mirror of
https://github.com/alkimake/paperclip.git
synced 2026-06-18 11:40:39 +09:00
[codex] Harden execution reliability and heartbeat tooling (#3679)
## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Reliable execution depends on heartbeat routing, issue lifecycle semantics, telemetry, and a fast enough local verification loop to keep regressions visible > - The remaining commits on this branch were mostly server/runtime correctness fixes plus test and documentation follow-ups in that area > - Those changes are logically separate from the UI-focused issue-detail and workspace/navigation branches even when they touch overlapping issue APIs > - This pull request groups the execution reliability, heartbeat, telemetry, and tooling changes into one standalone branch > - The benefit is a focused review of the control-plane correctness work, including the follow-up fix that restored the implicit comment-reopen helpers after branch splitting ## What Changed - Hardened issue/heartbeat execution behavior, including self-review stage skipping, deferred mention wakes during active execution, stranded execution recovery, active-run scoping, assignee resolution, and blocked-to-todo wake resumption - Reduced noisy polling/logging overhead by trimming issue run payloads, compacting persisted run logs, silencing high-volume request logs, and capping heartbeat-run queries in dashboard/inbox surfaces - Expanded telemetry and status semantics with adapter/model fields on task completion plus clearer status guidance in docs/onboarding material - Updated test infrastructure and verification defaults with faster route-test module isolation, cheaper default `pnpm test`, e2e isolation from local state, and repo verification follow-ups - Included docs/release housekeeping from the branch and added a small follow-up commit restoring the implicit comment-reopen helpers that were dropped during branch reconstruction ## Verification - `pnpm vitest run server/src/__tests__/issue-comment-reopen-routes.test.ts server/src/__tests__/issue-telemetry-routes.test.ts` - `pnpm vitest run server/src/__tests__/http-log-policy.test.ts server/src/__tests__/heartbeat-run-log.test.ts server/src/__tests__/health.test.ts` - `server/src/__tests__/activity-service.test.ts`, `server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and `server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted on this host but the embedded Postgres harness reported init-script/data-dir problems and skipped or failed to start, so they are noted as environment-limited ## Risks - Medium: this branch changes core issue/heartbeat routing and reopen/wakeup behavior, so regressions would affect agent execution flow rather than isolated UI polish - Because it also updates verification infrastructure, reviewers should pay attention to whether the new tests are asserting the right failure modes and not just reshaping harness behavior ## Model Used - OpenAI Codex coding agent (GPT-5-class runtime in Codex CLI; exact deployed model ID is not exposed in this environment), reasoning enabled, tool use and local code execution enabled ## 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) - [ ] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [ ] If this change affects the UI, I have included before/after screenshots - [x] I have updated relevant documentation to reflect my changes - [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
GitHub
parent
e89076148a
commit
7f893ac4ec
106 changed files with 4682 additions and 713 deletions
|
|
@ -95,6 +95,10 @@ async function waitFor(condition: () => boolean | Promise<boolean>, timeoutMs =
|
|||
throw new Error("Timed out waiting for condition");
|
||||
}
|
||||
|
||||
async function closeDbClient(db: ReturnType<typeof createDb> | undefined) {
|
||||
await db?.$client?.end?.({ timeout: 0 });
|
||||
}
|
||||
|
||||
async function createControlledGatewayServer() {
|
||||
const server = createServer();
|
||||
const wss = new WebSocketServer({ server });
|
||||
|
|
@ -225,6 +229,7 @@ describe("heartbeat comment wake batching", () => {
|
|||
}, 45_000);
|
||||
|
||||
afterAll(async () => {
|
||||
await closeDbClient(db);
|
||||
await instance?.stop();
|
||||
if (dataDir) {
|
||||
fs.rmSync(dataDir, { recursive: true, force: true });
|
||||
|
|
@ -761,6 +766,169 @@ describe("heartbeat comment wake batching", () => {
|
|||
}
|
||||
}, 20_000);
|
||||
|
||||
it("defers mentioned-agent wakes while another agent is actively executing the same issue", async () => {
|
||||
const gateway = await createControlledGatewayServer();
|
||||
const companyId = randomUUID();
|
||||
const primaryAgentId = randomUUID();
|
||||
const mentionedAgentId = randomUUID();
|
||||
