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

Merge PR #415 into Ralph tool stack

Browse Source
This commit is contained in:
Tianyi Cui
2026-07-20 18:10:21 +08:00
parent 2f13acd2b9 283c78eec8
commit 94a6a95c8e
95 changed files with 1082 additions and 1195 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
examples/acp-agent/tests/goal-snapshots/goal-session/input.json Normal file
View File

@@ -0,0 +1,12 @@
{
"steps": [
{ "op": "initialize" },
{ "op": "newSession" },
{
"op": "promptAndWaitForAgentMessage",
"text": "Create a durable two-round goal for the ACP snapshot, inspect it, then report readiness.",
"waitForText": "partial"
},
{ "op": "cancel" }
]
}

43
examples/acp-agent/tests/goal-snapshots/goal-session/replay.override.json Normal file
View File

@@ -0,0 +1,43 @@
[
{
"kind": "chunks",
"chunks": [
{ "type": "block-start", "index": 0, "blockType": "tool-call" },
{ "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": "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": "usage", "usage": { "inputTokens": 20, "outputTokens": 8 } },
{ "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_goal_get", "name": "get_goal", "argumentsDelta": "{}" },
{ "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_goal_get", "name": "get_goal", "arguments": "{}" } },
{ "type": "usage", "usage": { "inputTokens": 30, "outputTokens": 4 } },
{ "type": "finish", "reason": { "kind": "tool-calls" } }
]
},
{
"kind": "chunks",
"chunks": [
{ "type": "block-start", "index": 0, "blockType": "text" },
{ "type": "text-delta", "index": 0, "text": "GOAL READY" },
{ "type": "block-end", "index": 0, "block": { "type": "text", "text": "GOAL READY" } },
{ "type": "usage", "usage": { "inputTokens": 35, "outputTokens": 2 } },
{ "type": "finish", "reason": { "kind": "stop" } }
]
},
{
"kind": "chunks",
"chunks": [
{ "type": "block-start", "index": 0, "blockType": "text" },
{ "type": "text-delta", "index": 0, "text": "GOAL ROUND ONE" },
{ "type": "block-end", "index": 0, "block": { "type": "text", "text": "GOAL ROUND ONE" } },
{ "type": "usage", "usage": { "inputTokens": 40, "outputTokens": 3 } },
{ "type": "finish", "reason": { "kind": "stop" } }
]
},
{ "kind": "hang" }
]

53
examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl Normal file
View File

@@ -0,0 +1,53 @@
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}"}
{"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"}},"surfaceOp":"append"}
{"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":5,"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":6,"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":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":20,"outputTokens":8}}}}
{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":9,"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":[4,5,6,7,8],"surfaceOp":"append"}
{"type":"tool/call","seq":10,"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":11,"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":[10],"surfaceOp":"append"}
{"type":"context/message","seq":12,"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},"envelope":"raw","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":13,"time":0,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":14,"time":0,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":16,"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":17,"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":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":30,"outputTokens":4}}}}
{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":20,"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":[15,16,17,18,19],"surfaceOp":"append"}
{"type":"tool/call","seq":21,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_get","name":"get_goal","arguments":"{}"}}
{"type":"tool/result","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"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},"sourceEventSeqs":[21],"surfaceOp":"append"}
{"type":"step/end","seq":23,"time":0,"data":{"turn":1,"step":2}}
{"type":"step/start","seq":24,"time":0,"data":{"turn":1,"step":3}}
{"type":"assistant/chunk","seq":25,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":26,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":0,"text":"GOAL READY"}}}
{"type":"assistant/chunk","seq":27,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GOAL READY"}}}}
{"type":"assistant/chunk","seq":28,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":35,"outputTokens":2}}}}
{"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":30,"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":[25,26,27,28,29],"surfaceOp":"append"}
{"type":"step/end","seq":31,"time":0,"data":{"turn":1,"step":3}}
{"type":"turn/end","seq":32,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}
{"type":"turn/start","seq":33,"time":0,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":1}}}}
{"type":"user/message","seq":34,"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}},"surfaceOp":"append"}
{"type":"step/start","seq":35,"time":0,"data":{"turn":2,"step":1}}
{"type":"assistant/chunk","seq":36,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":37,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":0,"text":"GOAL ROUND ONE"}}}
{"type":"assistant/chunk","seq":38,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GOAL ROUND ONE"}}}}
{"type":"assistant/chunk","seq":39,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":40,"outputTokens":3}}}}
{"type":"assistant/chunk","seq":40,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":41,"time":0,"data":{"turn":2,"step":1,"content":[{"type":"text","text":"GOAL ROUND ONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":40,"outputTokens":3}},"sourceEventSeqs":[36,37,38,39,40],"surfaceOp":"append"}
{"type":"step/end","seq":42,"time":0,"data":{"turn":2,"step":1}}
{"type":"turn/end","seq":43,"time":0,"data":{"turn":2,"reason":{"kind":"completed"}}}
{"type":"turn/start","seq":44,"time":0,"data":{"turn":3,"trigger":{"kind":"message","source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":2}}}}
{"type":"user/message","seq":45,"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}},"surfaceOp":"append"}
{"type":"step/start","seq":46,"time":0,"data":{"turn":3,"step":1}}
{"type":"assistant/chunk","seq":47,"time":0,"data":{"turn":3,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":48,"time":0,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":0,"text":"partial"}}}
{"type":"context/message","seq":49,"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},"envelope":"raw","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":50,"time":0,"data":{"turn":3,"step":1}}
{"type":"turn/end","seq":51,"time":0,"data":{"turn":3,"reason":{"kind":"aborted","reason":"session/cancel"}}}

