Skip to content

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Fix interpolation for output_file in Task (#1803) (#1814)

devin-ai-integration[bot]73f328860b4a
diff --git a/src/crewai/task.py b/src/crewai/task.py
index 30ab79c00..a63bde57d 100644
--- a/src/crewai/task.py
+++ b/src/crewai/task.py
@@ -179,6 +179,7 @@ class Task(BaseModel):
_execution_span: Optional[Span] = PrivateAttr(default=None)
_original_description: Optional[str] = PrivateAttr(default=None)
_original_expected_output: Optional[str] = PrivateAttr(default=None)
+ _original_output_file: Optional[str] = PrivateAttr(default=None)
_thread: Optional[threading.Thread] = PrivateAttr(default=None)
_execution_time: Optional[float] = PrivateAttr(default=None)
@@ -213,8 +214,46 @@ class Task(BaseModel):
@field_validator("output_file")
@classmethod
- def output_file_validation(cls, value: str) -> str:
- """Validate the output file path by removing the / from the beginning of the path."""
+ def output_file_validation(cls, value: Optional[str]) -> Optional[str]:
+ """Validate the output file path.
+
+ Args:
+ value: The output file path to validate. Can be None or a string.
+ If the path contains template variables (e.g. {var}), leading slashes are preserved.
+ For regular paths, leading slashes are stripped.
+
+ Returns:
+ The validated and potentially modified path, or None if no path was provided.
+
+ Raises:
+ ValueError: If the path contains invalid characters, path traversal attempts,
+ or other security concerns.
+ """
+ if value is None:
+ return None
+
+ # Basic security checks
+ if ".." in value:
+ raise ValueError("Path traversal attempts are not allowed in output_file paths")
+
+ # Check for shell expansion first
+ if value.startswith('~') or value.startswith('$'):
+ raise ValueError("Shell expansion characters are not allowed in output_file paths")
+
+ # Then check other shell special characters
+ if any(char in value for char in ['|', '>', '<', '&', ';']):
+ raise ValueError("Shell special characters are not allowed in output_file paths")
+
+ # Don't strip leading slash if it's a template path with variables
+ if "{" in value or "}" in value:
+ # Validate template variable format
+ template_vars = [part.split("}")[0] for part in value.split("{")[1:]]
+ for var in template_vars:
+ if not var.isidentifier():
+ raise ValueError(f"Invalid template variable name: {var}")
+ return value
+
+ # Strip leading slash for regular paths
if value.startswith("/"):
return value[1:]
return value
@@ -393,27 +432,89 @@ class Task(BaseModel):
tasks_slices = [self.description, output]
return "\n".join(tasks_slices)
- def interpolate_inputs(self, inputs: Dict[str, Any]) -> None:
- """Interpolate inputs into the task description and expected output."""
+ def interpolate_inputs(self, inputs: Dict[str, Union[str, int, float]]) -> None:
+ """Interpolate inputs into the task description, expected output, and output file path.
+
+ Args:
+ inputs: Dictionary mapping template variables to their values.
+ Supported value types are strings, integers, and floats.
+
+ Raises:
+ ValueError: If a required template variable is missing from inputs.
+ """
if self._original_description is None:
self._original_description = self.description
if self._original_expected_output is None:
self._original_expected_output = self.expected_output
+ if self.output_file is not None and self._original_output_file is None:
+ self._original_output_file = self.output_file
+
+ if not inputs:
+ return
- if inputs:
+ try:
self.description = self._original_description.format(**inputs)
+ except KeyError as e:
+ raise ValueError(f"Missing required template variable '{e.args[0]}' in description") from e
+ except ValueError as e:
+ raise ValueError(f"Error interpolating description: {str(e)}") from e
+
+ try:
self.expected_output = self.interpolate_only(
input_string=self._original_expected_output, inputs=inputs
)
+ except (KeyError, ValueError) as e:
+ raise ValueError(f"Error interpolating expected_output: {str(e)}") from e
+
+ if self.output_file is not None:
+ try:
+ self.output_file = self.interpolate_only(
+ input_string=self._original_output_file, inputs=inputs
+ )
+ except (KeyError, ValueError) as e:
+ raise ValueError(f"Error interpolating output_file path: {str(e)}") from e
+
+ def interpolate_only(self, input_string: Optional[str], inputs: Dict[str, Union[str, int, float]]) -> str:
+ """Interpolate placeholders (e.g., {key}) in a string while leaving JSON untouched.
