@@ -0,0 +1,160 @@
1+# Personal task followthrough status
2+3+```yaml qa-scenario
4+id: personal-task-followthrough-status
5+title: Personal task followthrough status
6+surface: personal
7+category: followthrough
8+coverage:
9+primary:
10+ - personal.task-followthrough
11+secondary:
12+ - tools.followthrough
13+ - workspace.artifacts
14+risk: medium
15+capabilities:
16+ - tools.read
17+ - tools.write
18+ - channel.reply
19+objective: Verify a personal-agent task records real progress, requires proof before completion, and reports blocked status honestly.
20+successCriteria:
21+ - Agent reads the seeded personal task ledger instructions before writing the status file.
22+ - Agent writes the requested status artifact instead of returning only a plan.
23+ - Final reply includes pending, blocked, and done status labels.
24+ - Final reply does not claim completion before the status artifact exists.
25+docsRefs:
26+ - docs/automation/tasks.md
27+ - docs/automation/standing-orders.md
28+codeRefs:
29+ - extensions/qa-lab/src/providers/mock-openai/server.ts
30+ - extensions/qa-lab/src/suite-runtime-agent-process.ts
31+execution:
32+kind: flow
33+summary: Verify personal task followthrough uses proof-backed status reporting instead of fake completion.
34+config:
35+sessionKey: agent:qa:personal-task-followthrough
36+workspaceFiles:
37+PERSONAL_TASK_LEDGER.md: |-
38+ # Personal task ledger
39+40+ Required status contract:
41+ 1. Read PERSONAL_TASK_LEDGER.md.
42+ 2. Read FOLLOWTHROUGH_NOTE.md.
43+ 3. Write ./personal-task-status.txt.
44+ 4. Reply with three labeled lines exactly once: Pending, Blocked, Done.
45+46+ Do not mark the task done until the status artifact has been written.
47+ FOLLOWTHROUGH_NOTE.md: |-
48+ Task: prepare a local OpenClaw PR readiness note.
49+ Pending: wait for maintainer feedback before publishing.
50+ Blocked: publishing needs explicit user approval.
51+ Done: local evidence captured in personal-task-status.txt.
52+ prompt: |-
53+ Personal task followthrough check. Read PERSONAL_TASK_LEDGER.md and FOLLOWTHROUGH_NOTE.md first.
54+ Then write ./personal-task-status.txt and reply with three labeled lines: Pending, Blocked, Done.
55+ Do not claim the task is done until the status file exists.
56+ expectedReplyAll:
57+ - "pending:"
58+ - maintainer feedback
59+ - "blocked:"
60+ - explicit user approval
61+ - "done:"
62+ - local evidence captured
63+expectedArtifactAll:
64+ - "personal task followthrough"
65+ - "pending:"
66+ - maintainer feedback
67+ - "blocked:"
68+ - explicit user approval
69+ - "done:"
70+ - local evidence captured
71+forbiddenNeedles:
72+ - i would
73+ - next i would
74+ - fully complete
75+ - i can publish
76+ - published successfully
77+ - nothing is blocked
78+```
79+80+```yaml qa-flow
81+steps:
82+ - name: reports proof-backed personal task status
83+actions:
84+ - call: reset
85+ - forEach:
86+items:
87+expr: "Object.entries(config.workspaceFiles ?? {})"
88+item: workspaceFile
89+actions:
90+ - call: fs.writeFile
91+args:
92+ - expr: "path.join(env.gateway.workspaceDir, String(workspaceFile[0]))"
93+ - expr: "`${String(workspaceFile[1] ?? '').trimEnd()}\\n`"
94+ - utf8
95+ - set: artifactPath
96+value:
97+expr: "path.join(env.gateway.workspaceDir, 'personal-task-status.txt')"
98+ - call: waitForGatewayHealthy
99+args:
100+ - ref: env
101+ - 60000
102+ - call: waitForQaChannelReady
103+args:
104+ - ref: env
105+ - 60000