1
examples/acp-agent/tests/goal-snapshots/goal-session/session.jsonl Normal file
View File

@@ -0,0 +1 @@
{"type":"session","version":0,"id":"goal-session-placeholder","createdAt":0,"cwd":"/tmp/goal-session-placeholder"}

11
examples/acp-agent/tests/goal-snapshots/goal-session/stdout.expected.jsonl Normal file
View File

@@ -0,0 +1,11 @@
{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[<objective>|clear|edit <objective>|pause|resume]"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_goal_create","title":"Create goal","kind":"other","status":"in_progress","rawInput":"Finish the ACP goal-session snapshot proof"}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_goal_create","status":"completed","content":[{"type":"content","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\"}"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_goal_get","title":"Read current goal","kind":"read","status":"in_progress"}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_goal_get","status":"completed","content":[{"type":"content","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\"}"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"GOAL READY"}}}}
{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"GOAL ROUND ONE"}}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"partial"}}}}

114
examples/acp-agent/tests/goal.snapshot.ts Normal file
View File

@@ -0,0 +1,114 @@
import { readFile, writeFile } from 'node:fs/promises'
import { dirname, join } from 'node:path'
import { fileURLToPath } from 'node:url'
import {
normalizeSessionLog,
normalizeStdout,
runScenario,
scrubRequestHeaders,
type AgentUnderTest,
type InputScript,
type NormalizeContext,
} from '@deepseek-ai/dsh-acp-snapshot'
import { foldGoal } from '@deepseek-ai/dsh-goal'
import type { SessionEvent } from '@deepseek-ai/dsh-session'
import { describe, expect, it } from 'vitest'
// This lifecycle proof has goal-specific timestamp normalization and semantic
// assertions, so it owns a separate snapshot root from the generic ACP suite.
const scenarioDir = join(dirname(fileURLToPath(import.meta.url)), 'goal-snapshots/goal-session')
const fixtureFile = join(scenarioDir, 'session.jsonl')
const overrideFile = join(scenarioDir, 'replay.override.json')
const stdoutExpected = join(scenarioDir, 'stdout.expected.jsonl')
const sessionExpected = join(scenarioDir, 'session.expected.jsonl')
const refreshing = process.env.DSH_SNAPSHOT === 'refresh'
const agent: AgentUnderTest = {
binScript: fileURLToPath(new URL('../../../packages/examples/acp-demo/src/bin.ts', import.meta.url)),
configPath: fileURLToPath(new URL('../cordis.yml', import.meta.url)),
tsconfigPath: fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)),
}
interface JsonObject {
[key: string]: unknown
}
/** Parse non-empty records from one JSONL artifact. */
function parseJsonl(content: string): JsonObject[] {
return content.split('\n').filter(line => line.trim().length > 0)
.map(line => JSON.parse(line) as JsonObject)
}
/** Zero durable goal timestamps inside metadata records and rendered XML JSON. */
function normalizeGoalTimestamps(value: unknown): unknown {
if (typeof value === 'string') {
return value.replace(/("(?:createdAt|updatedAt|clearedAt)":)\d+/g, '$10')
}
if (Array.isArray(value)) return value.map(normalizeGoalTimestamps)
if (value !== null && typeof value === 'object') {
return Object.fromEntries(Object.entries(value).map(([key, item]) => [
key,
['createdAt', 'updatedAt', 'clearedAt'].includes(key) && typeof item === 'number'
? 0
: normalizeGoalTimestamps(item),
]))
}
return value
}
/** Normalize one persisted goal log after the shared snapshot scrubbers. */
function normalizeGoalLog(content: string, context: NormalizeContext): string {
return parseJsonl(scrubRequestHeaders(normalizeSessionLog(content, context)))
.map(record => JSON.stringify(normalizeGoalTimestamps(record)))
.join('\n') + '\n'
}
describe('ACP same-session goal snapshot', () => {
it('runs exact automatic rounds in the shipped application and persists cancellation', async () => {
const input = JSON.parse(await readFile(join(scenarioDir, 'input.json'), 'utf8')) as InputScript
const result = await runScenario(input, {
agent,
mode: 'replay',
fixtureFile,
overrideFile,
configPath: agent.configPath,
})
expect(result.stderr).toBe('')
expect(result.sessionLogs).toHaveLength(1)
const log = result.sessionLogs[0]
if (log === undefined) throw new Error('goal snapshot did not persist its ACP session')
const records = parseJsonl(log.content)
const events = records.slice(1) as unknown as SessionEvent[]
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]
: [])
expect(rounds).toEqual([1, 2])
expect(foldGoal(events)).toMatchObject({
goal: {
objective: 'Finish the ACP goal-session snapshot proof',
phase: 'paused',
revision: 2,
maxGoalRounds: 2,
},
roundsStarted: 2,
})
const context: NormalizeContext = {
sessionIds: [result.sessionId, log.id].filter((id): id is string => id !== undefined),
cwd: result.cwd,
}
const stdout = normalizeStdout(result.rawStdout, context)
const session = normalizeGoalLog(log.content, context)
if (refreshing) {
await Promise.all([
writeFile(stdoutExpected, stdout),
writeFile(sessionExpected, session),
])
}
expect(stdout).toBe(await readFile(stdoutExpected, 'utf8'))
expect(session).toBe(await readFile(sessionExpected, 'utf8'))
})
})

