ch08_tool_program

show: mock live

mock turns=10 · messages=25

live turns=6 · messages=17

scenario program_answers

scenario program_answers · tools=price_of · 3.2ms · 2 turns · ended: no_tool_calls

turn 1 · 2.8ms · asked for: price_of

model mock · 2.8ms · asked for: price_of

context sent — 2 message(s)

	role	content
[0]	system	You answer briefly and plainly. Use the tools you are given.
[1]	human	How much is milk?

declared tools (1)

tool	description	schema
price_of	The current shelf price of one of an item, in pounds.	{"$defs": {"GroceryItem": {"enum": ["bread", "butter", "chips", "milk"], "type": "string"}}, "description": "The current shelf price of one of an item, in pounds.", "properties": {"item": {"$ref": "#/$defs/GroceryItem"}}, "required": ["item"], "title": "price_of", "type": "object"}

tools declared to the mock model {"names": ["price_of"], "consulted": false}

context ignored by the mock model {"messages": 2, "roles": ["system", "human"]}

	role	content
[0]	ai	price_of({"item": "milk"})

tool price_of · 0.0ms · given: item=milk · returned: 1.20

args {"item": "milk"}

command {"line": "printf 1.20 --item milk"}

exit {"code": 0, "out": "1.20", "err": ""}

result {"value": "1.20"}

turn 2 · 0.2ms · responded with: Milk is 1.20.

model mock · 0.2ms · responded with: Milk is 1.20.

context sent — 4 message(s)

	role	content
[0]	system	You answer briefly and plainly. Use the tools you are given.
[1]	human	How much is milk?
[2]	ai	price_of({"item": "milk"})
[3]	tool	1.20

declared tools (1)

tool	description	schema
price_of	The current shelf price of one of an item, in pounds.	{"$defs": {"GroceryItem": {"enum": ["bread", "butter", "chips", "milk"], "type": "string"}}, "description": "The current shelf price of one of an item, in pounds.", "properties": {"item": {"$ref": "#/$defs/GroceryItem"}}, "required": ["item"], "title": "price_of", "type": "object"}

tools declared to the mock model {"names": ["price_of"], "consulted": false}

context ignored by the mock model {"messages": 4, "roles": ["system", "human", "ai", "tool"]}

	role	content
[0]	ai	Milk is 1.20.

ended {"reason": "no_tool_calls"}

scenario program_answers · tools=price_of · 2289.3ms · 2 turns · ended: no_tool_calls

turn 1 · 1381.3ms · 330 in / 39 out · asked for: price_of

model live · 1370.6ms (model provider 1138.6 · library 232.0) · 330 in / 39 out · asked for: price_of

context sent — 2 message(s)

	role	content
[0]	system	You answer briefly and plainly. Use the tools you are given.
[1]	human	How much is milk?

declared tools (1)

tool	description	schema
price_of	The current shelf price of one of an item, in pounds.	{"$defs": {"GroceryItem": {"enum": ["bread", "butter", "chips", "milk"], "type": "string"}}, "description": "The current shelf price of one of an item, in pounds.", "properties": {"item": {"$ref": "#/$defs/GroceryItem"}}, "required": ["item"], "title": "price_of", "type": "object"}

wire request

attempt

method

POST

url

https://api.deepseek.com/v1/chat/completions

defaulted (6)

temperature, max_tokens, top_p, stop, seed, tool_choice

headers (18)

show

accept	application/json
accept-encoding	gzip, deflate, zstd
authorization	not recorded
connection	keep-alive
content-length	454
content-type	application/json
host	api.deepseek.com
user-agent	OpenAI/Python 3.6.0
x-stainless-arch	arm64
x-stainless-async	false
x-stainless-lang	python
x-stainless-os	MacOS
x-stainless-package-version	3.6.0
x-stainless-raw-response	true
x-stainless-read-timeout	60.0
x-stainless-retry-count	0
x-stainless-runtime	CPython
x-stainless-runtime-version	3.14.7

