Merge pull request '[loop-cycle-11] fix: enrich self-knowledge with architecture map and self-modification (#81, #86)' (#110) from fix/self-knowledge-depth into main

src/timmy/prompts.py

@@ -34,11 +34,13 @@ Rules:
 - You are running in session "{session_id}".
 
 SELF-KNOWLEDGE:
-YOUR SOURCE CODE (src/timmy/): agent.py, agents/base.py, agents/loader.py, prompts.py, tools.py, tool_safety.py, tools_intro/, memory_system.py, semantic_memory.py, session.py, cli.py, thinking.py, agentic_loop.py, voice_loop.py, backends.py, mcp_tools.py, conversation.py. Config at src/config.py, agent YAML at config/agents.yaml.
+ARCHITECTURE: config/agents.yaml defines agents and routing patterns; agents/loader.py creates SubAgent instances from it; src/timmy/prompts.py provides system prompts (this file); src/timmy/tools.py registers available tools.
 
 YOUR CURRENT CAPABILITIES: Read/write files, execute shell/python, calculator, three-tier memory, system introspection, MCP Gitea integration, voice interface.
 
-YOUR KNOWN LIMITATIONS: Cannot run tests autonomously, cannot delegate to other agents, cannot search past sessions, Ollama may contend for GPU, cannot modify own source code, small 4K context window.
+SELF-MODIFICATION: You CAN propose changes to your own config and code. Edit config/agents.yaml to add/modify agents or routing. Edit src/timmy/prompts.py to change prompts. Always explain proposed changes before making them; tell the user to restart after config changes.
+
+YOUR KNOWN LIMITATIONS: Cannot run tests autonomously, cannot delegate to other agents, cannot search past sessions, Ollama may contend for GPU, small 4K context window.
 """
 
 # ---------------------------------------------------------------------------
@@ -90,25 +92,14 @@ IDENTITY:
 - You are running in session "{session_id}". Session types: "cli" = terminal user, "dashboard" = web UI, "loop" = dev loop automation, other = custom context.
 
 SELF-KNOWLEDGE:
-YOUR SOURCE CODE (src/timmy/):
-- agent.py: Main agent creation and model warmup
-- agents/base.py: SubAgent base class for the agent swarm
-- agents/loader.py: YAML-driven agent loading from config/agents.yaml
-- prompts.py: System prompts (this file)
-- tools.py: Tool registration (file, shell, python, calculator, etc.)
-- tool_safety.py: Safety classification (SAFE vs DANGEROUS tools)
-- tools_intro/__init__.py: System introspection (get_system_info, check_ollama_health)
-- memory_system.py: Three-tier memory (hot MEMORY.md, vault, semantic search)
-- semantic_memory.py: Embedding-based memory search
-- session.py: Session management and fact extraction
-- cli.py: CLI interface (timmy chat, timmy route, timmy voice)
-- thinking.py: Reasoning and thinking engine
-- agentic_loop.py: Multi-step task execution
-- voice_loop.py: Sovereign voice interface (local Whisper + Piper + Ollama)
-- backends.py: Model backend abstraction (Ollama, AirLLM, Grok)
-- mcp_tools.py: MCP protocol tool integration
-- conversation.py: Conversation history tracking
-- config is at src/config.py, agent YAML configs at config/agents.yaml
+ARCHITECTURE MAP:
+- Config layer: config/agents.yaml (agent definitions, routing patterns), src/config.py (settings)
+- Agent layer: agents/loader.py reads YAML → creates SubAgent instances via agents/base.py
+- Prompt layer: prompts.py provides system prompts, get_system_prompt() selects lite vs full
+- Tool layer: tools.py registers tool functions, tool_safety.py classifies them
+- Memory layer: memory_system.py (hot+vault+semantic), semantic_memory.py (embeddings)
+- Interface layer: cli.py, session.py (dashboard), voice_loop.py
+- Routing: pattern-based in agents.yaml, first match wins, fallback to orchestrator
 
 YOUR CURRENT CAPABILITIES:
 - Read and write files on the local filesystem
@@ -121,12 +112,19 @@ YOUR CURRENT CAPABILITIES:
 - Voice interface (local Whisper STT + Piper TTS)
 - Thinking/reasoning engine for complex problems
 
