dsh-data-cleaning-agent 0.7.0 → 0.8.1

package/lib/web.js

@@ -16,6 +16,13 @@ import { PHASE3_BATCH_LIMITS, Phase3BatchService, Phase3RunStore } from './qcc-p
 import { publicWorkflowContract } from './workflow-contract.js';
 import { DataCleaningWorkflowStore, WorkflowError } from './workflow.js';
 import { ArtifactError, WorkflowArtifactStore } from './artifacts.js';
+import {
+  ImageIntakeError,
+  ImageIntakeStore,
+  registerImageIntakeTool,
+  serializeImageExtractionPrompt,
+  TOOL_IMAGE_EXTRACT,
+} from './image-intake.js';
 
 const MAX_BODY = 16 * 1024 * 1024; // 16 MiB 上传上限（MVP）
 
@@ -119,6 +126,17 @@ function writeWorkflowError(res, error) {
   });
 }
 
+function writeImageError(res, error) {
+  if (error instanceof ImageIntakeError) {
+    return writeJson(res, error.status, { ok: false, code: error.code, message: error.message });
+  }
+  return writeJson(res, 500, {
+    ok: false,
+    code: 'DC_IMAGE_INTERNAL',
+    message: '图片名单接入请求失败。',
+  });
+}
+
 /** 从 JSON 协议解析上传：{ filename, content }。content 为字符串；xlsx 时为 base64。 */
 async function parseUpload(body) {
   let payload;
@@ -285,13 +303,17 @@ export function mountWebRoutes(wctx, { logger, report, TOOL_NAME, SKILL_NAME })
   const skills = wctx.skills;
   const disposers = [];
   const qccBridge = new QccHostBridge({ tools, logger });
+  const imageIntake = new ImageIntakeStore({ tools });
   const g5Runs = new G5RunStore();
   const qccCommands = new QccCommandStore({ bridge: qccBridge, runs: g5Runs });
   if (typeof tools?.register === 'function') {
     disposers.push(registerQccCommandTool(tools, qccCommands));
+    disposers.push(registerImageIntakeTool(tools, imageIntake));
     report.qccCommandToolRegistered = true;
+    report.imageIntakeToolRegistered = true;
   } else {
     report.qccCommandToolRegistered = false;
+    report.imageIntakeToolRegistered = false;
   }
   const phase3Service = new Phase3BatchService(qccBridge);
   const phase3Runs = new Phase3RunStore();
@@ -347,11 +369,65 @@ export function mountWebRoutes(wctx, { logger, report, TOOL_NAME, SKILL_NAME })
         workflowV2: Boolean(wctx.storageDomain),
         durableArtifacts: Boolean(artifactStore),
         artifactBinaryStrategy: artifactStore ? 'xlsx-base64-over-writeText' : 'unavailable',
+        imageIntake: imageIntake.capabilities(),
         qccBridge: qccBridge.capabilities(),
       },
     });
   });
 
