Files
rea/src/javascript/analysis/JavaScriptAnalysisWorker.ts
T

1235 lines
46 KiB
TypeScript

import { WorkerFrameSignal } from "../../process/WorkerFrameSignal.js";
import type { JavaScriptSemanticProjectionCapacity } from "../../domain/javascript/javascriptSemanticFileProjection.js";
import { createHash, randomUUID } from "node:crypto";
import { readFile, rm, stat, writeFile } from "node:fs/promises";
import { join } from "node:path";
import { StringDecoder } from "node:string_decoder";
import { fileURLToPath } from "node:url";
import { getHeapStatistics } from "node:v8";
import { z } from "zod";
import type { JavaScriptArtifactFile } from "../../domain/javascript/javascriptArtifactFiles.js";
import type { JavaScriptStaticAnalysis } from "../../domain/javascript/javascriptStaticAnalysisTypes.js";
import { estimateJavaScriptStaticApplicationProjection } from "../../domain/javascript/javascriptApplicationProjectionResources.js";
import type { JavaScriptModuleSemanticIr } from "../../domain/javascript/javascriptModuleSemanticIr.js";
import type { JavaScriptSemanticFileProjection } from "../../domain/javascript/javascriptSemanticFileProjection.js";
import type {
JavaScriptAnalyzedSource,
JavaScriptSourceAnalysisFailure,
JavaScriptSourceAnalysisLimits,
} from "../../domain/javascript/javascriptSourceAnalysis.js";
import { AnalysisError } from "../../domain/analysisErrorBase.js";
import {
AnalysisCancelledError,
AnalysisTimeoutError,
AnalysisOutputError,
AnalysisResourceConstraintError,
} from "../../domain/analysisErrorCore.js";
import { ProviderAdapterError } from "../../domain/providerAdapterError.js";
import { ProviderCleanupError } from "../../domain/providerCleanupError.js";
import { ok, err, type Result } from "../../domain/result.js";
import { javaScriptRuntime } from "../../domain/runtimeVersion.js";
import {
RuntimeControlUnavailableError,
runtimeControlCapabilityError,
} from "../../process/RuntimeControlUnavailableError.js";
import { javaScriptWorkerMemoryLimitBytes } from "../../process/JavaScriptWorkerMemoryLimit.js";
import {
spawnOwnedProviderProcess,
type ProviderProcessDiagnostic,
type ProviderProcessSupervisor,
} from "../../process/ProviderProcess.js";
import {
OwnedWorkerRuntime,
OwnedWorkerRuntimeCleanupError,
} from "../../process/OwnedWorkerRuntime.js";
import { prepareProcessOwnershipInspection } from "../../process/ProcessOwnershipObservation.js";
import {
ProviderStartupDeadline,
waitForAbortableDelay,
} from "../../process/ProviderDeadline.js";
import {
readJavaScriptAnalysisTransfer,
JAVASCRIPT_ANALYSIS_TRANSFER_RECORD_BYTES,
javaScriptForwardedTransferRemediation,
javaScriptTransferRetentionBytes,
} from "./JavaScriptAnalysisTransfer.js";
import {
JAVASCRIPT_PARENT_CHECKPOINT_HEAP_REMEDIATION,
JAVASCRIPT_PARENT_RESULT_BUDGET_REMEDIATION,
JAVASCRIPT_WORKER_HEAP_MIB_MAXIMUM,
JAVASCRIPT_WORKER_HEAP_MIB_MINIMUM,
javaScriptWorkerHeapExhaustionRecovery,
javaScriptWorkerHeapRemediation,
} from "../../domain/javascript/javascriptAnalysisResourceControls.js";
import { javaScriptWorkerStaticAnalysisSchema } from "./JavaScriptAnalysisWorkerSchemas.js";
import {
JAVASCRIPT_ANALYSIS_WORKER_DEFAULTS as DEFAULTS,
javaScriptCheckpointCeilingRemediation,
javaScriptWorkerMessageSchema,
javaScriptWorkerRequestSchema,
javaScriptWorkerAdmissionSchema,
type JavaScriptWorkerMessage,
} from "./JavaScriptAnalysisWorkerProtocol.js";
const OPERATION = "analyze_javascript_application";
const PROVIDER = "javascript-static-analysis";
const MIB = 1024 * 1024;
const STATIC_CHECKPOINT_RETENTION_EXPANSION = 6;
/** The worker runs on this executable; Bun accepts but ignores V8 heap flags. */
const WORKER_HEAP_FLAGS_ENFORCED =
javaScriptRuntime(process.versions).id === "node";
type WorkerPrimaryFailure =
| { readonly kind: "memory" }
| { readonly kind: "output"; readonly reason: string }
| { readonly kind: "input"; readonly cause: Error }
| {
readonly kind: "protocol";
readonly id: string;
readonly phase: string;
readonly response: Extract<JavaScriptWorkerMessage, { kind: "failure" }>;
}
| {
readonly kind: "exit";
readonly code: number | null;
readonly signal: NodeJS.Signals | null;
readonly heapExhaustion: boolean;
};
/** One sequential owned worker, retained between source files and closed after analysis. */
export class JavaScriptAnalysisWorker {
readonly #runId = `rea-javascript-analysis-${randomUUID()}`;
readonly #runtime: OwnedWorkerRuntime;
