huangruiteng · Oct 27, 2026 · Oct 27, 2026
@@ -0,0 +1,143 @@
+# Primary-action instruction selection
+
+[中文镜像](2026-10-27-primary-action-instruction-selection.zh-CN.md)
+
+## Boundary and ownership
+
+This Stage 2B slice removes the Python instruction decision owner while keeping
+caller-visible prose and rendering stable. `projectInteractionExecution` in
+`work_items/interaction_contract.ts` selects the existing mode and its primary
+instruction in the same `work_item.interaction_execution.project` request.
+There is no new operation, handler registration, runtime, provider or store.
+Qualification remains incomplete until the validation holds below are resolved.
+
+Retired Python symbols in `work_items/primary_action.py`:
+
+- `protocol_first_candidate_action`: source precedence, addressed labels,
+  capability candidate count, scoped successor and advancement fallbacks.
+- `protocol_replan_action_packet_instruction`: settlement-only, successor and
+  generic typed-outcome wording.
+- `resolve_canonical_primary_action`: exact mode prose, fallbacks and child/peer
+  lane counts, including the empty-child-list precedence over peer lanes.
+
+`interaction_contract.py::_project_interaction_execution` sends a single optional
+facts/views carrier and the existing `action_selection_context` projection.
+The final contract builder requests and threads the returned instruction through
+`_build_interaction_agent_channel` into `build_primary_action_projection`.
+`unadmitted_action_selection` retains its mode-only preflight and exact result
+shape. The TS owner composes `actionSelectionNeedsRecovery` before reading
+instruction facts; rejected/deferred recovery does not construct executable
+instructions. The existing Python recovery alternative, selection/capability
+channel overrides, blocked-successor override and blocked-wait override remain.
+
+Python retains `protocol_action_text` and `protocol_action_label`: Python `str`
+and nested repr, truthiness, whitespace, label prefixes and code-point limits
+are compatibility codecs, including `...` rather than the trace codec's `…`.
+`primary_action_instruction_facts` transports those views and existing Todo
+eligibility/lifecycle source facts; it does not select an instruction or retry a
+Python fallback. Python transports at most the first selectable row per list
+source, evaluated from the same coerced views; the typed owner applies the same
+predicates and source precedence. Request size is independent of backlog/Todo
+list length. Registered effective actions and agent-scope values come from
+their generated TS exports. Other existing local rule strings keep their exact
+spellings; no shared vocabulary or persisted schema is added.
+
+Python also retains `protocol_monitor_action` and the resolution trace through
+`state_projection.next_action_resolution_trace`. `primary_action` still precedes
+optional `resolution_trace`; channel insertion order and final Python JSON
+serialization are unchanged. Delete the trace/monitor facade only when their
+remaining consumers adopt a complete typed action/trace projection. Delete the
+scalar/label codecs and facts carrier only after the last Python text/label
+consumer exits and a complete typed compatibility codec proves Python coercion,
+Unicode, truncation and trace parity. This slice does not retire those owners.
+
+## Vocabulary budget
+
+The registry's `meaning` says "module_budget counts modules under loopx/ whose text carries the standalone field token" and "the token count stays until Q11 decides whether the syntactic metric replaces it"; this deliberately conservative lexical proxy protects against unexplained growth in potential field readers.
+On the same tracked-source workload, base `be1dc37a0` → `this commit` moves `goal_boundary` lexical counts from Python/TypeScript 30/2 → 29/3 (total 32 unchanged), originally failing `legacy field goal_boundary grew to 3 .ts modules; budget is 2` and retrodiction `(13, 15)` versus frozen `(12, 15)`.
+The moved sentence, `repair goal_boundary.write_scope projection before attempting the selected write`, is byte-identical agent-facing prose, adding no reader, writer or binder; the smoke's prose-versus-reader distinction keeps migration surfaces at Python 16 / TypeScript 1.
