Update agent.py

agent.py

@@ -103,7 +103,7 @@ def gemini_transcribe_audio(file_path: str, prompt: str = "Transcribe the audio.
             {"type": "media", "data": b64, "mime_type": mime},
         ]
     )
-    resp = asyncio.run(gemini_llm.invoke([message]))
+    resp = asyncio.run(safe_invoke([message]))
     return resp.content if hasattr(resp, "content") else str(resp)
 
 # ---------------------------------------------------------------------
@@ -121,7 +121,7 @@ def describe_image(file_path: str, prompt: str = "Describe this image.") -> str:
             img,  # langchain übernimmt Encoding
         ]
     )
-    resp = asyncio.run(gemini_llm.invoke([message]))
+    resp = asyncio.run(safe_invoke([message]))
     return resp.content
 
 # ---------------------------------------------------------------------
@@ -177,37 +177,35 @@ gemini_llm = ChatGoogleGenerativeAI(
 ).bind_tools([
     fetch_gaia_file, parse_csv, parse_excel,
     gemini_transcribe_audio, describe_image, ocr_image,
-    web_search, simple_calculator,
-])
-
-LLM_SEMA = asyncio.Semaphore(3)           # 3 gleichz. Anfragen ≈ < 15/min
-
-async def safe_invoke(msgs: List[Any]):
-    async with LLM_SEMA:
-        return gemini_llm.invoke(msgs)
+    web_search, simple_calculator,] ,return_named_tools=True)
+
+LLM_SEMA = asyncio.Semaphore(2)           # 3 gleichz. Anfragen ≈ < 15/min
+
+# safe_invoke neu (ersetzt die alte Funktion)
+async def safe_invoke(msgs, tries: int = 4):
+    """Gemini-Aufruf mit Semaphor + Exponential-Back-off bei 429 / Netzfehlern."""
+    delay = 4
+    for t in range(tries):
+        async with LLM_SEMA:
+            try:
+                return await gemini_llm.ainvoke(msgs)
+            except Exception as e:
+                # nur bei Rate-Limit oder Netzwerk erneut versuchen
+                if ("429" in str(e) or "RateLimit" in str(e)) and t < tries - 1:
+                    await asyncio.sleep(delay)
+                    delay *= 2          # 4 s, 8 s, 16 s …
+                    continue
+                raise
 
 # ---------------------------------------------------------------------
 # System-Prompt
 # ---------------------------------------------------------------------
 system_prompt = SystemMessage(content="""
-You are GAIA-Assist, a precise, tool-using agent.
-
-If a question mentions an attachment:
-1. Call fetch_gaia_file(task_id)
-2. Use exactly one specialised parser tool on the returned path.
-
-Otherwise decide between web_search or simple_calculator.
-
-Format for a tool call:
-Thought: Do I need to use a tool? Yes
-Action: <tool name>
-Action Input: <JSON arguments>
-
-Format for final answer:
-Thought: Do I need to use a tool? No
-Final Answer: <your answer>
-
-Stop once you output "Final Answer:".
+You are a helpful assistant tasked with answering questions using a set of tools. 
+Now, I will ask you a question. Report your thoughts, and finish your answer with the following template: 
+FINAL ANSWER: [YOUR FINAL ANSWER]. 
+YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
+Your answer should only start with "FINAL ANSWER: ", then follows with the answer. 
 """)
 
 # ---------------------------------------------------------------------