feat(data-process): 完善后台生成与失败重试

backend/app/db/sql/002_data_process.sql

@@ -80,6 +80,17 @@ CREATE TABLE IF NOT EXISTS data_process_tasks (
     error_count BIGINT NOT NULL DEFAULT 0 CHECK (error_count >= 0),
     failure_reason TEXT,
     generation_run_id TEXT,
+    results_confirmed BOOLEAN NOT NULL DEFAULT TRUE,
+    workflow_step VARCHAR(20) NOT NULL DEFAULT 'create'
+        CHECK (workflow_step IN ('create', 'model', 'upload', 'preview', 'generate', 'results')),
+    preview_status VARCHAR(20) NOT NULL DEFAULT 'idle'
+        CHECK (preview_status IN ('idle', 'queued', 'running', 'completed', 'failed', 'cancelled')),
+    preview_progress NUMERIC(5,2) NOT NULL DEFAULT 0
+        CHECK (preview_progress >= 0 AND preview_progress <= 100),
+    preview_run_id TEXT,
+    preview_failure_reason TEXT,
+    preview_total_files INTEGER NOT NULL DEFAULT 0 CHECK (preview_total_files >= 0),
+    preview_completed_files INTEGER NOT NULL DEFAULT 0 CHECK (preview_completed_files >= 0),
     tenant_id TEXT,
     project_id TEXT,
     owner_id TEXT,
@@ -95,6 +106,87 @@ CREATE TABLE IF NOT EXISTS data_process_tasks (
 );
 