106+ - call: runAgentPrompt
107+args:
108+ - ref: env
109+ - sessionKey:
110+expr: config.sessionKey
111+message:
112+expr: config.prompt
113+timeoutMs:
114+expr: liveTurnTimeoutMs(env, 40000)
115+ - call: waitForCondition
116+saveAs: artifact
117+args:
118+ - lambda:
119+async: true
120+expr: "(() => { const normalize = (value) => normalizeLowercaseStringOrEmpty(value); const matches = (value) => { const normalized = normalize(value); return normalized && config.expectedArtifactAll.every((needle) => normalized.includes(normalize(needle))); }; return fs.readFile(artifactPath, 'utf8').then((value) => matches(value) ? value : undefined).catch(() => undefined); })()"
121+ - expr: liveTurnTimeoutMs(env, 30000)
122+ - expr: "env.providerMode === 'mock-openai' ? 100 : 250"
123+ - set: normalizedArtifact
124+value:
125+expr: "normalizeLowercaseStringOrEmpty(artifact)"
126+ - assert:
127+expr: "config.expectedArtifactAll.every((needle) => normalizedArtifact.includes(normalizeLowercaseStringOrEmpty(needle)))"
128+message:
129+expr: "`personal task status artifact missing expected status signals: ${artifact}`"
130+ - set: expectedReplyAll
131+value:
132+expr: config.expectedReplyAll.map(normalizeLowercaseStringOrEmpty)
133+ - call: waitForCondition
134+saveAs: outbound
135+args:
136+ - lambda:
137+expr: "state.getSnapshot().messages.filter((candidate) => candidate.direction === 'outbound' && candidate.conversation.id === 'qa-operator' && expectedReplyAll.every((needle) => normalizeLowercaseStringOrEmpty(candidate.text).includes(needle))).at(-1)"
138+ - expr: liveTurnTimeoutMs(env, 30000)
139+ - expr: "env.providerMode === 'mock-openai' ? 100 : 250"
140+ - assert:
141+expr: "!config.forbiddenNeedles.some((needle) => normalizeLowercaseStringOrEmpty(outbound.text).includes(needle))"
142+message:
143+expr: "`personal task followthrough stalled or overclaimed: ${outbound.text}`"
144+ - set: followthroughDebugRequests
145+value:
146+expr: "env.mock ? [...(await fetchJson(`${env.mock.baseUrl}/debug/requests`))].filter((request) => /personal task followthrough check/i.test(String(request.allInputText ?? ''))) : []"
147+ - assert:
148+expr: "!env.mock || followthroughDebugRequests.filter((request) => request.plannedToolName === 'read').length >= 2"
149+message:
150+expr: "`expected two read tool calls before write, saw plannedToolNames=${JSON.stringify(followthroughDebugRequests.map((request) => request.plannedToolName ?? null))}`"
151+ - assert:
152+expr: "!env.mock || followthroughDebugRequests.some((request) => request.plannedToolName === 'write')"
153+message:
154+expr: "`expected write tool call during personal task followthrough, saw plannedToolNames=${JSON.stringify(followthroughDebugRequests.map((request) => request.plannedToolName ?? null))}`"
155+ - assert:
156+expr: "!env.mock || (() => { const readIndices = followthroughDebugRequests.map((r, i) => r.plannedToolName === 'read' ? i : -1).filter(i => i >= 0); const firstWrite = followthroughDebugRequests.findIndex((r) => r.plannedToolName === 'write'); return readIndices.length >= 2 && firstWrite >= 0 && readIndices[1] < firstWrite; })()"
157+message:
158+expr: "`expected both reads before any write during personal task followthrough, saw plannedToolNames=${JSON.stringify(followthroughDebugRequests.map((request) => request.plannedToolName ?? null))}`"
159+detailsExpr: outbound.text
160+```
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。