mirror of
https://github.com/alkimake/paperclip.git
synced 2026-06-17 03:10:38 +09:00
## Thinking Path > - Paperclip orchestrates AI agents for autonomous companies, and heartbeat execution is the control-plane loop that keeps assigned work moving. > - Max-turn exhaustion is a recoverable local-adapter stop condition for Claude and Gemini agents when a run needs another heartbeat to continue safely. > - The previous behavior could leave max-turn continuation details hard to inspect, and duplicate/stale continuation wakes could keep running after issue state changed. > - The adapter layer also needed to avoid trusting arbitrary stdout/stderr text as scheduler control metadata. > - This pull request adds bounded max-turn continuation scheduling, visible retry state, structured stop metadata handling, and stale/duplicate continuation guards. > - The benefit is safer automatic continuation after max-turn stops, clearer operator visibility, and fewer duplicate or stale agent runs. ## What Changed - Replaces closed PR #4952, whose head repository was deleted. - Rebases the recovered max-turn continuation branch onto current `paperclipai/paperclip:master`. - Adds max-turn continuation scheduling and retry-state plumbing for heartbeat runs. - Adds stale/duplicate continuation suppression when issue status, ownership, or execution locks change. - Normalizes Claude/Gemini max-turn detection around structured stop metadata instead of unstructured stdout/stderr text. - Surfaces max-turn continuation settings and retry visibility in the board UI. - Adds focused server, adapter, and UI tests for max-turn stop metadata, retry scheduling, stale queued-run invalidation, adapter parsing/execution, run ledger display, and agent config patching. ## Verification - `pnpm install --no-frozen-lockfile` to refresh local dependencies after rebasing onto current `master`. - `pnpm run preflight:workspace-links && pnpm exec vitest run server/src/__tests__/claude-local-adapter.test.ts server/src/__tests__/claude-local-execute.test.ts server/src/__tests__/gemini-local-adapter.test.ts server/src/__tests__/gemini-local-execute.test.ts server/src/__tests__/heartbeat-retry-scheduling.test.ts server/src/__tests__/heartbeat-stale-queue-invalidation.test.ts server/src/services/heartbeat-stop-metadata.test.ts ui/src/components/IssueRunLedger.test.tsx ui/src/lib/agent-config-patch.test.ts ui/src/lib/runRetryState.test.ts --testTimeout=20000` - `pnpm --filter @paperclipai/adapter-claude-local typecheck && pnpm --filter @paperclipai/adapter-gemini-local typecheck && pnpm --filter @paperclipai/server typecheck && pnpm --filter @paperclipai/ui typecheck` - UI screenshot note: the UI changes are limited to config/ledger state rendering rather than layout changes; component/unit coverage above verifies the rendered behavior. ## Risks - Medium behavior risk: heartbeat retry gating now suppresses max-turn continuations when issue state or execution locks drift, so any callers that relied on stale continuations running will now see cancellation instead. - Low adapter risk: Claude/Gemini unstructured text no longer triggers max-turn scheduler metadata, so only structured stop signals and Gemini exit code 53 are trusted. - No database migrations. > For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and discuss it in `#dev` before opening the PR. Feature PRs that overlap with planned core work may need to be redirected — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used - OpenAI Codex coding agent, GPT-5-class model, tool-enabled local repository editing and command execution. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] If this change affects the UI, I have included before/after screenshots (not applicable: state/default rendering only; covered by component/unit tests) - [x] I have updated relevant documentation to reflect my changes (not applicable: no user-facing command or docs contract changed) - [x] I have considered and documented any risks above - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
129 lines
4.4 KiB
TypeScript
129 lines
4.4 KiB
TypeScript
export type HeartbeatRunOutcome = "succeeded" | "failed" | "cancelled" | "timed_out";
|
|
|
|
export type HeartbeatRunStopReason =
|
|
| "completed"
|
|
| "timeout"
|
|
| "cancelled"
|
|
| "budget_paused"
|
|
| "paused"
|
|
| "max_turns_exhausted"
|
|
| "process_lost"
|
|
| "adapter_failed";
|
|
|
|
