mirror of
https://github.com/morluto/rea
synced 2026-10-25 22:08:11 -04:00
fix(javascript): declare owned analysis worker effects
Advertise internal worker launches and temporary source writes through the canonical effects owner so MCP hints and session availability agree with existing analysis behavior. Preserve non-destructive, idempotent semantics. Verify public metadata boundaries and a real Obsidian CLI/MCP workflow, retaining compact reproduction and cost records. Fixes #3867 Co-authored-by: Kaoru0822 <208281322+kaoru0822-kitauji@users.noreply.github.com>
This commit is contained in:
Ysopwnable
@@ -497,7 +497,10 @@ declared by their tools. Artifact extraction materializes the selected regular
|
||||
files into a fresh REA-chosen temporary directory and reports its path.
|
||||
|
||||
`analyze_javascript_application` reads the supplied local directory or ASAR path
|
||||
and returns its result and Evidence inline.
|
||||
and returns its result and Evidence inline. Its owned analysis worker and private
|
||||
temporary source files are declared as `launchesProcess` and `writesFilesystem`,
|
||||
including for a single JavaScript source. This internal analysis does not execute
|
||||
the supplied application code.
|
||||
|
||||
## Ghidra first-query deadlines and recovery
|
||||
|
||||
|
||||
@@ -0,0 +1,249 @@
|
||||
{
|
||||
"base_revision": "e598b4656ad90d59ede2d10454a0ac34f3813558",
|
||||
"scope": "Canonical effect metadata only; real static Obsidian reads, no target execution",
|
||||
"baseline_source_sha256": {
|
||||
"src/contracts/toolEffects.ts": "39505b5f1501768515229a37ff67e8a1a512faedfb6669aee7a690a2ac3ac633",
|
||||
"src/javascript/analysis/JavaScriptAnalysisWorker.ts": "49ea4e6344060fae3529ffe6e14bfadc534132067cfa5c370263dc7476375be0",
|
||||
"scripts/verify/javascript/module-references.mjs": "9d5f0b8b35ed2ebb4591f9dc3baea0fc116a0c3fd7d8e5ce30ec476c84671ed1"
|
||||
},
|
||||
"final_source_sha256": {
|
||||
"src/contracts/toolEffects.ts": "feb66f1b71c4a6849d1730227c9c74e4efbb67b4537d75fd41ce9ff615c25753",
|
||||
"src/javascript/analysis/JavaScriptAnalysisWorker.ts": "49ea4e6344060fae3529ffe6e14bfadc534132067cfa5c370263dc7476375be0",
|
||||
"scripts/verify/javascript/module-references.mjs": "9d5f0b8b35ed2ebb4591f9dc3baea0fc116a0c3fd7d8e5ce30ec476c84671ed1",
|
||||
"tests/boundary/mcp/electronMcp.test.ts": "e483bec8512cfeafa7f951c8faf25e1aecd6e6987ea74aead14230501912928d",
|
||||
"tests/boundary/mcp/toolSchemaValidity.test.ts": "ab6d9ba37035a6ff9279b820aa8660c50a3ef9f31d25f838c0ba40929148e89c"
|
||||
},
|
||||
"cohorts": {
|
||||
"baseline": {
|
||||
"metadata": {
|
||||
"tool": "analyze_javascript_application",
|
||||
"advertised_annotations": {
|
||||
"readOnlyHint": false,
|
||||
"destructiveHint": false,
|
||||
"idempotentHint": true,
|
||||
"openWorldHint": false
|
||||
},
|
||||
"session_effects": ["mutatesSession", "idempotent"],
|
||||
"session_annotations": ["idempotent"],
|
||||
"catalog_tool_count": 207
|
||||
},
|
||||
"metadata_probe_resources": {
|
||||
"elapsed_seconds": 10.711,
|
||||
"cpu_seconds": 10.503415,
|
||||
"peak_cgroup_bytes": 842891264,
|
||||
"payload_cleanup_verified": true,
|
||||
