fix(javascript): yield during per-file projection and graph construction (#1525)

analyze_javascript_application ran several long phases with no event-loop
turn, so MCP ping and cancellation waited: each file's parse, analysis and
semantic projection; building every application node and relationship
before the application graph's first sealing step; and whole-graph schema
parses inside both immutable graph factories.

- Each file runs as steps (parse, static analysis, semantic analysis, then
  each projection pass), driven by the existing time-sliced checkpoint.
- Application graph input construction yields between phases, per module
  link and per file of findings.
- The pipeline transfers its privately built graph inputs to new sealing
  steps that validate the graph's own fields synchronously and elements,
  content checks and the digest in steps. The public copying factories
  keep their synchronous capture.

Results are unchanged: graph IDs and the complete result digest match main
on five inputs including Obsidian's 23 MB obsidian.asar. On the issue's
1,200-function fixture the longest event-loop block falls from about
290 ms to 90 ms, and ping after abort from up to 286 ms to at most 56 ms.
On obsidian.asar it falls from 10.9 s to 5.4 s; the rest is one analyzer
stage of a single very large file.

Refs #1462

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: N0zoM1z0 <161784452+N0zoM1z0@users.noreply.github.com>
This commit is contained in:
Kaoru0822
2026-10-10 03:14:37 -07:00
committed by GitHub
parent 72b3209f3a
commit 5fdb0636b4
11 changed files with 438 additions and 83 deletions
@@ -42,6 +42,46 @@ describe("JavaScript analysis cancellation before publication", () => {
expect(phases).not.toContain("validate_javascript_application_result");
});
it("handles control turns and cancellation inside one large source file (#1462)", async () => {
const root = await createTestTempDirectory("rea-js-cancel-in-file-");
await writeFile(
join(root, "index.js"),
Array.from(
{ length: 1200 },
(_, index) =>
`export function f${index}(){return {name:'f${index}',value:${index}};}`,
).join("\n"),
);
const controller = new AbortController();
const phases: string[] = [];
let turns = 0;
// Count event-loop turns once the file starts; parsing, analysis and
// projection of this one file must leave room for them.
const tick = (): void => {
turns += 1;
if (turns === 3) controller.abort();
else if (!controller.signal.aborted) setImmediate(tick);
};
const result = await analyzeJavaScriptApplication(
{ input_path: root, format: "directory" },
{
signal: controller.signal,
progress: {
async report(event) {
phases.push(event.phase);
if (event.phase === "parse_javascript_source") setImmediate(tick);
},
},
},
);
if (result.ok) throw new Error("Cancelled analysis must not publish");
expect(projectAnalysisError(result.error)).toMatchObject({
code: "cancelled",
});
expect(phases).toContain("parse_javascript_source");
expect(phases).not.toContain("build_javascript_application_graph");
});
it.each([
"parse_javascript_source",
"build_javascript_application_graph",
@@ -33,6 +33,7 @@ import type {
JavaScriptSourceMapOriginal,
} from "./JavaScriptArtifactAnalysisTypes.js";
import { analyzeJavaScriptJsonModule } from "./JavaScriptJsonModules.js";
import { completeJavaScriptAnalysisSteps } from "./JavaScriptAnalysisControl.js";
import { htmlArtifactReferences } from "../../domain/javascript/htmlArtifactReferences.js";
interface MutableArtifactAnalysis<
@@ -56,34 +57,44 @@ interface ArtifactAnalysisContext<
readonly projectSemantics: (
file: JavaScriptArtifactFile,
ir: JavaScriptSemanticIr,
) => SemanticIr;
) => Generator<void, SemanticIr>;
}
/** Analyze every text source from the artifact without a result quota. */
export const analyzeJavaScriptArtifactFiles = (
fileSet: JavaScriptArtifactFileSet,
): JavaScriptArtifactAnalysis =>
analyzeArtifactFiles(fileSet, (_file, ir) => ir);
analyzeArtifactFiles(fileSet, function* (_file, ir) {
// The full IR needs no projection; one step keeps the shared protocol.
yield;
return ir;
});
/** Project each file's full IR immediately, retaining only later module facts. */
/**
* Project each file's full IR immediately, retaining only later module facts.