8
examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md
View File

@@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor
Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked.
Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).
<!-- dsh-user-approval-policy:never -->
@@ -72,7 +72,7 @@ declare const tools: {
/** Optional positive safe-integer limit on automatic continuation rounds. */
max_goal_rounds?: number;
}): Promise<string>;
/** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal. */
/** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal. */
get_goal(args: Record<string, unknown>): Promise<string>;
/** Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools. */
ralph(args: {
@@ -132,7 +132,7 @@ declare const tools: {
status: "pending" | "in_progress" | "completed";
})[];
}): Promise<string>;
/** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds. */
/** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */
update_goal(args: {
/** Exact id returned by get_goal. */
goal_id: string;
@@ -144,6 +144,8 @@ declare const tools: {
objective?: string;
/** Replacement cap; valid only with action edit. */
max_goal_rounds?: number;
/** Concrete blocking condition; required only with action blocked. */
blocked_reason?: string;
}): Promise<string>;
/** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */
workflow(args: {

8
examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json
View File

@@ -124,7 +124,7 @@
},
{
"name": "get_goal",
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.",
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.",
"parameters": {
"type": "object",
"properties": {}
@@ -324,7 +324,7 @@
},
{
"name": "update_goal",
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.",
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.",
"parameters": {
"type": "object",
"properties": {
@@ -354,6 +354,10 @@
"max_goal_rounds": {
"type": "number",
"description": "Replacement cap; valid only with action edit."
},
"blocked_reason": {
"type": "string",
"description": "Concrete blocking condition; required only with action blocked."
}
},
"required": [

8
examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md
View File

@@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor
Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked.
Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).
<!-- dsh-user-approval-policy:never -->
@@ -55,7 +55,7 @@ declare const tools: {
/** Optional positive safe-integer limit on automatic continuation rounds. */
max_goal_rounds?: number;
}): Promise<string>;
/** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal. */
/** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal. */
get_goal(args: Record<string, unknown>): Promise<string>;
/** Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools. */
ralph(args: {
@@ -115,7 +115,7 @@ declare const tools: {
status: "pending" | "in_progress" | "completed";
})[];
}): Promise<string>;
/** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds. */
/** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */
update_goal(args: {
/** Exact id returned by get_goal. */
goal_id: string;
@@ -127,6 +127,8 @@ declare const tools: {
objective?: string;
/** Replacement cap; valid only with action edit. */
max_goal_rounds?: number;
/** Concrete blocking condition; required only with action blocked. */
blocked_reason?: string;
}): Promise<string>;
/** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */
workflow(args: {

8
examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json
View File

@@ -67,7 +67,7 @@
},
{
"name": "get_goal",
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.",
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.",
"parameters": {
"type": "object",
"properties": {}
@@ -267,7 +267,7 @@
},
{
"name": "update_goal",
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.",
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.",
"parameters": {
"type": "object",
"properties": {
@@ -297,6 +297,10 @@
"max_goal_rounds": {
"type": "number",
"description": "Replacement cap; valid only with action edit."
},
"blocked_reason": {
"type": "string",
"description": "Concrete blocking condition; required only with action blocked."
}
},
"required": [

8
examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md
View File

@@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor
Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked.
Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).
<!-- dsh-user-approval-policy:never -->
@@ -55,7 +55,7 @@ declare const tools: {
/** Optional positive safe-integer limit on automatic continuation rounds. */
max_goal_rounds?: number;
}): Promise<string>;
/** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal. */
/** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal. */
get_goal(args: Record<string, unknown>): Promise<string>;
/** Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools. */
ralph(args: {
@@ -115,7 +115,7 @@ declare const tools: {
status: "pending" | "in_progress" | "completed";
})[];
}): Promise<string>;
/** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds. */
/** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */
update_goal(args: {
/** Exact id returned by get_goal. */
goal_id: string;
@@ -127,6 +127,8 @@ declare const tools: {
objective?: string;
/** Replacement cap; valid only with action edit. */
max_goal_rounds?: number;
/** Concrete blocking condition; required only with action blocked. */
blocked_reason?: string;
}): Promise<string>;
/** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */
workflow(args: {

8
examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md
View File

@@ -15,7 +15,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor
Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked.
Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).
<!-- dsh-user-approval-policy:never -->
@@ -72,7 +72,7 @@ declare const tools: {
/** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */
replace_all?: boolean;
}): Promise<string>;
/** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal. */
/** Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal. */
get_goal(args: Record<string, unknown>): Promise<string>;
/** Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools. */
ralph(args: {
@@ -141,7 +141,7 @@ declare const tools: {
status: "pending" | "in_progress" | "completed";
})[];
}): Promise<string>;
/** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds. */
/** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */
update_goal(args: {
/** Exact id returned by get_goal. */
goal_id: string;
@@ -153,6 +153,8 @@ declare const tools: {
objective?: string;
/** Replacement cap; valid only with action edit. */
max_goal_rounds?: number;
/** Concrete blocking condition; required only with action blocked. */
blocked_reason?: string;
}): Promise<string>;
/** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */
workflow(args: {

4
examples/acp-agent/tests/snapshots/model-switching/system-prompt.expected.md
View File

