test(agent-workspace): cover location conflict scopes

Author: Jacobinwwey

Knowledge_Base/raglocationconflict/location conflict probe.md

@@ -0,0 +1,13 @@
+# Control Module Location Conflict Probe
+
+Control module location conflict probe validates that controlled location contradictions are not flattened into one stable site.
+
+## Module Placement
+
+The control module location is Rack A in the primary bay.
+
+Context paragraph keeps the controlled location conflict inside one scoped section.
+
+The control module location is Rack B in the field bay.
+
+Operators must resolve the active placement record before publishing location guidance.

Knowledge_Base/ragtemporalqualifier/temporal location probe.md

@@ -0,0 +1,11 @@
+# Temporal Module Placement Probe
+
+Temporal module placement probe validates that the control module location is Rack A in the current release record while historical placement facts remain condition-qualified evidence rather than a conflict.
+
+## Module Placement History
+
+The control module location is Rack A in the current release record.
+
+Operators should answer with the active placement while retaining the older placement as provenance.
+
+The control module location is Rack B in the historical placement archive.

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, 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 evidence, and full-document remote-scan hard-negative coverage, 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, broader release-budget calibration, 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, 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, broader release-budget calibration, broader semantic conflict classes, and larger runtime probes remain follow-up work.
 
 Current code-vs-plan reading:
 
@@ -16,7 +16,7 @@ Current code-vs-plan reading:
 | Graph context should use in-degree/out-degree and neighbor content, not only neighbor titles | `KnowledgeLearningPlatform.agentConversation()` now materializes selected graph-neighbor items and lets the evidence assembler produce both snippet-level and full-document-aware `graph_neighbor_support` fragments. `graphContextAssembler.ts` now ranks predecessor/successor windows and connection paths with query-intent scoring policies, relation-kind priority, confidence/provenance scoring, anchor-equivalent filtering, bibliography exclusion, and intent-aligned ambiguity filtering before evidence assembly. Compare windows prefer `contrast` / `analogy` neighbors when present, fail open to structural neighbors only when no aligned candidate exists, and expose aligned/misaligned candidate diagnostics. | Implemented deterministic path; larger-corpus calibration remains |
 | The answer should be one visible message while orchestration stays in backend | `conversationComposer.ts` now passes `ragContextPack` and `ragSufficiencyReview` into `answerReleaseReview.ts`; release review can revise or enrich a public answer from direct, document, and graph fragments while keeping orchestration in trace/status surfaces, and `rag_claim_citation_support` now contracts drafts when sentence-level public claims are unsupported or only weakly covered by citation-backed RAG fragments. Compare-intent RAG answers now extract operands, keep explicit scope from being hard-narrowed to only title-hit document ids, reserve four direct-support clauses for both sides, rank evidence by operand/fragment coverage, and turn Mermaid comparison labels into readable evidence before graph contrast context is added. How-to answers now reserve direct/document/graph budget for ordered steps, prerequisites, downstream checks, and failure handling instead of collapsing to a generic overview. Generic answers now use query-term coverage ranking and two direct-support slots so broad prompts keep the most relevant grounded clauses instead of generic preambles. `KnowledgeLearningPlatform.ts` now records optional `answerClaimCitations` that map public-answer claims to citation ids, RAG fragment ids, and source paths for trace/export auditing, while `agent_workspace.js` / `workspace_panes.js` show compact status rather than extra chat messages. | Preserved and strengthened |
 | LLM judging should improve answer completeness | `ragSufficiencyJudge.ts` has deterministic gates plus an injected optional LLM judge hook. `ragSufficiencyProviderJudge.ts` now adapts the existing `LlmProviderClient` / NoteMD settings boundary with strict JSON parsing, timeout, no retries, and deterministic fallback through the reviewer catch path; malformed completion text now rejects at the adapter boundary so `llm_judge_failed:*` remains replayable. `KnowledgeLearningPlatform.agentConversation()` now performs at most one bounded recovery assembly/review pass when the first pack is recoverably borderline or insufficient. | Implemented for Unit 5 |
-| Weak evidence should degrade explicitly | `RagSufficiencyReview` now records `sufficient`, `borderline`, or `insufficient` plus degradation states such as `partial_coverage`, `conflict`, and `insufficient_evidence`; `evidenceContextAssembler.ts` now emits a `conflict` fragment for same-subject measurement or date/year evidence with divergent values when those facts are adjacent or non-adjacent inside the same scoped section, marks graph-neighbor source-window misses with graph-neighbor role provenance, and `ragSufficiencyJudge.ts` degrades graph context when the neighbor has only a direct span but no recoverable source window. `KnowledgeLearningPlatform.ts` classifies the resulting states under `context_assembly` or `graph_evidence` as appropriate. The frontend evidence pane displays the compact state. | Implemented for deterministic review |
+| Weak evidence should degrade explicitly | `RagSufficiencyReview` now records `sufficient`, `borderline`, or `insufficient` plus degradation states such as `partial_coverage`, `conflict`, and `insufficient_evidence`; `evidenceContextAssembler.ts` now emits a `conflict` fragment for same-subject measurement, date/year, explicit state/status, or controlled location evidence with divergent values when those facts are adjacent or non-adjacent inside the same scoped section, marks graph-neighbor source-window misses with graph-neighbor role provenance, and `ragSufficiencyJudge.ts` degrades graph context when the neighbor has only a direct span but no recoverable source window. `KnowledgeLearningPlatform.ts` classifies the resulting states under `context_assembly` or `graph_evidence` as appropriate. The frontend evidence pane displays the compact state. | Implemented for deterministic review; broader semantic classes remain open |
 
 Architecture ownership now has a sharper split:
 
@@ -65,6 +65,8 @@ Fresh implementation evidence in this slice:
 - The runtime probe `temporal_scoped_release_date_probe_en`, backed by `Knowledge_Base/ragtemporalqualifier`, extends the same condition-qualified false-positive guard to release dates: current and historical release-date facts can coexist as evidence without degrading the answer as a structured conflict. These temporal probes also reject generic predecessor/successor graph-profile narration in the one public RAG answer; graph content must come from citation-backed RAG evidence rather than automatic graph-window labels.
 - The runtime probe `temporal_scoped_planned_release_date_probe_en`, backed by `Knowledge_Base/ragtemporalqualifier`, extends the same condition-qualified guard to planned/future-qualified release dates: a current release date and a planned roadmap date can both be read from the full source document without becoming a false conflict.
 - 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 `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.
 - Focused provenance tests now verify that repeated snippet text does not force the first textual occurrence when offsets are stale. If an offset candidate does not contain the evidence snippet but the line-range candidate does, `evidenceContextAssembler.ts` uses the line provenance to select the intended source block and parent section.
@@ -77,7 +79,7 @@ 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, 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 structured measurement/date 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 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