test-wuying-agentbay-sdk 0.13.1-beta.20251224094729 → 0.13.1-beta.20251224103203

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (14) hide show
  1. package/dist/index.cjs +293 -160
  2. package/dist/index.cjs.map +1 -1
  3. package/dist/index.d.mts +83 -12
  4. package/dist/index.d.ts +83 -12
  5. package/dist/index.mjs +248 -115
  6. package/dist/index.mjs.map +1 -1
  7. package/docs/api/README.md +1 -0
  8. package/docs/api/common-features/advanced/agent.md +3 -4
  9. package/docs/api/common-features/advanced/browser-use-agent.md +42 -42
  10. package/docs/api/common-features/advanced/computer-use-agent.md +43 -43
  11. package/docs/api/common-features/advanced/mobile-use-agent.md +57 -71
  12. package/docs/api/common-features/basics/filesystem.md +91 -27
  13. package/docs/api/common-features/basics/logging.md +7 -0
  14. package/package.json +1 -1
package/docs/api/README.md CHANGED
@@ -14,6 +14,7 @@ These documents are generated automatically using TypeDoc. Run `npm run docs:gen
14
14
  - agent.md
15
15
  - browser-use-agent.md
16
16
  - computer-use-agent.md
17
+ - mobile-use-agent.md
17
18
  - oss.md
18
19
  - `common-features/basics`
19
20
  - agentbay.md
package/docs/api/common-features/advanced/agent.md CHANGED
@@ -5,10 +5,9 @@
5
5
  - [Agent Modules Guide](../../../../../docs/guides/common-features/advanced/agent-modules.md) - Learn about agent modules and custom agents
6
6
 
7
7
  An Agent to manipulate applications to complete specific tasks.
8
- According to the use scenary, The agent can be a browser use agent which is
9
- specialized for browser automation tasks, a computer use agent which is
10
- specialized for multiple applications automation tasks, or a mobile use agent
11
- which is specialized for mobile device automation tasks.
8
+ According to the use scenary, The agent can a browser use agent which is
9
+ specialized for browser automation tasks, The agent also can be a computer
10
+ use agent which is specialized for multiple applications automation tasks.
12
11
 
13
12
  ## Table of contents
14
13
 
package/docs/api/common-features/advanced/browser-use-agent.md CHANGED
@@ -1,14 +1,45 @@
1
1
  # Class: BrowserUseAgent
2
2
 
3
+ ## Hierarchy
4
+
5
+ - `BaseTaskAgent`
6
+
7
+ ↳ **`BrowserUseAgent`**
8
+
3
9
  ## Table of contents
4
10
 
5
11
 
12
+ ### Properties
13
+
14
+ - [session](#session)
15
+ - [toolPrefix](#toolprefix)
16
+
6
17
  ### Methods
7
18
 
8
19
  - [executeTask](#executetask)
9
20
  - [initialize](#initialize)
10
21
  - [terminateTask](#terminatetask)
11
22
 
23
+ ## Properties
24
+
25
+ ### session
26
+
27
+ • `Protected` **session**: ``McpSession``
28
+
29
+ #### Inherited from
30
+
31
+ BaseTaskAgent.session
32
+
33
+ ___
34
+
35
+ ### toolPrefix
36
+
37
+ • `Protected` **toolPrefix**: `string` = `'browser_use'`
38
+
39
+ #### Overrides
40
+
41
+ BaseTaskAgent.toolPrefix
42
+
12
43
  ## Methods
13
44
 
14
45
  ### executeTask
@@ -19,32 +50,18 @@ Execute a specific task described in human language.
19
50
 
20
51
  #### Parameters
21
52
 
22
- | Name | Type | Description |
23
- | :------ | :------ | :------ |
24
- | `task` | `string` | Task description in human language. |
25
- | `maxTryTimes` | `number` | Maximum number of retry attempts. |
53
+ | Name | Type |
54
+ | :------ | :------ |
55
+ | `task` | `string` |
56
+ | `maxTryTimes` | `number` |
26
57
 