 ALTER TABLE data_process_tasks ADD COLUMN IF NOT EXISTS generation_run_id TEXT;
+-- 历史任务在引入六步确认流程前已经完成审核，默认保留为已确认；
+-- 新任务由创建接口显式写入 FALSE，并在第六步确认后转为 TRUE。
+ALTER TABLE data_process_tasks
+    ADD COLUMN IF NOT EXISTS results_confirmed BOOLEAN NOT NULL DEFAULT TRUE;
+UPDATE data_process_tasks
+SET results_confirmed=FALSE
+WHERE status <> 'completed' AND results_confirmed=TRUE;
+
+-- 先以可空列接入旧库，才能只回填历史行；随后再收紧默认值与约束。
+ALTER TABLE data_process_tasks ADD COLUMN IF NOT EXISTS workflow_step VARCHAR(20);
+ALTER TABLE data_process_tasks ADD COLUMN IF NOT EXISTS preview_status VARCHAR(20);
+ALTER TABLE data_process_tasks ADD COLUMN IF NOT EXISTS preview_progress NUMERIC(5,2);
+ALTER TABLE data_process_tasks ADD COLUMN IF NOT EXISTS preview_run_id TEXT;
+ALTER TABLE data_process_tasks ADD COLUMN IF NOT EXISTS preview_failure_reason TEXT;
+ALTER TABLE data_process_tasks ADD COLUMN IF NOT EXISTS preview_total_files INTEGER;
+ALTER TABLE data_process_tasks ADD COLUMN IF NOT EXISTS preview_completed_files INTEGER;
+
+CREATE TEMP TABLE data_process_workflow_backfill_ids ON COMMIT DROP AS
+SELECT id FROM data_process_tasks WHERE workflow_step IS NULL;
+
+UPDATE data_process_tasks task
+SET workflow_step = CASE
+    WHEN task.status IN ('running', 'failed', 'stopped') THEN 'generate'
+    WHEN task.status = 'completed' AND task.results_confirmed=FALSE THEN 'generate'
+    WHEN task.status = 'completed' THEN 'results'
+    ELSE 'create'
+END
+WHERE task.workflow_step IS NULL;
+UPDATE data_process_tasks
+SET preview_status='idle', preview_progress=0,
+    preview_total_files=0, preview_completed_files=0
+WHERE preview_status IS NULL OR preview_progress IS NULL
+   OR preview_total_files IS NULL OR preview_completed_files IS NULL;
+
+ALTER TABLE data_process_tasks ALTER COLUMN workflow_step SET DEFAULT 'create';
+ALTER TABLE data_process_tasks ALTER COLUMN workflow_step SET NOT NULL;
+ALTER TABLE data_process_tasks ALTER COLUMN preview_status SET DEFAULT 'idle';
+ALTER TABLE data_process_tasks ALTER COLUMN preview_status SET NOT NULL;
+ALTER TABLE data_process_tasks ALTER COLUMN preview_progress SET DEFAULT 0;
+ALTER TABLE data_process_tasks ALTER COLUMN preview_progress SET NOT NULL;
+ALTER TABLE data_process_tasks ALTER COLUMN preview_total_files SET DEFAULT 0;
+ALTER TABLE data_process_tasks ALTER COLUMN preview_total_files SET NOT NULL;
+ALTER TABLE data_process_tasks ALTER COLUMN preview_completed_files SET DEFAULT 0;
+ALTER TABLE data_process_tasks ALTER COLUMN preview_completed_files SET NOT NULL;
+
+DO $$
+BEGIN
+    IF NOT EXISTS (
+        SELECT 1 FROM pg_constraint
+        WHERE conrelid='data_process_tasks'::regclass
+          AND conname='ck_data_process_tasks_workflow_step'
+    ) THEN
+        ALTER TABLE data_process_tasks ADD CONSTRAINT ck_data_process_tasks_workflow_step
+            CHECK (workflow_step IN ('create', 'model', 'upload', 'preview', 'generate', 'results'));
+    END IF;
+    IF NOT EXISTS (
+        SELECT 1 FROM pg_constraint
+        WHERE conrelid='data_process_tasks'::regclass
+          AND conname='ck_data_process_tasks_preview_status'
+    ) THEN
+        ALTER TABLE data_process_tasks ADD CONSTRAINT ck_data_process_tasks_preview_status
+            CHECK (preview_status IN ('idle', 'queued', 'running', 'completed', 'failed', 'cancelled'));
+    END IF;
+    IF NOT EXISTS (
+        SELECT 1 FROM pg_constraint
+        WHERE conrelid='data_process_tasks'::regclass
+          AND conname='ck_data_process_tasks_preview_progress'
+    ) THEN
+        ALTER TABLE data_process_tasks ADD CONSTRAINT ck_data_process_tasks_preview_progress
+            CHECK (preview_progress >= 0 AND preview_progress <= 100);
+    END IF;
+    IF NOT EXISTS (
+        SELECT 1 FROM pg_constraint
+        WHERE conrelid='data_process_tasks'::regclass
+          AND conname='ck_data_process_tasks_preview_file_counts'
+    ) THEN
+        ALTER TABLE data_process_tasks ADD CONSTRAINT ck_data_process_tasks_preview_file_counts
+            CHECK (preview_total_files >= 0 AND preview_completed_files >= 0
+                   AND preview_completed_files <= preview_total_files);
+    END IF;
+END $$;
 
 CREATE UNIQUE INDEX IF NOT EXISTS uq_data_process_tasks_name_alive
     ON data_process_tasks(name) WHERE deleted_at IS NULL;
@@ -153,6 +245,22 @@ CREATE TABLE IF NOT EXISTS data_process_preview_items (
 CREATE INDEX IF NOT EXISTS idx_data_process_preview_task_file
     ON data_process_preview_items(task_id, source_file_id, created_at);
 
+-- 子表在新库中到这里才存在；只修复本次新增 workflow_step 前的历史任务。
+UPDATE data_process_tasks task
+SET workflow_step = CASE
+    WHEN EXISTS (
+        SELECT 1 FROM data_process_preview_items preview
+        WHERE preview.task_id=task.id
+    ) THEN 'preview'
+    WHEN EXISTS (
+        SELECT 1 FROM data_process_source_files source_file
+        WHERE source_file.task_id=task.id AND source_file.deleted_at IS NULL
+    ) THEN 'upload'
+    ELSE task.workflow_step
+END
+WHERE task.id IN (SELECT id FROM data_process_workflow_backfill_ids)
+  AND task.status='pending';
+
 CREATE TABLE IF NOT EXISTS data_process_results (
     id TEXT PRIMARY KEY,
     task_id TEXT NOT NULL REFERENCES data_process_tasks(id) ON DELETE CASCADE,