Inside italic/bold code segments every bare word is a variable — including call arguments and method-call receivers — so text literals must be quoted and receivers no longer need backticks. A bare dotted callee `a.b` resolves as a method call when `a` is a local variable, otherwise as a library path (Python-style unified namespace), in both the tree-walk and bytecode backends. Migrate ~70 tests plus ext/web, ext/quantum, ext/ai and the example projects to the new idiom; update SKILL.md and the design docs; fix the web/quantum example data model (db/index.mq.md). Unit and gold suites pass; only the 3 network-live tests fail offline. Co-authored-by: Cursor <cursoragent@cursor.com>
3.4 KiB
title: agent plan decision + dual skeleton (offline) description: extract_plan_decision/summary; dual skeleton contains research+writer; patch apply on fixture. import agent:ext/ai/agent.mq.md import json:lib/json.mq.md import fs:lib/fs.mq.md
main
samples = > json.parse text={"done":"DECISION: DONE\nSUMMARY: all good\n","cont":"DECISION: CONTINUE\nPATCH:\n<<<\nFIND\nold\n===\nREPLACE\nnew\n>>>\n","zh":"决定:完成\n汇总:好了\n","run":"DECISION: RUN\n","zh_run":"决定:运行\n"}
d1 = > json.get value=samples key="done"
r1 = > agent.extract_plan_decision reply=d1
print text=
r1s1 = > agent.extract_plan_summary reply=d1print text=s1
d2 = > json.get value=samples key="cont"
r2 = > agent.extract_plan_decision reply=d2
print text=
r2
d3 = > json.get value=samples key="zh"
r3 = > agent.extract_plan_decision reply=d3
print text=
r3
d4 = > json.get value=samples key="run"
r4 = > agent.extract_plan_decision reply=d4
print text=
r4
d5 = > json.get value=samples key="zh_run"
r5 = > agent.extract_plan_decision reply=d5
print text=
r5
d6 = "DECISION: DONE\nSUMMARY: first wins\nDECISION: CONTINUE\nPATCH:\nbogus\n"
r6 = > agent.extract_plan_decision reply=d6
print text=
r6
act_call = "CALL:lib_catalog"
a1 = > agent.extract_plan_act reply=act_call
a1k = > json.get value=a1 key="kind"
a1n = > json.get value=a1 key="name"
print text=
a1kprint text=a1n
act_read = "READ:stderr"
a2 = > agent.extract_plan_act reply=act_read
a2k = > json.get value=a2 key="kind"
a2n = > json.get value=a2 key="name"
print text=
a2kprint text=a2n
act_dec = > json.get value=samples key="done"
a3 = > agent.extract_plan_act reply=act_dec
a3k = > json.get value=a3 key="kind"
print text=
a3k
cat = > agent.lib_catalog
files = > json.get value=cat key="files"
nf = > len value=files
nf> 5
print text=catalog-ok
print text=catalog-bad
dual = > agent.render_workbook_skeleton goal="demo" skeleton="dual"
has_r = > split value=dual sep="research"
n_r = > len value=has_r
n_r> 1
print text=dual-ok
print text=dual-missing
has_s = > split value=dual sep="Solidify"
n_s = > len value=has_s
n_s> 1
print text=solidify-ok
print text=solidify-missing
has_imp = > split value=dual sep="import llm:ext/ai/llm.mq.md"
n_imp = > len value=has_imp
n_imp> 1
print text=import-ok
print text=import-missing
paths = > json.parse text={"p":".marqdo/agent-runs/decision-patch.md","t":"keep old keep","fence":"alpha beta","p2":".marqdo/agent-runs/decision-fence.md"}
path = > json.get value=paths key="p"
seed = > json.get value=paths key="t"
fs.write_text path=
pathtext=seedn = > fs.apply_patch_blocks path=pathtext=d2print text=nout = > fs.read_text path=pathprint text=out
path2 = > json.get value=paths key="p2"
seed2 = > json.get value=paths key="fence"
fs.write_text path=
path2text=seed2fence_pack = > json.parse text={"t":"DECISION: CONTINUE\n\u0060\u0060\u0060find\nalpha\n\u0060\u0060\u0060\n\u0060\u0060\u0060replace\nALPHA\n\u0060\u0060\u0060\n"} fence_reply = > json.get value=fence_packkey="t" n2 = > fs.apply_patch_blocks path=path2text=fence_replyprint text=n2out2 = > fs.read_text path=path2print text=out2