27
58
  #### Returns
28
59
 
29
60
  `Promise`\<``ExecutionResult``\>
30
61
 
31
- ExecutionResult containing success status, task output, and
32
- error message if any.
62
+ #### Inherited from
33
63
 
34
- **`Example`**
35
-
36
- ```typescript
37
- const agentBay = new AgentBay({ apiKey: 'your_api_key' });
38
- const result = await agentBay.create({ imageId: 'linux_latest' });
39
- if (result.success) {
40
- const taskResult = await result.session.agent.browser.executeTask(
41
- 'Navigate to baidu and query the weather of Shanghai',
42
- 10
43
- );
44
- console.log(`Task status: ${taskResult.taskStatus}`);
45
- await result.session.delete();
46
- }
47
- ```
64
+ BaseTaskAgent.executeTask
48
65
 
49
66
  ### initialize
50
67
 
@@ -88,31 +105,14 @@ Terminate a task with a specified task ID.
88
105
 
89
106
  #### Parameters
90
107
 
91
- | Name | Type | Description |
92
- | :------ | :------ | :------ |
93
- | `taskId` | `string` | The ID of the running task. |
108
+ | Name | Type |
109
+ | :------ | :------ |
110
+ | `taskId` | `string` |
94
111
 
95
112
  #### Returns
96
113
 
97
114
  `Promise`\<``ExecutionResult``\>
98
115
 
99
- ExecutionResult containing success status, task output, and
100
- error message if any.
101
-
102
- **`Example`**
116
+ #### Inherited from
103
117
 
104
- ```typescript
105
- const agentBay = new AgentBay({ apiKey: 'your_api_key' });
106
- const result = await agentBay.create({ imageId: 'linux_latest' });
107
- if (result.success) {
108
- const taskResult = await result.session.agent.browser.executeTask(
109
- 'Navigate to baidu and query the weather of Shanghai',
110
- 10
111
- );
112
- const terminateResult = await result.session.agent.browser.terminateTask(
113
- taskResult.taskId
114
- );
115
- console.log(`Terminated: ${terminateResult.taskStatus}`);
116
- await result.session.delete();
117
- }
118
- ```
118
+ BaseTaskAgent.terminateTask
package/docs/api/common-features/advanced/computer-use-agent.md CHANGED
@@ -2,14 +2,45 @@
2
2
 
3
3
  An Agent to perform tasks on the computer.
4
4
 
5
+ ## Hierarchy
6
+
7
+ - `BaseTaskAgent`
8
+
9
+ ↳ **`ComputerUseAgent`**
10
+
5
11
  ## Table of contents
6
12
 
7
13
 
14
+ ### Properties
15
+
16
+ - [session](#session)
17
+ - [toolPrefix](#toolprefix)
18
+
8
19
  ### Methods
9
20
 
10
21
  - [executeTask](#executetask)
11
22
  - [terminateTask](#terminatetask)
12
23
 
24
+ ## Properties
25
+
26
+ ### session
27
+
28
+ • `Protected` **session**: ``McpSession``
29
+
30
+ #### Inherited from
31
+
32
+ BaseTaskAgent.session
33
+
34
+ ___
35
+
36
+ ### toolPrefix
37
+
38
+ • `Protected` **toolPrefix**: `string` = `'flux'`
39
+
40
+ #### Overrides
41
+
42
+ BaseTaskAgent.toolPrefix
43
+
13
44
  ## Methods
14
45
 
15
46
  ### executeTask
@@ -20,32 +51,18 @@ Execute a specific task described in human language.
20
51
 
21
52
  #### Parameters
22
53
 
23
- | Name | Type | Description |
24
- | :------ | :------ | :------ |
25
- | `task` | `string` | Task description in human language. |
26
- | `maxTryTimes` | `number` | Maximum number of retry attempts. |
54
+ | Name | Type |
55
+ | :------ | :------ |
56
+ | `task` | `string` |
57
+ | `maxTryTimes` | `number` |
27
58
 
