mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-09 16:35:27 +02:00
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work > - A core part of that experience is watching active agent runs without dropping into raw logs first > - Local and sandbox-backed adapters already record useful run output, progress, and tool activity > - But active issue threads could sit visually stale while the agent was syncing workspaces, tailing sandbox output, or emitting incremental tool-call updates > - Operators need timely, human-readable progress while preserving the raw transcript underneath > - This pull request streams sandbox run-log progress into runtime status, keeps visible issue threads refreshed, and folds repeated ACPX tool updates into stable transcript cards > - The benefit is that long-running agent work becomes easier to supervise without changing the task/comment control-plane model ## Linked Issues or Issue Description No public GitHub issue exists for this exact change. Problem/motivation: - During long-running sandboxed agent work, the issue UI can appear idle even though the agent is actively syncing, running tools, or producing incremental output. - Operators need realtime feedback at the issue-thread layer, not only after opening raw logs or waiting for the final heartbeat result. - Related public context: #1808 previously added live-run status dots to Projects; #4362 touches heartbeat wakeup behavior but is not a duplicate of this runtime/UI feedback change. ## What Changed - Added sandbox run-log streaming support and defaulted sandbox-capable local adapters into the richer live-feedback path. - Surfaced environment/sandbox sync progress through heartbeat runtime status with bounded, redacted snippets. - Added live issue-thread cache patching so visible active runs update as progress events arrive. - Folded repeated ACPX `tool_call` updates into one transcript card instead of stacking duplicate cards. - Updated adapter docs and added focused regression coverage for sandbox log streaming, runtime status, ACPX parsing, live updates, transcript rendering, and issue chat messages. ## Verification - `pnpm install --frozen-lockfile` - `pnpm exec vitest run ui/src/context/LiveUpdatesProvider.test.ts` - `pnpm exec vitest run server/src/services/heartbeat-run-runtime-status.test.ts server/src/__tests__/heartbeat-runtime-state.test.ts ui/src/context/LiveUpdatesProvider.test.ts` - `pnpm exec vitest run packages/adapter-utils/src/execution-target-sandbox.test.ts packages/adapter-utils/src/sandbox-managed-runtime.test.ts server/src/services/heartbeat-run-runtime-status.test.ts server/src/__tests__/agent-live-run-routes.test.ts server/src/__tests__/heartbeat-runtime-state.test.ts packages/adapters/acpx-local/src/ui/parse-stdout.test.ts ui/src/context/LiveUpdatesProvider.test.ts ui/src/components/transcript/RunTranscriptView.test.tsx ui/src/lib/issue-chat-messages.test.ts ui/src/components/IssueChatThread.test.tsx` - GitHub PR workflow on head `8397953e7b41ccd42e5d9457ee7e4dfb996e4ec5`: `verify`, build, typecheck/release-registry, e2e, general shards, serialized server shards, and canary dry run passed. - Greptile Review on head `8397953e7b41ccd42e5d9457ee7e4dfb996e4ec5`: Confidence Score 5/5, no unresolved review threads. ## Risks - Live issue-thread cache patching could miss an edge case for a route shape not covered by tests. - Surfacing active-run snippets needs continued care around redaction; this PR keeps snippets bounded and adds redaction-focused coverage. - More frequent active-run UI refreshes could expose performance issues on very large issue threads, though updates are scoped to visible run/query caches. ## Model Used OpenAI GPT-5 via Codex, operating as a tool-enabled coding agent with shell, git, and repository-editing capabilities. Context window size is not exposed in this runtime. ## 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 - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge Co-authored-by: Paperclip <noreply@paperclip.ing>
171 lines
6.1 KiB
TypeScript
171 lines
6.1 KiB
TypeScript
// Shared, throttled progress reporting for execution-target sync/restore.
