loopx_turn_envelope_v0 is an additive, bounded read model over an already
computed quota should-run decision. It gives an agent the next action and its
safety contract without replaying every diagnostic lane in the full quota
payload.
This page describes the current versioned representation. The unified-contract RFC proposes replacing the live quota/envelope format choice with one complete contract, including differential delivery. Historical captures retain their original schema and signature; the proposal does not introduce a new CLI switch. The proposed composition point precedes capture and encoding. Today's action signature compares its registered projection; equality alone does not establish complete source-clause preservation or qualify the unified contract. The RFC's C1 caller replacement also covers the direct Turn producer and final host prompts. Quota CLI output parity alone does not qualify those consumers. Historical v0 decoding remains separate from switching new admissions to a future unified version.
中文：本页记录当前版本。统一契约提案 的终态是一份包含差分交付能力的完整契约，取消线上 quota/envelope 格式选择； 历史捕获保留原 schema 与签名。本次文档更新不新增 CLI 开关。 提议的组合点位于 capture 与编码之前。当前 action signature 比较其注册投影； 仅签名相等不能证明完整来源条款得到保留，也不能验收统一契约。 RFC 的 C1 消费链替换 还覆盖直接生产契约的 Turn 入口和最终 host prompt；仅 quota CLI 输出等价不能验收 这些消费者。历史 v0 解码与新准入切换到未来统一版本分别处理。
Preview it explicitly:
loopx --format json quota should-run --goal-id <goal-id> --agent-id <agent-id> --turn-envelopeFor a tool with bounded output, optionally capture the full decided payload before its display projection. Choose a new directory for each invocation, even when reentering the same Turn:
loopx --format json quota should-run --goal-id <goal-id> --agent-id <agent-id> \
--turn-instance-id <turn-id> --turn-envelope --decision-output-dir ./guard-001
cat ./guard-001/decision.json--decision-output-dir is valid only with quota should-run and an explicit
--turn-instance-id. Its parent must exist. LoopX creates the directory privately
(0700 on POSIX) before running the guard, rejects existing paths including
symlinks, and atomically publishes decision.json (0600 on POSIX) before printing
the result. The file contains the unprojected decision and its original receipt;
it excludes display-only host poll metadata. It can contain private Goal context:
keep it out of public artifacts. No capture is created without a capture option.
New captures use compact UTF-8 JSON with a final newline, retaining every value,
including whitespace inside strings. Readers accept existing indented captures;
recovery preserves their original bytes rather than rewriting their layout.
If a tool truncates the displayed JSON, read this file instead of rerunning the
guard merely to recover the observation. The file is not fresh authority:
Todo selection, lease changes, cancellation, quota changes or other required
revalidation still use a fresh guard invocation and a new capture directory.
Check the saved Goal/Agent/Turn identity before use; a cache filename does not
prove identity. Nothing here bypasses the owning mutation-time validation.
Capture also preserves decided rejection/diagnostic payloads; inspect ok before
acting. A late disk failure can happen after the guard has committed its receipt;
the CLI reports that boundary rather than claiming rollback. An empty capture
directory is not a usable decision. Omit the option to disable capture; remove
unneeded local captures through ordinary file management.
When both capture and --turn-envelope are requested, detail_ref.full_decision
points to the saved file using a quoted POSIX cat -- command. A file-capable host
can read detail_ref.captured_decision.path directly instead. The typed projector
includes the expected Goal/Agent/Turn and a reference to the existing canonical
source-decision hash (a hash of the JSON value, not the formatted file bytes).
Verify those against the read observation, including ok; the link itself does
not verify file integrity or make saved admission current. Missing, malformed,
or mismatched files require recovery, never automatic guard replay. Consumers already referring to full_decision, such as compacted capability
context and peer diagnostics, now read this same observation. Scheduler-specific
legacy detail requests are unchanged. Replan obligations and fresh selection/lease/quota checks retain their existing owners.
Without capture, the historical full-decision route remains available. Enabling
capture does not enable TurnEnvelope or change admission/settlement defaults.
This opt-in detail link does not change action-signature coverage.
中文：同时开启短包和完整 decision 保存时，详情入口读取本次保存的文件，不再 为补读上下文重跑 guard。读取前核对身份和源哈希；旧观察不提供新的执行权限。 文件损坏或丢失不能自动重跑，选 Todo、lease 变化等仍需按原契约重新准入。
The default ordinary quota CLI view may replace an exactly identical nested
heartbeat_recommendation.blocked_priority_fallback diagnostic with
blocked_priority_fallback_ref="$.blocked_priority_fallback". Read the complete
root field in that same packet; resolving this reference needs no new guard or
detail command. Different mirrors remain inline. Raw decisions, saved captures
and the existing --include-detail agent-todos view retain their original shape.
Action dimensions remain equivalent; the raw source hash still identifies the
specific original rendering and must not be substituted across views.
The existing packet owner supplies this compatibility projection, keeping the
CLI from becoming another reader of the legacy guidance field.
中文：普通 quota CLI 热路径将完全相同的 fallback 副本改为本包根字段引用，完整 事实仍在当前包内，不需再次执行 guard。不同副本和既有详细视图保留；原始决定与 capture 不变。动作维度等价不意味着不同渲染可以共用原始 source hash。
For a successful replan with --decision-output-dir or --decision-output-root,
the CLI and TurnEnvelope expose replan_action_packet.review followed by
writeback. Both are executable quota replan-view commands bound to the same
captured JSON value and source hash. The first read supplies goal context,
previous decision/results, planning dependencies and evidence references; the
second supplies the existing authoring shape and settlement commands. No read
runs another guard, writes a receipt or authorizes work. There is no additional
read acknowledgement, mandatory model call or prescribed route change.
The required review is the delivery owner for the captured Goal and planning horizon. The CLI entry and staged Host presentation do not repeat those bodies. They retain admission, selected work, required reads, authority and stop rules; the CLI also retains its current action portfolio for explicit selection. The signed executor envelope and complete capture remain unchanged. Each Turn must read its own review before deciding: a changed dependency or priority changes the source-bound reader even when native context delta transport is disabled. Uncaptured consumers keep the inline path. This changes presentation timing, not the Goal requirements or which work is authorized.
中文：必读 review 统一交付本次捕获的 Goal 与规划范围，CLI 入口和分段 Host 呈现不再重复这两份正文。入口保留准入、已选工作、必读项、权限与停止规则， CLI 也保留供显式选项使用的当前 action portfolio。执行器签名包和完整 capture 不变；每个 Turn 决策前须读取自己的 review。依赖或优先级变化会改变绑定源摘要的 读取命令，关闭原生差分时也生效。未捕获的调用保留原内联路径。这调整交付时序， 不改变目标要求或授权工作范围。
Captured reads retain the caller's explicit --cli-bin route, including later
acceptance and Explore reads; an ambient executable cannot silently replace it.
Without an explicit route, new captured readers use the current installed Python
interpreter's -m loopx.entrypoint route rather than an unrelated PATH executable.
Native reads propagate that route through review, acceptance and writeback; the
complete original observation is not rewritten to carry a new command.
The review stage provides structured facts without a prescribed diagnostic
method. Writeback omits filled-in Vision/stride examples while retaining field
limits, legal options, source bindings and settlement rules. Stride exposes its
required field names and basis options independently of examples. The unchanged
full capture remains available for optional examples and source inspection.
This intentionally reduces advisory prompting; it does not remove acceptance,
authority or stop obligations, nor demonstrate better autonomous decisions.
Cumulative outcome requirements are indexed by exact content hash. Every objective, revision and requirement count remains visible; the acceptance read returns the complete original outcome. Identical IDs with different revisions or evidence remain distinct. Equal context/horizon copies share references; differing goal scopes remain separate. The full capture retains all evidence, original guidance and authoring examples. Explore has an optional, separately readable basis; unavailable evidence remains unavailable. These views do not assess acceptance, infer execution from counts or make a dependency global.
The captured CLI Todo summary also reuses this outcome index when its complete acceptance contract exactly matches the reviewed Goal contract. Summary counts and selection facts remain intact; differing contracts or an existing summary index stay unchanged. This needs no extra read or native delta transport.
中文：捕获后的 CLI Todo 摘要若携带与复盘 Goal 完全相同的验收契约，也复用 同一验收索引，避免把已分段的细则重新整段交付。计数和任务选择事实保留； 不同版本或已有摘要索引不变。无需新增读取或开启原生差分传输。
quota replan-view --decision-file <file> --source-hash <hash> defaults to
--replan-stage review; writeback, acceptance --outcome-ref <ref> and
explore read the corresponding original-source detail. Missing/mutated sources
fail without guard replay. Existing uncaptured calls, old native journals
without a saved reader route, and direct structured Host requests without that
route retain their prior full-source delivery. Those consumers can retire the
legacy prompt only after retaining a valid original capture and executable
reader; a missing source is never replaced by a fresh guard. The existing generic
followthrough is now available with stride off; its result-class counts and
observations remain evidence, not successful-work or goal-gain verdicts.
