Skip to content

Commit 47dffbc

Browse files
committed
updated node modules
1 parent a39f9de commit 47dffbc

89 files changed

Lines changed: 2398 additions & 484 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

test/snapshots/agent_and_compact_rpc/should_compact_session_history_after_messages.yaml

Lines changed: 26 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -5,18 +5,27 @@ conversations:
55
- role: system
66
content: ${system}
77
- role: user
8-
content: What is 2+2?
8+
content: >-
9+
What is 2+2?
10+
11+
12+
<system_reminder>
13+
14+
<sql_tables>No tables currently exist. Default tables (todos, todo_deps) will be created automatically when
15+
using the SQL tool for the first time.</sql_tables>
16+
17+
</system_reminder>
918
- role: assistant
10-
content: 2+2 = 4
19+
content: 2 + 2 = 4
1120
- role: user
1221
content: ${compaction_prompt}
1322
- role: assistant
1423
content: >-
1524
<overview>
1625
17-
The user asked a simple arithmetic question: "What is 2+2?" This was answered directly (4). No technical work,
18-
coding tasks, or file modifications were performed. This appears to have been a minimal test interaction with
19-
no substantive goals or technical requirements.
26+
The user asked a simple arithmetic question ("What is 2+2?") which was answered directly. No technical work,
27+
file modifications, or complex problem-solving was involved. This appears to be a test or demonstration
28+
conversation with no substantive development tasks.
2029
2130
</overview>
2231
@@ -25,25 +34,29 @@ conversations:
2534
2635
1. The user asked "What is 2+2?"
2736
- Provided the answer: 4
28-
- No further actions were taken or requested
37+
- No further actions required
2938
</history>
3039
3140
3241
<work_done>
3342
34-
No files were created, modified, or deleted. No technical tasks were performed. The conversation consisted
35-
solely of answering a basic arithmetic question.
43+
No files were created, modified, or deleted. No technical work was performed.
44+
45+
46+
Work completed:
47+
48+
- [x] Answered basic arithmetic question
3649
3750
38-
Current state: No active work in progress.
51+
Current state: Conversation complete with no ongoing tasks.
3952
4053
</work_done>
4154
4255
4356
<technical_details>
4457
45-
No technical concepts, decisions, or issues were encountered in this conversation. This was a straightforward
46-
arithmetic question with no technical context.
58+
No technical concepts, decisions, or issues were encountered in this conversation. This was a simple Q&A
59+
exchange with no development or debugging work.
4760
4861
</technical_details>
4962
@@ -57,9 +70,9 @@ conversations:
5770
5871
<next_steps>
5972
60-
No pending work or tasks. The user's question was fully addressed. Awaiting new requests or instructions.
73+
No pending work or next steps. The user's request has been fully addressed.
6174
6275
</next_steps>
6376
6477
65-
<checkpoint_title>Simple arithmetic question answered</checkpoint_title>
78+
<checkpoint_title>Basic arithmetic question answered</checkpoint_title>