{
  "messages": [
    {
      "content": "You answer briefly and plainly. Use the tools you are given.",
      "role": "system"
    },
    {
      "content": "How much is milk?",
      "role": "user"
    }
  ],
  "model": "deepseek-flash",
  "stream": false,
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "price_of",
        "description": "The current shelf price of one of an item, in pounds.",
        "parameters": {
          "properties": {
            "item": {
              "enum": [
                "bread",
                "butter",
                "chips",
                "milk"
              ],
              "type": "string"
            }
          },
          "required": [
            "item"
          ],
          "type": "object"
        }
      }
    }
  ]
}

wire response

status

200

headers (15)

show

access-control-allow-credentials	true
connection	keep-alive
content-encoding	gzip
content-type	application/json
date	Sun, 13 Sep 2026 21:51:54 GMT
server	elb
strict-transport-security	max-age=31536000; includeSubDomains; preload
transfer-encoding	chunked
vary	origin, access-control-request-method, access-control-request-headers
via	1.1 49a6d4f867bdc98619cc6ae406609b78.cloudfront.net (CloudFront)
x-amz-cf-id	08wFqysLJdNO53d-EeUMrurlAI5BbQ6oMJQ8_GeH6rlw9Xmi2sE1yw==
x-amz-cf-pop	DEN53-P6
x-cache	Miss from cloudfront
x-content-type-options	nosniff
x-ds-trace-id	a81f627fe77b5ecdb305df908ac16dea

{
  "id": "31c865d1-7eeb-4ed8-92d0-49c2fdb6bdc0",
  "object": "chat.completion",
  "created": 1789336314,
  "model": "deepseek-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "",
        "reasoning_content": "",
        "tool_calls": [
          {
            "index": 0,
            "id": "call_00_ET_2P9xgAVnpOfQUlyIqtg47071",
            "type": "function",
            "function": {
              "name": "price_of",
              "arguments": "{\"item\": \"milk\"}"
            }
          }
        ]
      },
      "logprobs": null,
      "finish_reason": "tool_calls"
    }
  ],
  "usage": {
    "prompt_tokens": 330,
    "completion_tokens": 39,
    "total_tokens": 369,
    "prompt_tokens_details": {
      "cached_tokens": 128
    },
    "completion_tokens_details": {
      "reasoning_tokens": 0
    },
    "prompt_cache_hit_tokens": 128,
    "prompt_cache_miss_tokens": 202
  },
  "system_fingerprint": "aeb56401ca74e127821c4f9126dcb669"
}

	role	content
[0]	ai	price_of({"item": "milk"})

tool price_of · 10.5ms · given: item=milk · returned: 1.20

args {"item": "milk"}

command {"line": "printf 1.20 --item milk"}

exit {"code": 0, "out": "1.20", "err": ""}

result {"value": "1.20"}

turn 2 · 907.8ms · 384 in / 9 out · responded with: Milk is £1.20.

model live · 907.7ms (model provider 898.5 · library 9.2) · 384 in / 9 out · responded with: Milk is £1.20.

context sent — 4 message(s)

	role	content
[0]	system	You answer briefly and plainly. Use the tools you are given.
[1]	human	How much is milk?
[2]	ai	price_of({"item": "milk"})
[3]	tool	1.20

declared tools (1)

tool	description	schema
price_of	The current shelf price of one of an item, in pounds.	{"$defs": {"GroceryItem": {"enum": ["bread", "butter", "chips", "milk"], "type": "string"}}, "description": "The current shelf price of one of an item, in pounds.", "properties": {"item": {"$ref": "#/$defs/GroceryItem"}}, "required": ["item"], "title": "price_of", "type": "object"}

wire request

attempt

method

POST

url

https://api.deepseek.com/v1/chat/completions

defaulted (6)

temperature, max_tokens, top_p, stop, seed, tool_choice

headers (18)

show

accept	application/json
accept-encoding	gzip, deflate, zstd
authorization	not recorded
connection	keep-alive
content-length	720
content-type	application/json
host	api.deepseek.com
user-agent	OpenAI/Python 3.6.0
x-stainless-arch	arm64
x-stainless-async	false
x-stainless-lang	python
x-stainless-os	MacOS
x-stainless-package-version	3.6.0
x-stainless-raw-response	true
x-stainless-read-timeout	60.0
x-stainless-retry-count	0
x-stainless-runtime	CPython
x-stainless-runtime-version	3.14.7