+  register('/data-cleaning/api/images/capabilities', (req, res) => {
+    if (!isTrusted(req)) return writeJson(res, 403, { ok: false, error: 'untrusted origin' });
+    if (req.method !== 'GET') return writeJson(res, 405, { ok: false, code: 'DC_METHOD', message: 'GET required' });
+    writeJson(res, 200, {
+      ok: true,
+      marker: 'data-cleaning-image-intake-v1',
+      tool: TOOL_IMAGE_EXTRACT,
+      toolRegistered: report.imageIntakeToolRegistered === true,
+      capabilities: imageIntake.capabilities(),
+      qccCalls: true,
+      billing: 'current-user-qcc-document-account',
+    });
+  });
+
+  register('/data-cleaning/api/images/commands', async (req, res) => {
+    if (!isTrusted(req)) return writeJson(res, 403, { ok: false, error: 'untrusted origin' });
+    try {
+      const pathname = new URL(req.url ?? '/data-cleaning/api/images/commands', 'http://127.0.0.1').pathname;
+      const segments = pathname.split('/').filter(Boolean);
+      const commandsIndex = segments.indexOf('commands');
+      const rest = commandsIndex >= 0 ? segments.slice(commandsIndex + 1) : [];
+      if (rest.length === 0 && req.method === 'POST') {
+        if (report.imageIntakeToolRegistered !== true) {
+          throw new ImageIntakeError('DC_IMAGE_TOOL_UNAVAILABLE', '当前 DSH Host 无法注册图片名单高层工具。', 503);
+        }
+        const payload = JSON.parse((await readBody(req)).toString('utf8'));
+        const command = await imageIntake.prepare(payload);
+        return writeJson(res, 201, {
+          ok: true,
+          marker: 'data-cleaning-image-intake-v1',
+          command: { ...command, prompt: serializeImageExtractionPrompt(command) },
+        });
+      }
+      if (rest.length === 1 && req.method === 'GET') {
+        return writeJson(res, 200, {
+          ok: true,
+          marker: 'data-cleaning-image-intake-v1',
+          command: imageIntake.status(decodeURIComponent(rest[0])),
+        });
+      }
+      if (rest.length === 1 && req.method === 'DELETE') {
+        await imageIntake.remove(decodeURIComponent(rest[0]));
+        return writeJson(res, 200, { ok: true, marker: 'data-cleaning-image-intake-v1', removed: true });
+      }
+      return writeJson(res, 405, { ok: false, code: 'DC_METHOD', message: 'POST a command, GET its status, or DELETE it.' });
+    } catch (error) {
+      if (error instanceof SyntaxError) {
+        return writeJson(res, 400, { ok: false, code: 'DC_BAD_JSON', message: 'Request body must be valid JSON.' });
+      }
+      return writeImageError(res, error);
+    }
+  });
+
   register('/data-cleaning/api/workflow/contract', (req, res) => {
     if (!isTrusted(req)) return writeJson(res, 403, { ok: false, error: 'untrusted origin' });
     if (req.method !== 'GET') {
@@ -955,6 +1031,7 @@ export function mountWebRoutes(wctx, { logger, report, TOOL_NAME, SKILL_NAME })
   return () => {
     if (state) { state.dispose().catch(() => {}); }
     if (workflow) { workflow.dispose().catch(() => {}); }
+    imageIntake.dispose().catch(() => {});
     for (const dispose of disposers) dispose();
   };
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-data-cleaning-agent",
-  "version": "0.7.0",
+  "version": "0.8.1",
   "description": "Clean, complete, and profile enterprise name lists in DeepSeek Harness — a data cleaning & completion agent plugin with local CSV/XLSX/JSON engine and optional Qichacha (QCC) MCP enrichment. Maintained by Qichacha/QCC.",
   "type": "module",
   "main": "lib/index.js",
@@ -36,6 +36,8 @@
     "docs/RELEASE-0.6.2.md",
     "docs/RELEASE-0.6.3.md",
     "docs/RELEASE-0.7.0.md",
+    "docs/RELEASE-0.8.0.md",
+    "docs/RELEASE-0.8.1.md",
     "docs/UI-WORKFLOW-V2.md",
     "docs/UI-WORKFLOW-V2-MIGRATION.md",
     "docs/UI-WORKFLOW-V2-ACCEPTANCE.md",
@@ -44,7 +46,7 @@
   ],
   "scripts": {
     "test": "node --test",
-    "lint": "node --check lib/index.js && node --check lib/engine.js && node --check lib/artifacts.js && node --check lib/tools.js && node --check lib/skill.js && node --check lib/qcc-field-catalog.js && node --check lib/qcc-phase2.js && node --check lib/qcc-phase3.js && node --check lib/qcc-phase3-batch.js && node --check lib/qcc-phase2-acceptance.js && node --check lib/skill-enrich.js && node --check lib/jobs.js && node --check lib/workflow-contract.js && node --check lib/workflow.js && node --check lib/qcc-safety.js && node --check lib/qcc.js && node --check lib/qcc-command.js && node --check lib/qcc-runs.js && node --check lib/web.js && node --check lib/client.js && node --check scripts/check-readme-version.mjs && node --check scripts/check-market-registration.mjs && node --check scripts/g5-e2e.mjs && node --check scripts/phase3-e2e.mjs && node --check scripts/phase2-acceptance.mjs",
+    "lint": "node --check lib/index.js && node --check lib/engine.js && node --check lib/artifacts.js && node --check lib/image-intake.js && node --check lib/tools.js && node --check lib/skill.js && node --check lib/qcc-field-catalog.js && node --check lib/qcc-phase2.js && node --check lib/qcc-phase3.js && node --check lib/qcc-phase3-batch.js && node --check lib/qcc-phase2-acceptance.js && node --check lib/skill-enrich.js && node --check lib/jobs.js && node --check lib/workflow-contract.js && node --check lib/workflow.js && node --check lib/qcc-safety.js && node --check lib/qcc.js && node --check lib/qcc-command.js && node --check lib/qcc-runs.js && node --check lib/web.js && node --check lib/client.js && node --check scripts/check-readme-version.mjs && node --check scripts/check-market-registration.mjs && node --check scripts/g5-e2e.mjs && node --check scripts/phase3-e2e.mjs && node --check scripts/phase2-acceptance.mjs",
     "docs:check": "node scripts/check-readme-version.mjs",
     "marketing:check": "node scripts/check-marketing.mjs",
     "verify-pack": "node scripts/verify-pack.mjs",