New web interface, move llm engine to separate process

README.md

@@ -311,18 +311,51 @@ Or xml comments used for inline reasoning are not saved after parsing.
 
 LLM engine subprocesses receive input as XML documents containing paths to required files and the context.
 
-**Example input to LLM engine subprocess:**
+##### Example interaction with the LLM engine subprocess:
+
+**Core -> LLM engine**
+
 ```xml
-<input>
-  <system_prompt_path>/root/sia/system_prompt.md</system_prompt_path>
-  <action_schema_path>/root/sia/action_schema.xsd</action_schema_path>
-  <context>
-    <context time="2024-10-18T12:00:00Z" memory_used="9556302234" memory_total="17179869184">
-      <!-- Working memory entries -->
-    </context>
-  </context>
-  <prefix><!-- Optional existing text to continue --></prefix>
-</input>
+<token_limit/>
+```
+
+**LLM engine -> Core**
+
+```
+1024\u0004
+```
+
+**Core -> LLM engine**
+
+```xml
+<token_count>
+  <schema>/root/sia/action_schema.xsd</schema>
+  <system><![CDATA[...]]></system>
+  <context><![CDATA[...]]></context>
+</token_count>
+```
+
+**LLM engine -> Core**
+
+```
+405\u0004
+```
+
+**Core -> LLM engine**
+
+```xml
+<infer_xml>
+  <schema>/root/sia/action_schema.xsd</schema>
+  <system><![CDATA[...]]></system>
+  <context><![CDATA[...]]></context>
+  <prefix><![CDATA[...]]></prefix>
+</infer_xml>
+```
+
+**LLM engine -> Core**
+
+```xml
+<reasoning>...</reasoning>
 ```
 
 Though the LLM can output any text, the goal is to output valid xml.
@@ -336,13 +369,6 @@ This character was chosen because:
 - It's a single byte, making it efficient to process
 - It's standard across all platforms
 
-**Example output from LLM engine subprocess:**
-```
-<reasoning>
-I should check the current state of the system and see if there are any pending tasks.
-</reasoning>\u0004
-```
-
 The communication protocol between the SIA agent and LLM engine subprocesses has been designed with simplicity as the primary goal.
 Opting for a minimal approach that:
 
@@ -453,16 +479,19 @@ classDiagram
         -monitor_loop() void
     }
 
-    class LLMEngine {
-        +LLMEngine(executable_path str)
-        +infer(system_prompt str, main_context str, prefix str) Iterator~str~
+    class LlmEngine {
+        +LlmEngine(executable_path str, action_schema_path str)
+        +infer(system_prompt str, main_context ET, prefix str) Iterator~str~
+        +token_count(system_prompt str, main_context ET, prefix str) int
+        +token_limit() int
+        +restart()
     }
 
     class BaseAgent {
         <<abstract>>
         -working_memory: WorkingMemory
         -metrics: SystemMetrics
-        -llm: LLMEngine
+        -llm: LlmEngine
         -parser: ResponseParser
         -validator: XMLValidator
         -action_schema: str
@@ -522,7 +551,7 @@ classDiagram
     }
 
     SystemMetrics "1" --* "1" BaseAgent
-    LLMEngine "1" --* "1" BaseAgent
+    LlmEngine "1" --* "1" BaseAgent
     XMLValidator "1" --* "1" BaseAgent
     BaseAgent "1" *-- "1" IOBuffer
     BaseAgent "1" *-- "1" WorkingMemory
@@ -560,7 +589,7 @@ classDiagram
         <<abstract>>
         -working_memory: WorkingMemory
         -metrics: SystemMetrics
-        -llm: LLMEngine
+        -llm: LlmEngine
         -parser: ResponseParser
         -validator: XMLValidator
         -action_schema: str