@equationalapplications/core-llm-wiki 7.6.0 → 7.7.1

package/dist/{testing-d1SrpDvg.d.mts → testing-A4Sofxyo.d.mts}

@@ -277,7 +277,11 @@ interface WikiConfig {
      * Default: undefined (pure semantic when embed provided).
      */
     hybridWeight?: number;
-    /** Global prompt overrides for text generation calls (`ingestDocument`, `runLibrarian`, `runHeal`). Does not affect embedding generation. Runtime overrides on individual method calls take precedence. */
+    /**
+     * Global prompt overrides for text generation calls (`ingestDocument`, `runLibrarian`, `runHeal`). Does not affect embedding generation. Runtime overrides on individual method calls take precedence.
+     *
+     * Returned verbatim by `getInstructions` and the `wiki_get_instructions` tool (`memory:read`): never put secrets, API keys or private data here.
+     */
     prompts?: PromptOverrides;
     /**
      * When true, entry and task mutations append an event to the internal outbox table.
@@ -1051,6 +1055,43 @@ interface DraftPage {
     facts: WikiFact[];
     nextCursor: string | null;
 }
+/**
+ * `pendingSources` status (spec §8.2). `partial`: live rows exist for the ref
+ * but none carries a hash, which is the intended retry state after a partial
+ * ingest. `current` is exactly the case where `hasChanged` returns false.
+ */
+type PendingSourceStatus = 'new' | 'changed' | 'partial' | 'current';
+/** Read-only maintenance report for one entity (spec §8.1). Counts cover live rows only. */
+interface WikiLintReport {
+    /** Edges whose source or target is missing, soft-deleted, or owned by another entity. */
+    danglingEdges: number;
+    /** Live-endpoint edges whose (source type, edge type, target type) is not in the effective manifest. 0 when ontology is off or the manifest is empty. */
+    manifestViolations: number;
+    /** Live facts with `okf_type` NULL. */
+    untypedFacts: number;
+    /** Live facts with `lifecycle_status = 'draft'`. */
+    drafts: number;
+    /** Live `librarian_inferred` facts with an empty `okf_verified`. */
+    unverifiedInferred: number;
+    /** Up to 20 ids each, ascending. */
+    sample: {
+        danglingEdgeIds: string[];
+        manifestViolationEdgeIds: string[];
+    };
+}
+/**
+ * Effective system prompts (spec §8.3): defaults with `WikiConfig.prompts`
+ * overrides applied and the ontology block appended. Templates only: data
+ * placeholders such as `{{documentChunk}}` stay verbatim, and no events,
+ * chunks or facts are ever included. Overrides are returned as written, so
+ * never put secrets or private data in `WikiConfig.prompts`.
+ */
+interface WikiInstructions {
+    ingest: string;
+    librarian: string;
+    heal: string;
+    ontologyBackfill: string;
+}
 
 interface WikiOutboxEvent<T = unknown> {
     id: string;
@@ -1384,6 +1425,15 @@ declare class EntryRepository extends BaseRepository {
      * Empty input is a synchronous early return with zero SQL calls.
      */
     findLatestSourceHashes(entityId: string, sourceRefs: readonly string[], tx?: SQLiteAdapter): Promise<Map<string, string | null>>;
+    /**
+     * Per source ref, the hash of the latest live row (same ordering as
+     * {@link findLatestSourceHashes}) and whether ANY live row carries a hash.
+     * Refs with no live row are absent. Chunked under the bind-variable limit.
+     */
+    findSourceStates(entityId: string, sourceRefs: readonly string[], tx?: SQLiteAdapter): Promise<Map<string, {
+        latestHash: string | null;
+        anyHashed: boolean;
+    }>>;
     /**
      * Return the live source_refs for an entity that hold the given source_hash.
      * Used by the ingestDocument duplicate-hash guard and by hosts auditing
@@ -2086,6 +2136,13 @@ declare class PromptService {
         systemPrompt: string;
         userPrompt: string;
     };
+    /**
+     * The system prompt each writer would send, without hydrating data (spec
+     * §8.3). `buildSystemPrompt` with no variables hydrates only ontology
+     * placeholders and leaves data placeholders verbatim; heal never receives
+     * ontology context, matching `buildHealPrompt`.
+     */
+    buildInstructionTemplates(ontologyContext: OntologyPromptContext | null): WikiInstructions;
 }
 
