Merge authoritative main into the task branch

Why: include the current integration baseline before verification. Evidence: fetched origin/main=adbef2f49c6c252a09449496afbdb6685201993b. Impact: integrate upstream changes without rewriting task history. Refs: task-sync
2026-10-20 08:46:38 +00:00
parent 0819e71cea adbef2f49c
commit b942e515f4
16 changed files with 1519 additions and 52 deletions
@@ -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。
@@ -0,0 +1,392 @@
+# feature/cursor-explicit-model-auto 任务卡
+
+任务主记录：PR #644 https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/644；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）= ac594c90e536cfb670e94680f045a6c8247a2513
+- 工作区：/home/weichen/projects/Agent-System-Dev-wt-feature-cursor-explicit-model-auto（worktree）；分支：feature/cursor-explicit-model-auto
+- 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=26514fc286b951bcd1dc272da658bb3a80a15f4ad1a0f0f6a575b43ccd8c5bfd；triage_receipt=/tmp/cursor-model-auto-triage.json；receipt_sha256=ae6f04fa5645ecbb8a67878709f9c97f8caa77e9f41ef4b6f5f76549bcf67a6b
+
+- 授权与交付终点：用户 2026-10-20 要求 cursor-agent 启动时加入 `--model auto`，并选定“只改 DM cursor 适配器 + Dev 升版本与说明”方案；授权范围内实施、验证、Review、PR 合入 Dev main 与安全收口。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（DM repin + AGENT-EXECUTION.md 说明）
+- 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：Dev 的 `scripts/agent-exec` 派发 cursor 候选时，argv 显式包含 `--model auto`。DM 侧已由 [Development-Manager PR #30](https://git-home.u1680832.nyat.app:30319/weichen/Development-Manager/pulls/30) 合入（merge `1e5ee55a2881dc9ed210ced48338c4d75697aa9c`：内置 cursor 适配器 auto 时传 `--model auto`，其他适配器不变）。本仓：`deps/development-manager` 从 `6c019595` 升到 `1e5ee55a`；`AGENT-EXECUTION.md` 说明改为 cursor 在 `model: auto` 时显式传 `--model auto`，其他 CLI 仍省略。
+
+验收：`scripts/agent-exec validate` 通过；DM adapters 测试在新 pin 通过；PR HEAD 完整 CI 通过。
+
+非目标：不改 profile/路由/尝试上限，不改 `deps/development-guidelines` 或其内嵌 DM pin，不改其他 CLI 的 auto 语义。
+
+## 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-cursor-explicit-auto-model-adopt | `deps/development-manager` gitlink + `AGENT-EXECUTION.md` 说明 | config_digest=ccf5b7c03ce4…（run 时 AGENT-EXECUTION.md blob e3c0b7f） | implementation | [cursor, antigravity, pi] | 1 | cursor-agent-stable 2026.10.14-0f9edde / auto（事件报告 `Auto`） | completed (success) | refs/agent-exec/1b5656f9…/ccc04e511e8a → 88f446531beb8702a4a95a41ce581e2d4323604d | 否 | /tmp/dev-cursor-model-auto-receipt.json（单元包 /tmp/dev-cursor-model-auto-unit.json） |
+| DM: agent-exec-cursor-explicit-auto-model | DM `internal/agentexec/adapters/{adapters,adapters_test}.go` | DM AGENT-EXECUTION.md config_digest=adeded0e9363… | implementation | [cursor, antigravity, pi] | 1 | cursor-agent-stable 2026.10.14-0f9edde / auto（事件报告 `Auto`） | completed (success) | DM refs/agent-exec/36405201…/9e8e5a55c9a5 → DM 9a565d65428c8acc02cf222fee1a7998a11de960 | 否 | /tmp/dm-cursor-model-auto-receipt.json |
+
+## 关联方向与规划
+
+- 适用状态：不适用（用户直接提出的执行器参数调整，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 | cursor-agent 启动显式带 `--model auto` | 符合：消除本机默认模型漂移；`cursor-agent-stable --list-models` 列出 `auto` | P2 | Dev pin 含 DM #30；AGENT-EXECUTION.md 说明一致；CI 通过 | DM #30（已合入） | 接受 |
+
+## 方案与计划
+
+- 方案引用：DM 适配器新增 `builtinSpec.autoModel`，仅 cursor 设 `"auto"`（DM #30）；Dev repin + 说明
+- 实施计划引用：I1 / R1：DM 单元 → DM PR #30 → Dev 单元（repin + 说明）
+- 测试计划引用：R1：DM adapters 表驱动测试（cursor auto 传 `--model auto`，其他适配器不传）；`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 | bef2032 | 已完成 | host | 2026-10-20 | 用户选定“只改 cursor 适配器”方案 |
+| 需求评估 | bef2032 | 已完成 | host | 2026-10-20 | R1 接受 |
+| 需求表确认 | bef2032 | 已完成 | 用户（AskQuestion 选择） | 2026-10-20 | 本卡授权段 |
+| 方案设计 | DM 9a565d6 | 已完成 | host | 2026-10-20 | DM #30 |
+| 实施计划 | bef2032 | 已完成 | host | 2026-10-20 | 本卡方案与计划段 |
+| 实施与自检 | 88f4465 | 已完成 | cursor-agent-stable（DM 与 Dev 各一单元） | 2026-10-20 | Agent 实施收据表 |
+| 正式测试与验收 | 2430123 | 已完成（SELF；GATE 待 CI） | host | 2026-10-20 | 证据表 |
+| 代码 Review | 88f4465 | 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 | cursor 显式 `--model auto` 可被 CLI 接受 | DM adapters + Dev pin/说明 | 测试与 CI 通过即停 | 用户选定方案 | `cursor-agent-stable -p --trust --model auto` 冒烟 success（SELF） | 仅 cursor argv | 否 |
+
+## 同步记录
+
+| 节点 | sync_base_sha | tested_head_sha | checked_at |
+|---|---|---|---|
+| 启动 | ac594c90e536cfb670e94680f045a6c8247a2513 | ac594c90e536cfb670e94680f045a6c8247a2513 | 2026-10-20T03:41:37Z |
+
+## 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 8141（mq-dev-20261020-cursor-explicit-model-auto-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：Dev 钉住 DM `1e5ee55a`（含 DM #30），`scripts/agent-exec` 派发 cursor 时 argv 显式带 `--model auto`；`AGENT-EXECUTION.md` 说明同步。其他 CLI 与机器配置块不变。
+- 验证：`make agent-exec-validate` PASS；新 pin 下 DM adapters 测试 PASS（证据表）；DM #30 CI success（GATE，DM b9627b8）；Dev 完整 CI 以 PR HEAD 为准。
+- 影响与剩余项：仅影响 cursor 候选启动参数。DM 卡 `.task/feature-cursor-explicit-model-auto.md` 状态已为“已完成（合入前闭合）”，因 DM pr-check 只认 `.task/` 顶层而未归档，留待 DM 下次闭合时归档。
+
+## 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，无后续规划）
+- 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 DM #30 diff（7c234e5..9a565d6，adapters 两文件）与 Dev diff（bef2032..88f4465：gitlink 6c01959→1e5ee55、AGENT-EXECUTION.md 两处说明、机器块未变），重放 `make agent-exec-validate` 与 adapters 测试；结论 PASS，无阻塞项。
+- 冲突记录：窗口内 `make task-sync` changed=0（sync_base ac594c90），无冲突；组件递归检查通过；折叠闭合遗留 IAM 卡（precheck [cards] 清零）仅 `.task/`。
+- 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": "2026-10-20T03:40:46.352366+00:00",
+  "command": "make precheck",
+  "exit_code": 0,
+  "cwd": "/home/weichen/projects/Agent-System-Dev",
+  "before_head": "ac594c90e536cfb670e94680f045a6c8247a2513",
+  "after_head": "ac594c90e536cfb670e94680f045a6c8247a2513",
+  "branch": "main",
+  "target_branch": "main",
+  "target_head": "ac594c90e536cfb670e94680f045a6c8247a2513",
+  "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=ac594c90e5",
+    "[remote] origin/main=ac594c90e5 ahead=0 behind=0",
+    "[tree]   clean submodules_drift=0 uninit=0",
+    "[worktrees] linked=8",
+    "[cards] 已合入未闭合任务卡:feature-iam-role-permission-linked-capabilities.md——make task-close 回填归档（主检出运行）",
+    "[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] ac594c90e5（完整：ac594c90e536cfb670e94680f045a6c8247a2513）",
+    "[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": "a8bd643e45829cc5e5757ed82e28c385f3d5f337ad481170f0e5aaf06c4799b8",
+  "receipt_sha256": "b27f90c202c8879151dbb323b7881696ef598898553f2e2f73b53759d7461426",
+  "receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/b27f90c202c8879151dbb323b7881696ef598898553f2e2f73b53759d7461426.json"
+}
+```
+
+<!-- Local receipt: SELF. Digests detect corruption; they do not authenticate a reviewer or CI. -->
+```json
+{
+  "summary_schema": 1,
+  "source": "SELF",
+  "timestamp": "2026-10-20T03:55:29.488261+00:00",
+  "command": "make agent-exec-validate",
+  "exit_code": 0,
+  "cwd": "/home/weichen/projects/Agent-System-Dev-wt-feature-cursor-explicit-model-auto",
+  "before_head": "88f446531beb8702a4a95a41ce581e2d4323604d",
+  "after_head": "88f446531beb8702a4a95a41ce581e2d4323604d",
+  "branch": "feature/cursor-explicit-model-auto",
+  "target_branch": "main",
+  "target_head": "ac594c90e536cfb670e94680f045a6c8247a2513",
+  "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-cursor-explicit-model-auto'",
+    "scripts/agent-exec validate --repo .",
+    "validate: ok",
+    "make[1]: Leaving directory '/home/weichen/projects/Agent-System-Dev-wt-feature-cursor-explicit-model-auto'"
+  ],
+  "output_sha256": "8990e6bcf74eb84039840fc508f9c301cd4e82f0aae947c9426b5bd994df8ebb",
+  "receipt_sha256": "2139d938d2fa14e6088e87cc0d8c65ee5b17eb0306fd9a0bca652fcb8e74b778",
+  "receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/2139d938d2fa14e6088e87cc0d8c65ee5b17eb0306fd9a0bca652fcb8e74b778.json"
+}
+```
+
+<!-- Local receipt: SELF. Digests detect corruption; they do not authenticate a reviewer or CI. -->
+```json
+{
+  "summary_schema": 1,
+  "source": "SELF",
+  "timestamp": "2026-10-20T03:55:35.879836+00:00",
+  "command": "go -C deps/development-manager test -count=1 ./internal/agentexec/adapters/...",
+  "exit_code": 0,
+  "cwd": "/home/weichen/projects/Agent-System-Dev-wt-feature-cursor-explicit-model-auto",
+  "before_head": "88f446531beb8702a4a95a41ce581e2d4323604d",
+  "after_head": "88f446531beb8702a4a95a41ce581e2d4323604d",
+  "branch": "feature/cursor-explicit-model-auto",
+  "target_branch": "main",
+  "target_head": "ac594c90e536cfb670e94680f045a6c8247a2513",
+  "root_target": "main",
+  "immediate_target": "main",
+  "before_tracked_diff_sha256": "c88c90fec9ec2e2a666329cbf8876b9e36446bf9b37620e580e4d30fb4d39869",
+  "after_tracked_diff_sha256": "c88c90fec9ec2e2a666329cbf8876b9e36446bf9b37620e580e4d30fb4d39869",
+  "output_tail": [
+    "ok  \tdevelopment-manager/internal/agentexec/adapters\t0.006s"
+  ],
+  "output_sha256": "a2539b823379f477727535b6ea6a4a1663a83e341b5c569d19ba3950de6065a8",
+  "receipt_sha256": "8ccaa9132ffbbe8c3be1dbf2443c752e1602f3e8fe28587e869ba85ea5b4303b",
+  "receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/8ccaa9132ffbbe8c3be1dbf2443c752e1602f3e8fe28587e869ba85ea5b4303b.json"
+}
+```
+
+<!-- Local receipt: SELF. Digests detect corruption; they do not authenticate a reviewer or CI. -->
+```json
+{
+  "summary_schema": 1,
+  "source": "SELF",
+  "timestamp": "2026-10-20T03:56:53.133447+00:00",
+  "command": "make agent-exec-validate",
+  "exit_code": 0,
+  "cwd": "/home/weichen/projects/Agent-System-Dev-wt-feature-cursor-explicit-model-auto",
+  "before_head": "88f446531beb8702a4a95a41ce581e2d4323604d",
+  "after_head": "88f446531beb8702a4a95a41ce581e2d4323604d",
+  "branch": "feature/cursor-explicit-model-auto",
+  "target_branch": "main",
+  "target_head": "ac594c90e536cfb670e94680f045a6c8247a2513",
+  "root_target": "main",
+  "immediate_target": "main",
+  "before_tracked_diff_sha256": "6221fca98cdc185f5a255a12a7982f29ae8332735aa8d258853872382e2fcc1a",
+  "after_tracked_diff_sha256": "6221fca98cdc185f5a255a12a7982f29ae8332735aa8d258853872382e2fcc1a",
+  "output_tail": [
+    "make[1]: Entering directory '/home/weichen/projects/Agent-System-Dev-wt-feature-cursor-explicit-model-auto'",
+    "scripts/agent-exec validate --repo .",
+    "validate: ok",
+    "make[1]: Leaving directory '/home/weichen/projects/Agent-System-Dev-wt-feature-cursor-explicit-model-auto'"
+  ],
+  "output_sha256": "8990e6bcf74eb84039840fc508f9c301cd4e82f0aae947c9426b5bd994df8ebb",
+  "receipt_sha256": "c036b3d15acaf33ae32da7ae882429cc42e1507f68acdb6b8476f180000fb897",
+  "receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/c036b3d15acaf33ae32da7ae882429cc42e1507f68acdb6b8476f180000fb897.json"
+}
+```
+
+<!-- Local receipt: SELF. Digests detect corruption; they do not authenticate a reviewer or CI. -->
+```json
+{
+  "summary_schema": 1,
+  "source": "SELF",
+  "timestamp": "2026-10-20T03:56:55.499605+00:00",
+  "command": "go -C deps/development-manager test -count=1 ./internal/agentexec/adapters/...",
+  "exit_code": 0,
+  "cwd": "/home/weichen/projects/Agent-System-Dev-wt-feature-cursor-explicit-model-auto",
+  "before_head": "88f446531beb8702a4a95a41ce581e2d4323604d",
+  "after_head": "88f446531beb8702a4a95a41ce581e2d4323604d",
+  "branch": "feature/cursor-explicit-model-auto",
+  "target_branch": "main",
+  "target_head": "ac594c90e536cfb670e94680f045a6c8247a2513",
+  "root_target": "main",
+  "immediate_target": "main",
+  "before_tracked_diff_sha256": "b9a88a2e41d0f40d725ae54b2ae633e44b9df560a0a72f7825ebbce88baa5c6e",
+  "after_tracked_diff_sha256": "b9a88a2e41d0f40d725ae54b2ae633e44b9df560a0a72f7825ebbce88baa5c6e",
+  "output_tail": [
+    "ok  \tdevelopment-manager/internal/agentexec/adapters\t0.004s"
+  ],
+  "output_sha256": "2cffdc38850f97e030e880c45699a6a11b06c2775981af4078ef33f632420023",
+  "receipt_sha256": "8cba28efa634b39f395787b9ab213398c002c0a585221d6f050c77280824a919",
+  "receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/8cba28efa634b39f395787b9ab213398c002c0a585221d6f050c77280824a919.json"
+}
+```
+
+<!-- Local receipt: SELF. Digests detect corruption; they do not authenticate a reviewer or CI. -->
+```json
+{
+  "summary_schema": 1,
+  "source": "SELF",
+  "timestamp": "2026-10-20T03:57:53.830073+00:00",
+  "command": "make task-sync",
+  "exit_code": 0,
+  "cwd": "/home/weichen/projects/Agent-System-Dev-wt-feature-cursor-explicit-model-auto",
+  "before_head": "e8cf50fb3f9deff94a9499921bacb6e5d2552108",
+  "after_head": "e8cf50fb3f9deff94a9499921bacb6e5d2552108",
+  "branch": "feature/cursor-explicit-model-auto",
+  "target_branch": "main",
+  "target_head": "ac594c90e536cfb670e94680f045a6c8247a2513",
+  "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-cursor-explicit-model-auto'",
+    "[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 121: recorded HEAD predates non-card changes ——关键检查须重跑并以 make evidence 重新写入",
+    "[synced] sync_base=ac594c90e536cfb670e94680f045a6c8247a2513 tested_head=e8cf50fb3f9deff94a9499921bacb6e5d2552108 checked_at=2026-10-20T03:58:47Z 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-cursor-explicit-model-auto'"
+  ],
+  "output_sha256": "87c7c6e85e7c7fbae5df8e2fc60123d345e043ab0fe2d822fb07e1a20ed7a39c",
+  "receipt_sha256": "43fcec3baa078cfeeb4b10d9c4f3e0554dba0f27792e1151a225bdf7d91541b1",
+  "receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/43fcec3baa078cfeeb4b10d9c4f3e0554dba0f27792e1151a225bdf7d91541b1.json"
+}
+```
+
+<!-- Local receipt: SELF. Digests detect corruption; they do not authenticate a reviewer or CI. -->
+```json
+{
+  "summary_schema": 1,
+  "source": "SELF",
+  "timestamp": "2026-10-20T03:58:56.449775+00:00",
+  "command": "make precheck",
+  "exit_code": 2,
+  "cwd": "/home/weichen/projects/Agent-System-Dev-wt-feature-cursor-explicit-model-auto",
+  "before_head": "e8cf50fb3f9deff94a9499921bacb6e5d2552108",
+  "after_head": "e8cf50fb3f9deff94a9499921bacb6e5d2552108",
+  "branch": "feature/cursor-explicit-model-auto",
+  "target_branch": "main",
+  "target_head": "ac594c90e536cfb670e94680f045a6c8247a2513",
+  "root_target": "main",
+  "immediate_target": "main",
+  "before_tracked_diff_sha256": "4317988e164abd60d49c490603d566068c2fce4ab71bd785fc0cdf2c1b0ebb4f",
+  "after_tracked_diff_sha256": "4317988e164abd60d49c490603d566068c2fce4ab71bd785fc0cdf2c1b0ebb4f",
+  "output_tail": [
+    "make[1]: Entering directory '/home/weichen/projects/Agent-System-Dev-wt-feature-cursor-explicit-model-auto'",
+    "[repo]   branch=feature/cursor-explicit-model-auto head=e8cf50fb3f",
+    "[remote] origin/main=ac594c90e5 ahead=4 behind=0",
+    "[tree]   dirty(1) submodules_drift=0 uninit=0",
+    "[worktrees] linked=8",
+    "[cards] 已合入未闭合任务卡:feature-iam-role-permission-linked-capabilities.md——make task-close 回填归档（主检出运行）",
+    "[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, standards/collaboration.md（树脏=他人或未收尾现场，不得写入）",
+    "[R0] ac594c90e5（完整：ac594c90e536cfb670e94680f045a6c8247a2513）",
+    "[verdict] SHARED_WORKSPACE_BUSY — 工作树不干净，不得写入；先收尾或经 owner 确认",
+    "make[1]: *** [Makefile:40: precheck] Error 3",
+    "make[1]: Leaving directory '/home/weichen/projects/Agent-System-Dev-wt-feature-cursor-explicit-model-auto'"
+  ],
+  "output_sha256": "2f0b15c181f2d0683f8c7b71ea16af91ac32206a5dcdaa2723015c8db8742ca2",
+  "receipt_sha256": "ab41cab72ef0a1e70cabdc5dd98152d4173659722144b49cd300d96a8b314af2",
+  "receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/ab41cab72ef0a1e70cabdc5dd98152d4173659722144b49cd300d96a8b314af2.json"
+}
+```
+
+<!-- Local receipt: SELF. Digests detect corruption; they do not authenticate a reviewer or CI. -->
+```json
+{
+  "summary_schema": 1,
+  "source": "SELF",
+  "timestamp": "2026-10-20T03:59:10.263393+00:00",
+  "command": "make precheck",
+  "exit_code": 0,
+  "cwd": "/home/weichen/projects/Agent-System-Dev-wt-feature-cursor-explicit-model-auto",
+  "before_head": "2430123837f52b5a1f23d8f780ab2820662213df",
+  "after_head": "2430123837f52b5a1f23d8f780ab2820662213df",
+  "branch": "feature/cursor-explicit-model-auto",
+  "target_branch": "main",
+  "target_head": "ac594c90e536cfb670e94680f045a6c8247a2513",
+  "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-cursor-explicit-model-auto'",
+    "[repo]   branch=feature/cursor-explicit-model-auto head=2430123837",
+    "[remote] origin/main=ac594c90e5 ahead=5 behind=0",
+    "[tree]   clean submodules_drift=0 uninit=0",
+    "[worktrees] linked=8",
+    "[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] ac594c90e5（完整：ac594c90e536cfb670e94680f045a6c8247a2513）",
+    "[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-wt-feature-cursor-explicit-model-auto'"
+  ],
+  "output_sha256": "6e0be0bead14cab83976c54cf02bb42c7f50ca9a970c936847c7468be0a08249",
+  "receipt_sha256": "74eb543778810cbc85366ba05a047687a2fb4c28758da747b5f4ea1937713e06",
+  "receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/74eb543778810cbc85366ba05a047687a2fb4c28758da747b5f4ea1937713e06.json"
+}
+```
+
+## 闭合记录（合入前折叠）
+
+- 本卡在 PR #644（https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/644）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。
@@ -0,0 +1,254 @@
+# feature/docker-test-image 任务卡
+
+任务主记录：PR #645 https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/645；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）= 162c5a0160955989608f325b4be30458e3717d16
+- 工作区：/home/weichen/projects/Agent-System-Dev-wt-feature-docker-test-image（worktree）；分支：feature/docker-test-image
+- 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=614aefe70dd97a672de9522beee5fece3da4719ee310d1c7cfc4d13fea081ac2；triage_receipt=/tmp/docker-image-triage.json；receipt_sha256=bc1c9cab074d853273d064a98599c6ef2519aa4022f2272bcc0830d3d97d01c0
+
+- 授权与交付终点：用户直接请求（2026-10-20）：为本系统准备 Docker 测试镜像（含系统环境、SSH、无头浏览器），后续测试用该镜像启动容器做隔离测试。终点=镜像定义与构建/验证入口合入 main：docker/ 定义文件 + Makefile image-build/image-verify + docker/README.md，镜像本机构建通过、容器内环境自检通过。未授权事项：不改动 modules/**、CI/治理脚本、部署形态（本仓交付仍非容器化）；不发布镜像到外部 registry；不把本镜像用于生产部署。
+- 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：需求拆解；当前增量：I1（待定义）
+- 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：一份可重复构建的测试环境镜像定义（docker/），镜像内提供与本机开发一致的工具链（Go 1.27.1、Node 26.10.0、Python 3.14、git、make）、SSH 服务（仅公钥、专用 dev 用户）与无头浏览器（Playwright 1.64.0 chromium，系统级缓存 /opt/ms-playwright），供后续以 `docker run` 启动一次性容器、挂载仓库做隔离测试。
+
+入口/影响：新增 docker/（Dockerfile、entrypoint.sh、verify-env.sh、README.md）；根 Makefile 新增 image-build / image-verify 两个目标。不嵌入仓库代码与任何密钥；不改变 `make test`/CI 行为；不引入部署容器化。
+
+非目标：镜像注册表发布、CI 内构建镜像、多架构构建、给镜像装业务代码/子模块、Windows/macOS 镜像。
+
+## 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 |
+|---|---|---|---|---|---|---|---|---|---|---|
+| docker-test-image | docker/**、Makefile | AGENT-EXECUTION.md（agent-execution/v1） | implementation | cursor→antigravity→pi（紧急 codex） | cursor#a1（运行 1） | cursor-agent-stable/auto | failed-unknown（cursor 后端连接反复中断，exit 1） | 未发生 | 无 | /tmp/docker-image-unit1-receipt.json；隔离工作区保留于 /tmp/agent-exec-1000/ebd031a7b7be000aca6f401395d70cd1/wt-bb3cf3ec9e85 |
+| docker-test-image | 同上（重派发） | 同上 | implementation | 同上 | cursor#a1（运行 2，重发前已对账+探活） | cursor-agent-stable/auto | failed-unknown（Cursor 月度额度耗尽 ActionRequiredError，非瞬时） | 未发生 | 无 | /tmp/docker-image-unit2-receipt.json；隔离工作区保留于 /tmp/agent-exec-1000/90bc3c29e3ea2d9fbebc9e376461846f/wt-c0358fa94a6b |
+| docker-test-image | 同上（误派发） | 同上 | implementation | 同上 | — | — | invalid-config（运行前检出脏：host 对 AGENT-EXECUTION.md 的直接改动被 admit 拒绝后残留，已回滚，未启动任何候选） | 未发生 | 无 | /tmp/docker-image-unit3-receipt.json |
+| docker-test-image | 同上（重派发） | AGENT-EXECUTION.md（cursor 停用后，16776aa） | implementation | antigravity→pi（紧急 codex） | agy#a1（运行 4） | antigravity/auto | failed-unknown（实现与验证全部完成、终态记录已输出，但会话尾部一次后端 API EOF 污染 result 信封，控制器 fail-closed 未建 transport；镜像已建成且 verify-env PASS 经 host 独立复核） | 未发生 | 无 | /tmp/docker-image-unit4-receipt.json；隔离区 /tmp/agent-exec-1000/78f91904001532b603bf0ceeb292b893/wt-3ec6b80250c3（含已验证实现） |
+| docker-test-image | 同上（重验证派发） | 同上 | implementation | 同上 | agy#a2（运行 5，对账后；连续第二次因传输机制的 failed-unknown 重派发，若再失败则回到用户决策，不无限循环） | 待运行 | NOT_RUN | NOT_RUN | NOT_RUN | /tmp/docker-image-unit5-receipt.json |
+
+- 配置摘要来源：AGENT-EXECUTION.md `agent-execution` 块（schema v1；implementation 候选 cursor/agy/pi，每候选至多 3 次，紧急 codex 一次，fallback_to_host=never）；运行收据由 scripts/agent-exec run 写出后原样保留在源码外路径。
+- 运行 1 对账（2026-10-20）：镜像未构建（docker images 无 agent-system-test-*）、无新增容器、规范检出干净；改动仅存在于保留的隔离工作区（Makefile M + docker/ 4 文件）；cursor 探活已恢复（探针 exit 0）。据此授权同一单元重新派发（新 run，非同 run 盲重试）。
+- 运行 2 对账（2026-10-20）：终态原因实为 Cursor Ultra 月度用量额度耗尽（ActionRequiredError，重置日 2026-11-10），属确定性不可用；host 依配置 enabled 机制停用 cursor 时被 pre-commit admit 拒绝（非豁免路径须 transport 来源），路由改动本身又需一次成功运行——死锁，经用户选项 1 解除（见下方决策点）。
+- 运行 4 对账（2026-10-20）：worker 完成实现且四条验证自报通过，host 独立重跑 `docker run --rm --shm-size=1g agent-system-test-env:dev /usr/local/bin/verify-env.sh` → verify-env: PASS；失败纯属会话尾部 API EOF 污染 result 信封（raw log 尾部 `streamGenerateContent: EOF`），非内容缺陷。镜像 agent-system-test-env:dev 已在 daemon 中（层缓存可复用）。授权重派发运行 5 作纯重验证；若再因传输机制失败，停止并回用户决策。
+
+## 关联方向与规划
+
+- 适用状态：待核对（无适用规划时说明原因）
+- 主记录路径/版本：待核对（路径按仓库根目录定位，归档后不变；只引用唯一正文）
+- 对应里程碑：待核对
+
+## 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 | 测试环境镜像定义：docker/ 内 Dockerfile 固定 ubuntu:24.04（amd64）+ Go 1.27.1 + Node 26.10.0 + Python 3.14（deadsnakes）+ git/make/openssh-server/sudo + Playwright 1.64.0 chromium（/opt/ms-playwright） | 与本机开发工具链版本一致（实测：go1.27.1 / v26.10.0 / 3.14.8 / playwright 1.64.0），避免测试行为漂移 | 高 | `docker build -t agent-system-test-env:dev docker/` 退出 0 | 无 | 已确认 |
+| R2 | SSH 就绪：容器以 root 入口前台跑 sshd；PermitRootLogin no、PasswordAuthentication no；dev 用户（UID 1000、NOPASSWD sudo）；host key 首启生成；authorized_keys 运行时只读挂载注入 | 隔离测试需要经 SSH 进入容器；公钥注入避免镜像携带凭据 | 高 | 容器内 `sshd -t` 通过；dev 存在且 sudo NOPASSWD；镜像内无任何私钥/secret | R1 | 已确认 |
+| R3 | 无头浏览器可用：镜像内预装 playwright 1.64.0 chromium 及系统依赖，ENV PLAYWRIGHT_BROWSERS_PATH=/opt/ms-playwright | frontend e2e（@playwright/test ^1.50.1，解析 1.64.0）容器内可直接跑；版本对齐避免浏览器 revision 漂移 | 高 | verify-env.sh 中 chromium --headless --dump-dom about:blank 输出 HTML | R1 | 已确认 |
+| R4 | 构建/验证入口与文档：Makefile image-build / image-verify；docker/README.md 覆盖构建、启动（端口映射、--shm-size、公钥挂载、仓库挂载 /workspace）、容器内跑 e2e 示例与安全边界 | 用户后续直接用这两个入口启动隔离测试容器 | 中 | `make image-build`、`make image-verify` 可用；README 含最小可复现命令 | R1–R3 | 已确认 |
+
+## 方案与计划
+
+- 方案引用：本卡「目标与非目标」+ 单元包 /tmp/unit-docker-test-image.json（digest 由运行收据记录）；固定版本事实：go1.27.1、node v26.10.0、python 3.14.8、playwright 1.64.0（本机实测于 2026-10-20）
+- 实施计划引用：单单元 docker-test-image（docker/** + Makefile 内聚小任务，合为一个包）
+- 测试计划引用：R1–R4 验收条件 = worker 窄检查（docker build + 容器内 verify-env.sh）；host 权威验证在 apply 后本仓重跑同两命令
+
+## 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 | R0=162c5a0160 | 已完成 | host 主模型 | 2026-10-20 | AGENTS.md 路由 + policy/delivery.md |
+| 需求评估 | R0=162c5a0160 | 已完成 | host 主模型 | 2026-10-20 | 本卡需求表 R1–R4 |
+| 需求表确认 | R0=162c5a0160 | 已完成 | 用户直接请求即授权 | 2026-10-20 | 授权与交付终点节 |
+| 方案设计 | R0=162c5a0160 | 已完成 | host 主模型 | 2026-10-20 | 见方案与计划 |
+| 实施计划 | R0=162c5a0160 | 已完成 | host 主模型 | 2026-10-20 | 单元 docker-test-image（单元包 /tmp/unit-docker-test-image.json） |
+| 实施与自检 | de3d3aff（transport de3d3aff285e0dcfd185c9904a3a9b01af34e2fa） | 已完成 | agy worker（运行 4 实现、运行 5 重验证）→ host apply | 2026-10-20 | /tmp/docker-image-unit5-receipt.json；运行 1–5 详见收据表 |
+| 正式测试与验收 | de3d3aff | 已完成（SELF；GATE 待 CI） | host 主模型 | 2026-10-20 | make image-build / image-verify 证据入卡；CI 待验 |
+| 代码 Review | de3d3aff | 进行中 | host 主模型（policy 允许，独立于实施会话） | 2026-10-20 | 见合入与清理节 Review 记录 |
+| 合入 | de3d3aff | 待执行 | host（授权范围内） | — | 按 policy/delivery.md 合入流程 |
+| 合入核验与收口 | — | 待执行 | host | — | — |
+
+### 决策点（2026-10-20，已闭合）
+
+implementation/repair 角色首候选 cursor 因月度额度耗尽必然失败，且路由配置无法由 host/worker 合规变更。选项及结果：
+
+1. **已采纳（用户 2026-10-20 选定选项 1）**：用户以自身授权在任务 worktree 编辑 AGENT-EXECUTION.md 将 cursor profile `enabled: false`（附注释，额度重置后恢复），并亲自 `git commit --no-verify` 提交为 16776aa（配置 diff 已在决策菜单中预告并经用户选择，validate 通过）。host 据此重派发，路由落到探活正常的 antigravity。额度重置后应恢复 enabled: true。
+2. 用户在 Cursor 提高 Spend Limit（未采用）。
+3. 等待 2026-11-10 重置（未采用）。
+4. host 以 role=test 派发（未采用，角色标签与工作性质不符）。
+
+## 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 | docker/ 镜像定义可构建、容器内自检通过 | 单一交付 | build+verify 通过即停，不做镜像优化迭代 | 授权与交付终点节 | NOT_RUN | 待评估 | 待评估 |
+
+## 同步记录
+
+| 节点 | sync_base_sha | tested_head_sha | checked_at |
+|---|---|---|---|
+| 启动 | 162c5a0160955989608f325b4be30458e3717d16 | 162c5a0160955989608f325b4be30458e3717d16 | 2026-10-20T02:39:22Z |
+
+## 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：未入队；调度记录：无
+- 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：docker/ 测试环境镜像定义（Dockerfile + entrypoint.sh + verify-env.sh + README.md）与根 Makefile image-build/image-verify 目标已由 worker 交付、host apply 入分支（de3d3aff）。镜像 ubuntu:24.04 + Go 1.27.1 + Node 26.10.0 + Python 3.14（deadsnakes）+ Playwright 1.64.0 chromium（/opt/ms-playwright）+ sshd（仅公钥、dev 用户 NOPASSWD sudo、root 登录关闭）。
+- 验证：`make image-build` exit=0（SELF，证据块）；`make image-verify` exit=0 且 verify-env: PASS（SELF）；worker 四条自检通过；R1–R4 验收条件全部满足。已知非阻塞项：Dockerfile `FROM --platform=linux/amd64` 触发 buildkit 一条 lint 警告（有意钉住 amd64，不改）。CI GATE 与 Review 见合入与清理节。
+- 影响与剩余项：仅新增 docker/ 与 Makefile 两个目标，不触碰 modules/CI/治理脚本；镜像不发布外部 registry。剩余：PR CI、独立 Review、合入与回收。
+
+## 规划进展与下一步
+
+- 本次推进/剩余：待核对（依据实际成果更新适用方案/规划）
+- 首选下一任务：待核对（无适用规划、已完成或受阻时如实说明，不虚构任务）
+- 推荐依据：待填写
+- 前置条件/待确认：待核对
+- 预期产物/验收条件：待定义
+- 重复任务核对：待核对（已有/在途任务、PR 与规划记录）
+- 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：PASS（host 主模型独立 Review，非实施会话；对象 base=origin/main/d2035c76 head=b9c0fc3）。范围核对：7 文件全部在授权内（docker/ 4 文件 + Makefile 增量 + 任务卡 + AGENT-EXECUTION.md 路由调整 16776aa）；Go/CI/脚本/modules 零触碰；secret 扫描无命中（仅 task-start 等词的 sk- 误报）；Makefile 除 .PHONY 一行外纯增量。非阻塞观察：① FROM --platform=linux/amd64 触发 buildkit lint 警告（有意钉 amd64，接受）；② sshd_config 追加式覆盖依赖 stock ubuntu 默认（测试镜像可接受，verify-env 已断言 sshd -t）。
+- 冲突记录：main 前进至 d2035c7（含 #644）后合并 origin/main（merge commit b9c0fc3），无冲突；新 gitlink 物化后 make test-worktree 递归核对通过；modules/frontend 仍解析 @playwright/test ^1.50.1（镜像内浏览器 1.64.0 对齐不变）。
+- CI 记录：CI_SUCCESS @ b9c0fc3fa1817812295394e069b457cc098e1f24（ci / test、test-pg、svc-realcombo 全绿，runs 4360）。过程备注：首候选 HEAD 8e062ca 的 test-pg 首跑 TestArtifactFacadeCard 失败（伴随 database is closed 收尾噪音），重跑同 job 即 success，判偶发；b9c0fc3 的 test 首跑为 npm EIDLETIMEOUT 网络抖动，重跑 success。两次均非本 PR 内容缺陷（本 PR 未触碰 Go/npm 依赖）。
+- 合入记录：待执行（合入后回填）
+- 清理记录：待执行（合入后回填）
+
+<!-- Local receipt: SELF. Digests detect corruption; they do not authenticate a reviewer or CI. -->
+```json
+{
+  "summary_schema": 1,
+  "source": "SELF",
+  "timestamp": "2026-10-20T02:38:25.695061+00:00",
+  "command": "make precheck",
+  "exit_code": 0,
+  "cwd": "/home/weichen/projects/Agent-System-Dev",
+  "before_head": "162c5a0160955989608f325b4be30458e3717d16",
+  "after_head": "162c5a0160955989608f325b4be30458e3717d16",
+  "branch": "main",
+  "target_branch": "main",
+  "target_head": "162c5a0160955989608f325b4be30458e3717d16",
+  "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=162c5a0160",
+    "[remote] origin/main=162c5a0160 ahead=0 behind=0",
+    "[tree]   clean submodules_drift=0 uninit=0",
+    "[worktrees] linked=6",
+    "[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] 162c5a0160（完整：162c5a0160955989608f325b4be30458e3717d16）",
+    "[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": "9e1904b7470a27857bd0243bc42faff0a9eb9cafc6916ad823fb1ccfea32f3b3",
+  "receipt_sha256": "838d0ce05fc8661b279c5ccd7696cbe4712cd582b3bf39411ede4265e314a7f1",
+  "receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/838d0ce05fc8661b279c5ccd7696cbe4712cd582b3bf39411ede4265e314a7f1.json"
+}
+```
+
+<!-- Local receipt: SELF. Digests detect corruption; they do not authenticate a reviewer or CI. -->
+```json
+{
+  "summary_schema": 1,
+  "source": "SELF",
+  "timestamp": "2026-10-20T04:24:06.218569+00:00",
+  "command": "make image-build",
+  "exit_code": 0,
+  "cwd": "/home/weichen/projects/Agent-System-Dev-wt-feature-docker-test-image",
+  "before_head": "de3d3aff285e0dcfd185c9904a3a9b01af34e2fa",
+  "after_head": "de3d3aff285e0dcfd185c9904a3a9b01af34e2fa",
+  "branch": "feature/docker-test-image",
+  "target_branch": "main",
+  "target_head": "d2035c76dc1cb15e01d2c184af5155d9d773cd9f",
+  "root_target": "main",
+  "immediate_target": "main",
+  "before_tracked_diff_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+  "after_tracked_diff_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+  "output_tail": [
+    "#10 CACHED",
+    "",
+    "#11 exporting to image",
+    "#11 exporting layers done",
+    "#11 exporting manifest sha256:1b70b78c47f81555bca6525d04f8fefa836eb817d37bd018fcd71632c9cce13b done",
+    "#11 exporting config sha256:af4c14981be06d79e082e1685dd6f5aac947bc2f08022de3efdb8a158d656ffb done",
+    "#11 exporting attestation manifest sha256:bebc178b5c4328c737af45858184422a642deb66ac627d6cc80d6ec3c003f246 done",
+    "#11 exporting manifest list sha256:b9244ca7c49a4192b6beee8cb66ea148f2b07d6c26e613f3661aba4e569b6fa4 done",
+    "#11 naming to docker.io/library/agent-system-test-env:dev done",
+    "#11 unpacking to docker.io/library/agent-system-test-env:dev done",
+    "#11 DONE 0.0s",
+    "",
+    " \u001b[33m1 warning found (use docker --debug to expand):",
+    "\u001b[0m - FromPlatformFlagConstDisallowed: FROM --platform flag should not use constant value \"linux/amd64\" (line 1)",
+    "make[1]: Leaving directory '/home/weichen/projects/Agent-System-Dev-wt-feature-docker-test-image'"
+  ],
+  "output_sha256": "9d5d28f761a75ec302f735b181d53f3a31893b29a7db1417da0b580d39a6ede9",
+  "receipt_sha256": "10c826d7803683685c0fe49e99b8a86a04e0d675b14aad637f50220a48b13d58",
+  "receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/10c826d7803683685c0fe49e99b8a86a04e0d675b14aad637f50220a48b13d58.json"
+}
+```
+
+<!-- Local receipt: SELF. Digests detect corruption; they do not authenticate a reviewer or CI. -->
+```json
+{
+  "summary_schema": 1,
+  "source": "SELF",
+  "timestamp": "2026-10-20T04:24:15.223285+00:00",
+  "command": "make image-verify",
+  "exit_code": 0,
+  "cwd": "/home/weichen/projects/Agent-System-Dev-wt-feature-docker-test-image",
+  "before_head": "de3d3aff285e0dcfd185c9904a3a9b01af34e2fa",
+  "after_head": "de3d3aff285e0dcfd185c9904a3a9b01af34e2fa",
+  "branch": "feature/docker-test-image",
+  "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-docker-test-image'",
+    "docker run --rm --shm-size=1g agent-system-test-env:dev /usr/local/bin/verify-env.sh",
+    "verify-env: PASS",
+    "make[1]: Leaving directory '/home/weichen/projects/Agent-System-Dev-wt-feature-docker-test-image'"
+  ],
+  "output_sha256": "4e670ae97df841f706396291f73ef43e7702f9fd60cfe163b37699ca5968804a",
+  "receipt_sha256": "3c69f4644d10998f86733da4486b1967e49c310aad4a932aa13a7bddaf387265",
+  "receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/3c69f4644d10998f86733da4486b1967e49c310aad4a932aa13a7bddaf387265.json"
+}
+```
+
+## 闭合记录（合入前折叠）
+
+- 本卡在 PR #645（https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/645）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。
@@ -0,0 +1,166 @@
+# feature/fast-slow-o2-i1-agent-native 任务卡
+
+任务主记录：PR #647 https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/647；Dev 草稿 PR [#647](https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/647)；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）= ac594c90e536cfb670e94680f045a6c8247a2513
+- 工作区：/home/weichen/projects/Agent-System-Dev-wt-feature-fast-slow-o2-i1-agent-native（worktree）；分支：feature/fast-slow-o2-i1-agent-native
+- 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=24717af8dcc91e7b1fbe4ceb92919ea31e43da66f46e51371e9ea2102d8b8cc5；triage_receipt=/tmp/o2i1-20261020/triage.json；receipt_sha256=7854667c4867dabc655b1ce4d1b8f026da6de0e2929fb26b4374353089474fa7
+
+- 授权与交付终点：用户 2026-10-20 阶段 4/5 人审“通过”（[方案](docs/superpowers/specs/2026-10-19-fast-slow-o2-route-contract-eof-design.md) §6.1 选 C2 同时接受 `http2_stream` 与 `known_length`+`match`；§6.2 配置仅系统层、默认关闭），并要求启动 I1。终点：Agent-Native I1 草稿 PR 经独立 Review 与 CI 通过 + 阶段 6 评审包，待用户阶段 6 人审后再合入。未授权：I2/I3 启动前另行确认、P1 付费探针（另提资源方案）、部署、真实模型/付费请求。
+- 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-Native 分支 feature/fast-slow-o2-i1-route-contract，base origin/main 9c24e22）
+- 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：对一条精确绑定的 OpenAI 兼容路由（模型 + 规范化基址 + 摘要），在流缺字面 `[DONE]` 但 C1–C9 全部成立时放行工具调用，终态标 `CompletionBasis=route_contract_eof`；合同为零值时行为逐字节等同现状。
+- 受影响：Agent-Native `runtime/llm`（`Client.RouteContract`、解析器延后判定、`Event`/`TerminalObservation` 新增 `completionBasis`/`contractCheck`）、新包 `runtime/argschema`、`runtime/tools/registry.go` 委托校验。
+- 非目标：不改 `StreamComplete` 语义；不泛化到其他路由/协议；Backend 配置与透传（I2）、Dev 改钉（I3）、付费探针（P1）不在本卡。
+
+## 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 |
+|---|---|---|---|---|---|---|---|---|---|---|
+| o2-i1-agent-native-route-contract | runtime/llm、runtime/argschema、registry.go(+test) | AGENT-EXECUTION.md | implementation | cursor→antigravity→pi | 1 | cursor / auto | scope-expansion（单元包 `allowed_paths` 误用 `**` 通配，执行器按前缀匹配，7 个范围内文件被判越界；fail-stop） | 未集成 | never | /tmp/o2i1-20261020/o2-i1-receipt.attempt1-scope-expansion.json |
+| o2-i1-agent-native-route-contract | 同上（改为前缀写法 `runtime/llm/`、`runtime/argschema/`，范围不变） | AGENT-EXECUTION.md | implementation | cursor→antigravity→pi | 2（用户 2026-10-20 授权全新重跑） | cursor / auto | success | `899fd70`（ref refs/agent-exec/e38bcf1c…/445c377b，parent 9c24e22），`agent-exec apply` 快进集成 | never | /tmp/o2i1-20261020/o2-i1-receipt.json |
+
+## 关联方向与规划
+
+- 适用状态：待核对（无适用规划时说明原因）
+- 主记录路径/版本：待核对（路径按仓库根目录定位，归档后不变；只引用唯一正文）
+- 对应里程碑：待核对
+
+## 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 | I1：Agent-Native `route_contract_eof` 限路由等价终态 | 符合：用户 2026-10-19 选定 O2，2026-10-20 阶段 4/5 通过 | P1 | 计划 §2 测试矩阵全部用例通过；拒绝时终态事件除 `contractCheck` 外与合同关闭 deep-equal；零值合同行为不变；现有断言不删减 | 无 | 实施中 |
+
+## 方案与计划
+
+- 方案引用：docs/superpowers/specs/2026-10-19-fast-slow-o2-route-contract-eof-design.md（Dev main，PR #639 合入）
+- 实施计划引用：docs/superpowers/plans/2026-10-19-fast-slow-o2-route-contract-eof-plan.md §2（I1）
+- 测试计划引用：同上 §2 测试表与验证命令
+
+## 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 | 待定 | 待执行 | — | — | — |
+| 需求评估 | 待定 | 待执行 | — | — | — |
+| 需求表确认 | 待定 | 待执行 | — | — | — |
+| 方案设计 | Dev 5a7a0da | 通过（C2 接受 known_length+match） | 用户 | 2026-10-20 | 阶段 4 人审 |
+| 实施计划 | Dev 5a7a0da | 通过 | 用户 | 2026-10-20 | 阶段 5 人审 |
+| 实施与自检 | Agent-Native 899fd70 | 完成（SELF） | cursor worker 实施；host 范围审阅与验证 | 2026-10-20 | 收据 o2-i1-receipt.json |
+| 正式测试与验收 | Agent-Native 899fd70 | 阶段 6 通过（接受 C2 编号） | 用户 | 2026-10-20 | PR #48 CI GATE success；评审包 2026-10-20-fast-slow-o2-i1-review.md |
+| 代码 Review | Agent-Native 899fd70 | PASS | 全新会话 code-reviewer | 2026-10-20 | 见合入与清理节 |
+| 合入 | Agent-Native 2fc66be | 已合入 Agent-Native main | host | 2026-10-20 | 用户阶段 6 授权 |
+| 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 |
+|---|---|---|---|---|---|---|---|
+| 待定义 | — | — | — | 待核对 | NOT_RUN | 待评估 | 待评估 |
+
+## 同步记录
+
+| 节点 | sync_base_sha | tested_head_sha | checked_at |
+|---|---|---|---|
+| 启动 | ac594c90e536cfb670e94680f045a6c8247a2513 | ac594c90e536cfb670e94680f045a6c8247a2513 | 2026-10-20T03:22:13Z |
+
+## 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：未入队；调度记录：无
+- 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：I1 在 Agent-Native 分支 `feature/fast-slow-o2-i1-route-contract`（`899fd70`，草稿 PR #48）交付；阶段 6 评审包 docs/superpowers/specs/2026-10-20-fast-slow-o2-i1-review.md。
+- 验证：host（SELF）@899fd70 vet、定向测试（含 -race）、`go test ./...` PASS；CI（GATE）PR #48 三项 success；独立 Review PASS。
+- 影响与剩余项：仅 Agent-Native `runtime/llm`、`runtime/argschema`、registry 委托；合同默认关闭。剩余：用户阶段 6；I2、I3、P1；评审包第 3 节非阻塞项。
+
+## 规划进展与下一步
+
+- 本次推进/剩余：待核对（依据实际成果更新适用方案/规划）
+- 首选下一任务：待核对（无适用规划、已完成或受阻时如实说明，不虚构任务）
+- 推荐依据：待填写
+- 前置条件/待确认：待核对
+- 预期产物/验收条件：待定义
+- 重复任务核对：待核对（已有/在途任务、PR 与规划记录）
+- 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：Cursor Task 子代理 code-reviewer（fresh_session=true，session=531ce711-73e7-44d8-8b9e-ed90d93856f7；只接收需求、方案/计划、base 9c24e22/head 899fd70 与 diff，未转交实施会话）；结论 PASS，0 阻塞，3 条非阻塞记入评审包第 3 节；评审者自跑 vet 与 -race 定向测试通过（SELF）。
+- CI 记录（Agent-Native）：PR #48 head `899fd70d27dd25bb88088a677546a71e54a86d9e` commit status success：`ci / vet-and-test`（runs/4350/jobs/7018）、`ci / docker-checkout-hostgateway`（runs/4350/jobs/7019）、`governance / governance`（runs/4351/jobs/7020）（GATE）。
+- 冲突记录：NOT_RUN（最新目标同步、冲突处置、组合兼容核验及复审/补测）
+- 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（Agent-Native）：用户 2026-10-20 阶段 6 通过；PR #48 核验 head `899fd70`、commit status success（3 项，GATE）后合入 Agent-Native main，合入提交 `2fc66be65201232ea38ba64d457efad5565d869d`；合入后 tree `720ec93` 与合入前 `git merge-tree` 预期一致。Dev 改钉在 I3 组合验证。
+- 合入记录（本 PR）：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：Agent-Native worktree `Agent-Native-wt-feature-fast-slow-o2-i1` 核验无写者、干净后移除，本地分支已删；Dev worktree 待本 PR 合入后回收。
+
+<!-- Local receipt: SELF. Digests detect corruption; they do not authenticate a reviewer or CI. -->
+```json
+{
+  "summary_schema": 1,
+  "source": "SELF",
+  "timestamp": "2026-10-20T03:21:23.593016+00:00",
+  "command": "make precheck",
+  "exit_code": 0,
+  "cwd": "/home/weichen/projects/Agent-System-Dev",
+  "before_head": "ac594c90e536cfb670e94680f045a6c8247a2513",
+  "after_head": "ac594c90e536cfb670e94680f045a6c8247a2513",
+  "branch": "main",
+  "target_branch": "main",
+  "target_head": "ac594c90e536cfb670e94680f045a6c8247a2513",
+  "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=ac594c90e5",
+    "[remote] origin/main=ac594c90e5 ahead=0 behind=0",
+    "[tree]   clean submodules_drift=0 uninit=0",
+    "[worktrees] linked=7",
+    "[cards] 已合入未闭合任务卡:feature-iam-role-permission-linked-capabilities.md——make task-close 回填归档（主检出运行）",
+    "[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] ac594c90e5（完整：ac594c90e536cfb670e94680f045a6c8247a2513）",
+    "[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": "8354ba7addbd3c5505eb65459b25cc49dc9c6513d9a4e8f6b38dc9f448b3f478",
+  "receipt_sha256": "a0e06fafe3a01436440290d8fe41abd0581c817dde2ad3481497f95cae50a473",
+  "receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/a0e06fafe3a01436440290d8fe41abd0581c817dde2ad3481497f95cae50a473.json"
+}
+```
+
+## 闭合记录（合入前折叠）
+
+- 本卡在 PR #647（https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/647）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。
+| 同步（记录前对象） | d2035c76dc1cb15e01d2c184af5155d9d773cd9f | 014655339962c1057970ddc9ce9e2025fe31f902 | 2026-10-20T05:56:34Z |
+| 同步（记录前对象） | f97917032d143188bc7faf665aff612d9814af4e | a577c9e11bae5655fc63a9ca313c84e70ad24aed | 2026-10-20T06:55:48Z |
@@ -1,6 +1,6 @@
 # feature/iam-role-permission-linked-capabilities 任务卡

-任务主记录：PR #628 https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/628；状态：进行中；owner：weichen
+任务主记录：PR #628 https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/628；状态：已完成（回填）；owner：weichen

 ## 基线与授权

@@ -153,7 +153,7 @@
  - ci/test-pg 失败原因：PostgreSQL+pgvector+Redis 服务未就绪
  - ci/svc-realcombo 失败原因：SQLite+Redis 服务未就绪

-## 结果与验证（完成后填写）
+## 结果与验证

 - 结果：
 - 验证：<结论摘要 PASS/FAIL/SKIP/NOT_RUN 逐项；逐条证据由 make evidence 写入上方证据表>
@@ -217,3 +217,9 @@
  "receipt_path": "/home/weichen/.cache/agent-system-dev/evidence/8ff8d4dd5f4fe50bf0b779d5de7c989c8eab122babf7bee5ba6237de8640f2af.json"
 }
 ```
+
+## 闭合记录（card-autoclose 回填）
+
+- 依据：merge ac594c90e536cfb670e94680f045a6c8247a2513（PR #643）已包含于 origin/main，分支成果已落盘；本段为合入后回填。
+- 合并主题：Merge pull request 'IAM L1 → main: capability-association + single-role-authority + capability-exposure + frontend-auto-discover + 7-canonical-two-trees (U1/U2/U3/U4/U7 + U5-Backend)' (#643) from feature/iam-role-permission-linked-capabilities into main
+- 归档：随闭合移入 .task/archive/；任务执行期的过程证据见原任务记录与 PR。
@@ -7,19 +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` lets a CLI use its configured default
-model; 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.

@@ -36,25 +39,34 @@ 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:
    adapter: cursor
    executable: cursor-agent-stable
    model: auto
+    # Re-enabled 2026-10-20: the earlier disable was based on a misreading
+    # of ActionRequiredError — the real cause was the DM executor not
+    # passing --model auto (cursor fell back to a quota-limited model).
+    # Fixed by PR #644 (deps/development-manager pin); quota itself is fine.
    enabled: true

  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:
@@ -66,7 +78,7 @@ profiles:
  codex:
    adapter: codex
    executable: codex
-    model: auto
+    model: gpt-6.1-sol
    enabled: true

 integration:
@@ -91,23 +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.
-  - Cursor: `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.
+- 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-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
@@ -13,7 +13,7 @@ PLUGINS    := plugins
 COMBO      := core=$(shell git -C $(CORE) rev-parse --short HEAD 2>/dev/null)+backend=$(shell git -C $(BACKEND) rev-parse --short HEAD 2>/dev/null)+frontend=$(shell git -C $(FRONTEND) rev-parse --short HEAD 2>/dev/null)+ui=$(shell git -C $(UI) rev-parse --short HEAD 2>/dev/null)+agentcmd=$(shell git -C deps/agent-command rev-parse --short HEAD 2>/dev/null)+documents=$(shell git -C modules/documents rev-parse --short HEAD 2>/dev/null)+native=$(shell git -C deps/agent-native rev-parse --short HEAD 2>/dev/null)+squad=$(shell git -C deps/agent-squad rev-parse --short HEAD 2>/dev/null)+intent=$(shell git -C deps/agent-intent rev-parse --short HEAD 2>/dev/null)
 VERSION    := $(shell git describe --tags --always --dirty 2>/dev/null)+$(COMBO)

-.PHONY: help sync status build frontend svc svc-list svc-info svc-commits svc-history svc-update svc-recover svc-watchdog test-backend test-backend-pg test-multi-instance test-lifecycle test-regulations-kb test-frontend test-ui test-core test-agentcmd test-pins test-libs dev pin clean setup precheck task-triage task-triage-decide task-start task-resume task-sync task-close task-finish task-pr-check ci-wait facts-verify evidence version agent-exec-validate agent-exec-apply agent-exec-admit
+.PHONY: help sync status build frontend svc svc-list svc-info svc-commits svc-history svc-update svc-recover svc-watchdog test-backend test-backend-pg test-multi-instance test-lifecycle test-regulations-kb test-frontend test-ui test-core test-agentcmd test-pins test-libs dev pin clean setup precheck task-triage task-triage-decide task-start task-resume task-sync task-close task-finish task-pr-check ci-wait facts-verify evidence version agent-exec-validate agent-exec-apply agent-exec-admit image-build image-verify

 version:
 	@echo "agent-system $(VERSION)"
@@ -99,6 +99,8 @@ help:
 	@echo "make dev         开发模式说明（前后端分离热更新）"
 	@echo "make pin         推进 submodule 指针到各仓远端 main（提交前须 make test 通过）"
 	@echo "make status      submodule 状态"
+	@echo "make image-build 构建 Docker 测试环境镜像 agent-system-test-env:dev"
+	@echo "make image-verify 运行镜像内环境自检 verify-env.sh"
 	@echo "make agent-exec-validate  校验 AGENT-EXECUTION.md（scripts/agent-exec validate，经 dm-server agent-exec）"
 	@echo "make agent-exec-apply RECEIPT=<path>  快进当前分支到成功收据的 transport"
 	@echo "make agent-exec-admit  校验暂存路径具备 transport 来源或属于 host 豁免"
@@ -118,6 +120,12 @@ agent-exec-apply:
 agent-exec-admit:
 	scripts/agent-exec admit --repo .

+image-build:
+	docker build -t agent-system-test-env:dev docker/
+
+image-verify:
+	docker run --rm --shm-size=1g agent-system-test-env:dev /usr/local/bin/verify-env.sh
+
 sync:
 	git submodule update --init --recursive --jobs 8

@@ -0,0 +1,50 @@
+FROM --platform=linux/amd64 ubuntu:24.04
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV PLAYWRIGHT_BROWSERS_PATH=/opt/ms-playwright
+ENV PATH=/usr/local/go/bin:/usr/local/lib/nodejs/node-v26.10.0-linux-x64/bin:${PATH}
+
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends \
+        ca-certificates \
+        curl \
+        git \
+        libatomic1 \
+        make \
+        openssh-server \
+        sudo \
+        xz-utils \
+        software-properties-common \
+    && add-apt-repository -y ppa:deadsnakes/ppa \
+    && apt-get update \
+    && apt-get install -y --no-install-recommends \
+        python3.14 \
+        python3.14-venv \
+    && python3.14 -m ensurepip --upgrade \
+    && ln -sf /usr/bin/python3.14 /usr/local/bin/python3 \
+    && ln -sf /usr/bin/python3.14 /usr/local/bin/python \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN curl -fsSL https://go.dev/dl/go1.27.1.linux-amd64.tar.gz -o /tmp/go1.27.1.linux-amd64.tar.gz \
+    && rm -rf /usr/local/go \
+    && tar -C /usr/local -xzf /tmp/go1.27.1.linux-amd64.tar.gz \
+    && curl -fsSL https://nodejs.org/dist/v26.10.0/node-v26.10.0-linux-x64.tar.xz -o /tmp/node-v26.10.0-linux-x64.tar.xz \
+    && mkdir -p /usr/local/lib/nodejs \
+    && tar -C /usr/local/lib/nodejs -xJf /tmp/node-v26.10.0-linux-x64.tar.xz \
+    && npx -y playwright@1.64.0 install --with-deps chromium \
+    && rm -f /tmp/go1.27.1.linux-amd64.tar.gz /tmp/node-v26.10.0-linux-x64.tar.xz \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN userdel -r ubuntu 2>/dev/null || true \
+    && groupdel ubuntu 2>/dev/null || true \
+    && groupadd --gid 1000 dev \
+    && useradd --uid 1000 --gid 1000 --create-home --shell /bin/bash dev \
+    && echo "dev ALL=(ALL) NOPASSWD:ALL" > /etc/sudoers.d/dev \
+    && chmod 0440 /etc/sudoers.d/dev \
+    && printf '\nPermitRootLogin no\nPasswordAuthentication no\nPubkeyAuthentication yes\n' >> /etc/ssh/sshd_config
+
+COPY --chmod=755 entrypoint.sh /usr/local/bin/entrypoint.sh
+COPY --chmod=755 verify-env.sh /usr/local/bin/verify-env.sh
+
+EXPOSE 22
+ENTRYPOINT ["/usr/local/bin/entrypoint.sh"]
@@ -0,0 +1,57 @@
+# Docker 测试环境镜像说明
+
+## 用途与边界
+
+本目录用于定义一个可重复构建的隔离测试环境镜像，供后续用该镜像启动一次性容器、挂载当前仓库做隔离测试。
+
+- 该镜像只提供测试运行环境，不包含仓库代码。
+- 该镜像不包含任何密钥、私钥或凭据。
+- 本仓正式交付流程仍以非容器化路径为准，此镜像仅用于辅助隔离测试。
+
+## 构建与自检
+
+在仓库根目录执行：
+
+```bash
+make image-build
+make image-verify
+```
+
+- `make image-build`：构建镜像 `agent-system-test-env:dev`。
+- `make image-verify`：运行镜像内环境自检脚本 `/usr/local/bin/verify-env.sh`。
+
+## 启动测试容器示例
+
+```bash
+docker run -d --name asdev-test --shm-size=1g -p 127.0.0.1:2222:22 -v ~/.ssh/id_ed25519.pub:/home/dev/.ssh/authorized_keys:ro -v $PWD:/workspace agent-system-test-env:dev
+```
+
+说明：
+
+- `authorized_keys` 挂载源可以替换为任意可用的 `.pub` 公钥文件。
+- 容器内 SSH 登录用户为 `dev`。
+- `dev` 用户已配置 sudo 免密。
+
+进入容器：
+
+```bash
+ssh -p 2222 dev@127.0.0.1
+```
+
+## 容器内最小测试流程
+
+```bash
+cd /workspace
+make sync
+cd modules/frontend
+npm ci
+npx playwright test
+```
+
+说明：镜像已内置 `PLAYWRIGHT_BROWSERS_PATH=/opt/ms-playwright` 下的 Chromium，通常无需在容器内再次执行 `playwright install`。
+
+## 安全说明
+
+- 容器内无密码登录，仅允许公钥认证。
+- 每个容器实例在启动时独立生成 SSH host key。
+- 不要将生产凭据、私钥或其他敏感文件带进容器。
@@ -0,0 +1,23 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+mkdir -p /run/sshd
+ssh-keygen -A
+
+install -d -m 0700 -o dev -g dev /home/dev/.ssh
+
+if [ -f /home/dev/.ssh/authorized_keys ]; then
+    tmp_authorized_keys="$(mktemp)"
+    cp /home/dev/.ssh/authorized_keys "${tmp_authorized_keys}"
+    install -m 0600 -o dev -g dev "${tmp_authorized_keys}" /home/dev/.ssh/authorized_keys 2>/dev/null || {
+        chown dev:dev /home/dev/.ssh/authorized_keys 2>/dev/null || true
+        chmod 0600 /home/dev/.ssh/authorized_keys 2>/dev/null || true
+    }
+    rm -f "${tmp_authorized_keys}"
+fi
+
+if [ "$#" -gt 0 ]; then
+    exec "$@"
+fi
+
+exec /usr/sbin/sshd -D -e
@@ -0,0 +1,50 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+fail_expect() {
+    local expected="$1"
+    local actual="$2"
+    echo "校验失败: 期望: ${expected}"
+    echo "校验失败: 实际: ${actual}"
+    exit 1
+}
+
+command -v git >/dev/null 2>&1 || fail_expect "git 可执行文件存在" "git 不存在"
+command -v make >/dev/null 2>&1 || fail_expect "make 可执行文件存在" "make 不存在"
+
+go_version="$(go version 2>&1 || true)"
+[[ "${go_version}" == *"go1.27.1"* ]] || fail_expect "go version 输出包含 go1.27.1" "${go_version}"
+
+node_version="$(node --version 2>&1 || true)"
+[[ "${node_version}" == "v26.10.0" ]] || fail_expect "v26.10.0" "${node_version}"
+
+npm_version="$(npm --version 2>&1 || true)"
+[[ -n "${npm_version}" ]] || fail_expect "npm --version 有输出" "空输出"
+
+python_version="$(python3 --version 2>&1 || true)"
+[[ "${python_version}" =~ ^Python\ 3\.14\.[0-9]+$ ]] || fail_expect "Python 3.14.x" "${python_version}"
+
+if ! sshd_output="$(sshd -t 2>&1)"; then
+    fail_expect "sshd -t 检查通过" "${sshd_output}"
+fi
+
+id dev >/dev/null 2>&1 || fail_expect "用户 dev 存在" "用户 dev 不存在"
+
+sudo_list="$(sudo -l -U dev 2>&1 || true)"
+echo "${sudo_list}" | grep -q "NOPASSWD" || fail_expect "sudo -l -U dev 含 NOPASSWD" "${sudo_list}"
+
+if [ "${PLAYWRIGHT_BROWSERS_PATH:-}" != "/opt/ms-playwright" ]; then
+    fail_expect "PLAYWRIGHT_BROWSERS_PATH=/opt/ms-playwright" "${PLAYWRIGHT_BROWSERS_PATH:-<未设置>}"
+fi
+
+chromium_path="$(
+    find /opt/ms-playwright -type f \( -name headless_shell -o -name chrome \) 2>/dev/null | head -n 1
+)"
+
+[ -n "${chromium_path}" ] || fail_expect "在 /opt/ms-playwright 下存在 headless_shell 或 chrome" "未找到可执行文件"
+[ -x "${chromium_path}" ] || fail_expect "chromium 可执行文件具有执行权限" "${chromium_path} 不可执行"
+
+chromium_dom="$("${chromium_path}" --headless --no-sandbox --disable-gpu --dump-dom about:blank 2>&1 || true)"
+echo "${chromium_dom}" | grep -q "<html" || fail_expect "chromium --dump-dom 输出包含 <html" "${chromium_dom}"
+
+echo "verify-env: PASS"
@@ -0,0 +1,36 @@
+# 快慢通道 O2 I1（Agent-Native `route_contract_eof`）：阶段 6 评审包
+
+- 状态：**用户阶段 6 通过（2026-10-20）**，接受第 3 节第 1 条的 C2 编号，并要求启动 I2。Agent-Native #48 已合入 main（`2fc66be`）。I3（Dev 改钉）待 I2 后启动，P1 付费探针另提资源方案。
+- 日期：2026-10-20；作者：host；Dev 任务：`feature/fast-slow-o2-i1-agent-native`。
+- 依据：[阶段 4 方案](2026-10-19-fast-slow-o2-route-contract-eof-design.md)与[阶段 5 计划 §2](../plans/2026-10-19-fast-slow-o2-route-contract-eof-plan.md)（用户 2026-10-20 通过；C2 同时接受 `http2_stream` 与 `known_length`+`match`）。
+- 交付对象：Agent-Native 草稿 PR [#48](https://git-home.u1680832.nyat.app:30319/weichen/Agent-Native/pulls/48)，base `9c24e22`（origin/main），head `899fd70`。
+
+## 1. 交付内容
+
+| 方案条目 | 实现 | 位置 |
+|---|---|---|
+| 路由合同与身份绑定（§4.1） | `RouteContractEOF{Model, BaseURL, IdentitySHA256}`、`RouteContractIdentity`、`NormalizeRouteBaseURL`（仅 https，含 userinfo/query/fragment 一律不匹配）；`Client.RouteContract` 为 nil/零值即关闭；重定向逐项比较 scheme、host、port、path | `runtime/llm/route_contract.go`、`client.go` |
+| 解析器延后判定（计划 §2.2） | 公开 `ParseSSE` 签名与零值行为不变；内部 `parseSSE(…, sseHooks)` 只在“有工具且缺 `[DONE]`”时把成功候选与今天的失败事件一起交给传输层；新增 `finishChunks`、`multiChoice`、`fragmentAfterFinish` 统计 | `runtime/llm/sse.go` |
+| 放行条件 C1–C9（§4.2） | 按顺序判定，记录第一个不满足的编号；放行时 `StreamComplete=false`、`CompletionBasis=route_contract_eof` | `route_contract.go` `check` |
+| 参数 schema 子集（§4.3） | 新包 `runtime/argschema.Validate`，由 `validateArgs`/`matchesType` 逐字迁移；registry 改为委托 | `runtime/argschema/`、`runtime/tools/registry.go` |
+| 可观测性（§4.4） | `Event.CompletionBasis`；`TerminalObservation.completionBasis`/`contractCheck`（仅枚举值）；`[DONE]` 成功路径记 `done_marker` | `types.go`、`client.go` |
+
+## 2. 验证
+
+- 实施：Cursor worker（`agent-exec`，attempt 2 success；attempt 1 因单元包 `allowed_paths` 误用 `**` 被判 scope-expansion，修正写法后经用户授权全新重跑），`agent-exec apply` 快进集成。
+- host 验证（SELF）@`899fd70`：改动文件 `gofmt` 合格；`git diff --check`；`go vet ./runtime/...`；`go test ./runtime/llm/... ./runtime/argschema/... ./runtime/tools/... -count=1`（另跑 `-race`）与 `go test ./... -count=1` 全部通过。
+- CI（GATE）：PR #48 head `899fd70` 三项检查 success（`ci / vet-and-test`、`ci / docker-checkout-hostgateway`、`governance / governance`）。
+- 独立 Review（全新会话 code-reviewer，只接收需求、base/head 与 diff；评审者自跑为 SELF）：**PASS，无阻塞项**。确认零值合同行为不变；拒绝事件与合同关闭事件除 `contractCheck` 外 `reflect.DeepEqual`；`argschema` 与旧实现逐行一致；无数据竞争；计划 §2 测试矩阵每一行都有带断言的用例，并同时断言 Usage 保留与放行次数。
+
+## 3. 需人审确认与非阻塞项
+
+1. **C3 行的编号差异**：计划写的是 HTTP/2 `RST_STREAM`/中途断连期望 C3，实现返回 **C2**。原因是 C2（传输边界）先于 C3 判定，断流时没有见到 EOF，先在 C2 失败。结论同样是拒绝，`contractCheck` 记录的是“第一个不满足的条件”，不一定是根因。请确认接受。
+2. **无工具的错误终态也会带 `contractCheck`**（非阻塞）：合同开启时，纯文本流遇到供应商错误这类终态也会补一次判定（如记为 `C2`），这类流本来就不可能放行。不影响验收条件 3，也不泄漏内容；可在后续把补判限定为含工具调用的终态。
+3. **重复 `finish_reason` 会被 C4 拒绝**（非阻塞，失败关闭）：若供应商在 usage 块里重复 `finish_reason`，一律拒绝。MiniMax 真实流是否这样，列为 P1 付费探针的观察点。
+4. **测试可加强**（非阻塞）：`release/http2` 与 `close-delimited` 用例可直接断言 `BodyBoundary.FramingClass`；补一个“合同开启时纯文本流不变”的回归用例（评审者已用临时探针确认行为不变）。
+
+## 4. 下一步（通过后）
+
+1. 合入 Agent-Native #48（组件仓，无需 #518 窗口）。
+2. 启动 I2（Backend：系统层配置键、`openLLMClient` 按身份挂合同、透传 `completionBasis`；启动前核对 Backend 是否有读 `StreamComplete` 的工具门控）。
+3. I3 Dev 改钉组合验证；P1 另提资源方案。
@@ -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 |