+
+ Args:
+ input_string: The string containing template variables to interpolate.
+ Can be None or empty, in which case an empty string is returned.
+ inputs: Dictionary mapping template variables to their values.
+ Supported value types are strings, integers, and floats.
+ If input_string is empty or has no placeholders, inputs can be empty.
+
+ Returns:
+ The interpolated string with all template variables replaced with their values.
+ Empty string if input_string is None or empty.
+
+ Raises:
+ ValueError: If a required template variable is missing from inputs.
+ KeyError: If a template variable is not found in the inputs dictionary.
+ """
+ if input_string is None or not input_string:
+ return ""
+ if "{" not in input_string and "}" not in input_string:
+ return input_string
+ if not inputs:
+ raise ValueError("Inputs dictionary cannot be empty when interpolating variables")
+
+ try:
+ # Validate input types
+ for key, value in inputs.items():
+ if not isinstance(value, (str, int, float)):
+ raise ValueError(f"Value for key '{key}' must be a string, integer, or float, got {type(value).__name__}")
- def interpolate_only(self, input_string: str, inputs: Dict[str, Any]) -> str:
- """Interpolate placeholders (e.g., {key}) in a string while leaving JSON untouched."""
- escaped_string = input_string.replace("{", "{{").replace("}", "}}")
+ escaped_string = input_string.replace("{", "{{").replace("}", "}}")
- for key in inputs.keys():
- escaped_string = escaped_string.replace(f"{{{{{key}}}}}", f"{{{key}}}")
+ for key in inputs.keys():
+ escaped_string = escaped_string.replace(f"{{{{{key}}}}}", f"{{{key}}}")
- return escaped_string.format(**inputs)
+ return escaped_string.format(**inputs)
+ except KeyError as e:
+ raise KeyError(f"Template variable '{e.args[0]}' not found in inputs dictionary") from e
+ except ValueError as e:
+ raise ValueError(f"Error during string interpolation: {str(e)}") from e
def increment_tools_errors(self) -> None:
"""Increment the tools errors counter."""
diff --git a/tests/cassettes/test_crew_output_file_end_to_end.yaml b/tests/cassettes/test_crew_output_file_end_to_end.yaml
new file mode 100644
index 000000000..2cbd6d9c3
--- /dev/null
+++ b/tests/cassettes/test_crew_output_file_end_to_end.yaml
@@ -0,0 +1,243 @@
+interactions:
+- request:
+ body: !!binary |
+ CuIcCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSuRwKEgoQY3Jld2FpLnRl
+ bGVtZXRyeRKjBwoQXK7w4+uvyEkrI9D5qyvcJxII5UmQ7hmczdIqDENyZXcgQ3JlYXRlZDABOfxQ
+ /hs4jBUYQUi3DBw4jBUYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoaCg5weXRob25fdmVy
+ c2lvbhIICgYzLjEyLjdKLgoIY3Jld19rZXkSIgogYzk3YjVmZWI1ZDFiNjZiYjU5MDA2YWFhMDFh
+ MjljZDZKMQoHY3Jld19pZBImCiRkZjY3NGMwYi1hOTc0LTQ3NTAtYjlkMS0yZWQxNjM3MzFiNTZK
+ HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
+ bnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgBStECCgtjcmV3
+ X2FnZW50cxLBAgq+Alt7ImtleSI6ICIwN2Q5OWI2MzA0MTFkMzVmZDkwNDdhNTMyZDUzZGRhNyIs
+ ICJpZCI6ICI5MDYwYTQ2Zi02MDY3LTQ1N2MtOGU3ZC04NjAyN2YzY2U5ZDUiLCAicm9sZSI6ICJS
+ ZXNlYXJjaGVyIiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6
+ IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwg
+ ImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZh
+ bHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUr/AQoKY3Jld190
+ YXNrcxLwAQrtAVt7ImtleSI6ICI2Mzk5NjUxN2YzZjNmMWM5NGQ2YmI2MTdhYTBiMWM0ZiIsICJp
+ ZCI6ICJjYTA4ZjkyOS0yMmI0LTQyZmQtYjViMC05N2M3MjM0ZDk5OTEiLCAiYXN5bmNfZXhlY3V0
+ aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIlJlc2Vh
+ cmNoZXIiLCAiYWdlbnRfa2V5IjogIjA3ZDk5YjYzMDQxMWQzNWZkOTA0N2E1MzJkNTNkZGE3Iiwg
+ InRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASjgIKEOTJZh9R45IwgGVg9cinZmISCJopKRMf
+ bpMJKgxUYXNrIENyZWF0ZWQwATlG+zQcOIwVGEHk0zUcOIwVGEouCghjcmV3X2tleRIiCiBjOTdi
+ NWZlYjVkMWI2NmJiNTkwMDZhYWEwMWEyOWNkNkoxCgdjcmV3X2lkEiYKJGRmNjc0YzBiLWE5NzQt
+ NDc1MC1iOWQxLTJlZDE2MzczMWI1NkouCgh0YXNrX2tleRIiCiA2Mzk5NjUxN2YzZjNmMWM5NGQ2
+ YmI2MTdhYTBiMWM0ZkoxCgd0YXNrX2lkEiYKJGNhMDhmOTI5LTIyYjQtNDJmZC1iNWIwLTk3Yzcy
+ MzRkOTk5MXoCGAGFAQABAAASowcKEEvwrN8+tNMIBwtnA+ip7jASCI78Hrh2wlsBKgxDcmV3IENy
+ ZWF0ZWQwATkcRqYeOIwVGEE8erQeOIwVGEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjg2LjBKGgoO
+ cHl0aG9uX3ZlcnNpb24SCAoGMy4xMi43Si4KCGNyZXdfa2V5EiIKIDhjMjc1MmY0OWU1YjlkMmI2
+ OGNiMzVjYWM4ZmNjODZkSjEKB2NyZXdfaWQSJgokZmRkYzA4ZTMtNDUyNi00N2Q2LThlNWMtNjY0
+ YzIyMjc4ZDgyShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQ
+ AEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIY
+ AUrRAgoLY3Jld19hZ2VudHMSwQIKvgJbeyJrZXkiOiAiOGJkMjEzOWI1OTc1MTgxNTA2ZTQxZmQ5
+ YzQ1NjNkNzUiLCAiaWQiOiAiY2UxNjA2YjktMjdiOS00ZDc4LWEyODctNDZiMDNlZDg3ZTA1Iiwg
+ InJvbGUiOiAiUmVzZWFyY2hlciIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwg
+ Im1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQt
+ NG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1
+ dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K
+ /wEKCmNyZXdfdGFza3MS8AEK7QFbeyJrZXkiOiAiMGQ2ODVhMjE5OTRkOTQ5MDk3YmM1YTU2ZDcz
+ N2U2ZDEiLCAiaWQiOiAiNDdkMzRjZjktMGYxZS00Y2JkLTgzMzItNzRjZjY0YWRlOThlIiwgImFz
+ eW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9s
+ ZSI6ICJSZXNlYXJjaGVyIiwgImFnZW50X2tleSI6ICI4YmQyMTM5YjU5NzUxODE1MDZlNDFmZDlj
+ NDU2M2Q3NSIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEo4CChAf4TXS782b0PBJ4NSB
+ JXwsEgjXnd13GkMzlyoMVGFzayBDcmVhdGVkMAE5mb/cHjiMFRhBGRTiHjiMFRhKLgoIY3Jld19r
+ ZXkSIgogOGMyNzUyZjQ5ZTViOWQyYjY4Y2IzNWNhYzhmY2M4NmRKMQoHY3Jld19pZBImCiRmZGRj
+ MDhlMy00NTI2LTQ3ZDYtOGU1Yy02NjRjMjIyNzhkODJKLgoIdGFza19rZXkSIgogMGQ2ODVhMjE5
+ OTRkOTQ5MDk3YmM1YTU2ZDczN2U2ZDFKMQoHdGFza19pZBImCiQ0N2QzNGNmOS0wZjFlLTRjYmQt
+ ODMzMi03NGNmNjRhZGU5OGV6AhgBhQEAAQAAEqMHChAyBGKhzDhROB5pmAoXrikyEgj6SCwzj1dU
+ LyoMQ3JldyBDcmVhdGVkMAE5vkjTHziMFRhBRDbhHziMFRhKGgoOY3Jld2FpX3ZlcnNpb24SCAoG
+ MC44Ni4wShoKDnB5dGhvbl92ZXJzaW9uEggKBjMuMTIuN0ouCghjcmV3X2tleRIiCiBiNjczNjg2
+ ZmM4MjJjMjAzYzdlODc5YzY3NTQyNDY5OUoxCgdjcmV3X2lkEiYKJGYyYWVlYTYzLTU2OWUtNDUz
+ NS1iZTY0LTRiZjYzZmU5NjhjN0ocCgxjcmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3
+ X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29m
+ X2FnZW50cxICGAFK0QIKC2NyZXdfYWdlbnRzEsECCr4CW3sia2V5IjogImI1OWNmNzdiNmU3NjU4