{
  "messages": [
    {
      "content": "You answer briefly and plainly. Use the tools you are given.",
      "role": "system"
    },
    {
      "content": "How much is milk?",
      "role": "user"
    },
    {
      "content": null,
      "role": "assistant",
      "tool_calls": [
        {
          "type": "function",
          "id": "call_00_ET_2P9xgAVnpOfQUlyIqtg47071",
          "function": {
            "name": "price_of",
            "arguments": "{\"item\": \"milk\"}"
          }
        }
      ]
    },
    {
      "content": "1.20",
      "role": "tool",
      "tool_call_id": "call_00_ET_2P9xgAVnpOfQUlyIqtg47071"
    }
  ],
  "model": "deepseek-flash",
  "stream": false,
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "price_of",
        "description": "The current shelf price of one of an item, in pounds.",
        "parameters": {
          "properties": {
            "item": {
              "enum": [
                "bread",
                "butter",
                "chips",
                "milk"
              ],
              "type": "string"
            }
          },
          "required": [
            "item"
          ],
          "type": "object"
        }
      }
    }
  ]
}

wire response

status

200

headers (15)

show

access-control-allow-credentials	true
connection	keep-alive
content-encoding	gzip
content-type	application/json
date	Sun, 13 Sep 2026 21:51:56 GMT
server	elb
strict-transport-security	max-age=31536000; includeSubDomains; preload
transfer-encoding	chunked
vary	origin, access-control-request-method, access-control-request-headers
via	1.1 3dc4c80cd959e984309833cac8f5a630.cloudfront.net (CloudFront)
x-amz-cf-id	QMvYUyIW099nPDPMQUmPOyow7bUPYkVatac3q14DD6wpBEN2QA61rA==
x-amz-cf-pop	DEN52-P2
x-cache	Miss from cloudfront
x-content-type-options	nosniff
x-ds-trace-id	593ea05111b4dede897bf4f38b278cd6

{
  "id": "c27faa9e-8560-44e4-8f35-977813532ab2",
  "object": "chat.completion",
  "created": 1789336315,
  "model": "deepseek-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Milk is \u00a31.20.",
        "reasoning_content": ""
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 384,
    "completion_tokens": 9,
    "total_tokens": 393,
    "prompt_tokens_details": {
      "cached_tokens": 128
    },
    "completion_tokens_details": {
      "reasoning_tokens": 0
    },
    "prompt_cache_hit_tokens": 128,
    "prompt_cache_miss_tokens": 256
  },
  "system_fingerprint": "aeb56401ca74e127821c4f9126dcb669"
}

	role	content
[0]	ai	Milk is £1.20.

ended {"reason": "no_tool_calls"}

scenario program_fails

scenario program_fails · 0.3ms · 2 turns · ended: no_tool_calls

turn 1 · 0.2ms · asked for: price_of

model mock · 0.1ms · asked for: price_of

context sent — 2 message(s)

	role	content
[0]	system	You answer briefly and plainly. Use the tools you are given.
[1]	human

context ignored by the mock model {"messages": 2, "roles": ["system", "human"]}

	role	content
[0]	ai	price_of({"item": "milk"})

tool price_of · 0.0ms · given: item=milk · raised: PriceProgramError (['ls'] exited ['1']: ls: /no-such-price-list/milk: No such f)

args {"item": "milk"}

command {"line": "ls /no-such-price-list/milk"}

exit {"code": 1, "out": "", "err": "ls: /no-such-price-list/milk: No such file or directory"}

failed {"exception": "PriceProgramError", "message": "['ls'] exited ['1']: ls: /no-such-price-list/milk: No such file or directory"}

turn 2 · 0.1ms · responded with: I could not get the price of milk.

model mock · 0.1ms · responded with: I could not get the price of milk.

context sent — 4 message(s)

	role	content
[0]	system	You answer briefly and plainly. Use the tools you are given.
[1]	human
[2]	ai	price_of({"item": "milk"})
[3]	tool	['price_of'] failed: ['ls'] exited ['1']: ls: /no-such-price-list/milk: No such file or directory. Answer without it.

context ignored by the mock model {"messages": 4, "roles": ["system", "human", "ai", "tool"]}

	role	content
[0]	ai	I could not get the price of milk.

