Skip to content

PATTERN Cited by 1 source

Append-only event log for agent state

Problem

An LLM agent turn is not a single request — it involves streaming tokens, calling tools, waiting for results, delegating to sub-agents, and potentially awaiting human approval. At any point the process can crash. All in-memory state (streaming connection, pending tool calls, turn progress) is lost.

Solution

Record every event in the agent's execution history to an append-only, immutable log. Each entry (prompt, tool response, model choice) becomes an unchangeable ledger entry. On crash, a new instance replays the log from the last entry and resumes.

Mechanism

[prompt] → [tool-call-1] → [tool-result-1] → [model-choice] → [tool-call-2] → ...
   ↓            ↓                ↓                 ↓                ↓
 log[0]      log[1]           log[2]            log[3]           log[4]

On recovery: new instance reads log, skips completed entries, resumes at log[N+1].

(Source: Agents platform post.)

Trade-offs

Pro Con
No lost turns; user sees continuation not spinner Log storage grows linearly with turn length
Deterministic replay Replay assumes idempotent tool calls (or deduplication)
Platform-independent (any storage backend) Adds write latency per event (amortised by batching)

Known uses

Seen in

Last updated · 542 distilled / 1,571 read