#ready = false;
#heapLimitBytes = 0;
#frames: JavaScriptWorkerMessage[] = [];
readonly #frameSignal = new WorkerFrameSignal();
#pending = "";
#decoder = new StringDecoder("utf8");
#primaryFailure: WorkerPrimaryFailure | undefined;
#activeJobId: string | undefined;
#activeJobPhase = "startup";
#staticResponseId: string | undefined;
#terminalResponseId: string | undefined;
#phase = "startup";
#lastFailure: AnalysisError | undefined;
#estimatedRetainedBytes = 0;
#applicationProjectionFailure: AnalysisResourceConstraintError | undefined;
#parentCapacityExhausted = false;
#sourcesRemaining: number | undefined;
#deadline: ProviderStartupDeadline | undefined;
#resultBudgetBytes = 0;
/** Null when the runtime enforces the V8 heap flags instead. */
readonly #processMemoryLimitBytes: number | null;
readonly #onStdout = (chunk: Buffer | string): void => {
if (this.#deadline?.interruption !== undefined) return;
this.#observeMemoryLimit();
try {
this.#pending +=
typeof chunk === "string" ? chunk : this.#decoder.write(chunk);
let newline: number;
while ((newline = this.#pending.indexOf("\n")) >= 0) {
const line = this.#pending.slice(0, newline);
this.#pending = this.#pending.slice(newline + 1);
if (
Buffer.byteLength(line) > DEFAULTS.protocolBytes ||
this.#frames.length >= 16
) {
this.#latchOutputFailure(
"JavaScript worker exceeded its control-frame budget",
);
return;
}
const raw: unknown = JSON.parse(line);
const frame = javaScriptWorkerMessageSchema.parse(raw);
this.#frames.push(frame);
this.#observeJobFrame(frame);
this.#frameSignal.wake("frame");
}
if (Buffer.byteLength(this.#pending) > DEFAULTS.protocolBytes)
this.#latchOutputFailure(
"JavaScript worker control frame is unterminated or oversized",
);
} catch (cause: unknown) {
this.#latchOutputFailure(message(cause));
}
};
constructor(
readonly limits: JavaScriptSourceAnalysisLimits = DEFAULTS,
readonly launcher: typeof spawnOwnedProviderProcess = spawnOwnedProviderProcess,
sourceCount?: number,
) {
this.#runtime = new OwnedWorkerRuntime({
rootPrefix: "rea-javascript-analysis-",
launcher,
supervisorOptions: {
captureStdout: false,
maxDiagnosticBytes: 256 * 1024,
onDiagnostic: (event) => this.#observeProcessDiagnostic(event),
},
onInputFailure: (cause) => this.#latchInputFailure(cause),
});
if (
!Number.isSafeInteger(limits.heapMb) ||
limits.heapMb < JAVASCRIPT_WORKER_HEAP_MIB_MINIMUM ||
limits.heapMb > JAVASCRIPT_WORKER_HEAP_MIB_MAXIMUM ||
!Number.isSafeInteger(limits.timeoutMs) ||
limits.timeoutMs <= 0 ||
limits.timeoutMs > 2_147_483_647
)
throw new RangeError(
"JavaScript worker requires valid heap and execution limits",
);
if (
sourceCount !== undefined &&
(!Number.isSafeInteger(sourceCount) || sourceCount < 0)
)
throw new RangeError(
"JavaScript worker source count must be a nonnegative safe integer",
);
this.#sourcesRemaining = sourceCount;
this.#processMemoryLimitBytes = javaScriptWorkerMemoryLimitBytes(
limits.heapMb,
);
this.#refreshResultBudget();
}
/**
* Whether this idle process can analyze another application. A failed,
* cancelled, or still-open job must not be reused.
*/
canReuse(): boolean {
return (
this.#ready &&
this.#activeJobId === undefined &&
this.#primaryFailure === undefined &&
this.#lastFailure === undefined &&
this.#frames.length === 0 &&
this.#pending === "" &&
this.#runtime.inputFailure === undefined &&
!this.#runtime.hasPendingCleanup &&
this.#runtime.supervisor !== undefined
);
}
/**
* Reset per-analysis admission for one idle process. The worker heap limit
* stays the one selected at launch; callers must not reuse across limits.
*/
prepareForAnotherAnalysis(sourceCount: number): boolean {
if (!this.canReuse()) return false;
if (!Number.isSafeInteger(sourceCount) || sourceCount < 0)
throw new RangeError(
"JavaScript worker source count must be a nonnegative safe integer",
);
this.#sourcesRemaining = sourceCount;
this.#estimatedRetainedBytes = 0;
this.#parentCapacityExhausted = false;
this.#applicationProjectionFailure = undefined;
this.#refreshResultBudget();
return true;
}
/** Keep the limit and usage in one V8 observation for every admission path. */
#remainingParentHeapBytes(): number {
const { heap_size_limit, used_heap_size } = getHeapStatistics();
return heap_size_limit - used_heap_size;
}
/**
* Reserve host-side control, schema/Evidence work, and a maximum record's
* transient copies. Admission also accounts for retained earlier files.
