Centralize location LLM assets

internal/modules/dnd/normalize/locations/assets.go

@@ -1,6 +0,0 @@
-package locations
-
-import "embed"
-
-//go:embed assets/prompts/*.yaml assets/prompts/*.md
-var embeddedAssets embed.FS

internal/modules/dnd/normalize/locations/assets/prompts/candidates.md

@@ -1,2 +0,0 @@
-Location candidates:
-{{ input "candidates" }}

internal/modules/dnd/normalize/locations/assets/prompts/dnd.locations.normalize.yaml

@@ -1,30 +0,0 @@
-id: dnd.locations.normalize
-version: "v1"
-default_profile: dnd-extraction
-inputs:
-  - name: candidates
-    required: true
-    content_type: application/json
-  - name: transcript
-    required: true
-    content_type: application/json
-messages:
-  - role: system
-    content_file: ./sharedassets/common-dnd-system.md
-  - role: user
-    content_file: ./task.md
-  - role: user
-    content_file: ./sharedassets/common-dnd-entity-reconciliation.md
-    cache_control:
-      type: ephemeral
-  - role: user
-    content_file: ./candidates.md
-  - role: user
-    content_file: ./sharedassets/common-dnd-transcript.md
-    cache_control:
-      type: ephemeral
-output:
-  format: json
-  validation_mode: json_schema
-  schema_path: dnd_entity_reconcile_llm.v1.json
-  repair_attempts: 0

internal/modules/dnd/normalize/locations/assets/prompts/task.md

@@ -1,8 +0,0 @@
-Review location candidates and cited transcript context. Group candidates only
-when the evidence clearly identifies one physical place.
-
-Do not group candidates solely because their names match, their evidence is
-nearby, one place is nested inside another, or their labels are generic. Keep
-parent and child places, similarly named places, and uncertain aliases
-separate. For an accepted group, select the supplied candidate with the
-clearest established display name as canonical.

internal/modules/dnd/normalize/locations/prompt_assets.go

@@ -2,8 +2,10 @@ package locations
 
 import (
 	"fmt"
+	"io/fs"
 	"sync"
 
+	rootassets "gitea.maximumdirect.net/eric/notarius/assets"
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/llm"
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/promptfs"
 	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
@@ -14,15 +16,27 @@ const promptAssetRoot = "assets/prompts"
 var promptAssetManifest = shared.PromptAssetManifest{
 	ModuleDir: PromptID,
 	ModuleFiles: []promptfs.ModulePromptFile{
-		{Name: "dnd.locations.normalize.yaml", Path: "assets/prompts/dnd.locations.normalize.yaml"},
-		{Name: "task.md", Path: "assets/prompts/task.md"},
-		{Name: "candidates.md", Path: "assets/prompts/candidates.md"},
+		{Name: "dnd.locations.normalize.yaml", Path: "prompts/dnd.locations.normalize.yaml"},
+		{Name: "task.md", Path: "prompts/task.md"},
+		{Name: "candidates.md", Path: "prompts/candidates.md"},
 	},
 	SharedFiles: []string{"common-dnd-system.md", "common-dnd-entity-reconciliation.md", "common-dnd-transcript.md"},
 }
 
+func moduleAssetFS() (fs.FS, error) {
+	assets, err := fs.Sub(rootassets.FS(), "dnd/locations/normalize")
+	if err != nil {
+		return nil, fmt.Errorf("scope location normalization assets: %w", err)
+	}
+	return assets, nil
+}
+
 func RegisterPromptAssets(registry *llm.AssetRegistry) error {
-	promptFS, err := promptAssetManifest.PromptFS(embeddedAssets)
+	assets, err := moduleAssetFS()
+	if err != nil {
+		return err
+	}
+	promptFS, err := promptAssetManifest.PromptFS(assets)
 	if err != nil {
 		return fmt.Errorf("prepare location normalization prompt assets: %w", err)
 	}
@@ -30,7 +44,14 @@ func RegisterPromptAssets(registry *llm.AssetRegistry) error {
 }
 
 func promptAssetMetadata() (string, error) {
-	promptAssetHashOnce.Do(func() { promptAssetHash, promptAssetHashErr = promptAssetManifest.Hash(embeddedAssets) })
+	promptAssetHashOnce.Do(func() {
+		assets, err := moduleAssetFS()
+		if err != nil {
+			promptAssetHashErr = err
+			return
+		}
+		promptAssetHash, promptAssetHashErr = promptAssetManifest.Hash(assets)
+	})
 	return promptAssetHash, promptAssetHashErr
 }