|
|
//
|
|
// Transports (sandbox / SSH) own the byte counting and call `report()` as bytes
|
|
// move; orchestrators own the per-phase label and direction. The reporter
|
|
// throttles emits so a long transfer doesn't flood the log: a line is emitted
|
|
// only when the percentage crosses a step boundary (default every 10%) or once
|
|
// at least `minIntervalMs` has elapsed since the last emit. The terminal
|
|
// completion line is always emitted via `complete()` (or when `report()` reaches
|
|
// the known total).
|
|
|
|
/** A sink for fully-formatted progress lines (newline included). */
|
|
export type RuntimeProgressSink = (line: string) => void | Promise<void>;
|
|
|
|
export type RuntimeProgressPhase =
|
|
| "Syncing"
|
|
| "Restoring"
|
|
| "Importing git history"
|
|
| "Exporting git history";
|
|
|
|
export type RuntimeProgressDirection = "to" | "from";
|
|
|
|
export type RuntimeProgressTarget = "sandbox" | "ssh";
|
|
|
|
export type RuntimeStatusPhase =
|
|
| "git_sync"
|
|
| "config_sync"
|
|
| "adapter_startup"
|
|
| "restore"
|
|
| "export"
|
|
| "finalize";
|
|
|
|
export interface RuntimeStatusUpdate {
|
|
phase: RuntimeStatusPhase;
|
|
message: string;
|
|
currentToolName?: string | null;
|
|
lastAssistantSnippet?: string | null;
|
|
lastEventAt?: Date | string | null;
|
|
}
|
|
|
|
export type RuntimeStatusSink = (update: RuntimeStatusUpdate) => void | Promise<void>;
|
|
|
|
export interface RuntimeProgressReporterOptions {
|
|
sink: RuntimeProgressSink;
|
|
phase: RuntimeProgressPhase;
|
|
/** Optional per-phase label, e.g. "workspace" or an asset key. */
|
|
label?: string;
|
|
direction: RuntimeProgressDirection;
|
|
target: RuntimeProgressTarget;
|
|
/** Emit when the percentage crosses this step. Default 10. */
|
|
stepPercent?: number;
|
|
/** Emit when at least this many ms have elapsed since the last emit. Default 2000. */
|
|
minIntervalMs?: number;
|
|
/** Injectable clock for deterministic tests. Default `Date.now`. */
|
|
now?: () => number;
|
|
}
|
|
|
|
export interface RuntimeProgressReporter {
|
|
/**
|
|
* Report progress. Throttled: only emits on a step crossing or after
|
|
* `minIntervalMs`. When `totalBytes` is known and `doneBytes` reaches it, the
|
|
* terminal 100% line is emitted and the reporter is marked complete.
|
|
*/
|
|
report(doneBytes: number, totalBytes: number | null): Promise<void>;
|
|
/**
|
|
* Emit the terminal completion line if it hasn't been emitted yet. Idempotent.
|
|
*/
|
|
complete(doneBytes?: number, totalBytes?: number | null): Promise<void>;
|
|
/**
|
|
* Emit a terminal failure line if no terminal line has been emitted yet, so a
|
|
* failed transfer leaves an explicit marker instead of a dangling percentage.
|
|
* Idempotent and mutually exclusive with `complete()`.
