Files
paperclip/server/src/__tests__/claude-local-adapter.test.ts
T
Dotta 15eac43b43 [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>
2026-05-03 11:30:48 -05:00

206 lines
5.5 KiB
TypeScript

import { describe, expect, it, vi } from "vitest";
import { isClaudeMaxTurnsResult } from "@paperclipai/adapter-claude-local/server";
import { parseClaudeStdoutLine } from "@paperclipai/adapter-claude-local/ui";
import { printClaudeStreamEvent } from "@paperclipai/adapter-claude-local/cli";
describe("claude_local max-turn detection", () => {
it("detects max-turn exhaustion by subtype", () => {
expect(
isClaudeMaxTurnsResult({
subtype: "error_max_turns",
result: "Reached max turns",
}),
).toBe(true);
});
it("detects max-turn exhaustion by stop_reason", () => {
expect(
isClaudeMaxTurnsResult({
stop_reason: "max_turns",
}),
).toBe(true);
});
it("checks every structured stop field for max-turn exhaustion", () => {
expect(
isClaudeMaxTurnsResult({
stop_reason: "end_turn",
stopReason: "max_turns_exhausted",
}),
).toBe(true);
});
it("returns false for non-max-turn results", () => {
expect(
isClaudeMaxTurnsResult({
subtype: "success",
stop_reason: "end_turn",
}),
).toBe(false);
});
it("does not detect max-turn exhaustion from unstructured result text", () => {
expect(
isClaudeMaxTurnsResult({
subtype: "error",
result: "Tool output said: Maximum turns reached.",
}),
).toBe(false);
});
});
describe("claude_local ui stdout parser", () => {
it("maps assistant text, thinking, tool calls, and tool results into transcript entries", () => {
const ts = "2026-03-29T00:00:00.000Z";
expect(
parseClaudeStdoutLine(
JSON.stringify({
type: "system",
subtype: "init",
model: "claude-sonnet-4-6",
session_id: "claude-session-1",
}),
ts,
),
).toEqual([
{
kind: "init",
ts,
model: "claude-sonnet-4-6",
sessionId: "claude-session-1",
},
]);
expect(
parseClaudeStdoutLine(
JSON.stringify({
type: "assistant",
session_id: "claude-session-1",
message: {
content: [
{ type: "text", text: "I will inspect the repo." },
{ type: "thinking", thinking: "Checking the adapter wiring" },
{ type: "tool_use", id: "tool_1", name: "bash", input: { command: "ls -1" } },
],
},
}),
ts,
),
).toEqual([
{ kind: "assistant", ts, text: "I will inspect the repo." },
{ kind: "thinking", ts, text: "Checking the adapter wiring" },
{ kind: "tool_call", ts, name: "bash", toolUseId: "tool_1", input: { command: "ls -1" } },
]);
expect(
parseClaudeStdoutLine(
JSON.stringify({
type: "user",
message: {
content: [
{
type: "tool_result",
tool_use_id: "tool_1",
content: [{ type: "text", text: "AGENTS.md\nREADME.md" }],
is_error: false,
},
],
},
}),
ts,
),
).toEqual([
{
kind: "tool_result",
ts,
toolUseId: "tool_1",
content: "AGENTS.md\nREADME.md",
isError: false,
},
]);
});
});
function stripAnsi(value: string) {
return value.replace(/\x1b\[[0-9;]*m/g, "");
}
describe("claude_local cli formatter", () => {
it("prints the user-visible and background transcript events from stream-json output", () => {
const spy = vi.spyOn(console, "log").mockImplementation(() => {});
try {
printClaudeStreamEvent(
JSON.stringify({
type: "system",
subtype: "init",
model: "claude-sonnet-4-6",
session_id: "claude-session-1",
}),
false,
);
printClaudeStreamEvent(
JSON.stringify({
type: "assistant",
message: {
content: [
{ type: "text", text: "I will inspect the repo." },
{ type: "thinking", thinking: "Checking the adapter wiring" },
{ type: "tool_use", id: "tool_1", name: "bash", input: { command: "ls -1" } },
],
},
}),
false,
);
printClaudeStreamEvent(
JSON.stringify({
type: "user",
message: {
content: [
{
type: "tool_result",
tool_use_id: "tool_1",
content: [{ type: "text", text: "AGENTS.md\nREADME.md" }],
is_error: false,
},
],
},
}),
false,
);
printClaudeStreamEvent(
JSON.stringify({
type: "result",
subtype: "success",
result: "Done",
usage: { input_tokens: 10, output_tokens: 5, cache_read_input_tokens: 2 },
total_cost_usd: 0.00042,
}),
false,
);
const lines = spy.mock.calls
.map((call) => call.map((value) => String(value)).join(" "))
.map(stripAnsi);
expect(lines).toEqual(
expect.arrayContaining([
"Claude initialized (model: claude-sonnet-4-6, session: claude-session-1)",
"assistant: I will inspect the repo.",
"thinking: Checking the adapter wiring",
"tool_call: bash",
'{\n "command": "ls -1"\n}',
"tool_result",
"AGENTS.md\nREADME.md",
"result:",
"Done",
"tokens: in=10 out=5 cached=2 cost=$0.000420",
]),
);
} finally {
spy.mockRestore();
}
});
});