"events_at_payload_exit": {
|
||||
"memory.events": {
|
||||
"low": 0,
|
||||
"high": 0,
|
||||
"max": 0,
|
||||
"oom": 0,
|
||||
"oom_kill": 0,
|
||||
"oom_group_kill": 0
|
||||
},
|
||||
"pids.events": {
|
||||
"max": 0
|
||||
}
|
||||
}
|
||||
},
|
||||
"real_workflow": {
|
||||
"artifact": {
|
||||
"path": "/tmp/rea-codemode-experiment-20261015/artifacts/obsidian-1.14.4.asar",
|
||||
"sha256": "146ef8470d8cbb4a6db209bdc19bf2bad13350444186c0fd93c31087b142b92f"
|
||||
},
|
||||
"parent_evidence_id": "ev_73ef06e3b9b944f54c5257f7960279127d8518d2a73cd8618bd045dbe44e6b5a",
|
||||
"samples": [
|
||||
{
|
||||
"round": 0,
|
||||
"mode": "references",
|
||||
"elapsed_ms": 109.19401700000162,
|
||||
"calls": 1,
|
||||
"structured_reply_bytes": 22158,
|
||||
"facts_sha256": "d3be5e91d2ec3fd9a95851cfbbdef9c168bb4c7153f78810b8b235e005401299",
|
||||
"matching_modules": 23,
|
||||
"coverage": {
|
||||
"status": "page",
|
||||
"examined": 23,
|
||||
"total": 23,
|
||||
"next_offset": null,
|
||||
"exhausted": true
|
||||
}
|
||||
}
|
||||
],
|
||||
"token_costs": {
|
||||
"tokenizer": "cl100k_base",
|
||||
"tiktoken_version": "0.12.0",
|
||||
"costs": {
|
||||
"references": {
|
||||
"selected_catalog": 7977,
|
||||
"full_catalog": 195522,
|
||||
"common_request": 53,
|
||||
"common_summary": 2675,
|
||||
"requests": 102,
|
||||
"structured_replies": 5741,
|
||||
"selected_catalog_task_total": 16548,
|
||||
"full_catalog_task_total": 204093
|
||||
}
|
||||
}
|
||||
},
|
||||
"cli_parity": {
|
||||
"evidence_id": "ev_b3586dfdf7d4f01157f8f2978326aaa7103987110f2df4fa5bf3331ff2898749",
|
||||
"facts_sha256": "d3be5e91d2ec3fd9a95851cfbbdef9c168bb4c7153f78810b8b235e005401299",
|
||||
"exact_cli_mcp_view_parity": true
|
||||
}
|
||||
},
|
||||
"real_workflow_resources": {
|
||||
"elapsed_seconds": 30.47,
|
||||
"cpu_seconds": 29.939807,
|
||||
"peak_cgroup_bytes": 1551282176,
|
||||
"payload_cleanup_verified": true,
|
||||
"events_at_payload_exit": {
|
||||
"memory.events": {
|
||||
"low": 0,
|
||||
"high": 0,
|
||||
"max": 0,
|
||||
"oom": 0,
|
||||
"oom_kill": 0,
|
||||
"oom_group_kill": 0
|
||||
},
|
||||
"pids.events": {
|
||||
"max": 0
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"final": {
|
||||
"metadata": {
|
||||
"tool": "analyze_javascript_application",
|
||||
"advertised_annotations": {
|
||||
"readOnlyHint": false,
|
||||
"destructiveHint": false,
|
||||
"idempotentHint": true,
|
||||
"openWorldHint": true
|
||||
},
|
||||
"session_effects": [
|
||||
"mutatesSession",
|
||||
"writesFilesystem",
|
||||
"launchesProcess",
|
||||
"idempotent"
|
||||
],
|
||||
"session_annotations": ["idempotent", "open_world"],
|
||||
"catalog_tool_count": 207
|
||||
},
|
||||
"metadata_probe_resources": {
|
||||
"elapsed_seconds": 10.909,
|
||||
"cpu_seconds": 10.664997,
|
||||
"peak_cgroup_bytes": 853958656,
|
||||
"payload_cleanup_verified": true,
|
||||
"events_at_payload_exit": {
|
||||
"memory.events": {
|
||||
"low": 0,
|
||||
"high": 0,
|
||||
"max": 0,
|
||||
"oom": 0,
|
||||
"oom_kill": 0,
|
||||
"oom_group_kill": 0
|
||||
},
|
||||
"pids.events": {
|
||||
"max": 0
|
||||
}
|
||||
}
|
||||
},
|
||||
"real_workflow": {
|
||||
"artifact": {
|
||||