+Retaining that instruction, the registry tightens the Python token budget to its measured 29 and increases TypeScript 2 → 3, with zero lexical headroom; migration-surface budgets and their anchor remain unchanged at 16/1, while the registry and `RETIREMENT_ANCHOR` move together in this same commit, as the anchor mechanism requires; the retrodiction baseline is unchanged and the measured result returns to `(12, 15)` (`would_have_caught=12/15`, `caught_baseline=12/15`) once the budget accepts the measured counts.
+
+## Economics and parity
+
+Against the immutable base, the three retired function spans contain 267 physical
+lines (269 including separating lines). Production Python is 185 lines smaller;
+TS grows by 109; net production is 76 lines smaller. The primary-action module
+shrinks 347 → 152 lines. The new Python facts codec is 77 lines plus its
+separators; remaining Python changes are transport/result plumbing. The TS
+helper contains 14 lines of local view decoders (`facts`, `object`, `text`,
+`rows`, `count`), not another RPC surface. The bounded
+companion refactor reuses `action_selection_context` rather than a second
+admission-fact encoder. Broader admission, monitor and trace migration is deferred.
+
+One untimed base/head execution and one logical-request trace per command,
+with isolated synthetic SQLite fixtures and one or three delegation bindings:
+
+| Command | Bindings | Crossings base → head | Stdout bytes base → head |
+| --- | --- | --- | --- |
+| `agent-context --phase before_plan` | 1 | 1 → 1 | 1885 → 1885 |
+| `agent-context --phase after_delegate_result` | 1 | 3 → 3 | 1612 → 1612 |
+| Same result phase with a Turn instance | 1 | 3 → 3 | 2594 → 2594 |
+| `quota should-run` | 1 | 75 → 75 | 25520 → 25520 |
+| `agent-context --phase before_plan` | 3 | 1 → 1 | 2247 → 2247 |
+| `agent-context --phase after_delegate_result` | 3 | 3 → 3 | 1612 → 1612 |
+| Same result phase with a Turn instance | 3 | 3 → 3 | 2594 → 2594 |
+| `quota should-run` | 3 | 75 → 75 | 25904 → 25904 |
+
+All eight normalized JSON outputs match after excluding timestamp keys ending
+in `_at`, `context_id`, `event_id` and `staleness_seconds`. This is equal byte
+count and normalized-content evidence, not literal equality of volatile fields
+or a latency improvement claim. No persisted-format change or data migration.
+
+## Validation and remaining gates
+
+A pre-change synthetic fixture pins 182 cases: all modes, candidate-source
+precedence, fallback and lane-count branches, empty/invalid source shapes,
+booleans, numbers, nested values, whitespace, Unicode/non-BMP and truncation.
+Native tests check those independently pinned instructions and the recovery
+getter sentinel; Python checks codec views, non-JSON `str` and projection order.
+Existing Python CLI/Host integration assertions are retained. Retire the pinned
+Python payload/view fixture when its last codec consumer exits and native
+invariant tests independently cover the same wording/source branches.
+
+The oversized-backlog regression pins 22,000 rows through the public Python
+projection: the lane instruction matches BASE, and rejected selection preserves
+the BASE recovery command with `must_attempt` and `delivery_allowed` both false.
+Encoded instruction facts stay below 16 KiB.
+
+<!-- validation-results -->
+Independent review's rule table found EQUIVALENT selection semantics with one
+DIVERGENT row for oversized eager transport; the bounded first-selectable-row
+carrier fixes it: facts for 22,000 rows shrink 2,354,852 → 959 bytes, with lane
+and rejected-selection recovery outputs byte-identical to base and pinned in
+tests. The fix passes 38 arbitration tests, 37 native tests and 309 Python
+adapter tests, including 182-case typed-instruction parity. The `goal_boundary`
+vocabulary budget decision moves Python/TypeScript 30/2 → 29/3 together with
+`RETIREMENT_ANCHOR` in this commit; the smoke reports
+`semantic-vocabulary-drift-smoke: ok`, architecture tests pass 128/128, and
+retrodiction returns to the unchanged 12/15 baseline. The full TS suite passes
+5,528 tests with 0 failures and 75 PostgreSQL skips. The original full Python
+suite records 27,169 passed, 908 failed, 234 skipped and 8 errors; base replay
+of its 147 failing files records 2,353 passed, 905 failed, 18 skipped and
+8 errors, reproducing 913/916 distinct failure/error IDs under the same guard,
+whose restrictions induced some failures. Of the three head-only failures,
+the two architecture failures are repaired above; the third is
+environment-induced because dashboard dependencies were installed mid-validation,
+while base skips that test. The final-code 44-module sweep has identical sets
+of 84 failures on base and head, zero new failures, 1,871 → 1,880 passes and
+20 skips on each; these scoped runs do not establish a green full Python suite.
+The final canary reports status: `passed`, ok: `true`, merge_gate_passed: `true`,
+manual_holds: `0`, with 0 failures. The four interleaved benchmark runs
+(25 timed runs and 3 warmups per command) retain equal bytes on all eight
+commands and unchanged 1/3/3/75 crossings for both binding counts; every median
+regression is within the stated 5% rule, so byte, crossing and median checks
+pass without a latency-improvement claim. CI-only limits remain a real
+PostgreSQL server, Node 22.22.3, Windows and browser lanes; PostgreSQL skips
+are not passes. Main's inherited failures remain tracked by #7433–#7436 and
+#7389; this validation does not resolve them.
+
+Installed wheel, minimum Node, Windows, real PostgreSQL and full CI are not
+qualified locally; PostgreSQL skips are not passes. The committed-head bilingual
+check and premerge canary remain orchestrator/validation responsibilities. These
+holds do not authorize broader authority/provider changes or weaker acceptance.
+Rollback is a code-only revert; no state rewrite is needed.
@@ -0,0 +1,120 @@
+# Primary-action 指令选择
+
+[English mirror](2026-10-27-primary-action-instruction-selection.md)
+
+## 边界与归属
+
+本 Stage 2B 切片删除 Python 指令决策 owner，保持调用方可见文字和渲染。
+`work_items/interaction_contract.ts` 中的 `projectInteractionExecution` 在原有
+`work_item.interaction_execution.project` 请求内同时选择 mode 与 primary 指令。
+不新增 operation、handler 注册、runtime、provider 或 store。
+下述验证 hold 解决之前，资格仍未完成。
+
+删除 `work_items/primary_action.py` 中的 Python 符号：
+
+- `protocol_first_candidate_action`：来源优先序、带地址标签、capability 候选数量、
+  scoped successor 与 advancement 回退。
+- `protocol_replan_action_packet_instruction`：仅结算、successor 和通用 typed-outcome 文字。
+- `resolve_canonical_primary_action`：各 mode 的精确文字、回退和 child/peer lane 数量，
+  包括空 child 列表优先于 peer lanes 的规则。
+
+`interaction_contract.py::_project_interaction_execution` 发送一个可选 facts/views
+carrier 和现有 `action_selection_context` 投影。最终 contract builder 请求并将返回
+指令经 `_build_interaction_agent_channel` 传入 `build_primary_action_projection`。
+`unadmitted_action_selection` 保留仅 mode 的 preflight 和精确结果形状。
+TS owner 在读取指令事实前组合 `actionSelectionNeedsRecovery`；rejected/deferred
+恢复不构建可执行指令。既有 Python 恢复分支、selection/capability channel 覆盖、
+blocked-successor 覆盖及 blocked-wait 覆盖均保留。
+
+Python 保留 `protocol_action_text` 和 `protocol_action_label`：Python `str`、嵌套
+repr、真值、空白、标签前缀和按码点限制都是兼容 codec，包括 `...`，而非 trace
+codec 的 `…`。`primary_action_instruction_facts` 传递这些视图及现有 Todo 资格／