28
59
  #### Returns
29
60
 
30
61
  `Promise`\<``ExecutionResult``\>
31
62
 
32
- ExecutionResult containing success status, task output, and error
33
- message if any.
63
+ #### Inherited from
34
64
 
35
- **`Example`**
36
-
37
- ```typescript
38
- const agentBay = new AgentBay({ apiKey: 'your_api_key' });
39
- const result = await agentBay.create({ imageId: 'windows_latest' });
40
- if (result.success) {
41
- const taskResult = await result.session.agent.computer.executeTask(
42
- 'Open notepad',
43
- 10
44
- );
45
- console.log(`Task status: ${taskResult.taskStatus}`);
46
- await result.session.delete();
47
- }
48
- ```
65
+ BaseTaskAgent.executeTask
49
66
 
50
67
  ### terminateTask
51
68
 
@@ -55,31 +72,14 @@ Terminate a task with a specified task ID.
55
72
 
56
73
  #### Parameters
57
74
 
58
- | Name | Type | Description |
59
- | :------ | :------ | :------ |
60
- | `taskId` | `string` | The ID of the running task. |
75
+ | Name | Type |
76
+ | :------ | :------ |
77
+ | `taskId` | `string` |
61
78
 
62
79
  #### Returns
63
80
 
64
81
  `Promise`\<``ExecutionResult``\>
65
82
 
66
- ExecutionResult containing success status, task output, and
67
- error message if any.
68
-
69
- **`Example`**
70
-
71
- ```typescript
72
- const agentBay = new AgentBay({ apiKey: 'your_api_key' });
73
- const result = await agentBay.create({ imageId: 'windows_latest' });
74
- if (result.success) {
75
- const taskResult = await result.session.agent.computer.executeTask(
76
- 'Open notepad',
77
- 5
78
- );
79
- const terminateResult = await result.session.agent.computer.terminateTask(
80
- taskResult.taskId
81
- );
82
- console.log(`Terminated: ${terminateResult.taskStatus}`);
83
- await result.session.delete();
84
- }
85
- ```
83
+ #### Inherited from
84
+
85
+ BaseTaskAgent.terminateTask
package/docs/api/common-features/advanced/mobile-use-agent.md CHANGED
@@ -2,37 +2,70 @@
2
2
 
3
3
  An Agent to perform tasks on mobile devices.
4
4
 
5
+ ## Hierarchy
6
+
7
+ - `BaseTaskAgent`
8
+
9
+ ↳ **`MobileUseAgent`**
10
+
5
11
  ## Table of contents
6
12
 
7
13
 
14
+ ### Properties
15
+
16
+ - [session](#session)
17
+ - [toolPrefix](#toolprefix)
18
+
8
19
  ### Methods
9
20
 
10
21
  - [executeTask](#executetask)
11
22
  - [executeTaskAndWait](#executetaskandwait)
12
- - [getTaskStatus](#gettaskstatus)
13
23
  - [terminateTask](#terminatetask)
14
24
 
25
+ ## Properties
26
+
27
+ ### session
28
+
29
+ • `Protected` **session**: ``McpSession``
30
+
31
+ #### Inherited from
32
+
33
+ BaseTaskAgent.session
34
+
35
+ ___
36
+
37
+ ### toolPrefix
38
+
39
+ • `Protected` **toolPrefix**: `string` = `''`
40
+
41
+ #### Overrides
42
+
43
+ BaseTaskAgent.toolPrefix
44
+
15
45
  ## Methods
16
46
 
17
47
  ### executeTask
18
48
 
19
49
  ▸ **executeTask**(`task`, `maxSteps?`, `maxStepRetries?`): `Promise`\<``ExecutionResult``\>
20
50
 
21
- Execute a task in human language without waiting for completion (non-blocking). This is a fire-and-return interface that immediately provides a task ID. Call getTaskStatus to check the task status.
51
+ Execute a task in human language without waiting for completion
52
+ (non-blocking). This is a fire-and-return interface that immediately
53
+ provides a task ID. Call getTaskStatus to check the task status.
22
54
 