+ NDg3MGViMWMzODgyM2Q3ZTI4IiwgImlkIjogImJiZjNkM2E4LWEwMjUtNGI0ZC1hY2Q0LTFmNzcz
+ NTI3MWJmMCIsICJyb2xlIjogIlJlc2VhcmNoZXIiLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9p
+ dGVyIjogMjAsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJs
+ bG0iOiAiZ3B0LTRvLW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3df
+ Y29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFt
+ ZXMiOiBbXX1dSv8BCgpjcmV3X3Rhc2tzEvABCu0BW3sia2V5IjogImE1ZTVjNThjZWExYjlkMDAz
+ MzJlNjg0NDFkMzI3YmRmIiwgImlkIjogIjBiOTRiMTY0LTM5NTktNGFmYS05Njg4LWJjNmEwZWMy
+ MWYzOCIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwg
+ ImFnZW50X3JvbGUiOiAiUmVzZWFyY2hlciIsICJhZ2VudF9rZXkiOiAiYjU5Y2Y3N2I2ZTc2NTg0
+ ODcwZWIxYzM4ODIzZDdlMjgiLCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKOAgoQyYfi
+ Ftim717svttBZY3p5hIIUxR5bBHzWWkqDFRhc2sgQ3JlYXRlZDABOV4OBiA4jBUYQbLjBiA4jBUY
+ Si4KCGNyZXdfa2V5EiIKIGI2NzM2ODZmYzgyMmMyMDNjN2U4NzljNjc1NDI0Njk5SjEKB2NyZXdf
+ aWQSJgokZjJhZWVhNjMtNTY5ZS00NTM1LWJlNjQtNGJmNjNmZTk2OGM3Si4KCHRhc2tfa2V5EiIK
+ IGE1ZTVjNThjZWExYjlkMDAzMzJlNjg0NDFkMzI3YmRmSjEKB3Rhc2tfaWQSJgokMGI5NGIxNjQt
+ Mzk1OS00YWZhLTk2ODgtYmM2YTBlYzIxZjM4egIYAYUBAAEAAA==
+ headers:
+ Accept:
+ - '*/*'
+ Accept-Encoding:
+ - gzip, deflate
+ Connection:
+ - keep-alive
+ Content-Length:
+ - '3685'
+ Content-Type:
+ - application/x-protobuf
+ User-Agent:
+ - OTel-OTLP-Exporter-Python/1.27.0
+ method: POST
+ uri: https://telemetry.crewai.com:4319/v1/traces
+ response:
+ body:
+ string: "\n\0"
+ headers:
+ Content-Length:
+ - '2'
+ Content-Type:
+ - application/x-protobuf
+ Date:
+ - Sun, 29 Dec 2024 04:43:27 GMT
+ status:
+ code: 200
+ message: OK
+- request:
+ body: '{"messages": [{"role": "system", "content": "You are Researcher. You have
+ extensive AI research experience.\nYour personal goal is: Analyze AI topics\nTo
+ give my best complete final answer to the task use the exact following format:\n\nThought:
+ I now can give a great answer\nFinal Answer: Your final answer must be the great
+ and the most complete as possible, it must be outcome described.\n\nI MUST use
+ these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent
+ Task: Explain the advantages of AI.\n\nThis is the expect criteria for your
+ final answer: A summary of the main advantages, bullet points recommended.\nyou
+ MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
+ This is VERY important to you, use the tools available and give your best Final
+ Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop":
+ ["\nObservation:"], "stream": false}'
+ headers:
+ accept:
+ - application/json
+ accept-encoding:
+ - gzip, deflate
+ connection:
+ - keep-alive
+ content-length:
+ - '922'
+ content-type:
+ - application/json
+ cookie:
+ - _cfuvid=eff7OIkJ0zWRunpA6z67LHqscmSe6XjNxXiPw1R3xCc-1733770413538-0.0.1.1-604800000
+ host:
+ - api.openai.com
+ user-agent:
+ - OpenAI/Python 1.52.1
+ x-stainless-arch:
+ - x64
+ x-stainless-async:
+ - 'false'
+ x-stainless-lang:
+ - python
+ x-stainless-os:
+ - Linux
+ x-stainless-package-version:
+ - 1.52.1
+ x-stainless-raw-response:
+ - 'true'
+ x-stainless-retry-count:
+ - '0'
+ x-stainless-runtime:
+ - CPython
+ x-stainless-runtime-version:
+ - 3.12.7
+ method: POST
+ uri: https://api.openai.com/v1/chat/completions
+ response:
+ content: "{\n \"id\": \"chatcmpl-AjfR6FDuTw7NGzy8w7sxjvOkUQlru\",\n \"object\":
+ \"chat.completion\",\n \"created\": 1735447404,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
+ \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
+ \"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
+ Answer: \\n**Advantages of AI** \\n\\n1. **Increased Efficiency and Productivity**
+ \ \\n - AI systems can process large amounts of data quickly and accurately,
+ leading to faster decision-making and increased productivity in various sectors.\\n\\n2.
+ **Cost Savings** \\n - Automation of repetitive and time-consuming tasks
+ reduces labor costs and increases operational efficiency, allowing businesses
+ to allocate resources more effectively.\\n\\n3. **Enhanced Data Analysis** \\n
+ \ - AI excels at analyzing big data, identifying patterns, and providing insights
+ that support better strategic planning and business decision-making.\\n\\n4.
+ **24/7 Availability** \\n - AI solutions, such as chatbots and virtual assistants,
+ operate continuously without breaks, offering constant support and customer
+ service, enhancing user experience.\\n\\n5. **Personalization** \\n - AI
+ enables the customization of content, products, and services based on user preferences
+ and behaviors, leading to improved customer satisfaction and loyalty.\\n\\n6.
+ **Improved Accuracy** \\n - AI technologies, such as machine learning algorithms,
+ reduce the likelihood of human error in various processes, leading to greater
+ accuracy and reliability.\\n\\n7. **Enhanced Innovation** \\n - AI fosters
+ innovative solutions by providing new tools and approaches to problem-solving,
+ enabling companies to develop cutting-edge products and services.\\n\\n8. **Scalability**
+ \ \\n - AI can be scaled to handle varying amounts of workloads without significant
+ changes to infrastructure, making it easier for organizations to expand operations.\\n\\n9.
+ **Predictive Capabilities** \\n - Advanced analytics powered by AI can anticipate
+ trends and outcomes, allowing businesses to proactively adjust strategies and
+ improve forecasting.\\n\\n10. **Health Benefits** \\n - In healthcare, AI
+ assists in diagnostics, personalized treatment plans, and predictive analytics,
+ leading to better patient care and improved health outcomes.\\n\\n11. **Safety
+ and Risk Mitigation** \\n - AI can enhance safety in various industries
+ by taking over dangerous tasks, monitoring for hazards, and predicting maintenance
+ needs for critical machinery, thereby preventing accidents.\\n\\n12. **Reduced
+ Environmental Impact** \\n - AI can optimize resource usage in areas such
+ as energy consumption and supply chain logistics, contributing to sustainability
+ efforts and reducing overall environmental footprints.\",\n \"refusal\":
+ null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