* Parsing, analysis and each projection pass run as separate steps, so control
* messages and cancellation are handled within one large file as well.
*/
export const analyzeAndProjectJavaScriptArtifactFiles = async (
fileSet: JavaScriptArtifactFileSet,
projectSemantics: (
file: JavaScriptArtifactFile,
ir: JavaScriptSemanticIr,
) => void,
) => Iterator<void, void> | void,
beforeFile?: (
file: JavaScriptArtifactFile,
completed: number,
total: number,
) => Promise<void>,
signal?: AbortSignal,
): Promise<JavaScriptModuleArtifactAnalysis> => {
const state = emptyArtifactAnalysis<JavaScriptModuleSemanticIr>();
const projectFileSemantics = (
const projectFileSemantics = function* (
file: JavaScriptArtifactFile,
ir: JavaScriptSemanticIr,
): JavaScriptModuleSemanticIr => {
projectSemantics(file, ir);
): Generator<void, JavaScriptModuleSemanticIr> {
const projection = projectSemantics(file, ir);
if (projection !== undefined) while (projection.next().done !== true) yield;
const programScopes = ir.scopes.filter(({ kind }) => kind === "program");
const programScopeId = programScopes[0]?.scopeId;
const localNames = new Set(
@@ -111,7 +122,10 @@ export const analyzeAndProjectJavaScriptArtifactFiles = async (
// Let progress, cancellation and garbage collection run between files.
await setImmediate();
await beforeFile?.(file, index, fileSet.files.length);
analyzeArtifactFile(file, context);
await completeJavaScriptAnalysisSteps(
analyzeArtifactFileSteps(file, context),
signal,
);
}
return finalizeArtifactAnalysis(state);
};
@@ -122,7 +136,10 @@ const analyzeArtifactFiles = <SemanticIr extends JavaScriptModuleSemanticIr>(
): JavaScriptArtifactAnalysis<SemanticIr> => {
const state = emptyArtifactAnalysis<SemanticIr>();
const context = { state, projectSemantics };
for (const file of fileSet.files) analyzeArtifactFile(file, context);
for (const file of fileSet.files) {
const steps = analyzeArtifactFileSteps(file, context);
while (steps.next().done !== true);
}
return finalizeArtifactAnalysis(state);
};
@@ -148,10 +165,12 @@ const finalizeArtifactAnalysis = <
};
};
const analyzeArtifactFile = <SemanticIr extends JavaScriptModuleSemanticIr>(
function* analyzeArtifactFileSteps<
SemanticIr extends JavaScriptModuleSemanticIr,
>(
file: JavaScriptArtifactFile,
context: ArtifactAnalysisContext<SemanticIr>,
): void => {
): Generator<void, void> {
const { state } = context;
addStructuredObservations(file, state);
if (file.kind === "html" && file.text.included)
@@ -162,6 +181,7 @@ const analyzeArtifactFile = <SemanticIr extends JavaScriptModuleSemanticIr>(
return;
}
const parsed = parseJavaScriptSource(file.text.value, file.path);
yield;
if (parsed === null) {
const analysis = failedJavaScriptStaticAnalysis();
state.files.push({ file, javascript: analysis, semantic: null });
@@ -175,17 +195,19 @@ const analyzeArtifactFile = <SemanticIr extends JavaScriptModuleSemanticIr>(
openReceiverFacts,
);
const staticFindings = findingCount(analysis);
yield;
const semantics =
analysis.parse_status === "complete" || analysis.parse_status === "partial"
? analyzeParsedJavaScriptSemantics(parsed)
: null;
const projected =
semantics === null
? null
: yield* context.projectSemantics(file, semantics);
state.files.push({
file,
javascript: analysis,
semantic:
semantics === null
? null
: { ir: context.projectSemantics(file, semantics) },
semantic: projected === null ? null : { ir: projected },
});
state.visitedNodes += analysis.visited_ast_nodes;
state.findings += staticFindings + (semantics?.moduleLinks.length ?? 0);
@@ -194,7 +216,7 @@ const analyzeArtifactFile = <SemanticIr extends JavaScriptModuleSemanticIr>(
0,
);
if (analysis.parse_status === "failed") state.parseFailures += 1;
};
}
const addSourceMap = (
file: JavaScriptArtifactFile,
@@ -1,7 +1,7 @@
import type { ArtifactInventorySnapshot } from "../../domain/artifactInventorySnapshot.js";
import {
createJavaScriptApplicationGraph,
createImmutableJavaScriptApplicationGraphSteps,
sealTransferredJavaScriptApplicationGraphSteps,
type JavaScriptApplicationGraph,
} from "../../domain/javascript/javascriptApplicationGraph.js";
import type { JavaScriptModuleArtifactAnalysis } from "./JavaScriptArtifactAnalysisTypes.js";
@@ -15,9 +15,9 @@ import {
addJavaScriptHtmlRoles,
addJavaScriptSourceMapOriginals,
} from "./JavaScriptArtifactGraphDocuments.js";
import { addJavaScriptStaticFindings } from "./JavaScriptArtifactGraphFindings.js";
import { addJavaScriptStaticFindingsSteps } from "./JavaScriptArtifactGraphFindings.js";
import {
addJavaScriptModuleRelationships,
addJavaScriptModuleRelationshipsSteps,
type JavaScriptModuleRelationshipOmissions,
addJavaScriptSourceModules,
} from "./JavaScriptModuleRelationships.js";
@@ -51,24 +51,42 @@ export const buildJavaScriptArtifactGraph = (
analysis: JavaScriptModuleArtifactAnalysis,
): JavaScriptApplicationGraph =>
createJavaScriptApplicationGraph(
buildJavaScriptArtifactGraphInput(snapshot, fileSet, analysis),
completeSynchronously(
buildJavaScriptArtifactGraphInputSteps(snapshot, fileSet, analysis),
),
);
/** Build a validated application graph with cooperative immutable ownership. */
export const buildImmutableJavaScriptArtifactGraphSteps = (
/**
* Build a validated application graph with cooperative immutable ownership.
* Constructing the graph input also runs in steps: projecting every module
* relationship and finding at once held the event loop for seconds.
*/
export function* buildImmutableJavaScriptArtifactGraphSteps(
snapshot: ArtifactInventorySnapshot,
fileSet: JavaScriptArtifactFileSet,
analysis: JavaScriptModuleArtifactAnalysis,
): Generator<void, JavaScriptApplicationGraph> =>
createImmutableJavaScriptApplicationGraphSteps(
buildJavaScriptArtifactGraphInput(snapshot, fileSet, analysis),
): Generator<void, JavaScriptApplicationGraph> {
const input = yield* buildJavaScriptArtifactGraphInputSteps(
snapshot,
fileSet,
analysis,
);
// The input was built here and is not retained, so it can be transferred.
return yield* sealTransferredJavaScriptApplicationGraphSteps(input);
}
const buildJavaScriptArtifactGraphInput = (
const completeSynchronously = <Value>(steps: Iterator<void, Value>): Value => {
for (;;) {
const step = steps.next();
if (step.done === true) return step.value;
}
};
function* buildJavaScriptArtifactGraphInputSteps(
snapshot: ArtifactInventorySnapshot,
fileSet: JavaScriptArtifactFileSet,
analysis: JavaScriptModuleArtifactAnalysis,
): unknown => {
): Generator<void, unknown> {
const accumulator = new JavaScriptArtifactGraphAccumulator();
const root = createJavaScriptArtifactRootNode(accumulator, snapshot);
const context: JavaScriptArtifactGraphContext = {
@@ -86,15 +104,23 @@ const buildJavaScriptArtifactGraphInput = (
containerNodes: new Map([[snapshot.manifest.root_sha256, root]]),
};
addJavaScriptArtifactContainers(context);
yield;
addJavaScriptArtifactFiles(context);
yield;
const packageRoots = addJavaScriptPackageNodes(context);
yield;
addJavaScriptSourceModules(context);
yield;
const bundlerLimitations = addJavaScriptBundlerNodes(context);
const relationshipOmissions = addJavaScriptModuleRelationships(context);
const findingLimitations = addJavaScriptStaticFindings(context);
const relationshipOmissions =
yield* addJavaScriptModuleRelationshipsSteps(context);
const findingLimitations = yield* addJavaScriptStaticFindingsSteps(context);
addElectronBoundaries(context);
yield;
addJavaScriptHtmlRoles(context);
yield;
addJavaScriptSourceMapOriginals(context);
yield;
const coverage = graphCoverage(context);
return {
schema: "JavaScriptApplicationGraph",
@@ -111,7 +137,7 @@ const buildJavaScriptArtifactGraphInput = (
...graphLimitations(context, coverage.status, relationshipOmissions),
],
};
};
}
const graphCoverage = (context: JavaScriptArtifactGraphContext) => {
const resourceLimits = semanticResourceLimits(context);
@@ -44,11 +44,12 @@ interface ResolvedReference {
}
/** Project imports, workers, roles, endpoints, storage, and source-map links. */
export const addJavaScriptStaticFindings = (
export function* addJavaScriptStaticFindingsSteps(
context: JavaScriptArtifactGraphContext,
): readonly string[] => {
): Generator<void, readonly string[]> {
const omissions = { selfReferences: 0 };
for (const analyzed of context.analysis.files) {
yield;
const { file, javascript } = analyzed;
const asset = context.assetNodes.get(file.path);
if (javascript === null || asset === undefined) continue;
@@ -69,7 +70,7 @@ export const addJavaScriptStaticFindings = (
["static reference", "static references"],
"the referencing module",
);
};
}
const addReference = (
context: JavaScriptArtifactGraphContext,
@@ -90,7 +90,7 @@ export const reconstructJavaScriptArtifact = async (
const semanticProjection = createJavaScriptSemanticGraphProjection();
const analysis = await analyzeAndProjectJavaScriptArtifactFiles(
files,
semanticProjection.projectFile,
semanticProjection.projectFileSteps,
async (file, completed, total) => {
abortIfNeeded(signal);
await progress?.report({
@@ -101,6 +101,7 @@ export const reconstructJavaScriptArtifact = async (
});
abortIfNeeded(signal);
},
signal,
);
await checkpointJavaScriptAnalysis(signal);
abortIfNeeded(signal);
@@ -136,15 +136,17 @@ export interface JavaScriptModuleRelationshipOmissions {
type RelationshipOmissionCounter = { selfImports: number };
/** Compose bounded CommonJS and ESM binding relationships across artifact files. */
export const addJavaScriptModuleRelationships = (
export function* addJavaScriptModuleRelationshipsSteps(
context: JavaScriptArtifactGraphContext,
): JavaScriptModuleRelationshipOmissions => {
): Generator<void, JavaScriptModuleRelationshipOmissions> {
const omissions = { selfImports: 0 };
for (const analyzed of context.analysis.files) {
const { file, semantic } = analyzed;
const source = context.sourceModuleNodes.get(file.path);
if (semantic === null || source === undefined) continue;
for (const link of semantic.ir.moduleLinks) {
// One module can export thousands of bindings, each with return shapes.
yield;
const input = { context, file, semantic, source, link };
if (isExportLink(link)) addExportRelationship(input, omissions);
else if (link.specifier !== null)
@@ -155,7 +157,7 @@ export const addJavaScriptModuleRelationships = (
}
}
return omissions;
};
}
const addExportRelationship = (
input: RelationshipInput,
@@ -1,6 +1,6 @@
import {
createJavaScriptSemanticGraph,
createImmutableJavaScriptSemanticGraphSteps,
sealTransferredJavaScriptSemanticGraphSteps,
type JavaScriptSemanticGraph,
} from "../../domain/javascript/javascriptSemanticGraph.js";
import type {
@@ -130,6 +130,11 @@ export interface JavaScriptSemanticGraphProjection {
file: JavaScriptArtifactFile,
ir: JavaScriptSemanticIr,
) => void;
/** Project one file in steps between its projection passes. */
readonly projectFileSteps: (
file: JavaScriptArtifactFile,
ir: JavaScriptSemanticIr,
) => Generator<void, void>;
readonly finish: (
rootArtifactSha256: string,
applicationGraph: BuilderInput["applicationGraph"],
@@ -146,10 +151,10 @@ export const createJavaScriptSemanticGraphProjection =
const state = emptyState({ nodes: [] });
const fingerprints: JavaScriptSemanticFingerprint[] = [];
let truncatedFiles = 0;
const projectSource = (
const projectSourceSteps = function* (
file: JavaScriptArtifactFile,
ir: JavaScriptSemanticIr,
): void => {
): Generator<void, void> {
if (state.nodes.size >= SEMANTIC_GRAPH_NODE_CEILING) {
truncatedFiles += 1;
return;
@@ -161,7 +166,7 @@ export const createJavaScriptSemanticGraphProjection =
remainingTreeBudget,
);
state.fileNodesDropped = false;
fingerprints.push(...projectFile(file, ir, state));
fingerprints.push(...(yield* projectFileSteps(file, ir, state)));
// Nodes were dropped only if the budget actually blocked creation. A file
// that exactly fills its share ends with a zero budget without dropping
// anything, so the remaining budget alone cannot decide truncation.
