@bastani/atomic 0.9.12 → 0.9.13-alpha.1

package/docs/workflows.md

@@ -117,7 +117,7 @@ Named workflow runs execute in the background. By default, after launch expect a
 
 For a request with several implementation items, do not turn list order into one serial workflow by default. Triage dependencies first, then launch independent items as a bounded wave of separate top-level runs; see [Task queues and software factories](#task-queues-and-software-factories).
 
-While a workflow is running, the visible below-editor `BACKGROUND` panel advances its elapsed label every second from the moment the run starts; it does not require opening or switching to the orchestrator. Updates repaint the existing mounted panel in place, paused timers stay frozen, the panel renders every qualifying top-level run, and terminal or quit cards retain their brief recent-run expiry. Quit cards remain resumable and discoverable with `/workflow status` after they leave the panel.
+While a workflow is running, the visible below-editor `BACKGROUND` panel advances its elapsed label every second from the moment the run starts; it does not require opening or switching to the orchestrator. Updates repaint the existing mounted panel in place, paused timers stay frozen, the panel renders every qualifying top-level run, and terminal or quit cards retain their brief recent-run expiry. Quit cards remain resumable and discoverable with `/workflow status` after they leave the panel. A run waiting for human input uses the blue `？` indicator in the BACKGROUND panel, the `/workflow connect` picker, and the `/workflow status` listing; answering or cancelling the prompt restores the run's current indicator.
 
 ### Workflow run identifiers and the BACKGROUND panel
 
@@ -2295,10 +2295,18 @@ readonly fallbackModels?: readonly string[];
 readonly fallbackThinkingLevels?: readonly string[];
 ```
 
-`fallbackModels` tries the primary first, each fallback in order, and then the current Atomic-selected model when available. It advances for rate limits and quota or usage-limit exhaustion, including messages such as `The usage limit has been reached` and codes such as `usage_limit_reached` or `insufficient_quota`. Auth/provider outages, unavailable models, network timeouts, generic transport errors such as `Connection error.` or `fetch failed`, and 5xx responses also advance the chain.
+`fallbackModels` tries the primary first, each fallback in order, and then the current Atomic-selected model when available. It advances for rate limits and quota or usage-limit exhaustion, including messages such as `The usage limit has been reached` and codes such as `usage_limit_reached` or `insufficient_quota`. Auth/provider outages, unavailable models, network timeouts, generic transport errors such as `Connection error.` or `fetch failed`, and 5xx responses also advance the chain. A thrown failure that another request to the same candidate can plausibly repair — a rate limit, provider outage, network timeout, or transport error — is retried on that candidate with exponential backoff from `settings.retry` before the chain advances; `retry.enabled: false` keeps immediate advancement. A failure the same candidate has already definitively rejected — a rejected credential, an unavailable model, or an incompatible request — skips the same-candidate retry and advances immediately, exactly as in main chat. A same-candidate retry resumes the existing turn when the stage transcript still ends in a message the agent can continue from, and otherwise re-sends the stage prompt; either way the failed provider error is dropped from the live transcript and the prompt is delivered exactly once.
 
 Request/context incompatibility also advances it, including HTTP 400/413/422 bad, unprocessable, or payload-too-large requests; unsupported tools or parameters; context-length or context-window overflow; and `too large`, `invalid_request`, or `bad_request` errors. This lets the chain reach the current selected user model when no configured candidate can serve the request.
 
+A context overflow that the stage session's compaction has already failed to resolve is terminal for its candidate: it skips the same-candidate retry, because re-sending an identical request cannot fit a context compaction could not shrink, and advances straight to the next candidate.
+
+The chain also covers session creation. A stage session created eagerly — by `ctx.__ensureSession()`, an eager stage call, or a control attach — retries transient creation failures on its candidate under `settings.retry` and then walks to the next configured candidate, so a provider that cannot even open a session does not strand the stage. Creation failures that same-candidate retry cannot repair — auth, unavailable model, incompatible request — advance immediately. A creation failure that exhausts the whole chain is not cached: the next call starts a fresh attempt.