Captured replans also reference Explore attachment syntax already present in the same captured writer instead of repeating it in the entry work context. This applies to default CLI/full recovery as well as optional delta delivery. Evidence, pagination, before-work feedback comparison, measurement provenance, optionality, privacy and lease-lifetime rules remain in the entry. Full authoring guidance and templates remain byte-for-byte in the writer. Only exact recognized guidance and matching fields with one captured Explore attachment qualify; unknown/custom text, differing templates, missing writers and uncaptured/non-replan calls stay inline. No new reader round trip or automatic evidence attachment is introduced.
捕获的重规划入口复用同一写回阶段已有的 Explore 附件说明，默认 CLI、完整恢复和可选 差分传输均适用。证据、分页、执行前反馈比较、测量来源、可选性、隐私与租约期限规则 仍在入口；完整写回说明及模板逐字保留。仅对已识别且完全一致、具有唯一捕获写回附件 的字段引用；未知或自定义说明、不同模板、缺少写回及未捕获或非重规划情形保持内联。 不增加读取往返，也不自动附加研究结论。
Live decisions replace the previous method checklist and duplicate stride planning advice with compact goal, evidence and authority boundaries. Review delivers those boundaries once, with the facts; writeback delivers the existing format. Eligible Todo order and agent-proposed candidate rules remain revisable planning choices, while original priorities, constraints, budgets and stops remain binding. Old captures retain their original text. This is an intentional change to advisory prompting, not a lossless claim about model behavior.
The benchmark checkpoint preflight uses the same CLI decision capture with TurnEnvelope off. It retains the complete captured source for checkpoint selection and verification, and sends the projected CLI view to the model. The view's review/writeback commands read that exact observation; capture does not rerun admission, change evaluation opportunities or select a strategy. Identical work-context acceptance copies use that same read; other revisions stay inline. A source exceeding the RPC request bound uses the existing bounded local-snapshot transport for pure projection, preserving both transport limits.
With native context delivery off, captured CLI and TurnEnvelope entries share one projection that defers the settlement plan/command list to the writeback read instead of printing both. The signed settlement identity stays inline for the outer Turn executor; the reader returns the complete canonical plan. The required review retains the current Core Goal and planning horizon; these bodies are not repeated in the model entry. Only cumulative acceptance detail is indexed; dependency, priority, blocker and plan changes remain visible in that Turn's review. This uses the existing optional full/delta owner, not a new cache or acknowledgement. Its default-off path needs no retained baseline.
New native Turn journals bind the same readers to their original observation without rewriting it or inventing a quota receipt. Native Codex and structured Hosts use the shared review-before-format instruction. The Codex model receives verified Turn authority and reader routes while its journal and executor retain the full signed envelope. The model returns a semantic result; it does not run the CLI settlement sequence. A canonical replan attempt permits that semantic slice even when ordinary delivery is closed; explicit delivery denial/null, missing attempt, user and Stop restrictions retain their existing precedence. Full-source fallback remains available on the same capture. Whole-path cost must include entry, detail reads and recovery; indexing alone does not establish lower total cost or better decisions.
中文：关闭差分时，CLI 与短包入口也共享延后结算格式的投影，完整计划只在写回 读取时交付；外层仍拿到签名结算身份。每轮必读 review 保留当前 Core Goal 和 规划窗口，模型入口不再重复这两份正文；累计验收明细才索引读取，依赖、优先级、 阻塞与计划变化不可省略。新原生 journal 绑定同源读取，模型使用事实审视后再读格式，执行器保留完整签名包并独占状态、 额度与调度结算。规范 replan attempt 只允许该语义切片，不绕过显式拒绝、缺失 attempt、用户或 Stop 限制。旧 journal 与没有安全读取路由的调用继续读原包； 缺源只能恢复，不能重新准入补包。成本须计算全部读取及回退，不能只报告短包尺寸。 未显式指定 CLI 时，新读取命令固定当前已安装 Python 的模块入口，后续验收和写回 也沿用该路径，避免落到 PATH 中不支持该协议的另一份安装；原观察字节保持不变。
Selection, current admission and stop facts stay inline. Optional native full/delta presentation and full recovery carry this same CLI view; the original source remains unchanged for checkpoint qualification and authority inspection. For a captured autonomous replan with no admitted Todo and no Explore attachment in its settlement plan, the entry omits the current owner's unusable attachment syntax. It retains evidence, feedback, before-work obligations and independent graph commands, and explains that Todo-bound attachment is unavailable. Unknown guidance, missing binding proof and uncaptured reads remain unchanged. This neither grants attachment authority nor defers another required read.
中文：已捕获的纯自主 replan 没有准入 Todo、结算计划也没有 Explore 附件时，入口 不再投递当前不可用的附件格式。事实、反馈、工作前义务及独立图谱记录入口完整保留， 并说明附件需要 Todo 身份。未知指令、缺少绑定证明或未捕获的读取保持原样；这不增加 附件权限，也不增加必须执行的后续读取。
Writeback also offers refresh-state --settle-turn: after successful writeback
and delivery postconditions it follows the canonical owed quota command for the
same Goal, Agent, Todo/obligation and Turn, then verifies receipts. It collects no
guard, changes no binding and performs no Todo completion. Failed validation,
unsatisfied checkpoints, dry runs and no-spend closeout cannot debit quota.
An ambiguous response is reconciled through the original receipts; exact retry
cannot debit twice. Ordinary refresh without the option retains its behavior.
When --delivery-workspace-path names the producing worktree, the combined
operation also runs the owed command there, using the originating CLI's
implementation. The normal workspace and settlement guards still apply; a
missing or incompatible workspace leaves the original owed command recoverable.
An in-flight recommendation does not require keeping a completed Todo open.
Validate its original declaration, use ordinary completion when satisfied, and
write semantic closeout with an evidence-linked vision decision on the original
Turn. Unfinished bounded progress may retain the open Todo. On a fresh Turn,
an explicit prior closeout or typed path_delta.outcome=replan releases the old
continuation preference for ordinary eligible selection; it does not complete
the Todo, infer intent from prose, or override a committed same-Turn binding.
New route changes still use semantic closeout under the existing Vision
contract. Reading a prior typed replan is recovery of committed intent, not
permission to author a route change as in-flight progress.
中文：关闭 native 上下文差分传输时，CLI 捕获入口也将已有结算计划与命令表推迟到
writeback 读取，避免重复交付；当前准入、选择与停止事实仍在入口。可选 full/delta
展示和完整恢复沿用这份 CLI 视图，原始源包保留用于 checkpoint 资格与权限检查。
refresh-state --settle-turn 在写回与交付后置条件通过后，执行原 Goal/Agent/
Todo 或 obligation/Turn 的 canonical 待结算命令并验证回执；不重新 guard、换绑或
完成 Todo。验证失败、检查点未满足、dry-run 与无扣额收尾不能扣额；响应不确定时
按原回执恢复，精确重试不会重复扣额。不传此选项保持原 refresh 行为。
指定 --delivery-workspace-path 后，组合操作也在该交付工作区执行待结算命令，
继续使用原调用方的 CLI 实现。原工作区和结算校验保持；目录缺失或不兼容时保留
原待结算命令以便恢复。
执行中续跑建议不要求把已完成的 Todo 保持开放。原声明验收满足后可正常完成，并
在原 Turn 上按语义收尾写入有证据的 vision；未完成的阶段进展仍可保留开放状态。
新 Turn 尊重上轮明确收尾或结构化 path_delta.outcome=replan，放开旧续跑偏好，
重新按现有资格选任务；不自动完成 Todo、不按文案猜意图，也不覆盖已提交的当轮绑定。
新的路线变更仍须按既有 Vision 契约使用语义收尾；读取历史结构化 replan 是恢复已
提交的意图，不是允许把路线变更伪装为执行中进展。
对使用 --decision-output-dir 或 --decision-output-root 的成功 replan，CLI 和
TurnEnvelope 先给出 review 状态读取，再给出 writeback 格式读取。两步绑定同一
快照和来源哈希，不重新准入、不新增回执或授权，也不强制换路线。累计验收按完整
内容哈希建立索引：每个目标、版本及要求数量可见，明细完整读回；相同 ID 的不同
版本不会覆盖。相同的目标上下文副本共享引用，不同范围保留。Explore 明细单独按需
读取；不可用保持不可用。完整快照仍保存原指导、示例和证据。没有捕获或没有 CLI
读取路径的原生 journal 保持原交付方式。通用执行回顾不再依赖 stride 开关；分类
计数只表示观测，不等于工作成功或目标收益。
捕获后的读取沿用调用方显式选择的 --cli-bin，后续验收和 Explore 读取也不会
悄悄切换到环境中的其他版本。复盘视图提供结构化事实，不预设诊断方法；写回视图
移除预填的 Vision／stride 答案示例，保留字段限制、合法选项、来源绑定和结算规则。
stride 的必需字段与 basis 选项独立展示，完整快照仍可用于按需查看示例与源材料。
这是有意减少建议性提示，不删除验收、权限或停止义务，也不证明自主决策质量提升。
新决定用精简的目标、证据和权限边界替换原方法清单及重复的 stride 规划建议：复盘 一次交付这些边界与事实，写回提供既有格式。可执行 Todo 的次序和 agent 自拟候选 规则可以调整，原有优先目标、硬约束、预算与停止仍须保留。旧快照保留原文；这是 有意改变建议性提示，不能称为对模型行为无损。benchmark checkpoint 前置检查也 使用同一 CLI 捕获入口，TurnEnvelope 关闭仍生效：完整源包供 checkpoint 选择和 校验，模型读取投影视图，再从同一观察分段读取。不重复准入、不改变评测机会， 也不替 agent 选择策略。 work context 中完全相同的验收副本复用该读取，不同版本保留。超过 RPC 请求限额的 完整源包用既有有界本地快照传输做纯投影；两种传输限额均不放宽。
Regression budgets use compact UTF-8 JSON, separately from compute quota and provider tokens. The synthetic workload uses a real append index with 1,500 records, 21 later observations, 24 cumulative outcomes and a populated Explore log. Limits protect default input while exact details remain readable:
| View | Regression allocation |
|---|---|
| Replan entry packet | 2 KiB |
| Populated history review | 16 KiB |
| Planning inventory increment | 8 KiB |
| Cumulative acceptance index increment | 12 KiB |
| Explore increment in entry / review | 128 B / 768 B |
| Explore detail / writeback | 8 KiB / 16 KiB |
The whole-envelope differential also prevents a large acceptance copy moving to another hot carrier. These are fixture regression allocations, not runtime truncation or refusal limits; the existing 8 KiB envelope warning remains. File/SQLite CLI tests cover capture → reads → existing writeback, hash rejection and unchanged state during reads. They do not establish model choice quality, installed adoption, token savings or matched long-horizon benefit.
