[Manager]: route missing PR evidence to a capability-matched Agent

[huangruiteng]

Summary

The Lark manager can receive a question about a concrete pull request in a repository connected to an authorized Goal, but its bounded read tool exposes only sources, portfolio, todos, deliveries, and handoffs. If the PR was not previously materialized into a Core Todo/delivery record, the manager cannot inspect the PR body or diff. In the observed incident it paginated unrelated Goal records, then answered from the user's quoted sentence while saying it could not obtain the PR record.

This is not a transient GitHub/network failure. The current manager contract intentionally says arbitrary external links are not fetched and grants no shell. The product gap is that the manager did not convert the unsupported evidence request into a typed handoff to the capability-matched repository engineering Agent. A second configuration/source problem then exposed only the finance research Agent in the handoff directory, so the repair request was routed to the wrong responsibility lane.

Reproduction

1. Bind a Lark Goal Topic to a Goal with two registered Agents: a research Agent and a steward engineering Agent.
2. Ask the manager why a concrete LoopX PR preserves a compatibility behavior, using only #<number> in the message.
3. Ensure that PR has no exact Core Todo/delivery evidence row in the authorized manager projection.
4. Observe the manager Turn.

Observed on LoopX 1.0.3:

• manager.context was healthy but intentionally partial (complete=false);
• the model issued six successful loopx_manager_read calls over finance and LoopX-meta Todos/deliveries;
• no repository/PR evidence view or capability was available;
• the final answer correctly disclosed that the PR body/diff was unavailable, but still offered an architecture inference rather than opening a typed evidence-acquisition handoff;
• the follow-up repair was handed to the only projected candidate, finance-research-explorer, even though it was steward engineering work.

Root-cause allocation

1. Manager behavior gap: a concrete artifact question without exact evidence should not degrade into repeated broad pagination plus inference.
2. Product capability gap: the bounded manager read surface has no repository artifact view and no explicit evidence_unavailable -> capability-matched handoff route.
3. Configuration/source amplification: the delegation directory may be built from a stale/global projection and omit an Agent registered in the canonical Goal source. PR fix(configuration): preserve settings through canonical Goal source #4303 addresses that source-authority loss but does not by itself add the fallback policy.

Expected behavior

• Keep the manager sandbox bounded: do not grant arbitrary shell, credentials, or unconstrained network access.
• Resolve an explicit PR reference against the Goal's registered repository identity through one reviewed repository-evidence capability, or emit a typed unavailable result.
• When evidence is unavailable locally, offer/perform an authorized context_handoff to the registered Agent whose responsibility/capability matches repository engineering.
• Never select the sole visible Agent merely because it is the sole candidate; fail closed with a typed routing-gap receipt if no compatible receiver exists.
• Return the acquired conclusion through the existing inbox/link/conclusion receipt path and original Lark conversation, without rerunning the original request.

Acceptance coverage

• A fixture with two Agents and a PR-only question routes to the steward engineering Agent, not the research Agent.
• A stale global mirror followed by canonical-source refresh retains both registered Agents; cover source -> global -> restart readback alongside fix(configuration): preserve settings through canonical Goal source #4303.
• An unavailable PR record emits a typed evidence gap and one handoff, not repeated unrelated pagination or an unsupported factual claim.
• The receiving Agent's evidence link and conclusion return to the original Lark audience exactly once.
• Negative tests prove the manager still cannot read arbitrary paths, use raw shell, widen Goal scope, or infer a receiver from list position.

Evidence boundary

The reproduction was derived from bounded local manager Turn receipts: one healthy manager context, six successful Core reads, no tool/provider errors, and no PR/repository read tool in the advertised schema. Private message bodies and workspace paths are intentionally omitted.

[huangruiteng]

重新评估结论：用户问题有价值，但不再保留“缺 PR 证据就自动交接”的独立实现任务。按 superseded / not planned 关闭，未验收的真实场景已并入 #4339 的 “Inherited acceptance” 正文。不是 completed / fixed。

理由与当前证据：

• RFC: capable manager and semantic work handoff / 强能力管家与语义工作交接 #4330 已选择“授权宿主工具直接调查 + 通用语义交接”，fix(manager): read repository evidence before handoff #4306 也已据此关闭。继续建设 Manager 专用 GitHub provider 会增加一条维护路径；普通证据读取失败也不应自动创建后台工作。
• feat(manager): deliver RFC M1 private-owner host profile #4337 已提供显式 trusted_owner 与真实 sandbox/tool readback，短调查可以在现有授权内直接完成。默认 restricted 和外部/Lark audience 没有因此获得宿主权限，不能拿私有 Owner 能力宣称原飞书问题已解决。
• feat(collaboration): add semantic peer collaboration and durable Chat returns #4675 已提供语义 brief、接收方独立判断、同 Goal peer 协作和原会话回传；feat(manager): reconcile uncertain delegated result delivery #4372 已补不确定送达的只读核验。复用这些 owner，无需再建 PR 专属 handoff 协议。
• fix(configuration): preserve settings through canonical Goal source #4303 修复的是配置 canonical-source 问题；它不证明职责匹配。当前 manager_context.authority() 校验注册与 audience grant，输出 recipient identities；这不是工程能力匹配的证明。双角色选择、唯一不适任接收方、缺失/歧义职责，以及受限 Lark 的真实查证→交接→返回仍明确留在 Help wanted: capable manager & semantic handoff / 强能力管家与语义交接（RFC #4330） #4339 验收。

核对了 origin/main@0056a3120cfe87b4ba327578844fe0c137832fb4 的当前 RFC 与合并记录。相关实现核对及回归运行于 d64c4d3772400c958d51b773f1e1e165cbaca801；上述 Manager/profile/handoff/return 文件与该 origin/main 一致。uv run --extra test python -m pytest tests/capabilities/test_manager_runtime_profile.py tests/test_manager_context_handoff.py tests/test_manager_context_roundtrip.py -q：43 passed。这证明现有 profile、scope、幂等交接与回传回归通过，不是一次新的真实模型/飞书端到端验收。本次没有修改产品代码或启动 Agent/发送飞书消息。

后续只有在真实旅程复现具体残余失败时，才在现有 M1/M2/M3 owner 上补最小完整修复；保留 RFC §6 的 live investigation/routing 验收义务，不复活 #4306，也不凭 issue 关闭宣称能力完成。

English disposition: superseded, not fixed. Consolidated the remaining direct-investigation, responsibility-selection and original-audience return acceptance into #4339. Existing host tools and semantic collaboration are the product path; no PR-specific provider or automatic delegation on a missing read is planned. The exact external/Lark scenario remains unqualified.