test(agent-workspace): cover environment scoped facts

Author: Jacobinwwey

Knowledge_Base/ragenvironmentqualifier/environment scoped state status probe.md

@@ -0,0 +1,9 @@
+# Environment Scoped State Status Probe
+Environment scoped state status probe validates that the migration gate status is enabled in the staging environment while production status facts remain environment-qualified evidence rather than a conflict.
+
+## Gate Status By Environment
+The migration gate status is enabled in the staging environment.
+
+Operators should preserve the environment label when comparing deployment records.
+
+The migration gate status is disabled in the production environment.

docs/diataxis/en/explanation/development-progress-dashboard.md

@@ -5,7 +5,7 @@ It tracks what is already implemented, where the hard gaps remain, and how to ve
 
 ## 2026-07-05 RSE Document-Augmented Graph RAG Implementation Plan
 
-This slice now tracks implementation progress for richer Knowledge Workspace answers. The concrete plan remains at [RSE document-augmented graph RAG answer pipeline](../../../plans/2026-07-05-001-feat-rse-document-augmented-rag-plan.md), but the branch has moved beyond planning: the deterministic RSE/document-augmentation path, full-document graph-neighbor augmentation, query-intent graph-neighbor ranking, intent-aware graph connection-path ordering, intent-aligned graph-window ambiguity filtering, budgeted context pack, stable RAG context replay ids, provider-backed sufficiency trace, bounded one-step recovery, RAG failure-stage classification, RAG-aware one-message release review, claim-level citation-backed RAG release gating, prompt/preamble artifact filtering for public RAG clauses, answer claim-to-citation trace/export mapping, operand-aware compare answer-profile budgeting, how-to answer-profile budgeting, causal answer-profile budgeting, generic answer-profile ranking, Mermaid-label evidence extraction, runtime verifier fields, graph successor-window and graph-diagnostics verifier assertions, context-budget truncation/drop/malformed-provider/timeout-provider/graphintent probe coverage, conflicting adjacent, same-section non-adjacent, cross-document structured measurement/date/location evidence, full-document remote-scan hard-negative coverage, controlled current-vs-historical false-positive guards, single- and multi-neighbor graph source-unavailable hard-negative coverage, localized frontend RAG status, and export RAG trace preservation are implemented. Calibrated graph-confidence thresholds, broader replay tooling over larger corpora, more natural synthesis over label-heavy evidence, further profile-specific release-budget calibration, broader semantic conflict classes, and larger runtime probes remain follow-up work.
+This slice now tracks implementation progress for richer Knowledge Workspace answers. The concrete plan remains at [RSE document-augmented graph RAG answer pipeline](../../../plans/2026-07-05-001-feat-rse-document-augmented-rag-plan.md), but the branch has moved beyond planning: the deterministic RSE/document-augmentation path, full-document graph-neighbor augmentation, query-intent graph-neighbor ranking, intent-aware graph connection-path ordering, intent-aligned graph-window ambiguity filtering, budgeted context pack, stable RAG context replay ids, provider-backed sufficiency trace, bounded one-step recovery, RAG failure-stage classification, RAG-aware one-message release review, claim-level citation-backed RAG release gating, prompt/preamble artifact filtering for public RAG clauses, answer claim-to-citation trace/export mapping, operand-aware compare answer-profile budgeting, how-to answer-profile budgeting, causal answer-profile budgeting, generic answer-profile ranking, Mermaid-label evidence extraction, runtime verifier fields, graph successor-window and graph-diagnostics verifier assertions, context-budget truncation/drop/malformed-provider/timeout-provider/graphintent probe coverage, conflicting adjacent, same-section non-adjacent, cross-document structured measurement/date/location evidence, full-document remote-scan hard-negative coverage, controlled current-vs-historical and environment-qualified false-positive guards, single- and multi-neighbor graph source-unavailable hard-negative coverage, localized frontend RAG status, and export RAG trace preservation are implemented. Calibrated graph-confidence thresholds, broader replay tooling over larger corpora, more natural synthesis over label-heavy evidence, further profile-specific release-budget calibration, broader semantic conflict classes, and larger runtime probes remain follow-up work.
 