大小回归使用紧凑 UTF-8 JSON，与算力 quota 和 provider token 分开。通用 review、 累计验收索引和 Explore 分别约束增量，同时检查整个 envelope，防止把大副本挪到 另一处热输入。预算不在运行时截断或拒绝合法内容，原 8 KiB envelope 警告保留。 File/SQLite CLI 验证快照、分步读取、既有写回和哈希拒绝，不据此宣称模型决策、 已安装采用、token 节省或长程收益改善。
Executing turn run-once --execute now saves the original full decision before
Host invocation and binds the received envelope's detail route to that private
observation. This is the native Turn execution default; ordinary quota capture
remains opt-in. turn plan, managed-step inspection and run-once previews
remain read-only. No new capability or configuration switch is introduced.
The Turn journal owns the native Turn identity. Its capture reference includes
Goal, Agent, Turn instance, Turn key and the existing source-decision hash; it
does not invent a heartbeat admission receipt inside the saved decision. The
TypeScript envelope owner validates the observation and binding. Python only
publishes and reads the private file under the Turn journal lock. Captures live
in the journal directory's decisions child, outside the journal file inventory,
and are published atomically with owner-only file permissions without replacing
an existing observation. They can contain private Goal context and must not be
included in public logs or artifacts.
Host retry validates and reuses the original journal's capture even if current source text changes. Reading detail does not invoke quota or spend a slot. Current source admission, cancellation, workspace/lease and mutation checks retain their existing owners; the observation grants no fresh authority. Missing, corrupt, wrong-identity or source-hash-mismatched captures refuse Host reinvocation. Restore the original evidence rather than reconstructing it from a new guard. A capture published before a journal write failure is retained; a different observation cannot overwrite it on retry.
Compatibility: terminal journal readback and recovery using an already cached typed Host result retain the original effect receipts and do not need to launch a Host. An older journal without capture cannot safely reconstruct the omitted original context for another Host attempt. Preserve that journal, resolve its pending effects using the existing recovery path, then start a fresh Turn when permitted. Downgrading code must preserve journals and captures; deleting them is not rollback. This transport qualification does not establish live model, packaged App/Lark or overall convergence acceptance.
Repair and replan diagnostics remain in the journal's typed host_result,
including its summary and follow-up action. They do not implicitly replace Todo
notes or evidence, even when settlement succeeds. Semantic refusal and cached
result recovery must preserve that task context; explicit Todo lifecycle
operations retain their existing authority and validation.
中文：原生 turn run-once --execute 在启动 Host 前保存完整原始决策，实际短包详情
与失败重试均读取该快照，预览不写入。Turn 身份来自原 journal，不伪造 heartbeat
准入记录。旧观察不授予新权限；缺失、损坏或身份／哈希不符时拒绝重新启动 Host。
无快照的旧 journal 保留终态回读和已缓存结果的结算恢复，但不能重新构造当时的完整
上下文后继续调用 Host；先处置原效果，再按当前准入创建新 Turn。文件含私有上下文，
保留在运行时目录，禁止放入公开产物。
For repeated host-owned guards, --decision-output-root ./private-decisions
allocates a unique child directory per invocation below an existing directory.
It is mutually exclusive with --decision-output-dir; both require an explicit
Turn ID. The returned Todo selection command retains the root and requested
--turn-envelope projection, so choosing work never overwrites the first read.
Other repair/replan guard commands still require the caller to retain those
transport flags. A saved decision is not permission to skip revalidation.
The heartbeat renderer can capture decisions while retaining its ordinary dispatcher and quota display:
mkdir -m 700 ./private-decisions
loopx --format json heartbeat-prompt --thin --runtime-profile generic_cli \
--goal-id <goal-id> --agent-id <agent-id> --turn-instance-id <turn-id> \
--decision-output-root ./private-decisionsCapture and display are independent. --decision-output-root saves complete
decisions; --decision-handoff-socket optionally holds their output for a
caller-owned checkpoint. Neither enables TurnEnvelope. This corrects the old
renderer behavior where requesting capture also selected the short dispatcher.
Existing capture callers that intentionally want the short view must now add
--turn-envelope to heartbeat-prompt; the generated guard and thin regeneration
command retain that explicit choice. Quota's existing explicit flag is unchanged.
With that display opt-in, execute its guard, read the short action/contract/writeback fields, and use
detail_ref.full_decision to read the same invocation when selection, replan,
an agent_context.detail_ref or truncation requires detail. Replan history remains with the
existing owner; this option neither invents another history store nor chooses a
strategy. The renderer rejects full/compact/brief modes, missing Turn identity,
native Goal-owned Turns and invalid roots. Stable bootstrap prompts cannot pin a
Turn. Omit --turn-envelope to use the ordinary dispatcher, including when
checkpoint capture remains enabled. Captured files retain the full decision in
both display modes.
Capability planning context stays inline under the existing context owner's
3 KiB bound, including when the envelope exceeds its diagnostic budget. Read it
before planning; it is guidance, not permission. delivery=projected also labels
complete context and does not itself require a detail read. The shared DSH/cloud
Host adapter transports this signed context. For historical context with a
detail_ref, it also retains the original capture route and source signature;
only that saved observation may satisfy the missing context, never a fresh quota
guard. Missing or invalid evidence holds dependent planning while independent
work retains its authority. Capture validation and later mutation checks remain
with their existing owners; prompt delivery does not prove model adoption.
For admitted replans, the shared DSH/cloud adapter also carries the signed
replan_action_packet and the original capture route/signature. Read that saved
decision's autonomous_replan_obligation.replan_context before choosing the
semantic outcome, preserving the existing full Goal read. Missing or invalid
original evidence holds dependent replanning; never rerun admission to replace
it. Return the typed candidate rather than executing the packet's writeback
commands: the outer Turn executor owns state, quota and scheduler effects.
This repairs an adapter omission without adding an evidence-read receipt or
changing non-replan requests.
中文：已准入的重规划通过共享 DSH/cloud adapter 传递签名 action packet，以及原捕获 路由和签名。选择语义结果前从原决策读取既有 replan context，保留完整 Goal 必读； 来源缺失或无效时暂停依赖它的重规划，不能重跑准入替代。返回 typed candidate， 不执行 packet 内写回命令；状态、quota 和 scheduler 效果仍归外层 Turn executor。 本修复不增加补读回执，也不改变非重规划请求。
The unchanged public multi-subagent CLI fixture grows by 1,147 JSON characters and UTF-8 bytes when this context replaces its reference. Its differential allows 1,280 only for that reference-to-inline transition (133 headroom); absolute ceilings, line limits, later inline growth and the 8 KiB production diagnostic remain unchanged. This is an output qualification, not a full-cost SLO.
中文：同一公开 multi-subagent CLI 夹具恢复完整内联后增加 1,147 个 JSON 字符／UTF-8 字节；差分仅对该引用转内联的一次变化给予 1,280（余量 133），绝对上限、行数、后续 内联增长检查及生产 8 KiB 诊断不改；这不是完整成本 SLO 验收。
中文：能力规划上下文由既有 owner 限制在 3 KiB 内，短包超出诊断预算时仍完整内联。
规划前读取它，但它不授予权限。delivery=projected 也用于完整上下文，不能仅据该值
要求补读。共享 DSH/cloud Host 传递签名上下文；历史 detail_ref 保留原捕获路由与
源签名，只能补读原观察，不能重跑 quota。证据缺失或失效时暂停依赖它的规划，独立
工作保留原权限。捕获及后续写入校验仍归原 owner；输入到达不证明模型实际采用。
中文：捕获和模型输入投影独立。--decision-output-root 仅保存完整决策，
--decision-handoff-socket 仅保留检查点交接；二者均不隐式开启 TurnEnvelope。
此前捕获目录同时启用短包的行为已修正。需要短包的调用者须对
heartbeat-prompt 显式传 --turn-envelope；省略该开关时仍使用普通输入，
选择、结算、身份与完整私有捕获不变。旧运行的实际输入与设置不得追溯改写。
This is Python filesystem/command transport under the existing quota/context
owner, not a new capability or Python decision rule. The shared benchmark
heartbeat worker has a separate default-off turn_envelope option documented in
its runtime guide. Native /goal, Turn
driver, installed App automations, frontend and Lark are not switched by this
research-runner setting. Real local worker/renderer/selection/settlement tests
qualify transport; model token/IO costs, decision quality and long-run adoption
still require a separately pinned experiment. Capture grants no additional
read/write/lease authority. Keep captures private; disable the option in the
next run and use ordinary file management to remove unneeded records.
Whole-Goal requirements and selected work have different sources. After final delivery admission, the shared typed interaction owner adds these pre-work reads after any existing hook reads, without duplicating identical commands. The Agent channel is the single carrier; CLI actions do not repeat the list. See required work context for the changed exact-read default and caller migration:
cat -- <registered-state-file>restores the whole Goal intent, acceptance and stop conditions. The pointer is resolved from the registered Goal, not a selected Todo or run-history source label.- When canonical acceptance is enabled,
goal-acceptance inspect --goal-id …restores its full objective, non-goals, criteria, scope and revision. It does not execute validators or expose their commands. A scoped acceptance contract does not replace original Goal intent or prove global completion. - For selected work,
todo list --goal-id … --todo-id …restores full current task text and status/claim once attodo.text(exact reads remove list/role aliases and reject--thin), including when canonical Todos supersede a stale Markdown display. Adaptive work uses its primary ID.
Ordinary product heartbeat consumes current task/acceptance/User sources from
interaction_contract.agent_channel.work_context, then any remaining
agent_channel.required_reads. The Agent channel is the single content/read
carrier; the CLI channel carries transitions. TurnEnvelope consumes and signs
both as work_context and required_reads; it never independently synthesizes
another policy. Already delivered content requires no second CLI invocation.
The ordinary quota should-run display shares exact complete acceptance copies
within that response. Its preferred carrier is a loaded Goal-acceptance source
in work_context, otherwise the planning horizon (or the first available full
copy). Duplicate acceptance_contract / goal_acceptance_contract fields become
their corresponding _ref fields pointing to that inline carrier. Resolve them
in the same response, including when reading replan context; do not fetch a
new revision. Different revisions, scopes, sources, failures or JSON types stay
inline. Nothing is truncated or removed from the retained contract, and no
decision or acceptance verdict changes. Diagnostic detail options still share
these copies; canonical state and saved full-decision captures retain their
original structure. TurnEnvelope relocates the known work-context reference to
its own signed work_context root and rejects an unavailable or dangling source.
This reduces display bytes, not upstream authority reads, and does not by itself
establish model adoption or end-to-end efficiency.
中文：普通 quota should-run 在同一次响应内复用完全相同的完整验收内容，优先保留
work context 中已加载的来源，其次保留 planning horizon 或第一份完整副本。重复字段
改为对应的 _ref；读取重规划上下文时也必须沿同响应引用读取，不能另查新版本。
版本、作用域、来源、失败或 JSON 类型不同则保留原文，不截短要求或改变验收判断。
详情选项同样复用；权威状态和完整决策捕获不改。TurnEnvelope 将已知引用移到自己
签名覆盖的 work context，拒绝缺失或不可用来源。这只证明展示成本下降，尚不证明
上游读取减少、模型采用或完整任务效率提升。
Known Todo diagnostic lanes share quota/diagnostic_projection.ts through the
existing coarse context call. Read-only status/plan projects all rows in one
call, rather than a call per Goal or lane. Unknown lists, fields, versions and
complex nested item content remain full; field recognition reuses the canonical
Todo contract. Retained items, capability candidates, portfolio text, planning
horizon and selected-work sources are not shortened. Explicit detail returns the
original summaries. Upstream compaction remains visible as source_projection.
Status/plan adds one projection request; Agent/vision detail still needs one
when the User summary remains compact. Explicit full Todo roles bypass that
diagnostic request. These transport costs must be included in comparisons.
Diagnostic replies carry only display edits and references to the immutable
input. The Python adapter applies them to its original facts, preserving float
spelling, negative zero, large-integer precision and relocated upstream metadata.
Reference-only callers keep their existing transport; no Python compaction
decision is reintroduced. The read codec's content_revision is recognized as
known display metadata and remains on retained items.
The legacy detail command observes current state and cannot recover an earlier
decision. The scoped native consumer and original-capture reference are a separate
controller integration proposal,
which reuses this same owner. This does not change admission, claims, leases,
settlement or native context defaults; it does not qualify net efficiency gains.
中文：已知 Todo 诊断列表通过既有粗粒度上下文调用复用同一 typed owner；只读
status/plan 整批行只调用一次，不逐 Goal 或列表调用。未知列表、字段、版本和
复杂嵌套条目保留全文，字段识别复用规范 Todo 契约；保留条目、候选、portfolio
正文、规划视野和当前工作来源不截短，详情返回原摘要，上游压缩信息保留于
source_projection。旧详情命令读取当前状态，不能恢复历史决定。
status/plan 新增一次投影请求；Agent/vision 详情若仍压缩 User 摘要，也需一次；
显式展开两类 Todo 则跳过诊断投影。这些传输成本须计入比较。scoped 原生
消费者及同 capture 引用属于单独的 controller 集成提案 #7430，复用同一 owner。
此处不改准入、claim、lease、结算或原生默认，也不代表完整效率收益通过。
诊断回复只传展示变更及不可变输入的引用；Python adapter 在原始事实上应用，
保留浮点表示、负零、大整数精度及迁移后的上游元数据。仅引用的旧调用方保持
原传输行为，不重新引入 Python 裁剪决定。读取 codec 已有的 content_revision
属于已知展示元数据，在保留条目上仍完整存在。
The selected-Todo display body is display-only and may be bounded; the typed
owner validates the exact read against selected identity, lifecycle, claim and
source revision. A supplied full-body snapshot must match before fulfilling the read. If the full body is already
in the selected action, work_context.selected_todo_ref reuses that body while
the source retains unique continuation, relation and authority metadata. If the
selected view is bounded, the full canonical detail stays in
work_context.sources. TurnEnvelope must preserve those unique fields and may
omit only an actually duplicate body; if there are no other fields to retain,
work_context.selected_todo_authority carries the source and revision. All exact
commands remain in required_reads.
The mixed Goal document remains an exact progressive full read; quota checks
source availability rather than automatically copying unrelated tasks/history.
No heading heuristic replaces Goal intent. work_context.complete does not
settle pending read obligations. Full delivered sources and related User
obligations survive budget overflow. Missing,
ambiguous, failed or changed sources require recovery and a fresh guard before
dependent work; content grants no claim, lease or amendment authority.
This is a default decision/heartbeat behavior change, not an envelope opt-in. Admitted replans acquire Goal reads, without an old selected-Todo read. Non-delivery, selection-only, settlement-only and governed-capability lanes acquire no extra core work reads. Related User obligations remain scoped; full quota summaries stay compact. Shared adapters retain selected Todo context; text aliases require exact equality, never a case-folded or truncated-prefix match. Supplied selected text survives envelope serialization intact. Hosts must honor the reads; signing does not prove execution or model adherence. Full Goal requirement coverage and global closeout remain open.
The continuation-audit capsule preserves the source's complete ordered
required_before_closeout, continuation guidance, current vision_gap_judge,
accepted evidence kinds and insufficient-proof conditions. These are decision
obligations, so display truncation must not remove their clauses or list tails.
They enter the existing action signature; editing a step, its order or the judge
changes the signed dimensions. Detailed acceptance-gap records stay in the same
captured full decision. Historical saved envelopes retain their original
signatures; this projection change grants no closure or execution authority.
The 8 KiB warning remains diagnostic when required meaning exceeds it.
Shared DSH/cloud Host input forwards this audit from the signed capsule, with
the original capture route and hash for additional acceptance/coverage evidence.
Hosts read its ordered obligations and current judge before proposing closure;
they return a semantic result while the outer Turn executor owns state, quota
and scheduler effects. The same input carries the complete existing
execution_profile, including outcome-floor and degradation rules, to size and
qualify work. Display filtering must not discard those clauses or ordered
requirements before signing. A new material result carrying execution_profile
must return work_evidence and validation_evidence as separate arrays of
1-8 non-empty public-safe strings, at most 240 characters per item and 1,200
characters per field. The Host must preserve its actual
delivery_batch_scale and delivery_outcome rather than replacing them with a
fixed progress class. The outer Turn executor validates and retains this evidence
in the typed host result; turn run-once projects it as host_evidence.
Legacy journal replay may retain an older material result without these fields.
Stop results omit both arrays. The profile does not transfer writeback or quota
ownership. Historical profiles keep their original signature, and inputs without
either contract retain their prompt.
