mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-14 17:22:00 +01:00
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - When someone messages an agent, the turn must start fast. Time to first token (TTFT) is a first-class metric. > - The Phase 0 baseline (#19846) found that every local turn launches a new runner and loads the provider session again, because `per_turn` is the default lifecycle. That made a follow-up message slower than a new task. > - Warm runners keep the runner and provider session alive between runs. #19874 fixed the defect that broke warm OpenCode follow-ups, and #19879 bounds an idle warm runner whose controller dies. > - This pull request makes warm the default for local Codex and OpenCode agents, and migrates existing agents that only carried the old creation default. > - The benefit: follow-up TTFT p50 drops from 12.0 s to 4.7 s (Codex) and from 21.7 s to 4.2 s (OpenCode), with no new restart-chaos failures. ## Linked Issues or Issue Description Refs #19846 (TTFT baseline), #19852 (startup sub-spans), #19874 (warm completion contract), #19879 (warm reconnect grace). **What existing behavior does this improve?** The default runner lifecycle for native agents, and how a follow-up message starts. **Current behavior** Agent creation writes `lifecycleMode: "per_turn"` into every native agent. Every follow-up launches a new runner and restores the provider session: 4.2 s (Codex) and 16.3 s (OpenCode) at p50 before the turn starts. **Proposed behavior** New native agents store no lifecycle. On a local target, an unset lifecycle resolves to `warm` with the default 5-minute idle window for Codex and OpenCode. Other harnesses, remote targets and managed providers without warm support stay `per_turn`. An explicit choice always wins. Migration 0443 clears the stored creation default from existing agents, except where an edit set "Turn by turn" explicitly. **Reason and benefit** Measured locally (`doc/plans/2026-11-07-warm-follow-up-ttft.md`). Warm follow-ups are 2.6–5× faster for Codex and OpenCode, and restart recovery latency is equal or lower. ## What Changed - `native-lifecycle.ts`: an unset `agentMode` resolves to warm (5-minute idle window) for local `codex_app_server` and `opencode_server` agents. `runtime-selection.ts` passes `localTarget`. Explicit `per_turn` or `warm` wins. An admitted session keeps its persisted policy. ACPX Claude stays `per_turn`: it relaunches its provider process on every follow-up by design, so warm did not shorten its follow-up (10.7 s warm vs 10.5 s per_turn). - Creation and configuration writes no longer store `lifecycleMode: "per_turn"` for Codex, Claude or OpenCode. This covers `normalizePaperclipRunnerAdapterConfig` (runs on every create and update), `paperclipRunnerTransitionConfig` (switching to the native runner), `agent-runner-selection.ts`, `codex-local` `build-config.ts`, and the simplified new-agent setup (`paperclipRunnerCreationLifecycle` in `@paperclipai/shared`). Grok, Pi and Cursor keep their explicit value. - Agent form: the Runner lifecycle field shows the unset state as "Automatic". "Turn by turn" and "Warm session" remain. - Migration `0443_native_warm_follow_up_default.sql`: clears `lifecycleMode = 'per_turn'` from native Codex, OpenCode and Claude agents unless `agent_config_revisions` shows an edit that set it to `per_turn`. Each migrated agent gets an `agent.updated` activity entry with the old value (`actor_id = migration:native-warm-follow-up-default`). Creation records no revision, so a "Turn by turn" pick made at creation cannot be told apart from the old default. The product owner approved migrating those agents. Claude agents follow the default, which is `per_turn` today. - Restart chaos harness and TTFT driver: `--lifecycle per_turn|warm|default` (saved in the wave plan). `default` removes the catalog's pinned lifecycle, so a wave exercises the real default path. - Docs: `doc/DEVELOPING.md` "Runner lifecycle default", and the results in `doc/plans/2026-11-07-warm-follow-up-ttft.md`, which also documents baseline finding 4 (Claude's resumed turn-start gap is ACPX's per-turn process generation, not the provider). ## Verification - `server`: `native-lifecycle.test.ts` (new default cases: local Codex and OpenCode warm, Claude, remote, unknown target, unmeasured harness, managed Claude, admitted per-turn session, explicit choices, non-native adapter), `agent-runner-selection.test.ts`, `runtime-selection.test.ts` (335 pass). - `packages/db`: `native-warm-follow-up-default-migration.test.ts` on embedded Postgres. Default agents are cleared, the explicit edit is kept, other harnesses and legacy adapters are untouched, audit rows are written once, and a rerun is a no-op. Without the explicit-edit filter the test fails. `check:migrations` passes. - `codex-local` `build-config.test.ts` (65), `ui` `config-fields.test.tsx` (40), restart-chaos unit tests (134), `tsc --noEmit` for `server`. - `adapter-utils` `paperclip-runner-lifecycle-default.test.ts`: configuration writes and adapter conversion store no lifecycle for Codex, OpenCode and Claude, keep `per_turn` for the others, and preserve explicit choices. It fails without the fix. - End-to-end default check on this branch (`ttft-baseline.ts --lifecycle default`, codex and opencode, 2 samples): the agents read back with no stored lifecycle, and every follow-up reused the runner and provider session (no `runner.process.launch`). Follow-up TTFT was 3.6–4.8 s. This check found the per-write `per_turn` injection fixed here. - Restart chaos (codex and opencode, A1/B1/B5, K1/K2/K6, seed 4242), 8/8 PASS each with no open signatures: forced warm, forced per_turn, and `--lifecycle default` on this branch (agents created without a lifecycle). - `pnpm verify` selects broader CI (harness config is a global input), so required CI supplies the broad coverage. ## Risks - Behavior change: local Codex and OpenCode agents keep a runner and provider process for up to 5 minutes after a run. Instance sleep waits for that idle window. The process is reaped by the idle timer, by graceful shutdown, or by the #19879 reconnect grace if its controller dies. - Migration: agents whose "Turn by turn" was chosen at creation become Automatic. The activity entry records the old value; choosing "Turn by turn" restores it. - Previous-release story (`rules/upgrade-safe-run-state.mdc`): a task session keeps the lifecycle policy it was admitted with, so sessions saved before this change stay `per_turn`. New sessions get the default. No run, checkpoint or launch state changes shape. > 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 - Anthropic Claude Opus 5.5 (`claude-opus-5-5`) in Claude Code, with tool use (shell, file edit, test 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 searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [ ] All Paperclip CI gates are green - [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
56 lines
5.1 KiB
TypeScript
56 lines
5.1 KiB
TypeScript
import { describe, expect, it } from "vitest";
|
|
import { resolveHeartbeatNativeLifecyclePolicy, type NativeLifecyclePolicy } from "./native-lifecycle.js";
|
|
|
|
type Input = Parameters<typeof resolveHeartbeatNativeLifecyclePolicy>[0];
|
|
const warm: NativeLifecyclePolicy = { mode: "warm", idleTimeoutMs: 900_000 };
|
|
const perTurn: NativeLifecyclePolicy = { mode: "per_turn", idleTimeoutMs: null };
|
|
const base: Input = { adapterType: "paperclip_runner", backend: "codex_app_server", agentMode: "warm",
|
|
agentIdleTimeoutMs: 900_000, managedAiSelected: false, taskOwned: false };
|
|
|
|
describe("admitted native lifecycle policy", () => {
|
|
it.each<{ name: string; change: Partial<Input>; expected: NativeLifecyclePolicy }>([
|
|
{ name: "absent environment inherits agent warm", change: {}, expected: warm },
|
|
{ name: "inherited environment inherits agent warm", change: { environmentPolicy: null }, expected: warm },
|
|
{ name: "local selection inherits agent warm", change: { environmentPolicy: undefined }, expected: warm },
|
|
{ name: "explicit environment per-turn overrides agent warm", change: { environmentPolicy: perTurn }, expected: perTurn },