 declare class IngestionService {
@@ -2630,6 +2687,8 @@ declare class WikiMemory {
     private promptService;
     private ontologyService;
     private graphTraversalService;
+    private lintRepo;
+    private lintService;
     private readonly okfTrustWrites;
     constructor(db: SQLiteAdapter, options: WikiOptions);
     /**
@@ -2657,6 +2716,30 @@ declare class WikiMemory {
         changed: boolean;
         duplicateOf?: string;
     }>>;
+    /**
+     * Batch pending state per source (spec §8.2). `current` exactly when
+     * `hasChanged` is false; `partial` when live rows exist but none carries a
+     * hash (a first ingest with a failed chunk, or imported rows without a
+     * hash). A failed re-ingest of an already-hashed ref reports `changed`. Validation and raw-ref echo match
+     * batched `hasChanged`. Input order and duplicates are preserved. A
+     * non-array `sources`, or an entry that is not an object (including a hole
+     * in a sparse array), throws a `TypeError` before any SQL runs.
+     */
+    pendingSources(entityId: string, sources: Array<{
+        sourceRef: string;
+        sourceHash: string;
+    }>): Promise<Array<{
+        sourceRef: string;
+        status: PendingSourceStatus;
+    }>>;
+    /** Read-only maintenance report for one entity (spec §8.1). Reports, never repairs. */
+    lint(entityId: string): Promise<WikiLintReport>;
+    /**
+     * Effective system prompts for ingest, librarian, heal and ontology backfill
+     * (spec §8.3). Backs the `wiki_get_instructions` tool. Templates only;
+     * overrides are returned verbatim, so keep secrets out of `WikiConfig.prompts`.
+     */
+    getInstructions(entityId: string): Promise<WikiInstructions>;
     /**
      * Returns the live source_refs for an entity, one row per ref, with the most
      * recently-updated live `source_hash` and a live fact count. Refs are sorted
@@ -2991,4 +3074,4 @@ declare class WikiMemory {
     setGeneratedByTask(taskId: string, entityId: string, actor: string): Promise<void>;
 }
 