@@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor
Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked.
Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).
<!-- dsh-user-approval-policy:never -->
@@ -31,7 +31,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor
Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked.
Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).
<!-- dsh-user-approval-policy:never -->

16
examples/acp-agent/tests/snapshots/model-switching/tool-schemas.expected.json
View File

@@ -67,7 +67,7 @@
},
{
"name": "get_goal",
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.",
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.",
"parameters": {
"type": "object",
"properties": {}
@@ -251,7 +251,7 @@
},
{
"name": "update_goal",
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.",
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.",
"parameters": {
"type": "object",
"properties": {
@@ -281,6 +281,10 @@
"max_goal_rounds": {
"type": "number",
"description": "Replacement cap; valid only with action edit."
},
"blocked_reason": {
"type": "string",
"description": "Concrete blocking condition; required only with action blocked."
}
},
"required": [
@@ -431,7 +435,7 @@
},
{
"name": "get_goal",
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.",
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.",
"parameters": {
"type": "object",
"properties": {}
@@ -615,7 +619,7 @@
},
{
"name": "update_goal",
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.",
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.",
"parameters": {
"type": "object",
"properties": {
@@ -645,6 +649,10 @@
"max_goal_rounds": {
"type": "number",
"description": "Replacement cap; valid only with action edit."
},
"blocked_reason": {
"type": "string",
"description": "Concrete blocking condition; required only with action blocked."
}
},
"required": [

4
examples/acp-agent/tests/snapshots/permission-switching/system-prompt.expected.md
View File

@@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor
Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked.
<!-- dsh-user-approval-policy:ask -->
@@ -30,7 +30,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor
Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked.
Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).
<!-- dsh-user-approval-policy:never -->

16
examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.expected.json
View File

@@ -67,7 +67,7 @@
},
{
"name": "get_goal",
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.",
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.",
"parameters": {
"type": "object",
"properties": {}
@@ -251,7 +251,7 @@
},
{
"name": "update_goal",
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.",
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.",
"parameters": {
"type": "object",
"properties": {
@@ -281,6 +281,10 @@
"max_goal_rounds": {
"type": "number",
"description": "Replacement cap; valid only with action edit."
},
"blocked_reason": {
"type": "string",
"description": "Concrete blocking condition; required only with action blocked."
}
},
"required": [
@@ -431,7 +435,7 @@
},
{
"name": "get_goal",
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.",
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.",
"parameters": {
"type": "object",
"properties": {}
@@ -615,7 +619,7 @@
},
{
"name": "update_goal",
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.",
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.",
"parameters": {
"type": "object",
"properties": {
@@ -645,6 +649,10 @@
"max_goal_rounds": {
"type": "number",
"description": "Replacement cap; valid only with action edit."
},
"blocked_reason": {
"type": "string",
"description": "Concrete blocking condition; required only with action blocked."
}
},
"required": [

2
examples/acp-agent/tests/snapshots/skill-load/system-prompt.expected.md
View File

@@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor
Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked.
Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).
<!-- dsh-user-approval-policy:never -->

8
examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json
View File

@@ -67,7 +67,7 @@
},
{
"name": "get_goal",
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.",
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.",
"parameters": {
"type": "object",
"properties": {}
@@ -251,7 +251,7 @@
},
{
"name": "update_goal",
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.",
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.",
"parameters": {
"type": "object",
"properties": {
@@ -281,6 +281,10 @@
"max_goal_rounds": {
"type": "number",
"description": "Replacement cap; valid only with action edit."
},
"blocked_reason": {
"type": "string",
"description": "Concrete blocking condition; required only with action blocked."
}
},
"required": [

2
examples/acp-agent/tests/snapshots/text-turn/system-prompt.expected.md
View File

@@ -9,7 +9,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor
Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked.
Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).
<!-- dsh-user-approval-policy:never -->

8
examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json
View File

@@ -67,7 +67,7 @@
},
{
"name": "get_goal",
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.",
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.",
"parameters": {
"type": "object",
"properties": {}
@@ -251,7 +251,7 @@
},
{
"name": "update_goal",
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.",
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.",
"parameters": {
"type": "object",
"properties": {
@@ -281,6 +281,10 @@
"max_goal_rounds": {
"type": "number",
"description": "Replacement cap; valid only with action edit."
},
"blocked_reason": {
"type": "string",
"description": "Concrete blocking condition; required only with action blocked."
}
},
"required": [

2
examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md
View File

@@ -15,7 +15,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor
Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked.
Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).
<!-- dsh-user-approval-policy:never -->

8
examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json
View File

@@ -97,7 +97,7 @@
},
{
"name": "get_goal",
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.",
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.",
"parameters": {
"type": "object",
"properties": {}
@@ -305,7 +305,7 @@
},
{
"name": "update_goal",
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.",
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.",
"parameters": {
"type": "object",
"properties": {
@@ -335,6 +335,10 @@
"max_goal_rounds": {
"type": "number",
"description": "Replacement cap; valid only with action edit."
},
"blocked_reason": {
"type": "string",
"description": "Concrete blocking condition; required only with action blocked."
}
},
"required": [

2
examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.expected.md
View File

@@ -15,7 +15,7 @@ Check the [exit code: N] marker on every bash result; investigate failures befor
Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds; difficulty, uncertainty, or useful remaining work is not blocked.
Use goal tools for one long-running completion objective in the current session. create_goal may infer goal intent from a direct human request in any language; do not create a goal for routine single-turn work. Call get_goal before update_goal and copy its exact goal_id and revision. After session resume or fork, an active goal is disarmed: when a human asks to continue or resume in any wording or language, use update_goal action resume to rearm it. Mark complete only when the objective is actually achieved. Mark blocked only after the same blocking condition persists for at least 3 consecutive goal rounds, and report that concrete condition in blocked_reason; difficulty, uncertainty, or useful remaining work is not blocked.
Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).
<!-- dsh-user-approval-policy:never -->

8
examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.expected.json
View File

@@ -97,7 +97,7 @@
},
{
"name": "get_goal",
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, and whether another continuation is armed. Call this before updating a goal.",
"description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.",
"parameters": {
"type": "object",
"properties": {}
@@ -305,7 +305,7 @@
},
{
"name": "update_goal",
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds.",
"description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.",
"parameters": {
"type": "object",
"properties": {
@@ -335,6 +335,10 @@
"max_goal_rounds": {
"type": "number",
"description": "Replacement cap; valid only with action edit."
},
"blocked_reason": {
"type": "string",
"description": "Concrete blocking condition; required only with action blocked."
}
},
"required": [

25
examples/echo-agent/tests/fixtures/goal/goal-session/cordis.yml vendored
View File

@@ -1,25 +0,0 @@
# Test-only composition: one human turn creates a goal, then the driver runs two rounds.
- id: scripted-llm
name: './scripted-llm.ts'
- id: bash
name: '@deepseek-ai/dsh-bash-local'
- id: goal
name: '@deepseek-ai/dsh-goal'
- id: tool-goal
name: '@deepseek-ai/dsh-tool-goal'
- id: goal-session
name: '@deepseek-ai/dsh-goal-session'
- id: stdio-agent
name: '@deepseek-ai/dsh-stdio-demo'
config:
provider: goal-session-script
model: goal-session-script
persona: 'Execute the deterministic same-session goal-round proof.'
welcome: 'goal-session e2e ready.'
persistenceRoot: './.sessions'
workspaceContext: false

104
examples/echo-agent/tests/fixtures/goal/goal-session/scripted-llm.ts vendored
View File

@@ -1,104 +0,0 @@
/** Deterministic model for the same-session goal-round composition proof. */
import type { Context } from 'cordis'
import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm'
import type { GenerateOptions, Message, StreamChunk } from '@deepseek-ai/dsh-llm'
interface GoalState {
readonly id: string
readonly revision: number
}
/** Text and position of the latest human or goal-round prompt. */
function latestPrompt(messages: readonly Message[]): { index: number; text: string } {
for (let index = messages.length - 1; index >= 0; index -= 1) {
const message = messages[index]
if (message?.role !== 'user') continue
const text = message.content
.filter(block => block.type === 'text' && !block.text.startsWith('<goal_state>'))
.map(block => block.type === 'text' ? block.text : '')
.join('\n')
if (text.includes('<goal_round>') || text === 'start') return { index, text }
}
return { index: -1, text: '' }
}
/** Parse the latest durable goal snapshot retained in request history. */
function latestGoal(messages: readonly Message[]): GoalState | undefined {
for (const message of [...messages].reverse()) {
for (const block of [...message.content].reverse()) {
if (block.type !== 'text' || !block.text.startsWith('<goal_state>')) continue
const json = block.text.slice('<goal_state>'.length, -'</goal_state>'.length)
const value = JSON.parse(json) as { goal?: GoalState }
if (value.goal !== undefined) return value.goal
}
}
return undefined
}
/** Tool names already recorded after the prompt that owns this physical turn. */
function callsAfter(messages: readonly Message[], index: number): string[] {
return messages.slice(index + 1).flatMap(message => message.content)
.filter(block => block.type === 'tool-call')
.map(block => block.type === 'tool-call' ? block.name : '')
}
/** Emit one deterministic tool call, optionally with visible progress text. */
async function* toolCall(name: string, args: object, text?: string): AsyncIterable<StreamChunk> {
let index = 0
if (text !== undefined) {
yield { type: 'block-start', index, blockType: 'text' }
yield { type: 'text-delta', index, text }
yield { type: 'block-end', index, block: { type: 'text', text } }
index += 1
}
const id = CallId(`call-${name}`)
const raw = JSON.stringify(args)
yield { type: 'block-start', index, blockType: 'tool-call' }
yield { type: 'tool-call-delta', index, id, name, argumentsDelta: raw }
yield { type: 'block-end', index, block: { type: 'tool-call', id, name, arguments: raw } }
yield { type: 'finish', reason: { kind: 'tool-calls' } }
}
/** Emit one terminal text response. */
async function* textReply(text: string): AsyncIterable<StreamChunk> {
yield { type: 'block-start', index: 0, blockType: 'text' }
yield { type: 'text-delta', index: 0, text }
yield { type: 'block-end', index: 0, block: { type: 'text', text } }
yield { type: 'finish', reason: { kind: 'stop' } }
}
class GoalSessionScriptAdapter extends LlmAdapter {
override stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
const prompt = latestPrompt(options.messages)
const calls = callsAfter(options.messages, prompt.index)
if (prompt.text === 'start' && !calls.includes('create_goal')) {
return toolCall('create_goal', {
objective: 'Complete two deterministic same-session rounds',
max_goal_rounds: 2,
})
}
if (prompt.text === 'start') return textReply('GOAL CREATED')
if (prompt.text.includes('Round: 1/2')) return textReply('ROUND ONE')
if (prompt.text.includes('Round: 2/2') && !calls.includes('get_goal')) {
return toolCall('get_goal', {})
}
if (prompt.text.includes('Round: 2/2') && !calls.includes('update_goal')) {
const goal = latestGoal(options.messages)
if (goal === undefined) throw new Error('scripted goal state missing')
return toolCall('update_goal', {
goal_id: goal.id,
revision: goal.revision,
action: 'complete',
}, 'ROUND TWO COMPLETE')
}
return textReply('UNEXPECTED GOAL-SESSION REQUEST')
}
}
export const name = 'goal-session-scripted-llm'
export const inject = ['llm']
export function apply(ctx: Context): void {
ctx.llm.registerAdapter(['goal-session-script'], new GoalSessionScriptAdapter())
}

