Merge pull request 'Route CLI agents through a five-candidate chain with Codex last' (#648) from feature/cli-agent-fallback-chain into main
This commit was merged in pull request #648.
This commit is contained in:
@@ -0,0 +1,410 @@
|
||||
# feature/cli-agent-fallback-chain 任务卡
|
||||
|
||||
任务主记录：PR #648 https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/648；状态：已完成（合入前闭合）；owner：weichen
|
||||
|
||||
## 基线与授权
|
||||
|
||||
- 权威仓：ssh://git@git-ssh.u1680832.nyat.app:31411/weichen/Agent-System-Dev.git；目标分支：main；R0（initial_base_sha）= d2035c76dc1cb15e01d2c184af5155d9d773cd9f
|
||||
- 工作区：/home/weichen/projects/Agent-System-Dev-wt-feature-cli-agent-fallback-chain（worktree）；分支：feature/cli-agent-fallback-chain
|
||||
- 分支类型：standalone；root_target：main；immediate_target：main；accepting_requirements：false
|
||||
- 需求分流：verdict=NEW；selected_initiative=无；requirement_sha256=8817d4906061c95f5116cecb7e6b185dc6882b638ea71d2dde2db6e437903610；triage_receipt=/tmp/cli-fallback-chain-triage.json；receipt_sha256=555d302ea9cc489bc4b9ef51c0c5857332df08494cd57267646f93c1eabfaf7b
|
||||
|
||||
- 授权与交付终点：用户 2026-10-20 要求修改执行规范：CLI Agent 安全失败后不询问用户、自动换下一候选；候选为 cursor(auto)、agy(Gemini 3.8 Flash)、pi(GLM-5.3-flash)、pi(MiniMax-M3)，前三类顺序不限，Codex(GPT-6.1-Sol) 必须最后；每候选 3 次，全部失败后暂停询问是否重试。授权范围内实施、验证、Review、PR 合入 Dev main 与安全收口。不改 DM 控制器、不部署、不发布版本、不改分支保护。
|
||||
- 交付模式：goal-first（目标、范围和交付终点一次确认；范围内连续推进）
|
||||
- 实施执行：agent-per-unit（配置：AGENT-EXECUTION.md）
|
||||
- 合入执行：agent（已授权交付范围内，Review 通过、冲突解决且当前 HEAD 的 CI 通过后合入）
|
||||
- 人工决策点：仅限目标/范围/验收变更、重大取舍、高后果操作或无法自动判定的业务验收
|
||||
- 当前阶段：实施与自检；当前增量：I1（AGENT-EXECUTION.md 候选链 + 规范文字）
|
||||
- 流程依据：仓库根目录 policy/delivery.md（归档后仍按仓库根目录定位）
|
||||
|
||||
## 目标与非目标
|
||||
|
||||
目标：`AGENT-EXECUTION.md` 的四个角色候选均为 cursor(`auto`)、antigravity(`gemini-3.8-flash-high`)、pi-glm(`zai-coding-cn/glm-5.3-flash`)、pi(`minimax-cn/MiniMax-M3`)，codex(`gpt-6.1-sol`) 固定为最后候选；去掉 `emergency_profile`，`max_attempts_per_profile: 3` 对含 Codex 在内的每个候选生效。`policy/delivery.md`、`policy/governance.md`、`policy/tool-adaptation-matrix.md` 同步：安全可恢复失败自动换候选、不询问用户；Codex 之外的候选顺序可按角色调整但 Codex 必须最后；全部安全耗尽后 host 暂停并询问用户是否重试，仍不代写。
|
||||
|
||||
验收：`make agent-exec-validate` 通过；文档与机器块一致；PR HEAD 完整 CI 通过。
|
||||
|
||||
非目标：不改 DM 控制器（不实现运行时随机顺序；“顺序不限”由声明顺序满足）；fail-stop 终态（`failed-unknown` 等）语义不变；不改 `deps/development-guidelines`。
|
||||
|
||||
## Agent 实施收据
|
||||
|
||||
路由与 fail-stop 规则见根目录 AGENT-EXECUTION.md 与 policy/delivery.md；每次尝试一行，原始日志留在源码外收据路径。
|
||||
|
||||
| 单元 ID | 预期范围 | 配置摘要 | 角色 | 候选顺序 | attempt | CLI/模型 | 终态 | transport | fallback | 源码外收据路径 |
|
||||
|---|---|---|---|---|---|---|---|---|---|---|
|
||||
| dev-cli-agent-fallback-chain | `AGENT-EXECUTION.md`、`policy/{delivery,governance,tool-adaptation-matrix}.md` | config_digest=d2e3574ebf5a…（run 时 AGENT-EXECUTION.md 为 R0 版本） | implementation | [cursor, antigravity, pi] | 1 | cursor-agent-stable / auto | completed (success) | refs/agent-exec/68343647…/536ff962e681 → 8e21b66db4606c20a1d7de4f1293fbcd61780658 | 否 | /tmp/cli-fallback-chain-receipt.json（单元包 /tmp/cli-fallback-chain-unit.json） |
|
||||
|
||||
## 关联方向与规划
|
||||
|
||||
- 适用状态：不适用（用户直接提出的执行路由调整，无对应规划条目）
|
||||
- 主记录路径/版本：不适用
|
||||
- 对应里程碑：不适用
|
||||
|
||||
## 需求分析
|
||||
|
||||
| ID | 描述 | 项目符合度及依据 | 优先级 | 验收条件 | 依赖 | 结论 |
|
||||
|---|---|---|---|---|---|---|
|
||||
| R1 | 五个候选（含第二个 PI 档与 Codex）各 3 次、Codex 最后、全部失败暂停询问 | 符合：控制器已按声明顺序对 `unavailable`/`failed-clean` 自动续跑；模型 ID 经本机冒烟（agy `gemini-3.8-flash-high`、pi `zai-coding-cn/glm-5.3-flash`、codex `gpt-6.1-sol` 均回 OK，SELF） | P2 | validate 通过；文档一致；CI 通过 | 无 | 接受 |
|
||||
|
||||
## 方案与计划
|
||||
|
||||
- 方案引用：纯配置：Codex 从应急档改为各角色最后一个正常候选（校验器禁止应急档进入普通角色列表，且应急档只跑 1 次，故不保留 `emergency_profile`）；新增 `pi-glm` 档
|
||||
- 实施计划引用：I1 / R1：单一 Agent 单元改 `AGENT-EXECUTION.md` 与三份 policy 文本
|
||||
- 测试计划引用：R1：`make agent-exec-validate`；PR HEAD 完整 CI
|
||||
|
||||
## 阶段记录
|
||||
|
||||
| 阶段 | 对象版本 | 状态 | 决策/执行者 | 时间 | 依据 |
|
||||
|---|---|---|---|---|---|
|
||||
| 需求拆解 | d2035c7 | 已完成 | host | 2026-10-20 | 用户直接请求 |
|
||||
| 需求评估 | d2035c7 | 已完成 | host | 2026-10-20 | R1 接受 |
|
||||
| 需求表确认 | d2035c7 | 跳过 | — | 2026-10-20 | 用户请求已明确目标与验收，无取舍 |
|
||||
| 方案设计 | 890313e | 已完成 | host | 2026-10-20 | 本卡方案与计划段 |
|
||||
| 实施计划 | 890313e | 已完成 | host | 2026-10-20 | 本卡方案与计划段 |
|
||||
| 实施与自检 | 8e21b66 | 已完成 | cursor-agent-stable | 2026-10-20 | Agent 实施收据表 |
|
||||
| 正式测试与验收 | 8e21b66 | 已完成（SELF；GATE 待 CI） | host | 2026-10-20 | 证据表 |
|
||||
| 代码 Review | 8e21b66 | PASS | host 主模型 | 2026-10-20 | 合入与清理段 |
|
||||
| 合入 | 待定 | 待执行 | — | — | — |
|
||||
| 合入核验与收口 | 待定 | 待执行 | — | — | — |
|
||||
|
||||
## 探索试验与迭代
|
||||
|
||||
| 增量/试验 | 假设 | 范围 | 判断和停止条件 | 授权/决策依据 | 结果 | 变更影响 | 需重审补测 |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| I1 | 纯配置即可实现五候选链、Codex 最后、每候选 3 次 | AGENT-EXECUTION.md + 3 份 policy | validate 与 CI 通过即停 | 用户直接请求 | 三个新模型 ID 冒烟回 OK（SELF）；validate PASS | 全部角色路由 | 否 |
|
||||
|
||||
## 同步记录
|
||||
|
||||
| 节点 | sync_base_sha | tested_head_sha | checked_at |
