Skip to content

fix(testing): complete native semantic replan qualification - #8016

Merged
huangruiteng merged 3 commits into
mainfrom
codex/native-reader-qualification-20261103-185749
Nov 4, 2026
Merged

huangruiteng merged 3 commits into
mainfrom
codex/native-reader-qualification-20261103-185749

Conversation

@loopx-agent

@loopx-agent loopx-agent commented Nov 4, 2026 •

Copy link
Copy Markdown
Collaborator

Current replan qualification can fail before a valid outcome reaches the real writer: captured readers use a module launcher, typed-only scripted actions omit the required v2 decision, and the host tries successor re-entry before settling the original Turn.

Reuse the trusted CLI/current-capture reader and existing OS-isolated shell for model-authored Vision/stride drafts. The writer still owns semantic acceptance. A linked joint experiment can change the review basis; the actor now reads the exact recovery capture, reassesses the scheduled work and completes the original bound writeback/spend before observing successor adoption. Shell text cannot authorize another capture, and the host supplies no decision fields.

Validation on 32fba35023c37b164d2d3ebfb038fb450c345c5b, rebased onto main a0130633723210a5406dca61ee27aa33fe48b3f3:

  • Six real CLI/shell consumer modules: 188 passed, including the seven previously failing semantic/successor cases.
  • Native and inline delivery, current v2 persistence, draft containment, source/identity refusal, forged recovery refusal, original-Turn one-spend readback and successor/terminal adoption are covered.
  • Seven ordinary calls plus the existing three native-read allowance remain; recovery consumes ordinary budget. The separate required-Vision journey retains forty calls and its OS isolation/error cases.
  • Canonical CI Ruff, configured 17-file mypy, semantic inventory/owner smoke, CLI output budget, public-boundary scan, DCO and bilingual RFC checks pass.

Standard premerge executed six direct checks, five catalog canaries, eight risk-profile smokes and a public-boundary scan without run failures. It reports one inherited maintainability advisory; the overall gate is quality_invalid_receipt.

The additional whole-repository Ruff invocation still reports 122 errors, and expanded mypy import traversal still reports 4,706 errors in 476 files. These results remain failed without a baseline waiver. The exact-scope quality receipt remains failed; complete repository pytest, remote CI and independent review remain outstanding.

This qualifies scripted behavior through real isolated entrypoints. Live model behavior, installed-host adoption and long-horizon outcome/full-cost benefit remain unqualified. The PR remains open and unmerged.

@loopx-agent loopx-agent changed the title fix(testing): route native context readers through isolated CLI hosts fix(testing): qualify native readers and Vision closeout Nov 4, 2026
Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com>
Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com>
Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com>
@loopx-agent
loopx-agent force-pushed the codex/native-reader-qualification-20261103-185749 branch from e726033 to 32fba35 Compare November 4, 2026 09:12
@loopx-agent loopx-agent changed the title fix(testing): qualify native readers and Vision closeout fix(testing): complete native semantic replan qualification Nov 4, 2026

@loopx-agent loopx-agent left a comment

Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

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

Reviewer: model_agent; gpt-6.1-sol; OpenAI; runtime_reported; reasoning_effort=max.

Approval conclusion (author-owned PR; GitHub blocks formal self-approval)

动机 / Motivation

维护重规划资格测试的人需要让脚本 Agent 通过真实命令读证据、编写决策并完成原轮结算。原生读取命令换成 Python 模块入口后,旧测试宿主可能先拒绝合法读取;创建后续任务后又提前开启下一轮,导致原轮尚未回写和扣额便被当作完成。现在合法读取由固定解释器执行,Agent 自行编写当前决策;后续任务创建之后,仍须完成原轮真实回写、一次扣额和回读才能通过资格。本次不证明真实模型理解、已安装宿主采用或长程收益,也不授予后续任务在原轮执行的权限。真实模型、安装后采用和长程完整成本仍未资格化;仓库全量静态扩展检查及 exact-scope quality hold 也未据此豁免。

改动思路 / Approach

复用固定 CLI 执行器、当前 capture reader 和现有 OS 隔离 shell;宿主只观察真实 writer 的决策和结算,不代写 Vision、Stride 或 binding。当前 PR 的边界是五个文件内的隔离资格宿主、脚本 oracle 与相应文档;生产语义判定、持久化和结算仍由原有 typed owner 执行。这次有意修正的是资格宿主能否走完已经存在的合法流程,而不是降低真实 writer 的要求。旧版“创建 successor 便看下一轮”遗漏了原轮工作;新版先把创建结果作为观察保存,等当前决策、真实回写和原额度结算均已成立,再检查后续采用。

触发 原行为 当前可观察结果
合法模块 capture reader 宿主可能拒绝 固定解释器读取当前 source/SHA
successor 已创建 提前读取下一轮 原轮回写、扣额、回读后才观察采用
shell 打印 recovery JSON 不应产生权限 只有 bound writer 的真实拒绝能授权精确 recovery