-export { type WikiCheckpoint as $, type OntologyMode as A, type OntologyNodeType as B, type ChunkFailure as C, type DegradedRecord as D, type EmbedFactResult as E, type FormatContextOptions as F, type GraphNeighborhood as G, HEAL_BATCH_SIZE as H, type IngestDocumentResult as I, type OntologyPromptContext as J, type OntologyUpdates as K, type LLMProvider as L, type MemoryBundle as M, PromptService as N, ONTOLOGY_BACKFILL_BATCH_SIZE as O, type PromptOverrides as P, PrunePartialFailureError as Q, type ReadOptions as R, type SQLiteAdapter as S, type ReembedResult as T, type VectorRankerFallback as U, type VectorRanker as V, type WikiOptions as W, type VectorRankerRankArgs as X, type VectorRankerSemanticResult as Y, WikiBusyError as Z, type WikiBusyOperation as _, type MemoryDump as a, type WikiConfig as a0, type WikiDiagnostic as a1, type WikiDiagnosticCode as a2, type WikiDiagnosticDetail as a3, type WikiDiagnosticOperation as a4, type WikiDiagnosticSeverity as a5, type WikiDiagnosticTrigger as a6, WikiDraftNotFound as a7, WikiDuplicateHashError as a8, type WikiEdge as a9, type WikiEvent as aa, type WikiFact as ab, WikiGraphNodeOwnershipConflict as ac, WikiIngestEmptyError as ad, WikiInvalidReadOptions as ae, type WikiMemoryTestAccess as af, type WikiOutboxEvent as ag, WikiParseError as ah, WikiSourceRefHashCollision as ai, WikiStrictOntologyViolation as aj, type WikiTask as ak, WikiTransactionError as al, validateManifest as am, EmbeddingService as an, ImportExportService as ao, IngestionService as ap, JobManager as aq, MaintenanceService as ar, RetrievalService as as, SearchService as at, WriteService as au, type FormattedMemoryDump as b, WikiMemory as c, type ClassifierAnswer as d, type ClassifierQuestion as e, type ClassifyRequest as f, type ClassifyResponse as g, type DraftPage as h, type EmbedFailureKind as i, type EmbeddingMarkerKind as j, type EntityStatus as k, type ExtractedFact as l, type ExtractedFactEdge as m, type ExtractedFactWithOntology as n, type ExtractedTask as o, type GraphTraversalOptions as p, type GroundingConfig as q, HEAL_RECHECK_MS as r, HOOK_TIMEOUT_MARKER as s, type HealResult as t, ONTOLOGY_BACKFILL_MAX_PROMPT_CHARS as u, ONTOLOGY_BACKFILL_RECHECK_MS as v, type OntologyBackfillResult as w, type OntologyConfig as x, type OntologyEdgeType as y, type OntologyManifest as z };
+export { type WikiBusyOperation as $, type OntologyMode as A, type OntologyNodeType as B, type ChunkFailure as C, type DegradedRecord as D, type EmbedFactResult as E, type FormatContextOptions as F, type GraphNeighborhood as G, HEAL_BATCH_SIZE as H, type IngestDocumentResult as I, type OntologyPromptContext as J, type OntologyUpdates as K, type LLMProvider as L, type MemoryBundle as M, type PromptOverrides as N, ONTOLOGY_BACKFILL_BATCH_SIZE as O, type PendingSourceStatus as P, PromptService as Q, type ReadOptions as R, type SQLiteAdapter as S, PrunePartialFailureError as T, type ReembedResult as U, type VectorRanker as V, type WikiOptions as W, type VectorRankerFallback as X, type VectorRankerRankArgs as Y, type VectorRankerSemanticResult as Z, WikiBusyError as _, type MemoryDump as a, type WikiCheckpoint as a0, type WikiConfig as a1, type WikiDiagnostic as a2, type WikiDiagnosticCode as a3, type WikiDiagnosticDetail as a4, type WikiDiagnosticOperation as a5, type WikiDiagnosticSeverity as a6, type WikiDiagnosticTrigger as a7, WikiDraftNotFound as a8, WikiDuplicateHashError as a9, type WikiEdge as aa, type WikiEvent as ab, type WikiFact as ac, WikiGraphNodeOwnershipConflict as ad, WikiIngestEmptyError as ae, type WikiInstructions as af, WikiInvalidReadOptions as ag, type WikiLintReport as ah, type WikiMemoryTestAccess as ai, type WikiOutboxEvent as aj, WikiParseError as ak, WikiSourceRefHashCollision as al, WikiStrictOntologyViolation as am, type WikiTask as an, WikiTransactionError as ao, validateManifest as ap, EmbeddingService as aq, ImportExportService as ar, IngestionService as as, JobManager as at, MaintenanceService as au, RetrievalService as av, SearchService as aw, WriteService as ax, type FormattedMemoryDump as b, WikiMemory as c, type ClassifierAnswer as d, type ClassifierQuestion as e, type ClassifyRequest as f, type ClassifyResponse as g, type DraftPage as h, type EmbedFailureKind as i, type EmbeddingMarkerKind as j, type EntityStatus as k, type ExtractedFact as l, type ExtractedFactEdge as m, type ExtractedFactWithOntology as n, type ExtractedTask as o, type GraphTraversalOptions as p, type GroundingConfig as q, HEAL_RECHECK_MS as r, HOOK_TIMEOUT_MARKER as s, type HealResult as t, ONTOLOGY_BACKFILL_MAX_PROMPT_CHARS as u, ONTOLOGY_BACKFILL_RECHECK_MS as v, type OntologyBackfillResult as w, type OntologyConfig as x, type OntologyEdgeType as y, type OntologyManifest as z };