|
||||
|---|---|---|---|
|
||||
| 启动 | d2035c76dc1cb15e01d2c184af5155d9d773cd9f | d2035c76dc1cb15e01d2c184af5155d9d773cd9f | 2026-10-20T05:56:50Z |
|
||||
|
||||
## 证据（Evidence）
|
||||
|
||||
<!-- CMD="<命令>" make evidence 写入；手抄/转写输出视为无效证据（AGENTS.md 证据与验证门禁）。 -->
|
||||
| 时间(UTC) | 命令 | 被测HEAD | exit | 来源 | sha256(16) |
|
||||
|---|---|---|---|---|---|
|
||||
|
||||
## 交付调度
|
||||
|
||||
- 调度状态：窗口已领取；调度记录：#518 comment 8226（mq-dev-20261020-cli-agent-fallback-chain-01）
|
||||
- entry_id：无；attempt_id：无；窗口执行者：无
|
||||
- 固定候选：无（base/head、组件与相关配置引用实际尝试）
|
||||
- 调度依据：policy/delivery.md#合入调度
|
||||
- 固定后证据：源码外 RECEIPT；实际结果后按授权原样导入和闭合
|
||||
|
||||
## 结果与验证
|
||||
|
||||
- 结果：四个角色候选链为 cursor(auto) → antigravity(`gemini-3.8-flash-high`) → pi-glm(`zai-coding-cn/glm-5.3-flash`) → pi(`minimax-cn/MiniMax-M3`) → codex(`gpt-6.1-sol`)（test/review 前四项顺序不同，Codex 均最后），每候选最多 3 次；去掉 `emergency_profile`；policy 三份文本同步“自动换候选不询问、全部耗尽暂停询问是否重试”。
|
||||
- 验证：`make agent-exec-validate` PASS；`make test-governance` PASS（513 tests，skipped=18）；`make task-sync` PASS；三个新模型 ID 冒烟 PASS（SELF，未入证据表）；PR HEAD 完整 CI 待 GATE。
|
||||
- 影响与剩余项：仅影响 Agent 执行路由。运行时随机顺序未实现（非目标，声明顺序满足“顺序不限、Codex 最后”）；`failed-unknown` 等 fail-stop 仍立即停止、不换候选。
|
||||
|
||||
## 规划进展与下一步
|
||||
|
||||
- 本次推进/剩余：R1 完成，无剩余
|
||||
- 首选下一任务：无（独立小改动）
|
||||
- 推荐依据：不适用
|
||||
- 前置条件/待确认：无
|
||||
- 预期产物/验收条件：不适用
|
||||
- 重复任务核对：远端分流 NEW（唯一候选 rdm-two-trees-followup 无关）
|
||||
- 启动授权：未授权（建议不自动启动新任务，仍须明确授权）
|
||||
|
||||
## 合入与清理
|
||||
|
||||
- Review 记录：host 主模型（未撰写实施单元；平台账号 weichen）审阅 890313e..8e21b66 实际 diff（AGENT-EXECUTION.md 机器块与说明、delivery/governance/tool-adaptation-matrix 指定段落），重放 `make agent-exec-validate`；结论 PASS，无阻塞项（非阻塞：AGENT-EXECUTION.md 一行超过 78 列）。
|
||||
- 冲突记录：窗口内 `make task-sync` 合入 main f1866dc（changed=1），无冲突；main 侧对 AGENT-EXECUTION.md 仅在 cursor 档加注释，与本改动正交；合并后重跑 `make agent-exec-validate` PASS。
|
||||
- CI 记录：NOT_RUN（当前 HEAD 完整 SHA、全部必需检查、运行链接、执行身份及 GATE 结果）
|
||||
- 合入记录：NOT_RUN（交付授权范围、PR、被核验 HEAD、合入 SHA、目标分支及内容核验）
|
||||
- 清理记录：NOT_RUN（授权依据、写者退出确认、worktree/分支/任务卡处置）
|
||||
|
||||
<!-- Local receipt: SELF. Digests detect corruption; they do not authenticate a reviewer or CI. -->
|
||||
```json
|
||||
{
|
||||
"summary_schema": 1,
|
||||
"source": "SELF",
|
||||
"timestamp": "2026-10-20T05:55:50.540864+00:00",
|
||||
"command": "make precheck",
|
||||
"exit_code": 0,
|
||||
"cwd": "/home/weichen/projects/Agent-System-Dev",
|
||||
"before_head": "d2035c76dc1cb15e01d2c184af5155d9d773cd9f",
|
||||
"after_head": "d2035c76dc1cb15e01d2c184af5155d9d773cd9f",
|
||||
"branch": "main",
|
||||
"target_branch": "main",
|
||||
"target_head": "d2035c76dc1cb15e01d2c184af5155d9d773cd9f",
|
||||
"root_target": "main",
|
||||
"immediate_target": "main",
|
||||
"before_tracked_diff_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
||||
"after_tracked_diff_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
||||
"output_tail": [
|
||||
"make[1]: Entering directory '/home/weichen/projects/Agent-System-Dev'",
|
||||
"[repo] branch=main head=d2035c76dc",
|
||||
"[remote] origin/main=d2035c76dc ahead=0 behind=0",
|
||||
"[tree] clean submodules_drift=0 uninit=0",
|
||||
"[worktrees] linked=7",
|
||||
"[initiatives] local cards (not authoritative): none",
|
||||
"[hooks] core.hooksPath=scripts/hooks（pre-commit/post-merge 实际接线）",
|
||||
"[facts] policy/facts.md 6 条事实均在有效期内",
|
||||
"[required-reading] core/baseline.md, workflows/delivery.md §1, policy/delivery.md",
|
||||
"[R0] d2035c76dc（完整：d2035c76dc1cb15e01d2c184af5155d9d773cd9f）",
|
||||
"[worktree] before-sync: recursive component checks passed",
|
||||
"[verdict] READY — 保留本次 precheck receipt 后建任务工作区：PRECHECK_RECEIPT=/tmp/task-precheck.json make task-start NAME=feature/your-branch",
|
||||
"make[1]: Leaving directory '/home/weichen/projects/Agent-System-Dev'"
|
||||
],
|
||||
"output_sha256": "ecc7f16b6bcabae29ac639e9d5d31ab0bc39f85e0fe0b51449d7b69412ba2d08",
|
||||
"receipt_sha256": "a8789614c5e3adf44db1e46a6fee98cfabea7b7e79708756d63c4aa756359b79",
|
||||
"receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/a8789614c5e3adf44db1e46a6fee98cfabea7b7e79708756d63c4aa756359b79.json"
|
||||
}
|
||||
```
|
||||
|
||||
<!-- Local receipt: SELF. Digests detect corruption; they do not authenticate a reviewer or CI. -->
|
||||
```json
|
||||
{
|
||||
"summary_schema": 1,
|
||||
"source": "SELF",
|
||||
"timestamp": "2026-10-20T06:00:53.614147+00:00",
|
||||
"command": "make agent-exec-validate",
|
||||
"exit_code": 0,
|
||||
"cwd": "/home/weichen/projects/Agent-System-Dev-wt-feature-cli-agent-fallback-chain",
|
||||
"before_head": "8e21b66db4606c20a1d7de4f1293fbcd61780658",
|
||||
"after_head": "8e21b66db4606c20a1d7de4f1293fbcd61780658",
|
||||
"branch": "feature/cli-agent-fallback-chain",
|
||||
"target_branch": "main",
|
||||
"target_head": "d2035c76dc1cb15e01d2c184af5155d9d773cd9f",
|
||||
"root_target": "main",
|
||||
"immediate_target": "main",
|