 Current code-vs-plan reading:
 
@@ -67,6 +67,7 @@ Fresh implementation evidence in this slice:
 - The runtime probe `temporal_cross_document_planned_release_date_probe_en`, backed by `Knowledge_Base/ragtemporalcrossscope`, extends that guard to the cross-document conflict scanner: separate scoped current and planned roadmap documents can both be read in full and returned as evidence without producing a cross-document `conflict` fragment.
 - The runtime probe `conflicting_location_evidence_probe_en`, backed by `Knowledge_Base/raglocationconflict`, now extends the conflict slice to a conservative location comparable-fact class: explicit location/site/region/zone/room/rack/slot/bay subjects with Rack A and Rack B values produce a `conflict` fragment, keep both sides visible in the one public answer, and degrade under `context_assembly`.
 - The runtime probe `temporal_scoped_location_probe_en`, backed by `Knowledge_Base/ragtemporalqualifier`, verifies the paired hard negative: current and historical placement facts stay in separate comparable scopes, the public answer can use the current Rack A fact, and the RAG pack does not emit a false `conflict` fragment.
+- The runtime probe `environment_scoped_state_status_probe_en`, backed by `Knowledge_Base/ragenvironmentqualifier`, now verifies the next condition-qualified guard: staging-enabled and production-disabled status facts stay in explicit environment scopes, the RAG pack forbids `conflict`, and sufficiency remains `sufficient/none` instead of degrading a cross-environment state difference.
 - The runtime probe `causal_answer_profile_budget_en`, backed by `Knowledge_Base/ragcausalprofile`, now verifies that why/cause/mechanism-style requests use a bounded causal RAG profile (`20` fragments, `1500` chars per fragment, `7600` total chars), keep the source boundary at `full_document`, and return one public answer with mechanism and downstream evidence rather than a single definition sentence.
 - The runtime probe `conflicting_multi_document_evidence_probe_en`, backed by `Knowledge_Base/ragmulticonflict`, now verifies that contradictory `+/-0.10 mm` and `+/-0.50 mm` calibration-tolerance facts across two scoped documents produce a cross-document `conflict` fragment, stay visible in the one public answer, and degrade under `context_assembly`.
 - The runtime probe `full_document_scan_remote_conflict_probe_en`, backed by `Knowledge_Base/ragfullscan`, now verifies the corrected source-boundary rule: the local paragraph window is not the maximum range. Two selected documents are read in full, remote appendix facts outside the matched opening spans are scanned for structured conflict evidence, and only the budgeted `RagContextPack` is capped before model-visible answer composition.
@@ -80,7 +81,7 @@ Next movement:
 - Calibrate graph relation weights and low-confidence exclusion thresholds against representative hard negatives instead of treating the current scoring constants as final.
 - Expand runtime probes beyond the current `graphintent` intent-selection baseline into larger-corpus hard negatives and relation-extraction ambiguity samples.
 - Calibrate profile-specific release budgets beyond the current deterministic definition, compare, how-to, causal, and generic baselines while preserving hard public-answer caps.
-- Extend replay tooling beyond stable context ids, failure-stage classifications, graph-window ambiguity diagnostics, and answer claim-citation maps; add larger runtime probes for repeated snippets, conflict patterns beyond controlled structured measurement/date/state/location facts, broader multi-document missing graph-neighbor corpora, stricter total-character budget drop cases, broader relation-ambiguity corpora, and provider fallback.
+- Extend replay tooling beyond stable context ids, failure-stage classifications, graph-window ambiguity diagnostics, and answer claim-citation maps; add larger runtime probes for repeated snippets, conflict patterns beyond controlled structured measurement/date/state/location/environment-qualified facts, broader multi-document missing graph-neighbor corpora, stricter total-character budget drop cases, broader relation-ambiguity corpora, and provider fallback.
 