中文：验收 capsule 完整保留原来源的有序步骤、继续执行说明、当前结束／继续判断、
认可的证据种类和不能作为证明的条件；展示裁剪不能丢掉条款或列表尾部。新投影使用
既有签名维度，历史 envelope 的签名不重写。详细验收记录仍从同次捕获读取，体积
超过 8 KiB 时保留 warning，不以缩短义务或放大预算替代语义验收。
共享 DSH／云端 Host 输入也从签名 capsule 传递这份 audit，附原捕获路由与哈希，供
补读验收／覆盖证据；提议收尾前须读取有序义务及当前 judge。Host 返回语义结果，
状态、quota 和 scheduler 效果仍由外层 Turn executor 执行。同一输入也传递完整的既有
execution_profile，包括成果底线、退化规则和有序要求，供确定工作规模及验收；不能
在签名前按展示字段丢弃。携带 execution_profile 的新 material result 必须分别返回
work_evidence 与 validation_evidence 字符串数组：各 1-8 项、每项不超过 240 字符、
整字段不超过 1,200 字符，且公开安全。Host 必须保留实际
delivery_batch_scale 与 delivery_outcome，不能改写成固定的 progress 分类。外层
Turn executor 验证 typed result 并保留证据，turn run-once 以 host_evidence
投影回读；旧 journal replay 可保留缺少这些字段的历史 material result，stop result
不得返回两组证据。Host 不取得写回或扣额权。历史 profile 保留原签名；两种契约都不
存在时保持原 prompt。
No new frontend/Lark operation or configuration is introduced. Regenerate saved expanded heartbeat prompts to consume the new contract; bootstrap prompts reload installed rules on their next wake. This source-checkout change does not upgrade an installed runtime or modify an existing automation.
中文：共享 typed interaction owner 在准入后生成 Goal 原文、已启用的结构化验收、 当前 Todo 全文三层读取。普通产品 heartbeat 消费 agent channel 清单，TurnEnvelope 只传输并签名同一清单；不能仅由短包临时推导义务。Goal 原文恢复完整意图和停止条件， 局部验收不能替代完整目标，任务状态/claim 继续由精确 Todo reader 提供。读取失败、 缺失、歧义或变化须重新 guard；当前内容不是 selection 快照，签名也不证明模型已读。 这是默认 guard/heartbeat 行为变化：准入的 replan 读取 Goal，等待、待选择、仅结算及 受治理 capability 分支不追加读取。完整义务覆盖与全局收口仍未实现。旧的展开式 heartbeat prompt 需重新生成；bootstrap 会在下次唤醒重载已安装规则。本源码改动不会 升级已安装 runtime 或修改现有 automation，也不新增前端/Lark 操作。
The envelope flag selects a projection of the full decision. The original v0
contract left the default quota should-run output unchanged; the
PR-05 migration omits
protocol_action_packet from new full decisions, including live, paused and
recovery output, from the first release containing #4794. The subsequent
reader retirement in #7161 explicitly rejects packet-bearing decisions and
capsule witnesses. Packet-free v0 envelopes remain supported. The envelope keeps:
- the selected todo, claim, and effective action;
- the bounded action portfolio when the agent must choose among multiple admitted actions before delivery;
- the bounded read-only planning horizon when selected work has strategic Todo, relation, or goal-acceptance context;
- concrete user actions and gate reasons;
- required reads;
- write scope, approvals, guards, workspace/capability gates, and stop rule;
- delivery, repair, safe-bypass, and blocked-action policy;
- validation/writeback and quota-spend policy;
- the current scheduler action and cadence acknowledgement command.
The envelope also carries a contract_capsule for interaction mode,
work-lane and execution obligations, successor/replan duties, automation
liveness, vision/handoff state, and actionable warning references. A canonical
action_signature is independently built from the full decision and from the
envelope; matching hashes prove the covered action dimensions agree for that
projection. They do not prove that every possible quota state has test
coverage.
The five execution-contract objects work_lane_contract,
execution_obligation, autonomous_replan_scope, agent_scope_frontier, and
automation_liveness retain their complete source JSON, including nested data,
ordered lists, empty values and unrecognized metadata. Their clauses are not
subject to display truncation. Both quota-envelope emission and direct Turn
composition use this shared producer. The shared structured Host prompt now
forwards the remaining signed capsule for ordinary execution as well as staged
replanning; previously the ordinary path omitted it. Retaining metadata does
not interpret it as a new execution permission or support a new required
semantic. Existing schema/signature coverage and historical captured envelopes
remain readable without rewriting them. Re-projecting an older raw decision
with the corrected producer can produce a different signature; validate an
existing envelope against its saved content and digest. Raw quota output and admission,
scheduler and settlement decisions are unchanged. Larger capsule bytes remain
visible in the existing diagnostic budget warning; this correction does not
claim lower token cost or complete controller-contract unification.
中文：上述五份执行契约完整保留源 JSON，包括嵌套数据、有序列表、空值和未知 元数据，不按展示预算截断条款。quota 短包与直接 Turn 共用该生产者；共享结构化 Host 在普通执行和分阶段重规划中都传递剩余的已签名 capsule，修复普通执行 原先遗漏的问题。保留元数据不表示解释新权限或支持新的必需语义。既有 schema、 签名覆盖与历史捕获内容继续可读，不改写旧记录。用修正后的生产者重新投影旧 原始决定可能得到不同签名；既有 envelope 应按保存内容与摘要校验。原始 quota 输出、准入、调度和 结算决定不变。增长的字节量仍通过既有预算诊断可见；这项修正不证明 token 成本下降，也不表示 controller 契约已完全统一。
Live Turn planning, native Codex prompt construction and structured Host
consumption share the TypeScript owner's version gate. The current consumer
accepts loopx_turn_envelope_v0, action-signature schema v0 and the registered
v0–v5 coverage versions. An explicitly unknown or null version is rejected
before Host launch, even when its unchanged action digest still matches. The
historical digest document does not sign these version declarations, so digest
equality alone cannot establish consumer compatibility. Existing v0 callers
that omit signature-version metadata retain their prior behavior; digest,
lineage, current authority and settlement checks remain separate. Saved capture
bytes and old signature documents are not rewritten. This gate does not qualify
a future unified schema or interpret unknown required nested semantics.
中文：实时 Turn 规划、原生 Codex 提示构造和结构化 Host 消费共用 TypeScript owner 的版本门。当前 consumer 接受 envelope v0、action-signature schema v0 及已注册的 v0–v5 coverage；显式未知或 null 版本即使仍携带匹配的旧行动摘要， 也会在 Host 启动前拒绝。历史摘要文档不签署这些版本声明，摘要相等不能证明 消费者兼容。省略签名版本元数据的既有 v0 调用方保持原行为；摘要、谱系、当前 权限和结算校验仍各自负责。既有捕获字节和历史签名文档不改写。此门不表示未来 统一 schema 已获得资格，也不负责解释未知的必需嵌套语义。
Ordinary structured Host prompts also retain the signed user,
execution_policy, scheduler, response_plan, and
task_orchestration_contract sections, plus the existing captured-decision
reference when present. These sections are no longer conditional on a staged
replan reader. Notification policy does not grant or cancel execution authority;
carrying surrounding Turn plans does not delegate their effects. The prompt
keeps state writeback, quota and scheduler operations with the outer Turn
executor and asks the work segment to return its semantic result.
中文：普通结构化 Host 还保留已签名的用户通知、执行策略、调度、响应计划、 任务编排五个区段，以及已有的捕获决定引用，不再以分阶段 replan reader 是否存在为条件。通知策略不授予或取消执行权限；传递外围 Turn 计划不等于 委派其副作用。提示明确由外围 Turn executor 负责状态写回、quota 和调度操作， 工作段返回语义结果。
The structured Host also receives signed agent_id, decision, should_run,
effective_action and state. Its action object retains execution flags,
action choices and capability intent while the existing task/planning carriers
keep their established locations. recommended_action remains a display
fallback, omitted from this Host projection because it can retain an older
recommendation than the authoritative primary_action. Neither a suggested
alternative nor a transported intent overrides admission, scope or effect
ownership. This is input preservation, not a new admission decision or the
unified-contract writer transition.
中文：结构化 Host 同时收到已签名的 Agent 身份、决定、是否运行、有效行动和
状态；action 保留执行标记、行动选项及能力意图，任务和规划字段沿用已有位置。
recommended_action 是可能落后于权威 primary_action 的展示回退，仍不放入
此 Host 投影。建议选项和传递的意图不覆盖准入、作用域或副作用归属。这是输入
保真修复，不增加准入决策，也不表示统一契约 writer 已切换。
Required reads use the authoritative interaction_contract.agent_channel list,
including an explicit empty list. Historical interaction-root and payload lists
remain fallbacks when that carrier is absent. Commands retain their exact bytes;
existing ordering, hook_id and capability_id coordinates survive both the
quota transport and the signed envelope projection. Provider diagnostics remain
outside this whitelist. A matching signature cannot prove that omitted reads
were complete or that a host executed them. Newly projected decisions retain
these corrected facts in the existing required-read dimension; saved signatures
are not rewritten, and no new execution permission is granted.