||||
"before_tracked_diff_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
||||
"after_tracked_diff_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
||||
"output_tail": [
|
||||
"make[1]: Entering directory '/home/weichen/projects/Agent-System-Dev-wt-feature-cli-agent-fallback-chain'",
|
||||
"scripts/agent-exec validate --repo .",
|
||||
"validate: ok",
|
||||
"make[1]: Leaving directory '/home/weichen/projects/Agent-System-Dev-wt-feature-cli-agent-fallback-chain'"
|
||||
],
|
||||
"output_sha256": "74357235852380ff3b7cbcb532b030dc924e8d11a6b2e39dfcb729717e460660",
|
||||
"receipt_sha256": "1f3ed60af7d5c96fd19ba0b2f89142237b61597e30e7c9578ec20b8c6bfb60f5",
|
||||
"receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/1f3ed60af7d5c96fd19ba0b2f89142237b61597e30e7c9578ec20b8c6bfb60f5.json"
|
||||
}
|
||||
```
|
||||
|
||||
<!-- Local receipt: SELF. Digests detect corruption; they do not authenticate a reviewer or CI. -->
|
||||
```json
|
||||
{
|
||||
"summary_schema": 1,
|
||||
"source": "SELF",
|
||||
"timestamp": "2026-10-20T06:01:05.726907+00:00",
|
||||
"command": "make task-sync",
|
||||
"exit_code": 0,
|
||||
"cwd": "/home/weichen/projects/Agent-System-Dev-wt-feature-cli-agent-fallback-chain",
|
||||
"before_head": "95aba5d68d68f1e3f35887a93aec41b464638a95",
|
||||
"after_head": "95aba5d68d68f1e3f35887a93aec41b464638a95",
|
||||
"branch": "feature/cli-agent-fallback-chain",
|
||||
"target_branch": "main",
|
||||
"target_head": "d2035c76dc1cb15e01d2c184af5155d9d773cd9f",
|
||||
"root_target": "main",
|
||||
"immediate_target": "main",
|
||||
"before_tracked_diff_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
||||
"after_tracked_diff_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
||||
"output_tail": [
|
||||
"make[1]: Entering directory '/home/weichen/projects/Agent-System-Dev-wt-feature-cli-agent-fallback-chain'",
|
||||
"[worktree] before-sync: recursive component checks passed",
|
||||
"[worktree] before-update: recursive component checks passed",
|
||||
"[worktree] materialize: recursive component checks passed",
|
||||
"[worktree] after-sync: recursive component checks passed",
|
||||
"[evidence] WARN JSON receipt line 120: recorded HEAD predates non-card changes ——关键检查须重跑并以 make evidence 重新写入",
|
||||
"[synced] sync_base=d2035c76dc1cb15e01d2c184af5155d9d773cd9f tested_head=95aba5d68d68f1e3f35887a93aec41b464638a95 checked_at=2026-10-20T06:01:57Z changed=0 sync_target=main",
|
||||
"[next] 跑正式验收（make test 等），证据写入任务卡",
|
||||
"make[1]: Leaving directory '/home/weichen/projects/Agent-System-Dev-wt-feature-cli-agent-fallback-chain'"
|
||||
],
|
||||
"output_sha256": "e797ab5e6a3e9bd075c44fdfe89f72e36a3e2f2fa892e6194501f7c88f46ceb1",
|
||||
"receipt_sha256": "d05e26eda35110298bb7721e35872f95cdc6c62964c0bf8a84e6db0f06e07775",
|
||||
"receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/d05e26eda35110298bb7721e35872f95cdc6c62964c0bf8a84e6db0f06e07775.json"
|
||||
}
|
||||
```
|
||||
|
||||
<!-- Local receipt: SELF. Digests detect corruption; they do not authenticate a reviewer or CI. -->
|
||||
```json
|
||||
{
|
||||
"summary_schema": 1,
|
||||
"source": "SELF",
|
||||
"timestamp": "2026-10-20T06:04:41.162206+00:00",
|
||||
"command": "make task-sync",
|
||||
"exit_code": 0,
|
||||
"cwd": "/home/weichen/projects/Agent-System-Dev-wt-feature-cli-agent-fallback-chain",
|
||||
"before_head": "c41e773d1e11a052ff53b32d493a3fa3e025ea99",
|
||||
"after_head": "c41e773d1e11a052ff53b32d493a3fa3e025ea99",
|
||||
"branch": "feature/cli-agent-fallback-chain",
|
||||
"target_branch": "main",
|
||||
"target_head": "d2035c76dc1cb15e01d2c184af5155d9d773cd9f",
|
||||
"root_target": "main",
|
||||
"immediate_target": "main",
|
||||
"before_tracked_diff_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
||||
"after_tracked_diff_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
||||
"output_tail": [
|
||||
"make[1]: Entering directory '/home/weichen/projects/Agent-System-Dev-wt-feature-cli-agent-fallback-chain'",
|
||||
"[worktree] before-sync: recursive component checks passed",
|
||||
"[worktree] before-update: recursive component checks passed",
|
||||
"[worktree] materialize: recursive component checks passed",
|
||||
"[worktree] after-sync: recursive component checks passed",
|
||||
"[evidence] WARN JSON receipt line 120: recorded HEAD predates non-card changes ——关键检查须重跑并以 make evidence 重新写入",
|
||||
"[synced] sync_base=d2035c76dc1cb15e01d2c184af5155d9d773cd9f tested_head=c41e773d1e11a052ff53b32d493a3fa3e025ea99 checked_at=2026-10-20T06:05:34Z changed=0 sync_target=main",
|
||||
"[next] 跑正式验收（make test 等），证据写入任务卡",
|
||||
"make[1]: Leaving directory '/home/weichen/projects/Agent-System-Dev-wt-feature-cli-agent-fallback-chain'"
|
||||
],
|
||||
"output_sha256": "40878f3432df9e7aa449f4304ca79a36a9f2c9d3253e229481283dd119efc992",
|
||||
"receipt_sha256": "cf538efd2a1d13e0f740447675779b37e3ae0db15fa78cc6553856ac2dbb6cc1",
|
||||
"receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/cf538efd2a1d13e0f740447675779b37e3ae0db15fa78cc6553856ac2dbb6cc1.json"
|
||||
}
|
||||
```
|
||||
|
||||
<!-- Local receipt: SELF. Digests detect corruption; they do not authenticate a reviewer or CI. -->
|
||||
```json
|
||||
{
|
||||
"summary_schema": 1,
|
||||
"source": "SELF",
|
||||
"timestamp": "2026-10-20T06:06:03.531305+00:00",
|
||||
"command": "make task-sync",
|
||||
"exit_code": 0,
|
||||
"cwd": "/home/weichen/projects/Agent-System-Dev-wt-feature-cli-agent-fallback-chain",
|
||||
"before_head": "3a6ffb97ad0cab5c215f684f27108dbd92f23129",
|
||||
"after_head": "3a6ffb97ad0cab5c215f684f27108dbd92f23129",
|
||||
"branch": "feature/cli-agent-fallback-chain",
|
||||
"target_branch": "main",
|
||||
"target_head": "d2035c76dc1cb15e01d2c184af5155d9d773cd9f",
|
||||
"root_target": "main",
|
||||
"immediate_target": "main",
|
||||
"before_tracked_diff_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
||||
"after_tracked_diff_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
||||
"output_tail": [
|
||||
"make[1]: Entering directory '/home/weichen/projects/Agent-System-Dev-wt-feature-cli-agent-fallback-chain'",
|
||||
"[worktree] before-sync: recursive component checks passed",
|
||||
"[worktree] before-update: recursive component checks passed",
|
||||
"[worktree] materialize: recursive component checks passed",
|
||||
"[worktree] after-sync: recursive component checks passed",
|
||||
"[evidence] WARN JSON receipt line 120: recorded HEAD predates non-card changes ——关键检查须重跑并以 make evidence 重新写入",
|
||||
"[synced] sync_base=d2035c76dc1cb15e01d2c184af5155d9d773cd9f tested_head=3a6ffb97ad0cab5c215f684f27108dbd92f23129 checked_at=2026-10-20T06:06:49Z changed=0 sync_target=main",
|
||||
"[next] 跑正式验收（make test 等），证据写入任务卡",
|
||||
"make[1]: Leaving directory '/home/weichen/projects/Agent-System-Dev-wt-feature-cli-agent-fallback-chain'"
|
||||
],
|
||||
"output_sha256": "1be7bf73418483205369a97f0b90f7ff7a2709effd5ca44875e59f6ff1b2d955",
|
||||
"receipt_sha256": "2756940470feebd40744bd42504690f19dfeebd9d76cca06369b57e36fe7caa3",
|
||||
"receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/2756940470feebd40744bd42504690f19dfeebd9d76cca06369b57e36fe7caa3.json"
|
||||
}
|
||||
```
|
||||
|
||||
<!-- Local receipt: SELF. Digests detect corruption; they do not authenticate a reviewer or CI. -->
|
||||
```json
|
||||
{
|
||||
"summary_schema": 1,
|
||||
"source": "SELF",
|
||||
"timestamp": "2026-10-20T06:08:38.659173+00:00",
|
||||
"command": "make test-governance",
|
||||
"exit_code": 0,
|
||||
"cwd": "/home/weichen/projects/Agent-System-Dev-wt-feature-cli-agent-fallback-chain",
|
||||
"before_head": "286c3ab0c16fff6ead69a62f470977de4cec656e",
|
||||
"after_head": "286c3ab0c16fff6ead69a62f470977de4cec656e",
|
||||
"branch": "feature/cli-agent-fallback-chain",
|
||||
"target_branch": "main",
|
||||
"target_head": "d2035c76dc1cb15e01d2c184af5155d9d773cd9f",
|
||||
"root_target": "main",
|
||||
"immediate_target": "main",
|
||||
"before_tracked_diff_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
||||
"after_tracked_diff_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
||||
"output_tail": [
|
||||
"test_feature_missing_parent_is_allowed (test_write_guard.WriteGuardTests.test_feature_missing_parent_is_allowed) ... ok",
|
||||
"test_invalid_json_is_denied (test_write_guard.WriteGuardTests.test_invalid_json_is_denied) ... ok",
|
||||
"test_missing_parent_on_main_is_denied (test_write_guard.WriteGuardTests.test_missing_parent_on_main_is_denied) ... ok",
|
||||
"test_missing_unknown_and_malformed_write_input_are_denied (test_write_guard.WriteGuardTests.test_missing_unknown_and_malformed_write_input_are_denied) ... ok",
|
||||
"test_non_git_destination_is_explicitly_outside_scope (test_write_guard.WriteGuardTests.test_non_git_destination_is_explicitly_outside_scope) ... ok",
|
||||
"test_nonwrite_tools_are_outside_scope (test_write_guard.WriteGuardTests.test_nonwrite_tools_are_outside_scope) ... ok",
|
||||
"test_relative_path_uses_hook_cwd_not_process_cwd (test_write_guard.WriteGuardTests.test_relative_path_uses_hook_cwd_not_process_cwd) ... ok",
|
||||
"test_symlink_into_main_with_missing_parents_is_denied (test_write_guard.WriteGuardTests.test_symlink_into_main_with_missing_parents_is_denied) ... ok",
|
||||
"test_valid_multi_file_patch_on_feature_is_allowed (test_write_guard.WriteGuardTests.test_valid_multi_file_patch_on_feature_is_allowed) ... ok",
|
||||
"",
|
||||
"----------------------------------------------------------------------",
|
||||
"Ran 513 tests in 365.638s",
|
||||
"",
|
||||
"OK (skipped=18)",
|
||||
"make[1]: Leaving directory '/home/weichen/projects/Agent-System-Dev-wt-feature-cli-agent-fallback-chain'"
|
||||
],
|
||||
"output_sha256": "750f575e91446dc8480ec53ac70d500852145ae12a75d19ef96390baaf6d55a2",
|
||||
"receipt_sha256": "14ba55cc1c8585e2a24ef81e0f4edaf74277b83fb47d76fa7bd95dda815cceec",
|
||||
"receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/14ba55cc1c8585e2a24ef81e0f4edaf74277b83fb47d76fa7bd95dda815cceec.json"
|
||||
}
|
||||
```
|
||||
| 同步（记录前对象） | f1866dc3bb4537ac6446fdd26e696cb636b543ef | 16913620d8cbf214bf81792c5ff03eaee94752cd | 2026-10-20T07:48:20Z |
|
||||
|
||||
<!-- Local receipt: SELF. Digests detect corruption; they do not authenticate a reviewer or CI. -->
|
||||
```json
|
||||
{
|
||||
"summary_schema": 1,
|
||||
"source": "SELF",
|
||||
"timestamp": "2026-10-20T07:47:26.429534+00:00",
|
||||
"command": "make task-sync",
|
||||
"exit_code": 0,
|
||||
"cwd": "/home/weichen/projects/Agent-System-Dev-wt-feature-cli-agent-fallback-chain",
|
||||
"before_head": "6bf1000547cc533b914dcb79ad37573b7d33cf61",
|
||||
"after_head": "f60effc6326ae8847cb1a39bef469c83d812c385",
|
||||
"branch": "feature/cli-agent-fallback-chain",
|
||||
"target_branch": "main",
|
||||
"target_head": "f1866dc3bb4537ac6446fdd26e696cb636b543ef",
|
||||
"root_target": "main",
|
||||
"immediate_target": "main",
|
||||
"before_tracked_diff_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
||||
"after_tracked_diff_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
||||
"output_tail": [
|
||||
" create mode 100644 docker/verify-env.sh",
|
||||
" create mode 100644 docs/superpowers/specs/2026-10-20-fast-slow-o2-i1-review.md",
|
||||
"[worktree] before-update: recursive component checks passed",
|
||||
"[worktree] materialize: recursive component checks passed",
|
||||
"[worktree] after-sync: recursive component checks passed",
|
||||
"admit: ok",
|
||||
"[evidence] WARN JSON receipt line 120: recorded HEAD predates non-card changes ——关键检查须重跑并以 make evidence 重新写入",
|
||||
"[evidence] WARN JSON receipt line 159: recorded HEAD predates non-card changes ——关键检查须重跑并以 make evidence 重新写入",
|
||||
"[evidence] WARN JSON receipt line 189: recorded HEAD predates non-card changes ——关键检查须重跑并以 make evidence 重新写入",
|
||||
"[evidence] WARN JSON receipt line 224: recorded HEAD predates non-card changes ——关键检查须重跑并以 make evidence 重新写入",
|
||||
"[evidence] WARN JSON receipt line 259: recorded HEAD predates non-card changes ——关键检查须重跑并以 make evidence 重新写入",
|
||||
"[evidence] WARN JSON receipt line 294: recorded HEAD predates non-card changes ——关键检查须重跑并以 make evidence 重新写入",
|
||||
"[synced] sync_base=f1866dc3bb4537ac6446fdd26e696cb636b543ef tested_head=f60effc6326ae8847cb1a39bef469c83d812c385 checked_at=2026-10-20T07:48:20Z changed=1 sync_target=main",
|
||||
"[next] 跑正式验收（make test 等），证据写入任务卡",
|
||||
"make[1]: Leaving directory '/home/weichen/projects/Agent-System-Dev-wt-feature-cli-agent-fallback-chain'"
|
||||
],
|
||||
"output_sha256": "9671a18a5835bfbad2bade03cd21602d59eb40b92f070c258b186ecea7ae9a58",
|
||||
"receipt_sha256": "c4547470f11d63491ea2f2c4b23c6a46425e5362f37dd23d13f1770165e32057",
|
||||
"receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/c4547470f11d63491ea2f2c4b23c6a46425e5362f37dd23d13f1770165e32057.json"
|
||||
}
|
||||
```
|
||||
|
||||
<!-- Local receipt: SELF. Digests detect corruption; they do not authenticate a reviewer or CI. -->
|
||||
```json
|
||||
{
|
||||
"summary_schema": 1,
|
||||
"source": "SELF",
|
||||
"timestamp": "2026-10-20T07:48:38.505764+00:00",
|
||||
"command": "make agent-exec-validate",
|
||||
"exit_code": 0,
|
||||
"cwd": "/home/weichen/projects/Agent-System-Dev-wt-feature-cli-agent-fallback-chain",
|
||||
"before_head": "b90d3aaee9550271cb7c2acd200267f3605d6fca",
|
||||
"after_head": "b90d3aaee9550271cb7c2acd200267f3605d6fca",
|
||||
"branch": "feature/cli-agent-fallback-chain",
|
||||
"target_branch": "main",
|
||||
"target_head": "f1866dc3bb4537ac6446fdd26e696cb636b543ef",
|
||||
"root_target": "main",
|
||||
"immediate_target": "main",
|
||||
"before_tracked_diff_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
||||
"after_tracked_diff_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
||||
"output_tail": [
|
||||
"make[1]: Entering directory '/home/weichen/projects/Agent-System-Dev-wt-feature-cli-agent-fallback-chain'",
|
||||
"scripts/agent-exec validate --repo .",
|
||||
"validate: ok",
|
||||
"make[1]: Leaving directory '/home/weichen/projects/Agent-System-Dev-wt-feature-cli-agent-fallback-chain'"
|
||||
],
|
||||
"output_sha256": "74357235852380ff3b7cbcb532b030dc924e8d11a6b2e39dfcb729717e460660",
|
||||
"receipt_sha256": "8a2946c846a8e64c76222cefd05e91161131d1fae4d8b8412dd4e8d90c562fd7",
|
||||
"receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/8a2946c846a8e64c76222cefd05e91161131d1fae4d8b8412dd4e8d90c562fd7.json"
|
||||
}
|
||||
```
|
||||
|
||||
## 闭合记录（合入前折叠）
|
||||
|
||||
- 本卡在 PR #648（https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/648）合入前闭合并归档，随该 PR 一同合入。
|
||||
- 该 PR 的合并提交即本任务的落地记录。
|
||||
- 合入后无需回填，也无需单独的闭合 PR。
|
||||
+43
-34
@@ -7,20 +7,22 @@ parser accepts exactly one `agent-execution` fenced block.
|
||||
|
||||
U3's execution controller and U4's project wiring are integrated. This file is
|
||||
the execution-routing authority for implementation, repair, test, and review.
|
||||
Normal implementation, repair, and test routes stay Cursor, Antigravity
|
||||
(`agy`), and PI. Each of those profiles may be attempted up to
|
||||
`max_attempts_per_profile`, which is exactly 3 whenever `emergency_profile`
|
||||
is configured. Only after those candidates safely exhaust their attempts does
|
||||
the enabled emergency `codex` profile run once. Codex remains out of the three
|
||||
normal role lists and may also appear in review. `fallback_to_host` is
|
||||
`never`: the controller does not emit `host-fallback-authorized` and does not
|
||||
increment host fallback authorizations. Safe exhaustion without an emergency
|
||||
candidate ends `unavailable` or `blocked`, and that result does not authorize
|
||||
the host to write the unit. The legacy value `all-unavailable` remains
|
||||
parseable and likewise grants no host write authority. Cursor uses
|
||||
`cursor-agent-stable`. `model: auto` makes Cursor receive an explicit
|
||||
`--model auto`; the other CLIs omit the model flag and use their configured
|
||||
default. Any other value is passed to that CLI as its model selector. The
|
||||
Implementation, repair, test, and review all use the candidates Cursor,
|
||||
Antigravity (`agy`), PI with GLM (`pi-glm`), PI with MiniMax (`pi`), and
|
||||
Codex. Each candidate may be attempted up to `max_attempts_per_profile` (3)
|
||||
times on safe recoverable failures (`unavailable`, `failed-clean`); after that
|
||||
the controller moves to the next candidate automatically, and the host does
|
||||
not ask the user. The order of the non-Codex candidates may differ per role,
|
||||
but Codex must stay the last candidate in every role list. There is no
|
||||
`emergency_profile`. `fallback_to_host` is `never`: the controller does not
|
||||
emit `host-fallback-authorized` and does not increment host fallback
|
||||
authorizations. When every candidate is safely exhausted the run ends
|
||||
`unavailable` or `blocked`; the host pauses that unit and asks the user
|
||||
whether to retry, and does not write the unit. The legacy value
|
||||
`all-unavailable` remains parseable and likewise grants no host write
|
||||
authority. Cursor uses `cursor-agent-stable`. `model: auto` makes Cursor
|
||||
receive an explicit `--model auto`; the other CLIs omit the model flag and use
|
||||
their configured default. Any other value is passed to that CLI as its model selector. The
|
||||
`integration` block declares the host-exempt paths and the transport, admission,
|
||||
and cleanup entry points.
|
||||
|
||||
@@ -37,13 +39,12 @@ execution:
|
||||
summary_bytes: 16384
|
||||
raw_output_bytes: 10485760
|
||||
max_attempts_per_profile: 3
|
||||
emergency_profile: codex
|
||||
|
||||
roles:
|
||||
implementation: [cursor, antigravity, pi]
|
||||
repair: [cursor, antigravity, pi]
|
||||
test: [pi, antigravity, cursor]
|
||||
review: [pi, antigravity, cursor, codex]
|
||||
implementation: [cursor, antigravity, pi-glm, pi, codex]
|
||||
repair: [cursor, antigravity, pi-glm, pi, codex]
|
||||
test: [pi-glm, pi, antigravity, cursor, codex]
|
||||
review: [pi-glm, pi, antigravity, cursor, codex]
|
||||
|
||||
profiles:
|
||||
cursor:
|
||||
@@ -59,7 +60,13 @@ profiles:
|
||||
antigravity:
|
||||
adapter: antigravity
|
||||
executable: agy
|
||||
model: auto
|
||||
model: gemini-3.8-flash-high
|
||||
enabled: true
|
||||
|
||||
pi-glm:
|
||||
adapter: pi
|
||||
executable: pi
|
||||
model: zai-coding-cn/glm-5.3-flash
|
||||
enabled: true
|
||||
|
||||
pi:
|
||||
@@ -71,7 +78,7 @@ profiles:
|
||||
codex:
|
||||
adapter: codex
|
||||
executable: codex
|
||||
model: auto
|
||||
model: gpt-6.1-sol
|
||||
enabled: true
|
||||
|
||||
integration:
|
||||
@@ -96,23 +103,25 @@ section records only this project's choices.
|
||||
|
||||
- Planning, design and implementation plans: Codex or Claude when available,
|
||||
in the host or a fresh CLI session. This is a preference, not a routing role.
|
||||
- Bounded implementation, repair and test units: the existing normal
|
||||
candidates in the configured role order above. Requested models:
|
||||
- PI: `minimax-cn/MiniMax-M3`, passed as `--model provider/id`. PI
|
||||
actual events have reported `minimax-cn` / `MiniMax-M3` and the local
|
||||
offline catalog lists that profile; each run still records the effective
|
||||
model from that run's events.
|
||||
- Bounded implementation, repair, test and review units: the candidates in
|
||||
the configured role order above, with Codex last. Requested models:
|
||||
- Cursor: `auto`, passed explicitly as `--model auto` (Cursor Auto).
|
||||
- agy: Gemini 3.8 Flash is requested, but its exact selectable model ID and
|
||||
effective identity are `NOT_VERIFIED` (the `agy` models query needs a
|
||||
login that was not available). The profile therefore stays `model: auto`
|
||||
until an observed model ID exists; do not claim Gemini 3.8 Flash is active.
|
||||
- agy: `gemini-3.8-flash-high`. `agy models` listed it on 2026-10-20 and a
|
||||
one-line smoke run answered; the effective identity is still taken from
|
||||
each run's events.
|
||||
- PI GLM profile (`pi-glm`): `zai-coding-cn/glm-5.3-flash`, passed as
|
||||
`--model provider/id`.
|
||||
- PI MiniMax profile (`pi`): `minimax-cn/MiniMax-M3`, passed as
|
||||
`--model provider/id`. PI actual events have reported `minimax-cn` /
|
||||
`MiniMax-M3` and the local offline catalog lists that profile; each run
|
||||
still records the effective model from that run's events.
|
||||
- Codex: `gpt-6.1-sol`, always the last candidate.
|
||||
- Assigning a different candidate or model to a unit needs a concrete,
|
||||
task-specific reason recorded in the task record, and stays within the
|
||||
existing roles and candidate lists. It is not a silent permission or routing
|
||||
change. Role lists, attempt limits, timeouts, output limits, the single
|
||||
Codex emergency attempt, stage isolation and `fallback_to_host: never` are
|
||||
unchanged by these preferences.
|
||||
change. Role lists, attempt limits, timeouts, output limits, Codex as the
|
||||
last candidate, stage isolation and `fallback_to_host: never` are unchanged
|
||||
by these preferences.
|
||||
- A requested model is prompt/config intent. Only the model reported in a
|
||||
run's actual event envelope counts as effective; when the CLI does not report
|
||||
it, record `not-observable`. Unknown context capacity, a missing agy login
|
||||
|
||||
+11
-10
@@ -73,18 +73,19 @@
|
||||
[AGENT-EXECUTION.md](../AGENT-EXECUTION.md) 为唯一权威；按角色声明的候选顺序在新进程与
|
||||
隔离工作区中尝试外部 Agent。不得跨单元复用同一外部进程，也不得 resume 同一次尝试。
|
||||
|
||||
实施、修复与测试的正常候选只有 Cursor、Antigravity（`agy`）和 PI。每个候选对安全可恢复失败
|
||||
最多 3 次全新尝试：`unavailable`，或外部无副作用已被机制证明的 `failed-clean`。三次仍属这类失败后才进入
|
||||
下一候选。单元包的 `network=false` 与 `external_cost=false` 只是声明，不证明外部干净；当前没有强制的
|
||||
实施、修复、测试与 Review 的候选为 Cursor、Antigravity（`agy`）、PI（GLM 与 MiniMax 两个档）和
|
||||
Codex。每个候选对安全可恢复失败最多 3 次全新尝试：`unavailable`，或外部无副作用已被机制证明的
|
||||
`failed-clean`。三次仍属这类失败后由控制器自动进入下一候选，host 不为此询问用户。
|
||||
单元包的 `network=false` 与 `external_cost=false` 只是声明，不证明外部干净；当前没有强制的
|
||||
网络/外部费用隔离或可信对账，所以已启动的失败尝试即使私有克隆可精确恢复，也记为 `failed-unknown`
|
||||
并保留现场。三个正常候选都安全耗尽后，才允许一次全新的 Codex CLI 紧急尝试；这次不按每候选 3 次计算。
|
||||
紧急尝试若仍是安全可恢复失败，运行停在 `blocked`。host 不接过该单元继续撰写。
|
||||
并保留现场。
|
||||
|
||||
Codex 平时只用于规划、方案设计、实施计划，或独立 Review。执行配置没有单独的 plan 角色；
|
||||
上述规划与设计工作可以直接使用 Codex CLI。`review` 角色的候选可以包含 Codex，并按该角色自己的
|
||||
顺序和尝试上限执行。Codex 不出现在实施、修复、测试的正常候选里；这三个角色上的一次紧急尝试是唯一例外。
|
||||
Codex 之外的候选顺序可按角色在 [AGENT-EXECUTION.md](../AGENT-EXECUTION.md) 中调整，但 Codex
|
||||
必须是每个角色的最后一个候选，不设单次紧急尝试。全部候选安全耗尽后运行停在 `unavailable` 或
|
||||
`blocked`，host 暂停该单元并询问用户是否重试，不接过该单元继续撰写。Codex 另可直接用于规划、
|
||||
方案设计、实施计划（执行配置没有单独的 plan 角色）。
|
||||
|
||||
显式 fail-stop 立即停止整次运行，不重试、不换候选、不启动紧急尝试：`failed-unknown`、
|
||||
显式 fail-stop 立即停止整次运行，不重试、不换候选：`failed-unknown`、
|
||||
`scope-expansion`、`blocked`、`cancelled`、无效配置、未对账的 Git 状态与安全失败。总超时，
|
||||
以及 stdin/stdout/stderr 都没有活动的空闲超时，归入 `failed-unknown`。
|
||||
|
||||
@@ -123,7 +124,7 @@ host 可以直接编写并提交的豁免只有 `.task/**`、`docs/superpowers/s
|
||||
`docs/superpowers/plans/**`。除此之外，host 不直接撰写实施单元。
|
||||
|
||||
安全耗尽不发出 `host-fallback-authorized`，`host_fallback_authorizations` 保持为 0。
|
||||
未配置紧急候选时终态为 unavailable 或 blocked，不授权 host 撰写实施单元。现行
|
||||
安全耗尽的终态为 unavailable 或 blocked，不授权 host 撰写实施单元。现行
|
||||
[AGENT-EXECUTION.md](../AGENT-EXECUTION.md) 的 `fallback_to_host` 是 `never`。旧值
|
||||
`all-unavailable` 仍可解析，但同样不产生 host 撰写授权。已归档任务卡里的旧表述保持原样，
|
||||
不改写成现行规则。
|
||||
|
||||
@@ -11,12 +11,12 @@
|
||||
### Agent 实施收据与来源
|
||||
|
||||
每次外部实施尝试须在任务卡「Agent 实施收据」记录：配置摘要（`AGENT-EXECUTION.md` digest）、
|
||||
角色、声明候选顺序、attempt、CLI/模型、终态、transport、fallback（只表示该行是否为 Codex
|
||||
紧急尝试），以及源码外原始收据路径。初始生成状态为 `NOT_RUN`。原始事件流与超限输出保留在
|
||||
角色、声明候选顺序、attempt、CLI/模型、终态、transport、fallback（是否为应急尝试；现行配置无
|
||||
应急档，恒为否），以及源码外原始收据路径。初始生成状态为 `NOT_RUN`。原始事件流与超限输出保留在
|
||||
源码外；未知终态（`failed-unknown`）与 `scope-expansion` 的隔离工作区须保留待对账，不得静默丢弃。
|
||||
清理须有精确恢复或保留现场的可复核证据。
|
||||
|
||||
候选、尝试上限、Codex 紧急尝试、fallback、fail-stop、尝试结束条件，以及 transport/admit
|
||||
候选、尝试上限、fallback、fail-stop、尝试结束条件，以及 transport/admit
|
||||
与 host 豁免路径，以[迭代交付](delivery.md#agent-实施单元与主模型职责)为唯一权威。
|
||||
|
||||
## 启动与恢复
|
||||
|
||||
@@ -14,7 +14,7 @@
|
||||
| A5 回收 | 本地命令检查；写者退出须可证明，无法证明时才请求 owner 决策 | 登记根目录、锁/操作状态、父子仓与唯一文件、合入核验 | `tests/test_task.py` |
|
||||
| A6 秘密 | 本地脱敏及 CI 获取边界；权限与宿主隔离另验 | 命令/输出/摘要脱敏，凭据不持久写 Git 配置 | `tests/test_evidence.py`、`tests/test_ci_credentials.py` |
|
||||
| A7 证据 | 本地 SELF 收据；外部来源独立核验 | 首次捕获、完整脱敏输出/摘要、对象记录、原样导入 | `tests/test_evidence.py`；CI/审阅链接另核 |
|
||||
| A8 阶段记录与迭代 | goal-first + agent-per-unit（AGENT-EXECUTION.md）；模板默认连续执行，仅真实决策点需人工，没有全流程授权强制；实施/修复/测试仅 Cursor、agy、PI，每候选对安全可恢复失败最多 3 次全新尝试，全部安全耗尽后一次 Codex CLI 紧急尝试；Codex 平时仅规划、设计、计划或独立 Review；显式 fail-stop 立即停止；不限制推理时长、工具次数、规划方式或首次写文件时间；集成经成功 transport 的 agent-exec apply，或 pre-commit admit 精确内容来源；host 豁免仅为 .task/** 与 docs/superpowers/specs/**、plans/**；host 不直接实施；fallback_to_host 为 never；安全耗尽不发出 host-fallback-authorized，终态为 unavailable 或 blocked | policy/delivery.md、AGENT-EXECUTION.md；任务卡分别记录阶段状态、决策点、Agent 实施收据（配置摘要/角色/候选/attempt/CLI-模型/终态/transport/紧急尝试/源码外路径）、Review、冲突、当前 HEAD 的 CI 和合入；post-merge 默认仅提示 | `tests/test_task.py` 核对 goal-first/agent-per-unit 模板、正常路由、尝试上限、fail-stop、空闲超时与 apply/admit 来源表述，及钩子不自动写入；`scripts/agent-exec validate`（CI）与 parser·adapter·controller 假 CLI 契约（Development-Manager internal/agentexec 测试，经 deps/development-manager 钉住）为本地 SELF 强制行为；已安装 provider/model 身份待 U5，远端平台准入为 GATE；智能体核对授权范围、实施单元边界、Review、冲突及匹配 HEAD 的 CI/平台准入 |
|
||||
| A8 阶段记录与迭代 | goal-first + agent-per-unit（AGENT-EXECUTION.md）；模板默认连续执行，仅真实决策点需人工，没有全流程授权强制；实施/修复/测试/Review 候选为 Cursor、agy、PI（GLM、MiniMax）与最后的 Codex，每候选对安全可恢复失败最多 3 次全新尝试并自动换候选，全部安全耗尽后暂停询问用户是否重试；显式 fail-stop 立即停止；不限制推理时长、工具次数、规划方式或首次写文件时间；集成经成功 transport 的 agent-exec apply，或 pre-commit admit 精确内容来源；host 豁免仅为 .task/** 与 docs/superpowers/specs/**、plans/**；host 不直接实施；fallback_to_host 为 never；安全耗尽不发出 host-fallback-authorized，终态为 unavailable 或 blocked | policy/delivery.md、AGENT-EXECUTION.md；任务卡分别记录阶段状态、决策点、Agent 实施收据（配置摘要/角色/候选/attempt/CLI-模型/终态/transport/fallback/源码外路径）、Review、冲突、当前 HEAD 的 CI 和合入；post-merge 默认仅提示 | `tests/test_task.py` 核对 goal-first/agent-per-unit 模板、正常路由、尝试上限、fail-stop、空闲超时与 apply/admit 来源表述，及钩子不自动写入；`scripts/agent-exec validate`（CI）与 parser·adapter·controller 假 CLI 契约（Development-Manager internal/agentexec 测试，经 deps/development-manager 钉住）为本地 SELF 强制行为；已安装 provider/model 身份待 U5，远端平台准入为 GATE；智能体核对授权范围、实施单元边界、Review、冲突及匹配 HEAD 的 CI/平台准入 |
|
||||
| A9 长期方向与后续任务 | manual；模板不校验规划有效性或自动调度任务 | policy/delivery.md；PROJECT.md 提供规划入口，任务卡关联规划/里程碑并记录下一步建议 | `tests/test_task.py` 核对生成字段与未授权默认值；智能体核对当前规划、进展、重复任务和建议依据，新任务仍不自动获得授权 |
|
||||
| A10 交付窗口 | manual；无自动互斥或接管 | [合入调度](delivery.md#合入调度)与 #518：同一目标一个最终窗口，等待分支不追 main；轮到后同步、固定、验证并由智能体合入 | 每个实际 PR 核对窗口记录、精确 HEAD 三项 GATE、Review 和合入后 main；不要求额外试行或全写者审计 |
|
||||
| A11 固定后证据 | manual 选择源码外位置；工具捕获绝对未用路径/原始输出；无 OS 冻结 | policy/governance.md；RECEIPT 捕获，后续授权闭合再原样导入 | `tests/test_evidence.py` 固定对象、权限、覆盖拒绝、原样导入与幂等 |
|
||||
|
||||
Reference in New Issue
Block a user