+lifecycle 来源事实，不选择指令，也无 Python 决策回退。Python 对每个列表来源至多
+传输从相同强制转换视图判定的首个可选行；typed owner 应用相同谓词和来源优先序。
+请求大小不随 backlog／Todo 列表长度增长。已注册 effective action 和
+agent-scope 值导入生成的 TS exports。其他现有局部规则字符串保持精确拼写；
+不新增共享词汇或持久化 schema。
+
+Python 还保留 `protocol_monitor_action` 和经
+`state_projection.next_action_resolution_trace` 构建的 resolution trace。
+`primary_action` 仍先于可选 `resolution_trace`；channel 插入顺序和最终 Python JSON
+序列化不变。仅当剩余消费者采用完整 typed action/trace 投影时，才删除 trace/monitor
+facade。仅当最后一个 Python text/label 消费者退出，且完整 typed 兼容 codec 证明
+Python coercion、Unicode、截断及 trace 等价时，才删除 scalar/label codec 和 facts
+carrier。本切片不宣称这些 owner 已退役。
+
+## 词汇预算
+
+registry 的 `meaning` 写明 "module_budget counts modules under loopx/ whose text carries the standalone field token" 和 "the token count stays until Q11 decides whether the syntactic metric replaces it"；这一刻意保守的词法代理用于防止潜在字段 reader 数量出现无解释增长。
+在相同 tracked-source 负载上，base `be1dc37a0` → `this commit` 的 `goal_boundary` 词法计数从 Python/TypeScript 30/2 → 29/3（总数仍为 32），原始失败为 `legacy field goal_boundary grew to 3 .ts modules; budget is 2`，以及 retrodiction `(13, 15)` 对比冻结值 `(12, 15)`。
+迁移的句子 `repair goal_boundary.write_scope projection before attempting the selected write` 是逐字节一致的 agent-facing 文字，未新增 reader、writer 或 binder；smoke 对文字与 reader 的区分使 migration surface 保持 Python 16 / TypeScript 1。
+保留该指令，registry 将 Python token 预算收紧至实测 29，并将 TypeScript 从 2 增至 3，词法余量为零；migration-surface 预算及其 anchor 维持 16/1 不变，而 registry 与 `RETIREMENT_ANCHOR` 按 anchor 机制要求在同一提交中一起调整；retrodiction 基线不变，预算接受实测计数后，实测结果恢复为 `(12, 15)`（`would_have_caught=12/15`、`caught_baseline=12/15`）。
+
+## 经济性与等价
+
+相对固定基线，三个删除函数跨度共 267 物理行（含间隔行则为 269）。生产 Python
+净减 185 行，TS 增 109 行，生产总代码净减 76 行。primary-action 模块从 347 行缩为
+152 行。新增 Python facts codec 为 77 行加间隔；其余 Python 变化为 transport／结果
+传递。TS helper 内有 14 行局部 view decoder（`facts`、`object`、`text`、`rows`、
+`count`），不另建 RPC surface。伴随的有界重构复用 `action_selection_context`，不另建 admission facts 编码器。
+更广的 admission、monitor 和 trace 迁移延后。
+
+在隔离的合成 SQLite fixture 上，分别使用 1 或 3 个 delegation binding；每条命令
+各执行一次不计时的 base/head 输出和一次逻辑请求 trace：
+
+| 命令 | Binding 数 | Crossings base → head | Stdout 字节 base → head |
+| --- | --- | --- | --- |
+| `agent-context --phase before_plan` | 1 | 1 → 1 | 1885 → 1885 |
+| `agent-context --phase after_delegate_result` | 1 | 3 → 3 | 1612 → 1612 |
+| 同一 result phase，带 Turn instance | 1 | 3 → 3 | 2594 → 2594 |
+| `quota should-run` | 1 | 75 → 75 | 25520 → 25520 |