test/snapshots/ask_user/should_handle_freeform_user_input_response.yaml

Lines changed: 46 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -5,17 +5,60 @@ conversations:
55
- role: system
66
content: ${system}
77
- role: user
8-
content: Ask me a question using ask_user and then include my answer in your response. The question should be 'What is
8+
content: >-
9+
Ask me a question using ask_user and then include my answer in your response. The question should be 'What is
910
your favorite color?'
11+
12+
13+
<system_reminder>
14+
15+
<sql_tables>No tables currently exist. Default tables (todos, todo_deps) will be created automatically when
16+
using the SQL tool for the first time.</sql_tables>
17+
18+
</system_reminder>
1019
- role: assistant
20+
content: I'll ask you about your favorite color.
21+
- role: assistant
22+
tool_calls:
23+
- id: toolcall_0
24+
type: function
25+
function:
26+
name: ask_user
27+
arguments: '{"choices":["Blue","Red","Green","Purple","Yellow","Orange","Pink","Black"],"question":"What is your
28+
favorite color?"}'
29+
- messages:
30+
- role: system
31+
content: ${system}
32+
- role: user
33+
content: >-
34+
Ask me a question using ask_user and then include my answer in your response. The question should be 'What is
35+
your favorite color?'
36+
37+
38+
<system_reminder>
39+
40+
<sql_tables>No tables currently exist. Default tables (todos, todo_deps) will be created automatically when
41+
using the SQL tool for the first time.</sql_tables>
42+
43+
</system_reminder>
44+
- role: assistant
45+
content: I'll ask you about your favorite color.
1146
tool_calls:
1247
- id: toolcall_0
1348
type: function
1449
function:
1550
name: ask_user
16-
arguments: '{"question":"What is your favorite color?"}'
51+
arguments: '{"choices":["Blue","Red","Green","Purple","Yellow","Orange","Pink","Black"],"question":"What is your
52+
favorite color?"}'
1753
- role: tool
1854
tool_call_id: toolcall_0
1955
content: "User responded: This is my custom freeform answer that was not in the choices"
2056
- role: assistant
21-
content: 'You answered: "This is my custom freeform answer that was not in the choices"'
57+
content: >-
58+
Thank you for letting me know! Your answer was: "This is my custom freeform answer that was not in the
59+
choices"
60+
61+
62+
I see you chose to provide a custom response rather than selecting one of the predefined color options I
63+
offered. The ask_user tool allows for freeform answers in addition to the provided choices, which you took
64+
advantage of!

test/snapshots/ask_user/should_invoke_user_input_handler_when_model_uses_ask_user_tool.yaml

Lines changed: 37 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -5,17 +5,51 @@ conversations:
55
- role: system
66
content: ${system}
77
- role: user
8-
content: Ask me to choose between 'Option A' and 'Option B' using the ask_user tool. Wait for my response before
8+
content: >-
9+
Ask me to choose between 'Option A' and 'Option B' using the ask_user tool. Wait for my response before
910
continuing.
11+
12+
13+
<system_reminder>
14+
15+
<sql_tables>No tables currently exist. Default tables (todos, todo_deps) will be created automatically when
16+
using the SQL tool for the first time.</sql_tables>
17+
18+
</system_reminder>
1019
- role: assistant
20+
content: I'll ask you to choose between those two options.
21+
- role: assistant
22+
tool_calls:
23+
- id: toolcall_0
24+
type: function
25+
function:
26+
name: ask_user
27+
arguments: '{"choices":["Option A","Option B"],"question":"Which option would you like to choose?"}'
28+
- messages:
29+
- role: system
30+
content: ${system}
31+
- role: user
32+
content: >-
33+
Ask me to choose between 'Option A' and 'Option B' using the ask_user tool. Wait for my response before
34+
continuing.
35+
36+
37+
<system_reminder>
38+
39+
<sql_tables>No tables currently exist. Default tables (todos, todo_deps) will be created automatically when
40+
using the SQL tool for the first time.</sql_tables>
41+
42+
</system_reminder>
43+
- role: assistant
44+
content: I'll ask you to choose between those two options.
1145
tool_calls:
1246
- id: toolcall_0
1347
type: function
1448
function:
1549
name: ask_user
16-
arguments: '{"question":"Please choose between the following options:","choices":["Option A","Option B"]}'
50+
arguments: '{"choices":["Option A","Option B"],"question":"Which option would you like to choose?"}'
1751
- role: tool
1852
tool_call_id: toolcall_0
1953
content: "User selected: Option A"
2054
- role: assistant
21-
content: You selected **Option A**. What would you like me to do next?
55+
content: You chose **Option A**. How would you like to proceed?