23
55
  #### Parameters
24
56
 
25
57
  | Name | Type | Default value | Description |
26
58
  | :------ | :------ | :------ | :------ |
27
- | `task` | `string` | - | Task description in human language. |
28
- | `maxSteps` | `number` | `50` | Maximum number of steps (clicks/swipes/etc.) allowed. Used to prevent infinite loops or excessive resource consumption. |
29
- | `maxStepRetries` | `number` | `3` | Maximum retry times for MCP tool call failures at SDK level. Used to retry when callMcpTool fails (e.g., network errors, timeouts). |
59
+ | `task` | `string` | `undefined` | Task description in human language. |
60
+ | `maxSteps` | `number` | `50` | Maximum number of steps (clicks/swipes/etc.) allowed. Used to prevent infinite loops or excessive resource consumption. Default is 50. |
61
+ | `maxStepRetries` | `number` | `3` | Maximum retry times for MCP tool call failures at SDK level. Used to retry when callMcpTool fails (e.g., network errors, timeouts). Default is 3. |
30
62
 
31
63
  #### Returns
32
64
 
33
65
  `Promise`\<``ExecutionResult``\>
34
66
 
35
- ExecutionResult containing success status, task ID, task status, and error message if any.
67
+ ExecutionResult containing success status, task ID, task status,
68
+ and error message if any.
36
69
 
37
70
  **`Example`**
38
71
 
@@ -48,28 +81,36 @@ if (result.success) {
48
81
  }
49
82
  ```
50
83
 
84
+ #### Overrides
85
+
86
+ BaseTaskAgent.executeTask
87
+
51
88
  ___
52
89
 
53
90
  ### executeTaskAndWait
54
91
 
55
92
  ▸ **executeTaskAndWait**(`task`, `maxSteps?`, `maxStepRetries?`, `maxTryTimes?`): `Promise`\<``ExecutionResult``\>
56
93
 
57
- Execute a specific task described in human language synchronously. This is a synchronous interface that blocks until the task is completed or an error occurs, or timeout happens. The default polling interval is 3 seconds.
94
+ Execute a specific task described in human language synchronously.
95
+ This is a synchronous interface that blocks until the task is completed or
96
+ an error occurs, or timeout happens. The default polling interval is
97
+ 3 seconds.
58
98
 
59
99
  #### Parameters
60
100
 
61
101
  | Name | Type | Default value | Description |
62
102
  | :------ | :------ | :------ | :------ |
63
- | `task` | `string` | - | Task description in human language. |
64
- | `maxSteps` | `number` | `50` | Maximum number of steps (clicks/swipes/etc.) allowed. Used to prevent infinite loops or excessive resource consumption. |
65
- | `maxStepRetries` | `number` | `3` | Maximum retry times for MCP tool call failures at SDK level. Used to retry when callMcpTool fails (e.g., network errors, timeouts). |
103
+ | `task` | `string` | `undefined` | Task description in human language. |
104
+ | `maxSteps` | `number` | `50` | Maximum number of steps (clicks/swipes/etc.) allowed. Used to prevent infinite loops or excessive resource consumption. Default is 50. |
105
+ | `maxStepRetries` | `number` | `3` | Maximum retry times for MCP tool call failures at SDK level. Used to retry when callMcpTool fails (e.g., network errors, timeouts). Default is 3. |
66
106
  | `maxTryTimes` | `number` | `300` | Maximum number of polling attempts (each 3 seconds). Used to control how long to wait for task completion. Default is 300 (about 15 minutes). |
67
107
 
68
108
  #### Returns
69
109
 
70
110
  `Promise`\<``ExecutionResult``\>
71
111
 
72
- ExecutionResult containing success status, task ID, task status, and error message if any.
112
+ ExecutionResult containing success status, task ID, task status,
113
+ and error message if any.
73
114
 
74
115
  **`Example`**
75
116
 
@@ -85,45 +126,6 @@ if (result.success) {
85
126
  }
86
127
  ```
87
128
 
