# Task-Driven Workflow Tasks aren't just todos — they're the backbone of persistent LLM workflows. By creating tasks for multi-step work, you ensure continuity across sessions and provide audit trails for what was done. ## Why Task-Driven? Without tasks: - LLM starts each session unsure what to do - Multi-step work is forgotten mid-execution - No record of what's been done With tasks: - LLM resumes in-progress tasks immediately - Multi-step work survives across sessions - Built-in audit trail of all work ## The Pattern ``` 1. At session start: check in_progress tasks 2. If tasks exist: resume them 3. If no tasks: create new tasks for current work 4. Update task status as you progress 5. Mark done when complete ``` ## Implementation ### Step 1: Create a task for multi-step work ```python def start_workflow(title, steps): """Create a task for multi-step work.""" task_id = create_task( title=title, description=f"Steps:\n" + "\n".join(f" {i+1}. {s}" for i, s in enumerate(steps)), priority="high" ) return task_id # Example task_id = start_workflow("Deploy Synapse v1.6.0", [ "Bump version in package.json", "Update CHANGELOG.md", "Commit and push", "Wait for CI green", "Verify deployment" ]) ``` ### Step 2: Track progress in task description ```python def update_progress(task_id, current_step, total_steps, status_note): """Update task with current progress.""" description = f"Progress: {current_step}/{total_steps}\nStatus: {status_note}" update_task(task_id, status="in_progress", description=description) # Example update_progress(task_id, 2, 5, "CHANGELOG updated, committing now") ``` ### Step 3: Resume across sessions ```python def resume_work(): """At session start, find and resume in-progress tasks.""" tasks = list_tasks(status="in_progress") for task in tasks: print(f"Resuming: {task['title']}") print(f"Last status: {task['description']}") # Parse progress from description progress = parse_progress(task['description']) next_step = progress['current_step'] + 1 # Continue from next step continue_from_step(task['id'], next_step) ``` ### Step 4: Complete and archive ```python def complete_task(task_id, summary): """Mark task done with completion summary.""" update_task(task_id, status="done", description=f"COMPLETED. Summary: {summary}" ) # Also store as memory for long-term reference remember( category="project", key=f"completed_{task_id}", content=f"Task: {task_id}\nSummary: {summary}", tags=["completed", "task"], priority="normal" ) ``` ## Full Example: Deploy Workflow ```python class DeployWorkflow: def __init__(self, version): self.version = version self.task_id = None self.steps = [ ("Bump version", self.bump_version), ("Update changelog", self.update_changelog), ("Commit and push", self.commit_push), ("Wait for CI", self.wait_for_ci), ("Verify deployment", self.verify_deployment), ] def run(self): # Check if already in progress existing = self.find_existing() if existing: self.task_id = existing['id'] start_step = self.parse_progress(existing['description']) else: self.task_id = create_task( title=f"Deploy Synapse v{self.version}", description=self.build_description(0), priority="high" ) start_step = 0 # Execute remaining steps for i in range(start_step, len(self.steps)): step_name, step_fn = self.steps[i] self.update_progress(i, f"Running: {step_name}") try: step_fn() except Exception as e: self.update_progress(i, f"FAILED at {step_name}: {e}") raise self.complete() def update_progress(self, step_idx, status): update_task(self.task_id, status="in_progress", description=f"Step {step_idx+1}/{len(self.steps)}: {status}" ) def complete(self): complete_task(self.task_id, f"Deployed v{self.version} successfully") ``` ## Task Hierarchy For complex work, use parent-child task relationships: ```python # Parent task parent_id = create_task("v1.6.0 Release", priority="high") # Sub-tasks (linked via tags) create_task("Bump version", description=f"Parent: {parent_id}", tags=["v1.6.0", f"parent-{parent_id}"], priority="high") create_task("Update docs", description=f"Parent: {parent_id}", tags=["v1.6.0", f"parent-{parent_id}"], priority="normal") ``` Search for sub-tasks: ```bash curl -H "Authorization: Bearer $KEY" \ ".../memory/search?q=parent-{parent_id}&tag=v1.6.0" ``` ## Status Workflow ``` pending → in_progress → done ↘ cancelled ``` ### Pending Task created but not started. Use for planned work. ### In Progress Currently being worked on. **Update description with progress.** ### Done Completed successfully. Description should include summary. ### Cancelled Abandoned. Description should include reason. ## Best Practices > [!TIP] > - **Create tasks for multi-step work** — single-step work doesn't need a task > - **Update description with progress** — enables resumption > - **Use high priority for active work** — surfaces in recall > - **Complete tasks when done** — don't leave them in_progress > - **Store completion summaries as memories** — long-term reference ## Common Patterns ### Pattern: Bug Fix Workflow ```python def fix_bug(bug_id, description): task_id = create_task( title=f"Fix bug {bug_id}", description=description, priority="high" ) # Investigate update_progress(task_id, "Investigating root cause") root_cause = investigate() # Fix update_progress(task_id, f"Applying fix: {root_cause}") apply_fix(root_cause) # Test update_progress(task_id, "Testing fix") run_tests() # Deploy update_progress(task_id, "Deploying fix") deploy() complete_task(task_id, f"Fixed: {root_cause}") ``` ### Pattern: Research Workflow ```python def research_topic(topic): task_id = create_task( title=f"Research: {topic}", priority="normal" ) update_progress(task_id, "Gathering sources") sources = gather_sources(topic) update_progress(task_id, "Analyzing") analysis = analyze(sources) update_progress(task_id, "Storing findings") remember("fact", f"research_{topic}", analysis, tags=["research", topic], priority="normal") complete_task(task_id, f"Research complete: {len(sources)} sources") ``` ## Next Steps - [Session Start Pattern](/docs/llm-cookbook/session-start-pattern) - [Chat Polling Pattern](/docs/llm-cookbook/chat-polling-pattern) - [Error Recovery](/docs/llm-cookbook/error-recovery)