*/
#refreshResultBudget(): void {
this.#resultBudgetBytes = Math.max(
0,
Math.floor(
(this.#remainingParentHeapBytes() -
24 * JAVASCRIPT_ANALYSIS_TRANSFER_RECORD_BYTES) /
2,
),
);
}
/** Analyze inert source; hard worker failure does not terminate this process. */
async analyze(
file: JavaScriptArtifactFile,
capacity: JavaScriptSemanticProjectionCapacity,
signal?: AbortSignal,
onPhase?: (phase: string) => Promise<void>,
): Promise<
Result<JavaScriptAnalyzedSource, JavaScriptSourceAnalysisFailure>
> {
let javascript: JavaScriptStaticAnalysis | null = null;
let module: JavaScriptModuleSemanticIr | null = null;
let projection: JavaScriptSemanticFileProjection | null = null;
const id = randomUUID();
this.#applicationProjectionFailure = undefined;
this.#parentCapacityExhausted = false;
if (this.#sourcesRemaining !== undefined)
this.#sourcesRemaining = Math.max(0, this.#sourcesRemaining - 1);
let deadline: ProviderStartupDeadline | undefined;
let result: Result<
JavaScriptAnalyzedSource,
JavaScriptSourceAnalysisFailure
>;
try {
if (signal?.aborted === true)
throw new AnalysisCancelledError(OPERATION, { cause: signal.reason });
if (!file.text.included || file.kind !== "javascript")
throw new TypeError(
"JavaScript analysis worker requires included JavaScript text",
);
// Host ownership preparation is outside the parser execution deadline.
await prepareProcessOwnershipInspection(signal);
await OwnedWorkerRuntime.retryPending();
deadline = new ProviderStartupDeadline(this.limits.timeoutMs, signal);
this.#deadline = deadline;
await this.#start(deadline);
const rootPath = this.#runtime.rootPath;
const supervisor = this.#runtime.supervisor;
if (rootPath === undefined || supervisor === undefined)
throw new TypeError("JavaScript worker resources were not acquired");
if (this.#frames.length !== 0 || this.#pending !== "")
throw new AnalysisOutputError(
OPERATION,
"JavaScript worker has unsolicited or incomplete control frames",
);
supervisor.resetOutput();
this.#phase = "source-transfer";
await writeFile(join(rootPath, `${id}.source`), file.text.value, {
flag: "wx",
mode: 0o600,
signal: deadline.signal,
});
const { text: _text, ...metadata } = file;
let offeredResultBudget = 0;
const request = javaScriptWorkerRequestSchema.parse({
id,
node_budget: capacity.nodes,
unknown_budget: capacity.unknowns,
text_sha256: createHash("sha256").update(file.text.value).digest("hex"),
file: metadata,
});
const frame = `${JSON.stringify(request)}\n`;
if (Buffer.byteLength(frame) > DEFAULTS.protocolBytes)
throw new AnalysisResourceConstraintError(
OPERATION,
"transport",
`Source identity for ${file.path} exceeds the ${String(DEFAULTS.protocolBytes)}-byte worker request ceiling. This release has no runtime override.`,
{ worker_request_bytes: DEFAULTS.protocolBytes },
{
remediationAction: `This release has no runtime override for the ${String(DEFAULTS.protocolBytes)}-byte JavaScript worker request ceiling. Raising max_heap_mb does not raise it. Repeating the unchanged request fails the same way.`,
},
);
const stdin = supervisor.launch.process.stdin;
if (stdin === undefined || stdin === null)
throw new TypeError("JavaScript worker has no writable request stream");
this.#activeJobId = id;
this.#activeJobPhase = this.#phase;
this.#staticResponseId = undefined;
this.#terminalResponseId = undefined;
await new Promise<void>((resolve, reject) =>
stdin.write(frame, (error) =>
error === null || error === undefined ? resolve() : reject(error),
),
);
for (;;) {
const response = await this.#next(deadline, file.path);
if (response.kind === "ready" || response.id !== id)
throw new AnalysisOutputError(
OPERATION,
"JavaScript worker response names a different source job",
);
if (response.kind === "phase") {
this.#phase = response.phase;
await onPhase?.(response.phase);
continue;
}
if (response.kind === "static") {
if (javascript !== null)
throw new AnalysisOutputError(
OPERATION,
"JavaScript worker emitted a duplicate static checkpoint",
);
javascript = await this.#readCheckpoint(id, file.path, response);
if (this.#parentCapacityExhausted)
throw new AnalysisResourceConstraintError(
OPERATION,
"memory",
`The parent's result capacity was exhausted after retaining static facts for ${file.path}; remaining sources were not analyzed`,
{
...this.#limits(),
parent_result_budget_bytes: this.#resultBudgetBytes,
parent_result_budget_exhausted: true,
},
{
remediationAction: JAVASCRIPT_PARENT_RESULT_BUDGET_REMEDIATION,
},
);
offeredResultBudget =
this.#applicationProjectionFailure !== undefined &&
this.#sourcesRemaining !== undefined &&
this.#sourcesRemaining > 0
? 0
: this.#remainingResultBudget();
const admission = javaScriptWorkerAdmissionSchema.parse({
id,
semantic_result_budget_bytes: offeredResultBudget,
});
await new Promise<void>((resolve, reject) =>
stdin.write(`${JSON.stringify(admission)}\n`, (error) =>
error === null || error === undefined ? resolve() : reject(error),
),
);
continue;
}
if (response.kind === "failure") {
if (
this.#primaryFailure?.kind === "protocol" &&
this.#primaryFailure.id === response.id
)
this.#primaryFailure = undefined;
if (response.reason === "resource") {
result = err({
javascript,
module,
projection,
error: this.#protocolFailure(file.path, response, this.#phase),
});
break;
}
throw this.#protocolFailure(file.path, response, this.#phase);
}
if (javascript === null)
throw new AnalysisOutputError(
OPERATION,
"JavaScript worker completed before a static checkpoint",
);
if (response.descriptor === null) {
result = ok({ javascript, module: null, projection: null });
break;
}
const descriptor = response.descriptor;
// JSON bytes alone omit object/array overhead and the later graph/Evidence
// sealing/serialization copies. Reserve a conservative expansion budget.
