[codex] Retry max-turn exhausted heartbeats (#5096)

## 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>
This commit is contained in:
Dotta 2026-05-03 11:30:48 -05:00 committed by GitHub
parent 57229d0f24
commit 15eac43b43
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
21 changed files with 1915 additions and 120 deletions

View file

@ -6,6 +6,7 @@ export type HeartbeatRunStopReason =
| "cancelled"
| "budget_paused"
| "paused"
| "max_turns_exhausted"
| "process_lost"
| "adapter_failed";
@ -40,6 +41,12 @@ 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,
@ -76,6 +83,8 @@ export function inferHeartbeatRunStopReason(input: {
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") {
@ -107,9 +116,10 @@ export function mergeHeartbeatRunStopMetadata(
resultJson: Record<string, unknown> | null | undefined,
metadata: HeartbeatRunStopMetadata,
): Record<string, unknown> {
const existingMaxTurnStopReason = normalizeMaxTurnStopReason(resultJson?.stopReason);
return {
...(resultJson ?? {}),
stopReason: metadata.stopReason,
stopReason: existingMaxTurnStopReason ?? metadata.stopReason,
effectiveTimeoutSec: metadata.effectiveTimeoutSec,
timeoutConfigured: metadata.timeoutConfigured,
timeoutSource: metadata.timeoutSource,