Merge remote-tracking branch 'origin/master' into codex/session-title
# Conflicts: # docs/architecture.md # docs/config-catalog.md # docs/event-producer-consumer.md # docs/module-graph.md # examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/bash-spill/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/both-mode-turn/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/cancel-tool-calls/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/cancel/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/code-mode-turn/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/code-mode-workspace-context/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/error-finish/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-edit/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-read-window/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-read/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-write/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/model-switching/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/multi-turn/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/skill-load/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/subagent-fork/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/subagent-mixed/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/subagent-multi/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/subagent-spawn/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/text-turn/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/todo-plan/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/tool-call-turn/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/workflow-run/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/workspace-context/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/workspace-edit/stdout.expected.jsonl # examples/headless-agent/tests/headless.snapshot.ts # packages/examples/README.md # packages/examples/agent-spine-demo/README.md # packages/examples/agent-spine-demo/package.json # packages/ui/README.md # packages/ui/acp/README.md
This commit is contained in:
Tianyi Cui
24
examples/headless-agent/tests/fixtures/goal-domain/cordis.yml
vendored
Normal file
24
examples/headless-agent/tests/fixtures/goal-domain/cordis.yml
vendored
Normal file
@@ -0,0 +1,24 @@
|
||||
# Test-only composition: create one goal through a Loader-mounted step consumer.
|
||||
- id: cli-mock-llm
|
||||
name: '../cli-mock-llm.ts'
|
||||
|
||||
- id: bash
|
||||
name: '@deepseek-ai/dsh-bash-local'
|
||||
|
||||
- id: goal
|
||||
name: '@deepseek-ai/dsh-goal'
|
||||
config:
|
||||
defaultMaxGoalRounds: 11
|
||||
|
||||
- id: seed-goal
|
||||
name: './seed-goal.ts'
|
||||
|
||||
- id: cli-agent
|
||||
name: '@deepseek-ai/dsh-cli-demo'
|
||||
config:
|
||||
provider: cli-mock
|
||||
model: cli-mock
|
||||
persona: 'Test the persisted goal domain.'
|
||||
persistenceRoot: './.sessions'
|
||||
persistenceCompression: none
|
||||
workspaceContext: false
|
||||
17
examples/headless-agent/tests/fixtures/goal-domain/seed-goal.ts
vendored
Normal file
17
examples/headless-agent/tests/fixtures/goal-domain/seed-goal.ts
vendored
Normal file
@@ -0,0 +1,17 @@
|
||||
/** Test-only Loader plugin that creates a goal at the first real step edge. */
|
||||
|
||||
import type { Context } from 'cordis'
|
||||
import type {} from '@deepseek-ai/dsh-goal'
|
||||
|
||||
export const name = 'seed-goal'
|
||||
export const inject = ['goals']
|
||||
|
||||
export function apply(ctx: Context): void {
|
||||
ctx.on('agent/pre-step', (agent) => {
|
||||
if (ctx.goals.get(agent) !== undefined) return
|
||||
ctx.goals.create(agent, {
|
||||
objective: 'Prove the composed goal survives in the session log',
|
||||
maxGoalRounds: 7,
|
||||
})
|
||||
})
|
||||
}
|
||||
@@ -14,10 +14,14 @@ 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 ralphScenarioDir = join(snapshotsDir, 'ralph-loop')
|
||||
const ralphConfigPath = fileURLToPath(new URL('../ralph.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'
|
||||
@@ -73,12 +77,36 @@ 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
|
||||
}
|
||||
|
||||
@@ -93,11 +121,11 @@ 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 fixtureFiles = [
|
||||
sessionFixture,
|
||||
join(scenarioDir, 'session.1.jsonl'),
|
||||
join(scenarioDir, 'session.2.jsonl'),
|
||||
advancedSessionFixture,
|
||||
join(advancedScenarioDir, 'session.1.jsonl'),
|
||||
join(advancedScenarioDir, 'session.2.jsonl'),
|
||||
]
|
||||
