- CHANGELOG.md:v2.8.0 条目(中英双语); - README.md:版本行 2.7.1→2.8.0 + 愿景第 6 条(知识可证明); - doc/releases/v2.8.0.md:双语发版说明(亮点/用法/已知限制); - skills/marqdo-dev/index.mq.md:新增 prove 任务(路径/目录模式/ require_lean/json;参数用 + 行声明升参,check 与 narrative-ratio 通过); - 设计文档 §12.5 标记已合入;发版链接统一指向 doc/releases/v2.8.0.md。
3.1 KiB
Executable File
markup, title, description, import
| markup | title | description | import | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| occlusion | OKF plan llm_free hit + list_tasks curation (A1 offline) | Promote solidified workbook; plan same goal takes cache=hit; near→soft-hit; list_tasks exposes status/llm_free. |
|
main
p = > plugin.native_path name="agent"
p
plugin.load path=
p
print text=no-agent-plugin sys.exit code=1
sys.env_set name="OPENAI_API_KEY" value="offline-a1-dummy" model = > llm.llm tools = > json.parse text=[] 助手 = > agent.agent model=
modeltools=toolsstanding="offline plan-hit"
paths = > json.parse text={"kb":".marqdo/agent-kb-a1-plan-hit","wb":".marqdo/agent-runs/a1-pong-solid.mq.md","goal":"Reply with exactly the word pong and nothing else.","near":"Reply with exactly the word pong.","body":"---\ntitle: a1 pong\n---\n\n# main\n\nmsg = "pong"\n\nmsg\n"}
kb = > json.get value=paths key="kb"
wb = > json.get value=paths key="wb"
goal = > json.get value=paths key="goal"
near_g = > json.get value=paths key="near"
body = > json.get value=paths key="body"
-
fs.exists path=
kb
fs.remove path=
kb
_ = 1
fs.write_text path=
wbtext=body
prom = > agent_kb_promote kb_dir=kb goal=goal workbook=wb
okp = > json.get value=prom key="promoted"
okp
print text=promoted
print text=promote-fail sys.exit code=1
listed = > agent_kb_list_tasks kb_dir=kb
tc = > json.get value=listed key="count"
tc> 0
print text=list-ok
print text=list-bad sys.exit code=1
tasks = > json.get value=listed key="tasks"
t0 = > at value=tasks index=0
lf = > json.get value=t0 key="llm_free"
lf
print text=list-free
print text=list-not-free st = > json.get value=
t0key="status" print text=stdesc = > json.get value=t0key="description"
desc
print text=list-desc
print text=list-no-desc
out = > 助手.plan goal=goal max_rounds=2 writeback=False kb_dir=kb explore_n=0 promote=False
cache = > json.get value=out key="cache"
print text=
cachemk = > json.get value=outkey="match" print text=mkval = > json.get value=outkey="result" print text=valsum = > json.get value=outkey="summary" has = > split value=sumsep="exact" hn = > len value=has
hn> 1
print text=sum-exact
print text=sum-bad
evs = > json.get value=out key="events"
en = > len value=evs
en> 2
print text=events-ok
print text=events-bad e0 = > at value=
evsindex=0 t0 = > json.get value=e0key="type" print text=t0d0 = > json.get value=e0key="decision" print text=d0
out2 = > 助手.plan goal=near_g max_rounds=2 writeback=False kb_dir=kb explore_n=0 promote=False
cache2 = > json.get value=out2 key="cache"
print text=
cache2mk2 = > json.get value=out2key="match" print text=mk2val2 = > json.get value=out2key="result" print text=val2