feat(scraper-create): write {collector_id, ...} envelope to -o

README.md

@@ -319,24 +319,58 @@ brightdata scraper create <url> <description> [options]
 | `--name <name>` | Scraper template name (default: `cli-scraper-<timestamp>`) |
 | `--deliver-webhook <url>` | Webhook URL for the deliver stub (default: `https://example.com/webhook`) |
 | `--timeout <seconds>` | Polling timeout in seconds (default: `600`) |
-| `-o, --output <path>` | Write output to file |
+| `-o, --output <path>` | Write the JSON envelope to a file (see below) |
 | `--json` / `--pretty` | JSON output (raw / indented) |
+| `--legacy-output` | Write the pre-v0.3 bare AI-progress payload to `-o` instead of the envelope. Migration only. |
 | `--timing` | Show request timing |
 | `-k, --api-key <key>` | Override API key |
 
 > **Note:** The scraper is created with a placeholder webhook delivery target (`https://example.com/webhook`). You can reconfigure the actual delivery endpoint in the [Bright Data web UI](https://brightdata.com/cp/scrapers) after creation.
 
+#### Output envelope (`-o create.json`)
+
+Every termination path — success or failure — writes the same JSON envelope shape:
+
+```json
+{
+  "collector_id":    "c_mp7x8a9b2c0d1e2f",
+  "name":            "my-product-scraper",
+  "status":          "done",
+  "completed_steps": ["prepare_intent_analyzer", "planner", "..."],
+  "view_url":        "https://brightdata.com/cp/scrapers/c_mp7x8a9b2c0d1e2f",
+  "created_at":      "2026-05-18T07:28:30Z"
+}
+```
+
+On failure paths the envelope adds an `error` field and the `status` reflects the failure category (`ai_trigger_failed`, `failed`, `poll_failed`). The `collector_id` and `view_url` are still present so you can recover or inspect the half-built scraper.
+
+This makes the documented chain in [recipes.md](https://github.com/brightdata/skills/blob/main/skills/scraper-studio/references/recipes.md) work as written:
+
+```bash
+brightdata scraper create https://example.com/product/1 "..." \
+    -o create.json
+COLLECTOR_ID=$(jq -r '.collector_id' create.json)
+brightdata scraper run "$COLLECTOR_ID" https://example.com/product/2
+```
+
+> The file format follows the `-o` extension, so `.json` is written compact (ideal for `jq`). Use `--pretty` for indented JSON on stdout when you omit `-o`.
+
+Use `--legacy-output` if you have an existing script that depended on the pre-v0.3 bare-progress shape; the flag is supported for one minor version while you migrate.
+
 **Examples**
 
 ```bash
 # Build a scraper for a product page
 brightdata scraper create https://example.com/product/1 \
     "Extract title, price, and image URL from this product page"
 
-# Name the scraper and save the full AI output to a file
+# Name the scraper and save the envelope to a file
 brightdata scraper create https://example.com/product/1 \
     "Extract title, price, and image URL from this product page" \
-    --name my-product-scraper --pretty -o scraper-output.json
+    --name my-product-scraper -o create.json
+
+# Capture the collector_id for chaining
+COLLECTOR_ID=$(jq -r '.collector_id' create.json)
 
 # Use a custom webhook delivery URL
 brightdata scraper create https://example.com/product/1 \

src/__tests__/commands/scraper.test.ts

@@ -50,6 +50,7 @@ import {
     extract_progress_status,
     format_create_summary,
     handle_create_scraper,
+    build_create_envelope,
     handle_run_scraper,
     build_run_request,
     build_run_query,
@@ -115,7 +116,7 @@ describe('commands/scraper', ()=>{
             expect(extract_progress_status({status: 'done'})).toBe('done');
         });
 
-        it('returns sentinel running token for any non-done status', ()=>{
+        it('returns sentinel running token for in-progress statuses', ()=>{
             expect(extract_progress_status({status: 'running'}))
                 .toBe('__running__');
             expect(extract_progress_status({status: 'queued'}))
@@ -124,6 +125,16 @@ describe('commands/scraper', ()=>{
                 .toBe('__running__');
         });
 
+        it('returns terminal failure statuses verbatim so polling stops',
+            ()=>{
+            expect(extract_progress_status({status: 'failed'}))
+                .toBe('failed');
+            expect(extract_progress_status({status: 'error'}))
+                .toBe('error');
+            expect(extract_progress_status({status: 'cancelled'}))
+                .toBe('cancelled');
+        });
+
         it('returns undefined for missing/invalid input', ()=>{
             expect(extract_progress_status(null as never)).toBeUndefined();
             expect(extract_progress_status({} as never)).toBeUndefined();
@@ -149,6 +160,212 @@ describe('commands/scraper', ()=>{
         });
     });
 
+    describe('build_create_envelope', ()=>{
