[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

@ -777,6 +777,7 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
const transientUpstream =
failed &&
!loginMeta.requiresLogin &&
!clearSessionForMaxTurns &&
isClaudeTransientUpstreamError({
parsed,
stdout: proc.stdout,
@ -793,11 +794,14 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
: null;
const resolvedErrorCode = loginMeta.requiresLogin
? "claude_auth_required"
: failed && clearSessionForMaxTurns
? "max_turns_exhausted"
: transientUpstream
? "claude_transient_upstream"
: null;
const mergedResultJson: Record<string, unknown> = {
...parsed,
...(failed && clearSessionForMaxTurns ? { stopReason: "max_turns_exhausted" } : {}),
...(transientUpstream ? { errorFamily: "transient_upstream" } : {}),
...(transientRetryNotBefore ? { retryNotBefore: transientRetryNotBefore.toISOString() } : {}),
...(transientRetryNotBefore ? { transientRetryNotBefore: transientRetryNotBefore.toISOString() } : {}),

View file

@ -170,11 +170,19 @@ export function isClaudeMaxTurnsResult(parsed: Record<string, unknown> | null |
const subtype = asString(parsed.subtype, "").trim().toLowerCase();
if (subtype === "error_max_turns") return true;
const stopReason = asString(parsed.stop_reason, "").trim().toLowerCase();
if (stopReason === "max_turns") return true;
const structuredStopReasons = [
parsed.stop_reason,
parsed.stopReason,
parsed.error_code,
parsed.errorCode,
].map((value) => asString(value, "").trim().toLowerCase());
const resultText = asString(parsed.result, "").trim();
return /max(?:imum)?\s+turns?/i.test(resultText);
return structuredStopReasons.some((reason) =>
reason === "max_turns" ||
reason === "max_turns_exhausted" ||
reason === "turn_limit" ||
reason === "turn_limit_exhausted",
);
}
export function isClaudeUnknownSessionError(parsed: Record<string, unknown>): boolean {

View file

@ -531,7 +531,21 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
};
}
const clearSessionForTurnLimit = isGeminiTurnLimitResult(attempt.parsed.resultEvent, attempt.proc.exitCode);
const parsedError = typeof attempt.parsed.errorMessage === "string" ? attempt.parsed.errorMessage.trim() : "";
const stderrLine = firstNonEmptyLine(attempt.proc.stderr);
const structuredFailure = attempt.parsed.resultEvent
? describeGeminiFailure(attempt.parsed.resultEvent)
: null;
const fallbackErrorMessage =
parsedError ||
structuredFailure ||
stderrLine ||
`Gemini exited with code ${attempt.proc.exitCode ?? -1}`;
const failed = (attempt.proc.exitCode ?? 0) !== 0;
const clearSessionForTurnLimit = isGeminiTurnLimitResult(
attempt.parsed.resultEvent,
attempt.proc.exitCode,
);
// On retry, don't fall back to old session ID — the old session was stale
const canFallbackToRuntimeSession = !isRetry;
@ -551,23 +565,24 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
: {}),
} as Record<string, unknown>)
: null;
const parsedError = typeof attempt.parsed.errorMessage === "string" ? attempt.parsed.errorMessage.trim() : "";
const stderrLine = firstNonEmptyLine(attempt.proc.stderr);
const structuredFailure = attempt.parsed.resultEvent
? describeGeminiFailure(attempt.parsed.resultEvent)
: null;
const fallbackErrorMessage =
parsedError ||
structuredFailure ||
stderrLine ||
`Gemini exited with code ${attempt.proc.exitCode ?? -1}`;
const resultJson: Record<string, unknown> = {
...(attempt.parsed.resultEvent ?? {
stdout: attempt.proc.stdout,
stderr: attempt.proc.stderr,
}),
...(failed && clearSessionForTurnLimit ? { stopReason: "max_turns_exhausted" } : {}),
};
return {
exitCode: attempt.proc.exitCode,
signal: attempt.proc.signal,
timedOut: false,
errorMessage: (attempt.proc.exitCode ?? 0) === 0 ? null : fallbackErrorMessage,
errorCode: (attempt.proc.exitCode ?? 0) !== 0 && authMeta.requiresAuth ? "gemini_auth_required" : null,
errorMessage: failed ? fallbackErrorMessage : null,
errorCode: failed && authMeta.requiresAuth
? "gemini_auth_required"
: failed && clearSessionForTurnLimit
? "max_turns_exhausted"
: null,
usage: attempt.parsed.usage,
sessionId: resolvedSessionId,
sessionParams: resolvedSessionParams,
@ -577,10 +592,7 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
model,
billingType,
costUsd: attempt.parsed.costUsd,
resultJson: attempt.parsed.resultEvent ?? {
stdout: attempt.proc.stdout,
stderr: attempt.proc.stderr,
},
resultJson,
summary: attempt.parsed.summary,
question: attempt.parsed.question,
clearSession: clearSessionForTurnLimit || Boolean(clearSessionOnMissingSession && !resolvedSessionId),

View file

@ -273,9 +273,18 @@ export function isGeminiTurnLimitResult(
if (exitCode === 53) return true;
if (!parsed) return false;
const status = asString(parsed.status, "").trim().toLowerCase();
if (status === "turn_limit" || status === "max_turns") return true;
const structuredStopReasons = [
parsed.status,
parsed.stopReason,
parsed.stop_reason,
parsed.errorCode,
parsed.error_code,
].map((value) => asString(value, "").trim().toLowerCase());
const error = asString(parsed.error, "").trim();
return /turn\s*limit|max(?:imum)?\s+turns?/i.test(error);
return structuredStopReasons.some((reason) =>
reason === "turn_limit" ||
reason === "max_turns" ||
reason === "max_turns_exhausted" ||
reason === "turn_limit_exhausted",
);
}