const issueId = randomUUID();
|
||||
const issuePrefix = `T${companyId.replace(/-/g, "").slice(0, 6).toUpperCase()}`;
|
||||
const heartbeat = heartbeatService(db);
|
||||
|
||||
try {
|
||||
await db.insert(companies).values({
|
||||
id: companyId,
|
||||
name: "Paperclip",
|
||||
issuePrefix,
|
||||
requireBoardApprovalForNewAgents: false,
|
||||
});
|
||||
|
||||
await db.insert(agents).values([
|
||||
{
|
||||
id: primaryAgentId,
|
||||
companyId,
|
||||
name: "Primary Agent",
|
||||
role: "engineer",
|
||||
status: "idle",
|
||||
adapterType: "openclaw_gateway",
|
||||
adapterConfig: {
|
||||
url: gateway.url,
|
||||
headers: {
|
||||
"x-openclaw-token": "gateway-token",
|
||||
},
|
||||
payloadTemplate: {
|
||||
message: "wake now",
|
||||
},
|
||||
waitTimeoutMs: 2_000,
|
||||
},
|
||||
runtimeConfig: {},
|
||||
permissions: {},
|
||||
},
|
||||
{
|
||||
id: mentionedAgentId,
|
||||
companyId,
|
||||
name: "Mentioned Agent",
|
||||
role: "engineer",
|
||||
status: "idle",
|
||||
adapterType: "openclaw_gateway",
|
||||
adapterConfig: {
|
||||
url: gateway.url,
|
||||
headers: {
|
||||
"x-openclaw-token": "gateway-token",
|
||||
},
|
||||
payloadTemplate: {
|
||||
message: "wake now",
|
||||
},
|
||||
waitTimeoutMs: 2_000,
|
||||
},
|
||||
runtimeConfig: {},
|
||||
permissions: {},
|
||||
},
|
||||
]);
|
||||
|
||||
await db.insert(issues).values({
|
||||
id: issueId,
|
||||
companyId,
|
||||
title: "Prevent concurrent mention execution",
|
||||
status: "todo",
|
||||
priority: "high",
|
||||
assigneeAgentId: primaryAgentId,
|
||||
issueNumber: 1,
|
||||
identifier: `${issuePrefix}-1`,
|
||||
});
|
||||
|
||||
const primaryRun = await heartbeat.wakeup(primaryAgentId, {
|
||||
source: "assignment",
|
||||
triggerDetail: "system",
|
||||
reason: "issue_assigned",
|
||||
payload: { issueId },
|
||||
contextSnapshot: {
|
||||
issueId,
|
||||
taskId: issueId,
|
||||
wakeReason: "issue_assigned",
|
||||
},
|
||||
requestedByActorType: "system",
|
||||
requestedByActorId: null,
|
||||
});
|
||||
|
||||
expect(primaryRun).not.toBeNull();
|
||||
await waitFor(() => gateway.getAgentPayloads().length === 1);
|
||||
|
||||
const mentionComment = await db
|
||||
.insert(issueComments)
|
||||
.values({
|
||||
companyId,
|
||||
issueId,
|
||||
authorUserId: "user-1",
|
||||
body: "@Mentioned Agent please inspect this after the current run.",
|
||||
})
|
||||
.returning()
|
||||
.then((rows) => rows[0]);
|
||||
|
||||
const mentionRun = await heartbeat.wakeup(mentionedAgentId, {
|
||||
source: "automation",
|
||||
triggerDetail: "system",
|
||||
reason: "issue_comment_mentioned",
|
||||
payload: { issueId, commentId: mentionComment.id },
|
||||
contextSnapshot: {
|
||||
issueId,
|
||||
taskId: issueId,
|
||||
commentId: mentionComment.id,
|
||||
wakeCommentId: mentionComment.id,
|
||||
wakeReason: "issue_comment_mentioned",
|
||||
source: "comment.mention",
|
||||
},
|
||||
requestedByActorType: "user",
|
||||
requestedByActorId: "user-1",
|
||||
});
|
||||
|
||||
expect(mentionRun).toBeNull();
|
||||
|
||||
await waitFor(async () => {
|
||||
const deferred = await db
|
||||
.select()
|
||||
.from(agentWakeupRequests)
|
||||
.where(
|
||||
and(
|
||||
eq(agentWakeupRequests.companyId, companyId),
|
||||
eq(agentWakeupRequests.agentId, mentionedAgentId),
|
||||
eq(agentWakeupRequests.status, "deferred_issue_execution"),
|
||||
),
|
||||
)
|
||||
.then((rows) => rows[0] ?? null);
|
||||
return Boolean(deferred);
|
||||
});
|
||||
|
||||
expect(gateway.getAgentPayloads()).toHaveLength(1);
|
||||
|
||||
gateway.releaseFirstWait();
|
||||
|
||||
await waitFor(() => gateway.getAgentPayloads().length === 2, 90_000);
|
||||
await waitFor(async () => {
|
||||
const runs = await db
|
||||
.select()
|
||||
.from(heartbeatRuns)
|
||||
.where(eq(heartbeatRuns.agentId, mentionedAgentId))
|
||||
.orderBy(asc(heartbeatRuns.createdAt));
|
||||
return runs.length === 1 && runs[0]?.status === "succeeded";
|
||||
}, 90_000);
|
||||
|
||||
const mentionedRuns = await db
|
||||
.select()
|
||||
.from(heartbeatRuns)
|
||||
.where(eq(heartbeatRuns.agentId, mentionedAgentId))
|
||||
.orderBy(asc(heartbeatRuns.createdAt));
|
||||
|
||||
expect(mentionedRuns).toHaveLength(1);
|
||||
expect(mentionedRuns[0]?.contextSnapshot).toMatchObject({
|
||||
issueId,
|
||||
wakeReason: "issue_comment_mentioned",
|
||||
});
|
||||
} finally {
|
||||
gateway.releaseFirstWait();
|
||||
await gateway.close();
|
||||
}
|
||||
}, 120_000);
|
||||
it("treats the automatic run summary as fallback-only when the run already posted a comment", async () => {
|
||||
const gateway = await createControlledGatewayServer();
|
||||
const companyId = randomUUID();
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue