Skip to content

feat(walkthrough): add host fake-fixture parity walkthrough smoke (GH… - #3130

Closed
rootkiller6788 wants to merge 1 commit into
huangruiteng:mainfrom
rootkiller6788:feat/gh-c60-host-fake-fixture-parity
Closed

feat(walkthrough): add host fake-fixture parity walkthrough smoke (GH…#3130
rootkiller6788 wants to merge 1 commit into
huangruiteng:mainfrom
rootkiller6788:feat/gh-c60-host-fake-fixture-parity

Conversation

@rootkiller6788

Copy link
Copy Markdown
Contributor

…-C60)

Coverage across all 13 agent types, 3 Turn hosts, scheduler runtime profiles, host surface mappings, and skill-delivery modes:

  • Agent type catalog completeness (13 canonical types, 4 ambiguous inputs)
  • Host surface -> agent type parity (22 surface routes including shell, http, worker-bridge)
  • Activation packet parity (distinct activation methods, host surfaces, mutations per agent type)
  • Scheduler runtime profile bindings (11 bound, 2 unbound, 5 generic_cli)
  • Turn host identity parity (3 hosts, 2 execution modes, Pi/OpenCode aliases)
  • Host mode plan selects distinct modes per intent and host identity
  • Missing capability routes fail closed (6 fail-closed cases)
  • Scoped identity gating (selection_required, single_agent auto-select, explicit bypass)
  • Skill delivery parity (9 surface_managed, 3 host_managed, manual none)
  • No-spend transition and boundary proofs
  • Markdown rendering and public-safety scan (13 agent types scanned)
  • Runtime-owned cadence ownership (11 bound types reference quota/gating)

Summary

Issue Or Task

  • Closes #
  • Contributor task ID:

Validation

  • python3 -m py_compile loopx/*.py
  • loopx check --scan-root .
  • Other:

Type of Change

  • Bug fix
  • New feature
  • Breaking change
  • Refactoring (no functional changes)
  • Documentation update
  • Test update

LoopX Area

  • Control plane (goals, todos, quota, scheduler, registry, runtime)
  • Benchmark boundary (adapters, runners, verifiers, scoring, evidence)
  • Capability or extension (providers, adapters, skills)
  • Public docs or presentation surface (README, protocols, dashboard)
  • Build, packaging, installer, or CI
  • Host or runtime integration

Boundary Checklist

  • I did not commit .loopx/, .codex/goals/, live ACTIVE_GOAL_STATE.md, credentials, private benchmark traces, verifier output, raw agent sessions, internal document links, or local machine paths.
  • I did not duplicate maintainer-owned benchmark work unless a maintainer split out a public issue for it.
  • I kept the change scoped to the linked issue/task.

…-C60)

Coverage across all 13 agent types, 3 Turn hosts, scheduler runtime
profiles, host surface mappings, and skill-delivery modes:

- Agent type catalog completeness (13 canonical types, 4 ambiguous inputs)
- Host surface -> agent type parity (22 surface routes including shell,
  http, worker-bridge)
- Activation packet parity (distinct activation methods, host surfaces,
  mutations per agent type)
- Scheduler runtime profile bindings (11 bound, 2 unbound, 5 generic_cli)
- Turn host identity parity (3 hosts, 2 execution modes, Pi/OpenCode
  aliases)
- Host mode plan selects distinct modes per intent and host identity
- Missing capability routes fail closed (6 fail-closed cases)
- Scoped identity gating (selection_required, single_agent auto-select,
  explicit bypass)
- Skill delivery parity (9 surface_managed, 3 host_managed, manual none)
- No-spend transition and boundary proofs
- Markdown rendering and public-safety scan (13 agent types scanned)
- Runtime-owned cadence ownership (11 bound types reference quota/gating)

@huangruiteng huangruiteng left a comment

Copy link
Copy Markdown
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

详细中文评审(durable_smoke_value 门槛)

精确评审头: 3130@62ef307ee5075504d8fde9e31ca93a564cbd5ee4

动机

本 PR 是单文件 examples/host-fake-fixture-parity-walkthrough-smoke.py(+805 行),演示跨 host 的 fake-fixture parity。按 durable_smoke_value 门槛,例程类 PR 必须证明对仓库/产品的真实、持久价值;本 PR 不满足。

改动思路

12 个 scenario 覆盖 13 种 agent 类型、22 条 host surface 路由、scheduler runtime profile 绑定、Turn host 身份、missing capability fail-closed、skill delivery mode、no-spend 与 public safety。作为演示自洽,但全部是对已发布 host-mode/skill-delivery 行为的合成断言,且体积达 805 行。

具体改动(关键内容讲解)

  • existing_coverage_scantests/test_host_mode_planner.pytests/test_host_loop_activation.pytests/test_loopx_turn_driver.pytests/test_pi_goal_mode.pytests/test_ark_managed_agent_host.pytests/test_gemini_cursor_host_surfaces.py 已覆盖 host surface 路由、runtime profile、fail-closed capability 与 skill delivery 的关键路径;examples/loopx-turn-fake-host-walkthrough-smoke.py 等已有 walkthrough。本文件的 12 个 scenario 与既有覆盖高度重叠,属重复演示。
  • same_author_batch_scan#3130(805 行)、#3131(585 行)、#3133(545 行)由同一作者在 11:18–11:20 两分钟内连续提交,叠加 #3113#3120 同构系列,是明确批量刷 PR 信号。
  • real_product_or_repo_value_verdict:若部分 parity 断言确实缺失,正确做法是在 tests/ 补 thin focused test;805 行 example 脚手架重复既有覆盖,对仓库是噪音。

对主干的风险

代码本身无运行时风险。风险在模式:同作者分钟级堆叠同形状 walkthrough PR,消耗评审队列、稀释真实 runtime 改动的可见度。本批次 #3131/#3133 已被 REQUEST_CHANGES,本 PR 属同一批次,不应例外放行。

我的整体评价

REQUEST_CHANGES。 修复建议(择一):(1) 将关键断言收敛为 thin focused pytest;(2) 与 #3131/#3133 合并为一个有差异化价值的 walkthrough 并删除重复 scaffolding。贡献行为警告:按 PR #3134 的新政策,若同一作者在收到警告后再提交此类低价值同形状 PR,将禁止该账号继续向本仓库提交 PR(owner 执行屏蔽)。


English Verdict

REQUEST_CHANGES — exact head 62ef307ee5075504d8fde9e31ca93a564cbd5ee4.

Under the durable_smoke_value gate, this 805-line example-only walkthrough duplicates existing host-parity coverage (test_host_mode_planner.py, test_host_loop_activation.py, test_loopx_turn_driver.py, etc.) and is part of a same-author 3-PR batch opened within two minutes (#3130/#3131/#3133). Consolidate into thin focused tests or one differentiated walkthrough. Contribution warning: further low-value same-shape PRs after this warning will lead to the account being blocked from submitting PRs to this repository.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants