You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Posted by an agent on behalf of @Dong1017 (incremental only; points already raised by @david6666666 and the prior reviewers are not repeated).
Incremental finding on the current #466 head: the accepted default workflow is still missing from the WorkSwarm plugin instructions.
The accepted #379 scope decision says to make find → read the default knowledge-retrieval flow in the README, quickstart, and plugins (decision). The InferRSI plugin was updated, but the WorkSwarm skill still presents the old discovery path as its research workflow: knowledge research, knowledge search, and collect --relevance are the only discovery commands in plugins/workswarm/inferrsi/skills/inferrsi/SKILL.md:42-49, followed by an exact read. A user following that installed plugin will therefore not get the accepted cross-kind find → displayed read command, casebook results, or the documented PyYAML fallback.
Please update that WorkSwarm “Research and diagnose” section to lead with find "<problem or symptom>" and its displayed read arguments, and carry over the PyYAML fallback guidance. Keep the existing package-only commands available as compatibility/fallback operations, as the #379 decision requires.
Scope: read #379 and all five comments, #380, #370, PR #466 metadata/comments/reviews, and the current pr466 head diff. I did not run the test suite or modify code.
Implementer note for #466: WorkSwarm’s Research section still needs the same find → read default (InferRSI plugin already updated). Steward Request changes on that gap: #466 (review)
Could the tracker record default-entry delivery separately from evidence of decision quality? The frozen #380 comparison uses collect, collect plus case lookup, and directory/rg; none of its arms runs find → read. Its results can inform the older retrieval designs, but should not count as validation of #466’s default. Please keep that distinction in the acceptance record when the results arrive.
Independent code/evidence review at main 61303fa8150472dfbda62ec8d77908bc05c73f3b.
Finding: useful discovery and attribution infrastructure is present; the tracking goal is not yet a demonstrated retrieval-efficiency or optimization-quality result. I reviewed the material-discovery/use goal, not linked discussion conclusions or product/budget decisions.
src/inferrsi/knowledge/knowledge_find.py:732-783 ranks skills, records and cases together, exposes matched items and checks whether selected material can be opened. Its own contract correctly says that a lexical match is not proof of applicability. This supports finding historical material from partial clues, not an automatic adoption decision.
knowledge/knowledge_operations.py:786-813 retains the actual collect request, ranking method, returned references/revisions, counts and assembly state. harness/optimization.py:145-157 retains delivered context by path and digest. These are auditable retrieval/delivery facts, not evidence that an agent read or used a resource.
apps/views/search_attribution.py:270-339 supports round-bounded search/read observations, caller-reviewed use and candidate-result links. Missing/partial coverage produces null counts rather than a misleading zero. harness/records/optimization_log.py:150-174,208-224 separately records purpose, takeaways, used/rejected references and round context links. The delivery tests also require a matching versioned resource block in a model-facing return. These distinctions are important: hit, delivered/read, adopted and successful outcome must not be collapsed into one number.
Continuing without a fresh search is supported by the workflow contract (docs/optimization-workflow-unification.md:196); it does not require retrieval on every round. A comparison should preserve that valid no-new-search case rather than count it as an automatic failure.
Remaining evidence/acceptance gap: the clean requirement supplied for this tracking item does not define an original quantitative threshold, frozen tool-comparison protocol or repository-level closure criterion. The code/tests above cannot supply those missing decisions or establish which retrieval tool improves real optimization. A defensible comparison would need a pinned corpus and workload/query set, tool versions/configuration, equal budgets and knowledge conditions, an explicit applicability/read/adoption rubric, and round-level links from the cited material to the changed experiment or validation decision and its measured outcome. These are review recommendations, not accepted scope or a commitment to implement/run a campaign.
Validation actually run: PYTHONPATH=$PWD/src <existing-test-venv>/bin/python -m pytest -q tests/test_knowledge_find.py tests/test_search_capture_delivery.py tests/test_search_attribution.py tests/test_optimization_story.py tests/test_optimization_trace.py: 150 tests passed, exit 0, against the pinned checkout. Collection independently confirmed 60 + 1 + 18 + 41 + 30 tests. No repository changes. No full-suite/CI verification, external retrieval-tool comparison, paid/model/device experiment, or inference performance/quality measurement was run.
Conclusion: focused scaffold behavior is verified; end-to-end improvement and Issue closure remain INCONCLUSIVE, not PASS.
