chore: format & lint

Author: bhouston

docs/features/message-compaction.md

@@ -7,6 +7,7 @@ When agents run for extended periods, they accumulate a large history of message
 ### 1. Token Usage Tracking
 
 The LLM abstraction now tracks and returns:
+
 - Total tokens used in the current completion request
 - Maximum allowed tokens for the model/provider
 
@@ -15,17 +16,20 @@ This information is used to monitor context window usage and trigger appropriate
 ### 2. Status Updates
 
 Agents receive status updates with information about:
+
 - Current token usage and percentage of the maximum
 - Cost so far
 - Active sub-agents and their status
 - Active shell processes and their status
 - Active browser sessions and their status
 
 Status updates are sent:
+
 1. Every 5 agent interactions (periodic updates)
 2. Whenever token usage exceeds 50% of the maximum (threshold-based updates)
 
 Example status update:
+
 ```
 --- STATUS UPDATE ---
 Token Usage: 45,235/100,000 (45%)
@@ -72,6 +76,7 @@ Agents are instructed to monitor their token usage through status updates and us
 ## Configuration
 
 The message compaction feature is enabled by default with reasonable defaults:
+
 - Status updates every 5 agent interactions
 - Recommendation to compact at 70% token usage
 - Default preservation of 10 recent messages when compacting
@@ -81,17 +86,20 @@ The message compaction feature is enabled by default with reasonable defaults:
 The system includes token limits for various models:
 
 ### Anthropic Models
+
 - claude-3-opus-20240229: 200,000 tokens
 - claude-3-sonnet-20240229: 200,000 tokens
 - claude-3-haiku-20240307: 200,000 tokens
 - claude-2.1: 100,000 tokens
 
 ### OpenAI Models
+
 - gpt-4o: 128,000 tokens
 - gpt-4-turbo: 128,000 tokens
 - gpt-3.5-turbo: 16,385 tokens
 
 ### Ollama Models
+
 - llama2: 4,096 tokens
 - mistral: 8,192 tokens
 - mixtral: 32,768 tokens
@@ -102,4 +110,4 @@ The system includes token limits for various models:
 - Maintains important context for agent operation
 - Enables longer-running agent sessions
 - Makes the system more robust for complex tasks
-- Gives agents self-awareness of resource usage
+- Gives agents self-awareness of resource usage

example-status-update.md

@@ -47,4 +47,4 @@ The agent can use the compactHistory tool like this:
 }
 ```
 
-This will summarize all but the 10 most recent messages into a single summary message, significantly reducing token usage while preserving important context.
+This will summarize all but the 10 most recent messages into a single summary message, significantly reducing token usage while preserving important context.

packages/agent/CHANGELOG.md

@@ -1,9 +1,8 @@
 # [mycoder-agent-v1.6.0](https://github.com/drivecore/mycoder/compare/mycoder-agent-v1.5.0...mycoder-agent-v1.6.0) (2025-03-21)
 
-
 ### Features
 
-* **browser:** add system browser detection for Playwright ([00bd879](https://github.com/drivecore/mycoder/commit/00bd879443c9de51c6ee5e227d4838905506382a)), closes [#333](https://github.com/drivecore/mycoder/issues/333)
+- **browser:** add system browser detection for Playwright ([00bd879](https://github.com/drivecore/mycoder/commit/00bd879443c9de51c6ee5e227d4838905506382a)), closes [#333](https://github.com/drivecore/mycoder/issues/333)
 
 # [mycoder-agent-v1.5.0](https://github.com/drivecore/mycoder/compare/mycoder-agent-v1.4.2...mycoder-agent-v1.5.0) (2025-03-20)
 

packages/agent/src/core/llm/providers/anthropic.ts

@@ -12,6 +12,21 @@ import {
   ProviderOptions,
 } from '../types.js';
 
+// Define model context window sizes for Anthropic models
+const ANTHROPIC_MODEL_LIMITS: Record<string, number> = {
+  default: 200000,
+  'claude-3-7-sonnet-20250219': 200000,
+  'claude-3-7-sonnet-latest': 200000,
+  'claude-3-5-sonnet-20241022': 200000,
+  'claude-3-5-sonnet-latest': 200000,
+  'claude-3-haiku-20240307': 200000,
+  'claude-3-opus-20240229': 200000,
+  'claude-3-sonnet-20240229': 200000,
+  'claude-2.1': 100000,
+  'claude-2.0': 100000,
+  'claude-instant-1.2': 100000,
+};
+
 /**
  * Anthropic-specific options
  */
@@ -81,28 +96,16 @@ function addCacheControlToMessages(
   });
 }
 