 ## 2026-07-04 Knowledge Workspace Scope Visibility, Grouped RAG Answers, and File-First Hit Interaction
 

docs/diataxis/zh/explanation/development-progress-dashboard.md

@@ -5,7 +5,7 @@
 
 ## 2026-07-05 RSE + document augmentation 图谱 RAG 实践计划
 
-本切片现在记录更充分 Knowledge Workspace 回答的实现进展。具体方案仍以 [RSE document-augmented graph RAG answer pipeline](../../../plans/2026-07-05-001-feat-rse-document-augmented-rag-plan.md) 为准，但当前分支已经不只是规划：确定性的 RSE / document augmentation 链路、完整文档感知的图邻居 augmentation、query-intent 图邻居排序、intent-aware graph connection-path 排序、intent-aligned graph-window ambiguity filtering、有界 context pack、稳定 RAG context replay id、接入 provider 的充分性 trace、有界一次性 recovery、RAG failure-stage classification、RAG-aware 单消息 release review、claim-level citation-backed RAG release gate、public RAG clause 的 prompt / preamble artifact 过滤、answer claim-to-citation trace / export 映射、基于 operand 的 compare answer-profile 预算、how-to answer-profile 预算、causal answer-profile 预算、generic answer-profile 排序、Mermaid label evidence 抽取、runtime verifier 字段、graph successor-window 与 graph-diagnostics verifier 断言、context-budget truncation/drop/malformed-provider/timeout-provider/graphintent 探针覆盖、相邻 / 同节非相邻 / 跨文档 structured measurement / date / location conflicting evidence 与 full-document remote-scan hard-negative 覆盖、受控 current-vs-historical false-positive guard、单邻居与多邻居 graph source-unavailable hard-negative 覆盖、前端本地化 RAG 状态，以及导出 RAG trace 保留已经落地。图置信阈值校准、大语料上的更完整 replay tooling、对 label-heavy evidence 的自然语言 synthesis、继续细化的 profile-specific release-budget 校准、更广语义 conflict 类和更大的 runtime probe 语料仍是后续工作。
+本切片现在记录更充分 Knowledge Workspace 回答的实现进展。具体方案仍以 [RSE document-augmented graph RAG answer pipeline](../../../plans/2026-07-05-001-feat-rse-document-augmented-rag-plan.md) 为准，但当前分支已经不只是规划：确定性的 RSE / document augmentation 链路、完整文档感知的图邻居 augmentation、query-intent 图邻居排序、intent-aware graph connection-path 排序、intent-aligned graph-window ambiguity filtering、有界 context pack、稳定 RAG context replay id、接入 provider 的充分性 trace、有界一次性 recovery、RAG failure-stage classification、RAG-aware 单消息 release review、claim-level citation-backed RAG release gate、public RAG clause 的 prompt / preamble artifact 过滤、answer claim-to-citation trace / export 映射、基于 operand 的 compare answer-profile 预算、how-to answer-profile 预算、causal answer-profile 预算、generic answer-profile 排序、Mermaid label evidence 抽取、runtime verifier 字段、graph successor-window 与 graph-diagnostics verifier 断言、context-budget truncation/drop/malformed-provider/timeout-provider/graphintent 探针覆盖、相邻 / 同节非相邻 / 跨文档 structured measurement / date / location conflicting evidence 与 full-document remote-scan hard-negative 覆盖、受控 current-vs-historical 和 environment-qualified false-positive guard、单邻居与多邻居 graph source-unavailable hard-negative 覆盖、前端本地化 RAG 状态，以及导出 RAG trace 保留已经落地。图置信阈值校准、大语料上的更完整 replay tooling、对 label-heavy evidence 的自然语言 synthesis、继续细化的 profile-specific release-budget 校准、更广语义 conflict 类和更大的 runtime probe 语料仍是后续工作。
 