let expectedSessions = await Promise.all(fixtureFiles.map(file => readFile(file, 'utf8')))
|
||||
let runCwd = ''
|
||||
@@ -105,13 +133,16 @@ describe('headless stream-json snapshots', () => {
|
||||
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 },
|
||||
@@ -157,6 +188,131 @@ 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)
|
||||
|
||||
it('replays two fresh Ralph rounds through the one-shot app', async () => {
|
||||
const prompt = await scenarioPrompt(ralphScenarioDir, 'ralph-loop')
|
||||
const streamExpected = join(ralphScenarioDir, 'stream-json.expected.jsonl')
|
||||
let runCwd = ''
|
||||
const result = await runLoaderSmoke({
|
||||
label: 'Ralph loop headless stream-json snapshot',
|
||||
tempDirPrefix: 'headless-snapshot-ralph-loop-',
|
||||
binScript,
|
||||
configPath: ralphConfigPath,
|
||||
binArgs: ['--config', ralphConfigPath, '--output-format', 'stream-json', prompt],
|
||||
tsconfigPath,
|
||||
env: {
|
||||
DSH_SNAPSHOT: 'replay',
|
||||
DSH_SNAPSHOT_FILE: join(ralphScenarioDir, 'session.jsonl'),
|
||||
DSH_SNAPSHOT_OVERRIDE: join(ralphScenarioDir, 'replay.override.json'),
|
||||
DSH_SNAPSHOT_CHILD_FILES: [
|
||||
join(ralphScenarioDir, 'session.1.jsonl'),
|
||||
join(ralphScenarioDir, 'session.2.jsonl'),
|
||||
].join(delimiter),
|
||||
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(3)
|
||||
const parent = logs.find(log => typeof log.header.parentSession !== 'string')
|
||||
if (parent === undefined) throw new Error('Ralph snapshot did not persist its parent session')
|
||||
const parentId = parent.header.id
|
||||
expect(typeof parentId).toBe('string')
|
||||
const children = logs.filter(log => typeof log.header.parentSession === 'string')
|
||||
.sort((left, right) => Number(left.header.createdAt) - Number(right.header.createdAt))
|
||||
expect(children).toHaveLength(2)
|
||||
expect(children.map(child => child.header.parentSession)).toEqual([parentId, parentId])
|
||||
expect(children.map(child => child.header.cwd)).toEqual([parent.header.cwd, parent.header.cwd])
|
||||
expect(parent.header.delegationDepth).toBe(0)
|
||||
expect(children.map(child => child.header.delegationDepth)).toEqual([1, 1])
|
||||
expect(children.map(child => child.header.seedLength)).toEqual([undefined, undefined])
|
||||
expect(new Set(children.map(child => child.header.id)).size).toBe(2)
|
||||
|
||||
const parentRecords = parseJsonl(parent.content)
|
||||
const parentCalls = parentRecords.filter(record => record.type === 'tool/call')
|
||||
expect(parentCalls.map(record => (record.data as JsonObject | undefined)?.name)).toEqual(['ralph'])
|
||||
const parentResult = parentRecords.find(record => record.type === 'tool/result')
|
||||
const parentResultData = parentResult?.data as JsonObject | undefined
|
||||
expect(parentResultData?.isError).toBe(false)
|
||||
expect(JSON.stringify(parentResultData?.content)).toContain('reported completion after 2 rounds')
|
||||
|
||||
const childRecords = children.map(child => parseJsonl(child.content))
|
||||
const childPrompts = childRecords.map((records) => {
|
||||
const message = records.find(record => record.type === 'user/message')
|
||||
return JSON.stringify((message?.data as JsonObject | undefined)?.content)
|
||||
})
|
||||
expect(childPrompts[0]).toContain('Ralph round: 1 of 2.')
|
||||
expect(childPrompts[0]).toContain('(none — this is the first round)')
|
||||
expect(childPrompts[0]).not.toContain('ROUND_ONE_HANDOFF')
|
||||
expect(childPrompts[1]).toContain('Ralph round: 2 of 2.')
|
||||
expect(childPrompts[1]).toContain('ROUND_ONE_HANDOFF')
|
||||
for (const childPrompt of childPrompts) {
|
||||
expect(childPrompt).toContain('Prove two fresh Ralph rounds through the shipped headless app.')
|
||||
expect(childPrompt).not.toContain('Run a two-round fresh-agent Ralph loop')
|
||||
}
|
||||
for (const records of childRecords) {
|
||||
const calls = records.filter(record => record.type === 'tool/call')
|
||||
expect(calls.map(record => (record.data as JsonObject | undefined)?.name))
|
||||
.toEqual(['structured_output'])
|
||||
}
|
||||
},
|
||||
})
|
||||
|
||||
expect(result.stderr).toBe('')
|
||||
const normalized = normalizeHeadlessStream(result.stdout, runCwd)
|
||||
if (refreshing) await writeFile(streamExpected, normalized)
|
||||
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"steps": [
|
||||
{
|
||||
"op": "prompt",
|
||||
"text": "Create a durable goal to finish the snapshot proof, then inspect it."