+
+That walk runs behind a single creation gate. A concurrent `ctx.__ensureSession()` or a first `ctx.prompt()` joins the creation already in flight rather than starting a second walk, so the stage never has two live sessions competing for the same generation.
+
+Controlled pauses are honored throughout. A pause that starts and finishes while a session is still being created keeps its replacement objective, which the next prompt sends exactly once; a pause during a same-candidate continuation is settled as a pause rather than a model failure, so resuming recovers the stage instead of spending a fallback candidate.
+
 Workflow-code errors, tool failures, validation failures, refusals, content-filter or safety blocks, cancellations, and task failures do not advance the chain. A reattached finished stage starts on the model that last succeeded; if that model fails retryably, the full chain restarts from the primary.
 
 ### `thinkingLevel` (deprecated)
@@ -3112,7 +3120,15 @@ The visible card preserves the lifecycle custom type, raw notice text, exact det
 
 When an active recoverable block is resumed in-process, Atomic dispatches a fresh-ID continuation that replays the source's completed stages and re-runs the failed one. The durable source is left untouched (stays `blocked`/resumable) so it remains discoverable and recoverable — including a zero-checkpoint first-stage block — if the process dies before the continuation settles; the local source snapshot is killed so the same session will not re-resume it. A process-local claim prevents a concurrent same-session double-dispatch.
 
-Configure lifecycle behavior with `workflowNotifications.enabled` (default `true`) and `workflowNotifications.notifyOn` (default `["completed", "failed", "blocked", "awaiting_input"]`).
+Deliberate control actions on a top-level run report themselves too. `/workflow <name>` emits a `WORKFLOW STARTED` notice (`▶`), `/workflow pause` a `WORKFLOW PAUSED` notice (`⏸`, warning tone), `/workflow quit` a `WORKFLOW QUIT` notice (`⏹`, warning tone, carrying a `resumable` field), and `/workflow resume` a `WORKFLOW RESUMED` notice (`▶`). All four travel the same steer delivery, capped-backoff retry, and notice-card path as the failure notice. The paused and quit text states that the stop was deliberate and user-requested and tells the model not to resume the run or take the work over unless asked, with `/workflow resume <run-id>` as the card hint; the resumed text does not, because the run is progressing again.
+
+**Only user actions notify.** The equivalent `workflow({ action: "run" | "pause" | "quit" | "resume" })` tool calls stay silent: the tool result already tells the agent what it just did, and a second steer would spend a turn repeating it. `/workflow interrupt` raises no notice at all. Engine-internal transitions are silent for the same reason a notice must name an actor to exist — answering a human-in-the-loop prompt resumes the run internally, and reporting that would both flood the chat and defeat the deliberate decision that `awaiting_input` never wakes the model.
+
+**Two attributions.** *Origin* is who launched the run and renders on every kind as "which you started" or "which the user started"; it is set once at dispatch, persisted through session restore and durable resume, and inherited by a continuation from the run it continues. *Actor* is who performed this one event and renders as "The user paused" or "You paused". They differ routinely — the agent starts a run and the user quits it. A run with no recorded origin, including a legacy or restored snapshot, omits the clause entirely rather than guessing.
+
+**One notice per request.** A whole-run pause or resume reports at run scope. A stage-scoped `/workflow pause <run> <stage>` that leaves other stages running reports at stage scope, and one that stops the last active stage reports the run instead — never a stage card and a run card for the same request. A quit reports only the quit, never the pause it publishes on the way. Because control actions are reversible, these notices are deduplicated by run id *and* the occurrence timestamp, so pause → resume → pause → resume emits four notices while repeated snapshot invalidations at one unchanged state emit one. Resuming reports a resume and never a start, whoever asked for it — a resumed run re-enters the dispatch path, so keying that on the resume rather than on the requester is what stops an agent-requested resume of a user-started run from being announced as a fresh launch. Resuming a failed or blocked run launches a continuation under a fresh run id, and its notice names both ("run 4d7e, continuing run 8c31"); resuming a quit run reuses the original workflow id so durable checkpoints replay, so that notice names the one id. A run that is already started, paused, or quit when notifications install — restore, replay, `/reload`, or a session-preserving reinstall — is seeded as delivered and stays silent, and nested `ctx.workflow(...)` child runs never notify at top level.
