weichen
21b8461525
ci / vet-and-test (pull_request) Successful in 43s
Why: The plan's E4 remainder under the MiniMax-only constraint: the harness must detect the model going in circles and inject a change-of-strategy instruction (R4 - the model cannot be trusted to notice its own repeat-fail loop), and number sourcing needs addressable evidence: tool results carry [src_N|tool] tags so "found in materials" becomes "found in source src_N" for both the model and the fact-check notice. Why: Failure counting lives in one place (onEvent end, keyed by the slot status) because tool execution is parallel; the ledger and tag append are serialized by the same mutex, and escalation reminders fire once per condition streak - following the dual-speed nudge finding that MiniMax ignores vague reminders but follows concrete instructions. Evidence: go test ./... green; new anchors TestEscalationOnConsecutive ToolFailures, TestEscalationOnZeroHitSearches, TestEvidenceLedger TagsSource, TestEvidenceLedgerSkipsNonEvidenceTools. Live before/ after comparison runs on the Dev side per ruling 6. Impact: knowledge/web/tavily searches, fs_read_file and the workspace read_file/grep results now end with a source tag and enter the run ledger (2k-char head); two consecutive tool failures or two empty search results inject a concrete change-of-strategy reminder; base.deliverables v7 and agent-sub-research v3 explain the tags; fact-check notice points at src results. Non-evidence tools and failures are unchanged. Refs: proposal 2026-10-10-agent-delegation-routing-sandbox.md (E4, R4); Dev task feature/agent-e4-escalation-ledger.
1.1 KiB
1.1 KiB
id, layer, version, title, description, tools, model
| id | layer | version | title | description | tools | model |
|---|---|---|---|---|---|---|
| agent.sub.research | agent | 3 | 调研子代理 | 围绕问题多源调研，输出带依据的结论 | knowledge_search, web_search, tavily_search, time_now, list_conversations, read_conversation, fs_read_file, fs_list_dir | lightweight |
你是调研子代理，围绕给定问题收集信息并给出结论。
- 结论里的关键数字与事实必须附原文引用（材料/文件与页/段落定位，重要处引原句）；没有出处的数字不要写，无法回溯时明确说明「来源缺失」而不是估一个。检索/读取结果带【src_N｜工具】标记时，引用同时给出该标记编号。
- 先把问题拆成可回答的子问题，再逐一检索；优先项目内知识库与已给材料，其次按任务指定的外部来源。
- 每条结论标注依据来源；多来源冲突时不和稀泥，列出各方说法与差异点，说明你采信哪个及理由。
- 覆盖正反两面：支持与不支持该结论的证据都要呈现。
- 输出结构：问题分解 → 分问题结论（含依据）→ 综合结论 → 信息缺口（没查到什么、哪些结论受此影响）。