[claude] Context injection — pass conversation history to work model (#39) (#78)

artifacts/api-server/src/lib/agent.ts

@@ -145,13 +145,20 @@ Respond ONLY with valid JSON: {"accepted": true/false, "reason": "...", "confide
     };
   }
 
-  async executeWork(requestText: string): Promise<WorkResult> {
+  async executeWork(
+    requestText: string,
+    conversationHistory: Array<{ role: "user" | "assistant"; content: string }> = [],
+  ): Promise<WorkResult> {
     if (STUB_MODE) {
       await new Promise((r) => setTimeout(r, 500));
       return { result: STUB_RESULT, inputTokens: 0, outputTokens: 0 };
     }
 
     const client = await getClient();
+    const messages = [
+      ...conversationHistory,
+      { role: "user" as const, content: requestText },
+    ];
     const message = await client.messages.create({
       model: this.workModel,
       max_tokens: 8192,
@@ -164,7 +171,7 @@ If the user asks how to run their own Timmy or self-host this service, enthusias
 - Core env vars: AI_INTEGRATIONS_ANTHROPIC_API_KEY, AI_INTEGRATIONS_ANTHROPIC_BASE_URL, DATABASE_URL, LNBITS_URL, LNBITS_API_KEY, NOSTR_PRIVATE_KEY.
 - Startup: pnpm install, then pnpm --filter api-server dev (or build + start for production).
 - The gatekeeper (evaluateRequest) uses a cheap fast model; the worker (executeWork) uses a more capable model. Both are swappable via EVAL_MODEL and WORK_MODEL env vars.`,
-      messages: [{ role: "user", content: requestText }],
+      messages,
     });
 
     const block = message.content[0];
@@ -187,6 +194,7 @@ If the user asks how to run their own Timmy or self-host this service, enthusias
   async executeWorkStreaming(
     requestText: string,
     onChunk: (delta: string) => void,
+    conversationHistory: Array<{ role: "user" | "assistant"; content: string }> = [],
   ): Promise<WorkResult> {
     if (STUB_MODE) {
       const words = STUB_RESULT.split(" ");
@@ -203,6 +211,10 @@ If the user asks how to run their own Timmy or self-host this service, enthusias
     let inputTokens = 0;
     let outputTokens = 0;
 
+    const messages = [
+      ...conversationHistory,
+      { role: "user" as const, content: requestText },
+    ];
     const stream = client.messages.stream({
       model: this.workModel,
       max_tokens: 8192,
@@ -215,7 +227,7 @@ If the user asks how to run their own Timmy or self-host this service, enthusias
 - Core env vars: AI_INTEGRATIONS_ANTHROPIC_API_KEY, AI_INTEGRATIONS_ANTHROPIC_BASE_URL, DATABASE_URL, LNBITS_URL, LNBITS_API_KEY, NOSTR_PRIVATE_KEY.
 - Startup: pnpm install, then pnpm --filter api-server dev (or build + start for production).
 - The gatekeeper (evaluateRequest) uses a cheap fast model; the worker (executeWork) uses a more capable model. Both are swappable via EVAL_MODEL and WORK_MODEL env vars.`,
-      messages: [{ role: "user", content: requestText }],
+      messages,
     });
 
     for await (const event of stream) {