+        it('returns the documented success shape', ()=>{
+            const env = build_create_envelope({
+                collector_id: 'c_xyz',
+                name: 'product-v1',
+                status: 'done',
+                progress: {status: 'done',
+                    completed_steps: ['a', 'b', 'c']},
+                created_at: '2026-05-18T07:28:30Z',
+            });
+            expect(env).toEqual({
+                collector_id: 'c_xyz',
+                name: 'product-v1',
+                status: 'done',
+                completed_steps: ['a', 'b', 'c'],
+                view_url: 'https://brightdata.com/cp/scrapers/c_xyz',
+                created_at: '2026-05-18T07:28:30Z',
+            });
+        });
+
+        it('omits created_at when not known', ()=>{
+            const env = build_create_envelope({
+                collector_id: 'c_xyz',
+                name: 'n',
+                status: 'done',
+                progress: {status: 'done', completed_steps: []},
+            });
+            expect(env).not.toHaveProperty('created_at');
+        });
+
+        it('records the error message and partial steps on failure',
+            ()=>{
+            const env = build_create_envelope({
+                collector_id: 'c_xyz',
+                name: 'n',
+                status: 'ai_trigger_failed',
+                error: 'Cannot run more than 3 jobs in parallel',
+            });
+            expect(env.collector_id).toBe('c_xyz');
+            expect(env.status).toBe('ai_trigger_failed');
+            expect(env.error).toMatch(/parallel/);
+            expect(env.completed_steps).toEqual([]);
+            expect(env.view_url)
+                .toBe('https://brightdata.com/cp/scrapers/c_xyz');
+        });
+
+        it('still includes view_url on every termination path', ()=>{
+            for (const status of ['done', 'failed', 'ai_trigger_failed',
+                'poll_failed'])
+            {
+                const env = build_create_envelope({
+                    collector_id: 'c_xyz', name: 'n', status,
+                });
+                expect(env.view_url)
+                    .toBe('https://brightdata.com/cp/scrapers/c_xyz');
+            }
+        });
+    });
+
+    describe('handle_create_scraper envelope output', ()=>{
+        const setup_success = ()=>{
+            mocks.post
+                .mockResolvedValueOnce({
+                    id: 'c_xyz', name: 'product-v1',
+                    created: '2026-05-18T07:28:30Z',
+                })
+                .mockResolvedValueOnce({id: 'ia_xyz', queued: false});
+            mocks.poll_until.mockResolvedValue({
+                result: {status: 'done',
+                    completed_steps: ['a', 'b', 'c']},
+                attempts: 4,
+            });
+        };
+
+        it('writes the new envelope to -o on success', async()=>{
+            setup_success();
+            await handle_create_scraper(
+                'https://x.com/p', 'd',
+                {output: 'create.json', pretty: true}
+            );
+            expect(mocks.print).toHaveBeenCalledWith(
+                expect.objectContaining({
+                    collector_id: 'c_xyz',
+                    name: 'product-v1',
+                    status: 'done',
+                    completed_steps: ['a', 'b', 'c'],
+                    view_url: 'https://brightdata.com/cp/scrapers/c_xyz',
+                    created_at: '2026-05-18T07:28:30Z',
+                }),
+                expect.objectContaining({output: 'create.json'})
+            );
+        });
+
+        it('the documented `jq -r .collector_id` recipe works on the '
+            +'envelope', async()=>{
+            setup_success();
+            await handle_create_scraper('https://x.com/p', 'd',
+                {output: 'create.json'});
+            const written = mocks.print.mock.calls[0][0] as {
+                collector_id?: string};
+            expect(written.collector_id).toBe('c_xyz');
+        });
+
+        it('--legacy-output preserves the bare progress payload',
+            async()=>{
+            setup_success();
+            await handle_create_scraper(
+                'https://x.com/p', 'd',
+                {output: 'create.json', legacyOutput: true}
+            );
+            const written = mocks.print.mock.calls[0][0] as {
+                collector_id?: unknown; status?: string};
+            expect(written.collector_id).toBeUndefined();
+            expect(written).not.toHaveProperty('view_url');
+            expect(written.status).toBe('done');
+        });
+
+        it('writes the envelope when AI trigger fails (stub-collector '
+            +'recovery path), with a single-line error', async()=>{
+            // multi-line client error -> envelope keeps the first line.