const moduleEstimate = javaScriptTransferRetentionBytes(
descriptor.module_bytes,
descriptor.module_records,
);
const graphEstimate = javaScriptTransferRetentionBytes(
descriptor.graph_bytes,
descriptor.graph_records,
);
const remaining = Math.min(
offeredResultBudget,
this.#remainingResultBudget(),
);
if (moduleEstimate > remaining) {
result = err({
javascript,
module: null,
projection: null,
error: new AnalysisResourceConstraintError(
OPERATION,
"memory",
`Completed module facts for ${file.path} exceed the parent's remaining result budget; static facts were retained`,
{
...this.#limits(),
parent_result_budget_bytes: this.#resultBudgetBytes,
parent_available_result_budget_bytes: remaining,
module_transfer_bytes: descriptor.module_bytes,
module_retention_estimate_bytes: moduleEstimate,
},
{
remediationAction: `Use the retained static facts or analyze fewer source files. ${JAVASCRIPT_PARENT_RESULT_BUDGET_REMEDIATION}`,
},
),
});
break;
}
const retainGraph = moduleEstimate + graphEstimate <= remaining;
this.#phase = "result-admission";
const decoded = await readJavaScriptAnalysisTransfer(
join(rootPath, `${id}.records`),
descriptor,
file,
deadline.signal,
retainGraph ? capacity : null,
);
module = decoded.module;
projection = decoded.projection;
this.#estimatedRetainedBytes +=
moduleEstimate + (retainGraph ? graphEstimate : 0);
result = retainGraph
? ok({ javascript, module, projection: decoded.projection })
: err({
javascript,
module,
projection,
error: new AnalysisResourceConstraintError(
OPERATION,
"memory",
`Semantic graph for ${file.path} exceeds the parent's remaining result budget; static and module facts were retained`,
{
...this.#limits(),
parent_result_budget_bytes: this.#resultBudgetBytes,
parent_available_result_budget_bytes: remaining,
module_retention_estimate_bytes: moduleEstimate,
graph_retention_estimate_bytes: graphEstimate,
graph_transfer_bytes: descriptor.graph_bytes,
graph_records: descriptor.graph_records,
},
{
remediationAction: `Use the retained static and module facts or analyze fewer source files. ${JAVASCRIPT_PARENT_RESULT_BUDGET_REMEDIATION}`,
},
),
});
break;
}
// An allocation failure may surface as a protocol failure or be caught
// inside the worker; any reached limit makes this file's result partial.
this.#observeMemoryLimit();
if (this.#primaryFailure?.kind === "memory")
throw this.#projectPrimaryFailure(file.path);
} catch (cause: unknown) {
const error = this.#failure(cause, file.path, deadline, signal);
if (
this.#primaryFailure !== undefined &&
deadline?.interruption === "cancelled"
)
error.retainSecondaryFailure(
new AnalysisCancelledError(OPERATION, {
cause: deadline.signal.reason,
capturedOutput: this.#captured(),
}),
);
this.#lastFailure = error;
// Complete checkpoints remain readable after a child crash or cancellation.
const cleanup = await this.#stop(error);
if (
cleanup === undefined &&
javascript === null &&
this.#runtime.rootPath !== undefined
) {
try {
javascript = await this.#readCheckpoint(id, file.path);
} catch (checkpointCause: unknown) {
void checkpointCause;
}
}
result = err({ error: cleanup ?? error, javascript, module, projection });
} finally {
deadline?.dispose();
if (this.#deadline === deadline) this.#deadline = undefined;
if (this.#activeJobId === id) this.#activeJobId = undefined;
}
if (result.ok) this.#lastFailure = undefined;
else if (!(result.error.error instanceof ProviderCleanupError))
this.#lastFailure = result.error.error;
// Child stop must be verified before temporary files are released. On
// cleanup uncertainty, close retains this owner for a later retry.