+ \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 168,\n \"completion_tokens\":
+ 440,\n \"total_tokens\": 608,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
+ 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
+ \ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
+ 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\":
+ \"fp_0aa8d3e20b\"\n}\n"
+ headers:
+ CF-Cache-Status:
+ - DYNAMIC
+ CF-RAY:
+ - 8f9721053d1eb9f1-SEA
+ Connection:
+ - keep-alive
+ Content-Encoding:
+ - gzip
+ Content-Type:
+ - application/json
+ Date:
+ - Sun, 29 Dec 2024 04:43:32 GMT
+ Server:
+ - cloudflare
+ Set-Cookie:
+ - __cf_bm=5enubNIoQSGMYEgy8Q2FpzzhphA0y.0lXukRZrWFvMk-1735447412-1.0.1.1-FIK1sMkUl3YnW1gTC6ftDtb2mKsbosb4mwabdFAlWCfJ6pXeavYq.bPsfKNvzAb5WYq60yVGH5lHsJT05bhSgw;
+ path=/; expires=Sun, 29-Dec-24 05:13:32 GMT; domain=.api.openai.com; HttpOnly;
+ Secure; SameSite=None
+ - _cfuvid=63wmKMTuFamkLN8FBI4fP8JZWbjWiRxWm7wb3kz.z_A-1735447412038-0.0.1.1-604800000;
+ path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+ Transfer-Encoding:
+ - chunked
+ X-Content-Type-Options:
+ - nosniff
+ access-control-expose-headers:
+ - X-Request-ID
+ alt-svc:
+ - h3=":443"; ma=86400
+ openai-organization:
+ - crewai-iuxna1
+ openai-processing-ms:
+ - '7577'
+ openai-version:
+ - '2020-10-01'
+ strict-transport-security:
+ - max-age=31536000; includeSubDomains; preload
+ x-ratelimit-limit-requests:
+ - '30000'
+ x-ratelimit-limit-tokens:
+ - '150000000'
+ x-ratelimit-remaining-requests:
+ - '29999'
+ x-ratelimit-remaining-tokens:
+ - '149999793'
+ x-ratelimit-reset-requests:
+ - 2ms
+ x-ratelimit-reset-tokens:
+ - 0s
+ x-request-id:
+ - req_55b8d714656e8f10f4e23cbe9034d66b
+ http_version: HTTP/1.1
+ status_code: 200
+version: 1
diff --git a/tests/crew_test.py b/tests/crew_test.py
index 2003ddada..74bcf08d3 100644
--- a/tests/crew_test.py
+++ b/tests/crew_test.py
@@ -1941,6 +1941,90 @@ def test_crew_log_file_output(tmp_path):
assert test_file.exists()
[email protected](filter_headers=["authorization"])
+def test_crew_output_file_end_to_end(tmp_path):
+ """Test output file functionality in a full crew context."""
+ # Create an agent
+ agent = Agent(
+ role="Researcher",
+ goal="Analyze AI topics",
+ backstory="You have extensive AI research experience.",
+ allow_delegation=False,
+ )
+
+ # Create a task with dynamic output file path
+ dynamic_path = tmp_path / "output_{topic}.txt"
+ task = Task(
+ description="Explain the advantages of {topic}.",
+ expected_output="A summary of the main advantages, bullet points recommended.",
+ agent=agent,
+ output_file=str(dynamic_path),
+ )
+
+ # Create and run the crew
+ crew = Crew(
+ agents=[agent],
+ tasks=[task],
+ process=Process.sequential,
+ )
+ crew.kickoff(inputs={"topic": "AI"})
+
+ # Verify file creation and cleanup
+ expected_file = tmp_path / "output_AI.txt"
+ assert expected_file.exists(), f"Output file {expected_file} was not created"
+
+
[email protected](filter_headers=["authorization"])
+def test_crew_output_file_validation_failures():
+ """Test output file validation failures in a crew context."""
