{"action":"set","scope":"nested\u0000AGENTS.md","path":"nested/AGENTS.md","digest":"c446df9a85c7e73a3055f394a4822a19ac9ead5a"}]}},"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":14,"time":1783778297072,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":15,"time":1783778297072,"data":{"turn":1,"step":2}}
|
||||
{"type":"assistant/chunk","seq":16,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
|
||||
|
||||
@@ -42,7 +42,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
|
||||
const log = vi.spyOn(console, 'log').mockImplementation(() => {})
|
||||
const agent = ctx.agentLoop.create(SessionId('cordis-e2e-listener'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
|
||||
|
||||
agent.send([{
|
||||
agent.followup([{
|
||||
type: 'text',
|
||||
text: 'Use cordis_mount to mount a plugin that listens to the \'agent/status\' '
|
||||
+ 'cordis event and logs every change with console.log. Reply "mounted" once done.',
|
||||
@@ -58,7 +58,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
|
||||
})
|
||||
expect(resultText(mid)).toContain('dyn-')
|
||||
|
||||
agent.send([{ type: 'text', text: 'Now unmount the plugin you just mounted.' }])
|
||||
agent.followup([{ type: 'text', text: 'Now unmount the plugin you just mounted.' }])
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
const after = await ctx.tools.execute({
|
||||
@@ -72,7 +72,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
|
||||
ctx = await cordisHarness()
|
||||
const agent = ctx.agentLoop.create(SessionId('cordis-e2e-selftool'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
|
||||
|
||||
agent.send([{
|
||||
agent.followup([{
|
||||
type: 'text',
|
||||
text: 'Give yourself a new tool: use cordis_mount to mount a plugin with '
|
||||
+ 'inject ["tools"] that calls harness.registerTool(ctx, harness.defineTool({...})) '
|
||||
@@ -119,7 +119,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
|
||||
ctx = await cordisHarness()
|
||||
const agent = ctx.agentLoop.create(SessionId('cordis-e2e-compose'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
|
||||
|
||||
agent.send([{
|
||||
agent.followup([{
|
||||
type: 'text',
|
||||
text: 'Mount TWO separate plugins with cordis_mount. First a provider: apply calls '
|
||||
+ 'ctx.provide(\'shouter\', { shout: (s) => s.toUpperCase() }). Second a consumer with '
|
||||
@@ -144,7 +144,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
|
||||
.flatMap(event => event.data.content.filter(block => block.type === 'text').map(block => block.text))
|
||||
expect(shoutResults.some(text => text.includes('QUIET'))).toBe(true)
|
||||
|
||||
agent.send([{ type: 'text', text: 'Now unmount ONLY the provider plugin (the one that provided shouter).' }])
|
||||
agent.followup([{ type: 'text', text: 'Now unmount ONLY the provider plugin (the one that provided shouter).' }])
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
// The consumer must have been parked by cordis itself: service gone,
|
||||
|
||||
@@ -311,7 +311,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p
|
||||
ctx = await codeModeHarness(workdir)
|
||||
const agent = ctx.agentLoop.create(SessionId('e2e-code-mode'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
|
||||
|
||||
agent.send([{
|
||||
agent.followup([{
|
||||
type: 'text',
|
||||
text: 'Using one run_code program: run `echo alpha-7` with the bash tool, run `echo beta-9` with the bash tool, '
|
||||
+ 'then write both outputs joined by a plus sign into combined.txt (bash heredoc or redirect), '
|
||||
@@ -363,7 +363,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p
|
||||
agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
|
||||
})
|
||||
|
||||
handle.agent.send([{
|
||||
handle.agent.followup([{
|
||||
type: 'text',
|
||||
text: 'Use one run_code program to call tools.read on pkg/deep/task.txt. After it finishes, answer: Code Mode workspace handshake?',
|
||||
}])
|
||||
@@ -372,7 +372,8 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p
|
||||
const events: SessionEvent[] = [...handle.agent.session.events]
|
||||
const dispatch = events.find(event => event.type === 'tool/code-dispatch' && event.data.name === 'read')
|
||||
const outerResult = events.find(event => event.type === 'tool/result')
|
||||
const workspaceContext = events.find(event => event.type === 'context/message'