const rootPath = this.#runtime.rootPath;
if (rootPath !== undefined && !this.#runtime.hasPendingCleanup) {
try {
for (const suffix of ["source", "static.json", "records"])
await rm(join(rootPath, `${id}.${suffix}`), { force: true });
} catch (cause: unknown) {
this.#runtime.retainForCleanup();
const error = this.#cleanupError(message(cause));
this.#runtime.bindCleanupFailure(error);
result = err({
javascript,
module,
projection,
error,
});
}
}
if (this.#applicationProjectionFailure !== undefined)
return result.ok
? ok({
...result.value,
applicationProjectionFailure: this.#applicationProjectionFailure,
})
: err({
...result.error,
applicationProjectionFailure: this.#applicationProjectionFailure,
});
return result;
}
/** Verify process cleanup, then release the private runtime; failed close is retryable. */
async close(): Promise<void> {
try {
await this.#runtime.close();
this.#ready = false;
this.#resetState();
} catch (cause: unknown) {
if (cause instanceof OwnedWorkerRuntimeCleanupError) {
const error = this.#cleanupError(
cause.message,
this.#lastFailure,
cause.cleanupResources,
cause.processId,
);
cause.bindCleanupFailure(error);
throw error;
}
throw cause;
}
}
async #start(deadline: ProviderStartupDeadline): Promise<void> {
if (this.#runtime.supervisor !== undefined && this.#ready) return;
this.#phase = "startup";
this.#heapLimitBytes = 0;
const environment: NodeJS.ProcessEnv = {
...process.env,
UV_THREADPOOL_SIZE: "1",
};
delete environment.NODE_OPTIONS;
await this.#runtime.start(
{
command: process.execPath,
arguments: [
`--max-old-space-size=${String(this.limits.heapMb)}`,
"--max-semi-space-size=8",
"--v8-pool-size=1",
"--expose-gc",
"--stack_size=2048",
fileURLToPath(import.meta.resolve("#javascript-analysis-worker")),
],
runId: `${this.#runId}-${randomUUID()}`,
hostEnvironment: environment,
stdin: "pipe",
...(this.#processMemoryLimitBytes === null
? {}
: { memoryLimitBytes: this.#processMemoryLimitBytes }),
signal: deadline.signal,
},
async () => {
this.#runtime.onStdout(this.#onStdout);
const ready = await this.#next(deadline, "worker startup");
if (ready.kind !== "ready")
throw new AnalysisOutputError(
OPERATION,
"JavaScript worker emitted facts before its startup handshake",
);
if ((ready.heap_limit_bytes === null) === WORKER_HEAP_FLAGS_ENFORCED)
throw new AnalysisOutputError(
OPERATION,
"JavaScript worker heap limit does not match the runtime that launched it",
);
this.#heapLimitBytes = ready.heap_limit_bytes ?? 0;
this.#ready = true;
},
);
}
async #next(
deadline: ProviderStartupDeadline,
path: string,
): Promise<JavaScriptWorkerMessage> {
for (;;) {
if (deadline.interruption !== undefined) {
const failure = this.#interruptionFailure(path, deadline);
throw failure;
}
this.#observeMemoryLimit();
const inputFailure = this.#runtime.inputFailure;
if (inputFailure !== undefined) this.#latchInputFailure(inputFailure);
if (
this.#primaryFailure !== undefined &&
this.#primaryFailure.kind !== "exit" &&
this.#primaryFailure.kind !== "protocol"
)
throw this.#projectPrimaryFailure(path);
const frame = this.#frames.shift();
if (frame !== undefined) return frame;
const supervisor = this.#runtime.supervisor;
const snapshot = supervisor?.snapshot();
if (
supervisor !== undefined &&
snapshot !== undefined &&
(snapshot.exitCode !== undefined || snapshot.signal !== undefined)
) {
// Exit does not complete the protocol: descendants may still hold its pipes
// or write a final response. The operation deadline bounds this wait.
const outcome = await this.#waitForFrameOrOutputClose(
supervisor,
deadline,
);
if (outcome === "interrupted") {
const completedFrame = this.#frames.shift();
if (completedFrame !== undefined) return completedFrame;
throw this.#interruptionFailure(path, deadline);
}
if (outcome === "failure") {
const bufferedFrame = this.#frames.shift();
if (bufferedFrame !== undefined) return bufferedFrame;
throw this.#selectedWorkerFailure(path);
}
const finalFrame = this.#frames.shift();
if (finalFrame !== undefined) return finalFrame;
if (outcome === "frame") continue;
throw this.#selectedWorkerFailure(path);
}
await waitForAbortableDelay(10, deadline.signal);
}
}
async #readCheckpoint(
id: string,
sourcePath: string,
expected?: { readonly bytes: number; readonly sha256: string },
): Promise<JavaScriptStaticAnalysis> {
const rootPath = this.#runtime.rootPath;
if (rootPath === undefined)
throw new TypeError("JavaScript checkpoint has no owned runtime");
const path = join(rootPath, `${id}.static.json`);
const bytes = (await stat(path)).size;
if (
bytes > DEFAULTS.checkpointBytes ||
(expected !== undefined && expected.bytes !== bytes)
)
throw new AnalysisOutputError(
OPERATION,
"JavaScript static checkpoint byte count exceeds or differs from its declared budget",
);
if (bytes * 16 + 4 * MIB > this.#remainingParentHeapBytes() - 64 * MIB)
throw new AnalysisResourceConstraintError(
OPERATION,
"memory",
"The parent's remaining heap cannot safely decode the completed JavaScript static checkpoint",
{ ...this.#limits(), checkpoint_bytes: bytes },
{
remediationAction: JAVASCRIPT_PARENT_CHECKPOINT_HEAP_REMEDIATION,
},
);
const text = await readFile(path, "utf8");
if (
expected !== undefined &&
createHash("sha256").update(text).digest("hex") !== expected.sha256
)
throw new AnalysisOutputError(
OPERATION,
"JavaScript static checkpoint digest does not match",
);
const value: unknown = JSON.parse(text);
const facts = javaScriptWorkerStaticAnalysisSchema.parse(value);
const remaining = this.#remainingTotalResultBudget();
const retainedBytes = bytes * STATIC_CHECKPOINT_RETENTION_EXPANSION;
this.#parentCapacityExhausted = retainedBytes > remaining;
this.#estimatedRetainedBytes += retainedBytes;
const expandedBytes = estimateJavaScriptStaticApplicationProjection(
facts,
bytes,
sourcePath,
);
const availableResultBudget = this.#remainingResultBudget();
if (expandedBytes <= availableResultBudget)
this.#estimatedRetainedBytes += expandedBytes;
else
this.#applicationProjectionFailure = new AnalysisResourceConstraintError(
OPERATION,
"memory",
`Expanded application relationships for ${sourcePath} exceed the parent's result budget; complete static facts were retained on the file node`,
{
parent_result_budget_bytes: this.#resultBudgetBytes,
parent_available_result_budget_bytes: availableResultBudget,
application_projection_required_bytes: expandedBytes,
},
{
remediationAction: `Read the complete static facts on the file node or analyze fewer source files. Expanded application relationships exceed the parent result budget. ${JAVASCRIPT_PARENT_RESULT_BUDGET_REMEDIATION}`,
},
);
return facts;
}
#limits() {
return {
...(WORKER_HEAP_FLAGS_ENFORCED
? {
worker_old_space_mb: this.limits.heapMb,
...(this.#heapLimitBytes === 0
? {}
: { worker_heap_limit_bytes: this.#heapLimitBytes }),
}
: // Bun enforces no worker heap limit; report it as unavailable.
{ worker_heap_limit_bytes: null }),
...(this.#processMemoryLimitBytes === null
? {}
: {
worker_process_memory_limit_bytes: this.#processMemoryLimitBytes,
}),
worker_timeout_ms: this.limits.timeoutMs,
};
}
#memoryLimitReached(): boolean {
return this.#runtime.supervisor?.launch.process.memoryLimitReached === true;
}
#memoryFailure(path: string): AnalysisResourceConstraintError {
return new AnalysisResourceConstraintError(
OPERATION,
"memory",
`Owned JavaScript worker reached its ${this.#processMemoryLimitBytes === null ? "" : `${String(this.#processMemoryLimitBytes)}-byte `}process memory limit while analyzing ${path} during ${this.#phase}. That limit is max_heap_mb ${String(this.limits.heapMb)} MiB plus a 512 MiB Bun runtime reserve`,
this.#limits(),
{
capturedOutput: this.#captured(),
remediationAction: javaScriptWorkerHeapRemediation(this.limits.heapMb),
},
);
}
#remainingResultBudget(): number {
// One sequential worker produces one next checkpoint at a time. Reserve
// its maximum protocol size at the same retained expansion used on receipt;
// earlier checkpoints are already charged to estimatedRetainedBytes.
// Reserving every unexamined source's maximum would reject useful results
// merely because many small files remain. Actual retained growth and live
// heap capacity are checked again for every checkpoint and transfer.
const checkpointReserve =
DEFAULTS.checkpointBytes * STATIC_CHECKPOINT_RETENTION_EXPANSION;
const staticReserve =
this.#sourcesRemaining !== undefined && this.#sourcesRemaining > 0
? checkpointReserve
: 0;
return Math.max(0, this.#remainingTotalResultBudget() - staticReserve);
}
#remainingTotalResultBudget(): number {
return Math.max(
0,
Math.min(
this.#resultBudgetBytes - this.#estimatedRetainedBytes,
this.#remainingParentHeapBytes() -
24 * JAVASCRIPT_ANALYSIS_TRANSFER_RECORD_BYTES,
),
);
}
#captured() {
const snapshot = this.#runtime.supervisor?.snapshot();
const supervisor = this.#runtime.supervisor;
return {
stdout: "",
stderr: snapshot?.stderr.text ?? "",
truncated:
snapshot?.diagnosticTruncated === true ||
snapshot?.outputIncomplete === true ||
(supervisor !== undefined && !supervisor.observedOutputClose()),
stderr_bytes: snapshot?.stderr.observedBytes ?? 0,
exit_code: snapshot?.exitCode ?? null,
signal: snapshot?.signal ?? null,
};
}
#observeProcessDiagnostic(event: ProviderProcessDiagnostic): void {
if (this.#deadline?.interruption !== undefined) return;
this.#observeMemoryLimit();
if (event.type === "output-close") {
if (
this.#deadline !== undefined &&
(this.#activeJobId === undefined ||
this.#terminalResponseId !== this.#activeJobId)
)
this.#latchOutputFailure(
"JavaScript worker closed output before the operation received its terminal response",
);
return;
}
if (
event.type === "output" &&
event.stream === "stderr" &&
this.#primaryFailure?.kind === "exit" &&
/heap out of memory|heap limit|allocation failed/iu.test(
this.#runtime.supervisor?.snapshot().stderr.text ?? "",
)
) {
this.#primaryFailure = { ...this.#primaryFailure, heapExhaustion: true };
this.#frameSignal.wake("failure");
}
if (event.type === "exit" && (event.code !== 0 || event.signal !== null)) {
if (this.#primaryFailure === undefined)
this.#primaryFailure = {
kind: "exit",
code: event.code,
signal: event.signal,
heapExhaustion:
/heap out of memory|heap limit|allocation failed/iu.test(
event.snapshot.stderr.text,
),
};
else if (
this.#primaryFailure.kind === "exit" &&
/heap out of memory|heap limit|allocation failed/iu.test(
event.snapshot.stderr.text,
)
) {
this.#primaryFailure = {
...this.#primaryFailure,
heapExhaustion: true,
};
this.#frameSignal.wake("failure");
}
}
}
#observeMemoryLimit(): void {
if (
this.#deadline?.interruption === undefined &&
this.#memoryLimitReached()
) {
if (this.#primaryFailure === undefined)
this.#primaryFailure = { kind: "memory" };
else if (this.#primaryFailure.kind === "exit")
this.#primaryFailure = {
...this.#primaryFailure,
heapExhaustion: true,
};
if (
this.#primaryFailure?.kind === "memory" ||
this.#primaryFailure?.kind === "exit"
)
this.#frameSignal.wake("failure");
}
}
#observeJobFrame(frame: JavaScriptWorkerMessage): void {
if (
this.#deadline?.interruption !== undefined ||
this.#activeJobId === undefined ||
frame.kind === "ready"
)
return;
if (frame.id !== this.#activeJobId) return;
if (frame.kind === "phase") {
this.#activeJobPhase = frame.phase;
return;
}
if (frame.kind === "static") {
this.#staticResponseId = frame.id;
return;
}
if (frame.kind === "complete") {
if (this.#staticResponseId !== frame.id) {
if (this.#primaryFailure === undefined)
this.#primaryFailure = {
kind: "output",
reason: "JavaScript worker completed before a static checkpoint",
};
this.#frameSignal.wake("failure");
return;
}
this.#terminalResponseId = frame.id;
return;
}
if (frame.kind === "failure") this.#terminalResponseId = frame.id;
if (frame.kind === "failure" && this.#primaryFailure === undefined)
this.#primaryFailure = {
kind: "protocol",
id: frame.id,
phase: this.#activeJobPhase,
response: frame,
};
}
#latchOutputFailure(reason: string): void {
if (this.#deadline?.interruption !== undefined) return;
if (this.#primaryFailure === undefined)
this.#primaryFailure = { kind: "output", reason };
