fix(ingest): attribute historic-sql evidence writes in bundle report (#220)

The emit_historic_sql_evidence tool took rawPath as LLM-supplied input,
so projection actions frequently lacked defensible raw paths and every
row in bundle_ingest_reports fell through as actionType: 'skipped' with
null artifact metadata, hiding the wiki pages and SL merges the run had
actually produced (KLO-698).

The tool now reads the work unit's rawFiles from session.allowedRawPaths
and stores them on the evidence envelope; the projection emits actions
with those paths, and stale/archive actions are anchored to manifest.json
so they also surface as non-skipped provenance rows.

packages/cli/src/context/ingest/adapters/historic-sql/chunk-unified.ts

@@ -60,7 +60,7 @@ export async function chunkHistoricSqlUnifiedStagedDir(stagedDir: string, diffSe
       dependencyPaths: ['manifest.json'],
       peerFileIndex: files.filter((file) => file !== path && file !== 'manifest.json').sort(),
       notes:
-        `Use historic_sql_patterns. Read ${path} and emit pattern objects with emit_historic_sql_evidence using rawPath "${path}". Do not call wiki_write or sl_write_source.`,
+        `Use historic_sql_patterns. Read ${path} and emit pattern objects with emit_historic_sql_evidence. Do not call wiki_write or sl_write_source.`,
     });
   }
 

packages/cli/src/context/ingest/adapters/historic-sql/evidence-tool.ts

@@ -10,7 +10,6 @@ const emitHistoricSqlEvidenceInputSchema = z
   .object({
     kind: z.enum(['table_usage', 'pattern']),
     table: z.string().min(1).optional(),
-    rawPath: z.string().min(1),
     usage: tableUsageOutputSchema.optional(),
     pattern: patternOutputSchema.optional(),
   })
@@ -46,6 +45,7 @@ interface EmitHistoricSqlEvidenceToolContext {
   connectionId?: string | null;
   session?: {
     ingest?: { runId: string; sourceKey: string };
+    allowedRawPaths?: ReadonlySet<string>;
     configService?: {
       writeFile(
         path: string,
@@ -66,7 +66,7 @@ function unitKeyForEvidence(input: EmitHistoricSqlEvidenceInput): string {
   return `historic-sql-pattern-${String(input.pattern?.slug).replace(/[^a-zA-Z0-9]+/g, '-').replace(/^-+|-+$/g, '')}`;
 }
 
-function evidenceEnvelope(input: EmitHistoricSqlEvidenceInput, connectionId: string) {
+function evidenceEnvelope(input: EmitHistoricSqlEvidenceInput, connectionId: string, rawPaths: string[]) {
   if (input.kind === 'table_usage') {
     if (!input.table || !input.usage) {
       throw new Error('Invalid historic-SQL table usage evidence input.');
@@ -75,7 +75,7 @@ function evidenceEnvelope(input: EmitHistoricSqlEvidenceInput, connectionId: str
       kind: 'table_usage' as const,
       connectionId,
       table: input.table,
-      rawPath: input.rawPath,
+      rawPaths,
       usage: input.usage,
     };
   }
@@ -85,7 +85,7 @@ function evidenceEnvelope(input: EmitHistoricSqlEvidenceInput, connectionId: str
   return {
     kind: 'pattern' as const,
     connectionId,
-    rawPath: input.rawPath,
+    rawPaths,
     pattern: input.pattern,
   };
 }
@@ -102,9 +102,13 @@ export function createEmitHistoricSqlEvidenceTool(defaultContext?: EmitHistoricS
       if (!ingest || ingest.sourceKey !== 'historic-sql' || !configService || !context?.connectionId) {
         return 'Error: emit_historic_sql_evidence is only available during historic-sql ingest.';
       }
+      const rawPaths = context.session?.allowedRawPaths ? [...context.session.allowedRawPaths].sort() : [];
+      if (rawPaths.length === 0) {
+        return 'Error: emit_historic_sql_evidence requires a WorkUnit context with at least one raw file.';
+      }
 
       const unitKey = unitKeyForEvidence(input);
-      const evidence = evidenceEnvelope(input, context.connectionId);
+      const evidence = evidenceEnvelope(input, context.connectionId, rawPaths);
       const content = serializeHistoricSqlEvidence(evidence);
       await configService.writeFile(
         historicSqlEvidencePath(ingest.runId, unitKey),

packages/cli/src/context/ingest/adapters/historic-sql/evidence.ts

@@ -14,7 +14,7 @@ export const historicSqlTableUsageEvidenceSchema = z.object({
   kind: z.literal('table_usage'),
   connectionId: z.string().min(1),
   table: z.string().min(1),
-  rawPath: z.string().min(1),
+  rawPaths: z.array(z.string().min(1)).min(1),
   usage: tableUsageOutputSchema,
 });
 