@@ -198,7 +203,8 @@ export const createJavaScriptSemanticGraphProjection =
evidence_contexts: state.evidenceContexts.contexts,
nodes: [...state.nodes.values()],
relations,
fingerprints,
// The input is transferred to the factory; `fingerprints` is cleared below.
fingerprints: [...fingerprints],
unknowns,
coverage: {
status: truncatedFiles > 0 ? "partial" : "unknown",
@@ -246,7 +252,11 @@ export const createJavaScriptSemanticGraphProjection =
return graph;
};
return {
projectFile: projectSource,
projectFile: (file, ir) => {
const steps = projectSourceSteps(file, ir);
while (steps.next().done !== true);
},
projectFileSteps: projectSourceSteps,
finish: (rootArtifactSha256, applicationGraph) =>
finishWith(
createJavaScriptSemanticGraph,
@@ -255,18 +265,19 @@ export const createJavaScriptSemanticGraphProjection =
),
finishImmutableSteps: (rootArtifactSha256, applicationGraph) =>
finishWith(
createImmutableJavaScriptSemanticGraphSteps,
sealTransferredJavaScriptSemanticGraphSteps,
rootArtifactSha256,
applicationGraph,
),
};
};
const projectFile = (
function* projectFileSteps(
file: JavaScriptArtifactFile,
ir: JavaScriptSemanticIr,
state: BuilderState,
): JavaScriptSemanticFingerprint[] => {
): Generator<void, JavaScriptSemanticFingerprint[]> {
yield;
const moduleNode = retainNode(state, file, {
kind: "module",
roleKey: "module",
@@ -328,6 +339,7 @@ const projectFile = (
callableOwnerAt,
callSiteAt: createSemanticCallSiteLookup(ir, callSiteNodes),
};
yield;
projectDefinitionsAndReferences(definitions);
const context: FileContext = {
...definitions,
@@ -335,26 +347,20 @@ const projectFile = (
definitions.referenceNodes,
),
};
projectSemanticValues(context);
projectSemanticObjects(context);
projectCalls(context);
projectSemanticPromises(context);
projectSemanticEvents(context);
projectSemanticTimers(context);
projectSemanticChildProcesses(context);
projectSemanticConfiguration(context);
projectSemanticRequests(context);
projectSemanticBoundaries(context);
projectSemanticResources(context);
projectSemanticClosureCaptures(context);
projectSemanticFrontiers(context);
// Each pass completes before the next starts, so yielding between passes
// keeps projection order and results unchanged.
for (const project of FILE_PROJECTION_PASSES) {
yield;
project(context);
}
yield;
return projectSemanticFunctionFingerprints(
file,
ir,
callableNodes,
state.evidenceContexts,
);
};
}
const createReturnSiteNodes = (
file: JavaScriptArtifactFile,
@@ -543,3 +549,20 @@ const createArgumentNode = (
: `argument ${String(argument.index)}`,
functionNodeId: callNode.function_node_id,
});
/** Per-file projection passes, run in this order with a yield between each. */
const FILE_PROJECTION_PASSES: readonly ((context: FileContext) => void)[] = [
projectSemanticValues,
projectSemanticObjects,
projectCalls,
projectSemanticPromises,
projectSemanticEvents,
projectSemanticTimers,
projectSemanticChildProcesses,
projectSemanticConfiguration,
projectSemanticRequests,
projectSemanticBoundaries,
projectSemanticResources,
projectSemanticClosureCaptures,
projectSemanticFrontiers,
];