ended {"reason": "no_tool_calls"}

scenario program_fails · 657.8ms · 1 turn · ended: no_tool_calls

turn 1 · 657.8ms · 43 in / 33 out · responded with: I'm ready — what would you like me to help with?

model live · 657.8ms (model provider 650.8 · library 7.0) · 43 in / 33 out · responded with: I'm ready — what would you like me to help with?

context sent — 2 message(s)

	role	content
[0]	system	You answer briefly and plainly. Use the tools you are given.
[1]	human

wire request

attempt

method

POST

url

https://api.deepseek.com/v1/chat/completions

defaulted (7)

temperature, max_tokens, top_p, stop, seed, tools, tool_choice

headers (18)

show

accept	application/json
accept-encoding	gzip, deflate, zstd
authorization	not recorded
connection	keep-alive
content-length	174
content-type	application/json
host	api.deepseek.com
user-agent	OpenAI/Python 3.6.0
x-stainless-arch	arm64
x-stainless-async	false
x-stainless-lang	python
x-stainless-os	MacOS
x-stainless-package-version	3.6.0
x-stainless-raw-response	true
x-stainless-read-timeout	60.0
x-stainless-retry-count	0
x-stainless-runtime	CPython
x-stainless-runtime-version	3.14.7

{
  "messages": [
    {
      "content": "You answer briefly and plainly. Use the tools you are given.",
      "role": "system"
    },
    {
      "content": "",
      "role": "user"
    }
  ],
  "model": "deepseek-flash",
  "stream": false
}

wire response

status

200

headers (15)

show

access-control-allow-credentials	true
connection	keep-alive
content-encoding	gzip
content-type	application/json
date	Sun, 13 Sep 2026 21:51:56 GMT
server	elb
strict-transport-security	max-age=31536000; includeSubDomains; preload
transfer-encoding	chunked
vary	origin, access-control-request-method, access-control-request-headers
via	1.1 3fc2177a4dd115307e9fe96ea7fefd84.cloudfront.net (CloudFront)
x-amz-cf-id	KMNkcNf1xjeWm2foKON6cXkm-CWqidrdkVi7TzYrmtWGpE0GCe0QlA==
x-amz-cf-pop	DEN53-P3
x-cache	Miss from cloudfront
x-content-type-options	nosniff
x-ds-trace-id	1c918d0ddee8da9f3c7f999bc6991ffb

{
  "id": "6637859f-ef58-44d3-9e02-b17dd4c4aa52",
  "object": "chat.completion",
  "created": 1789336316,
  "model": "deepseek-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I'm ready \u2014 what would you like me to help with?",
        "reasoning_content": "The user has given no actual question or task. I should respond briefly asking what they need."
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 43,
    "completion_tokens": 33,
    "total_tokens": 76,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 19
    },
    "prompt_cache_hit_tokens": 0,
    "prompt_cache_miss_tokens": 43
  },
  "system_fingerprint": "aeb56401ca74e127821c4f9126dcb669"
}

	role	content
[0]	ai	I'm ready — what would you like me to help with?

ended {"reason": "no_tool_calls"}

scenario program_is_missing

scenario program_is_missing · 0.3ms · 2 turns · ended: no_tool_calls

turn 1 · 0.1ms · asked for: price_of

model mock · 0.1ms · asked for: price_of

context sent — 2 message(s)

	role	content
[0]	system	You answer briefly and plainly. Use the tools you are given.
[1]	human

context ignored by the mock model {"messages": 2, "roles": ["system", "human"]}

	role	content
[0]	ai	price_of({"item": "milk"})

tool price_of · 0.0ms · given: item=milk · raised: PriceProgramError (['price-of'] exited ['127']: price-of: command not found)

args {"item": "milk"}

command {"line": "price-of --item milk"}

exit {"code": 127, "out": "", "err": "price-of: command not found"}

failed {"exception": "PriceProgramError", "message": "['price-of'] exited ['127']: price-of: command not found"}

turn 2 · 0.1ms · responded with: I could not get the price of milk.

model mock · 0.1ms · responded with: I could not get the price of milk.

