mirror of
https://github.com/openclaw/openclaw.git
synced 2026-08-15 07:04:01 -06:00
6a8e11e63c
* fix(qa): repair parity and matrix media setup Punchcard-Session: silver-valley-valley-dt * test(qa): accept token-budgeted compaction suffix Punchcard-Session: silver-valley-valley-dt * test(qa): scope request diagnostics Punchcard-Session: silver-valley-valley-dt * test(qa): prove thread-memory causality Punchcard-Session: silver-valley-valley-dt * test(qa): configure Matrix image generation and fail fast Punchcard-Session: silver-valley-valley-dt * fix(qa): require memory get before thread recall Punchcard-Session: silver-valley-valley-dt * fix(qa): unify mock provider dispatch Punchcard-Session: silver-valley-valley-dt * fix(qa): repair Anthropic IDs and compaction causality Punchcard-Session: silver-valley-valley-dt * fix(qa): authenticate compaction wire causality Punchcard-Session: silver-valley-valley-dt * fix(qa): preserve Responses tool item identity Punchcard-Session: silver-valley-valley-dt * fix(qa): scope restart heartbeat proof Punchcard-Session: silver-valley-valley-dt * test(qa): assert causal traces before delivery Punchcard-Session: silver-valley-valley-dt * fix(qa): validate code mode completion evidence Punchcard-Session: silver-valley-valley-dt * test(qa): split causal catalog checks Punchcard-Session: silver-valley-valley-dt * style(qa): format matrix scenario tests Punchcard-Session: silver-valley-valley-dt
153 lines
7.0 KiB
YAML
153 lines
7.0 KiB
YAML
title: Thread memory isolation
|
|
|
|
scenario:
|
|
id: thread-memory-isolation
|
|
surface: session-memory
|
|
runtimePairLane: core
|
|
coverage:
|
|
primary:
|
|
- session-memory.cross-client-history-thread-isolation
|
|
secondary:
|
|
- channels.native-threads
|
|
objective: Verify a memory-backed answer requested inside a thread stays in-thread and does not leak into the root channel.
|
|
successCriteria:
|
|
- Agent uses memory tools inside the thread.
|
|
- The hidden fact is answered correctly in the thread.
|
|
- No root-channel outbound message leaks during the threaded memory reply.
|
|
docsRefs:
|
|
- docs/concepts/memory-search.md
|
|
- docs/channels/qa-channel.md
|
|
- docs/channels/group-messages.md
|
|
codeRefs:
|
|
- extensions/memory-core/src/tools.ts
|
|
- extensions/qa-channel/src/protocol.ts
|
|
- extensions/qa-lab/src/suite.ts
|
|
execution:
|
|
kind: flow
|
|
summary: Verify a memory-backed answer requested inside a thread stays in-thread and does not leak into the root channel.
|
|
channel: qa-channel
|
|
providerMode: mock-openai
|
|
retryCount: 0
|
|
config:
|
|
memoryFact: "Thread-hidden codename: ORBIT-22."
|
|
memoryQuery: "hidden thread codename ORBIT-22"
|
|
expectedMemoryPath: MEMORY.md
|
|
expectedNeedle: "ORBIT-22"
|
|
channelId: qa-room
|
|
channelTitle: QA Room
|
|
threadTitle: "Thread memory QA"
|
|
prompt: "@openclaw Thread memory check: what is the hidden thread codename stored only in memory? Use memory tools first and reply only in this thread."
