fix: use gemini-2.5-flash model and restore goreleaser changelog (#2)

## Summary
- Update default model from gemini-2.0-flash to gemini-2.5-flash across
flags, action, and reusable workflow
- Restore goreleaser changelog config (disable: true broke
--release-notes flag)

## Test plan
- [ ] Trigger release and verify AI-generated notes appear in release
body

Author: murilopmachado

.github/workflows/releaseforge.yml

@@ -22,7 +22,7 @@ on:
       model:
         description: "LLM model for generate"
         type: string
-        default: "gemini-2.0-flash"
+        default: "gemini-2.5-flash"
       template-name:
         description: "Built-in template name"
         type: string

.goreleaser.yml

@@ -46,7 +46,11 @@ snapshot:
   version_template: "{{ incpatch .Version }}-next"
 
 changelog:
-  disable: true
+  sort: asc
+  filters:
+    exclude:
+      - '^docs:'
+      - '^test:'
 
 release:
   github:

action.yml

@@ -24,7 +24,7 @@ inputs:
   model:
     description: "LLM model name for generate"
     required: false
-    default: "gemini-2.0-flash"
+    default: "gemini-2.5-flash"
   api-key:
     description: "API key for the LLM provider (generate command)"
     required: false

flags.go

@@ -11,8 +11,8 @@ var providerFlag = cli.StringFlag{
 
 var modelFlag = cli.StringFlag{
 	Name:   "model, m",
-	Value:  "gemini-2.0-flash",
-	Usage:  "Model name (e.g. gemini-2.0-flash, gpt-4o, claude-sonnet-4-5-20250929)",
+	Value:  "gemini-2.5-flash",
+	Usage:  "Model name (e.g. gemini-2.5-flash, gpt-4o, claude-sonnet-4-5-20250929)",
 	EnvVar: "RELEASEFORGE_MODEL",
 }