+ agent = Agent(
+ role="Researcher",
+ goal="Analyze data",
+ backstory="You analyze data files.",
+ allow_delegation=False,
+ )
+
+ # Test path traversal
+ with pytest.raises(ValueError, match="Path traversal"):
+ task = Task(
+ description="Analyze data",
+ expected_output="Analysis results",
+ agent=agent,
+ output_file="../output.txt"
+ )
+ Crew(agents=[agent], tasks=[task]).kickoff()
+
+ # Test shell special characters
+ with pytest.raises(ValueError, match="Shell special characters"):
+ task = Task(
+ description="Analyze data",
+ expected_output="Analysis results",
+ agent=agent,
+ output_file="output.txt | rm -rf /"
+ )
+ Crew(agents=[agent], tasks=[task]).kickoff()
+
+ # Test shell expansion
+ with pytest.raises(ValueError, match="Shell expansion"):
+ task = Task(
+ description="Analyze data",
+ expected_output="Analysis results",
+ agent=agent,
+ output_file="~/output.txt"
+ )
+ Crew(agents=[agent], tasks=[task]).kickoff()
+
+ # Test invalid template variable
+ with pytest.raises(ValueError, match="Invalid template variable"):
+ task = Task(
+ description="Analyze data",
+ expected_output="Analysis results",
+ agent=agent,
+ output_file="{invalid-name}/output.txt"
+ )
+ Crew(agents=[agent], tasks=[task]).kickoff()
+
+
@pytest.mark.vcr(filter_headers=["authorization"])
def test_manager_agent():
from unittest.mock import patch
@@ -3125,4 +3209,4 @@ def test_multimodal_agent_live_image_analysis():
# Verify we got a meaningful response
assert isinstance(result.raw, str)
assert len(result.raw) > 100 # Expecting a detailed analysis
- assert "error" not in result.raw.lower() # No error messages in response
\ No newline at end of file
+ assert "error" not in result.raw.lower() # No error messages in response
diff --git a/tests/task_test.py b/tests/task_test.py
index 40eb98e54..dc15c251f 100644
--- a/tests/task_test.py
+++ b/tests/task_test.py
@@ -719,21 +719,24 @@ def test_interpolate_inputs():
task = Task(
description="Give me a list of 5 interesting ideas about {topic} to explore for an article, what makes them unique and interesting.",
expected_output="Bullet point list of 5 interesting ideas about {topic}.",
+ output_file="/tmp/{topic}/output_{date}.txt"
)
- task.interpolate_inputs(inputs={"topic": "AI"})
+ task.interpolate_inputs(inputs={"topic": "AI", "date": "2024"})
assert (
task.description
== "Give me a list of 5 interesting ideas about AI to explore for an article, what makes them unique and interesting."
)
assert task.expected_output == "Bullet point list of 5 interesting ideas about AI."
+ assert task.output_file == "/tmp/AI/output_2024.txt"
- task.interpolate_inputs(inputs={"topic": "ML"})
+ task.interpolate_inputs(inputs={"topic": "ML", "date": "2025"})
assert (
task.description
== "Give me a list of 5 interesting ideas about ML to explore for an article, what makes them unique and interesting."
)
assert task.expected_output == "Bullet point list of 5 interesting ideas about ML."
+ assert task.output_file == "/tmp/ML/output_2025.txt"
def test_interpolate_only():
@@ -872,3 +875,61 @@ def test_key():
assert (
task.key == hash
), "The key should be the hash of the non-interpolated description."
+
+
+def test_output_file_validation():
+ """Test output file path validation."""
+ # Valid paths
+ assert Task(
+ description="Test task",
+ expected_output="Test output",
+ output_file="output.txt"
+ ).output_file == "output.txt"
+ assert Task(
+ description="Test task",
+ expected_output="Test output",
+ output_file="/tmp/output.txt"
+ ).output_file == "tmp/output.txt"
+ assert Task(
+ description="Test task",
+ expected_output="Test output",
+ output_file="{dir}/output_{date}.txt"
+ ).output_file == "{dir}/output_{date}.txt"
+
+ # Invalid paths
+ with pytest.raises(ValueError, match="Path traversal"):
+ Task(
+ description="Test task",
+ expected_output="Test output",
+ output_file="../output.txt"
+ )
+ with pytest.raises(ValueError, match="Path traversal"):
+ Task(
+ description="Test task",
+ expected_output="Test output",
+ output_file="folder/../output.txt"
+ )
+ with pytest.raises(ValueError, match="Shell special characters"):
+ Task(
+ description="Test task",
+ expected_output="Test output",
+ output_file="output.txt | rm -rf /"
+ )
+ with pytest.raises(ValueError, match="Shell expansion"):
+ Task(
+ description="Test task",
+ expected_output="Test output",
+ output_file="~/output.txt"
+ )
+ with pytest.raises(ValueError, match="Shell expansion"):
+ Task(
+ description="Test task",
+ expected_output="Test output",
+ output_file="$HOME/output.txt"
+ )
+ with pytest.raises(ValueError, match="Invalid template variable"):
+ Task(
+ description="Test task",
+ expected_output="Test output",
+ output_file="{invalid-name}/output.txt"
+ )