|
|
promptSnippet: "Thread memory check"
|
|
|
|
flow:
|
|
steps:
|
|
- name: answers the memory-backed fact inside the thread only
|
|
actions:
|
|
- call: reset
|
|
- call: fs.writeFile
|
|
args:
|
|
- expr: "path.join(env.gateway.workspaceDir, 'MEMORY.md')"
|
|
- expr: "`${config.memoryFact}\\n`"
|
|
- utf8
|
|
- call: forceMemoryIndex
|
|
args:
|
|
- env:
|
|
ref: env
|
|
query:
|
|
expr: config.memoryQuery
|
|
expectedNeedle:
|
|
expr: config.expectedNeedle
|
|
- call: waitForGatewayHealthy
|
|
args:
|
|
- ref: env
|
|
- 60000
|
|
- call: waitForQaChannelReady
|
|
args:
|
|
- ref: env
|
|
- 60000
|
|
- call: handleQaAction
|
|
saveAs: threadPayload
|
|
args:
|
|
- env:
|
|
ref: env
|
|
action: thread-create
|
|
args:
|
|
channelId:
|
|
expr: config.channelId
|
|
title:
|
|
expr: config.threadTitle
|
|
- set: threadId
|
|
value:
|
|
expr: "threadPayload?.thread?.id"
|
|
- assert:
|
|
expr: Boolean(threadId)
|
|
message: missing thread id for memory isolation check
|
|
- set: requestCursorBefore
|
|
value:
|
|
expr: "(await fetchJson(`${env.mock.baseUrl}/debug/request-cursor`)).cursor"
|
|
- set: outboundStartIndex
|
|
value:
|
|
expr: state.getSnapshot().messages.length
|
|
- sendInbound:
|
|
conversation:
|
|
id:
|
|
expr: config.channelId
|
|
kind: channel
|
|
title:
|
|
expr: config.channelTitle
|
|
senderId: alice
|
|
senderName: Alice
|
|
text:
|
|
expr: config.prompt
|
|
threadId:
|
|
ref: threadId
|
|
threadTitle:
|
|
expr: config.threadTitle
|
|
- call: waitForCondition
|
|
saveAs: scenarioRequests
|
|
args:
|
|
- lambda:
|
|
async: true
|
|
expr: "(async () => { const requests = (await fetchJson(`${env.mock.baseUrl}/debug/requests?after=${requestCursorBefore}`)).filter((request) => String(request.allInputText ?? '').includes(config.promptSnippet)); return requests.length >= 3 ? requests : undefined; })()"
|
|
- expr: liveTurnTimeoutMs(env, 30000)
|
|
- 100
|
|
- assert:
|
|
expr: scenarioRequests.length === 3
|
|
message:
|
|
expr: "`expected one memory_search plan, one memory_get plan, and one final request: ${JSON.stringify(scenarioRequests)}`"
|
|
- set: searchPlanRequest
|
|
value:
|
|
expr: scenarioRequests[0]
|
|
- set: searchResultRequest
|
|
value:
|
|
expr: scenarioRequests[1]
|
|
- set: finalRequest
|
|
value:
|
|
expr: scenarioRequests[2]
|
|
- assert:
|
|
expr: "searchPlanRequest.plannedToolName === 'memory_search' && searchPlanRequest.plannedToolArgs?.query === config.memoryQuery && typeof searchPlanRequest.plannedToolCallId === 'string' && searchPlanRequest.plannedToolCallId.length > 0 && !searchPlanRequest.toolOutputCallId && !String(searchPlanRequest.allInputText ?? '').includes(config.expectedNeedle)"
|
|
message:
|
|
expr: "`initial thread request exposed the hidden fact, disabled memory_search, or routed incorrectly: ${JSON.stringify(searchPlanRequest)}`"
|
|
- assert:
|
|
expr: "searchResultRequest.cursor > searchPlanRequest.cursor && searchResultRequest.toolOutputCallId === searchPlanRequest.plannedToolCallId && searchResultRequest.toolOutputStructuredError !== true && String(searchResultRequest.toolOutput ?? '').includes(config.expectedMemoryPath) && String(searchResultRequest.toolOutput ?? '').includes(config.expectedNeedle) && searchResultRequest.plannedToolName === 'memory_get' && searchResultRequest.plannedToolArgs?.path === config.expectedMemoryPath && typeof searchResultRequest.plannedToolCallId === 'string' && searchResultRequest.plannedToolCallId.length > 0 && searchResultRequest.plannedToolCallId !== searchPlanRequest.plannedToolCallId"
|
|
message:
|
|
expr: "`memory_search result did not causally plan memory_get: ${JSON.stringify(searchResultRequest)}`"
|
|
- assert:
|
|
expr: "finalRequest.cursor > searchResultRequest.cursor && finalRequest.toolOutputCallId === searchResultRequest.plannedToolCallId && finalRequest.toolOutputStructuredError !== true && String(finalRequest.toolOutput ?? '').includes(config.expectedNeedle) && !finalRequest.plannedToolName"
|
|
message:
|
|
expr: "`final thread request did not consume the matching memory_get result: ${JSON.stringify(finalRequest)}`"
|
|
- call: waitForOutboundMessage
|
|
saveAs: outbound
|
|
args:
|
|
- ref: state
|
|
- lambda:
|
|
params: [candidate]
|
|
expr: "((candidate.conversation.id === config.channelId && candidate.threadId === threadId) || candidate.conversation.id === threadId) && candidate.text.includes(config.expectedNeedle)"
|
|
- expr: liveTurnTimeoutMs(env, 300000)
|
|
- sinceIndex:
|
|
ref: outboundStartIndex
|
|
- assert:
|
|
expr: "!state.getSnapshot().messages.slice(outboundStartIndex).some((candidate) => candidate.direction === 'outbound' && candidate.conversation.id === config.channelId && !candidate.threadId)"
|
|
message: threaded memory answer leaked into root channel
|
|
detailsExpr: outbound.text
|