中文：必读列表优先使用 agent_channel 的权威列表，包括明确的空列表；缺失时 才兼容旧位置。命令原样保留，已有读取顺序、hook 和 capability 身份贯穿 quota 传输与签名短包，私有诊断不进入该列表。修正新投影不重写历史签名；签名相等 不能证明读取完整或宿主已经执行，也不提供新的权限。
Action-signature coverage is versioned independently from the envelope schema.
turn_envelope_action_dimensions_v0 covers the original action projection;
turn_envelope_action_dimensions_v1 additionally covers a blocking user
gate's response_plan; turn_envelope_action_dimensions_v2 additionally signs
action.action_portfolio; turn_envelope_action_dimensions_v3 additionally
signs action.planning_horizon; v4 additionally signs capability agent_context;
turn_envelope_action_dimensions_v5 additionally preserves the canonical
writeback.settlement_plan. Base/head qualification accepts a declared
coverage migration as a review signal. The bounded, JSON-only v2 and v3
migration budgets apply only to their named schema transitions; ordinary
growth limits resume once the new version is the baseline. A digest change
without a supported coverage migration, or a projection above its one-version
budget, still fails closed.
For a decision carrying a settlement plan, the opt-in envelope now transports that plan intact: effect identity, ordered steps, command conditions, expected receipts and the host-owned handoff. It also keeps the corresponding next CLI commands untruncated. This repairs the earlier preview that could report matching action hashes while omitting the settlement plan. The plan remains owned by the shared settlement algebra; the envelope neither rebuilds it nor grants authority to execute an unadmitted step. Packets without a plan keep their previous coverage and do not acquire one from a historical heartbeat receipt. Stored v0–v4 signatures are not rewritten. The v5 migration is an explicit semantic review signal and has no additional size allowance; overflow still requires the existing budget analysis. Default full quota output and settlement rules are unchanged.
Newly generated turn-scoped settlement commands include global --format json
before the subcommand. This changes the generated command output default for App
heartbeat, generic CLI, and visible Goal lanes, in both full decisions and
TurnEnvelope. It also applies to settlement_owed.command after writeback.
Execute the returned command after filling its declared placeholders; do not
append --format json after quota spend-slot, where it is not a subcommand
option. Inspect both the exit code and JSON ok. Direct CLI invocations retain
their existing output defaults; stored commands and receipts are not rewritten.
This is command rendering over the existing settlement owner: validation,
identity, step conditions, authority and one-spend semantics are unchanged.
中文：新生成的结算命令自带位置正确的全局 JSON 参数，完整包、短包及写回后的
补结算命令保持一致。填充占位项后直接执行，检查退出码和 JSON ok；不再需要
手工在子命令后追加格式参数。直接 CLI 的默认格式、历史回执与结算权限均不变。
When an admitted Turn's verified durable writeback is followed by a Todo
dependency wait, its replay now projects only the original quota_spend step.
The later wait cannot replace the committed outcome with a blocked writeback.
This default guard recovery grants no independent work and preserves the Todo
wait and successor. The envelope retains the same complete executable command,
including identity arguments after long registry/runtime paths. The spend owner
still validates the original receipts, workspace and checkpoint; a missing spend
receipt is repaired on that identity without another debit. Before verified
writeback, registered causal waits retain the blocked no-spend closeout.
This is shared CLI/heartbeat decision transport; it adds no frontend/Lark
operation, changes no host cadence and does not update installed runtimes.
中文：原 Turn 已有验证通过的持久写回，之后 Todo 才进入依赖等待时，同一 Turn
重入只补原 quota_spend 步骤，不再要求用 blocked 覆盖已有结果。等待和后继任务
保持原样，不准入独立工作；短包保留完整命令和原身份。额度 owner 仍校验原回执、
工作区和 checkpoint，补回执不重复扣额。尚无验证写回的因果等待仍走不扣额收口。
此项修复不改变宿主调度、已安装版本或前端/Lark 操作。
The shared CLI plan also explains delivery classification before writeback.
Validated evidence that excludes a route and informs the next decision can be
outcome_progress even when the attempted candidate does not improve the target
metric. A failed attempt, an unchanged metric, or a new Todo alone does not prove
progress. Record the validated evidence and its consequence. outcome_gap is the
existing blocked-settlement path: it requires --progress-result-class blocked,
blocker/evidence IDs, and the existing continuation checks. These authoring hints
neither judge evidence nor relax validation, completion, lease, or spend rules;
an invalid outcome_gap plus advanced still fails before writeback. The same
plan reaches full CLI output and the opt-in envelope. This changes agent-facing
guidance in both views. Full, compact, brief and thin heartbeat prompts scope
no-refresh/spend closeout to exact monitor settlement; auxiliary polling leaves
the original work settlement due. Admitted work follows its settlement plan;
an unchanged artifact alone does not imply no progress. The shared heartbeat
renderer supplies this wording, while the TypeScript settlement owner retains
classification semantics. This adds no capability, automatic classification, or
frontend/Lark operation. Model error-rate reduction remains unqualified.
中文：短包现在完整保留已有结算计划及执行命令，签名 v5 覆盖结算身份、步骤顺序、 条件和宿主边界；没有计划的输入不会凭空获得结算权限。旧签名保留，默认完整输出 不变，大小预算不放宽。此修复是短上下文实验的前置条件，尚不证明模型收益。
quota_planning_horizon_v0 remains advisory even when carried by the envelope.
Its selection_contract points back to selected_todo and action_portfolio,
and horizon_changes_selection=false. Effect Program transports this
observation; the TypeScript work-item reducer owns its ordering and bounds.
The quota projection keeps the horizon's typed detail_refs. TurnEnvelope does
not copy those commands a second time: it emits
action.planning_horizon.detail_refs_ref="$.detail_ref", and the existing
top-level cold path owns the full-decision, Todo, and status reads. This
transport compaction is covered by the same action signature and does not
change horizon completeness or selection authority.
See quota_planning_horizon_v0.
For quota_action_portfolio_v2, the envelope carries the recommendation and
bounded, non-exhaustive suggested_actions, but neither is a settlement
identity or permission list. When the full interaction contract says
selection_required=true, the agent must rerun quota in the same turn with any
currently authoritative, same-agent, capability-ready Todo. The full decision's
selection_command.command_args_template is a rendering template, not a
permission list. It and candidate_discovery_args share one bound
route_prefix; the discovery route exposes the current open agent queue
when the bounded suggestions are insufficient. The requested Todo remains
pending until the second guard re-runs current lane arbitration and eligibility;
only a qualified request upgrades the identity-less receipt. A newly due hard
lane leaves the receipt unbound, and only the resulting receipt-bound envelope
is a delivery contract.
An unbound selection that no longer qualifies is a preflight outcome, not a
settlement-identity conflict. The full quota response preserves the TypeScript
action_selection_qualification_v0 result and returns
quota_action_selection_deferred or quota_action_selection_rejected, including
the exact current preemption or eligibility reason. An existing identity-less
receipt appends an identity-less pending_action_selection revision when an
otherwise eligible explicit choice is deferred. That revision is not delivery
or settlement authority: it preserves the explicit choice only so a no-argument
same-Turn reentry cannot replace it with the current recommendation. An
ineligible/rejected choice still replays the receipt without mutation; a
first-call rejection reports
heartbeat_receipt.status=not_committed and writes no receipt event.
A receipt-bound refresh-state --next-action must refine that original Turn's
Goal, Agent and Todo. If waiting or completion makes the current selector choose
another Todo, the existing typed recommendation owner rejects the step before
appending a run; even the other Todo's fresh read basis cannot retarget the
original writeback. Finish the original writeback without --next-action, then
select subsequent work through a fresh guard. A matching bound step records
settlement_alignment=exact; ordinary unbound steps retain not_applicable.
This changes the previous acceptance of a mismatched task-step write, without
clearing dependencies, altering Todo authority or granting another Turn.
中文：绑定回执的 refresh-state --next-action 必须属于原 Turn 的 Goal、Agent
和 Todo。原任务等待或完成后，即使当前选择器已选中另一个 Todo，且提供其最新
read basis，同一 TS recommendation owner 仍在追加 run 前拒绝跨任务步骤。
先去掉 --next-action 完成原写回，再通过 fresh guard 选择后续工作。匹配步骤保留
settlement_alignment=exact，无 Turn 绑定的普通步骤仍为 not_applicable。
本项修复此前错误接受的跨任务写入，不清依赖、不改变 Todo 权威或授予新 Turn。
For an eligible explicit choice deferred solely by runnable autonomous replan,
the typed qualifier adds inline_reentry_allowed=true. The CLI executes one
same-Turn guard reentry and returns its fresh result directly, including in
TurnEnvelope mode. With an existing receipt it first durably retains the choice.
On the first guard it carries that choice internally until the final receipt,
without emitting an intermediate refusal or an unbound discovery packet. A
concurrent receipt appearing during this first-call retry stops the retry;
it cannot replace the other caller's binding. This changes the previous first-call
refusal that required the model to read discovery and binding packets separately.
