- 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。
2.6 KiB
Executable File
markup, title, description, import
| markup | title | description | import | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| occlusion | Agent Framework P4 — Adaptive Routing + Policy Compilation (offline) | Learn skill, compile policy from skill-tagged episodes, route via marqdo backend without Jev/LLM. |
|
main
p = > plugin.native_path name="agent"
p
plugin.load path=
p
print text=no-agent-plugin sys.exit code=1
paths = > json.parse text={"mem":".marqdo/agent-memory-p4-test","kb":".marqdo/agent-kb-p4-test","task":"Reply with exactly the word pong and nothing else.","skill":"concepts/skills/reply-with-exactly-the-word-pong-and-nothing-els.md"}
mem = > json.get value=paths key="mem"
kb = > json.get value=paths key="kb"
task = > json.get value=paths key="task"
skill = > json.get value=paths key="skill"
-
fs.exists path=
mem
fs.remove_tree path=
mem
_ = 1
-
fs.exists path=
kb
fs.remove_tree path=
kb
_ = 1
agent_memory_ensure memory_dir=
mem
ep1 = > agent_record_episode task=task status="ok" result="pong" mode="explore" skill=skill llm_calls=2 memory_dir=mem
ep2 = > agent_record_episode task=task status="ok" result="pong" mode="explore" skill=skill llm_calls=2 memory_dir=mem
ep3 = > agent_record_episode task=task status="ok" result="pong" mode="explore" skill=skill llm_calls=2 memory_dir=mem
learned = > agent_maybe_learn task=task memory_dir=mem kb_dir=kb improve_every=3 promote=True
did = > json.get value=learned key="learned"
did
print text=skill-learned
print text=skill-skip
ep4 = > agent_record_episode task=task status="ok" result="pong" mode="compiled" skill=skill llm_calls=0 memory_dir=mem
ep5 = > agent_record_episode task=task status="ok" result="pong" mode="compiled" skill=skill llm_calls=0 memory_dir=mem
ep6 = > agent_record_episode task=task status="ok" result="pong" mode="compiled" skill=skill llm_calls=0 memory_dir=mem
pol = > agent_compile_policy memory_dir=mem min_evidence=3
pok = > json.get value=pol key="ok"
pok
print text=policy-ok
print text=policy-fail
routed = > agent_route task=task backend="auto" memory_dir=mem kb_dir=kb
matched = > json.get value=routed key="matched"
needs = > json.get value=routed key="needs_llm"
matched- not
needs> print text=route-hit -
> print text=route-needs-llm
print text=route-miss
backend = > json.get value=routed key="backend"
print text=
backend