export interface HeartbeatRunTimeoutPolicy {
|
|
effectiveTimeoutSec: number | null;
|
|
effectiveTimeoutMs?: number | null;
|
|
timeoutConfigured: boolean;
|
|
timeoutSource: "config" | "default" | "unknown";
|
|
}
|
|
|
|
export interface HeartbeatRunStopMetadata extends HeartbeatRunTimeoutPolicy {
|
|
stopReason: HeartbeatRunStopReason;
|
|
timeoutFired: boolean;
|
|
}
|
|
|
|
function readFiniteNumber(value: unknown): number | null {
|
|
if (typeof value === "number") {
|
|
return Number.isFinite(value) ? value : null;
|
|
}
|
|
if (typeof value === "string") {
|
|
const parsed = Number(value.trim());
|
|
return Number.isFinite(parsed) ? parsed : null;
|
|
}
|
|
return null;
|
|
}
|
|
|
|
function hasOwn(record: Record<string, unknown>, key: string) {
|
|
return Object.prototype.hasOwnProperty.call(record, key);
|
|
}
|
|
|
|
function defaultTimeoutSecForAdapter(adapterType: string) {
|
|
return adapterType === "openclaw_gateway" ? 120 : 0;
|
|
}
|
|
|
|
export function normalizeMaxTurnStopReason(value: unknown): Extract<HeartbeatRunStopReason, "max_turns_exhausted"> | null {
|
|
return value === "max_turns_exhausted" || value === "turn_limit_exhausted"
|
|
? "max_turns_exhausted"
|
|
: null;
|
|
}
|
|
|
|
export function resolveHeartbeatRunTimeoutPolicy(
|
|
adapterType: string,
|
|
adapterConfig: Record<string, unknown> | null | undefined,
|
|
): HeartbeatRunTimeoutPolicy {
|
|
const config = adapterConfig ?? {};
|
|
|
|
if (adapterType === "http") {
|
|
const hasTimeoutMs = hasOwn(config, "timeoutMs");
|
|
const rawTimeoutMs = hasTimeoutMs ? readFiniteNumber(config.timeoutMs) : 0;
|
|
const timeoutMs = Math.max(0, Math.floor(rawTimeoutMs ?? 0));
|
|
return {
|
|
effectiveTimeoutSec: timeoutMs / 1000,
|
|
effectiveTimeoutMs: timeoutMs,
|
|
timeoutConfigured: timeoutMs > 0,
|
|
timeoutSource: hasTimeoutMs ? "config" : "default",
|
|
};
|
|
}
|
|
|
|
const hasTimeoutSec = hasOwn(config, "timeoutSec");
|
|
const defaultTimeoutSec = defaultTimeoutSecForAdapter(adapterType);
|
|
const rawTimeoutSec = hasTimeoutSec ? readFiniteNumber(config.timeoutSec) : defaultTimeoutSec;
|
|
const timeoutSec = Math.max(0, Math.floor(rawTimeoutSec ?? defaultTimeoutSec));
|
|
|
|
return {
|
|
effectiveTimeoutSec: timeoutSec,
|
|
timeoutConfigured: timeoutSec > 0,
|
|
timeoutSource: hasTimeoutSec ? "config" : "default",
|
|
};
|
|
}
|
|
|
|
export function inferHeartbeatRunStopReason(input: {
|
|
outcome: HeartbeatRunOutcome;
|
|
errorCode?: string | null;
|
|
errorMessage?: string | null;
|
|
}): HeartbeatRunStopReason {
|
|
if (input.outcome === "succeeded") return "completed";
|
|
const maxTurnStopReason = normalizeMaxTurnStopReason(input.errorCode);
|
|
if (maxTurnStopReason) return maxTurnStopReason;
|
|
if (input.outcome === "timed_out") return "timeout";
|
|
if (input.outcome === "failed" && input.errorCode === "process_lost") return "process_lost";
|
|
if (input.outcome === "cancelled") {
|
|
const message = (input.errorMessage ?? "").toLowerCase();
|
|
if (message.includes("budget")) return "budget_paused";
|
|
if (message.includes("pause") || message.includes("paused")) return "paused";
|
|
return "cancelled";
|
|
}
|
|
return "adapter_failed";
|
|
}
|
|
|
|
export function buildHeartbeatRunStopMetadata(input: {
|
|
adapterType: string;
|
|
adapterConfig: Record<string, unknown> | null | undefined;
|
|
outcome: HeartbeatRunOutcome;
|
|
errorCode?: string | null;
|
|
errorMessage?: string | null;
|
|
}): HeartbeatRunStopMetadata {
|
|
const timeoutPolicy = resolveHeartbeatRunTimeoutPolicy(input.adapterType, input.adapterConfig);
|
|
const stopReason = inferHeartbeatRunStopReason(input);
|
|
return {
|
|
...timeoutPolicy,
|
|
stopReason,
|
|
timeoutFired: stopReason === "timeout",
|
|
};
|
|
}
|
|
|
|
export function mergeHeartbeatRunStopMetadata(
|
|
resultJson: Record<string, unknown> | null | undefined,
|
|
metadata: HeartbeatRunStopMetadata,
|
|
): Record<string, unknown> {
|
|
const existingMaxTurnStopReason = normalizeMaxTurnStopReason(resultJson?.stopReason);
|
|
return {
|
|
...(resultJson ?? {}),
|
|
stopReason: existingMaxTurnStopReason ?? metadata.stopReason,
|
|
effectiveTimeoutSec: metadata.effectiveTimeoutSec,
|
|
timeoutConfigured: metadata.timeoutConfigured,
|
|
timeoutSource: metadata.timeoutSource,
|
|
timeoutFired: metadata.timeoutFired,
|
|
...(metadata.effectiveTimeoutMs != null ? { effectiveTimeoutMs: metadata.effectiveTimeoutMs } : {}),
|
|
};
|
|
}
|