- 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。
2.0 KiB
Executable File
markup, title, description, import
| markup | title | description | import | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| occlusion | OKF agent-kb near_match (offline) | Promote trip resource; near-dupe goals hit match=near; unrelated misses. |
|
main
p = > plugin.native_path name="agent"
p
plugin.load path=
p
print text=no-agent-plugin sys.exit code=1
kb = ".marqdo/agent-kb-near-test" wb = ".marqdo/agent-runs/near-trip.mq.md" goal = "帮我规划明天的行程" body = "---\ntitle: trip\n---\n\n# main\n\nmsg = "trip-ok"\n\nmsg\n"
fs.write_text path=
wbtext=bodyprom = > agent_kb_promote kb_dir=kbgoal=goalworkbook=wbokp = > json.get value=promkey="promoted"
okp
print text=promoted
print text=promote-fail
slug = > json.get value=prom key="slug"
g1 = "帮我规划明天行程"
hit1 = > agent_kb_lookup kb_dir=kb goal=g1 near_match=True near_threshold=0.78
hit1
print text=near-ok
print text=near-miss mk1 = > json.get value=
hit1key="match" print text=mk1slug1 = > json.get value=hit1key="slug"
slug==slug1
print text=same-slug
print text=slug-drift
off = > agent_kb_lookup kb_dir=kb goal=g1 near_match=False
off
print text=off-hit
print text=off-miss
g2 = "明天做什么好"
hit2 = > agent_kb_lookup kb_dir=kb goal=g2 near_match=True near_threshold=0.78
hit2
print text=neg-hit
print text=neg-miss
ranked = > agent_kb_near_match kb_dir=kb goal=g1
best = > json.get value=ranked key="best"
bs = > json.get value=best key="slug"
bs==slug
print text=rank-ok
print text=rank-bad
tasks = > json.get value=ranked key="candidates"
prompt = > agent.build_soft_match_prompt goal=g1 tasks=tasks
has = > split value=prompt sep="score="
hn = > len value=has
hn> 1
print text=prompt-score-ok
print text=prompt-score-bad