 当前代码 / 方案对齐判断：
 
@@ -56,6 +56,7 @@
 - runtime probe `graphintent_compare_neighbor_selection_en` 现在验证 `compare brittle glass vessel with polymer cup material behavior` 会从 `Knowledge_Base/graphintent` 选择 analogy graph successors，从 `successorWindow` 排除高重叠 procedural successor，保留 `graph_neighbor_support`，至少包含一个 `full_document` 图邻居支撑 fragment，并且不会把 procedural path 泄漏进公开回答。
 - runtime probe `graphintent_missing_neighbor_source_window_en` 现在验证当被选中的图邻居 source path 不可用时，图邻居 direct span 仍可观测，但不能单独满足图证据充分性：source decision 会包含 `source_resolver_returned_no_content:direct_support,graph_neighbor_support`，sufficiency 保持 `borderline/partial_coverage`，failure classification 同时包含 `parsing_source` 与 `graph_evidence`。
 - runtime probe `graphintent_multi_neighbor_source_loss_en` 现在要求两个被选 graph-neighbor 源文档同时不可用，并断言至少两个 `source_window_unavailable` decision；对应 assembler 测试也会分别记录两个缺源邻居文档，因此多文档图证据缺失可以按邻居回放。
+- runtime probe `environment_scoped_state_status_probe_en`，backed by `Knowledge_Base/ragenvironmentqualifier`，现在验证下一类条件限定 guard：staging-enabled 与 production-disabled 状态事实会留在显式 environment scope 中，RAG pack 禁止 `conflict`，sufficiency 保持 `sufficient/none`，而不是把跨环境状态差异误降级为 conflict。
 - focused hard-negative 测试现在验证 graph-neighbor source-window 不可用时不会仅凭图邻居标题或 direct span 通过图证据充分性：`evidenceContextAssembler.ts` 会记录 `source_resolver_returned_no_content:graph_neighbor_support`，`ragSufficiencyJudge.ts` 会保持 `borderline/partial_coverage` 并输出 `graph_neighbor_evidence_missing`。
 - focused graph-window ambiguity 测试现在验证：compare intent 在存在 `contrast` / `analogy` 邻居时会过滤高置信 `sequence` / `prerequisite` successor；当图里没有 compare-aligned 邻居时仍 fail-open 到结构 successor。runtime verifier 现在也会在 `graphintent` compare 探针中断言 graph diagnostics：至少 2 个 intent-aligned successor candidate、至少 1 个 intent-misaligned successor candidate，并确认没有使用 misaligned-successor fallback。
 
@@ -64,7 +65,7 @@
 - 基于代表性 hard negative 校准图关系权重与低置信排除阈值，不把当前 scoring 常量当作最终形态。
 - 在当前 `graphintent` intent-selection 基线之上，继续扩展大语料 hard negative 与关系抽取歧义样本的 runtime probes。
 - 在当前 deterministic definition / compare / how-to / causal / generic 基线之上继续校准 profile-specific release budget，同时保留公开回答硬上限。
-- 在稳定 context id、failure-stage classification、graph-window ambiguity diagnostics 与 answer claim-citation map 之上扩展 replay tooling，并补齐 repeated snippet、超出受控 structured measurement / date / state / location 事实的更广 conflict pattern、更大规模多文档 missing graph-neighbor 语料、更严格的 total-character budget drop、更广 relation-ambiguity 语料、provider fallback 的更大 runtime probes。
+- 在稳定 context id、failure-stage classification、graph-window ambiguity diagnostics 与 answer claim-citation map 之上扩展 replay tooling，并补齐 repeated snippet、超出受控 structured measurement / date / state / location / environment-qualified 事实的更广 conflict pattern、更大规模多文档 missing graph-neighbor 语料、更严格的 total-character budget drop、更广 relation-ambiguity 语料、provider fallback 的更大 runtime probes。
 
 ## 2026-07-04 知识工作区 scope 可见性、聚合 RAG 回答与命中文件交互收口