"path": "/tmp/rea-codemode-experiment-20261015/artifacts/obsidian-1.14.4.asar",
|
||||
"sha256": "146ef8470d8cbb4a6db209bdc19bf2bad13350444186c0fd93c31087b142b92f"
|
||||
},
|
||||
"parent_evidence_id": "ev_73ef06e3b9b944f54c5257f7960279127d8518d2a73cd8618bd045dbe44e6b5a",
|
||||
"samples": [
|
||||
{
|
||||
"round": 0,
|
||||
"mode": "references",
|
||||
"elapsed_ms": 110.17946600000141,
|
||||
"calls": 1,
|
||||
"structured_reply_bytes": 22158,
|
||||
"facts_sha256": "d3be5e91d2ec3fd9a95851cfbbdef9c168bb4c7153f78810b8b235e005401299",
|
||||
"matching_modules": 23,
|
||||
"coverage": {
|
||||
"status": "page",
|
||||
"examined": 23,
|
||||
"total": 23,
|
||||
"next_offset": null,
|
||||
"exhausted": true
|
||||
}
|
||||
}
|
||||
],
|
||||
"token_costs": {
|
||||
"tokenizer": "cl100k_base",
|
||||
"tiktoken_version": "0.12.0",
|
||||
"costs": {
|
||||
"references": {
|
||||
"selected_catalog": 7977,
|
||||
"full_catalog": 195522,
|
||||
"common_request": 53,
|
||||
"common_summary": 2675,
|
||||
"requests": 102,
|
||||
"structured_replies": 5741,
|
||||
"selected_catalog_task_total": 16548,
|
||||
"full_catalog_task_total": 204093
|
||||
}
|
||||
}
|
||||
},
|
||||
"cli_parity": {
|
||||
"evidence_id": "ev_b3586dfdf7d4f01157f8f2978326aaa7103987110f2df4fa5bf3331ff2898749",
|
||||
"facts_sha256": "d3be5e91d2ec3fd9a95851cfbbdef9c168bb4c7153f78810b8b235e005401299",
|
||||
"exact_cli_mcp_view_parity": true
|
||||
}
|
||||
},
|
||||
"real_workflow_resources": {
|
||||
"elapsed_seconds": 31.059,
|
||||
"cpu_seconds": 30.663163,
|
||||
"peak_cgroup_bytes": 1584574464,
|
||||
"payload_cleanup_verified": true,
|
||||
"events_at_payload_exit": {
|
||||
"memory.events": {
|
||||
"low": 0,
|
||||
"high": 0,
|
||||
"max": 0,
|
||||
"oom": 0,
|
||||
"oom_kill": 0,
|
||||
"oom_group_kill": 0
|
||||
},
|
||||
"pids.events": {
|
||||
"max": 0
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"conditions": "Separate fresh MCP sessions, uncontrolled warm filesystem/build and shared-host scheduling. One CPU, 8 GiB hard cap, 6 GiB early stop, no swap. Resource counters are at payload exit with the observer alive, not final whole-scope counters; memory includes charged file cache, not summed RSS. Whole real-verifier resources include analysis, export, CLI parity and tokenizer; metadata probe resources are separate. Static BPE uses name/description/inputSchema catalog projections plus requests/structured replies, excludes annotations, metadata-probe calls, rendering/replay/reasoning/final-answer/model usage. No performance improvement or equivalence bound established by one before/after pair.",
|
||||
"regressions": {
|
||||
"baseline": "20 executed: 2 expected metadata failures, 18 passed",
|
||||
"final": "27 passed after the test ownership cleanup across canonical effects and MCP/catalog boundaries",
|
||||
"interim_correction": "26 passed before metadata assertions were split into their own target-free case to satisfy function-size lint"
|
||||
},
|
||||
"selected_input": {
|
||||
"input_path": "/tmp/rea-codemode-experiment-20261015/artifacts/obsidian-1.14.4.asar",
|
||||
"detail": "summary",
|
||||
"source_paths": ["package.json", "main.js"]
|
||||
},
|
||||