+            mocks.post
+                .mockResolvedValueOnce({id: 'c_stub', name: 'n'})
+                .mockRejectedValueOnce(new Error(
+                    'Error: Cannot run more than 3 jobs in parallel\n'
+                    +'  Status: 429\n  Hint: serialise your launches.'));
+            const exit = vi.spyOn(process, 'exit')
+                .mockImplementation(()=>undefined as never);
+            const error = vi.spyOn(console, 'error')
+                .mockImplementation(()=>{});
+            await handle_create_scraper(
+                'https://x.com/p', 'd',
+                {output: 'create.json'}
+            );
+            expect(mocks.print).toHaveBeenCalledWith(
+                expect.objectContaining({
+                    collector_id: 'c_stub',
+                    status: 'ai_trigger_failed',
+                    error: 'Cannot run more than 3 jobs in parallel',
+                    view_url: 'https://brightdata.com/cp/scrapers/c_stub',
+                }),
+                expect.objectContaining({output: 'create.json'})
+            );
+            exit.mockRestore();
+            error.mockRestore();
+        });
+
+        it('writes the envelope when poll returns status != done',
+            async()=>{
+            mocks.post
+                .mockResolvedValueOnce({id: 'c_abc', name: 'n'})
+                .mockResolvedValueOnce({id: 'ia_xyz', queued: false});
+            mocks.poll_until.mockResolvedValue({
+                result: {status: 'failed',
+                    completed_steps: ['planner']},
+                attempts: 2,
+            });
+            const exit = vi.spyOn(process, 'exit')
+                .mockImplementation(()=>undefined as never);
+            const error = vi.spyOn(console, 'error')
+                .mockImplementation(()=>{});
+            await handle_create_scraper(
+                'https://x.com/p', 'd',
+                {output: 'create.json'}
+            );
+            expect(mocks.print).toHaveBeenCalledWith(
+                expect.objectContaining({
+                    collector_id: 'c_abc',
+                    status: 'failed',
+                    completed_steps: ['planner'],
+                    error: expect.stringMatching(/finished with status/),
+                }),
+                expect.objectContaining({output: 'create.json'})
+            );
+            exit.mockRestore();
+            error.mockRestore();
+        });
+
+        it('writes the envelope when polling itself throws (timeout '
+            +'or network)', async()=>{
+            mocks.post
+                .mockResolvedValueOnce({id: 'c_abc', name: 'n'})
+                .mockResolvedValueOnce({id: 'ia_xyz', queued: false});
+            mocks.poll_until.mockRejectedValue(
+                new Error(
+                    'Timeout after 600 seconds waiting for AI generation'));
+            const exit = vi.spyOn(process, 'exit')
+                .mockImplementation(()=>undefined as never);
+            const error = vi.spyOn(console, 'error')
+                .mockImplementation(()=>{});
+            await handle_create_scraper(
+                'https://x.com/p', 'd',
+                {output: 'create.json'}
+            );
+            expect(mocks.print).toHaveBeenCalledWith(
+                expect.objectContaining({
+                    collector_id: 'c_abc',
+                    status: 'poll_failed',
+                    error: expect.stringMatching(/Timeout/),
+                }),
+                expect.objectContaining({output: 'create.json'})
+            );
+            exit.mockRestore();
+            error.mockRestore();
+        });
+    });
+
     describe('handle_create_scraper', ()=>{
         it('chains create → trigger → poll and prints JSON in non-TTY',
             async()=>{
@@ -195,7 +412,13 @@ describe('commands/scraper', ()=>{
                 })
             );
             expect(mocks.print).toHaveBeenCalledWith(
-                progress,
+                expect.objectContaining({
+                    collector_id: 'c_abc',
+                    name: 'cli-scraper-1',
+                    status: 'done',
+                    completed_steps: ['a', 'b'],
+                    view_url: 'https://brightdata.com/cp/scrapers/c_abc',
+                }),
                 {json: undefined, pretty: undefined, output: undefined}
             );
         });
@@ -209,7 +432,10 @@ describe('commands/scraper', ()=>{
                 result: progress, attempts: 1});
             await handle_create_scraper('https://x.com', 'd', {json: true});
             expect(mocks.print).toHaveBeenCalledWith(
-                progress,
+                expect.objectContaining({
+                    collector_id: 'c_abc',
+                    status: 'done',
+                }),
                 {json: true, pretty: undefined, output: undefined}
             );
         });