|
||||
const workspaceContext = events.find(event => event.type === 'user/message'
|
||||
&& event.data.source.kind === 'plugin'
|
||||
&& typeof event.data.meta === 'object'
|
||||
&& event.data.meta !== null
|
||||
&& !Array.isArray(event.data.meta)
|
||||
|
||||
@@ -56,7 +56,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('coding task: fix a failing test
|
||||
ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT })
|
||||
const agent = ctx.agentLoop.create(SessionId('e2e-task'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
|
||||
|
||||
agent.send([{
|
||||
agent.followup([{
|
||||
type: 'text',
|
||||
text: 'In the current directory, `node add.test.js` fails because add.js has a bug. '
|
||||
+ 'Fix add.js so the test passes, run `node add.test.js` to verify, and report the result. '
|
||||
|
||||
@@ -46,7 +46,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa
|
||||
})
|
||||
const agent = ctx.agentLoop.create(SessionId('e2e-compaction'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
|
||||
|
||||
agent.send([{
|
||||
agent.followup([{
|
||||
type: 'text',
|
||||
text: 'Read file1.txt, file2.txt, file3.txt, and file4.txt one at a '
|
||||
+ 'time using cat (a separate bash command for each). After reading all four, tell me how '
|
||||
|
||||
@@ -30,7 +30,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('full loop: real model + real bas
|
||||
ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT })
|
||||
const agent = ctx.agentLoop.create(SessionId('e2e-loop'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
|
||||
|
||||
agent.send([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }])
|
||||
agent.followup([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }])
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
const events = [...agent.session.events]
|
||||
|
||||
@@ -222,9 +222,14 @@ describe('headless stream-json snapshots', () => {
|
||||
const records = parseJsonl(logs[0]?.content ?? '')
|
||||
const calls = records.filter(record => record.type === 'tool/call')
|
||||
.map(record => (record.data as JsonObject | undefined)?.name)
|
||||
expect(calls).toEqual(['create_goal', 'get_goal'])
|
||||
expect(calls).toEqual(['update_goal', 'create_goal', 'get_goal'])
|
||||
const probeResult = records.find(record => record.type === 'tool/result'
|
||||
&& (record.data as JsonObject | undefined)?.callId === 'call_goal_probe')
|
||||
const probeData = probeResult?.data as JsonObject | undefined
|
||||
expect(probeData?.isError).toBe(true)
|
||||
expect((probeData?.error as JsonObject | undefined)?.code).toBe('GOAL_NOT_FOUND')
|
||||
const goalChanges = records.filter((record) => {
|
||||
if (record.type !== 'context/message') return false
|
||||
if (record.type !== 'user/message') return false
|
||||
const data = record.data as JsonObject | undefined
|
||||
const meta = data?.meta as JsonObject | undefined
|
||||
return meta?.kind === 'goal/change'
|
||||
|
||||
@@ -41,7 +41,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses
|
||||
sessionId: SESSION_ID,
|
||||
agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
|
||||
})).agent
|
||||
first.send([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }])
|
||||
first.followup([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }])
|
||||
await waitForIdle(ctx, first)
|
||||
await ctx.fiber.dispose()
|
||||
ctx = undefined
|
||||
@@ -58,7 +58,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses
|
||||
// The prior user turn is in the rehydrated log before the model is asked.
|
||||
expect(JSON.stringify(resumed.session.deriveMessages())).toContain(SECRET)
|
||||
|
||||
resumed.send([{ type: 'text', text: 'What was the code I asked you to remember? Reply with just the code.' }])
|
||||
resumed.followup([{ type: 'text', text: 'What was the code I asked you to remember? Reply with just the code.' }])
|
||||
await waitForIdle(ctx, resumed)
|
||||
|
||||
// The model recalls it — only possible from the resumed history.
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"steps": [
|
||||
{
|
||||
"op": "prompt",
|
||||
"text": "Create a durable goal to finish the snapshot proof, then inspect it."
|
||||
"text": "Probe strict-schema fillers against missing-goal revision 1, then create a durable goal to finish the snapshot proof and inspect it."