context sent — 4 message(s)

	role	content
[0]	system	You answer briefly and plainly. Use the tools you are given.
[1]	human
[2]	ai	price_of({"item": "milk"})
[3]	tool	['price_of'] failed: ['price-of'] exited ['127']: price-of: command not found. Answer without it.

context ignored by the mock model {"messages": 4, "roles": ["system", "human", "ai", "tool"]}

	role	content
[0]	ai	I could not get the price of milk.

ended {"reason": "no_tool_calls"}

scenario program_is_missing · 1080.7ms · 1 turn · ended: no_tool_calls

turn 1 · 1080.6ms · 43 in / 15 out · responded with: Ready. What would you like me to do?

model live · 1080.6ms (model provider 1068.7 · library 11.9) · 43 in / 15 out · responded with: Ready. What would you like me to do?

context sent — 2 message(s)

	role	content
[0]	system	You answer briefly and plainly. Use the tools you are given.
[1]	human

wire request

attempt

method

POST

url

https://api.deepseek.com/v1/chat/completions

defaulted (7)

temperature, max_tokens, top_p, stop, seed, tools, tool_choice

headers (18)

show

accept	application/json
accept-encoding	gzip, deflate, zstd
authorization	not recorded
connection	keep-alive
content-length	174
content-type	application/json
host	api.deepseek.com
user-agent	OpenAI/Python 3.6.0
x-stainless-arch	arm64
x-stainless-async	false
x-stainless-lang	python
x-stainless-os	MacOS
x-stainless-package-version	3.6.0
x-stainless-raw-response	true
x-stainless-read-timeout	60.0
x-stainless-retry-count	0
x-stainless-runtime	CPython
x-stainless-runtime-version	3.14.7

{
  "messages": [
    {
      "content": "You answer briefly and plainly. Use the tools you are given.",
      "role": "system"
    },
    {
      "content": "",
      "role": "user"
    }
  ],
  "model": "deepseek-flash",
  "stream": false
}

wire response

status

200

headers (15)

show

access-control-allow-credentials	true
connection	keep-alive
content-encoding	gzip
content-type	application/json
date	Sun, 13 Sep 2026 21:51:57 GMT
server	elb
strict-transport-security	max-age=31536000; includeSubDomains; preload
transfer-encoding	chunked
vary	origin, access-control-request-method, access-control-request-headers
via	1.1 153d2cbd7c83442a049eab26571069f6.cloudfront.net (CloudFront)
x-amz-cf-id	lrC3yQGZCD51zf_GhdWr74TVqsWkE1QHvziggIxmF5QdJ9SVuYaMpQ==
x-amz-cf-pop	DEN53-P6
x-cache	Miss from cloudfront
x-content-type-options	nosniff
x-ds-trace-id	2cbc7b1c6e2d1b57fbaefa046c716eb0

{
  "id": "af63547a-e3cc-45e5-bf4d-ba7091529590",
  "object": "chat.completion",
  "created": 1789336317,
  "model": "deepseek-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Ready. What would you like me to do?",
        "reasoning_content": "The user hasn"
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 43,
    "completion_tokens": 15,
    "total_tokens": 58,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 3
    },
    "prompt_cache_hit_tokens": 0,
    "prompt_cache_miss_tokens": 43
  },
  "system_fingerprint": "aeb56401ca74e127821c4f9126dcb669"
}

	role	content
[0]	ai	Ready. What would you like me to do?

ended {"reason": "no_tool_calls"}

scenario program_hangs

scenario program_hangs · 0.3ms · 2 turns · ended: no_tool_calls

turn 1 · 0.1ms · asked for: price_of

model mock · 0.1ms · asked for: price_of

context sent — 2 message(s)

	role	content
[0]	system	You answer briefly and plainly. Use the tools you are given.
[1]	human

context ignored by the mock model {"messages": 2, "roles": ["system", "human"]}

	role	content
[0]	ai	price_of({"item": "milk"})

tool price_of · 0.0ms · given: item=milk · raised: PriceProgramError (['sleep'] exited ['None']: killed after 2s)

args {"item": "milk"}

command {"line": "sleep 30 # milk"}

exit {"code": null, "out": "", "err": "killed after 2s"}

failed {"exception": "PriceProgramError", "message": "['sleep'] exited ['None']: killed after 2s"}

turn 2 · 0.1ms · responded with: I could not get the price of milk.