+
+Configure lifecycle behavior with `workflowNotifications.enabled` (default `true`) and `workflowNotifications.notifyOn` (default `["started", "completed", "failed", "blocked", "awaiting_input", "paused", "quit", "resumed"]`). A config that pins `notifyOn` explicitly keeps exactly the kinds it lists, so `notifyOn: ["failed"]` suppresses every control notice.
 
 Human input is runtime-only: call `ctx.ui.input`, `ctx.ui.confirm`, `ctx.ui.select`, `ctx.ui.editor`, or `ctx.ui.custom<T>` when the workflow needs a decision. No builder-level declaration is required or supported.
 
@@ -3407,7 +3423,7 @@ Example config:
   "resumeInFlight": "ask",
   "workflowNotifications": {
     "enabled": true,
-    "notifyOn": ["completed", "failed", "blocked", "awaiting_input"]
+    "notifyOn": ["started", "completed", "failed", "blocked", "awaiting_input", "paused", "quit", "resumed"]
   },
   "worktree": {
     "symlinkDirectories": ["node_modules"]
@@ -3425,7 +3441,7 @@ Runtime config defaults:
 | `statusFile` | `false` | Write a derived status file; defaults under `.atomic/workflows/status.json` when enabled |
 | `resumeInFlight` | `"ask"` | Behavior when discovering resumable in-flight work |
 | `workflowNotifications.enabled` | `true` | Emit workflow lifecycle notices into the active main chat |
-| `workflowNotifications.notifyOn` | `["completed", "failed", "blocked", "awaiting_input"]` | Lifecycle states to track; terminal `completed`/`failed`/`blocked` outcomes and active recoverable blocks create main-chat notices, while `awaiting_input` is tracked for dedupe/restore without waking the main agent |
+| `workflowNotifications.notifyOn` | `["started", "completed", "failed", "blocked", "awaiting_input", "paused", "quit", "resumed"]` | Lifecycle states to track; terminal `completed`/`failed`/`blocked` outcomes, active recoverable blocks, and the user-initiated `started`/`paused`/`quit`/`resumed` control actions on a top-level run create main-chat notices, while `awaiting_input` is tracked for dedupe/restore without waking the main agent |
 | `worktree.symlinkDirectories` | `["node_modules"]` | Main-root directories symlinked into each runner-managed temporary worktree during post-creation setup |
 
 Invalid JSON or invalid shapes produce `CONFIG_INVALID` diagnostics. Missing config files are ignored.

package/examples/extensions/gondolin/package-lock.json

@@ -173,9 +173,9 @@
 			"license": "Unlicense"
 		},
 		"node_modules/undici": {
-			"version": "6.27.0",
-			"resolved": "https://registry.npmjs.org/undici/-/undici-6.27.0.tgz",
-			"integrity": "sha512-YmfV3YnEDzXRC5lZ2jWtWWHKGUm1zIt8AhesR1tens+HTNv+YZlN/dp6G727LOvMJ8xjP9Be7Y2Sdr96LDm+pg==",
+			"version": "6.28.0",
+			"resolved": "https://registry.npmjs.org/undici/-/undici-6.28.0.tgz",
+			"integrity": "sha512-LIY910g9TI13YS95lrMFrs8Rm/u/irgHeTWoKCoteeJ04CUJ92eEfj0rVn+7VKMPBpUPiUoBKfhNyLI23EE/KA==",
 			"license": "MIT",
 			"engines": {
 				"node": ">=18.17"

package/npm-shrinkwrap.json

@@ -1,15 +1,15 @@
 {
 	"name": "@bastani/atomic",
-	"version": "0.9.12",
+	"version": "0.9.13-alpha.1",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "@bastani/atomic",
-			"version": "0.9.12",
+			"version": "0.9.13-alpha.1",
 			"license": "MIT",
 			"dependencies": {
-				"@bastani/atomic-natives": "0.9.12",
+				"@bastani/atomic-natives": "0.9.13-alpha.1",