|
|
{ name: "explicit environment warm overrides agent per-turn", change: { agentMode: "per_turn", environmentPolicy: warm }, expected: warm },
|
|
{ name: "admitted per-turn stays pinned", change: { persistedPolicy: perTurn, environmentPolicy: warm }, expected: perTurn },
|
|
{ name: "admitted warm stays pinned", change: { persistedPolicy: warm, environmentPolicy: perTurn }, expected: warm },
|
|
{ name: "default agent is per-turn", change: { agentMode: undefined }, expected: perTurn },
|
|
{ name: "managed Codex supports warm", change: { managedAiSelected: true }, expected: warm },
|
|
{ name: "managed process provider without warm support is per-turn", change: { backend: "acpx_runtime", acpxAgent: "claude", managedAiSelected: true, environmentPolicy: warm }, expected: perTurn },
|
|
{ name: "unmanaged ACP retains its prior warm policy", change: { backend: "acpx_runtime", acpxAgent: "claude" }, expected: warm },
|
|
{ name: "Copilot API-key ownership supports warm", change: { backend: "acpx_runtime", acpxAgent: "copilot", managedAiSelected: true,
|
|
managedAiAttribution: { provider: "github", method: "api_key" } }, expected: warm },
|
|
{ name: "unqualified Copilot ownership remains per-turn", change: { backend: "acpx_runtime", acpxAgent: "copilot", managedAiSelected: true,
|
|
managedAiAttribution: { provider: "github", method: "subscription" } }, expected: perTurn },
|
|
{ name: "non-native adapter does not gain managed warm support", change: { adapterType: "codex_local", managedAiSelected: true }, expected: perTurn },
|
|
{ name: "task-owned provider keeps its existing ownership gate", change: { backend: "acpx_runtime", acpxAgent: "claude", managedAiSelected: true, taskOwned: true }, expected: warm },
|
|
...(["openai_dot_mcp", "grok_bot_mcp", "muse_external", "cursor_cloud_api"] as const).map(backend =>
|
|
({ name: `${backend} remains per-turn`, change: { backend, environmentPolicy: warm }, expected: perTurn })),
|
|
])("$name", ({ change, expected }) => {
|
|
expect(resolveHeartbeatNativeLifecyclePolicy({ ...base, ...change })).toEqual(expected);
|
|
});
|
|
});
|
|
|
|
describe("default lifecycle for an agent that never chose one", () => {
|
|
const defaultWarm: NativeLifecyclePolicy = { mode: "warm", idleTimeoutMs: 300_000 };
|
|
const unset: Input = { ...base, agentMode: undefined, agentIdleTimeoutMs: undefined, localTarget: true };
|
|
it.each<{ name: string; change: Partial<Input>; expected: NativeLifecyclePolicy }>([
|
|
{ name: "local Codex keeps a warm runner for the default idle window", change: {}, expected: defaultWarm },
|
|
{ name: "local OpenCode is warm", change: { backend: "opencode_server" }, expected: defaultWarm },
|
|
// ACPX relaunches its provider every follow-up turn, so warm buys Claude no TTFT.
|
|
{ name: "local Claude stays per-turn", change: { backend: "acpx_runtime", acpxAgent: "claude" }, expected: perTurn },
|
|
{ name: "an explicit per-turn choice is honored", change: { agentMode: "per_turn" }, expected: perTurn },
|
|
{ name: "an explicit warm idle window is honored", change: { agentMode: "warm", agentIdleTimeoutMs: 900_000 }, expected: warm },
|
|
{ name: "a remote target stays per-turn", change: { localTarget: false }, expected: perTurn },
|
|
{ name: "an unknown target stays per-turn", change: { localTarget: undefined }, expected: perTurn },
|
|
{ name: "an unmeasured ACP harness stays per-turn", change: { backend: "acpx_runtime", acpxAgent: "grok" }, expected: perTurn },
|
|
{ name: "managed Claude without warm support stays per-turn", change: { backend: "acpx_runtime", acpxAgent: "claude", managedAiSelected: true }, expected: perTurn },
|
|
{ name: "a session admitted per-turn before the default changed stays per-turn", change: { persistedPolicy: perTurn }, expected: perTurn },
|
|
{ name: "a non-native adapter stays per-turn", change: { adapterType: "codex_local" }, expected: perTurn },
|
|
])("$name", ({ change, expected }) => {
|
|
expect(resolveHeartbeatNativeLifecyclePolicy({ ...unset, ...change })).toEqual(expected);
|
|
});
|
|
});
|