26
examples/echo-agent/tests/fixtures/goal/tool-goal/cordis.yml vendored
View File

@@ -1,26 +0,0 @@
# Test-only composition: drive all three goal tools through a real root agent.
- id: scripted-llm
name: './scripted-llm.ts'
- id: bash
name: '@deepseek-ai/dsh-bash-local'
- id: goal
name: '@deepseek-ai/dsh-goal'
config:
defaultMaxGoalRounds: 11
- id: tool-goal
name: '@deepseek-ai/dsh-tool-goal'
config:
blockedAfterConsecutiveRounds: 3
- id: stdio-agent
name: '@deepseek-ai/dsh-stdio-demo'
config:
provider: goal-script
model: goal-script
persona: 'Execute the deterministic goal-tool composition test.'
welcome: 'goal-tools e2e ready.'
persistenceRoot: './.sessions'
workspaceContext: false

88
examples/echo-agent/tests/fixtures/goal/tool-goal/scripted-llm.ts vendored
View File

@@ -1,88 +0,0 @@
/** Deterministic adapter that creates, reads, pauses, then acknowledges one goal. */
import type { Context } from 'cordis'
import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm'
import type { GenerateOptions, Message, StreamChunk } from '@deepseek-ai/dsh-llm'
interface GoalState {
readonly id: string
readonly revision: number
}
/** Text from the latest ordinary user message, excluding raw goal-state context. */
function latestPrompt(messages: readonly Message[]): { index: number; text: string } {
for (let index = messages.length - 1; index >= 0; index -= 1) {
const message = messages[index]
if (message?.role !== 'user') continue
const text = message.content
.filter(block => block.type === 'text' && !block.text.startsWith('<goal_state>'))
.map(block => block.type === 'text' ? block.text : '')
.join('\n')
if (text.length > 0) return { index, text }
}
return { index: -1, text: '' }
}
/** Parse the latest domain snapshot rendered into history. */
function latestGoal(messages: readonly Message[]): GoalState | undefined {
for (const message of [...messages].reverse()) {
for (const block of [...message.content].reverse()) {
if (block.type !== 'text' || !block.text.startsWith('<goal_state>')) continue
const json = block.text.slice('<goal_state>'.length, -'</goal_state>'.length)
const value = JSON.parse(json) as { goal?: GoalState }
if (value.goal !== undefined) return value.goal
}
}
return undefined
}
/** Names of tool calls recorded after the latest ordinary prompt. */
function callsAfter(messages: readonly Message[], index: number): string[] {
return messages.slice(index + 1).flatMap(message => message.content)
.filter(block => block.type === 'tool-call')
.map(block => block.type === 'tool-call' ? block.name : '')
}
/** Emit one tool-call response. */
async function* toolCall(name: string, args: object): AsyncIterable<StreamChunk> {
const id = CallId(`call-${name}`)
const raw = JSON.stringify(args)
yield { type: 'block-start', index: 0, blockType: 'tool-call' }
yield { type: 'tool-call-delta', index: 0, id, name, argumentsDelta: raw }
yield { type: 'block-end', index: 0, block: { type: 'tool-call', id, name, arguments: raw } }
yield { type: 'finish', reason: { kind: 'tool-calls' } }
}
/** Emit one terminal text response. */
async function* textReply(text: string): AsyncIterable<StreamChunk> {
yield { type: 'block-start', index: 0, blockType: 'text' }
yield { type: 'text-delta', index: 0, text }
yield { type: 'block-end', index: 0, block: { type: 'text', text } }
yield { type: 'finish', reason: { kind: 'stop' } }
}
class GoalScriptAdapter extends LlmAdapter {
override stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
const prompt = latestPrompt(options.messages)
const calls = callsAfter(options.messages, prompt.index)
if (prompt.text === 'start' && !calls.includes('create_goal')) {
return toolCall('create_goal', { objective: 'Finish the composed goal-tool proof', max_goal_rounds: 7 })
}
if (prompt.text === 'start' && !calls.includes('get_goal')) return toolCall('get_goal', {})
if (prompt.text === 'start') return textReply('GOAL CREATED')
if (prompt.text === 'pause' && !calls.includes('update_goal')) {
const goal = latestGoal(options.messages)
if (goal === undefined) throw new Error('scripted goal state missing')
return toolCall('update_goal', { goal_id: goal.id, revision: goal.revision, action: 'pause' })
}
if (prompt.text === 'pause') return textReply('GOAL PAUSED')
return textReply('UNEXPECTED PROMPT')
}
}
export const name = 'goal-tool-scripted-llm'
export const inject = ['llm']
export function apply(ctx: Context): void {
ctx.llm.registerAdapter(['goal-script'], new GoalScriptAdapter())
}