package/dist/{testing-d1SrpDvg.d.ts → testing-A4Sofxyo.d.ts}

@@ -277,7 +277,11 @@ interface WikiConfig {
      * Default: undefined (pure semantic when embed provided).
      */
     hybridWeight?: number;
-    /** Global prompt overrides for text generation calls (`ingestDocument`, `runLibrarian`, `runHeal`). Does not affect embedding generation. Runtime overrides on individual method calls take precedence. */
+    /**
+     * Global prompt overrides for text generation calls (`ingestDocument`, `runLibrarian`, `runHeal`). Does not affect embedding generation. Runtime overrides on individual method calls take precedence.
+     *
+     * Returned verbatim by `getInstructions` and the `wiki_get_instructions` tool (`memory:read`): never put secrets, API keys or private data here.
+     */
     prompts?: PromptOverrides;
     /**
      * When true, entry and task mutations append an event to the internal outbox table.
@@ -1051,6 +1055,43 @@ interface DraftPage {
     facts: WikiFact[];
     nextCursor: string | null;
 }
+/**
+ * `pendingSources` status (spec §8.2). `partial`: live rows exist for the ref
+ * but none carries a hash, which is the intended retry state after a partial
+ * ingest. `current` is exactly the case where `hasChanged` returns false.
+ */
+type PendingSourceStatus = 'new' | 'changed' | 'partial' | 'current';
+/** Read-only maintenance report for one entity (spec §8.1). Counts cover live rows only. */
+interface WikiLintReport {
+    /** Edges whose source or target is missing, soft-deleted, or owned by another entity. */
+    danglingEdges: number;
+    /** Live-endpoint edges whose (source type, edge type, target type) is not in the effective manifest. 0 when ontology is off or the manifest is empty. */
+    manifestViolations: number;
+    /** Live facts with `okf_type` NULL. */
+    untypedFacts: number;
+    /** Live facts with `lifecycle_status = 'draft'`. */
+    drafts: number;
+    /** Live `librarian_inferred` facts with an empty `okf_verified`. */
+    unverifiedInferred: number;
+    /** Up to 20 ids each, ascending. */
+    sample: {
+        danglingEdgeIds: string[];
+        manifestViolationEdgeIds: string[];
+    };
+}
+/**
+ * Effective system prompts (spec §8.3): defaults with `WikiConfig.prompts`
+ * overrides applied and the ontology block appended. Templates only: data
+ * placeholders such as `{{documentChunk}}` stay verbatim, and no events,
+ * chunks or facts are ever included. Overrides are returned as written, so
+ * never put secrets or private data in `WikiConfig.prompts`.
+ */
+interface WikiInstructions {
+    ingest: string;
+    librarian: string;
+    heal: string;
+    ontologyBackfill: string;
+}
 
 interface WikiOutboxEvent<T = unknown> {
     id: string;
@@ -1384,6 +1425,15 @@ declare class EntryRepository extends BaseRepository {
      * Empty input is a synchronous early return with zero SQL calls.
      */
     findLatestSourceHashes(entityId: string, sourceRefs: readonly string[], tx?: SQLiteAdapter): Promise<Map<string, string | null>>;
+    /**
+     * Per source ref, the hash of the latest live row (same ordering as
+     * {@link findLatestSourceHashes}) and whether ANY live row carries a hash.
+     * Refs with no live row are absent. Chunked under the bind-variable limit.
+     */
+    findSourceStates(entityId: string, sourceRefs: readonly string[], tx?: SQLiteAdapter): Promise<Map<string, {
+        latestHash: string | null;
+        anyHashed: boolean;
+    }>>;
     /**
      * Return the live source_refs for an entity that hold the given source_hash.
      * Used by the ingestDocument duplicate-hash guard and by hosts auditing
@@ -2086,6 +2136,13 @@ declare class PromptService {
         systemPrompt: string;
         userPrompt: string;
     };
+    /**
+     * The system prompt each writer would send, without hydrating data (spec
+     * §8.3). `buildSystemPrompt` with no variables hydrates only ontology
+     * placeholders and leaves data placeholders verbatim; heal never receives
+     * ontology context, matching `buildHealPrompt`.
+     */
+    buildInstructionTemplates(ontologyContext: OntologyPromptContext | null): WikiInstructions;
 }
 
 declare class IngestionService {
@@ -2630,6 +2687,8 @@ declare class WikiMemory {
     private promptService;
     private ontologyService;
     private graphTraversalService;
+    private lintRepo;
+    private lintService;
     private readonly okfTrustWrites;
     constructor(db: SQLiteAdapter, options: WikiOptions);
     /**
@@ -2657,6 +2716,30 @@ declare class WikiMemory {
         changed: boolean;
         duplicateOf?: string;
     }>>;
+    /**
+     * Batch pending state per source (spec §8.2). `current` exactly when
+     * `hasChanged` is false; `partial` when live rows exist but none carries a
+     * hash (a first ingest with a failed chunk, or imported rows without a
+     * hash). A failed re-ingest of an already-hashed ref reports `changed`. Validation and raw-ref echo match
+     * batched `hasChanged`. Input order and duplicates are preserved. A
+     * non-array `sources`, or an entry that is not an object (including a hole
+     * in a sparse array), throws a `TypeError` before any SQL runs.
+     */
+    pendingSources(entityId: string, sources: Array<{
+        sourceRef: string;
+        sourceHash: string;
+    }>): Promise<Array<{
+        sourceRef: string;
+        status: PendingSourceStatus;
+    }>>;
+    /** Read-only maintenance report for one entity (spec §8.1). Reports, never repairs. */
+    lint(entityId: string): Promise<WikiLintReport>;
+    /**
+     * Effective system prompts for ingest, librarian, heal and ontology backfill
+     * (spec §8.3). Backs the `wiki_get_instructions` tool. Templates only;
+     * overrides are returned verbatim, so keep secrets out of `WikiConfig.prompts`.
+     */
+    getInstructions(entityId: string): Promise<WikiInstructions>;
     /**
      * Returns the live source_refs for an entity, one row per ref, with the most
      * recently-updated live `source_hash` and a live fact count. Refs are sorted
@@ -2991,4 +3074,4 @@ declare class WikiMemory {
     setGeneratedByTask(taskId: string, entityId: string, actor: string): Promise<void>;
 }
 
