feat(hub): external capability registry for PDF/ASR transforms (ADR-0027) (#5)

Co-authored-by: Hong Jiarong <me@jrhim.com> Co-committed-by: Hong Jiarong <me@jrhim.com>
2026-07-18 15:55:02 +08:00
parent aaa098bb8b
commit b673dd1fe9
10 changed files with 1057 additions and 1 deletions
@@ -0,0 +1,152 @@
+/**
+ * ADR-0027: pdf_to_md_bundle capability adapter.
+ *
+ * Converts a PDF in the run's workspace into a Markdown bundle (md + extracted
+ * images) by calling the MinerU document parsing service, writing outputs into
+ * the workspace, and recording consumption on a UsageFact (ADR-0026).
+ *
+ * Invariants (ADR-0027):
+ *   1. Credential isolation — the capability credential is resolved in Hub and
+ *      never reaches the Agent process. The MineruClient receives it as a
+ *      call argument, not from the environment.
+ *   2. Workspace containment — input and output paths are confined to the
+ *      run's workspace dir (ADR-0018 AgentSurface). Escapes are rejected.
+ *   3. Mandatory fact — a successful invocation always writes ≥1 UsageFact
+ *      with kind=external_capability, even when costUsd is null (ADR-0022:
+ *      missing cost ≠ zero).
+ */
+import { mkdir, writeFile } from "node:fs/promises";
+import { join, resolve, relative, isAbsolute } from "node:path";
+import type { PrismaClient } from "@prisma/client";
+import { LocalSecretEnvelope } from "../security/secretEnvelope.js";
+import { resolveCapabilityCredential } from "./capabilityConnections.js";
+import { MineruClientError, type MineruClient } from "./mineruClient.js";
+import {
+  CAPABILITIES,
+  type CapabilityAdapter,
+  type CapabilityInvocationInput,
+  type CapabilityInvocationResult,
+  type CapabilityOutputArtifact,
+} from "./types.js";
+
+const CAPABILITY_ID = "pdf_to_md_bundle" as const;
+const PROVIDER_ID = "mineru";
+
+/** Thrown when a requested path escapes the workspace root (ADR-0018). */
+export class CapabilityPathEscape extends Error {
+  constructor(readonly requested: string, readonly workspaceDir: string) {
+    super(`capability path escapes workspace: ${requested} (root ${workspaceDir})`);
+    this.name = "CapabilityPathEscape";
+  }
+}
+
+/** Resolve a workspace-relative path, rejecting escapes (ADR-0018 AgentSurface). */
+function confineToWorkspace(requestedPath: string, workspaceDir: string): string {
+  if (isAbsolute(requestedPath)) {
+    const rel = relative(workspaceDir, requestedPath);
+    if (rel.startsWith("..") || rel === "") {
+      throw new CapabilityPathEscape(requestedPath, workspaceDir);
+    }
+    return requestedPath;
+  }
+  const resolved = resolve(workspaceDir, requestedPath);
+  const rel = relative(workspaceDir, resolved);
+  if (rel.startsWith("..")) {
+    throw new CapabilityPathEscape(requestedPath, workspaceDir);
+  }
+  return resolved;
+}
+
+export interface PdfToMdBundleDeps {
+  readonly secrets: LocalSecretEnvelope;
+  readonly client: MineruClient;
+  readonly prisma: PrismaClient;
+}
+
+/** Build the pdf_to_md_bundle adapter. The MineruClient is injectable for testing. */
+export function createPdfToMdBundleAdapter(deps: PdfToMdBundleDeps): CapabilityAdapter {
+  return {
+    capabilityId: CAPABILITY_ID,
+    async invoke(input: CapabilityInvocationInput): Promise<CapabilityInvocationResult> {
+      const descriptor = CAPABILITIES[CAPABILITY_ID];
+      // 1. Resolve org-scoped credential (fail-closed, ADR-0024/0027).
+      const credential = await resolveCapabilityCredential(deps.prisma, deps.secrets, {
+        organizationId: input.organizationId,
+        capabilityId: CAPABILITY_ID,
+      });
+
+      // 2. Confine input + output paths to the workspace (ADR-0018).
+      const absoluteInput = confineToWorkspace(input.inputPath, input.workspaceDir);
+      const absoluteOutputDir = confineToWorkspace(input.outputDir, input.workspaceDir);
+      await mkdir(absoluteOutputDir, { recursive: true });
+
+      // 3. Call the backing service.
+      let result;
+      try {
+        result = await deps.client.parse(credential, { inputFilePath: absoluteInput });
+      } catch (e) {
+        if (e instanceof MineruClientError) throw e;
+        throw new MineruClientError(
+          e instanceof Error ? e.message : String(e),
+          "mineru_unreachable",
+        );
+      }
+      if (result.markdown === "") {
+        throw new MineruClientError("MinerU returned empty markdown", "mineru_no_output");
+      }
+
+      // 4. Write outputs into the workspace.
+      const artifacts: CapabilityOutputArtifact[] = [];
+      const mdPath = join(absoluteOutputDir, "document.md");
+      await writeFile(mdPath, result.markdown, "utf8");
+      artifacts.push({ path: relative(input.workspaceDir, mdPath), kind: "markdown" });
+
+      for (const image of result.images) {
+        const imagePath = join(absoluteOutputDir, image.filename);
+        const rel = relative(absoluteOutputDir, imagePath);
+        if (rel.startsWith("..")) {
+          // Defensive: image filename must not escape the output dir.
+          throw new CapabilityPathEscape(image.filename, absoluteOutputDir);
+        }
+        await writeFile(imagePath, image.data);
+        artifacts.push({ path: relative(input.workspaceDir, imagePath), kind: "image" });
+      }
+
+      // 5. Write the UsageFact (ADR-0026/0027). Always written on success;
+      //    costUsd null means unknown, NOT zero (ADR-0022).
+      const occurredAt = new Date();
+      await deps.prisma.usageFact.create({
+        data: {
+          runId: input.runId,
+          occurredAt,
+          kind: "external_capability",
+          provider: PROVIDER_ID,
+          model: null,
+          inputTokens: null,
+          outputTokens: null,
+          quantity: result.pageCount,
+          unit: descriptor.meteringUnit,
+          costUsd: result.costUsd,
+          costSource: result.costUsd !== null ? "provider_reported" : "unknown",
+          capabilityId: CAPABILITY_ID,
+          correlationId: result.requestId,
+          metadata: {},
+        },
+      });
+
+      return {
+        artifacts,
+        consumption: {
+          provider: PROVIDER_ID,
+          model: null,
+          inputTokens: null,
+          outputTokens: null,
+          quantity: result.pageCount,
+          unit: descriptor.meteringUnit,
+          costUsd: result.costUsd,
+          correlationId: result.requestId,
+        },
+      };
+    },
+  };
+}