Activity
amy-why-3459 commentedon Nov 10, 2026
感谢建立这个跟踪入口。“只给目录”对照“同目录加简短检索指引”这个首轮方向和 #370 改变的变量是分开的,我同意先做这一组。冻结 A/B 用例之前,有几点建议,想先对齐一下:
KnowledgeReader返回的sha256:revision 或 commit),保证两组对照读到的是同一份材料。另外想确认一下:核心改进任务创建后,会作为本 issue 的子任务关联,还是单独开 issue 再回链?方便后续 review 时对照范围。
jiaran-king commentedon Nov 10, 2026
回应 Amy 在此的建议,执行细节和首个超限样本已同步到 #380。
jiaran-king commentedon Nov 10, 2026
搜索域基线复盘:先例发现、可见送达和决策边界
承接 roadmap 第 4 项,范围是整个搜索域:材料覆盖、选取/排序、上下文送达、继续查询和适用条件判断;“何时停止”是其中一个假设。当前产品入口先维持原状:#380 所测短指引未达到推广门槛,本次新 case 也未使默认 package Indexer 在两个开发查询进入 top 3。这不是目录/
rg已足够省成本的证明。rg对照。#380rg2.374×;完整会话 token 分别为 8,015,641 / 14,597,699。events=[]、counts=null,不意味着未读取。新候选在该单轮 CPU Collect 协议内通过。离线范围检查:默认 package relevance 只排序已登记的 skill owner,相关 case 正文在 owner 选中后才有机会交付;
rg可在真实仓库范围内搜evidence/,因此默认入口差异不能伪装成共同语料下的排序差异。共同语料的 75 个 common/ascend owner 中,Qwen/Drama3 casebook 分别排第 23/51;前三未交付目标。rg对同一资源集可命中相应案例,但行输出与完整上下文是不同交付量,不能直接比较 token 或任务效果。经请求者明确授权,新的三入口、三个决策点、各两次 Agent 对照已在 #380 冻结并开始。它将分别报告决策、材料送达/采用与成本;旧 #255 通用准确度未达成的结论、#370 工具对照以及 #344/#384 记录能力各归原 issue,不在此宣称完成。
jiaran-king commentedon Nov 16, 2026
建议接受 #466 的入口切换,请请求者和维护者在 #379 记录决定。常规知识发现先用
find,再用结果给出的read命令读材料。保留旧命令作为兼容和回退入口。 PR #466#380 当时比较的是在已有目录和
rg的环境中增加一段短检索指引。暂不推广的决定针对那次指引试验。#380 第二轮结果用 #466 的基础 wheel 在无 PyYAML 的 Python 3.11 环境复测了
ascend graph mode。限定 Skill 时,find命中ascend-graph-mode并报告缺少 PyYAML。遇到这个情况,保留collect --relevance 'ascend graph mode' --limit 1 --material --json回退。实测它能找到打包 Skill,随后可用返回的ref、revision和skill_documents.original通过resource读回完整SKILL.md,字节与安装包一致。 David 的评审说明这次提议的验收范围是知识入口。#466 已验证固定查询的命中和案例正文读回。Agent 是否实际采用材料,以及是否带来优化收益,仍待验证。
jiaran-king commentedon Nov 17, 2026
由 Codex 代为记录 #379 请求者
jiaran-king确认的范围决定。接受 #466 将find → read设为 README、quickstart 和插件的默认知识检索流程。原有命令保留为兼容和回退入口。无 PyYAML 时,可以用collect --relevance重新搜索打包的 Skill,判断新结果是否适用后再读回正文。 PR #466#380 暂不推广的决定针对当时测试的短检索指引。#466 验证了固定查询的命中和案例正文读回,单次 Qwen-Image 对照也记录了两份材料的具体采用。稳定的决策质量改善和优化收益仍待验证,#379 的后续目标验收按原有职责推进。 #380 第二轮结果
Dong1017 commentedon Nov 17, 2026
Posted by an agent on behalf of @Dong1017 (incremental only; points already raised by @david6666666 and the prior reviewers are not repeated).
Incremental finding on the current #466 head: the accepted default workflow is still missing from the WorkSwarm plugin instructions.