-export { type WikiCheckpoint as $, type OntologyMode as A, type OntologyNodeType as B, type ChunkFailure as C, type DegradedRecord as D, type EmbedFactResult as E, type FormatContextOptions as F, type GraphNeighborhood as G, HEAL_BATCH_SIZE as H, type IngestDocumentResult as I, type OntologyPromptContext as J, type OntologyUpdates as K, type LLMProvider as L, type MemoryBundle as M, PromptService as N, ONTOLOGY_BACKFILL_BATCH_SIZE as O, type PromptOverrides as P, PrunePartialFailureError as Q, type ReadOptions as R, type SQLiteAdapter as S, type ReembedResult as T, type VectorRankerFallback as U, type VectorRanker as V, type WikiOptions as W, type VectorRankerRankArgs as X, type VectorRankerSemanticResult as Y, WikiBusyError as Z, type WikiBusyOperation as _, type MemoryDump as a, type WikiConfig as a0, type WikiDiagnostic as a1, type WikiDiagnosticCode as a2, type WikiDiagnosticDetail as a3, type WikiDiagnosticOperation as a4, type WikiDiagnosticSeverity as a5, type WikiDiagnosticTrigger as a6, WikiDraftNotFound as a7, WikiDuplicateHashError as a8, type WikiEdge as a9, type WikiEvent as aa, type WikiFact as ab, WikiGraphNodeOwnershipConflict as ac, WikiIngestEmptyError as ad, WikiInvalidReadOptions as ae, type WikiMemoryTestAccess as af, type WikiOutboxEvent as ag, WikiParseError as ah, WikiSourceRefHashCollision as ai, WikiStrictOntologyViolation as aj, type WikiTask as ak, WikiTransactionError as al, validateManifest as am, EmbeddingService as an, ImportExportService as ao, IngestionService as ap, JobManager as aq, MaintenanceService as ar, RetrievalService as as, SearchService as at, WriteService as au, type FormattedMemoryDump as b, WikiMemory as c, type ClassifierAnswer as d, type ClassifierQuestion as e, type ClassifyRequest as f, type ClassifyResponse as g, type DraftPage as h, type EmbedFailureKind as i, type EmbeddingMarkerKind as j, type EntityStatus as k, type ExtractedFact as l, type ExtractedFactEdge as m, type ExtractedFactWithOntology as n, type ExtractedTask as o, type GraphTraversalOptions as p, type GroundingConfig as q, HEAL_RECHECK_MS as r, HOOK_TIMEOUT_MARKER as s, type HealResult as t, ONTOLOGY_BACKFILL_MAX_PROMPT_CHARS as u, ONTOLOGY_BACKFILL_RECHECK_MS as v, type OntologyBackfillResult as w, type OntologyConfig as x, type OntologyEdgeType as y, type OntologyManifest as z };
+export { type WikiBusyOperation as $, type OntologyMode as A, type OntologyNodeType as B, type ChunkFailure as C, type DegradedRecord as D, type EmbedFactResult as E, type FormatContextOptions as F, type GraphNeighborhood as G, HEAL_BATCH_SIZE as H, type IngestDocumentResult as I, type OntologyPromptContext as J, type OntologyUpdates as K, type LLMProvider as L, type MemoryBundle as M, type PromptOverrides as N, ONTOLOGY_BACKFILL_BATCH_SIZE as O, type PendingSourceStatus as P, PromptService as Q, type ReadOptions as R, type SQLiteAdapter as S, PrunePartialFailureError as T, type ReembedResult as U, type VectorRanker as V, type WikiOptions as W, type VectorRankerFallback as X, type VectorRankerRankArgs as Y, type VectorRankerSemanticResult as Z, WikiBusyError as _, type MemoryDump as a, type WikiCheckpoint as a0, type WikiConfig as a1, type WikiDiagnostic as a2, type WikiDiagnosticCode as a3, type WikiDiagnosticDetail as a4, type WikiDiagnosticOperation as a5, type WikiDiagnosticSeverity as a6, type WikiDiagnosticTrigger as a7, WikiDraftNotFound as a8, WikiDuplicateHashError as a9, type WikiEdge as aa, type WikiEvent as ab, type WikiFact as ac, WikiGraphNodeOwnershipConflict as ad, WikiIngestEmptyError as ae, type WikiInstructions as af, WikiInvalidReadOptions as ag, type WikiLintReport as ah, type WikiMemoryTestAccess as ai, type WikiOutboxEvent as aj, WikiParseError as ak, WikiSourceRefHashCollision as al, WikiStrictOntologyViolation as am, type WikiTask as an, WikiTransactionError as ao, validateManifest as ap, EmbeddingService as aq, ImportExportService as ar, IngestionService as as, JobManager as at, MaintenanceService as au, RetrievalService as av, SearchService as aw, WriteService as ax, type FormattedMemoryDump as b, WikiMemory as c, type ClassifierAnswer as d, type ClassifierQuestion as e, type ClassifyRequest as f, type ClassifyResponse as g, type DraftPage as h, type EmbedFailureKind as i, type EmbeddingMarkerKind as j, type EntityStatus as k, type ExtractedFact as l, type ExtractedFactEdge as m, type ExtractedFactWithOntology as n, type ExtractedTask as o, type GraphTraversalOptions as p, type GroundingConfig as q, HEAL_RECHECK_MS as r, HOOK_TIMEOUT_MARKER as s, type HealResult as t, ONTOLOGY_BACKFILL_MAX_PROMPT_CHARS as u, ONTOLOGY_BACKFILL_RECHECK_MS as v, type OntologyBackfillResult as w, type OntologyConfig as x, type OntologyEdgeType as y, type OntologyManifest as z };

