diff --git a/packages/agent/CHANGELOG.md b/packages/agent/CHANGELOG.md
index dfd1dd9..3dffbed 100644
--- a/packages/agent/CHANGELOG.md
+++ b/packages/agent/CHANGELOG.md
@@ -1,3 +1,14 @@
+# [mycoder-agent-v1.7.0](https://github.com/drivecore/mycoder/compare/mycoder-agent-v1.6.0...mycoder-agent-v1.7.0) (2025-03-21)
+
+### Bug Fixes
+
+- Fix TypeScript errors and tests for message compaction feature ([d4f1fb5](https://github.com/drivecore/mycoder/commit/d4f1fb5d197e623bf98f2221352f9132dcb3e5de))
+
+### Features
+
+- Add automatic compaction of historical messages for agents ([a5caf46](https://github.com/drivecore/mycoder/commit/a5caf464a0a8dca925c7b46023ebde4727e211f8)), closes [#338](https://github.com/drivecore/mycoder/issues/338)
+- Improve message compaction with proactive suggestions ([6276bc0](https://github.com/drivecore/mycoder/commit/6276bc0bc5fa27c4f1e9be61ff4375690ad04c62))
+
 # [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
diff --git a/packages/agent/package.json b/packages/agent/package.json
index 7af27a4..2a35330 100644
--- a/packages/agent/package.json
+++ b/packages/agent/package.json
@@ -1,6 +1,6 @@
 {
   "name": "mycoder-agent",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "description": "Agent module for mycoder - an AI-powered software development assistant",
   "type": "module",
   "main": "dist/index.js",
diff --git a/packages/agent/src/core/llm/providers/anthropic.ts b/packages/agent/src/core/llm/providers/anthropic.ts
index 95a0458..9d191c1 100644
--- a/packages/agent/src/core/llm/providers/anthropic.ts
+++ b/packages/agent/src/core/llm/providers/anthropic.ts
@@ -12,8 +12,9 @@ import {
   ProviderOptions,
 } from '../types.js';
 
-// Define model context window sizes for Anthropic models
-const ANTHROPIC_MODEL_LIMITS: Record<string, number> = {
+// Fallback model context window sizes for Anthropic models
+// Used only if models.list() call fails or returns incomplete data
+const ANTHROPIC_MODEL_LIMITS_FALLBACK: Record<string, number> = {
   default: 200000,
   'claude-3-7-sonnet-20250219': 200000,
   'claude-3-7-sonnet-latest': 200000,
@@ -96,7 +97,14 @@ function addCacheControlToMessages(
   });
 }
 
-function tokenUsageFromMessage(message: Anthropic.Message, model: string) {
+// Cache for model context window sizes
+const modelContextWindowCache: Record<string, number> = {};
+
+function tokenUsageFromMessage(
+  message: Anthropic.Message,
+  model: string,
+  contextWindow?: number,
+) {
   const usage = new TokenUsage();
   usage.input = message.usage.input_tokens;
   usage.cacheWrites = message.usage.cache_creation_input_tokens ?? 0;
@@ -104,7 +112,12 @@ function tokenUsageFromMessage(message: Anthropic.Message, model: string) {
   usage.output = message.usage.output_tokens;
 
   const totalTokens = usage.input + usage.output;
-  const maxTokens = ANTHROPIC_MODEL_LIMITS[model] || 100000; // Default fallback
+  // Use provided context window, or fallback to cached value, or use hardcoded fallback
+  const maxTokens =
+    contextWindow ||
+    modelContextWindowCache[model] ||
+    ANTHROPIC_MODEL_LIMITS_FALLBACK[model] ||
+    ANTHROPIC_MODEL_LIMITS_FALLBACK.default;
 
   return {
     usage,
@@ -123,6 +136,7 @@ export class AnthropicProvider implements LLMProvider {
   private client: Anthropic;
   private apiKey: string;
   private baseUrl?: string;
+  private modelContextWindow?: number;
 
   constructor(model: string, options: AnthropicOptions = {}) {
     this.model = model;
@@ -138,6 +152,72 @@ export class AnthropicProvider implements LLMProvider {
       apiKey: this.apiKey,
       ...(this.baseUrl && { baseURL: this.baseUrl }),
     });
+
+    // Initialize model context window detection
+    // This is async but we don't need to await it here
+    // If it fails, we'll fall back to hardcoded limits
+    this.initializeModelContextWindow().catch((error) => {
+      console.warn(
+        `Failed to initialize model context window: ${error.message}`,
+      );
+    });
+  }
+
+  /**
+   * Fetches the model context window size from the Anthropic API
+   *
+   * @returns The context window size if successfully fetched, otherwise undefined
+   */
+  private async initializeModelContextWindow(): Promise<number | undefined> {
+    try {
+      const response = await this.client.models.list();
+
+      if (!response?.data || !Array.isArray(response.data)) {
+        console.warn(`Invalid response from models.list() for ${this.model}`);
+        return undefined;
+      }
+
+      // Try to find the exact model
+      let model = response.data.find((m) => m.id === this.model);
+
+      // If not found, try to find a model that starts with the same name
+      // This helps with model aliases like 'claude-3-sonnet-latest'
+      if (!model) {
+        // Split by '-latest' or '-20' to get the base model name
+        const parts = this.model.split('-latest');
+        const modelPrefix =
+          parts.length > 1 ? parts[0] : this.model.split('-20')[0];
+
+        if (modelPrefix) {
+          model = response.data.find((m) => m.id.startsWith(modelPrefix));
+
+          if (model) {
+            console.info(
+              `Model ${this.model} not found, using ${model.id} for context window size`,
+            );
+          }
+        }
+      }
+
+      // Using type assertion to access context_window property
+      // The Anthropic API returns context_window but it may not be in the TypeScript definitions
+      if (model && 'context_window' in model) {
+        const contextWindow = (model as any).context_window;
+        this.modelContextWindow = contextWindow;
+        // Cache the result for future use
+        modelContextWindowCache[this.model] = contextWindow;
+        return contextWindow;
+      } else {
+        console.warn(`No context window information found for ${this.model}`);
+        return undefined;
+      }
+    } catch (error) {
+      console.warn(
+        `Failed to fetch model context window for ${this.model}: ${(error as Error).message}`,
+      );
+      // Will fall back to hardcoded limits
+      return undefined;
+    }
   }
 
   /**
@@ -198,7 +278,11 @@ export class AnthropicProvider implements LLMProvider {
           };
         });
 
-      const tokenInfo = tokenUsageFromMessage(response, this.model);
+      const tokenInfo = tokenUsageFromMessage(
+        response,
+        this.model,
+        this.modelContextWindow,
+      );
 
       return {
         text: content,