-// Define model context window sizes for Anthropic models
-const ANTHROPIC_MODEL_LIMITS: Record<string, number> = {
-  'claude-3-opus-20240229': 200000,
-  'claude-3-sonnet-20240229': 200000,
-  'claude-3-haiku-20240307': 200000,
-  'claude-3-7-sonnet-20250219': 200000,
-  'claude-2.1': 100000,
-  'claude-2.0': 100000,
-  'claude-instant-1.2': 100000,
-  // Add other models as needed
-};
-
 function tokenUsageFromMessage(message: Anthropic.Message, model: string) {
   const usage = new TokenUsage();
   usage.input = message.usage.input_tokens;
   usage.cacheWrites = message.usage.cache_creation_input_tokens ?? 0;
   usage.cacheReads = message.usage.cache_read_input_tokens ?? 0;
   usage.output = message.usage.output_tokens;
-  
+
   const totalTokens = usage.input + usage.output;
   const maxTokens = ANTHROPIC_MODEL_LIMITS[model] || 100000; // Default fallback
-  
+
   return {
     usage,
     totalTokens,
@@ -196,7 +199,7 @@ export class AnthropicProvider implements LLMProvider {
         });
 
       const tokenInfo = tokenUsageFromMessage(response, this.model);
-      
+
       return {
         text: content,
         toolCalls: toolCalls,

packages/agent/src/core/llm/providers/ollama.ts

@@ -13,22 +13,6 @@ import {
 
 import { TokenUsage } from '../../tokens.js';
 import { ToolCall } from '../../types.js';
-// Define model context window sizes for Ollama models
-// These are approximate and may vary based on specific model configurations
-const OLLAMA_MODEL_LIMITS: Record<string, number> = {
-  'llama2': 4096,
-  'llama2-uncensored': 4096,
-  'llama2:13b': 4096,
-  'llama2:70b': 4096,
-  'mistral': 8192,
-  'mistral:7b': 8192,
-  'mixtral': 32768,
-  'codellama': 16384,
-  'phi': 2048,
-  'phi2': 2048,
-  'openchat': 8192,
-  // Add other models as needed
-};
 import { LLMProvider } from '../provider.js';
 import {
   GenerateOptions,
@@ -38,6 +22,23 @@ import {
   FunctionDefinition,
 } from '../types.js';
 
+// Define model context window sizes for Ollama models
+// These are approximate and may vary based on specific model configurations
+const OLLAMA_MODEL_LIMITS: Record<string, number> = {
+  default: 4096,
+  llama2: 4096,
+  'llama2-uncensored': 4096,
+  'llama2:13b': 4096,
+  'llama2:70b': 4096,
+  mistral: 8192,
+  'mistral:7b': 8192,
+  mixtral: 32768,
+  codellama: 16384,
+  phi: 2048,
+  phi2: 2048,
+  openchat: 8192,
+};
+
 /**
  * Ollama-specific options
  */
@@ -130,16 +131,17 @@ export class OllamaProvider implements LLMProvider {
     const tokenUsage = new TokenUsage();
     tokenUsage.output = response.eval_count || 0;
     tokenUsage.input = response.prompt_eval_count || 0;
-    
+
     // Calculate total tokens and get max tokens for the model
     const totalTokens = tokenUsage.input + tokenUsage.output;
-    
+
     // Extract the base model name without specific parameters
     const baseModelName = this.model.split(':')[0];
     // Check if model exists in limits, otherwise use base model or default
-    const modelMaxTokens = OLLAMA_MODEL_LIMITS[this.model] || 
-                          (baseModelName ? OLLAMA_MODEL_LIMITS[baseModelName] : undefined) || 
-                          4096; // Default fallback
+    const modelMaxTokens =
+      OLLAMA_MODEL_LIMITS[this.model] ||
+      (baseModelName ? OLLAMA_MODEL_LIMITS[baseModelName] : undefined) ||
+      4096; // Default fallback
 
     return {
       text: content,

packages/agent/src/core/llm/providers/openai.ts

@@ -21,6 +21,11 @@ import type {
 
 // Define model context window sizes for OpenAI models
 const OPENAI_MODEL_LIMITS: Record<string, number> = {
+  default: 128000,
+  'o3-mini': 200000,
+  'o1-pro': 200000,
+  o1: 200000,
+  'o1-mini': 128000,
   'gpt-4o': 128000,
   'gpt-4-turbo': 128000,
   'gpt-4-0125-preview': 128000,
@@ -29,7 +34,6 @@ const OPENAI_MODEL_LIMITS: Record<string, number> = {
   'gpt-4-32k': 32768,
   'gpt-3.5-turbo': 16385,
   'gpt-3.5-turbo-16k': 16385,
-  // Add other models as needed
 };
 
 /**
@@ -129,7 +133,7 @@ export class OpenAIProvider implements LLMProvider {
       const tokenUsage = new TokenUsage();
       tokenUsage.input = response.usage?.prompt_tokens || 0;
       tokenUsage.output = response.usage?.completion_tokens || 0;
-      
+
       // Calculate total tokens and get max tokens for the model
       const totalTokens = tokenUsage.input + tokenUsage.output;
       const modelMaxTokens = OPENAI_MODEL_LIMITS[this.model] || 8192; // Default fallback
@@ -217,4 +221,4 @@ export class OpenAIProvider implements LLMProvider {
       },
     }));
   }
-}
+}

packages/agent/src/core/llm/types.ts

@@ -81,8 +81,8 @@ export interface LLMResponse {
   toolCalls: ToolCall[];
   tokenUsage: TokenUsage;
   // Add new fields for context window tracking
-  totalTokens?: number;  // Total tokens used in this request
-  maxTokens?: number;    // Maximum allowed tokens for this model
+  totalTokens?: number; // Total tokens used in this request
+  maxTokens?: number; // Maximum allowed tokens for this model
 }
 