+SELF-MODIFICATION:
+You can read and modify your own configuration and code using your file tools.
+- To add a new agent: edit config/agents.yaml (add agent block + routing patterns), restart.
+- To change your own prompt: edit src/timmy/prompts.py.
+- To add a tool: implement in tools.py, register in agents.yaml.
+- Always explain proposed changes to the user before making them.
+- After modifying config, tell the user to restart for changes to take effect.
+
 YOUR KNOWN LIMITATIONS (be honest about these when asked):
 - Cannot run your own test suite autonomously
 - Cannot delegate coding tasks to other agents (like Kimi)
 - Cannot reflect on or search your own past behavior/sessions
 - Ollama inference may contend with other processes sharing the GPU
-- Cannot modify your own source code or configuration
 - Cannot analyze Bitcoin transactions locally (no local indexer yet)
 - Small context window (4096 tokens) limits complex reasoning
 - You are a language model — you confabulate. When unsure, say so.

tests/timmy/test_self_awareness.py

@@ -21,10 +21,10 @@ class TestSelfKnowledgeInPrompts:
         with patch("config.settings", mock_settings):
             yield mock_settings
 
-    def test_full_prompt_contains_source_code_header(self, mock_settings):
-        """Full prompt should contain 'YOUR SOURCE CODE' section."""
+    def test_full_prompt_contains_architecture_header(self, mock_settings):
+        """Full prompt should contain 'ARCHITECTURE MAP' section."""
         prompt = get_system_prompt(tools_enabled=True)
-        assert "YOUR SOURCE CODE" in prompt
+        assert "ARCHITECTURE MAP" in prompt
 
     def test_full_prompt_contains_tool_safety_reference(self, mock_settings):
         """Full prompt should mention tool_safety.py specifically."""
@@ -41,10 +41,10 @@ class TestSelfKnowledgeInPrompts:
         prompt = get_system_prompt(tools_enabled=True)
         assert "Cannot run your own test suite" in prompt
 
-    def test_lite_prompt_contains_source_code_header(self, mock_settings):
-        """Lite prompt should also contain 'YOUR SOURCE CODE' section."""
+    def test_lite_prompt_contains_architecture_header(self, mock_settings):
+        """Lite prompt should contain 'ARCHITECTURE' section."""
         prompt = get_system_prompt(tools_enabled=False)
-        assert "YOUR SOURCE CODE" in prompt
+        assert "ARCHITECTURE" in prompt
 
     def test_lite_prompt_contains_known_limitations(self, mock_settings):
         """Lite prompt should also contain 'KNOWN LIMITATIONS' section."""
@@ -62,15 +62,27 @@ class TestSelfKnowledgeInPrompts:
             f"full prompt ({len(full_prompt)} chars)"
         )
 
-    def test_full_prompt_contains_codebase_structure(self, mock_settings):
-        """Full prompt should contain detailed codebase structure."""
+    def test_full_prompt_contains_architecture_layers(self, mock_settings):
+        """Full prompt should describe architecture layers."""
         prompt = get_system_prompt(tools_enabled=True)
 
-        # Should list key modules
-        assert "agent.py" in prompt
-        assert "memory_system.py" in prompt
-        assert "cli.py" in prompt
-        assert "backends.py" in prompt
+        # Should describe key architectural layers
+        assert "Config layer" in prompt
+        assert "Agent layer" in prompt
+        assert "Memory layer" in prompt
+        assert "agents.yaml" in prompt
+
+    def test_full_prompt_contains_self_modification(self, mock_settings):
+        """Full prompt should describe self-modification pathway."""
+        prompt = get_system_prompt(tools_enabled=True)
+        assert "SELF-MODIFICATION" in prompt
+        assert "agents.yaml" in prompt
+        assert "explain proposed changes" in prompt
+
+    def test_lite_prompt_contains_self_modification(self, mock_settings):
+        """Lite prompt should mention self-modification ability."""
+        prompt = get_system_prompt(tools_enabled=False)
+        assert "SELF-MODIFICATION" in prompt
 
     def test_full_prompt_contains_capabilities(self, mock_settings):
         """Full prompt should list current capabilities."""
@@ -82,6 +94,6 @@ class TestSelfKnowledgeInPrompts:
         prompt = get_system_prompt(tools_enabled=False)
 
         # Should have the key sections but in condensed form
-        assert "YOUR SOURCE CODE" in prompt
+        assert "ARCHITECTURE" in prompt
         assert "YOUR CURRENT CAPABILITIES" in prompt
         assert "YOUR KNOWN LIMITATIONS" in prompt