package/dist/testing.d.mts

@@ -1,3 +1,3 @@
-export { an as EmbeddingService, ao as ImportExportService, ap as IngestionService, aq as JobManager, aq as JobManagerType, ar as MaintenanceService, as as RetrievalService, at as SearchService, at as SearchServiceType, af as WikiMemoryTestAccess, au as WriteService } from './testing-d1SrpDvg.mjs';
+export { aq as EmbeddingService, ar as ImportExportService, as as IngestionService, at as JobManager, at as JobManagerType, au as MaintenanceService, av as RetrievalService, aw as SearchService, aw as SearchServiceType, ai as WikiMemoryTestAccess, ax as WriteService } from './testing-A4Sofxyo.mjs';
 import '@equationalapplications/core-okf';
 import 'minisearch';

package/dist/testing.d.ts

@@ -1,3 +1,3 @@
-export { an as EmbeddingService, ao as ImportExportService, ap as IngestionService, aq as JobManager, aq as JobManagerType, ar as MaintenanceService, as as RetrievalService, at as SearchService, at as SearchServiceType, af as WikiMemoryTestAccess, au as WriteService } from './testing-d1SrpDvg.js';
+export { aq as EmbeddingService, ar as ImportExportService, as as IngestionService, at as JobManager, at as JobManagerType, au as MaintenanceService, av as RetrievalService, aw as SearchService, aw as SearchServiceType, ai as WikiMemoryTestAccess, ax as WriteService } from './testing-A4Sofxyo.js';
 import '@equationalapplications/core-okf';
 import 'minisearch';

