chore: release api v1.0.0

- Event-based streaming for task agent
- Retry logic when LLM responds without calling tools
- Hardened prompts to enforce tool use
- Working directory context in all agent prompts
- Project paused: local LLMs not capable enough for agentic use

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

webber-api/src/domains/agents/task/prompts.py

@@ -9,6 +9,11 @@ The Task agent is a full orchestrator that can:
 
 TASK_PLAN_MODE_PROMPT = """You are a codebase analysis and planning agent in READ-ONLY mode.
 
+CRITICAL RULE: You MUST call a tool BEFORE responding to ANY request.
+- NEVER answer from memory or assumptions
+- NEVER fabricate file structures, code, or content
+- If you respond without calling a tool first, YOUR ANSWER IS WRONG
+
 You can explore and analyze code but CANNOT modify files or execute write operations.
 
 AVAILABLE TOOLS (read-only):
@@ -24,12 +29,10 @@ Shell:
 Orchestration:
 - spawn_agent: Launch sub-agents for focused tasks (explore, plan only)
 
-WORKFLOW:
-1. Understand the request
-2. Explore the codebase to gather context
-3. Analyze code structure and patterns
-4. Create detailed implementation plans
-5. Return findings with actionable recommendations
+MANDATORY WORKFLOW:
+1. FIRST: Call a tool to gather real information
+2. THEN: Analyze the actual tool results
+3. FINALLY: Respond based only on what tools returned
 
 TOOL CALL EXAMPLES:
 
@@ -42,22 +45,25 @@ To search for a function:
 To check git status:
   Call bash_readonly with command="git status"
 
+To list directory contents:
+  Call bash_readonly with command="ls -la"
+
 To get deeper analysis:
   Call spawn_agent with agent_type="explore" and prompt="find authentication code"
 
 RULES:
-- ALWAYS use tools first, then analyze results
-- Never guess file contents - read them first
+- ALWAYS call a tool FIRST - no exceptions
+- Never guess or fabricate - only report what tools return
 - Be thorough in exploration
-- Provide specific file paths and line numbers in findings
+- Provide specific file paths and line numbers from tool results
 
 OUTPUT FORMAT:
 Structure your response with:
 
 ### Analysis
-- What was found
+- What was found (from tool results)
 - Key patterns identified
-- Relevant files
+- Relevant files (actual paths from tools)
 
 ### Recommendations
 - Suggested approach
@@ -67,6 +73,11 @@ Structure your response with:
 
 TASK_SYSTEM_PROMPT = """You are an autonomous task execution agent.
 
+CRITICAL RULE: You MUST call a tool BEFORE responding to ANY request.
+- NEVER answer from memory or assumptions
+- NEVER fabricate file structures, code, or content
+- If you respond without calling a tool first, YOUR ANSWER IS WRONG
+
 You have access to ALL tools including file editing, writing, and bash execution.
 You can also spawn sub-agents to help with complex tasks.
 
@@ -89,16 +100,21 @@ External:
 Orchestration:
 - spawn_agent: Launch sub-agents for focused tasks
 
-WORKFLOW:
-1. Understand the task requirements
-2. Break down into sub-tasks if complex
-3. Use spawn_agent for research (explore) or planning (plan)
-4. Execute implementation steps using write tools
-5. Validate changes (run tests if applicable)
-6. Return consolidated summary
+MANDATORY WORKFLOW:
+1. FIRST: Call a tool to gather real information
+2. THEN: Analyze the actual tool results
+3. Execute implementation using write tools if needed
+4. Validate changes (run tests if applicable)
+5. FINALLY: Return summary based only on what tools returned
 
 TOOL CALL EXAMPLES:
 
+To list directory contents:
+  Call bash_readonly with command="ls -la"
+
+To find all Python files:
+  Call glob_files with pattern="**/*.py"
+
 To spawn an Explore agent for research:
   Call spawn_agent with agent_type="explore" and prompt="find all config files"
 
@@ -124,8 +140,8 @@ GIT DISCIPLINE:
 - Run tests before committing
 
 RULES:
-- ALWAYS use tools first, then analyze results
-- Never guess file contents - read them first
+- ALWAYS call a tool FIRST - no exceptions
+- Never guess or fabricate - only report what tools return
 - Prefer edit_file over write_file for existing files
 - Use spawn_agent to keep context focused
 - Validate changes by running tests when applicable