Skip tool guidance, custom prompt, and Agent Skills for tool-incapable models

effectiveSystemPrompt now gates tool-usage guidelines, the user's
custom system prompt, and active Agent Skills behind whether the
selected model actually supports tools (ModelInfo.capabilities.tools).
All three assume tool/file/web access and can easily blow past small
context windows.

Confirmed live against Apple Intelligence: the default system prompt
dropped from 16,377 to ~250 tokens (well under the 4K on-device
limit), fully resolving the context-exceeded error from the initial
Phase 1 rollout. Verified end-to-end with a real successful generation
in the app after the fix.

Also: .gitignore now excludes *.profraw (stray code-coverage artifact
picked up while testing).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

.gitignore

@@ -31,6 +31,9 @@ DerivedData/
 *.dSYM.zip
 *.dSYM
 
+## Code coverage
+*.profraw
+
 ## Playgrounds
 timeline.xctimeline
 playground.xcworkspace

oAI/ViewModels/ChatViewModel.swift

@@ -151,8 +151,14 @@ Don't narrate future actions ("Let me...") - just use the tools.
 
     /// Builds the complete system prompt by combining default + conditional sections + custom
     private var effectiveSystemPrompt: String {
+        // Tool guidance, the user's custom prompt, and Agent Skills all generally assume tool
+        // access and can easily blow past small context windows (e.g. Apple's on-device 4K
+        // limit) — skip all three for tool-incapable models.
+        let modelSupportsTools = selectedModel?.capabilities.tools ?? true
+
         // Check if user wants to replace the default prompt entirely (BYOP mode)
-        if settings.customPromptMode == .replace,
+        if modelSupportsTools,
+           settings.customPromptMode == .replace,
            let customPrompt = settings.systemPrompt,
            !customPrompt.isEmpty {
             // BYOP: Use ONLY the custom prompt
@@ -170,18 +176,20 @@ Don't narrate future actions ("Let me...") - just use the tools.
         }
 
         // Add tool-specific guidelines if MCP is enabled (tools are available)
-        if mcpEnabled {
+        if mcpEnabled && modelSupportsTools {
             prompt += toolUsageGuidelines
         }
 
         // Append custom prompt if in append mode and custom prompt exists
-        if settings.customPromptMode == .append,
+        if modelSupportsTools,
+           settings.customPromptMode == .append,
            let customPrompt = settings.systemPrompt,
            !customPrompt.isEmpty {
             prompt += "\n\n---\n\nAdditional Instructions:\n" + customPrompt
         }
 
         // Append active agent skills (SKILL.md-style behavioral instructions)
+        if modelSupportsTools {
             let activeSkills = settings.agentSkills.filter { $0.isActive }
             if !activeSkills.isEmpty {
                 prompt += "\n\n---\n\n## Installed Skills\n\nThe following skills are active. Apply them when relevant:\n\n"
@@ -197,6 +205,7 @@ Don't narrate future actions ("Let me...") - just use the tools.
                     }
                 }
             }
+        }
 
         return prompt
     }