"selected_view": {
|
||||
"kind": "javascript",
|
||||
"collection": "modules",
|
||||
"projection": "references",
|
||||
"where": {
|
||||
"path": "main.js",
|
||||
"kind": "javascript-module"
|
||||
}
|
||||
},
|
||||
"observer_sources_sha256": {
|
||||
"resource-run.py": "7728862171415e7dee2c11af2ead2b9a54265fccaf82a7113956d36b29065e33",
|
||||
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
||||
},
|
||||
"runtime": {
|
||||
"platform": "Linux x64",
|
||||
"node": "24.18.0",
|
||||
"npm": "11.16.0",
|
||||
"tiktoken": "0.12.0"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,121 @@
|
||||
# JavaScript analysis effect metadata verification
|
||||
|
||||
Tracks #3867 under #4027. The canonical effect record omitted existing internal
|
||||
worker launches and source staging. `CapabilityInventory` and SDK registration
|
||||
already consume that owner directly; no adapter override is required. The
|
||||
[worker](../../src/javascript/analysis/JavaScriptAnalysisWorker.ts) creates a
|
||||
private runtime root, stages `.source` files and launches an owned REA worker.
|
||||
These are source-derived facts; the analyzed application code is not executed.
|
||||
|
||||
## Executed results
|
||||
|
||||
Public stdio MCP before/after:
|
||||
|
||||
| Surface | Before | After |
|
||||
| ---------------------------- | ------------------------------ | ------------------------------------------ |
|
||||
| `tools/list` `openWorldHint` | `false` | `true` |
|
||||
| `binary_session` effects | `mutatesSession`, `idempotent` | also `writesFilesystem`, `launchesProcess` |
|
||||
| Session annotation flags | `idempotent` | also `open_world` |
|
||||
| Advertised tools | 207 | 207 |
|
||||
|
||||
Regression assertions failed on the original contract: **2 failed,
|
||||
18 passed**. After correction and separating the target-free metadata case, **27 passed** across canonical effects, public
|
||||
Electron/JavaScript MCP and SDK-converted catalog validity. The tests retain the
|
||||
non-destructive, idempotent hints and exact session effects; no foreign target
|
||||
execution is declared.
|
||||
|
||||
The existing real verifier analyzed official Obsidian 1.14.4 with `package.json`
|
||||
and `main.js` selected, then read the typed module references and verified exact
|
||||
public CLI/MCP parity. Both revisions returned the same parent/view Evidence
|
||||
identities and 23-row fact digest. Query replies remained 22,158 bytes and the
|
||||
selected-schema task remained 16,548 `cl100k_base` BPE tokens (204,093 with the full
|
||||
name/description/inputSchema catalog projection). These are static counts, not
|
||||
model billing; annotations, the separate metadata probe, host rendering/replay,
|
||||
reasoning and final answers are outside this projection. No hosted agent was run.
|
||||
|
||||
| Complete real verifier | Before | After |
|
||||
| ---------------------- | ------------: | ------------: |
|
||||
| Elapsed seconds | 30.470 | 31.059 |
|
||||
| CPU seconds | 29.939807 | 30.663163 |
|
||||
| Peak cgroup bytes | 1,551,282,176 | 1,584,574,464 |
|
||||
|
||||
The scope includes shared analysis, temporary export, CLI parity and tokenizer.