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -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" } }
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -0,0 +1,35 @@
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Create a durable goal to finish the snapshot proof, then inspect it."}],"source":{"kind":"user"}},"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"session/title","seq":2,"time":0,"data":{"title":"Create a durable goal to","messageSeqs":[1],"source":{"kind":"fallback"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":4,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_create","name":"create_goal","argumentsDelta":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":20,"outputTokens":8}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":9,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":10,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":20,"outputTokens":8}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":12,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":7},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"context/message","seq":13,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":7},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":0},"meta":{"kind":"goal/change","version":1,"operation":"create","goal":{"id":"goal-{{sessionId}}","revision":1,"objective":"Finish the headless goal-tool snapshot proof","phase":"active","maxGoalRounds":7},"roundsStarted":0,"createdAt":0,"updatedAt":0}},"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":14,"time":0,"data":{"turn":1,"step":1}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":15,"time":0,"data":{"turn":1,"step":2}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_get","name":"get_goal","argumentsDelta":"{}"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_get","name":"get_goal","arguments":"{}"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":30,"outputTokens":4}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":20,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":21,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"call_goal_get","name":"get_goal","arguments":"{}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":30,"outputTokens":4}},"sourceEventSeqs":[16,17,18,19,20],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_get","name":"get_goal","arguments":"{}"}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":23,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_get","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":7},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[22],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":24,"time":0,"data":{"turn":1,"step":2}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":25,"time":0,"data":{"turn":1,"step":3}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":26,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":27,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":0,"text":"GOAL READY"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":28,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GOAL READY"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":35,"outputTokens":2}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":30,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":31,"time":0,"data":{"turn":1,"step":3,"content":[{"type":"text","text":"GOAL READY"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":35,"outputTokens":2}},"sourceEventSeqs":[26,27,28,29,30],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":32,"time":0,"data":{"turn":1,"step":3}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":33,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}}
|
||||
{"type":"result","success":true,"sessionId":"{{sessionId}}","turn":1,"result":"GOAL READY","reason":{"kind":"completed"},"usage":{"inputTokens":85,"outputTokens":14}}
|
||||
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"steps": [
|
||||
{
|
||||
"op": "prompt",
|
||||
"text": "Run a two-round fresh-agent Ralph loop to prove the shipped headless integration."
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,22 @@
|
||||
[
|
||||
{
|
||||
"kind": "chunks",
|
||||
"chunks": [
|
||||
{ "type": "block-start", "index": 0, "blockType": "tool-call" },
|
||||
{ "type": "tool-call-delta", "index": 0, "id": "call_ralph", "name": "ralph", "argumentsDelta": "{\"objective\":\"Prove two fresh Ralph rounds through the shipped headless app.\",\"maxRounds\":2}" },
|
||||
{ "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_ralph", "name": "ralph", "arguments": "{\"objective\":\"Prove two fresh Ralph rounds through the shipped headless app.\",\"maxRounds\":2}" } },
|
||||
{ "type": "usage", "usage": { "inputTokens": 20, "outputTokens": 8 } },
|
||||
{ "type": "finish", "reason": { "kind": "tool-calls" } }
|
||||
]
|
||||
},
|
||||
{
|
||||
"kind": "chunks",
|
||||
"chunks": [
|
||||
{ "type": "block-start", "index": 0, "blockType": "text" },
|
||||
{ "type": "text-delta", "index": 0, "text": "RALPH SNAPSHOT COMPLETE" },
|
||||
{ "type": "block-end", "index": 0, "block": { "type": "text", "text": "RALPH SNAPSHOT COMPLETE" } },
|
||||
{ "type": "usage", "usage": { "inputTokens": 30, "outputTokens": 4 } },
|
||||
{ "type": "finish", "reason": { "kind": "stop" } }
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -0,0 +1,6 @@
|
||||
{"type":"session","version":0,"id":"42222222-2222-4222-8222-222222222222","createdAt":1783951001000,"cwd":"/tmp/ralph-headless","parentSession":"41111111-1111-4111-8111-111111111111"}
|
