Repository navigation
fix(chat): preserve the first Goal's registered conversation - #8798
Conversation
Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com>
Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com>
There was a problem hiding this comment.
Reviewer: model_agent; GPT-6; OpenAI; self_reported
Approval conclusion (author-owned PR; GitHub blocks formal self-approval)
动机 / Motivation
默认 Codex 创建 Goal 的用户,需要从创建回执重新进入原工作会话。 以前进入 Goal 可能打开另一条会话,丢失原回复的连续性;现在从同一回执进入已保存的原会话,重试不会选择后来创建的会话。 这种分离会增加寻找原回复、重新解释上下文和重复打开的恢复成本。已验证原会话、历史和后续普通回复保持同一身份,未知身份停止恢复并显示原操作的恢复入口。 本次不自动产生可信检查器,不将普通回复作为 Task 验收,也不宣称真实模型、完整 R1 或安装版 M3 已资格。 真实模型、自动可信检查器、context 保留、完整成本及 D2/D5 组合与完整目标回归仍未资格。
当前评审固定 #8798 的 head 177eedd092b582e22677dc57f399146559f327ad,base 与实际 merge-base 为 6dfd1c90c4c1a186c43de0a2c05243fa14b5a76e。它交付一个可逆、可独立验证的原会话入口增量,避免只补 serializer 或后台 helper 而仍无法进入原历史。原 Goal apply 的授权轮次保留;新入口无需重复输入已有 Goal、Agent 或 Session,也没有增加确认轮次。未知原身份的停止是已有正确性边界,恢复由原状态 owner 负责。
改动思路 / Approach
创建身份、持久化会话与导航各复用现有 owner;后端单独修复不能让用户重新进入原历史,另建注册表或执行管线没有必要。 本 PR 交付默认 Codex 的原注册会话入口和已发布 Session 恢复增量,保持旧会话及普通消息语义。 TypeScript presentation/Core 决定新默认身份,Chat owner 保存并复核原 Session,前端只投影地址并通过既有 managed discovery/history 再验证。相比不修复、让用户手动追踪 Session id 或新建注册表,这条路径同时保留原工作、历史和真实权限边界。Session IO 已在既有 session_open.py 内复用;没有第二个执行管线、永久状态库、HTTP exact-id 参数或新 editor。
| 触发 | 旧行为 | 本次结果 |
|---|---|---|
| 新的默认 Codex Goal | 未分配 Goal 会话、重入可能另开 | 创建操作绑定原 registered Session,回执进入原历史 |
| 响应丢失或同路由出现后来 Session | latest 可能选另一条 | 仅复用原已发布 identity;未知/不明确 metadata hold |
| 旧 recorded Session、显式 native budget、其他 endpoint | 原有路径 | 保留原身份与 non-routing 输出 |
| 已标记但无效的回执或源失败 | 可能借用/另开 | 错误与读回恢复;reconnect 只刷新 reader |
具体改动 / Changes
关键代码讲解
- compileActionReviewPlan 只为未打开过 Session 的新默认 Codex 创建操作给出注册身份。已保存的 Session/Turn、显式 token budget 和损坏 checkpoint 继续由原恢复契约处理;这个投影不证明 Task 已执行或验收。
- ChatActionService._apply_goal_create 从原创建操作导出稳定的 Session id,绑定原 client Turn,并在打开、重试和回执交付前重新读取实际 Store/checkpoint。它不再用“最新会话”代替原会话,也不直接相信 Runtime 返回的旧快照。
- Session 恢复入口 核对原 Goal、Agent 与记录的路由;注册 Session 还核对 lifetime/workspace。历史恢复枚举实际目录,metadata 缺失、被重定向或无法证明原操作时停止,避免把未知状态当作不存在。旧 legacy Session 保留原身份,不补造缺失的注册关系。
- ChatRuntimeController.open_session 的内部 exact-id 接口要求 mode=new,锁覆盖观察、打开与持久化。已存在的 exact Session 只返回原记录,不重配 adapter/defaults;未传 id 的原调用者仍走既有分支。HTTP 没有获得任意 exact-id 创建入口。
- goalCreatedManagedSession 将已验证创建回执投影为已有导航地址,由现有 resolver/history 再验证。Dashboard 原子选择 Goal、Agent 和原 Session;legacy 回执仍进入 overview,无效 managed 回执显示恢复入口。重新连接只刷新读取,不启动 Task 或新会话。
create_session 的严格目录保留没有改为覆盖写。exact existing 返回原 metadata,不调用 ensure_adapter、新 defaults 或状态复活。新/恢复/最终 receipt 都读实际 Store 和当前 checkpoint;原 Turn 仍绑定 client_turn_id/message。goalCreatedManagedSession 核对 applied/verified creation、Goal/Agent/channel/Session 与显式 lifetime,再原子设置 URL;registered directory、readOnly、abort 与 history scope 检查继续由现有 owner 负责。ordinary first/subsequent reply 没有 execution_control,原 Task 仍需独立 canonical checker。
最后从 3688a1f612b6f92b9bc7baa581eefd9efbf6990d 到本 head 仅三行测试 delta:将 expected/failed artifact 内容先赋给局部变量,再插入 f-string;checker oracle、valid/missing/failed 内容与后置条件不变。此前 Python3.11 grammar P1 已在本 head 独立 Ruff stdin、隔离3.11 compile 和六个 File/SQLite owner-check 案例中解决。三个 recovery P1 的七例独立证据与本 head 四个生产源码 SHA256 完全相同,已显式核对复用条件。
验收依据是修改前的公共 RFC:https://github.com/loopx-project/loopx/blob/6dfd1c90c4c1a186c43de0a2c05243fa14b5a76e/docs/architecture/rfcs/monorepo-distribution-split-v0.md ,spec revision 6dfd1c90c4c1a186c43de0a2c05243fa14b5a76e。本 PR 追加中英 checkpoint,没有重写旧验收为本次测试结果;以下整体资格仍 deferred:
| criterion_id | 本 head 的 disposition 与剩余证据 |
|---|---|
| V1 | deferred:尚未证明选定组合的完整 install/load/activation 闭包。 |
| V2 | deferred:本轮原 Task 的正负路径已验证;双 preset 的完整权限、恢复和一次结算资格仍待证明。 |
| V3 | deferred:保留了 reducer/Runtime 兼容证据,尚未完成全部支持命令及缺失 Node/provider 的差分语料。 |
| V4 | deferred:本轮覆盖已发布 Session 的恢复;真实模型任务、未知 native 效果协调与完整恢复成本仍待验证。 |
| V5 | deferred:原历史可读回;模型 compaction/lost-ACK 保留和安装版 context 资格仍未完成。 |
| V10 | deferred:没有匹配的完整成本比较,测试数量与本轮行数不能替代它。 |
| R1 | deferred:V1–V5/V10 的完整组合资格尚未满足,本轮仅交付入口与已发布会话恢复增量。 |
| M3 | deferred:需在独立安装中重做合格的 R1/R2 journey;本轮不发布或资格化 split packages。 |