test/snapshots/ask_user/should_receive_choices_in_user_input_request.yaml

Lines changed: 38 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -5,17 +5,51 @@ conversations:
55
- role: system
66
content: ${system}
77
- role: user
8-
content: "Use the ask_user tool to ask me to pick between exactly two options: 'Red' and 'Blue'. These should be
9-
provided as choices. Wait for my answer."
8+
content: >-
9+
Use the ask_user tool to ask me to pick between exactly two options: 'Red' and 'Blue'. These should be
10+
provided as choices. Wait for my answer.
11+
12+
13+
<system_reminder>
14+
15+
<sql_tables>No tables currently exist. Default tables (todos, todo_deps) will be created automatically when
16+
using the SQL tool for the first time.</sql_tables>
17+
18+
</system_reminder>
1019
- role: assistant
20+
content: I'll ask you to choose between Red and Blue.
21+
- role: assistant
22+
tool_calls:
23+
- id: toolcall_0
24+
type: function
25+
function:
26+
name: ask_user
27+
arguments: '{"choices":["Red","Blue"],"question":"Which color do you prefer?"}'
28+
- messages:
29+
- role: system
30+
content: ${system}
31+
- role: user
32+
content: >-
33+
Use the ask_user tool to ask me to pick between exactly two options: 'Red' and 'Blue'. These should be
34+
provided as choices. Wait for my answer.
35+
36+
37+
<system_reminder>
38+
39+
<sql_tables>No tables currently exist. Default tables (todos, todo_deps) will be created automatically when
40+
using the SQL tool for the first time.</sql_tables>
41+
42+
</system_reminder>
43+
- role: assistant
44+
content: I'll ask you to choose between Red and Blue.
1145
tool_calls:
1246
- id: toolcall_0
1347
type: function
1448
function:
1549
name: ask_user
16-
arguments: '{"question":"Please pick one of the following options:","choices":["Red","Blue"],"allow_freeform":false}'
50+
arguments: '{"choices":["Red","Blue"],"question":"Which color do you prefer?"}'
1751
- role: tool
1852
tool_call_id: toolcall_0
1953
content: "User selected: Red"
2054
- role: assistant
21-
content: You selected **Red**.
55+
content: You selected **Red**!

test/snapshots/builtin_tools/should_capture_exit_code_in_output.yaml

Lines changed: 29 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -5,38 +5,59 @@ conversations:
55
- role: system
66
content: ${system}
77
- role: user
8-
content: Run 'echo hello && echo world'. Tell me the exact output.
8+
content: >-
9+
Run 'echo hello && echo world'. Tell me the exact output.
10+
11+
12+
<system_reminder>
13+
14+
<sql_tables>No tables currently exist. Default tables (todos, todo_deps) will be created automatically when
15+
using the SQL tool for the first time.</sql_tables>
16+
17+
</system_reminder>
18+
- role: assistant
19+
content: I'll run that command for you.
920
- role: assistant
1021
tool_calls:
1122
- id: toolcall_0
1223
type: function
1324
function:
1425
name: report_intent
15-
arguments: '{"intent":"Running echo commands"}'
26+
arguments: '{"intent":"Running echo command"}'
1627
- role: assistant
1728
tool_calls:
1829
- id: toolcall_1
1930
type: function
2031
function:
2132
name: ${shell}
22-
arguments: '{"command":"echo hello && echo world","description":"Run echo hello && echo world"}'
33+
arguments: '{"command":"echo hello && echo world","description":"Run echo commands"}'
2334
- messages:
2435
- role: system
2536
content: ${system}
2637
- role: user
27-
content: Run 'echo hello && echo world'. Tell me the exact output.
38+
content: >-
39+
Run 'echo hello && echo world'. Tell me the exact output.
40+
41+
42+
<system_reminder>
43+
44+
<sql_tables>No tables currently exist. Default tables (todos, todo_deps) will be created automatically when
45+
using the SQL tool for the first time.</sql_tables>
46+
47+
</system_reminder>
2848
- role: assistant
49+
content: I'll run that command for you.
2950
tool_calls:
3051
- id: toolcall_0
3152
type: function
3253
function:
3354
name: report_intent
34-
arguments: '{"intent":"Running echo commands"}'
55+
arguments: '{"intent":"Running echo command"}'
3556
- id: toolcall_1
3657
type: function
3758
function:
3859
name: ${shell}
39-
arguments: '{"command":"echo hello && echo world","description":"Run echo hello && echo world"}'
60+
arguments: '{"command":"echo hello && echo world","description":"Run echo commands"}'
4061
- role: tool
4162
tool_call_id: toolcall_0
4263
content: Intent logged
@@ -53,3 +74,5 @@ conversations:
5374
hello
5475
world
5576
```
77+
78+
The command executed successfully with exit code 0.

0 commit comments

Comments
 (0)