chore(backend): remove deprecated inference engines and character agent

backend/src/inference.py

@@ -2,7 +2,6 @@ import threading
 import asyncio
 import json
 import os
-#import ollama
 import traceback
 import random
 from stream import Stream
@@ -163,16 +162,6 @@ async def chat_completion(app,
 
     if model_engine == "llama-cpp":
         result = await local_chat_completion(app, messages, model=model_name, tools=tools, opts=opts, agent_run=agent_run)
-    elif model_engine == "replicate":
-        # Clone opts to avoid mutating the caller's dict
-        opts = dict(opts)
-        if 'parameters' in db_model:
-            opts['parameters'] = db_model['parameters']
-        if 'format' in db_model:
-            opts['format'] = db_model['format']
-        result = await replicate_completion(app, messages, model=model_name, tools=tools, opts=opts, agent_run=agent_run)
-    elif model_engine == "ollama":
-        result = await ollama_chat_completion(app, messages, model=model_name, tools=tools, opts=opts, agent_run=agent_run)
     elif model_engine == "openrouter":
         result = await openrouter_chat_completion(app, messages, model=model_name, tools=tools, opts=opts, agent_run=agent_run)
     else:
@@ -256,57 +245,6 @@ async def local_chat_completion(app, messages, model, tools=[], opts={}, agent_r
         return None
     return content_stream
 
-async def ollama_list(app, messages, model, opts={}):
-    # TODO: test the output, and use this
-    return ollama.list()
-
-async def ollama_chat_completion(app, messages, model, tools=[], opts={}, agent_run=None):
-    raise Exception("ollama disabled")
-    if agent_run:
-        content_stream = agent_run.stream
-    else:
-        content_stream = Stream(app)
-
-    async def worker():
-        print("START OLLAMA INFERENCE")
-        kwargs = {
-            'model': model,
-            'messages': [msg.to_dict() for msg in messages],
-            'stream': True,
-        }
-
-        # Pass tools in Ollama format if provided
-        formatted_tools = format_tools_for_engine(tools, "ollama") if tools else None
-        if formatted_tools:
-            kwargs['tools'] = formatted_tools
-
-        try:
-            stream_response = await ollama.AsyncClient().chat(**kwargs)
-
-            async for part in stream_response:
-                if agent_run and agent_run.cancelled:
-                    print(f"Cancelling ollama inference for run {agent_run.id}")
-                    break
-                    
-                if part.message.content:
-                    content_stream.feed(part.message.content)
-        except asyncio.CancelledError:
-            print(f"Ollama task cancelled for run {agent_run.id}")
-            raise
-
-        content_stream.close()
-        print("END OLLAMA INFERENCE")
-
-    task = asyncio.create_task(worker())
-    if agent_run:
-        agent_run.task = task
-    else:
-        task.start()
-
-    if agent_run:
-        return None
-    return content_stream
-
 
 async def openrouter_chat_completion(app, messages, model, tools=[], opts={}, agent_run=None):
     if not agent_run:
@@ -437,56 +375,6 @@ async def openrouter_chat_completion(app, messages, model, tools=[], opts={}, ag
     agent_run.task = task
 
 
-async def replicate_completion(app, messages, model=None, tools=[], opts={}, agent_run=None):
-    if model is None:
-        model = Models.llama_8b
-
-    parameter_names = opts.get('parameters', {})
-
-    arguments = {}
-
-    # Build the prompt, injecting tool descriptions for models that rely on
-    # prompt-based tool usage rather than native function calling.
-    prompt_text = format_instruct(messages)
-    if tools:
-        tool_prefix = build_tool_prompt_prefix(tools)
-        if tool_prefix:
-            prompt_text = tool_prefix + "\n\n" + prompt_text
-
-    arguments[parameter_names.get('prompt', 'prompt')] = prompt_text
-    arguments[parameter_names.get('temperature', 'temperature')] = opts.get('temperature') or 0.75
-    arguments[parameter_names.get('max_tokens', 'max_tokens')] = opts.get('max_tokens', 2048)
-
-    arguments[parameter_names.get('system_prompt', 'system_prompt')] = ""
-
-    result = await replicate_base_completion(app, model, arguments, agent_run=agent_run)
-    if agent_run:
-        return None
-    return result
-
-async def replicate_base_completion(app, model, input, agent_run=None):
-    if agent_run:
-        content_stream = agent_run.stream
-    else:
-        content_stream = Stream(app)
-    thread = threading.Thread(
-        target=run_replicate_inference_loop,
-        kwargs={
-            'replicate_client': app.replicate_client,
-            'model': model,
-            'content_stream': content_stream,
-            'input': input,
-            'agent_run': agent_run
-        }
-    )
-    thread.start()
-    #response = await content_stream.content_wait()
-    #return response.lstrip()
-    if agent_run:
-        agent_run.thread = thread
-        return None
-    return content_stream
-
 async def mock_completion(app, agent_run=None):
     VERBS = ['fix','scan','sync','deploy','parse','render','cache','trace',
         'merge','purge','index','probe','flush','bind','warm','drain']
@@ -512,25 +400,3 @@ async def mock_completion(app, agent_run=None):
 
     asyncio.create_task(content_task())
     if not agent_run: return content_stream
-
-
-def run_replicate_inference_loop(replicate_client, model, input, content_stream, agent_run=None):
-    print("START INFERENCE")
-    completion = replicate_client.run(model, input=input, stream=True)
-    for event in completion:
-        if agent_run and agent_run.cancelled:
-            print(f"Cancelling replicate inference for run {agent_run.id}")
-            break
-            # TODO: does completion need explicit cancellation?
-            
-        if event:
-            content_stream.feed(str(event))
-    print("END INFERENCE")
-    content_stream.close()
-
-def format_instruct(messages):
-    prompt = "<|begin_of_text|>"
-    for message in messages:
-        prompt += f"<|start_header_id|>{message.role}<|end_header_id|>\n\n{message.content}<|eot_id|>"
-    prompt += f"<|start_header_id|>assistant<|end_header_id|>"
-    return prompt