| D2 | deferred:完整 core capability 选择及闭包仍由既有 owner 继续核定。 |
| D5 | deferred:精确 host/storage 组合还需真实任务及恢复证据,不能只凭合成测试确定资格。 |
生产增量集中在 Session/presentation owner:Runtime 2,503→2,524 行、Any38 不变;ChatActionService Any52 不变;Session entry owner224/Any5。reviewed regression ceiling 与同域消费价值一同记录,默认上限、持久化/权限门和冻结标准不变。example fake 现在使用真实 Chat completion owner保存普通回复,而不是伪造 Goal/Task 成果;测试与 paired RFC 补足原路径与边界,没有因测试数扩大资格。
对主干的风险 / Risks
本轮正负路径有实际 owner 验证:最终源码的首次 Goal、Session 与 workspace 共 96 项通过;Python 3.11 的 valid/missing/failed 检查在 File/SQLite 六条原 Task 路径通过。三个恢复缺陷的七个独立探针全部通过,受审生产文件与本 head 的哈希相同。packaged frontend 连接真实 SQLite/Chat,合成 Codex 验证创建、原历史、普通后续消息、reload、失效与一次重连;首尾只有一个 Session、一个 native thread,验收状态仍为 unverified。
兼容证据保留准确来源:106 项 Runtime 语料在不可变 base 与较早候选均通过;最后 exact-id 门只作用于新增非空参数,旧 None-id 分支未变,最终受影响 Runtime 26 项补验通过。TS reducer 的 27 项测试与 56 组 base/head 向量通过;旧实现的三个注册路由断言失败,四条 legacy 反例仍通过,证明该 oracle 对目标差异敏感。前端与已观察 packaged tree 48aabf0748bc4df9ea00511414d58d7f3f226ced 相同,这些截图没有被冒充最终模型输出。
本 head 的 premerge 为 6 项直接检查、16 项选定检查全部 PASS。两张 WebP 的像素与 metadata 已人工检查:1440×960 与 390×844,只有公共合成内容,没有 EXIF 或私有路径。自动文本扫描不能替代这项人工检查。与 CI 相同的本地依赖锁/模块预算七项测试及完整指定 Ruff 目录也通过。
完整 control-plane typecheck 仍 FAIL:相同 npm run typecheck:control-plane 在不可变 7f74fb7a032fb4400c1320f2bf1ea6c364d751ce(tree 等于 base6df)与候选均报告 coordination_runtime_shadow.test.ts:380 的 TS2345。其因果路径未变,受影响 reducer 的 scoped typecheck 与正负测试通过,因此是已证明的既有失败。旧 3688 head 的 kernel-static CI 失败原因仍未知;最终 177 packet 只观察到九项 pending。当地验证不等于远端 CI 通过,merge-readiness 继续判断其实际状态。
最新 C1 #8266 固定为 aa3bc29b6d403402f0d8c31ba8a2370e119b5dbe,与本 head 的组合 tree 为 01ba7590152dcf2a8b31be1e436cbdd12ba6f0e6,无冲突。相关 Session、Native Task validation 与 context owner 源码与已验版本一致;新增结算/bootstrap 路径补验为原 Task 6 项、原 Turn 结算 14 项、实际 bootstrap 4 项、TS 191 项及 typecheck 全部通过。新的独立 Core wheel 包含 12 个实际变动 payload,wheel/source/installed 字节一致,对应安装测试参数化后 16 项通过。这只支持这些当前生产边界,不批准 C1 整体 cutover。
保留负面证据:旧 e7b 组合的独立 Core 回归为 38/39,一项深路径 context frame 达 4,009 字节,超过原有 4,000 字节限制;短 TMP 下相同 wheel/interpreter/cap/oracle 的单例重放通过,不能把原失败改为 39 项全通过。真实 native 模型尝试也因所选模型不受账号支持而失败。未持久化的 native thread-start、自动可信 checker、真实模型/context、完整成本、D2/D5 与完整 R1/M3 仍未资格。
补充 CI 核查:node-minimum-compatibility 与 typescript-core (1/3) 的实际失败均是上述同一 TS2345;本轮 routing 在 Node 22.22.3 下 27 项通过。typescript-core (2/3) 的 digest guard 在不可变 base6df 与本 head 用相同命令重放,均指向未改动的 native_child_result_inbox.ts:109,完整错误一致。新 Python Session id 不在该 TypeScript scanner 的输入范围内,两个失败均保留为既有失败。
Windows 的 cli-output-budget-regression-smoke 在生成基线回执、执行 pinned detail reader 时发生 WinError2,head probe 尚未开始。涉及的 fixture、renderer 和 reader 在 base/head 全部相同,且没有经过本轮新 Session 路由;没有取得 Windows 双臂通过证据,也没有将其归为基础设施故障。它保留为未解决的 Windows CLI/context 资格缺口与 CI hold。当前 Session、Task、minimum Node 和 C1 改动边界有独立通过证据,code approval 与这个 hold 分开判断。
我的整体评价 / Verdict
已查看实际桌面和 390px 页面,以及长双语内容和 source-unavailable 状态;原回复、输入与恢复入口可见,长内容保持滚动。 这些是 packaged SQLite/Chat 与合成 Codex 回复的展示证据;真实模型质量、完整 Task 成果与 installed V5 不在该视觉资格内。
在已发布原 Session 的范围内,long_horizon=improved、user_experience=improved:回执直接进入原回复与后续普通消息,响应丢失不会借用后来会话,失效后仍有明确读回恢复。已知 Goal/Agent/Session 无需重新输入,没有新增确认轮次;完整长内容和错误仍可读取。source failure 时的通用 executor 提示是保留的展示限制。
创建身份、持久化会话与导航各复用现有 owner;后端单独修复不能让用户重新进入原历史,另建注册表或执行管线没有必要。 本 PR 交付默认 Codex 的原注册会话入口和已发布 Session 恢复增量,保持旧会话及普通消息语义。
本 head 没有未解决的阻断 finding,支持 APPROVE 这个可逆的入口和已发布会话恢复增量。它没有把测试数、metadata、合成答复或一次安装读回当作完整 R1 成果。保留原十项要求,以及完成原目标前的完整回归;真实任务/模型恢复、自动检查来源、context 保留、默认闭包和可比完整成本仍需继续。准确版本评审、CI/readiness、合入授权分别判断。依已有维护者授权,本增量可使用 admin bypass 处理 GitHub/CI hold;这不取消失败记录或 Windows、模型及完整 R1 的资格要求。
English verdict: APPROVE - head 177eedd; original published-Session creation, readback and re-entry are independently validated, including the current C1 shared boundaries. No blocking finding remains. Full R1/M3, real-model and complete-cost qualification remain open.