package/dist/testing.js

@@ -1774,6 +1774,21 @@ ${JSON.stringify(facts, null, 2)}`
 ${JSON.stringify(facts, null, 2)}`
     };
   }
+  /**
+   * The system prompt each writer would send, without hydrating data (spec
+   * §8.3). `buildSystemPrompt` with no variables hydrates only ontology
+   * placeholders and leaves data placeholders verbatim; heal never receives
+   * ontology context, matching `buildHealPrompt`.
+   */
+  buildInstructionTemplates(ontologyContext) {
+    const o = this.globalOverrides;
+    return {
+      ingest: this.appendGrounding(this.buildSystemPrompt(o?.ingestSystemPrompt ?? INGEST_SYSTEM_PROMPT, {}, ontologyContext), "ingest"),
+      librarian: this.appendGrounding(this.buildSystemPrompt(o?.librarianSystemPrompt ?? LIBRARIAN_SYSTEM_PROMPT, {}, ontologyContext), "librarian"),
+      heal: this.appendGrounding(o?.healSystemPrompt ?? HEAL_SYSTEM_PROMPT, "heal"),
+      ontologyBackfill: this.buildSystemPrompt(o?.ontologyBackfillSystemPrompt ?? ONTOLOGY_BACKFILL_SYSTEM_PROMPT, {}, ontologyContext)
+    };
+  }
 };
 function applyBodyTruncation(candidates, attemptLevel, bodyTruncationChars) {
   if (attemptLevel < 3) {
@@ -1956,11 +1971,16 @@ var IngestionService = class {
       let ingestedChunks = 0;
       let failedChunks = 0;
       const failures = [];
-      const seen = /* @__PURE__ */ new Set();
-      const orderedChunkFacts = [];
-      const groundingLedger = /* @__PURE__ */ new Map();
+      const winners = /* @__PURE__ */ new Map();
       const diagBuffer = new DiagnosticBuffer();
       const diagBase = { entityId, operation: "ingest", trigger: "call" };
+      const pushDeduplicated = (chunkIndex, itemIndex) => {
+        diagBuffer.push({
+          ...diagBase,
+          code: "fact_deduplicated",
+          detail: { sourceRef, chunkIndex, itemIndex, reason: "exact_title" }
+        });
+      };
       for (const [chunkIndex, slot] of chunkResults.entries()) {
         if (slot.status === "failed") {
           failedChunks++;
@@ -1971,22 +1991,32 @@ var IngestionService = class {
         for (const r of slot.rejected) {
           diagBuffer.push({ ...diagBase, code: "fact_rejected", detail: { sourceRef, chunkIndex, itemIndex: r.itemIndex, reason: r.reason } });
         }
-        const dedupedFacts = [];
         slot.facts.forEach((fact, k) => {
-          const normalizedTitle = normalizeTitleKey(fact.title);
-          if (!seen.has(normalizedTitle)) {
-            seen.add(normalizedTitle);
-            dedupedFacts.push(fact);
-            if (ingestGrounding) groundingLedger.set(fact, { verdict: slot.verdicts[k], chunkIndex, itemIndex: slot.itemIndexes[k] });
+          const key = normalizeTitleKey(fact.title);
+          const candidate = { chunkIndex, k, itemIndex: slot.itemIndexes[k], rank: slot.verdicts[k]?.status === "grounded" ? 1 : 0 };
+          const current = winners.get(key);
+          if (!current) {
+            winners.set(key, candidate);
+          } else if (candidate.rank > current.rank) {
+            pushDeduplicated(current.chunkIndex, current.itemIndex);
+            winners.set(key, candidate);
           } else {
-            diagBuffer.push({
-              ...diagBase,
-              code: "fact_deduplicated",
-              detail: { sourceRef, chunkIndex, itemIndex: slot.itemIndexes[k], reason: "exact_title" }
-            });
+            pushDeduplicated(candidate.chunkIndex, candidate.itemIndex);
           }
         });
-        orderedChunkFacts.push({ facts: dedupedFacts, ontology_updates: slot.ontology_updates });
+      }
+      const orderedChunkFacts = [];
+      const groundingLedger = /* @__PURE__ */ new Map();
+      for (const [chunkIndex, slot] of chunkResults.entries()) {
+        if (slot.status === "failed") continue;
+        const keptFacts = [];
+        slot.facts.forEach((fact, k) => {
+          const winner = winners.get(normalizeTitleKey(fact.title));
+          if (winner?.chunkIndex !== chunkIndex || winner.k !== k) return;
+          keptFacts.push(fact);
+          if (ingestGrounding) groundingLedger.set(fact, { verdict: slot.verdicts[k], chunkIndex, itemIndex: winner.itemIndex });
+        });
+        orderedChunkFacts.push({ facts: keptFacts, ontology_updates: slot.ontology_updates });
       }
       for (const reason of ["parse", "llm"]) {
         const ofReason = failures.filter((f) => f.source === reason);