this.#frameSignal.wake("failure");
}
#latchInputFailure(cause: Error): void {
if (this.#deadline?.interruption !== undefined) return;
if (this.#primaryFailure === undefined)
this.#primaryFailure = { kind: "input", cause };
this.#frameSignal.wake("failure");
}
async #waitForFrameOrOutputClose(
supervisor: ProviderProcessSupervisor,
deadline: ProviderStartupDeadline,
): Promise<"frame" | "failure" | "closed" | "interrupted"> {
if (this.#frames.length !== 0) return "frame";
return this.#frameSignal.waitForOutputClose(supervisor, deadline.signal);
}
#selectedWorkerFailure(path: string): AnalysisError {
if (this.#primaryFailure !== undefined)
return this.#projectPrimaryFailure(path);
const snapshot = this.#runtime.supervisor?.snapshot();
if (snapshot?.exitCode !== undefined || snapshot?.signal !== undefined)
return this.#workerExitFailure(path, {
kind: "exit",
code: snapshot.exitCode ?? null,
signal: snapshot.signal ?? null,
heapExhaustion: false,
});
return new ProviderAdapterError(PROVIDER, OPERATION, {
capturedOutput: this.#captured(),
diagnostics: { source_path: path, phase: this.#phase },
});
}
#interruptionFailure(
path: string,
deadline: ProviderStartupDeadline,
): AnalysisError {
if (this.#primaryFailure !== undefined)
return this.#projectPrimaryFailure(path);
return deadline.interruption === "timeout"
? new AnalysisTimeoutError(OPERATION, this.limits.timeoutMs, {
capturedOutput: this.#captured(),
userMessage: `JavaScript source analysis reached its ${String(this.limits.timeoutMs)}ms per-source server/provider deadline (analysis_timeout_ms), not the MCP client deadline.`,
remediationAction:
"Reuse accessible partial_observation Evidence to avoid recomputation; reading it is not a prerequisite for a corrected retry. Increase analysis_timeout_ms through MCP, or use rea analyze-javascript-application <input_path> --analysis-timeout-ms <milliseconds> on the CLI. Alternatively, reduce semantic limits or select exact inventoried source_paths (CLI: --source-path on that command). Omit source_paths to analyze all sources; an empty array is invalid. detail: summary reduces response size, not analysis work. Allow execution, cleanup and delivery headroom in the MCP client tool deadline; increasing that client deadline alone does not change this server budget. Resolve any reported incomplete cleanup before retrying.",
})
: new AnalysisCancelledError(OPERATION, {
cause: deadline.signal.reason,
capturedOutput: this.#captured(),
});
}
#workerExitFailure(
path: string,
failure: Extract<WorkerPrimaryFailure, { kind: "exit" }>,
): AnalysisError {
if (failure.heapExhaustion) {
const recovery = javaScriptWorkerHeapExhaustionRecovery({
heapFlagsEnforced: WORKER_HEAP_FLAGS_ENFORCED,
heapMb: this.limits.heapMb,
path,
phase: this.#phase,
});
return new AnalysisResourceConstraintError(
OPERATION,
"memory",
recovery.reason,
this.#limits(),
{
capturedOutput: this.#captured(),
remediationAction: recovery.remediationAction,
},
);
}
return new ProviderAdapterError(PROVIDER, OPERATION, {
capturedOutput: this.#captured(),
diagnostics: {
source_path: path,
phase: this.#phase,
exit_code: failure.code,
signal: failure.signal,
},
});
}
#projectPrimaryFailure(path: string): AnalysisError {
const failure = this.#primaryFailure;
if (failure === undefined) return this.#selectedWorkerFailure(path);
if (failure.kind === "memory") return this.#memoryFailure(path);
if (failure.kind === "exit") return this.#workerExitFailure(path, failure);
if (failure.kind === "input")
return new AnalysisOutputError(
OPERATION,
`Owned JavaScript worker request stream failed during ${path}`,
{ cause: failure.cause, capturedOutput: this.#captured() },
);
if (failure.kind === "protocol") {
return this.#protocolFailure(path, failure.response, failure.phase);
}
return new AnalysisOutputError(OPERATION, failure.reason, {
capturedOutput: this.#captured(),
});
}
#protocolFailure(
path: string,
response: Extract<JavaScriptWorkerMessage, { kind: "failure" }>,
phase: string,
): AnalysisError {
if (response.reason === "io")
return new ProviderAdapterError(PROVIDER, OPERATION, {
capturedOutput: this.#captured(),
userMessage: `Owned JavaScript worker storage failed for ${path} during ${phase}. Retained observations and cleanup status are reported separately.`,
remediationAction:
"Check the availability and permissions of REA's private temporary storage, correct the reported I/O failure, and retry. Changing the selected source is not required by this storage failure.",
diagnostics: {
source_path: path,
phase,
worker_failure_reason: response.reason,
message: response.message,
},
});
if (response.reason === "resource") {
const reported = response.limits;
const limits = { ...this.#limits(), ...reported };
const transferRemediation =
javaScriptForwardedTransferRemediation(reported);
const checkpointBytes = reported?.checkpoint_limit_bytes;
const checkpointRemediation =
typeof checkpointBytes === "number"
? javaScriptCheckpointCeilingRemediation(checkpointBytes)
: undefined;
const parentBudget =
reported?.semantic_result_budget_bytes !== undefined ||
reported?.parent_result_budget_bytes !== undefined;
const remediationAction =
transferRemediation ??
