mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-12 06:10:44 +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>
75 lines
4.0 KiB
TypeScript
75 lines
4.0 KiB
TypeScript
export type AgentRunnerChoice = "auto" | "paperclip" | "legacy";
|
|
export type AgentRunner = Exclude<AgentRunnerChoice, "auto">;
|
|
|
|
export interface AgentRunnerAvailability {
|
|
supportedRunners: AgentRunner[];
|
|
defaultRunner: AgentRunner;
|
|
}
|
|
|
|
export function paperclipRunnerProfileForHarness(harness: string): { provider: "codex" | "opencode" | "cursor_cloud" } | { provider: "acpx"; acpxAgent: "claude" | "pi" | "grok" } | undefined {
|
|
if (harness === "codex_local") return { provider: "codex" };
|
|
if (harness === "claude_local") return { provider: "acpx", acpxAgent: "claude" };
|
|
if (harness === "pi_local") return { provider: "acpx", acpxAgent: "pi" };
|
|
if (harness === "grok_local") return { provider: "acpx", acpxAgent: "grok" };
|
|
if (harness === "opencode_local") return { provider: "opencode" };
|
|
if (harness === "cursor_cloud") return { provider: "cursor_cloud" };
|
|
return undefined;
|
|
}
|
|
|
|
/**
|
|
* The lifecycle a new native agent stores. Codex, OpenCode and Claude store
|
|
* none, so the server applies the product default (warm on a local target for
|
|
* Codex and OpenCode). Other harnesses keep an explicit per_turn.
|
|
*/
|
|
export function paperclipRunnerCreationLifecycle(
|
|
profile: NonNullable<ReturnType<typeof paperclipRunnerProfileForHarness>>,
|
|
): { lifecycleMode?: "per_turn" } {
|
|
return profile.provider === "codex" || profile.provider === "opencode"
|
|
|| (profile.provider === "acpx" && profile.acpxAgent === "claude")
|
|
? {} : { lifecycleMode: "per_turn" };
|
|
}
|
|
|
|
export const PAPERCLIP_RUNNER_MINIMUM_GLIBC_VERSION = "2.39";
|
|
|
|
function supportsLinuxLibc(libc?: "glibc" | "musl" | "unknown", version?: string): boolean {
|
|
if (libc !== undefined && libc !== "glibc") return false;
|
|
if (version === undefined) return true;
|
|
const match = typeof version === "string" ? version.trim().match(/^(?:glibc\s+)?(\d+)\.(\d+)(?:\.\d+)?$/) : null;
|
|
if (!match) return false;
|
|
const major = Number(match[1]), minor = Number(match[2]);
|
|
if (!Number.isSafeInteger(major) || !Number.isSafeInteger(minor)) return false;
|
|
const [requiredMajor, requiredMinor] = PAPERCLIP_RUNNER_MINIMUM_GLIBC_VERSION.split(".").map(Number);
|
|
return major > requiredMajor! || (major === requiredMajor && minor >= requiredMinor!);
|
|
}
|
|
|
|
export function paperclipRunnerSupportsPlatform(harness: string, platform: string, architecture: string, libc?: "glibc" | "musl" | "unknown", glibcVersion?: string): boolean {
|
|
return !!paperclipRunnerProfileForHarness(harness)
|
|
&& (harness !== "grok_local" || (platform === "linux" && architecture === "x64") || (platform === "darwin" && architecture === "arm64"))
|
|
&& !(["opencode_local", "pi_local"].includes(harness) && platform === "linux" && architecture === "arm64")
|
|
&& ((platform === "linux" && supportsLinuxLibc(libc, glibcVersion) && (architecture === "x64" || architecture === "arm64"))
|
|
|| (platform === "darwin" && (architecture === "arm64" || architecture === "x64")));
|
|
}
|
|
|
|
export function agentHarnessType(adapterType: string, config: Record<string, unknown> = {}): string {
|
|
if (adapterType !== "paperclip_runner") return adapterType;
|
|
if (config.provider === undefined || config.provider === "codex") return "codex_local";
|
|
if (config.provider === "opencode") return "opencode_local";
|
|
if (config.provider === "acpx") {
|
|
const agent = config.acpxAgent ?? "claude";
|
|
return ({ codex: "codex_local", claude: "claude_local", grok: "grok_local", cursor: "cursor", pi: "pi_local", kimi: "kimi_local", antigravity: "antigravity_runtime" } as Record<string, string>)[String(agent)] ?? `acpx:${String(agent)}`;
|
|
}
|
|
return String(config.provider);
|
|
}
|
|
|
|
export function agentRunner(adapterType: string): AgentRunner {
|
|
return adapterType === "paperclip_runner" ? "paperclip" : "legacy";
|
|
}
|
|
|
|
/** Stable configuration group across native and legacy execution backends. */
|
|
export function agentRuntimeSettingsHarness(adapterType: string, config: Record<string, unknown> = {}): string {
|
|
const harness = agentHarnessType(adapterType, config);
|
|
if (harness === "acpx:copilot") return "copilot_runtime";
|
|
if (harness === "cursor") return "cursor_local";
|
|
return harness;
|
|
}
|