88
- ___
89
-
90
- ### getTaskStatus
91
-
92
- ▸ **getTaskStatus**(`taskId`): `Promise`\<``QueryResult``\>
93
-
94
- Get the status of the task with the given task ID.
95
-
96
- #### Parameters
97
-
98
- | Name | Type | Description |
99
- | :------ | :------ | :------ |
100
- | `taskId` | `string` | The ID of the task. |
101
-
102
- #### Returns
103
-
104
- `Promise`\<``QueryResult``\>
105
-
106
- QueryResult containing task status, task action, and task product.
107
-
108
- **`Example`**
109
-
110
- ```typescript
111
- const agentBay = new AgentBay({ apiKey: 'your_api_key' });
112
- const result = await agentBay.create({ imageId: 'mobile_latest' });
113
- if (result.success) {
114
- const execResult = await result.session.agent.mobile.executeTask(
115
- 'Open WeChat app', 100, 5
116
- );
117
- const statusResult = await result.session.agent.mobile.getTaskStatus(
118
- execResult.taskId
119
- );
120
- console.log(`Task status: ${statusResult.taskStatus}`);
121
- await result.session.delete();
122
- }
123
- ```
124
-
125
- ___
126
-
127
129
  ### terminateTask
128
130
 
129
131
  ▸ **terminateTask**(`taskId`): `Promise`\<``ExecutionResult``\>
@@ -132,30 +134,14 @@ Terminate a task with a specified task ID.
132
134
 
133
135
  #### Parameters
134
136
 
135
- | Name | Type | Description |
136
- | :------ | :------ | :------ |
137
- | `taskId` | `string` | The ID of the running task. |
137
+ | Name | Type |
138
+ | :------ | :------ |
139
+ | `taskId` | `string` |
138
140
 
139
141
  #### Returns
140
142
 
141
143
  `Promise`\<``ExecutionResult``\>
142
144
 
143
- ExecutionResult containing success status, task output, and error message if any.
144
-
145
- **`Example`**
146
-
147
- ```typescript
148
- const agentBay = new AgentBay({ apiKey: 'your_api_key' });
149
- const result = await agentBay.create({ imageId: 'mobile_latest' });
150
- if (result.success) {
151
- const taskResult = await result.session.agent.mobile.executeTask(
152
- 'Open WeChat app', 100, 5
153
- );
154
- const terminateResult = await result.session.agent.mobile.terminateTask(
155
- taskResult.taskId
156
- );
157
- console.log(`Terminated: ${terminateResult.taskStatus}`);
158
- await result.session.delete();
159
- }
160
- ```
145
+ #### Inherited from
161
146
 
147
+ BaseTaskAgent.terminateTask
package/docs/api/common-features/basics/filesystem.md CHANGED
@@ -197,7 +197,7 @@ if (result.success) {
197
197
 
198
198
  ### list
199
199
 
200
- ▸ **list**(`path`): `Promise`\<`DirectoryListResult`\>
200
+ ▸ **list**(`path`): `Promise`\<``DirectoryListResult``\>
201
201
 
202
202
  Alias of listDirectory().
203
203
 
@@ -209,13 +209,13 @@ Alias of listDirectory().
209
209
 
210
210
  #### Returns
211
211
 
212
- `Promise`\<`DirectoryListResult`\>
212
+ `Promise`\<``DirectoryListResult``\>
213
213
 
214
214
  ___
215
215
 
216
216
  ### listDirectory
217
217
 
218
- ▸ **listDirectory**(`path`): `Promise`\<`DirectoryListResult`\>
218
+ ▸ **listDirectory**(`path`): `Promise`\<``DirectoryListResult``\>
219
219
 
220
220
  Lists the contents of a directory.
221
221
 
@@ -227,7 +227,7 @@ Lists the contents of a directory.
227
227
 
228
228
  #### Returns
229
229
 
230
- `Promise`\<`DirectoryListResult`\>
230
+ `Promise`\<``DirectoryListResult``\>
231
231
 