…000 commits (#8759) * Deliver verified images in private Lark answers Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Keep image retries behind new private Lark replies Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Recover missing images from one verified private Lark reply Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Use one wall clock for private Lark image retries Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Recheck the original Lark reply before historical image writes Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Verify private Lark image sources before every redirect Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * feat(coordination): add postgresql authority checkpoints and local-to-pg-seed exporter - Add authority_checkpoints table DDL and tenant-scoped RLS policies. - Store incremental delta in authority_commits and bounded checkpoints every 64 commits and on genesis cursor 1, resolving table bloat and the 20,000 commit recovery ceiling. - Implement scanCommitted bounded delta replay from covering checkpoint via AuthorityStateReplay. - Add setupPostgreSqlAuthoritySchemaAndRole for explicit schema installation and least-privilege restricted role assembly. - Add exportLocalToPgGenesisSeed with sanitization (expired leases, local absolute paths, .local/ references, Feishu IDs, private materials) and fail-closed privacy boundary scan. - Add loopx postgres setup and loopx postgres local-to-pg-seed CLI commands. - Add test suites for checkpoints, sanitization, role assembly, and CLI invocation. Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Recheck the historical Lark reply before each media write Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Retry Lark image uploads after an explicit App scope rejection Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Honor original Lark stop and closure before deferred images Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Recheck private answer control after Lark source read Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Read the current Core session after delayed image controls Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Fence private answer media dispatch with original controls Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Keep Lark media checks with private delivery Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Recheck Lark image sources after recording upload intent Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Read both original Feishu messages together before media upload Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Verify Feishu sources at the guarded image dispatch Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Preserve pre-dispatch Feishu source and session validation Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Recover and verify PostgreSQL checkpoint history with append-only privileges Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Verify backup history to its captured cursor beyond 20000 commits Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Generate explicitly synthetic secret fixtures at test time Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Recover private image uploads when the Lark CLI cannot start Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * fix(chat): preserve the first Goal's registered conversation (#8798) * fix(chat): preserve the first Goal's registered conversation Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> * test(chat): keep original Goal adoption compatible with Python 3.11 Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> --------- Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> * Avoid rereading delivered Lark settings records and empty queues Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Recover private Lark images after a CLI descriptor limit Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Enable existing checks and the original authorized Task in managed Chat Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> * Reuse the canonical boundary projection and narrow Task JSON types Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> * Keep confirmed Goal creation attached to its original Task (#8805) Reuse the existing C1 source observation guard Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> * Assert the lease source probe returned an observation (#8796) (cherry picked from commit 2c099be) Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Recover an owed replan debit before the next host Turn (#8794) * Recover an owed replan debit before the next host Turn Consider the original Todo binding when an admitted replan has verified writeback. Require the exact spend receipt before another guard grants delivery, even if the Todo lifecycle has changed. Keep explicit selection on the same recovery path and let the existing settlement owner replay the original debit. Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Preserve ordinary completed-Todo successor admission Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Replay one validated Turn debit across concurrent observations Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Validate original Turn spend terms before debit and replay Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> --------- Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Keep conversation history rendering off the typing path (#8781) Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * feat(coordination): complete remote task lifecycle and opt-in gateway access (#8747) (#8765) * feat(coordination): add complete remote task lifecycle and opt-in gateway access (#8747) Align with PR #8747 (multi-loopx-agent-cloud-collaboration-v0) and remote-authority-task-service-v0 (#8508): 1. Extend RemoteAuthorityService with full remote task settlement: - Add 'complete', 'block', 'defer', 'todo_add', and 'snapshot' operations. - Enforce hard-lease fencing and claim-request ownership checks. - Settle completion receipts and deterministic cross-machine snapshot digests. - Maintain default-deny Tenant/Goal/Actor authorization and incarnation pinning. 2. Introduce controlled remote authority gateway in Python control plane: - Default-disabled access: local private Goals never connect to remote authority or leak local credentials. - Opt-in gateway metadata projection for explicitly configured goals and the 'loopx-quality-review' canary. - Fail-closed should-run health check when remote authority is unconfigured or unreachable. 3. Conformance and unit test coverage across TypeScript and Python suites. Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * test(coordination): assert subprocess readback before decoding Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * fix(coordination): qualify explicit remote task reads and lifecycle receipts Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * fix(coordination): preserve existing successors on remote completion Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * test(remote-authority): prove ordinary admission stays local Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> --------- Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * test(chat): preserve create-only intent in workspace selection smoke Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Defer material inventory during configuration discovery (#8807) Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> * Defer report providers during Turn reads Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> * test(core): require installed provenance before qualification Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> * Reuse the final source check for staged Turn requests (#8820) Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> * Defer PR wait provider loading until permission is checked (#8821) Load the optional PR reconciler only after the invocation-time observation permission check, inside the existing provider failure boundary. Preserve original permission, cadence, result and unknown-effect owners, and document the bounded default-closure and timing-window change. Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> * Load provider options only for the selected capability editor (#8822) Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> * docs: describe README session continuity directly (#8823) * Skip automatic usage observers for supported opt-outs (#8824) * Skip automatic usage observers for supported opt-outs Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> * Record installed Core and C1 observer qualification Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> --------- Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> * docs(blog): add EdgeBench controlled Context ON vs OFF 10-task score comparison (#8760) * docs(blog): add EdgeBench controlled Context ON vs OFF 10-task score comparison Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * docs(blog): use declarative mechanism-led opening in zh context-delivery score section Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> --------- Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * fix(heartbeat): preserve proven waits before their due time (#8825) Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Fix manager discovery in ordinary installs (#8830) * Package the manager discovery projection Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> * Record selected manager discovery distribution qualification Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> --------- Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> * test(workspace): verify confirmed Goal creation against the current contract (#8816) Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Fix Windows CLI output probe reader invocation (#8817) Port the probe fixture and native Windows regression coverage from e6eb92d and 8d200aa. Decode the generated PowerShell literals into argv before launching the pinned reader. Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * refactor(issue_fix): fold reviewer source trust/freshness vocabularies into one owner (#8826) reviewer_recommendation.py restated the trust and freshness sets that repository_context.py already owns. Import both as aliases of the owner objects so the decision has a single source, and add an architecture guard that pins single ownership by value, by identity, and by wiring through both public builders. REVIEWER_SOURCE_KINDS stays local (deliberately narrower). Signed-off-by: psychologister <230141834+psychologister@users.noreply.github.com> Co-authored-by: psychologister <230141834+psychologister@users.noreply.github.com> * fix(scheduler): reject superseded heartbeat receipts on the Python follow-up route (#8708) * fix(scheduler): reject superseded heartbeat receipts on the Python follow-up route The Python compatibility route for scheduler-ack-current/scheduler-fail-current checked only that the receipt for --turn-instance-id exists; a receipt already superseded by a newer heartbeat Turn still committed scheduler state, while the native TypeScript transaction rejects it as heartbeat_receipt_stale. Thread the Turn from build_scheduler_followup_payload through record_quota_scheduler_ack / record_quota_scheduler_ack_for_decision / record_quota_scheduler_failure_for_decision into _run_native_followup, which now sends turn_instance_id with require_heartbeat_receipt=true. The TypeScript transaction remains the single owner of the missing/stale/superseded fence (it also rechecks under the scheduler state lock); optional parameters keep the in-process API, which has no Turn, unchanged. Fixes #8605 Signed-off-by: Lihua <1017343802@qq.com> * Keep scheduler follow-up hint reads out of legacy migration Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> --------- Signed-off-by: Lihua <1017343802@qq.com> Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> Co-authored-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Resume the original quota settlement after lifecycle writeback (#8728) * fix(replan): resume settlement after lifecycle review writeback Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Recover committed replan settlement before rebuilding its review Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> --------- Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * fix(antigravity): keep the project registry in generated wakes (#8768) Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * fix(chat): keep workspace checker reads portable (#8814) Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Reject external Turn