 /**

packages/agent/src/core/toolAgent/__tests__/statusUpdates.test.ts

@@ -3,11 +3,11 @@
  */
 import { describe, expect, it, vi } from 'vitest';
 
-import { TokenTracker } from '../../tokens.js';
-import { ToolContext } from '../../types.js';
 import { AgentStatus } from '../../../tools/agent/AgentTracker.js';
-import { ShellStatus } from '../../../tools/shell/ShellTracker.js';
 import { SessionStatus } from '../../../tools/session/SessionTracker.js';
+import { ShellStatus } from '../../../tools/shell/ShellTracker.js';
+import { TokenTracker } from '../../tokens.js';
+import { ToolContext } from '../../types.js';
 import { generateStatusUpdate } from '../statusUpdates.js';
 
 describe('Status Updates', () => {
@@ -16,7 +16,7 @@ describe('Status Updates', () => {
     const totalTokens = 50000;
     const maxTokens = 100000;
     const tokenTracker = new TokenTracker('test');
-    
+
     // Mock the context
     const context = {
       agentTracker: {
@@ -29,14 +29,21 @@ describe('Status Updates', () => {
         getSessionsByStatus: vi.fn().mockReturnValue([]),
       },
     } as unknown as ToolContext;
-    
+
     // Execute
-    const statusMessage = generateStatusUpdate(totalTokens, maxTokens, tokenTracker, context);
-    
+    const statusMessage = generateStatusUpdate(
+      totalTokens,
+      maxTokens,
+      tokenTracker,
+      context,
+    );
+
     // Verify
     expect(statusMessage.role).toBe('system');
     expect(statusMessage.content).toContain('--- STATUS UPDATE ---');
-    expect(statusMessage.content).toContain('Token Usage: 50,000/100,000 (50%)');
+    expect(statusMessage.content).toContain(
+      'Token Usage: 50,000/100,000 (50%)',
+    );
     expect(statusMessage.content).toContain('Active Sub-Agents: 0');
     expect(statusMessage.content).toContain('Active Shell Processes: 0');
     expect(statusMessage.content).toContain('Active Browser Sessions: 0');
@@ -47,13 +54,13 @@ describe('Status Updates', () => {
     // With 50% usage, it should now show the high usage warning
     expect(statusMessage.content).toContain('Your token usage is high');
   });
-  
+
   it('should include active agents, shells, and sessions', () => {
     // Setup
     const totalTokens = 70000;
     const maxTokens = 100000;
     const tokenTracker = new TokenTracker('test');
-    
+
     // Mock the context with active agents, shells, and sessions
     const context = {
       agentTracker: {
@@ -64,29 +71,36 @@ describe('Status Updates', () => {
       },
       shellTracker: {
         getShells: vi.fn().mockReturnValue([
-          { 
-            id: 'shell1', 
-            status: ShellStatus.RUNNING, 
-            metadata: { command: 'npm test' } 
+          {
+            id: 'shell1',
+            status: ShellStatus.RUNNING,
+            metadata: { command: 'npm test' },
           },
         ]),
       },
       browserTracker: {
         getSessionsByStatus: vi.fn().mockReturnValue([
-          { 
-            id: 'session1', 
-            status: SessionStatus.RUNNING, 
-            metadata: { url: 'https://example.com' } 
+          {
+            id: 'session1',
+            status: SessionStatus.RUNNING,
+            metadata: { url: 'https://example.com' },
           },
         ]),
       },
     } as unknown as ToolContext;
-    
+
     // Execute
-    const statusMessage = generateStatusUpdate(totalTokens, maxTokens, tokenTracker, context);
-    
+    const statusMessage = generateStatusUpdate(
+      totalTokens,
+      maxTokens,
+      tokenTracker,
+      context,
+    );
+
     // Verify
-    expect(statusMessage.content).toContain('Token Usage: 70,000/100,000 (70%)');
+    expect(statusMessage.content).toContain(
+      'Token Usage: 70,000/100,000 (70%)',
+    );
     expect(statusMessage.content).toContain('Your token usage is high (70%)');
     expect(statusMessage.content).toContain('recommended to use');
     expect(statusMessage.content).toContain('Active Sub-Agents: 2');
@@ -97,4 +111,4 @@ describe('Status Updates', () => {
     expect(statusMessage.content).toContain('Active Browser Sessions: 1');
     expect(statusMessage.content).toContain('- session1: https://example.com');
   });
-});
+});