checkpointRemediation ??
(parentBudget
? JAVASCRIPT_PARENT_RESULT_BUDGET_REMEDIATION
: undefined);
return new AnalysisResourceConstraintError(
OPERATION,
response.resource ?? "memory",
response.message,
limits,
remediationAction === undefined ? undefined : { remediationAction },
);
}
return new AnalysisOutputError(
OPERATION,
`${path} during ${phase}: ${response.message}`,
{ capturedOutput: this.#captured() },
);
}
#failure(
cause: unknown,
path: string,
deadline: ProviderStartupDeadline | undefined,
signal: AbortSignal | undefined,
): AnalysisError {
if (
deadline?.interruption === "cancelled" &&
cause === deadline.signal.reason
)
return this.#interruptionFailure(path, deadline);
if (
deadline === undefined &&
signal?.aborted === true &&
cause === signal.reason
)
return new AnalysisCancelledError(OPERATION, {
cause: signal.reason,
capturedOutput: this.#captured(),
});
if (cause instanceof OwnedWorkerRuntimeCleanupError) {
const error = this.#cleanupError(
cause.message,
this.#lastFailure,
cause.cleanupResources,
cause.processId,
);
cause.bindCleanupFailure(error);
return error;
}
// Ownership preparation is abortable before the worker deadline exists.
if (deadline?.interruption !== undefined)
return this.#interruptionFailure(path, deadline);
if (
deadline === undefined &&
signal?.aborted === true &&
!(cause instanceof ProviderCleanupError)
)
return new AnalysisCancelledError(OPERATION, {
cause: signal.reason,
capturedOutput: this.#captured(),
});
const inputFailure = this.#runtime.inputFailure;
if (inputFailure !== undefined)
return new AnalysisOutputError(
OPERATION,
`Owned JavaScript worker request stream failed during ${this.#phase}`,
{ cause: inputFailure, capturedOutput: this.#captured() },
);
// A reached process limit explains the worker's exit, broken pipe or
// truncated frame better than the symptom it produced.
if (
this.#memoryLimitReached() &&
!(cause instanceof AnalysisResourceConstraintError)
)
return this.#memoryFailure(path);
if (cause instanceof AnalysisError) return cause;
if (
cause instanceof z.ZodError ||
cause instanceof TypeError ||
cause instanceof SyntaxError
)
return new AnalysisOutputError(
OPERATION,
`${path} during ${this.#phase}: ${message(cause)}`,
{ cause, capturedOutput: this.#captured() },
);
return cause instanceof RuntimeControlUnavailableError
? runtimeControlCapabilityError(PROVIDER, OPERATION, cause)
: new ProviderAdapterError(PROVIDER, OPERATION, {
cause,
capturedOutput: this.#captured(),
diagnostics: {
source_path: path,
phase: this.#phase,
message: message(cause),
},
});
}
#cleanupError(
reason: string,
original: AnalysisError | undefined = this.#lastFailure,
cleanupResources: readonly string[] = [
this.#runId,
...(this.#runtime.rootPath === undefined ? [] : [this.#runtime.rootPath]),
],
processId: number | null = this.#runtime.supervisor?.launch.process.pid ??
null,
): ProviderCleanupError {
return new ProviderCleanupError(
PROVIDER,
cleanupResources,
{
reason,
worker_pid: processId,
...(original === undefined
? {}
: {
execution_failure: {
tag: original._tag,
message: original.message,
captured_output: {
stdout: original.capturedOutput?.stdout ?? "",
stderr: original.capturedOutput?.stderr ?? "",
truncated: original.capturedOutput?.truncated ?? false,
},
},
}),
},
{
operation: OPERATION,
...(original === undefined ? {} : { cleanupPrimary: original }),
cause: new Error(
reason,
original === undefined ? undefined : { cause: original },
),
},
);
}
async #stop(
original: AnalysisError | undefined = this.#lastFailure,
): Promise<ProviderCleanupError | undefined> {
const stopped = await this.#runtime.stop();
if (stopped.status === "incomplete") {
this.#resetState();
const error = this.#cleanupError(stopped.reason, original);
this.#runtime.bindCleanupFailure(error);
return error;
}
this.#ready = false;
this.#resetState();
return undefined;
}
#resetState(): void {
this.#ready = false;
this.#frames = [];
this.#frameSignal.clear();
this.#pending = "";
this.#decoder = new StringDecoder("utf8");
this.#primaryFailure = undefined;
this.#activeJobId = undefined;
this.#staticResponseId = undefined;
this.#terminalResponseId = undefined;
}
}
const message = (cause: unknown): string =>
cause instanceof Error ? cause.message : String(cause);