It grants no delivery or spend authority: the fresh guard and receipt owner
still decide the Todo/replan binding, and may return a newly changed gate. It
does not retry other hard lanes or missing candidates. The reentry has no explicit selection, so it
cannot recursively retry. Hosts that do not execute this CLI path can continue
to use the existing recovery command.
When native context delivery is enabled, rejected guards keep their error, original receipt and recovery action within the configured output budget. The full captured rejection is optional diagnostic detail, available through the digest-checked reader. Oversized diagnostics use a selected read of those failure fields. Neither response enters pending context delivery or establishes a differential baseline; disabled context delivery keeps its ordinary output.
中文：已知且合格的任务仅因自主重规划被推迟时，首次调用内部完成一次同 Turn 重判，只交付最终绑定结果，不要求模型先读拒绝、再读发现包、再读绑定包。 已有回执仍先持久化选择；首次重试期间出现并发回执则拒绝覆盖。 重判仍检查当前停止条件和额度，后续交付仍需新 Turn。启用原生上下文传输时， 拒绝响应有界交付错误、原回执及恢复动作；完整失败包仅供按需诊断， 不会建立差分基线。关闭该功能时保留原输出。
For other refusals, the agent receives
recovery_action=reenter_guard_without_selection and one executable
same-Turn guard in the full decision's cli_channel.next_cli_actions; the compact
envelope preserves the recovery in its action and writeback preview. The failed
selection exposes no settlement plan, spend command, or unadmitted replan action
packet. Execute that guard without
a Todo/replan argument before following the resulting binding or portfolio. A
receipt already bound to a different Todo or autonomous replan obligation
remains a hard heartbeat_receipt_identity_conflict. On reentry, an identical
projected Todo may bind normally. If a hard autonomous replan owns the current
lane, the replan receives the Turn's settlement identity and the retained Todo
is reported as deferred_to_fresh_turn; a different recommended Todo never
inherits the retained choice or its authority.
When a due monitor is visible only as auxiliary context for an advancement lane,
the typed reason is
auxiliary_monitor_not_selectable_in_advancement_lane. The agent selects a
current advancement Todo or retries after the monitor becomes the hard lane;
this state is never reported as a receipt write failure.
A selection may also qualify while repository delivery is temporarily blocked
by the peer workspace guard. In that case the response and bound receipt keep
the selected Todo, effective_action=agent_workspace_repair, and the typed
worktree recovery instruction. Moving to an independent worktree and rerunning
the guard with the same Turn id resumes the selected Todo; the wrapper must not
rewrite this recoverable state as a settlement-identity conflict.
For admitted local delivery, the workspace hint points to the registered Goal workspace and defers isolation requirements to the current workspace guard and repository rules. A peer identity alone does not require moving to another worktree. This corrects the previous unconditional Git-peer hint in both full quota output and TurnEnvelope; admission and settlement enforcement are unchanged.
An executed, turn-scoped quota monitor-poll is a no-spend closeout only when
its observed Todo exactly matches the Turn's settlement_todo_id. That response
includes turn_continuation.next_turn_required=true and requires a fresh Turn
before unrelated work. An admitted auxiliary monitor uses its own observed Todo
while retaining the advancement Todo as settlement_todo_id; its continuation
keeps current_turn_settled=false and next_turn_required=false so the original
writeback and spend can finish. A missing exact or typed auxiliary binding never
claims settlement.
Portfolio v2 preserves v1's selection policy, candidate ordering, and
settlement rules, and adds an optional continuation_hint to each suggested
action. The default quota producer and Turn controller now require v2. The
compact quota CLI view uses the independently versioned
quota_cli_action_portfolio_compaction_v1 detail marker and inlines candidate
text, priority, action_kind, and continuation_hint alongside the v1
identity fields. TurnEnvelope keeps the same loopx_turn_envelope_v0 outer
schema and v2 action-signature coverage; only its nested action portfolio
version changes. Hosts that strictly accept v1 must update before consuming
the new default. LoopX does not dual-emit or negotiate a v1 downgrade, so an
unknown nested portfolio version must fail closed. Ignoring an absent
continuation_hint remains valid when reading stored v1 evidence, but it does
not make a v1-only live decoder compatible with the v2 producer.
loopx turn plan and loopx turn run-once have no agent selection phase before
they build the host transaction. When such a Turn sees a v2 portfolio, its
outer controller binds the advisory primary by rerunning the same current
eligibility qualification, retains the portfolio in the envelope for audit,
and marks the selected Todo with
selected_by=turn_controller_advisory_primary. This deterministic compatibility
path does not apply to heartbeat/model turns: their first response remains
identity-less and delivery-blocked until the agent explicitly chooses.
The compact envelope does not truncate those executable commands into unusable
strings. It carries non-exhaustive writeback.suggested_todo_ids plus
selection_command_ref; the full decision remains the authority for exact argv.
Packet-bearing historical decisions and contract_capsule.protocol_action_packet
witnesses are unsupported under the retirement contract.
Presence, even null or empty, fails before conversion, hashing, capture binding
or Host admission. Ordered legacy reconstruction, residue and opaque-summary
fallback are removed. No signed dimension is silently dropped and no historical
record or signature is rewritten. Callers must acquire a fresh typed decision;
this does not introduce a question or an additional admission workflow.
Packet-free sources produce no packet witness. All other typed obligations and signature dimensions retain their existing interpretation, including frozen packet-free v0 records. Source and envelope canonical documents must agree; missing, mismatched or tampered signatures still fail. This is a deliberate input-format retirement, not a retirement of all Envelope v0 records. The contract defines the source/release boundary and recovery without promising a whole-store rollback or qualification of unknown external readers.
Large todo summaries, frontier diagnostics, readiness history, compatibility
fields, and warning collections stay on the referenced full-decision/status
cold paths. The envelope has an 8 KiB compact UTF-8 JSON performance target,
not an execution-admission limit. compaction.envelope_utf8_bytes measures the
final packet, including diagnostics. The historical source_json_bytes and
envelope_json_bytes fields still count Unicode code points for v0 compatibility;
do not use them as wire-byte measurements.
The envelope preserves complete write_scope, available_capabilities,
requires_parent_approval, guards and stop_condition values, including
literal path whitespace and explicit empty lists. Resolved checkpointed write
approval retains every active scope; private approval entries stay on the
authorized full-decision path. Display limits must not remove restrictions or
change path patterns. The 8 KiB warning remains diagnostic.
The shared DSH/cloud candidate prompt carries the remaining signed boundary
under boundary. Its existing write_scope and workspace_guard fields keep
their original locations and are not duplicated in that remainder. These are
instructions for the Host, not a new enforcement mechanism or permission grant;
owning admission, lease and mutation checks still apply. Boundary facts already
belong to the action signature: new projections can change hashes, while saved
signatures and receipts are not rewritten. Signature equality alone cannot
prove source completeness when both sides use the same projection.
中文：envelope 完整保留范围、能力、审批要求、守卫和停止条件，路径空白、空数组及 已批准的全部范围也不裁剪。共享 DSH／云端提示传递其余签名边界，原范围和 workspace 字段继续兼容且只传一份。它们是宿主指令，不替代准入、lease 或写入校验；8 KiB 仍只 警告，不改写历史签名和回执。两边共用投影时，签名相等本身不能证明来源条款完整。
boundary.capability_gate carries the existing quota gate's required and
missing arrays intact, including an empty missing array after admission.
Earlier compact projection used only required_capabilities and
missing_capabilities, which could report matching projection signatures while
omitting the current refusal facts. Historical names are still carried when
present in the supplied source; they are not synthesized or rewritten.
These facts participate in the existing boundary signature. Newly built projections over current sources therefore have different hashes; saved signatures are not rewritten and this is not a cross-version hash-equivalence promise. Full quota output, admission, optional capability activation, claim, lease and mutation checks are unchanged. No capability is granted by reading these arrays. The default full heartbeat packet remains the source decision; compact/Turn hosts retain its reason for refusal without recomputing readiness.
中文：短包原样保留现有能力门禁的 required/missing（包括合法空数组），历史字段 只在源中存在时保留。新投影签名覆盖这些事实，不改写历史签名；完整包、准入、 可选能力开关和 claim/lease 权限不变。读取缺失项不授予能力。
The compact boundary retains the verified Goal/Agent Reward Memory automation
facts in boundary.capabilities.reward_memory: automatic_recall and
automatic_ingest. Unconfigured, disabled or unavailable bindings omit this
projection. It carries neither private provider configuration nor memory content
and grants no action authority. Existing action-signature coverage includes it.
Codex CLI host requests use these facts together with the fresh runtime binding readback. Recall guidance is added only with enabled recall and actual context; the reflection instruction and output-schema field appear only with enabled ingest. A disabled or stale recall packet cannot activate either operation. Older/custom hosts may still return a reflection field: while ingest is off the adapter ignores it before validation and journaling, preserving ordinary work. When enabled, bounded reflection validation, exact independent attestation and post-settlement ingest retain their existing rules. Provider failure remains fail-open. The host adapter is Python IO transport over the existing capability resolver and TypeScript envelope owner, not a new enablement policy.
