feat: Add MaxTokens option for AI model output control

Introduce a new `MaxTokens` flag and configuration option to allow users to specify the maximum number of tokens to generate in AI model responses.

This option is integrated across:
- Anthropic: Uses `MaxTokens` for `MessageNewParams`.
- Gemini: Sets `MaxOutputTokens` in `GenerateContentConfig`.
- Ollama: Sets `num_predict` option in chat requests.
- Dryrun: Includes `MaxTokens` in the formatted output.

Update example configuration to include `maxTokens` with a descriptive comment.

Resolved test issues

Resolved test issues

Author: 2b3pro

cmd/generate_changelog/incoming/1747.txt

@@ -0,0 +1,12 @@
+### PR [#1747](https://github.com/danielmiessler/Fabric/pull/1747) by [2b3pro](https://github.com/2b3pro): feat: Add MaxTokens option for AI model output control
+
+- Feat: Add MaxTokens option for AI model output control
+Introduce a new `MaxTokens` flag and configuration option to allow users to specify the maximum number of tokens to generate in AI model responses.
+This option is integrated across:
+- Anthropic: Uses `MaxTokens` for `MessageNewParams`.
+
+- Gemini: Sets `MaxOutputTokens` in `GenerateContentConfig`.
+- Ollama: Sets `num_predict` option in chat requests.
+
+- Dryrun: Includes `MaxTokens` in the formatted output.
+Update example configuration to include `maxTokens` with a descriptive comment.

internal/cli/example.yaml

@@ -17,6 +17,9 @@ topp: 0.67
 temperature: 0.88
 seed: 42
 
+# Maximum number of tokens to generate
+maxTokens: 1000
+
 stream: true
 raw: false
 

internal/cli/flags.go

@@ -102,6 +102,7 @@ type Flags struct {
 	Notification                    bool                 `long:"notification" yaml:"notification" description:"Send desktop notification when command completes"`
 	NotificationCommand             string               `long:"notification-command" yaml:"notificationCommand" description:"Custom command to run for notifications (overrides built-in notifications)"`
 	Thinking                        domain.ThinkingLevel `long:"thinking" yaml:"thinking" description:"Set reasoning/thinking level (e.g., off, low, medium, high, or numeric tokens for Anthropic or Google Gemini)"`
+	MaxTokens                       int                  `long:"max-tokens" yaml:"maxTokens" description:"Maximum number of tokens to generate (provider-specific limits apply)"`
 	Debug                           int                  `long:"debug" description:"Set debug level (0=off, 1=basic, 2=detailed, 3=trace)" default:"0"`
 }
 
@@ -457,6 +458,7 @@ func (o *Flags) BuildChatOptions() (ret *domain.ChatOptions, err error) {
 		Raw:                 o.Raw,
 		Seed:                o.Seed,
 		Thinking:            o.Thinking,
+		MaxTokens:           o.MaxTokens,
 		ModelContextLength:  o.ModelContextLength,
 		Search:              o.Search,
 		SearchLocation:      o.SearchLocation,