|
||||
The metadata-only probe separately used 10.711/10.909 s wall,
|
||||
10.503415/10.664997 s CPU and 842,891,264/853,958,656 B peak cgroup memory.
|
||||
All scopes used one CPU, an 8 GiB hard cap, 6 GiB early stop and no swap; cleanup
|
||||
was verified with no OOM. Memory includes charged file cache, not summed RSS.
|
||||
Counters were observed at payload exit while the observer remained alive.
|
||||
Fresh MCP sessions do not establish an OS-cold cache. Shared-host scheduling and
|
||||
filesystem/build warmness were uncontrolled; one pair establishes neither a
|
||||
performance improvement nor an equivalence bound. Linux x64 static ASAR analysis
|
||||
was executed; live Electron and other platforms were not exercised locally.
|
||||
[Compact records and source hashes](javascript-analysis-effects-2026-10-15.json)
|
||||
preserve these distinctions without archiving the downloadable application.
|
||||
|
||||
## Reproduce
|
||||
|
||||
Use pinned Node/npm, `npm ci`, then `npm run build:cached`. Run the following as
|
||||
an ES module from the checkout root (`node --input-type=module < probe.mjs`):
|
||||
|
||||
```javascript
|
||||
import assert from "node:assert/strict";
|
||||
import { Client } from "@modelcontextprotocol/client";
|
||||
import { StdioClientTransport } from "@modelcontextprotocol/client/stdio";
|
||||
import { toolAvailabilityInventory } from "./dist/contracts/toolOutputSchemaPrimitives.js";
|
||||
import { closeVerifierResources } from "./scripts/lib/verifier-cleanup.mjs";
|
||||
|
||||
const client = new Client({
|
||||
name: "javascript-effect-verification",
|
||||
version: "1",
|
||||
});
|
||||
const transport = new StdioClientTransport({
|
||||
command: process.execPath,
|
||||
args: ["scripts/rea.mjs", "mcp"],
|
||||
stderr: "pipe",
|
||||
});
|
||||
let primaryError;
|
||||
try {
|
||||
await client.connect(transport);
|
||||
transport.stderr?.resume();
|
||||
const { tools } = await client.listTools();
|
||||
const tool = tools.find(
|
||||
({ name }) => name === "analyze_javascript_application",
|
||||
);
|
||||
assert.ok(tool);
|
||||
const response = await client.callTool({
|
||||
name: "binary_session",
|
||||
arguments: {},
|
||||
});
|
||||
assert.notEqual(response.isError, true);
|
||||
const inventory = toolAvailabilityInventory.parse(
|
||||
response.structuredContent?.result?.tool_availability,
|
||||
);
|
||||
const group = inventory.groups.find(({ names }) => names.includes(tool.name));
|
||||
assert.ok(group);
|
||||
console.log(
|
||||
JSON.stringify({
|
||||
tool: tool.name,
|
||||
advertised_annotations: tool.annotations,
|
||||
session_effects: group.effects,
|
||||
session_annotations: group.annotations,
|
||||
catalog_tool_count: tools.length,
|
||||
}),
|
||||
);
|
||||
} catch (cause) {
|
||||
primaryError = cause;
|
||||
throw cause;
|
||||
} finally {
|
||||
await closeVerifierResources(
|
||||
[() => client.close(), () => transport.close()],
|
||||
primaryError,
|
||||
);
|
||||
}
|
||||
```
|
||||
|
||||
For the real workflow, follow the artifact acquisition/digest instructions in
|
||||
[module-reference verification](javascript-module-references-2026-10-15.md).
|
||||
Run its existing command with `--mode references --rounds 1 --cli-parity` and the
|
||||
same selected source paths and tokenizer. That verifier is unchanged by this
|
||||
fix. The preserved 8 GiB cgroup observer and its source hashes are documented in
|
||||
the same guide. The machine-readable records separate metadata-probe resources
|
||||
from the complete real-workflow resources.
