feat(agent-workspace): cover dependency conflicts

Author: Jacobinwwey

Knowledge_Base/ragdependencyconflict/dependency conflict probe.md

@@ -0,0 +1,10 @@
+# Dependency Conflict Probe
+Dependency conflict probe records competing storage dependency values: SQLite and PostgreSQL.
+
+## Storage Dependency
+The storage dependency is SQLite in the release manifest.
+
+Context paragraph keeps the dependency conflict inside one scoped section.
+
+The storage dependency is PostgreSQL in the rollback manifest.
+Operators must resolve which storage dependency is active before release.

Knowledge_Base/ragdependencyqualifier/environment scoped dependency probe.md

@@ -0,0 +1,10 @@
+# Environment Scoped Dependency Probe
+Environment scoped dependency probe records that the storage dependency is SQLite for staging and PostgreSQL for production.
+
+## Environment Dependencies
+The storage dependency is SQLite in the staging environment.
+
+Context paragraph keeps both environment-specific dependencies in one scoped section.
+
+The storage dependency is PostgreSQL in the production environment.
+Operators should not collapse staging and production dependency records into one single storage dependency.

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/quantity evidence including plural unitless quantity facts, same-document and cross-document controlled ownership identity conflicts, full-document remote-scan hard-negative coverage, controlled current-vs-historical, environment-qualified, version-qualified, and platform-qualified false-positive guards including condition-scoped ownership identity, 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/quantity evidence including plural unitless quantity facts, same-document and cross-document controlled ownership identity conflicts, controlled endpoint and dependency conflicts, full-document remote-scan hard-negative coverage, controlled current-vs-historical, environment-qualified, version-qualified, and platform-qualified false-positive guards including condition-scoped ownership identity plus environment-qualified endpoint/dependency 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:
 
@@ -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, unitless quantity/limit, date/year, explicit state/status, controlled location, or controlled ownership identity 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 |
+| 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, unitless quantity/limit, date/year, explicit state/status, controlled location, controlled ownership identity, controlled endpoint, or controlled dependency 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:
 
@@ -80,6 +80,7 @@ Fresh implementation evidence in this slice:
 - The runtime probe `platform_scoped_ownership_identity_probe_en`, backed by `Knowledge_Base/ragplatformqualifier`, extends that platform guard to controlled ownership identity facts: Windows `Release Ops` and Android `Rollback Team` owners remain platform-qualified evidence rather than a false conflict.
 - The runtime probes `cross_document_environment_scoped_ownership_identity_probe_en`, `cross_document_version_scoped_ownership_identity_probe_en`, and `cross_document_platform_scoped_ownership_identity_probe_en`, backed by `Knowledge_Base/ragconditionownercrossscope`, now verify that the full-document cross-document conflict scanner preserves environment-, version-, and platform-qualified owner facts across separate scoped documents instead of producing false `conflict` fragments.
 - The runtime probes `conflicting_endpoint_evidence_probe_en` and `environment_scoped_endpoint_probe_en`, backed by `Knowledge_Base/ragendpointconflict` and `Knowledge_Base/ragendpointqualifier`, now extend controlled semantic-conflict coverage to explicit endpoint/url/uri/route facts. Same-section `/api/v1/hooks` versus `/api/v2/hooks` produces a `conflict` fragment and `context_assembly` degradation, while staging and production endpoint routes stay environment-qualified evidence without a false conflict. Endpoint path segments such as `/v1/` are treated as route values, not version scopes.
+- The runtime probes `conflicting_dependency_evidence_probe_en` and `environment_scoped_dependency_probe_en`, backed by `Knowledge_Base/ragdependencyconflict` and `Knowledge_Base/ragdependencyqualifier`, now extend controlled semantic-conflict coverage to explicit dependency/package/provider/driver/runtime/library/module/plugin/adapter facts. Same-section SQLite versus PostgreSQL storage dependency statements produce a `conflict` fragment and `context_assembly` degradation, while staging and production dependency records stay environment-qualified evidence without a false conflict.
 - 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.

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

@@ -72,6 +72,7 @@
 - runtime probe `temporal_scoped_ownership_identity_probe_en` 现在由 `Knowledge_Base/ragtemporalqualifier` 支撑，把 current-vs-historical false-positive guard 扩展到受控责任归属 identity facts：current `Release Ops` owner 与 historical `Rollback Team` owner 会保留为条件限定 evidence，而不是误产出 `conflict` fragment。
 - runtime probe `cross_document_environment_scoped_ownership_identity_probe_en`、`cross_document_version_scoped_ownership_identity_probe_en` 与 `cross_document_platform_scoped_ownership_identity_probe_en` 现在由 `Knowledge_Base/ragconditionownercrossscope` 支撑，验证完整文档 cross-document conflict scanner 会在两个 scoped documents 之间保留 environment / version / platform 限定 owner facts，而不是误产出 `conflict` fragment。
 - runtime probe `conflicting_endpoint_evidence_probe_en` 与 `environment_scoped_endpoint_probe_en` 现在由 `Knowledge_Base/ragendpointconflict` 和 `Knowledge_Base/ragendpointqualifier` 支撑，把受控语义冲突覆盖扩展到显式 endpoint/url/uri/route facts。同一 section 中 `/api/v1/hooks` 与 `/api/v2/hooks` 会产出 `conflict` fragment 并在 `context_assembly` 下降级；staging 与 production endpoint routes 会保留为 environment-qualified evidence，不会误产出 conflict。`/v1/` 这类 endpoint path segment 会被视为 route value，而不是 version scope。
+- runtime probe `conflicting_dependency_evidence_probe_en` 与 `environment_scoped_dependency_probe_en` 现在由 `Knowledge_Base/ragdependencyconflict` 和 `Knowledge_Base/ragdependencyqualifier` 支撑，把受控语义冲突覆盖扩展到显式 dependency/package/provider/driver/runtime/library/module/plugin/adapter facts。同一 section 中 SQLite 与 PostgreSQL storage dependency 会产出 `conflict` fragment 并在 `context_assembly` 下降级；staging 与 production dependency records 会保留为 environment-qualified evidence，不会误产出 conflict。
 
 后续推进：