 				"@dbos-inc/dbos-sdk": "4.24.16",
 				"@earendil-works/pi-agent-core": "^0.83.0",
 				"@earendil-works/pi-ai": "^0.83.0",
@@ -515,18 +515,18 @@
 			}
 		},
 		"node_modules/@bastani/atomic-natives": {
-			"version": "0.9.12",
-			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives/-/atomic-natives-0.9.12.tgz",
+			"version": "0.9.13-alpha.1",
+			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives/-/atomic-natives-0.9.13-alpha.1.tgz",
 			"license": "MIT",
 			"optionalDependencies": {
-				"@bastani/atomic-natives-darwin-arm64": "0.9.12",
-				"@bastani/atomic-natives-darwin-x64": "0.9.12",
-				"@bastani/atomic-natives-linux-arm64-gnu": "0.9.12",
-				"@bastani/atomic-natives-linux-arm64-musl": "0.9.12",
-				"@bastani/atomic-natives-linux-x64-gnu": "0.9.12",
-				"@bastani/atomic-natives-linux-x64-musl": "0.9.12",
-				"@bastani/atomic-natives-win32-arm64-msvc": "0.9.12",
-				"@bastani/atomic-natives-win32-x64-msvc": "0.9.12"
+				"@bastani/atomic-natives-darwin-arm64": "0.9.13-alpha.1",
+				"@bastani/atomic-natives-darwin-x64": "0.9.13-alpha.1",
+				"@bastani/atomic-natives-linux-arm64-gnu": "0.9.13-alpha.1",
+				"@bastani/atomic-natives-linux-arm64-musl": "0.9.13-alpha.1",
+				"@bastani/atomic-natives-linux-x64-gnu": "0.9.13-alpha.1",
+				"@bastani/atomic-natives-linux-x64-musl": "0.9.13-alpha.1",
+				"@bastani/atomic-natives-win32-arm64-msvc": "0.9.13-alpha.1",
+				"@bastani/atomic-natives-win32-x64-msvc": "0.9.13-alpha.1"
 			},
 			"engines": {
 				"bun": ">=1.3.14",
@@ -534,8 +534,8 @@
 			}
 		},
 		"node_modules/@bastani/atomic-natives-darwin-arm64": {
-			"version": "0.9.12",
-			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-darwin-arm64/-/atomic-natives-darwin-arm64-0.9.12.tgz",
+			"version": "0.9.13-alpha.1",
+			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-darwin-arm64/-/atomic-natives-darwin-arm64-0.9.13-alpha.1.tgz",
 			"license": "MIT",
 			"os": [
 				"darwin"
@@ -546,8 +546,8 @@
 			"optional": true
 		},
 		"node_modules/@bastani/atomic-natives-darwin-x64": {
-			"version": "0.9.12",
-			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-darwin-x64/-/atomic-natives-darwin-x64-0.9.12.tgz",
+			"version": "0.9.13-alpha.1",
+			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-darwin-x64/-/atomic-natives-darwin-x64-0.9.13-alpha.1.tgz",
 			"license": "MIT",
 			"os": [
 				"darwin"
@@ -558,8 +558,8 @@
 			"optional": true
 		},
 		"node_modules/@bastani/atomic-natives-linux-arm64-gnu": {
-			"version": "0.9.12",
-			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-linux-arm64-gnu/-/atomic-natives-linux-arm64-gnu-0.9.12.tgz",
+			"version": "0.9.13-alpha.1",
+			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-linux-arm64-gnu/-/atomic-natives-linux-arm64-gnu-0.9.13-alpha.1.tgz",
 			"license": "MIT",
 			"os": [
 				"linux"
@@ -573,8 +573,8 @@
 			"optional": true
 		},
 		"node_modules/@bastani/atomic-natives-linux-arm64-musl": {
-			"version": "0.9.12",
-			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-linux-arm64-musl/-/atomic-natives-linux-arm64-musl-0.9.12.tgz",
+			"version": "0.9.13-alpha.1",
+			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-linux-arm64-musl/-/atomic-natives-linux-arm64-musl-0.9.13-alpha.1.tgz",
 			"license": "MIT",
 			"os": [
 				"linux"
@@ -588,8 +588,8 @@
 			"optional": true