@@ -22,7 +22,7 @@ export const historicSqlTableUsageEvidenceSchema = z.object({
 export const historicSqlPatternEvidenceSchema = z.object({
   kind: z.literal('pattern'),
   connectionId: z.string().min(1),
-  rawPath: z.string().min(1),
+  rawPaths: z.array(z.string().min(1)).min(1),
   pattern: patternOutputSchema,
 });
 

packages/cli/src/context/ingest/adapters/historic-sql/projection.ts

@@ -278,7 +278,7 @@ export async function projectHistoricSqlEvidence(input: HistoricSqlProjectionInp
             key: sourceName,
             targetConnectionId: input.connectionId,
             detail: `Merged historic-SQL usage for ${matchingEvidence.table}`,
-            rawPaths: [matchingEvidence.rawPath],
+            rawPaths: matchingEvidence.rawPaths,
           });
         }
       } else if (entry.usage && !currentTables.has(tableRef)) {
@@ -298,6 +298,7 @@ export async function projectHistoricSqlEvidence(input: HistoricSqlProjectionInp
             key: sourceName,
             targetConnectionId: input.connectionId,
             detail: `Marked historic-SQL usage stale for ${tableRef}`,
+            rawPaths: ['manifest.json'],
           });
         }
       }
@@ -341,7 +342,7 @@ export async function projectHistoricSqlEvidence(input: HistoricSqlProjectionInp
       type: reusable ? 'updated' : 'created',
       key,
       detail: `Projected historic-SQL pattern ${pattern.pattern.title}`,
-      rawPaths: [pattern.rawPath],
+      rawPaths: pattern.rawPaths,
     });
   }
 
@@ -361,6 +362,7 @@ export async function projectHistoricSqlEvidence(input: HistoricSqlProjectionInp
         type: 'updated',
         key: page.key,
         detail: `Archived stale historic-SQL pattern page ${page.key}`,
+        rawPaths: ['manifest.json'],
       });
       continue;
     }
@@ -377,6 +379,7 @@ export async function projectHistoricSqlEvidence(input: HistoricSqlProjectionInp
       type: 'updated',
       key: page.key,
       detail: `Marked historic-SQL pattern page ${page.key} stale`,
+      rawPaths: ['manifest.json'],
     });
   }
 

packages/cli/src/skills/historic_sql_patterns/SKILL.md

@@ -15,8 +15,7 @@ Use this skill when the WorkUnit raw file is a `patterns-input/part-0001.json` s
 3. Call `read_raw_file` for that exact raw file path.
 4. Identify recurring analytical intents that span at least two tables and have repeated usage signal.
 5. Emit one `pattern` evidence object per durable cross-table intent by calling `emit_historic_sql_evidence`.
-6. Set each evidence object's `rawPath` to the exact raw file path read in step 3.
-7. Stop after all pattern evidence has been emitted.
+6. Stop after all pattern evidence has been emitted.
 
 Every join column mentioned in pattern descriptions must be verified via
 entity_details for both sides of the join.
@@ -56,7 +55,6 @@ Each call to `emit_historic_sql_evidence` must use this shape:
 ```json
 {
   "kind": "pattern",
-  "rawPath": "patterns-input/part-0001.json",
   "pattern": {
     "slug": "order-lifecycle-analysis",
     "title": "Order Lifecycle Analysis",

packages/cli/src/skills/historic_sql_table_digest/SKILL.md

@@ -53,7 +53,6 @@ Call `emit_historic_sql_evidence` with this shape:
 {
   "kind": "table_usage",
   "table": "public.orders",
-  "rawPath": "tables/public.orders.json",
   "usage": {
     "narrative": "Orders are repeatedly queried for paid/refunded lifecycle analysis and customer-level rollups.",
     "frequencyTier": "high",