Buggy Agent Function Calling

[user905]

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:)
• Please do not modify this template :) and fill in all the required fields.

1. Is this request related to a challenge you're experiencing? Tell me about your story.

Agent function calls using either FunctionCalling or ReAct are failing without much explanation.

This issue is discussed here and here, but neither chain provides a solution.

Here is the model we are using:

Here's the chatflow's DSL:
app:
description: ''
icon: 🤖
icon_background: '#FFEAD5'
mode: advanced-chat
name: test
use_icon_as_answer_icon: false
dependencies: []
kind: app
version: 0.1.5
workflow:
conversation_variables: []
environment_variables: []
features:
file_upload:
allowed_file_extensions:
- .JPG
- .JPEG
- .PNG
- .GIF
- .WEBP
- .SVG
allowed_file_types:
- image
allowed_file_upload_methods:
- local_file
- remote_url
enabled: false
fileUploadConfig:
audio_file_size_limit: 50
batch_count_limit: 20
file_size_limit: 200
image_file_size_limit: 10
video_file_size_limit: 100
workflow_file_upload_limit: 10
image:
enabled: false
number_limits: 3
transfer_methods:
- local_file
- remote_url
number_limits: 3
opening_statement: ''
retriever_resource:
enabled: true
sensitive_word_avoidance:
enabled: false
speech_to_text:
enabled: false
suggested_questions: []
suggested_questions_after_answer:
enabled: false
text_to_speech:
enabled: false
language: ''
voice: ''
graph:
edges:
- data:
isInLoop: false
sourceType: start
targetType: agent
id: 1744914522833-source-1744914530369-target
source: '1744914522833'
sourceHandle: source
target: '1744914530369'
targetHandle: target
type: custom
zIndex: 0
- data:
isInLoop: false
sourceType: agent
targetType: answer
id: 1744914530369-source-answer-target
source: '1744914530369'
sourceHandle: source
target: answer
targetHandle: target
type: custom
zIndex: 0
nodes:
- data:
desc: ''
selected: false
title: Start
type: start
variables: []
height: 54
id: '1744914522833'
position:
x: 80
y: 282
positionAbsolute:
x: 80
y: 282
sourcePosition: right
targetPosition: left
type: custom
width: 244
- data:
agent_parameters:
instruction:
type: constant
value: when a user inputs a question about a project/, return the PARSID
of that project. otherwise say the question isn't project related.
model:
type: constant
value:
completion_params: {}
mode: chat
model: gpt-4o
model_type: llm
provider: langgenius/azure_openai/azure_openai
type: model-selector
query:
type: constant
value: '{{#sys.query#}}'
tools:
type: constant
value:
- enabled: true
extra:
description: ''
parameters: {}
provider_name: 682a753b-74e4-4434-b86c-4261aac96680
schemas: []
settings: {}
tool_label: projects_get
tool_name: projects_get
type: api
agent_strategy_label: ReAct
agent_strategy_name: ReAct
agent_strategy_provider_name: langgenius/agent/agent
desc: ''
output_schema: null
plugin_unique_identifier: langgenius/agent:0.0.9@f16916b704a20067317dbe9030f62aa28f0832021a3ef6d4ce699504074c5e13
selected: true
title: Agent
type: agent
height: 198
id: '1744914530369'
position:
x: 380
y: 282
positionAbsolute:
x: 380
y: 282
selected: true
sourcePosition: right
targetPosition: left
type: custom
width: 244
- data:
answer: '{{#llm.text#}}'
desc: ''
selected: false
title: Answer
type: answer
variables: []
height: 104
id: answer
position:
x: 680
y: 282
positionAbsolute:
x: 680
y: 282
sourcePosition: right
targetPosition: left
type: custom
width: 244
viewport:
x: 470
y: 233.5
zoom: 1

2. Additional context or comments

No response