The capability layer registers post-selection context once for executing native
Turn and quota/heartbeat guards. Internal turn_context_contributions carry
bounded context fields, instructions and optional text-result schemas; they are
not provider permissions. Hosts consume the generic capability_context_fields,
capability_instructions and capability_result_fields projection. The existing
reward_memory_recall readback and 2,400-character reflection limit remain.
Programmatic callers contributing memory use the registered context path;
inserting a legacy recall readback alone cannot activate a host contribution.
An inactive binding leaves ordinary host input, prompt and result schema intact.
The registered contribution carries the full optional recall only once, in
host context; its readback retains bounded participation facts without a
second context copy. If the complete recall would exceed the existing 64 KiB
contribution budget, that recall context is omitted for the Turn while the
verified binding, reflection schema and post-settlement ingest remain enabled.
The hard budget is not raised and omission never grants action authority.
Recovery also reads pre-registration journals that already contain a bounded
reflection and its independent validation receipt. Without a contribution
annotation, only this cached result field retains its existing 2,400-character
wire decoding; new Host results still require registered context. Recovery
preserves the original result, validation digest and plan without repeating the
Host or task validator. Current ingest policy, independent evidence and the
original settlement/idempotency owners still decide any provider effect.
The cached reader and capability composition reuse the same verified automation
fact projection in control_plane/reward_memory.py; provider policy is not
copied into the executor.
中文：恢复注册前的执行日志时，保留已准入的有界反思、原独立证明及原 plan；缺少
贡献 annotation 的旧缓存仅沿用该结果字段原有的 2,400 字符解码，不重新启动 Host
或 validator，也不为新 Host 输入开启旧接线。provider 效果仍由当前 ingest 策略、
独立证据及原结算／去重 owner 判定。
注册贡献只在 host context 中携带一份可选 recall，readback 只保留有界参与事实，
不再重复正文。若完整 recall 会超过既有 64 KiB contribution 预算，则该 Turn
省略召回正文，但仍保留已核验绑定、反思 schema 与结算后 ingest；不提高硬预算，
省略正文也不授予任何 action authority。
缓存 reader 和能力组合复用 control_plane/reward_memory.py 的同一参与事实投影，
executor 不复制 provider 策略。
TypeScript binds each contribution to the existing governing signature document
and its source readback. Capture locations and size diagnostics may change;
actor, authority, binding readback or contribution changes discard that optional
context. Capabilities cannot overwrite core authority or result fields.
Ingest-only input omits recalled context. Host adapters preserve enabled optional
result values for outer bounds/material validation and independent attestation.
Registered PostSettlement callbacks invoke the original ingest/sidecar owners
after accountable settlement. post_writeback remains effect-free. Per-hook
receipts preserve completed callbacks during partial recovery; provider receipts
and idempotency remain with their existing owner. Unknown effects remain unknown.
After terminal settlement, a resume leaves the journal and its original
post_settlement receipt unchanged. When that receipt is uncertain, the owner
may reconcile the same effect and return post_settlement_recovery as current
readback. The owner retains the durable receipt; this projection grants no new
work, validation, quota debit or scheduler action.
中文：执行中的 native Turn 与 quota/heartbeat guard 通过注册的选择后上下文路径接入
记忆；三种宿主消费统一贡献，不再各自判断记忆模式。原 recall 读回和反思大小限制保留，
只有旧读回而无注册贡献不能开启宿主记忆输入。关闭保持普通输入／指导／schema 原样。
TS 复用 governing 签名文档和来源绑定，允许捕获定位变化，拒绝 actor／权限／绑定／
贡献变更及核心字段替换。独立精确证明和可记账结算后，注册的 PostSettlement 调用
原 ingest owner；无副作用的 post_writeback 不变。逐 hook 回执与原 provider 去重
共同恢复，不把不确定效果写成零。终态重放保留原 journal／post_settlement，通过原
owner 对同一效果恢复的当前读回放入 post_settlement_recovery；持久回执仍由原 owner
保管，不触发业务工作、验证、扣额或调度。隔离 File/SQLite／宿主／provider 验证不代表安装态
App/Lark、模型采用或真实服务资格。
This is a bounded shared-facts step. Heartbeat still has its existing full and compact rendering paths; it is not yet the same installed host journey. The remaining convergence work is tracked in the existing effect-interpreter RFC.
中文：短包只携带已核验的 recall/ingest 参与事实；关闭、未配置或不可用时不加入。 Codex CLI 据此及新鲜绑定读回装配指令和 schema，关闭 ingest 时忽略旧宿主返回的 反思字段。权限、独立验证与结算规则不变。heartbeat 与 TurnEnvelope 的安装态统一 仍待验证，不能把这一步当作完成。
Oversize valid envelopes keep their normal Turn plan/controller route. They
report compaction.within_budget=false and a structured
warning.code=turn_envelope_budget_exceeded, with excess_bytes, additive
section_bytes and over_target_sections. JSON carries this through the Turn
plan and host request; Markdown plan/envelope output calls out the warning.
Schema, signatures, identity, permissions, receipt validation and execution
quota are still hard gates. This changes previous behavior for all Turn hosts:
packet growth alone no longer produces contract_error or stops a Turn loop.
The TypeScript owner keeps review allocations totaling 8,192 bytes. These are diagnostic targets, not permission to truncate fields or hard per-section caps:
| Section | Target bytes | Included fields |
|---|---|---|
| action | 800 | action, user, required reads, replan packet, response plan |
| boundary | 2,000 | boundary and execution policy |
| writeback | 600 | validation/settlement commands and policy |
| scheduler | 600 | scheduler action and acknowledgement |
| contracts | 1,800 | contract capsule |
| context | 1,400 | capability context and task orchestration |
| transport | 992 | identity/metadata, signatures, cold-read commands, diagnostics |
Counts include JSON property names, delimiters and UTF-8 text. Their sum equals
the measured final packet; dividing each by envelope_utf8_bytes gives its
share. Diagnostic detail is emitted only on overflow, not every normal Turn.
Use the existing quota should-run --turn-envelope or turn plan JSON output
to inspect the breakdown. Record a public-safe reproduction and compare each
section with the same fixture on the baseline before changing its owner.
First remove repeated presentation or move non-actionable detail to an existing
cold read. Never trim write scope, executable arguments, signatures or required
reads to silence a warning, and do not simply raise the target. The cold-read
commands remain; their redundant human-readable contains inventory is retired.
Repository size/parity canaries remain blocking delivery-time regression checks, independent of runtime warning semantics. Representative fixtures must still fit the target. A warning is a performance investigation signal, not an automatic Todo, new authority, or permission to spend an extra Turn.
中文：TurnEnvelope 超出 8 KiB 后产生可分析的 warning，不再仅因大小中断合法 Turn。按最终 UTF-8 字节数统计各部分占比，先压缩重复展示内容，再检查对应规则 所属模块；不得截断权限、签名或执行指令，也不应单纯提高预算掩盖增长。 身份、权限、签名和执行配额仍是硬门禁；仓库的体积与语义回归检查仍阻止交付。
Hot-path fields may use explicit references when the inline value would only
repeat another authoritative field. In particular,
action.selected_todo.text_ref = action.recommended_action means the selected
todo text is already present as the recommended action. Scheduler reset plans
keep the exact acknowledgement argv inline when it satisfies the executable
argv limits; the failure argv stays behind failure_cli_args_detail_ref until
the host update actually fails. Both omitted-argv references now carry a
detail_ref into full_decision.scheduler_hint.<source carrier> instead of an
unbound quota should-run --include-detail scheduler request. Resolve that path
through this envelope's captured detail_ref.full_decision, check its
Goal/Agent/Turn and source hash, and retain the original argv verbatim. The
carrier is app_automation when supplied, otherwise the historical codex_app;
an alias must not redirect the reference to another source. Missing capture
requires recovery, never another admission disguised as a detail read. Actual
host readback and current scheduler mutation validation still apply.
中文：被省略的 ACK 和失败上报参数通过同一 Turn 保存的完整决策读取，不再
提示执行未绑定的新 quota 命令。先核对 Goal/Agent/Turn 和来源哈希，再按
detail_ref 读取原始参数；历史 Codex 投影仍使用其原始来源。捕获丢失须恢复，
不得将重新准入当作细节读取；此引用不代替实际 host 读回或调度写入时的验证。
This contract is a projection only. It does not change quota selection, todo routing, scheduler state, history writes, or state transitions. Promoting it to the default agent view requires separate parity evidence across delivery, monitor, user-gate, capability-gate, workspace-guard, and blocked states.
tests/fixtures/turn_envelope_state_matrix.json is the durable synthetic
promotion fixture. It covers delivery, monitor quiet-skip, user gate,
capability gate, workspace guard, autonomous replan, successor replan,
blocked, and throttled decisions. Every case must preserve the canonical action
signature and remain within the 8 KiB budget. Historical packet-bearing inputs
must retain their reconstruction, residue, or opaque-summary witness; inputs
without a packet must preserve typed obligations without inventing a witness.
The matrix records exact measurements in validation rather than treating a dated size range as the contract. This keeps the projection available as an opt-in host view. It is not sufficient to change the default CLI response: default promotion still requires shadow parity from a real host integration, no consumer regression with the full decision available as a cold path, and explicit compatibility acceptance for the default-view change.