mirror of
https://github.com/maybe-finance/maybe.git
synced 2025-08-06 14:05:20 +02:00
Transaction rules engine V1 (#1900)
* Domain model sketch
* Scaffold out rules domain
* Migrations
* Remove existing data enrichment for clean slate
* Sketch out business logic and basic tests
* Simplify rule scope building and action executions
* Get generator working again
* Basic implementation + tests
* Remove manual merchant management (rules will replace)
* Revert "Remove manual merchant management (rules will replace)"
This reverts commit 83dcbd9ff0.
* Family and Provider merchants model
* Fix brakeman warnings
* Fix notification loader
* Update notification position
* Add Rule action and condition registries
* Rule form with compound conditions and tests
* Split out notification types, add CTA type
* Rules form builder and Stimulus controller
* Clean up rule registry domain
* Clean up rules stimulus controller
* CTA message for rule when user changes transaction category
* Fix tests
* Lint updates
* Centralize notifications in Notifiable concern
* Implement category rule prompts with auto backoff and option to disable
* Fix layout bug caused by merge conflict
* Initialize rule with correct action for category CTA
* Add rule deletions, get rules working
* Complete dynamic rule form, split Stimulus controllers by resource
* Fix failing tests
* Change test password to avoid chromium conflicts
* Update integration tests
* Centralize all test password references
* Add re-apply rule action
* Rule confirm modal
* Run migrations
* Trigger rule notification after inline category updates
* Clean up rule styles
* Basic attribute locking for rules
* Apply attribute locks on user edits
* Log data enrichments, only apply rules to unlocked attributes
* Fix merge errors
* Additional merge conflict fixes
* Form UI improvements, ignore attribute locks on manual rule application
* Batch AI auto-categorization of transactions
* Auto merchant detection, ai enrichment in batches
* Fix Plaid merchant assignments
* Plaid category matching
* Cleanup 1
* Test cleanup
* Remove stale route
* Fix desktop chat UI issues
* Fix mobile nav styling issues
This commit is contained in:
Zach Gollwitzer
GitHub
parent
8edd7ecef0
commit
297a695d0f
152 changed files with 4502 additions and 612 deletions
194
test/vcr_cassettes/openai/auto_categorize.yml
Normal file
194
test/vcr_cassettes/openai/auto_categorize.yml
Normal file
|
|
@ -0,0 +1,194 @@
|
|||
---
|
||||
http_interactions:
|
||||
- request:
|
||||
method: post
|
||||
uri: https://api.openai.com/v1/responses
|
||||
body:
|
||||
encoding: UTF-8
|
||||
string: '{"model":"gpt-4.1-mini","input":[{"role":"developer","content":"Here
|
||||
are the user''s available categories in JSON format:\n\n```json\n[{\"id\":\"shopping_id\",\"name\":\"Shopping\",\"is_subcategory\":false,\"parent_id\":null,\"classification\":\"expense\"},{\"id\":\"subscriptions_id\",\"name\":\"Subscriptions\",\"is_subcategory\":true,\"parent_id\":null,\"classification\":\"expense\"},{\"id\":\"restaurants_id\",\"name\":\"Restaurants\",\"is_subcategory\":false,\"parent_id\":null,\"classification\":\"expense\"},{\"id\":\"fast_food_id\",\"name\":\"Fast
|
||||
Food\",\"is_subcategory\":true,\"parent_id\":\"restaurants_id\",\"classification\":\"expense\"},{\"id\":\"income_id\",\"name\":\"Income\",\"is_subcategory\":false,\"parent_id\":null,\"classification\":\"income\"}]\n```\n\nUse
|
||||
the available categories to auto-categorize the following transactions:\n\n```json\n[{\"id\":\"1\",\"name\":\"McDonalds\",\"amount\":20,\"classification\":\"expense\",\"merchant\":\"McDonalds\",\"hint\":\"Fast
|
||||
Food\"},{\"id\":\"2\",\"name\":\"Amazon purchase\",\"amount\":100,\"classification\":\"expense\",\"merchant\":\"Amazon\"},{\"id\":\"3\",\"name\":\"Netflix
|
||||
subscription\",\"amount\":10,\"classification\":\"expense\",\"merchant\":\"Netflix\",\"hint\":\"Subscriptions\"},{\"id\":\"4\",\"name\":\"paycheck\",\"amount\":3000,\"classification\":\"income\"},{\"id\":\"5\",\"name\":\"Italian