model mock · 0.1ms · responded with: I could not get the price of milk.

context sent — 4 message(s)

	role	content
[0]	system	You answer briefly and plainly. Use the tools you are given.
[1]	human
[2]	ai	price_of({"item": "milk"})
[3]	tool	['price_of'] failed: ['sleep'] exited ['None']: killed after 2s. Answer without it.

context ignored by the mock model {"messages": 4, "roles": ["system", "human", "ai", "tool"]}

	role	content
[0]	ai	I could not get the price of milk.

ended {"reason": "no_tool_calls"}

scenario program_hangs · 1253.9ms · 1 turn · ended: no_tool_calls

turn 1 · 1253.8ms · 43 in / 96 out · responded with: What would you like help with?

model live · 1253.8ms (model provider 1243.3 · library 10.5) · 43 in / 96 out · responded with: What would you like help with?

context sent — 2 message(s)

	role	content
[0]	system	You answer briefly and plainly. Use the tools you are given.
[1]	human

wire request

attempt

method

POST

url

https://api.deepseek.com/v1/chat/completions

defaulted (7)

temperature, max_tokens, top_p, stop, seed, tools, tool_choice

headers (18)

show

accept	application/json
accept-encoding	gzip, deflate, zstd
authorization	not recorded
connection	keep-alive
content-length	174
content-type	application/json
host	api.deepseek.com
user-agent	OpenAI/Python 3.6.0
x-stainless-arch	arm64
x-stainless-async	false
x-stainless-lang	python
x-stainless-os	MacOS
x-stainless-package-version	3.6.0
x-stainless-raw-response	true
x-stainless-read-timeout	60.0
x-stainless-retry-count	0
x-stainless-runtime	CPython
x-stainless-runtime-version	3.14.7

{
  "messages": [
    {
      "content": "You answer briefly and plainly. Use the tools you are given.",
      "role": "system"
    },
    {
      "content": "",
      "role": "user"
    }
  ],
  "model": "deepseek-flash",
  "stream": false
}

wire response

status

200

headers (15)

show

access-control-allow-credentials	true
connection	keep-alive
content-encoding	gzip
content-type	application/json
date	Sun, 13 Sep 2026 21:51:58 GMT
server	elb
strict-transport-security	max-age=31536000; includeSubDomains; preload
transfer-encoding	chunked
vary	origin, access-control-request-method, access-control-request-headers
via	1.1 975ade3143a5f26adabbac0540e470ce.cloudfront.net (CloudFront)
x-amz-cf-id	D2N3RxPLFVBy1UrBf3rlc_-J8aUMrS3CSYWcEkyOwqGjsehgeiGXVw==
x-amz-cf-pop	DEN53-P6
x-cache	Miss from cloudfront
x-content-type-options	nosniff
x-ds-trace-id	8650cf01dce4fcee9a0abff56718d861

{
  "id": "3aa8aa9f-e069-4e2d-ab8c-bc9c6f486923",
  "object": "chat.completion",
  "created": 1789336318,
  "model": "deepseek-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "What would you like help with?",
        "reasoning_content": "We need answer user? There is no question. Maybe this is a setup. Need ask what they need. But instruction says answer briefly and plainly. Use tools given. No tools used. We need respond perhaps ask for task. Since no prompt, should say \"What would you like help with?\" But maybe there is hidden? We only see user blank? The conversation: system then user empty. We should ask clarification. Final concise."
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 43,
    "completion_tokens": 96,
    "total_tokens": 139,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 88
    },
    "prompt_cache_hit_tokens": 0,
    "prompt_cache_miss_tokens": 43
  },
  "system_fingerprint": "aeb56401ca74e127821c4f9126dcb669"
}

	role	content
[0]	ai	What would you like help with?

ended {"reason": "no_tool_calls"}

scenario argument_is_a_command

scenario argument_is_a_command · 0.3ms · 2 turns · ended: no_tool_calls

turn 1 · 0.1ms · asked for: price_of

model mock · 0.1ms · asked for: price_of

context sent — 2 message(s)

	role	content
[0]	system	You answer briefly and plainly. Use the tools you are given.
[1]	human

context ignored by the mock model {"messages": 2, "roles": ["system", "human"]}

	role	content
[0]	ai	price_of({"item": "milk; echo pwned"})

tool price_of · 0.0ms · given: item=milk; echo pwned · returned: 1.20 pwned

args {"item": "milk; echo pwned"}

command {"line": "printf 1.20 --item milk; echo pwned"}

exit {"code": 0, "out": "1.20\npwned", "err": ""}

result {"value": "1.20\npwned"}

turn 2 · 0.1ms · responded with: Milk is 1.20 pwned.

model mock · 0.1ms · responded with: Milk is 1.20 pwned.

context sent — 4 message(s)

	role	content
[0]	system	You answer briefly and plainly. Use the tools you are given.
[1]	human
[2]	ai	price_of({"item": "milk; echo pwned"})
[3]	tool	1.20 pwned

context ignored by the mock model {"messages": 4, "roles": ["system", "human", "ai", "tool"]}

	role	content
[0]	ai	Milk is 1.20 pwned.

ended {"reason": "no_tool_calls"}

scenario argument_is_a_command · 1198.7ms · 1 turn · ended: no_tool_calls

turn 1 · 1198.7ms · 43 in / 69 out · responded with: What would you like help with?

model live · 1198.6ms (model provider 1190.3 · library 8.3) · 43 in / 69 out · responded with: What would you like help with?

context sent — 2 message(s)

	role	content
[0]	system	You answer briefly and plainly. Use the tools you are given.
[1]	human

wire request

attempt

method

POST

url

https://api.deepseek.com/v1/chat/completions

defaulted (7)

temperature, max_tokens, top_p, stop, seed, tools, tool_choice

headers (18)

show

accept	application/json
accept-encoding	gzip, deflate, zstd
authorization	not recorded
connection	keep-alive
content-length	174
content-type	application/json
host	api.deepseek.com
user-agent	OpenAI/Python 3.6.0
x-stainless-arch	arm64
x-stainless-async	false
x-stainless-lang	python
x-stainless-os	MacOS
x-stainless-package-version	3.6.0
x-stainless-raw-response	true
x-stainless-read-timeout	60.0
x-stainless-retry-count	0
x-stainless-runtime	CPython
x-stainless-runtime-version	3.14.7

{
  "messages": [
    {
      "content": "You answer briefly and plainly. Use the tools you are given.",
      "role": "system"
    },
    {
      "content": "",
      "role": "user"
    }
  ],
  "model": "deepseek-flash",
  "stream": false
}

wire response

status

200

headers (15)

show

access-control-allow-credentials	true
connection	keep-alive
content-encoding	gzip
content-type	application/json
date	Sun, 13 Sep 2026 21:51:59 GMT
server	elb
strict-transport-security	max-age=31536000; includeSubDomains; preload
transfer-encoding	chunked
vary	origin, access-control-request-method, access-control-request-headers
via	1.1 f0a2a95cb4d25b2414a9c1a7a754943e.cloudfront.net (CloudFront)
x-amz-cf-id	_afHgA8riexgXZQYUBwYtphyzoqkcP39al--11gDKTMHfgDvkMCLyg==
x-amz-cf-pop	DEN52-P2
x-cache	Miss from cloudfront
x-content-type-options	nosniff
x-ds-trace-id	464202d632c6f63cf9e6c763e3c6b009

{
  "id": "466715f3-9281-4046-ab08-6e266e408cf6",
  "object": "chat.completion",
  "created": 1789336319,
  "model": "deepseek-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "What would you like help with?",
        "reasoning_content": "We need answer to user? There is no user query. We need maybe wait? The prompt is empty except system. Need respond? We should ask what they need. But instruction says answer briefly and plainly. We can say \"What would you like help with?\" But maybe no question. Need final."
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 43,
    "completion_tokens": 69,
    "total_tokens": 112,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 61
    },
    "prompt_cache_hit_tokens": 0,
    "prompt_cache_miss_tokens": 43
  },
  "system_fingerprint": "aeb56401ca74e127821c4f9126dcb669"
}

	role	content
[0]	ai	What would you like help with?

ended {"reason": "no_tool_calls"}