# Task-getriebener Workflow Tasks sind nicht nur Todos — sie sind das Rückgrat persistenter LLM-Workflows. Indem du für mehrschrittige Arbeit Tasks anlegst, sicherst du Kontinuität über Sessions und stellst Audit-Trails für getane Arbeit bereit. ## Warum Task-getrieben? Ohne Tasks: - LLM startet jede Session unsicher, was zu tun ist - Mehrschrittige Arbeit wird mitten in der Ausführung vergessen - Kein Record darüber, was getan wurde Mit Tasks: - LLM nimmt in-progress Tasks sofort wieder auf - Mehrschrittige Arbeit überdauert Sessions - Eingebauter Audit-Trail aller Arbeit ## Das 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 ``` ## Implementierung ### Schritt 1: Einen Task für mehrschrittige Arbeit anlegen ```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" ]) ``` ### Schritt 2: Fortschritt in Task-Beschreibung tracken ```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") ``` ### Schritt 3: Über Sessions hinweg fortsetzen ```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) ``` ### Schritt 4: Abschließen und archivieren ```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" ) ``` ## Vollständiges Beispiel: 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-Hierarchie Für komplexe Arbeit verwende Parent-Child-Task-Beziehungen: ```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") ``` Nach Sub-Tasks suchen: ```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 angelegt, aber nicht begonnen. Für geplante Arbeit verwenden. ### In Progress Wird gerade bearbeitet. **Beschreibung mit Fortschritt aktualisieren.** ### Done Erfolgreich abgeschlossen. Beschreibung sollte Zusammenfassung enthalten. ### Cancelled Abgebrochen. Beschreibung sollte den Grund enthalten. ## Best Practices > [!TIP] > - **Tasks für mehrschrittige Arbeit anlegen** — einschrittige Arbeit braucht keinen Task > - **Beschreibung mit Fortschritt aktualisieren** — ermöglicht Wiederaufnahme > - **Hohe Priorität für aktive Arbeit** — taucht im Recall auf > - **Tasks abschließen, wenn erledigt** — nicht in_progress lassen > - **Abschluss-Zusammenfassungen als Memories speichern** — langfristige Referenz ## Häufige 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: Recherche-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") ``` ## Nächste Schritte - [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)