|
||||
dinner with friends\",\"amount\":100,\"classification\":\"expense\"},{\"id\":\"6\",\"name\":\"1212XXXBCaaa
|
||||
charge\",\"amount\":2.99,\"classification\":\"expense\"}]\n```\n"}],"text":{"format":{"type":"json_schema","name":"auto_categorize_personal_finance_transactions","strict":true,"schema":{"type":"object","properties":{"categorizations":{"type":"array","description":"An
|
||||
array of auto-categorizations for each transaction","items":{"type":"object","properties":{"transaction_id":{"type":"string","description":"The
|
||||
internal ID of the original transaction","enum":["1","2","3","4","5","6"]},"category_name":{"type":"string","description":"The
|
||||
matched category name of the transaction, or null if no match","enum":["Shopping","Subscriptions","Restaurants","Fast
|
||||
Food","Income","null"]}},"required":["transaction_id","category_name"],"additionalProperties":false}}},"required":["categorizations"],"additionalProperties":false}}},"instructions":"You
|
||||
are an assistant to a consumer personal finance app. You will be provided
|
||||
a list\nof the user''s transactions and a list of the user''s categories. Your
|
||||
job is to auto-categorize\neach transaction.\n\nClosely follow ALL the rules
|
||||
below while auto-categorizing:\n\n- Return 1 result per transaction\n- Correlate
|
||||
each transaction by ID (transaction_id)\n- Attempt to match the most specific
|
||||
category possible (i.e. subcategory over parent category)\n- Category and
|
||||
transaction classifications should match (i.e. if transaction is an \"expense\",
|
||||
the category must have classification of \"expense\")\n- If you don''t know
|
||||
the category, return \"null\"\n - You should always favor \"null\" over false
|
||||
positives\n - Be slightly pessimistic. Only match a category if you''re
|
||||
60%+ confident it is the correct one.\n- Each transaction has varying metadata
|
||||
that can be used to determine the category\n - Note: \"hint\" comes from
|
||||
3rd party aggregators and typically represents a category name that\n may
|
||||
or may not match any of the user-supplied categories\n"}'
|
||||
headers:
|
||||
Content-Type:
|
||||
- application/json
|
||||
Authorization:
|
||||
- Bearer <OPENAI_ACCESS_TOKEN>
|
||||
Accept-Encoding:
|
||||
- gzip;q=1.0,deflate;q=0.6,identity;q=0.3
|
||||
Accept:
|
||||
- "*/*"
|
||||
User-Agent:
|
||||
- Ruby
|
||||
response:
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
headers:
|
||||
Date:
|
||||
- Wed, 16 Apr 2025 14:07:39 GMT
|
||||
Content-Type:
|
||||
- application/json
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
Connection:
|
||||
- keep-alive
|
||||
Openai-Version:
|
||||
- '2020-10-01'
|
||||
Openai-Organization:
|
||||
- user-r6cwd3mn6iv6gn748b2xoajx
|
||||
X-Request-Id:
|
||||
- req_01b869bd9eb7b994a80e79f6de92e5a2
|
||||
Openai-Processing-Ms:
|
||||
- '2173'
|
||||
Strict-Transport-Security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
Cf-Cache-Status:
|
||||
- DYNAMIC
|
||||
Set-Cookie:
|
||||
- __cf_bm=xGkX7L6XeEFLp6ZPB2Y.LLHD_YSpzTH28MUro6fQG7Y-1744812459-1.0.1.1-uy8WQsFzGblq3h.u6WFs2vld_HM.5fveVAFBsQ6y.Za22DSEa22k3NS7.GAUbgAvoVjGvSQlkm8LkSZyU3wZfN70cUpZrg27orQt0Nfq91U;
|
||||
path=/; expires=Wed, 16-Apr-25 14:37:39 GMT; domain=.api.openai.com; HttpOnly;
|
||||
Secure; SameSite=None
|
||||
- _cfuvid=LicWzTMZxt1n1GLU6XQx3NnU0PbKnI0m97CH.p0895U-1744812459077-0.0.1.1-604800000;
|
||||
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
Server:
|
||||
- cloudflare
|
||||
Cf-Ray:
|
||||
- 93143ffeffe8cf6b-CMH
|
||||
Alt-Svc:
|
||||
- h3=":443"; ma=86400
|
||||
body:
|
||||
encoding: ASCII-8BIT
|
||||
string: |-
|
||||
{
|
||||
"id": "resp_67ffb9a8e530819290c5d3ec8aaf326d0e0f06e2ac13ae37",
|
||||
"object": "response",
|
||||
"created_at": 1744812456,