12
examples/headless-agent/goal.cordis.snapshot.yml Normal file
View File

@@ -0,0 +1,12 @@
# Replay counterpart to goal.cordis.yml; only the live model is replaced.
- id: base
name: '@cordisjs/plugin-include'
config:
path: ./goal.cordis.yml
patches:
- id: llm-deepseek
name: '@deepseek-ai/dsh-llm-deepseek'
disabled: true
- insert:
- id: llm-replay
name: '@deepseek-ai/dsh-llm-replay'

11
examples/headless-agent/goal.cordis.yml Normal file
View File

@@ -0,0 +1,11 @@
# Add the persisted goal domain and its model-facing tools to the real one-shot app.
- id: base
name: '@cordisjs/plugin-include'
config:
path: ./cordis.yml
patches:
- insert:
- id: goal
name: '@deepseek-ai/dsh-goal'
- id: tool-goal
name: '@deepseek-ai/dsh-tool-goal'

109
examples/headless-agent/tests/headless.snapshot.ts
View File

@@ -11,10 +11,12 @@ import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-l
import { describe, expect, it } from 'vitest'
const snapshotsDir = join(dirname(fileURLToPath(import.meta.url)), 'snapshots')
const scenarioDir = join(snapshotsDir, 'advanced-toolchain')
const sessionFixture = join(scenarioDir, 'session.jsonl')
const streamExpected = join(scenarioDir, 'stream-json.expected.jsonl')
const configPath = fileURLToPath(new URL('../advanced.cordis.snapshot.yml', import.meta.url))
const advancedScenarioDir = join(snapshotsDir, 'advanced-toolchain')
const advancedSessionFixture = join(advancedScenarioDir, 'session.jsonl')
const advancedStreamExpected = join(advancedScenarioDir, 'stream-json.expected.jsonl')
const advancedConfigPath = fileURLToPath(new URL('../advanced.cordis.snapshot.yml', import.meta.url))
const goalScenarioDir = join(snapshotsDir, 'goal-tools')
const goalConfigPath = fileURLToPath(new URL('../goal.cordis.snapshot.yml', import.meta.url))
const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url))
const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
const refreshing = process.env.DSH_SNAPSHOT === 'refresh'
@@ -70,12 +72,36 @@ function normalizeHeadlessStream(rawStdout: string, cwd: string): string {
return normalizeStdout(`${normalizedRecords.map(record => JSON.stringify(record)).join('\n')}\n`, context)
}
async function advancedPrompt(): Promise<string> {
const input = JSON.parse(await readFile(join(scenarioDir, 'input.json'), 'utf8')) as {
/** Zero durable goal timestamps inside both metadata records and rendered XML JSON. */
function normalizeGoalTimestamps(value: unknown): unknown {
if (typeof value === 'string') {
return value.replace(/("(?:createdAt|updatedAt|clearedAt)":)\d+/g, '$10')
}
if (Array.isArray(value)) return value.map(normalizeGoalTimestamps)
if (value !== null && typeof value === 'object') {
return Object.fromEntries(Object.entries(value).map(([key, item]) => [
key,
['createdAt', 'updatedAt', 'clearedAt'].includes(key) && typeof item === 'number'
? 0
: normalizeGoalTimestamps(item),
]))
}
return value
}
/** Normalize the stream's durable goal timestamps after the shared scrubbers. */
function normalizeGoalStream(rawStdout: string, cwd: string): string {
return parseJsonl(normalizeHeadlessStream(rawStdout, cwd))
.map(record => JSON.stringify(normalizeGoalTimestamps(record)))
.join('\n') + '\n'
}
async function scenarioPrompt(dir: string, label: string): Promise<string> {
const input = JSON.parse(await readFile(join(dir, 'input.json'), 'utf8')) as {
steps?: { op?: unknown; text?: unknown }[]
}
const prompt = input.steps?.find(step => step.op === 'prompt')?.text
if (typeof prompt !== 'string') throw new Error('advanced-toolchain input has no prompt step')
if (typeof prompt !== 'string') throw new Error(`${label} input has no prompt step`)
return prompt
}
@@ -90,24 +116,27 @@ async function persistedLogs(cwd: string): Promise<PersistedLog[]> {
describe('headless stream-json snapshots', () => {
it('replays the advanced toolchain through the one-shot app', async () => {
const prompt = await advancedPrompt()
const prompt = await scenarioPrompt(advancedScenarioDir, 'advanced-toolchain')
const expectedSessions = await Promise.all([
sessionFixture,
join(scenarioDir, 'session.1.jsonl'),
join(scenarioDir, 'session.2.jsonl'),
advancedSessionFixture,
join(advancedScenarioDir, 'session.1.jsonl'),
join(advancedScenarioDir, 'session.2.jsonl'),
].map(file => readFile(file, 'utf8')))
let runCwd = ''
const result = await runLoaderSmoke({
label: 'advanced headless stream-json snapshot',
tempDirPrefix: 'headless-snapshot-advanced-',
binScript,
configPath,
binArgs: ['--config', configPath, '--output-format', 'stream-json', prompt],
configPath: advancedConfigPath,
binArgs: ['--config', advancedConfigPath, '--output-format', 'stream-json', prompt],
tsconfigPath,
env: {
DSH_SNAPSHOT: 'replay',
DSH_SNAPSHOT_FILE: sessionFixture,
DSH_SNAPSHOT_CHILD_FILES: [join(scenarioDir, 'session.1.jsonl'), join(scenarioDir, 'session.2.jsonl')].join(delimiter),
DSH_SNAPSHOT_FILE: advancedSessionFixture,
DSH_SNAPSHOT_CHILD_FILES: [
join(advancedScenarioDir, 'session.1.jsonl'),
join(advancedScenarioDir, 'session.2.jsonl'),
].join(delimiter),
NODE_OPTIONS: [process.env.NODE_OPTIONS, '--disable-warning=ExperimentalWarning'].filter(Boolean).join(' '),
},
prepare: (cwd) => { runCwd = cwd },
@@ -134,6 +163,56 @@ describe('headless stream-json snapshots', () => {
expect(result.stderr).toBe('')
const normalized = normalizeHeadlessStream(result.stdout, runCwd)
if (refreshing) await writeFile(advancedStreamExpected, normalized)
expect(normalized).toBe(await readFile(advancedStreamExpected, 'utf8'))
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
it('replays persisted goal tools through the one-shot app', async () => {
const prompt = await scenarioPrompt(goalScenarioDir, 'goal-tools')
const streamExpected = join(goalScenarioDir, 'stream-json.expected.jsonl')
let runCwd = ''
const result = await runLoaderSmoke({
label: 'goal tools headless stream-json snapshot',
tempDirPrefix: 'headless-snapshot-goal-tools-',
binScript,
configPath: goalConfigPath,
binArgs: ['--config', goalConfigPath, '--output-format', 'stream-json', prompt],
tsconfigPath,
env: {
DSH_SNAPSHOT: 'replay',
DSH_SNAPSHOT_FILE: join(goalScenarioDir, 'session.jsonl'),
DSH_SNAPSHOT_OVERRIDE: join(goalScenarioDir, 'replay.override.json'),
NODE_OPTIONS: [process.env.NODE_OPTIONS, '--disable-warning=ExperimentalWarning'].filter(Boolean).join(' '),
},
prepare: (cwd) => { runCwd = cwd },
inspect: async (cwd) => {
const logs = await persistedLogs(cwd)
expect(logs).toHaveLength(1)
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'])
const goalChanges = records.filter((record) => {
if (record.type !== 'context/message') return false
const data = record.data as JsonObject | undefined
const meta = data?.meta as JsonObject | undefined
return meta?.kind === 'goal/change'
})
expect(goalChanges).toHaveLength(1)
const data = goalChanges[0]?.data as JsonObject | undefined
const meta = data?.meta as JsonObject | undefined
const goal = meta?.goal as JsonObject | undefined
expect(meta?.operation).toBe('create')
expect(goal).toMatchObject({
objective: 'Finish the headless goal-tool snapshot proof',
phase: 'active',
maxGoalRounds: 7,
})
},
})
expect(result.stderr).toBe('')
const normalized = normalizeGoalStream(result.stdout, runCwd)
if (refreshing) await writeFile(streamExpected, normalized)
expect(normalized).toBe(await readFile(streamExpected, 'utf8'))
}, LOADER_SMOKE_TEST_TIMEOUT_MS)