|
|
*/
|
|
fail(doneBytes?: number, totalBytes?: number | null): Promise<void>;
|
|
}
|
|
|
|
const BYTES_PER_MB = 1024 * 1024;
|
|
|
|
function formatMb(bytes: number): string {
|
|
return (Math.max(0, bytes) / BYTES_PER_MB).toFixed(1);
|
|
}
|
|
|
|
function clampPercent(value: number): number {
|
|
if (!Number.isFinite(value)) return 0;
|
|
return Math.min(100, Math.max(0, Math.round(value)));
|
|
}
|
|
|
|
export function createRuntimeProgressReporter(
|
|
options: RuntimeProgressReporterOptions,
|
|
): RuntimeProgressReporter {
|
|
const stepPercent = options.stepPercent && options.stepPercent > 0 ? options.stepPercent : 10;
|
|
const minIntervalMs =
|
|
options.minIntervalMs && options.minIntervalMs > 0 ? options.minIntervalMs : 2000;
|
|
const now = options.now ?? Date.now;
|
|
const prefix = `[paperclip] ${options.phase}${options.label ? ` ${options.label}` : ""} ${options.direction} ${options.target}`;
|
|
|
|
let lastEmitAt: number | null = null;
|
|
let lastStep = -1;
|
|
let lastDoneBytes = 0;
|
|
let lastTotalBytes: number | null = null;
|
|
let completed = false;
|
|
|
|
function buildLine(doneBytes: number, totalBytes: number | null): string {
|
|
if (totalBytes != null && totalBytes > 0) {
|
|
const pct = clampPercent((doneBytes / totalBytes) * 100);
|
|
return `${prefix}: ${pct}% (${formatMb(doneBytes)}/${formatMb(totalBytes)} MB)\n`;
|
|
}
|
|
return `${prefix}: ${formatMb(doneBytes)} MB\n`;
|
|
}
|
|
|
|
function buildFailLine(doneBytes: number, totalBytes: number | null): string {
|
|
if (totalBytes != null && totalBytes > 0) {
|
|
const pct = clampPercent((doneBytes / totalBytes) * 100);
|
|
return `${prefix}: failed at ${pct}% (${formatMb(doneBytes)}/${formatMb(totalBytes)} MB)\n`;
|
|
}
|
|
return `${prefix}: failed after ${formatMb(doneBytes)} MB\n`;
|
|
}
|
|
|
|
async function emit(doneBytes: number, totalBytes: number | null): Promise<void> {
|
|
lastEmitAt = now();
|
|
if (totalBytes != null && totalBytes > 0) {
|
|
lastStep = Math.floor(((doneBytes / totalBytes) * 100) / stepPercent);
|
|
}
|
|
await options.sink(buildLine(doneBytes, totalBytes));
|
|
}
|
|
|
|
return {
|
|
async report(doneBytes, totalBytes) {
|
|
lastDoneBytes = doneBytes;
|
|
lastTotalBytes = totalBytes;
|
|
if (completed) return;
|
|
|
|
const elapsedOk = lastEmitAt == null || now() - lastEmitAt >= minIntervalMs;
|
|
|
|
if (totalBytes != null && totalBytes > 0) {
|
|
const terminal = doneBytes >= totalBytes;
|
|
const step = Math.floor(((doneBytes / totalBytes) * 100) / stepPercent);
|
|
const stepOk = step > lastStep;
|
|
if (terminal || stepOk || elapsedOk) {
|
|
await emit(doneBytes, totalBytes);
|
|
}
|
|
if (terminal) completed = true;
|
|
return;
|
|
}
|
|
|
|
// Unknown total: no step boundaries, throttle purely on elapsed time.
|
|
if (elapsedOk) {
|
|
await emit(doneBytes, totalBytes);
|
|
}
|
|
},
|
|
async complete(doneBytes, totalBytes) {
|
|
if (completed) return;
|
|
completed = true;
|
|
const total = totalBytes !== undefined ? totalBytes : lastTotalBytes;
|
|
const done =
|
|
doneBytes !== undefined
|
|
? doneBytes
|
|
: total != null && total > 0
|
|
? total
|
|
: lastDoneBytes;
|
|
await options.sink(buildLine(done, total));
|
|
},
|
|
async fail(doneBytes, totalBytes) {
|
|
if (completed) return;
|
|
completed = true;
|
|
const total = totalBytes !== undefined ? totalBytes : lastTotalBytes;
|
|
const done = doneBytes !== undefined ? doneBytes : lastDoneBytes;
|
|
await options.sink(buildFailLine(done, total));
|
|
},
|
|
};
|
|
}
|