Dauerhafte Agentenausführung

Macht Agentenausführung durch klare Lebenszykluszustände, dauerhafte Werkzeughistorie und begrenzte Fortsetzung nach Unterbrechungen wiederherstellbar.

agent-runtime-state

Teammitglieder mit diesem Skill

Entdecke, wie der Skill hilft

Wann ist der Skill hilfreich?

Nutze ihn, wenn Läufe auf Freigabe warten oder abstürzen, während ein Werkzeug bereits Änderungen bewirkt haben könnte.

Wobei hilft er dir?

Definiert Warteschlange, Ausführung, Freigabe und Endzustände ausdrücklich.
Speichert Werkzeugabsichten vor Ausführung und verwendet vorhandene Ergebnisse.
Begrenzt Schleifen und klärt unsichere Schreibvorgänge vor Wiederholung.

Das könntest du fragen

Stelle einen unterbrochenen Agentenlauf ohne doppelte Nachrichtenzustellung wieder her. Simuliere einen Absturz nach der Zustellung, aber vor dem letzten Speicherpunkt. Gleiche die Nachrichtenkennung ab und setze nur unerledigte Arbeit fort.

Ausführliche Dokumentation

Hier findest du die ursprüngliche Anleitung, Beispiele und Prüfschritte des Skills in ihrer Originalsprache.

Details…Weniger anzeigen

Agent Runtime & State Machines

Treat an agent run as a durable, event-sourced state machine rather than an in-memory while loop around an LLM call. Every model turn, tool invocation, human approval pause, and cancellation must transition through explicit states and persist enough history to resume cleanly after a process restart or crash.

Explicit Run State Machine

Model the lifecycle of an agent run and each turn with unambiguous states and legal transitions:

State	Meaning	Allowed Next States	Persistence Requirement
`queued`	Run created, awaiting worker slot	`running`, `cancelled`	Initial input, configuration, correlation ID
`running`	Model inference or turn orchestration active	`awaiting_tool`, `awaiting_approval`, `completed`, `failed`, `cancelled`	Append `turn_started` and streamed deltas or final assistant message
`awaiting_tool`	One or more tool calls dispatched	`running`, `awaiting_approval`, `failed`, `cancelled`	Persist `tool_call_requested` with `tool_call_id`, name, and canonical arguments before executing
`awaiting_approval`	Paused on human or policy gate	`awaiting_tool`, `running`, `cancelled`, `timed_out`	Persist pending `tool_call_id`, approval payload, and resume token
`completed`	Terminal goal or stop condition reached	(terminal)	Final structured output, stop reason, aggregated usage
`failed`	Unrecoverable error or budget exhausted	`queued` (explicit retry/resume)	Structured error code, failure phase, last checkpoint ID
`cancelled` / `timed_out`	Aborted by caller, signal, or deadline	`queued` (explicit resume)	Cancellation reason, any partial tool outputs completed before abort

Append-Only Event Log & Checkpointing

Write-ahead tool intent: Persist the assistant message containing tool_use blocks to the run store before invoking any tool handler. If the worker crashes mid-tool, recovery knows exactly which tool call was in flight.
Idempotent tool result recording: Record each tool_result keyed by (run_id, turn_index, tool_call_id). When resuming an interrupted turn, replay already-recorded tool_result entries from storage instead of re-executing completed tools.
Side-effect classification:
- read_only: Safe to automatically re-run on crash recovery if no result was recorded.
- idempotent_write: Safe to re-run only when called with the persisted deterministic idempotency_key (sha256(run_id + tool_call_id)).
- non_idempotent: Never auto-retry after an ambiguous crash (in_flight without result); transition to awaiting_approval or emit a reconciliation status check tool first.

Loop Guards, Budgets & Termination

Never rely solely on the model deciding to stop:

Hard turn & step ceilings: Enforce max_turns and max_tool_calls_per_turn. When turn_count == max_turns - 1, inject a final system notice instructing the model to synthesize its best answer or return a structured partial-progress handoff without calling further tools.
Token and cost budgets: Track cumulative input_tokens, output_tokens, cache_creation_input_tokens, and cache_read_input_tokens after every response. Halt with budget_exceeded before starting a turn that would breach the run budget.
Cycle and repetition detection: Hash (tool_name, canonical_json(args)) across a sliding window. If the agent invokes the identical failing or no-op tool call $N$ times (e.g., 3 consecutive identical calls), intercept the call and return a synthetic isError: true tool result explaining the loop and requiring a different strategy.
Cooperative cancellation (AbortSignal): Thread an AbortSignal into both the LLM stream and every tool execution context. On abort, cancel in-flight HTTP streams, terminate child processes with SIGTERM followed by SIGKILL after grace period, and close the turn with a synthetic cancelled tool_result so conversation history remains valid for future resumption.

Enthaltene Dateien 1

SKILL.md