|
||||
"status": "completed",
|
||||
"error": null,
|
||||
"incomplete_details": null,
|
||||
"instructions": "You are an assistant to a consumer personal finance app. You will be provided a list\nof the user's transactions and a list of the user's categories. Your job is to auto-categorize\neach transaction.\n\nClosely follow ALL the rules below while auto-categorizing:\n\n- Return 1 result per transaction\n- Correlate each transaction by ID (transaction_id)\n- Attempt to match the most specific category possible (i.e. subcategory over parent category)\n- Category and transaction classifications should match (i.e. if transaction is an \"expense\", the category must have classification of \"expense\")\n- If you don't know the category, return \"null\"\n - You should always favor \"null\" over false positives\n - Be slightly pessimistic. Only match a category if you're 60%+ confident it is the correct one.\n- Each transaction has varying metadata that can be used to determine the category\n - Note: \"hint\" comes from 3rd party aggregators and typically represents a category name that\n may or may not match any of the user-supplied categories\n",
|
||||
"max_output_tokens": null,
|
||||
"model": "gpt-4.1-mini-2025-04-14",
|
||||
"output": [
|
||||
{
|
||||
"id": "msg_67ffb9a96b3c81928d9da130e889a9aa0e0f06e2ac13ae37",
|
||||
"type": "message",
|
||||
"status": "completed",
|
||||
"content": [
|
||||
{
|
||||
"type": "output_text",
|
||||
"annotations": [],
|
||||
"text": "{\"categorizations\":[{\"transaction_id\":\"1\",\"category_name\":\"Fast Food\"},{\"transaction_id\":\"2\",\"category_name\":\"Shopping\"},{\"transaction_id\":\"3\",\"category_name\":\"Subscriptions\"},{\"transaction_id\":\"4\",\"category_name\":\"Income\"},{\"transaction_id\":\"5\",\"category_name\":\"Restaurants\"},{\"transaction_id\":\"6\",\"category_name\":\"null\"}]}"
|
||||
}
|
||||
],
|
||||
"role": "assistant"
|
||||
}
|
||||
],
|
||||
"parallel_tool_calls": true,
|
||||
"previous_response_id": null,
|
||||
"reasoning": {
|
||||
"effort": null,
|
||||
"summary": null
|
||||
},
|
||||
"store": true,
|
||||
"temperature": 1.0,
|
||||
"text": {
|
||||
"format": {
|
||||
"type": "json_schema",
|
||||
"description": null,
|
||||
"name": "auto_categorize_personal_finance_transactions",
|
||||
"schema": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"categorizations": {
|
||||
"type": "array",
|
||||
"description": "An array of auto-categorizations for each transaction",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"transaction_id": {
|
||||
"type": "string",
|
||||
"description": "The internal ID of the original transaction",
|
||||
"enum": [
|
||||
"1",
|
||||
"2",
|
||||
"3",
|
||||
"4",
|
||||
"5",
|
||||
"6"
|
||||
]
|
||||
},
|
||||
"category_name": {
|
||||
"type": "string",
|
||||
"description": "The matched category name of the transaction, or null if no match",
|
||||
"enum": [
|
||||
"Shopping",
|
||||
"Subscriptions",
|
||||
"Restaurants",
|
||||
"Fast Food",
|
||||
"Income",
|
||||
"null"
|
||||
]
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"transaction_id",
|
||||
"category_name"
|
||||
],
|
||||
"additionalProperties": false
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"categorizations"
|
||||
],
|
||||
"additionalProperties": false
|
||||
},
|
||||
"strict": true
|
||||
}
|
||||
},
|
||||
"tool_choice": "auto",
|
||||
"tools": [],
|
||||
"top_p": 1.0,
|
||||
"truncation": "disabled",
|
||||
"usage": {
|
||||
"input_tokens": 659,
|
||||
"input_tokens_details": {
|
||||
"cached_tokens": 0
|
||||
},
|
||||
"output_tokens": 70,
|
||||
"output_tokens_details": {
|
||||
"reasoning_tokens": 0
|
||||
},
|
||||
"total_tokens": 729
|
||||
},
|
||||
"user": null,
|
||||
"metadata": {}
|
||||
}
|
||||
recorded_at: Wed, 16 Apr 2025 14:07:39 GMT
|
||||
recorded_with: VCR 6.3.1
|
||||
Loading…
Add table
Add a link
Reference in a new issue