232
232
  Promise resolving to DirectoryListResult containing array of entries.
233
233
 
@@ -263,7 +263,7 @@ ___
263
263
 
264
264
  ### ls
265
265
 
266
- ▸ **ls**(`path`): `Promise`\<`DirectoryListResult`\>
266
+ ▸ **ls**(`path`): `Promise`\<``DirectoryListResult``\>
267
267
 
268
268
  Alias of listDirectory().
269
269
 
@@ -275,7 +275,7 @@ Alias of listDirectory().
275
275
 
276
276
  #### Returns
277
277
 
278
- `Promise`\<`DirectoryListResult`\>
278
+ `Promise`\<``DirectoryListResult``\>
279
279
 
280
280
  ___
281
281
 
@@ -316,7 +316,7 @@ ___
316
316
 
317
317
  ### read
318
318
 
319
- ▸ **read**(`path`): `Promise`\<`FileContentResult`\>
319
+ ▸ **read**(`path`): `Promise`\<``FileContentResult``\>
320
320
 
321
321
  Alias of readFile().
322
322
 
@@ -328,15 +328,15 @@ Alias of readFile().
328
328
 
329
329
  #### Returns
330
330
 
331
- `Promise`\<`FileContentResult`\>
331
+ `Promise`\<``FileContentResult``\>
332
332
 
333
333
  ___
334
334
 
335
335
  ### readFile
336
336
 
337
- ▸ **readFile**(`path`): `Promise`\<`FileContentResult`\>
337
+ ▸ **readFile**(`path`): `Promise`\<``FileContentResult``\>
338
338
 
339
- Reads the entire content of a file.
339
+ Reads the entire content of a file (text format, default).
340
340
 
341
341
  #### Parameters
342
342
 
@@ -346,7 +346,7 @@ Reads the entire content of a file.
346
346
 
347
347
  #### Returns
348
348
 
349
- `Promise`\<`FileContentResult`\>
349
+ `Promise`\<``FileContentResult``\>
350
350
 
351
351
  Promise resolving to FileContentResult containing:
352
352
  - success: Whether the read operation succeeded
@@ -354,10 +354,6 @@ Promise resolving to FileContentResult containing:
354
354
  - requestId: Unique identifier for this API request
355
355
  - errorMessage: Error description if read failed
356
356
 
357
- **`Throws`**
358
-
359
- Error if the API call fails.
360
-
361
357
  **`Example`**
362
358
 