 		},
 		"node_modules/@bastani/atomic-natives-linux-x64-gnu": {
-			"version": "0.9.12",
-			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-linux-x64-gnu/-/atomic-natives-linux-x64-gnu-0.9.12.tgz",
+			"version": "0.9.13-alpha.1",
+			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-linux-x64-gnu/-/atomic-natives-linux-x64-gnu-0.9.13-alpha.1.tgz",
 			"license": "MIT",
 			"os": [
 				"linux"
@@ -603,8 +603,8 @@
 			"optional": true
 		},
 		"node_modules/@bastani/atomic-natives-linux-x64-musl": {
-			"version": "0.9.12",
-			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-linux-x64-musl/-/atomic-natives-linux-x64-musl-0.9.12.tgz",
+			"version": "0.9.13-alpha.1",
+			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-linux-x64-musl/-/atomic-natives-linux-x64-musl-0.9.13-alpha.1.tgz",
 			"license": "MIT",
 			"os": [
 				"linux"
@@ -618,8 +618,8 @@
 			"optional": true
 		},
 		"node_modules/@bastani/atomic-natives-win32-arm64-msvc": {
-			"version": "0.9.12",
-			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-win32-arm64-msvc/-/atomic-natives-win32-arm64-msvc-0.9.12.tgz",
+			"version": "0.9.13-alpha.1",
+			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-win32-arm64-msvc/-/atomic-natives-win32-arm64-msvc-0.9.13-alpha.1.tgz",
 			"license": "MIT",
 			"os": [
 				"win32"
@@ -630,8 +630,8 @@
 			"optional": true
 		},
 		"node_modules/@bastani/atomic-natives-win32-x64-msvc": {
-			"version": "0.9.12",
-			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-win32-x64-msvc/-/atomic-natives-win32-x64-msvc-0.9.12.tgz",
+			"version": "0.9.13-alpha.1",
+			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-win32-x64-msvc/-/atomic-natives-win32-x64-msvc-0.9.13-alpha.1.tgz",
 			"license": "MIT",
 			"os": [
 				"win32"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/atomic",
-  "version": "0.9.12",
+  "version": "0.9.13-alpha.1",
   "description": "Atomic coding agent CLI with read, bash, edit, write tools and session management",
   "type": "module",
   "atomicConfig": {
@@ -78,7 +78,7 @@
     "prepublishOnly": "bun run clean && bun run build && bun run shrinkwrap"
   },
   "dependencies": {
-    "@bastani/atomic-natives": "0.9.12",
+    "@bastani/atomic-natives": "0.9.13-alpha.1",
     "@dbos-inc/dbos-sdk": "4.24.16",
     "@earendil-works/pi-agent-core": "^0.83.0",
     "@earendil-works/pi-ai": "^0.83.0",

package/dist/builtin/subagents/src/runs/background/async-event-journal.ts

@@ -1,112 +0,0 @@
-import * as fs from "node:fs";
-import { acquireEventWriter } from "../../shared/event-jsonl-writer.ts";
-import type { DrainableSource, JsonlWriteStream } from "../../shared/jsonl-writer.ts";
-
-const DEFAULT_TELEMETRY_BYTES = 512 * 1024;
-const CAPPED_CHILD_EVENT_TYPES = new Set([
-	"message_update",
-	"tool_execution_update",
-	"subagent.child.stdout",
-	"subagent.child.stderr",
-]);
-
-interface ChildEventJournalContext {
-	runId: string;
-	stepIndex?: number;
-	agent: string;
-}
-
-interface ChildEventJournalDeps {
-	maxTelemetryBytes?: number;
-	createWriteStream?: (filePath: string) => JsonlWriteStream;
-	now?: () => number;
-}
-
-export interface ChildEventJournal {
-	append(event: Record<string, unknown>): void;
-	close(): Promise<void>;
-}
-
-function withoutKey(record: Record<string, unknown>, key: string): Record<string, unknown> {