|
||||
@@ -647,7 +647,11 @@ export const TOOL_EFFECTS: Readonly<Record<string, ToolEffects>> = {
|
||||
}),
|
||||
list_javascript_runtime_targets: browserEvidence,
|
||||
observe_javascript_runtime: browserEvidence,
|
||||
analyze_javascript_application: evidence,
|
||||
analyze_javascript_application: effects({
|
||||
mutatesSession: true,
|
||||
writesFilesystem: true,
|
||||
launchesProcess: true,
|
||||
}),
|
||||
inspect_electron_fuses: evidence,
|
||||
export_web_scripts: effects({
|
||||
mutatesSession: true,
|
||||
|
||||
@@ -25,6 +25,7 @@ import { writeElectronBoundaryFixture } from "../../fixtures/electronBoundaryApp
|
||||
import { createElectronActiveObservationFixtureResult } from "../../../src/domain/javascript/electronActiveObservation.fixture.js";
|
||||
import { parseMcpToolError } from "../../fixtures/mcpToolError.js";
|
||||
import { AsarArtifactReader } from "../../../src/artifacts/AsarArtifactReader.js";
|
||||
import { toolAvailabilityInventory } from "../../../src/contracts/toolOutputSchemaPrimitives.js";
|
||||
|
||||
const browsers: FakeCdpBrowser[] = [];
|
||||
const resources: Array<{ close(): Promise<unknown> }> = [];
|
||||
@@ -138,6 +139,47 @@ it("lets MCP JavaScript analysis continue only with recorded untrusted ASAR byte
|
||||
});
|
||||
});
|
||||
|
||||
it("advertises owned JavaScript analysis effects without foreign target execution", async () => {
|
||||
const session = createTestBinarySession(() => ({
|
||||
execute: () => Promise.resolve(observed(null)),
|
||||
close: () => Promise.resolve(resultOk(null)),
|
||||
}));
|
||||
const server = createServer({ kind: "session", session });
|
||||
const client = new Client({
|
||||
name: "javascript-analysis-effects",
|
||||
version: "1",
|
||||
});
|
||||
const [clientTransport, serverTransport] =
|
||||
InMemoryTransport.createLinkedPair();
|
||||
resources.push(client, server, session);
|
||||
await server.connect(serverTransport);
|
||||
await client.connect(clientTransport);
|
||||
|
||||
const status = await client.callTool({
|
||||
name: "binary_session",
|
||||
arguments: {},
|
||||
});
|
||||
expect(status.isError).not.toBe(true);
|
||||
const { result } = z
|
||||
.object({
|
||||
result: z.object({ tool_availability: toolAvailabilityInventory }),
|
||||
})
|
||||
.parse(status.structuredContent);
|
||||
const analysisAvailability = result.tool_availability.groups.find(
|
||||
({ names }) => names.includes("analyze_javascript_application"),
|
||||
);
|
||||
expect(analysisAvailability?.effects.toSorted()).toEqual([
|
||||
"idempotent",
|
||||
"launchesProcess",
|
||||
"mutatesSession",
|
||||
"writesFilesystem",
|
||||
]);
|
||||
expect(analysisAvailability?.annotations.toSorted()).toEqual([
|
||||
"idempotent",
|
||||
"open_world",
|
||||
]);
|
||||
});
|
||||
|
||||
it("exposes endpoint-scoped Electron discovery and inspection as Evidence", async () => {
|
||||
const root = await createTestTempDirectory("rea-electron-mcp-");
|
||||
temporary.push(root);
|
||||
|
||||
@@ -129,6 +129,12 @@ function expectKnownAuthorityHints(tools: readonly ToolSchemas[]): void {
|
||||
idempotentHint: false,
|
||||
openWorldHint: false,
|
||||
},
|
||||
analyze_javascript_application: {
|
||||
readOnlyHint: false,
|
||||
destructiveHint: false,
|
||||
idempotentHint: true,
|
||||
openWorldHint: true,
|
||||
},
|
||||
capture_process_scenario: {
|
||||
readOnlyHint: false,
|
||||
destructiveHint: true,
|
||||
|
||||
Reference in New Issue
Block a user