+| `agent-context --phase before_plan` | 3 | 1 → 1 | 2247 → 2247 |
+| `agent-context --phase after_delegate_result` | 3 | 3 → 3 | 1612 → 1612 |
+| 同一 result phase，带 Turn instance | 3 | 3 → 3 | 2594 → 2594 |
+| `quota should-run` | 3 | 75 → 75 | 25904 → 25904 |
+
+排除以 `_at` 结尾的时间字段、`context_id`、`event_id` 和 `staleness_seconds` 后，
+八组规范化 JSON 均一致。这证明字节数和规范化内容等价，不代表易变字段字面一致，
+也不宣称延迟提升。不改变持久化格式，无数据迁移。
+
+## 验证与剩余门禁
+
+修改前合成 fixture 固定 182 个案例：全部 mode、候选来源优先序、回退及 lane 数量
+分支、空／非法来源形状、布尔值、数值、嵌套值、空白、Unicode／非 BMP 和截断。
+原生测试核对独立固定的指令和 recovery getter sentinel；Python 核对 codec 视图、
+非 JSON `str` 及投影顺序。既有 Python CLI／Host 集成断言保留。仅当最后一个 codec 消费者退出，且原生
+invariant 测试独立覆盖相同文字／来源分支时，才删除固定的 Python payload/view fixture。
+
+超大 backlog 回归通过公开 Python 投影固定 22,000 行：lane 指令与 BASE 一致，
+rejected selection 保留 BASE 恢复命令，且 `must_attempt` 和 `delivery_allowed` 均为 false。
+编码后的指令事实保持在 16 KiB 以下。
+
+<!-- validation-results -->
+独立 review 的规则表判定选择语义为 EQUIVALENT，仅超大 eager transport 一行为
+DIVERGENT；有界首个可选行 carrier 修复该问题：22,000 行的 facts 从
+2,354,852 字节缩至 959 字节，lane 与 rejected-selection recovery 输出均与 base
+逐字节一致，并由测试固定。修复通过 38 项 arbitration、37 项原生及 309 项 Python
+adapter 测试，包含 182 案例 typed-instruction parity。`goal_boundary` 词汇预算决策
+将 Python/TypeScript 从 30/2 调整为 29/3，并在本提交中同步调整
+`RETIREMENT_ANCHOR`；smoke 报告 `semantic-vocabulary-drift-smoke: ok`，
+architecture 测试 128/128 通过，retrodiction 恢复至未变的 12/15 基线。
+完整 TS suite 为 5,528 项通过、0 项失败、75 项 PostgreSQL skip。原始完整 Python
+suite 记录 27,169 项通过、908 项失败、234 项 skip、8 项 error；base 重放其
+147 个失败文件，记录 2,353 项通过、905 项失败、18 项 skip、8 项 error，
+在相同 guard 下复现 913/916 个不同的 failure/error ID，其中部分失败由 guard
+限制引起。三个 head-only 失败中，两个 architecture 失败已由上述修复解决；第三个
+由环境引起，因为验证期间安装了 dashboard 依赖，而 base 跳过该测试。最终代码的
+44 模块 sweep 在 base 与 head 上具有完全相同的 84 个失败，新增失败为零，
+通过数为 1,871 → 1,880，两边各有 20 项 skip；这些限定范围的运行不能证明完整
+Python suite 全绿。最终 canary 报告 status: `passed`、ok: `true`、
+merge_gate_passed: `true`、manual_holds: `0`，失败数为 0。四轮交错 benchmark
+运行（每条命令 25 次计时、3 次 warmup）中，八条命令的字节数全部相等，两种 binding
+数量的 crossings 均维持 1/3/3/75；每项中位数回退均在既定 5% 规则内，因此字节数、
+crossing 和中位数检查通过，不宣称延迟提升。仅 CI 可验证的限制仍包括真实
+PostgreSQL server、Node 22.22.3、Windows 和 browser lanes；PostgreSQL skip
+不等于通过。main 的继承失败仍由 #7433–#7436 和 #7389 跟踪；本次验证未解决它们。
+
+本地未验证 installed wheel、最低 Node、Windows、真实 PostgreSQL 及完整 CI；
+PostgreSQL skip 不等于通过。提交确切 head 后的双语检查和 premerge canary 由
+orchestrator／验证工程师负责。这些 hold 不授权更广的 authority/provider 修改或
+降低验收。回滚仅需撤销代码，无需改写状态。