-	const { [key]: _removed, ...rest } = record;
-	return rest;
-}
-
-/** Remove cumulative streaming snapshots while retaining compact delta metadata. */
-export function sanitizeChildEvent(event: Record<string, unknown>): Record<string, unknown> {
-	let sanitized = event;
-	if (event.type === "message_update") {
-		sanitized = withoutKey(event, "message");
-		const assistantEvent = sanitized.assistantMessageEvent;
-		if (assistantEvent && typeof assistantEvent === "object" && !Array.isArray(assistantEvent)) {
-			let compactEvent = withoutKey(withoutKey(assistantEvent as Record<string, unknown>, "partial"), "message");
-			if (!("delta" in compactEvent)) {
-				compactEvent = withoutKey(withoutKey(compactEvent, "content"), "toolCall");
-			}
-			sanitized = { ...sanitized, assistantMessageEvent: compactEvent };
-		}
-	}
-	if (event.type === "message_start") sanitized = withoutKey(sanitized, "message");
-	if (event.type === "tool_execution_update") sanitized = withoutKey(sanitized, "partialResult");
-	if (event.type === "turn_end") sanitized = withoutKey(sanitized, "message");
-	if (event.type === "agent_end") sanitized = withoutKey(sanitized, "messages");
-	return sanitized;
-}
-
-export function createChildEventJournal(
-	filePath: string | undefined,
-	source: DrainableSource,
-	context: ChildEventJournalContext,
-	deps: ChildEventJournalDeps = {},
-): ChildEventJournal {
-	if (!filePath) return { append() {}, async close() {} };
-	const createStream = deps.createWriteStream ?? ((target: string) => fs.createWriteStream(target, { flags: "a" }));
-	const writer = acquireEventWriter(filePath, source, createStream);
-	if (!writer) return { append() {}, async close() {} };
-	const maxTelemetryBytes = deps.maxTelemetryBytes ?? DEFAULT_TELEMETRY_BYTES;
-	const now = deps.now ?? Date.now;
-	let closed = false;
-	let closePromise: Promise<void> | undefined;
-	const write = (record: Record<string, unknown>): void => writer.writeLine(JSON.stringify(record));
-
-	const enrich = (event: Record<string, unknown>): Record<string, unknown> => ({
-		...event,
-		subagentSource: "child",
-		subagentRunId: context.runId,
-		subagentStepIndex: context.stepIndex,
-		subagentAgent: context.agent,
-		observedAt: now(),
-	});
-
-	return {
-		append(event) {
-			if (closed) return;
-			const sanitized = sanitizeChildEvent(event);
-			const record = enrich(sanitized);
-			const lineBytes = Buffer.byteLength(`${JSON.stringify(record)}\n`, "utf-8");
-			const assistantEvent =
-				event.type === "message_update" &&
-				event.assistantMessageEvent &&
-				typeof event.assistantMessageEvent === "object" &&
-				!Array.isArray(event.assistantMessageEvent)
-					? (event.assistantMessageEvent as Record<string, unknown>)
-					: undefined;
-			const nestedTerminal = assistantEvent?.type === "done" || assistantEvent?.type === "error";
-			const capped = !nestedTerminal && typeof event.type === "string" && CAPPED_CHILD_EVENT_TYPES.has(event.type);
-			if (capped && !writer.reserveTelemetry(lineBytes, maxTelemetryBytes)) {
-				if (writer.claimTruncationMarker()) {
-					write(enrich({ type: "subagent.child.telemetry_truncated", maxTelemetryBytes }));
-				}
-				return;
-			}
-			write(record);
-		},
-		close() {
-			if (!closePromise) {
-				closed = true;
-				closePromise = writer.close();
-			}
-			return closePromise;
-		},
-	};
-}