这是源码和执行结果的对照;没有把命令拼接或测试数量当成真实模型理解。既有 required-Vision 的四十调用路径仍独立,narrow 路径保持七个普通调用加最多三个 native read;恢复读取消耗普通预算。

具体改动 / Changes

关键代码讲解

  1. _module_reader_tokens 只把两个模块名下的 quota context-read/replan-view 规范化。实际执行仍走既有固定解释器;模型提供的 Python 路径不会被执行。QuotaToolContext.read 继续核对当前路径、SHA、重复参数和 override,不能借相同内容的另一份文件换 source。
  2. _bound_semantic_writeback 检查项目内已编写草稿与原 obligation/Turn,再调用真实 writer,并核对历史中的 semantic delta、checkpoint 和 settlement identity。恢复 capture 只能来自该 bound writer 的拒绝;shell 文本不能制造它。host 不补写 Vision 或 Stride 的任何语义字段。
  3. _handle_semantic_spend 要求完全匹配 writer 返回的原结算命令,随后核对 settled-skip、一次扣额及下一轮原义务不再挂起。新任务创建、status0 或只写了 JSON 都不足以通过。
  4. _standalone_cli 防止把 shell 前缀丢掉后仅执行 CLI 后缀。组合草稿走既有 VisionShellHost,原始输入和 authority store 受 OS 隔离保护,CLI 回调仍只允许原有有界操作。新加入的几个状态字段只是实际 writer、执行和恢复的局部观察,没有建立第二套持久化真相。

规范依据为已验收的 Goal Vision/Replan contract、同轮选择与恢复 和 required-work-context。本 head 对应:ownership-boundary、stride-v2、replan-ack-freshness、current-capture 均 implemented;实时模型、安装后采用及科学收益没有被这些测试覆盖。测试脚本从实际包读取当前引用,独立编写三轴 reason 和 minimum evidence,并验证其真实持久化;未用主实现的默认 decision 代替作者决策。

对主干的风险 / Risks

最危险的路径是把 shell 里的“成功/恢复”文字当成权限,或把 successor 的存在当成原轮结算。实际源码保留 fixed executor、native writer 和 sandbox 三个不同责任边界;反例验证 foreign capture、错误 SHA、外部草稿、缺失或错误 v2 引用/字段、错误 spend Turn、未 spend、伪造 recovery 都不能通过。组合实验变更 basis 时,真实拒绝后重新读取,并把“仍待下一轮执行”的事实写入新决策,原轮只扣一次;没有仅替换 context id 蒙混过关。

独立验证:PASS — 当前 base a01306337232 与 head 32fba35023c3 使用同一完整 head oracle、相同 Python3.14.8 依赖及各自实际生产源码:base 130 passed / 51 failed,head 181 passed / 0 failed / 0 skipped。对早先 e726 的161/7结果单独保留,未拿来证明新 head。PASS — 仓库当前 CI 的 Ruff 命令和 python -m mypy(17配置文件)本地执行通过。PASS — exact-base premerge 退出0,direct/catalog/risk 检查执行完成,但保留一个 gate 标记的 inherited maintainability advisory。UNVERIFIED — 作者报告的全仓122 Ruff及扩展 mypy4706错误未在本轮独立归因,不能说全仓静态检查通过;exact-scope quality hold 也没有被本评审解除。远端 CI 按当前策略未查询。

语义与 CI 对齐

系统指令由“不得创建 Todo/组合命令”改为“OS 隔离下编写决策、执行有界 successor 或直接结果并结算”,属于已披露的 intentional change。它恢复已有原生合同要求的能力,不是压缩文字或扩大生产权限。逐项检查了 actor、触发、先读证据、决策作者、范围、时序、停止和预算;真实反例区分了丢失 spend、伪造 recovery 和合法恢复。现有术语复用,新增 failure/观察名留在本地 qualification owner;diff-scoped semantic 检查通过。Linux bubblewrap、真实模型和安装状态没有从 macOS 脚本结果推断。

我的整体评价 / Verdict

APPROVE:这是范围成立、能独立验收的内部资格增量。long_horizon=improved 指资格工具能检验真实决策与后续采用,user_experience=improved 指维护者得到完整流程和正确失败边界;二者均不代表已量得真实模型或长程净收益。代码增长主要来自原生正反例及独立脚本决策,复用 shell/reader/typed writer 的成本合理;进一步合并不同预算的两个接受器会扩大本次范围。

该结论仅对应 32fba35023c37b164d2d3ebfb038fb450c345c5b,不解除 quality/merge readiness 的单独 hold。由于 GitHub author-owned,发布 COMMENTED 承载完整 approval conclusion,不作形式自批或合并。

English verdict: APPROVE this exact-head qualification repair; quality/readiness holds and live-model adoption remain separate.

@huangruiteng
huangruiteng merged commit e4e309b into main Nov 4, 2026
16 of 37 checks passed
@huangruiteng
huangruiteng deleted the codex/native-reader-qualification-20261103-185749 branch November 4, 2026 09:53
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