retries when the captured work changes (#8828) * Recheck captured work before launching an external Turn host Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Keep complete-source metadata assembly outside Turn planning Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> --------- Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Preserve PostgreSQL runtime access and recover seed output retries Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> * Validate recovery cursor metadata without a fixed history ceiling Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> --------- Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> Signed-off-by: lusendong.6789 <lusendong.6789@bytedance.com> Signed-off-by: psychologister <230141834+psychologister@users.noreply.github.com> Signed-off-by: Lihua <1017343802@qq.com> Co-authored-by: Lusen Dong <lusendong.6789@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> Co-authored-by: Lusen Dong <cicomaple@gmail.com> Co-authored-by: psychologister <st040325@gmail.com> Co-authored-by: psychologister <230141834+psychologister@users.noreply.github.com> Co-authored-by: Lihua <1017343802@qq.com>
Default Codex Goal creation now keeps its original registered Agent conversation. “Enter Goal” reopens that Session and its history; a lost opening response no longer selects a later conversation. Creation receipts re-read stored identity, and incomplete or unidentified historical reservations retain an explicit recovery hold.
The TypeScript presentation owner selects new-session identity. Existing Chat Session, Task validation and frontend discovery/history owners carry creation, replay and re-entry. Explicit native token budgets, recorded legacy Sessions and other endpoints keep their existing paths. Ordinary messages remain read-only Chat, and Task completion still requires its independent owner check.
RFC alignment
This is an R1/V2/V4 entry and recovery increment in the minimal-kernel/distribution RFC. Both RFC mirrors document the delivered boundary and remaining acceptance. It reuses C1's existing owners; combination validation is pinned to #8266 at
aa3bc29b6d403402f0d8c31ba8a2370e119b5dbeand does not qualify C1 cutover.The original full R1/M3, D2/D5 closure, automatic checker production, native-model/context and complete-cost acceptance remain open. Published-Session recovery does not prove recovery of an unrecorded native thread-start effect.
Validation
aa3bc29b6d403402f0d8c31ba8a2370e119b5dbe: six original-Task, 14 settlement, four bootstrap, 191 TypeScript cases and typecheck pass. Its fresh Core wheel matches source/installed payload; 16 affected installation cases pass. Earlier source 75/Runtime 26/Node 14 and Core 38/39 remain separately scoped. The earlier deep-path context reference measured 4,009 bytes against its retained 4,000-byte cap; a same-cap short-path replay passes but does not erase that failure or qualify full installed V5.coordination_runtime_shadow.test.ts:380; the scoped TypeScript check passes. Native-model qualification remains unverified. These limits are preserved rather than labelled green.Session IO is shared in the existing Session entry owner. The Runtime coordinator adds a bounded exact-opening seam; its reviewed line ceiling moves from 2,503 to 2,524 with unchanged
Anycounts and default limits.Visual evidence
These are the current original-conversation design references used by the RFC: packaged frontend, real SQLite/Chat backend, synthetic replies, desktop and 390px viewport. They illustrate presentation and retained identity, not real-model or Goal completion. Tested frontend/normal journey: source tree
48aabf0748bc; the final recovery guard is verified separately at this PR head. No layout redesign is introduced.Final CI/readiness also retains existing full-tree TS2345 and a base/head-identical digest guard failure. The Windows CLI differential stops in its baseline pinned reader before the candidate probe; its unchanged host-command boundary remains unqualified. Exact-head local/real-path validation passes; remote CI is not reported green.