8
examples/headless-agent/tests/snapshots/goal-tools/input.json Normal file
View File

@@ -0,0 +1,8 @@
{
"steps": [
{
"op": "prompt",
"text": "Create a durable goal to finish the snapshot proof, then inspect it."
}
]
}

32
examples/headless-agent/tests/snapshots/goal-tools/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_goal_create", "name": "create_goal", "argumentsDelta": "{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}" },
{ "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": "usage", "usage": { "inputTokens": 20, "outputTokens": 8 } },
{ "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_goal_get", "name": "get_goal", "argumentsDelta": "{}" },
{ "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_goal_get", "name": "get_goal", "arguments": "{}" } },
{ "type": "usage", "usage": { "inputTokens": 30, "outputTokens": 4 } },
{ "type": "finish", "reason": { "kind": "tool-calls" } }
]
},
{
"kind": "chunks",
"chunks": [
{ "type": "block-start", "index": 0, "blockType": "text" },
{ "type": "text-delta", "index": 0, "text": "GOAL READY" },
{ "type": "block-end", "index": 0, "block": { "type": "text", "text": "GOAL READY" } },
{ "type": "usage", "usage": { "inputTokens": 35, "outputTokens": 2 } },
{ "type": "finish", "reason": { "kind": "stop" } }
]
}
]

34
examples/headless-agent/tests/snapshots/goal-tools/stream-json.expected.jsonl Normal file
View File

@@ -0,0 +1,34 @@
{"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":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":3,"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":4,"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":5,"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":6,"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":7,"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":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":9,"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":[4,5,6,7,8],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":10,"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":11,"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":[10],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"context/message","seq":12,"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},"envelope":"raw","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":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_get","name":"get_goal","argumentsDelta":"{}"}}}}
{"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_get","name":"get_goal","arguments":"{}"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":18,"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":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_get","name":"get_goal","arguments":"{}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":30,"outputTokens":4}},"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_get","name":"get_goal","arguments":"{}"}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":22,"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":[21],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":23,"time":0,"data":{"turn":1,"step":2}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":24,"time":0,"data":{"turn":1,"step":3}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":25,"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":26,"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":27,"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":28,"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":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":30,"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":[25,26,27,28,29],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":31,"time":0,"data":{"turn":1,"step":3}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":32,"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}}