The accepted #379 scope decision says to make
find → readthe default knowledge-retrieval flow in the README, quickstart, and plugins (decision). The InferRSI plugin was updated, but the WorkSwarm skill still presents the old discovery path as its research workflow:knowledge research,knowledge search, andcollect --relevanceare the only discovery commands inplugins/workswarm/inferrsi/skills/inferrsi/SKILL.md:42-49, followed by an exactread. A user following that installed plugin will therefore not get the accepted cross-kindfind→ displayed read command, casebook results, or the documented PyYAML fallback.Please update that WorkSwarm “Research and diagnose” section to lead with
find "<problem or symptom>"and its displayed read arguments, and carry over the PyYAML fallback guidance. Keep the existing package-only commands available as compatibility/fallback operations, as the #379 decision requires.Scope: read #379 and all five comments, #380, #370, PR #466 metadata/comments/reviews, and the current
pr466head diff. I did not run the test suite or modify code.Dong1017 commentedon Nov 17, 2026
Posted by an agent on behalf of @Dong1017 (authorized steward while hosted Dong-bot is on
usage_limit).Maintainer decision — accept
find → readas default discovery for #466Accepted. Agree with the requester confirmation (comment):
find "<problem or symptom>"then the displayedreadcommand.knowledge research/knowledge search/collect --relevance/ exactreadremain as compatibility and fallback.findentry, not that short guidance.Implementer note for #466: WorkSwarm’s Research section still needs the same
find → readdefault (InferRSI plugin already updated). Steward Request changes on that gap: #466 (review)david6666666 commentedon Nov 17, 2026
Could the tracker record default-entry delivery separately from evidence of decision quality? The frozen #380 comparison uses
collect,collectplus case lookup, and directory/rg; none of its arms runsfind → read. Its results can inform the older retrieval designs, but should not count as validation of #466’s default. Please keep that distinction in the acceptance record when the results arrive.zengchuang-hw commentedon Nov 17, 2026
Independent code/evidence review at main
61303fa8150472dfbda62ec8d77908bc05c73f3b.Finding: useful discovery and attribution infrastructure is present; the tracking goal is not yet a demonstrated retrieval-efficiency or optimization-quality result. I reviewed the material-discovery/use goal, not linked discussion conclusions or product/budget decisions.
src/inferrsi/knowledge/knowledge_find.py:732-783ranks skills, records and cases together, exposes matched items and checks whether selected material can be opened. Its own contract correctly says that a lexical match is not proof of applicability. This supports finding historical material from partial clues, not an automatic adoption decision.knowledge/knowledge_operations.py:786-813retains the actual collect request, ranking method, returned references/revisions, counts and assembly state.harness/optimization.py:145-157retains delivered context by path and digest. These are auditable retrieval/delivery facts, not evidence that an agent read or used a resource.apps/views/search_attribution.py:270-339supports round-bounded search/read observations, caller-reviewed use and candidate-result links. Missing/partial coverage produces null counts rather than a misleading zero.harness/records/optimization_log.py:150-174,208-224separately records purpose, takeaways, used/rejected references and round context links. The delivery tests also require a matching versioned resource block in a model-facing return. These distinctions are important: hit, delivered/read, adopted and successful outcome must not be collapsed into one number.docs/optimization-workflow-unification.md:196); it does not require retrieval on every round. A comparison should preserve that valid no-new-search case rather than count it as an automatic failure.Remaining evidence/acceptance gap: the clean requirement supplied for this tracking item does not define an original quantitative threshold, frozen tool-comparison protocol or repository-level closure criterion. The code/tests above cannot supply those missing decisions or establish which retrieval tool improves real optimization. A defensible comparison would need a pinned corpus and workload/query set, tool versions/configuration, equal budgets and knowledge conditions, an explicit applicability/read/adoption rubric, and round-level links from the cited material to the changed experiment or validation decision and its measured outcome. These are review recommendations, not accepted scope or a commitment to implement/run a campaign.
Validation actually run:
PYTHONPATH=$PWD/src <existing-test-venv>/bin/python -m pytest -q tests/test_knowledge_find.py tests/test_search_capture_delivery.py tests/test_search_attribution.py tests/test_optimization_story.py tests/test_optimization_trace.py: 150 tests passed, exit 0, against the pinned checkout. Collection independently confirmed 60 + 1 + 18 + 41 + 30 tests. No repository changes. No full-suite/CI verification, external retrieval-tool comparison, paid/model/device experiment, or inference performance/quality measurement was run.Conclusion: focused scaffold behavior is verified; end-to-end improvement and Issue closure remain INCONCLUSIVE, not PASS.