||||
{"type":"assistant/chunk","seq":0,"time":1783951001001,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
|
||||
{"type":"assistant/chunk","seq":1,"time":1783951001002,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"round-one-report","name":"structured_output","argumentsDelta":"{\"status\":\"continue\",\"summary\":\"ROUND_ONE_HANDOFF\",\"evidence\":[\"Round one inspected the workspace.\"],\"nextSteps\":[\"Finish the snapshot objective.\"],\"blocker\":\"\"}"}}}
|
||||
{"type":"assistant/chunk","seq":2,"time":1783951001003,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"round-one-report","name":"structured_output","arguments":"{\"status\":\"continue\",\"summary\":\"ROUND_ONE_HANDOFF\",\"evidence\":[\"Round one inspected the workspace.\"],\"nextSteps\":[\"Finish the snapshot objective.\"],\"blocker\":\"\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":3,"time":1783951001004,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":30,"outputTokens":12}}}}
|
||||
{"type":"assistant/chunk","seq":4,"time":1783951001005,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
@@ -0,0 +1,6 @@
|
||||
{"type":"session","version":0,"id":"43333333-3333-4333-8333-333333333333","createdAt":1783951002000,"cwd":"/tmp/ralph-headless","parentSession":"41111111-1111-4111-8111-111111111111"}
|
||||
{"type":"assistant/chunk","seq":0,"time":1783951002001,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
|
||||
{"type":"assistant/chunk","seq":1,"time":1783951002002,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"round-two-report","name":"structured_output","argumentsDelta":"{\"status\":\"complete\",\"summary\":\"The Ralph snapshot objective is complete.\",\"evidence\":[\"Two fresh rounds completed through the shipped app.\"],\"nextSteps\":[],\"blocker\":\"\"}"}}}
|
||||
{"type":"assistant/chunk","seq":2,"time":1783951002003,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"round-two-report","name":"structured_output","arguments":"{\"status\":\"complete\",\"summary\":\"The Ralph snapshot objective is complete.\",\"evidence\":[\"Two fresh rounds completed through the shipped app.\"],\"nextSteps\":[],\"blocker\":\"\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":3,"time":1783951002004,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":40,"outputTokens":12}}}}
|
||||
{"type":"assistant/chunk","seq":4,"time":1783951002005,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
@@ -0,0 +1 @@
|
||||
{"type":"session","version":0,"id":"41111111-1111-4111-8111-111111111111","createdAt":1783951000000,"cwd":"/tmp/ralph-headless"}
|
||||
@@ -0,0 +1,24 @@
|
||||
{"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":"Run a two-round fresh-agent Ralph loop to prove the shipped headless integration."}],"source":{"kind":"user"}},"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"session/title","seq":2,"time":0,"data":{"title":"Run a two-round fresh-agent Ralph","messageSeqs":[1],"source":{"kind":"fallback"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":4,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_ralph","name":"ralph","argumentsDelta":"{\"objective\":\"Prove two fresh Ralph rounds through the shipped headless app.\",\"maxRounds\":2}"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_ralph","name":"ralph","arguments":"{\"objective\":\"Prove two fresh Ralph rounds through the shipped headless app.\",\"maxRounds\":2}"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":20,"outputTokens":8}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":9,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":10,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_ralph","name":"ralph","arguments":"{\"objective\":\"Prove two fresh Ralph rounds through the shipped headless app.\",\"maxRounds\":2}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":20,"outputTokens":8}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_ralph","name":"ralph","arguments":"{\"objective\":\"Prove two fresh Ralph rounds through the shipped headless app.\",\"maxRounds\":2}"}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":12,"time":0,"data":{"turn":1,"step":1,"callId":"call_ralph","content":[{"type":"text","text":"Ralph worker reported completion after 2 rounds.\nFinal report:\n{\n \"status\": \"complete\",\n \"summary\": \"The Ralph snapshot objective is complete.\",\n \"evidence\": [\n \"Two fresh rounds completed through the shipped app.\"\n ],\n \"nextSteps\": [],\n \"blocker\": \"\"\n}"}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":13,"time":0,"data":{"turn":1,"step":1}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":14,"time":0,"data":{"turn":1,"step":2}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"RALPH SNAPSHOT COMPLETE"}}}}
|
||||
{"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":"text","text":"RALPH SNAPSHOT COMPLETE"}}}}}
|
||||
{"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":"stop"}}}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":20,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"text","text":"RALPH SNAPSHOT COMPLETE"}],"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":"step/end","seq":21,"time":0,"data":{"turn":1,"step":2}}}
|
||||
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":22,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}}
|
||||
{"type":"result","success":true,"sessionId":"{{sessionId}}","turn":1,"result":"RALPH SNAPSHOT COMPLETE","reason":{"kind":"completed"},"usage":{"inputTokens":50,"outputTokens":12}}
|
||||
Reference in New Issue
Block a user