2026-04-06 09:34:15 -05:00
|
|
|
import { describe, expect, it, vi } from "vitest";
|
[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>
2026-04-14 13:34:52 -05:00
|
|
|
import { buildSkillMentionHref } from "@paperclipai/shared";
|
|
|
|
|
import {
|
|
|
|
|
applyRunScopedMentionedSkillKeys,
|
|
|
|
|
extractMentionedSkillIdsFromSources,
|
|
|
|
|
resolveExecutionRunAdapterConfig,
|
|
|
|
|
} from "../services/heartbeat.ts";
|
2026-04-06 09:34:15 -05:00
|
|
|
|
|
|
|
|
describe("resolveExecutionRunAdapterConfig", () => {
|
|
|
|
|
it("overlays project env on top of agent env and unions secret keys", async () => {
|
|
|
|
|
const resolveAdapterConfigForRuntime = vi.fn().mockResolvedValue({
|
|
|
|
|
config: {
|
|
|
|
|
env: {
|
|
|
|
|
SHARED_KEY: "agent",
|
|
|
|
|
AGENT_ONLY: "agent-only",
|
|
|
|
|
},
|
|
|
|
|
other: "value",
|
|
|
|
|
},
|
|
|
|
|
secretKeys: new Set(["AGENT_SECRET"]),
|
|
|
|
|
});
|
|
|
|
|
const resolveEnvBindings = vi.fn().mockResolvedValue({
|
|
|
|
|
env: {
|
|
|
|
|
SHARED_KEY: "project",
|
|
|
|
|
PROJECT_ONLY: "project-only",
|
|
|
|
|
},
|
|
|
|
|
secretKeys: new Set(["PROJECT_SECRET"]),
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const result = await resolveExecutionRunAdapterConfig({
|
|
|
|
|
companyId: "company-1",
|
|
|
|
|
executionRunConfig: { env: { SHARED_KEY: "agent" } },
|
|
|
|
|
projectEnv: { SHARED_KEY: "project" },
|
|
|
|
|
secretsSvc: {
|
|
|
|
|
resolveAdapterConfigForRuntime,
|
|
|
|
|
resolveEnvBindings,
|
|
|
|
|
} as any,
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
expect(result.resolvedConfig).toMatchObject({
|
|
|
|
|
other: "value",
|
|
|
|
|
env: {
|
|
|
|
|
SHARED_KEY: "project",
|
|
|
|
|
AGENT_ONLY: "agent-only",
|
|
|
|
|
PROJECT_ONLY: "project-only",
|
|
|
|
|
},
|
|
|
|
|
});
|
|
|
|
|
expect(Array.from(result.secretKeys).sort()).toEqual(["AGENT_SECRET", "PROJECT_SECRET"]);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("skips project env resolution when the project has no bindings", async () => {
|
|
|
|
|
const resolveAdapterConfigForRuntime = vi.fn().mockResolvedValue({
|
|
|
|
|
config: { env: { AGENT_ONLY: "agent-only" } },
|
|
|
|
|
secretKeys: new Set<string>(),
|
|
|
|
|
});
|
|
|
|
|
const resolveEnvBindings = vi.fn();
|
|
|
|
|
|
|
|
|
|
const result = await resolveExecutionRunAdapterConfig({
|
|
|
|
|
companyId: "company-1",
|
|
|
|
|
executionRunConfig: { env: { AGENT_ONLY: "agent-only" } },
|
|
|
|
|
projectEnv: null,
|
|
|
|
|
secretsSvc: {
|
|
|
|
|
resolveAdapterConfigForRuntime,
|
|
|
|
|
resolveEnvBindings,
|
|
|
|
|
} as any,
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
expect(result.resolvedConfig.env).toEqual({ AGENT_ONLY: "agent-only" });
|
|
|
|
|
expect(resolveEnvBindings).not.toHaveBeenCalled();
|
|
|
|
|
});
|
|
|
|
|
});
|
[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>
2026-04-14 13:34:52 -05:00
|
|
|
|
|
|
|
|
describe("extractMentionedSkillIdsFromSources", () => {
|
|
|
|
|
it("collects explicit skill mention ids across issue sources", () => {
|
|
|
|
|
const releaseHref = buildSkillMentionHref("skill-1", "release-changelog");
|
|
|
|
|
const browserHref = buildSkillMentionHref("skill-2", "agent-browser");
|
|
|
|
|
|
|
|
|
|
expect(
|
|
|
|
|
extractMentionedSkillIdsFromSources([
|
|
|
|
|
`Please use [/release-changelog](${releaseHref})`,
|
|
|
|
|
`And also [/agent-browser](${browserHref})`,
|
|
|
|
|
`Duplicate mention [/release-changelog](${releaseHref})`,
|
|
|
|
|
]),
|
|
|
|
|
).toEqual(["skill-1", "skill-2"]);
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe("applyRunScopedMentionedSkillKeys", () => {
|
|
|
|
|
it("adds mentioned skills without mutating the original config", () => {
|
|
|
|
|
const originalConfig = {
|
|
|
|
|
command: "codex",
|
|
|
|
|
paperclipSkillSync: {
|
|
|
|
|
desiredSkills: ["paperclipai/paperclip/paperclip"],
|
|
|
|
|
},
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
const updatedConfig = applyRunScopedMentionedSkillKeys(originalConfig, [
|
|
|
|
|
"company/company-1/release-changelog",
|
|
|
|
|
"paperclipai/paperclip/paperclip",
|
|
|
|
|
"company/company-1/release-changelog",
|
|
|
|
|
]);
|
|
|
|
|
|
|
|
|
|
expect(updatedConfig).toEqual({
|
|
|
|
|
command: "codex",
|
|
|
|
|
paperclipSkillSync: {
|
|
|
|
|
desiredSkills: [
|
|
|
|
|
"paperclipai/paperclip/paperclip",
|
|
|
|
|
"company/company-1/release-changelog",
|
|
|
|
|
],
|
|
|
|
|
},
|
|
|
|
|
});
|
|
|
|
|
expect(originalConfig).toEqual({
|
|
|
|
|
command: "codex",
|
|
|
|
|
paperclipSkillSync: {
|
|
|
|
|
desiredSkills: ["paperclipai/paperclip/paperclip"],
|
|
|
|
|
},
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
});
|