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -1,4 +1,14 @@
|
||||
[
|
||||
{
|
||||
"kind": "chunks",
|
||||
"chunks": [
|
||||
{ "type": "block-start", "index": 0, "blockType": "tool-call" },
|
||||
{ "type": "tool-call-delta", "index": 0, "id": "call_goal_probe", "name": "update_goal", "argumentsDelta": "{\"goal_id\":\"missing-goal\",\"revision\":1,\"action\":\"pause\",\"objective\":\"\",\"max_goal_rounds\":0,\"blocked_reason\":\"\"}" },
|
||||
{ "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_goal_probe", "name": "update_goal", "arguments": "{\"goal_id\":\"missing-goal\",\"revision\":1,\"action\":\"pause\",\"objective\":\"\",\"max_goal_rounds\":0,\"blocked_reason\":\"\"}" } },
|
||||
{ "type": "usage", "usage": { "inputTokens": 15, "outputTokens": 6 } },
|
||||
{ "type": "finish", "reason": { "kind": "tool-calls" } }
|
||||
]
|
||||
},
|
||||
{
|
||||
"kind": "chunks",
|
||||
"chunks": [
|
||||
|
||||
@@ -1,35 +1,45 @@
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Create a durable goal to finish the snapshot proof, then inspect it."}],"source":{"kind":"user"}},"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"session/title","seq":2,"time":0,"data":{"title":"Create a durable goal to","messageSeqs":[1],"source":{"kind":"fallback"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"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"}},"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"session/title","seq":2,"time":0,"data":{"title":"Probe strict-schema fillers against miss","messageSeqs":[1],"source":{"kind":"fallback"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":4,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"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 headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"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 headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":20,"outputTokens":8}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_probe","name":"update_goal","argumentsDelta":"{\"goal_id\":\"missing-goal\",\"revision\":1,\"action\":\"pause\",\"objective\":\"\",\"max_goal_rounds\":0,\"blocked_reason\":\"\"}"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"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_probe","name":"update_goal","arguments":"{\"goal_id\":\"missing-goal\",\"revision\":1,\"action\":\"pause\",\"objective\":\"\",\"max_goal_rounds\":0,\"blocked_reason\":\"\"}"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":15,"outputTokens":6}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":9,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":10,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":20,"outputTokens":8}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":12,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":7},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"context/message","seq":13,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":7},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":0},"meta":{"kind":"goal/change","version":1,"operation":"create","goal":{"id":"goal-{{sessionId}}","revision":1,"objective":"Finish the headless goal-tool snapshot proof","phase":"active","maxGoalRounds":7},"roundsStarted":0,"createdAt":0,"updatedAt":0}},"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":14,"time":0,"data":{"turn":1,"step":1}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":15,"time":0,"data":{"turn":1,"step":2}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"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":"session_event","sessionId":"{{sessionId}}","event":{"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":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":30,"outputTokens":4}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":20,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":21,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"call_goal_get","name":"get_goal","arguments":"{}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":30,"outputTokens":4}},"sourceEventSeqs":[16,17,18,19,20],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_get","name":"get_goal","arguments":"{}"}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":23,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_get","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":7},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[22],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":10,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_goal_probe","name":"update_goal","arguments":"{\"goal_id\":\"missing-goal\",\"revision\":1,\"action\":\"pause\",\"objective\":\"\",\"max_goal_rounds\":0,\"blocked_reason\":\"\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":15,"outputTokens":6}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_probe","name":"update_goal","arguments":"{\"goal_id\":\"missing-goal\",\"revision\":1,\"action\":\"pause\",\"objective\":\"\",\"max_goal_rounds\":0,\"blocked_reason\":\"\"}"}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":12,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_probe","content":[{"type":"text","text":"Error: no current goal"}],"isError":true,"error":{"name":"GoalError","code":"GOAL_NOT_FOUND"}},"sourceEventSeqs":[11],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":13,"time":0,"data":{"turn":1,"step":1}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":14,"time":0,"data":{"turn":1,"step":2}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_create","name":"create_goal","argumentsDelta":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":20,"outputTokens":8}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":20,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":20,"outputTokens":8}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":21,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_create","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":7},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[21],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":23,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":7},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":0},"meta":{"kind":"goal/change","version":1,"operation":"create","goal":{"id":"goal-{{sessionId}}","revision":1,"objective":"Finish the headless goal-tool snapshot proof","phase":"active","maxGoalRounds":7},"roundsStarted":0,"createdAt":0,"updatedAt":0}},"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":"step/start","seq":25,"time":0,"data":{"turn":1,"step":3}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":26,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":27,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":0,"text":"GOAL READY"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"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":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":35,"outputTokens":2}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":30,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":31,"time":0,"data":{"turn":1,"step":3,"content":[{"type":"text","text":"GOAL READY"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":35,"outputTokens":2}},"sourceEventSeqs":[26,27,28,29,30],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":32,"time":0,"data":{"turn":1,"step":3}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":33,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}}
|
||||
{"type":"result","success":true,"sessionId":"{{sessionId}}","turn":1,"result":"GOAL READY","reason":{"kind":"completed"},"usage":{"inputTokens":85,"outputTokens":14}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":26,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":27,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_get","name":"get_goal","argumentsDelta":"{}"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":28,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_get","name":"get_goal","arguments":"{}"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":30,"outputTokens":4}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":30,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":31,"time":0,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"call_goal_get","name":"get_goal","arguments":"{}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":30,"outputTokens":4}},"sourceEventSeqs":[26,27,28,29,30],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":32,"time":0,"data":{"turn":1,"step":3,"callId":"call_goal_get","name":"get_goal","arguments":"{}"}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":33,"time":0,"data":{"turn":1,"step":3,"callId":"call_goal_get","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":7},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[32],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":34,"time":0,"data":{"turn":1,"step":3}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":35,"time":0,"data":{"turn":1,"step":4}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":36,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":37,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"text-delta","index":0,"text":"GOAL READY"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":38,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GOAL READY"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":39,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":35,"outputTokens":2}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":40,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":41,"time":0,"data":{"turn":1,"step":4,"content":[{"type":"text","text":"GOAL READY"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":35,"outputTokens":2}},"sourceEventSeqs":[36,37,38,39,40],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":42,"time":0,"data":{"turn":1,"step":4}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":43,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}}
|
||||
{"type":"result","success":true,"sessionId":"{{sessionId}}","turn":1,"result":"GOAL READY","reason":{"kind":"completed"},"usage":{"inputTokens":100,"outputTokens":20}}
|
||||
|
||||
@@ -28,7 +28,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a
|
||||
ctx = await codingHarness(workdir, { persona: TODO_SYSTEM_PROMPT })
|
||||
const agent = ctx.agentLoop.create(SessionId('e2e-todo'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
|
||||
|
||||
agent.send([{ type: 'text', text:
|
||||
agent.followup([{ type: 'text', text:
|
||||
'Use the todo_write tool to record a plan of exactly two steps: first '
|
||||
+ '"inspect the failing test" (in_progress), then "apply the fix" (pending). '
|
||||
+ 'Send both in one todo_write call, then reply with the single word DONE.' }])
|
||||
|
||||
@@ -26,6 +26,7 @@
|
||||
"@deepseek-ai/dsh-jsonrpc": "workspace:*",
|
||||
"@deepseek-ai/dsh-llm": "workspace:*",
|
||||
"@deepseek-ai/dsh-llm-deepseek": "workspace:*",
|
||||
"@deepseek-ai/dsh-llm-pi-ai": "workspace:*",
|
||||
"@deepseek-ai/dsh-llm-replay": "workspace:*",
|
||||
"@deepseek-ai/dsh-lsp": "workspace:*",
|
||||
"@deepseek-ai/dsh-lsp-local": "workspace:*",
|
||||
|
||||
@@ -341,7 +341,7 @@ async function runScenario(scenario: Scenario): Promise<ScenarioResult> {
|
||||
}
|
||||
expect(exit.seq).toBeLessThan(afterExit.seq)
|
||||
expect(afterExit.data.header.system).not.toContain('Snapshot plan mode instructions.')
|
||||
expect(events.filter(event => event.type === 'context/message').map(event => event.data.content))
|
||||
expect(events.filter(event => event.type === 'user/message' && event.data.source.kind === 'plugin').map(event => (event.data as { content: unknown }).content))
|
||||
.toContainEqual([{ type: 'text', text: 'The user switched this session back to the default mode.' }])
|
||||
}
|
||||
expect(events.filter(event => event.type === 'tool/result').every(event => !event.data.isError)).toBe(true)
|
||||
|
||||
Reference in New Issue
Block a user