363
359
  ```typescript
@@ -369,11 +365,83 @@ const result = await agentBay.create();
369
365
  if (result.success) {
370
366
  const session = result.session;
371
367
 
372
- // Read a text file
368
+ // Read a text file (default)
373
369
  const fileResult = await session.fileSystem.readFile('/etc/hostname');
374
370
  if (fileResult.success) {
375
371
  console.log(`Content: ${fileResult.content}`);
376
- // Output: Content: agentbay-session-xyz
372
+ }
373
+
374
+ await session.delete();
375
+ }
376
+ ```
377
+
378
+ ▸ **readFile**(`path`, `opts`): `Promise`\<``FileContentResult``\>
379
+
380
+ Reads the entire content of a file with explicit text format.
381
+
382
+ #### Parameters
383
+
384
+ | Name | Type | Description |
385
+ | :------ | :------ | :------ |
386
+ | `path` | `string` | Absolute path to the file to read. |
387
+ | `opts` | `Object` | Options object with format set to "text". |
388
+ | `opts.format` | ``"text"`` | - |
389
+
390
+ #### Returns
391
+
392
+ `Promise`\<``FileContentResult``\>
393
+
394
+ Promise resolving to FileContentResult containing:
395
+ - success: Whether the read operation succeeded
396
+ - content: String content of the file
397
+ - requestId: Unique identifier for this API request
398
+ - errorMessage: Error description if read failed
399
+
400
+ **`Example`**
401
+
402
+ ```typescript
403
+ const fileResult = await session.fileSystem.readFile('/tmp/test.txt', { format: 'text' });
404
+ ```
405
+
406
+ ▸ **readFile**(`path`, `opts`): `Promise`\<``BinaryFileContentResult``\>
407
+
408
+ Reads the entire content of a file in binary format.
409
+
410
+ #### Parameters
411
+
412
+ | Name | Type | Description |
413
+ | :------ | :------ | :------ |
414
+ | `path` | `string` | Absolute path to the file to read. |
415
+ | `opts` | `Object` | Options object with format set to "bytes". |
416
+ | `opts.format` | ``"bytes"`` | - |
417
+
418
+ #### Returns
419
+
420
+ `Promise`\<``BinaryFileContentResult``\>
421
+
422
+ Promise resolving to BinaryFileContentResult containing:
423
+ - success: Whether the read operation succeeded
424
+ - content: Uint8Array binary content of the file
425
+ - requestId: Unique identifier for this API request
426
+ - errorMessage: Error description if read failed
427
+ - contentType: Optional MIME type of the file
428
+ - size: Optional size of the file in bytes
429
+
430
+ **`Example`**
431
+
432
+ ```typescript
433
+ import { AgentBay } from 'wuying-agentbay-sdk';
434
+
435
+ const agentBay = new AgentBay({ apiKey: 'your_api_key' });
436
+ const result = await agentBay.create();
437
+
438
+ if (result.success) {
439
+ const session = result.session;
440
+
441
+ // Read a binary file
442
+ const binaryResult = await session.fileSystem.readFile('/tmp/image.png', { format: 'bytes' });
443
+ if (binaryResult.success) {
444
+ console.log(`File size: ${binaryResult.content.length} bytes`);
377
445
  }
378
446
 
379
447
  await session.delete();
@@ -384,19 +452,15 @@ if (result.success) {
384
452
 
385
453
  **Behavior:**
386
454
  - Automatically handles large files by reading in 60KB chunks
387
- - Returns empty string for empty files
455
+ - Returns empty Uint8Array for empty files
388
456
  - Fails if path is a directory or doesn't exist
389
- - Content is returned as UTF-8 string
390
-
391
- **`See`**
392
-
393
- [writeFile](#writefile), [listDirectory](#listdirectory)
457
+ - Content is returned as Uint8Array (backend uses base64 encoding internally)
394
458
 
395
459
  ___
396
460
 
397
461
  ### readMultipleFiles
398
462
 
399
- ▸ **readMultipleFiles**(`paths`): `Promise`\<`MultipleFileContentResult`\>
463
+ ▸ **readMultipleFiles**(`paths`): `Promise`\<``MultipleFileContentResult``\>
400
464
 
401
465
  Reads the content of multiple files.
402
466
  Corresponds to Python's read_multiple_files() method
@@ -409,7 +473,7 @@ Corresponds to Python's read_multiple_files() method
409
473
 
410
474
  #### Returns
411
475
 
412
- `Promise`\<`MultipleFileContentResult`\>
476
+ `Promise`\<``MultipleFileContentResult``\>
413
477
 
414
478
  MultipleFileContentResult with file contents and requestId
415
479
 
@@ -467,7 +531,7 @@ ___
467
531
 
468
532
  ### searchFiles
469
533
 
470
- ▸ **searchFiles**(`path`, `pattern`, `excludePatterns?`): `Promise`\<`FileSearchResult`\>
534
+ ▸ **searchFiles**(`path`, `pattern`, `excludePatterns?`): `Promise`\<``FileSearchResult``\>
471
535
 
472
536
  Searches for files in a directory that match a wildcard pattern.
473
537
  Corresponds to Python's search_files() method
@@ -482,7 +546,7 @@ Corresponds to Python's search_files() method
482
546
 
483
547
  #### Returns
484
548
 
485
- `Promise`\<`FileSearchResult`\>
549
+ `Promise`\<``FileSearchResult``\>
486
550
 
487
551
  FileSearchResult with search results and requestId
488
552