744faf12c0
Extract "response cost" object to unify calculations around LLM usage costs
2025-08-27 13:18:41 +02:00
81d6df3616
Remove comments from card prompts
...
We don't use to_prompt to generate AI responses anymore, only for events. Grabbing
all the comments don't make as much sense, and I'm sure it is quite expensive
2025-08-27 09:56:13 +02:00
853a75a54f
Rename "cost_microcents" => "cost_in_microcents"
2025-08-27 09:38:23 +02:00
fc0fccef11
Show only published cards to Fizzy Ask
2025-08-26 11:42:12 +02:00
c3e0deb57f
Remove test for now private method
2025-08-25 10:32:33 +02:00
6b89aa6805
Improve naming & remove money accessors
2025-08-25 10:30:43 +02:00
abad369c6a
Introduce a Quota and Money object
2025-08-25 10:29:00 +02:00
cb5fe7c4f8
Add spend limits to conversations
2025-08-25 10:24:15 +02:00
78fdabf62f
Merge pull request #932 from basecamp/fizzy-bar-v1
...
Fizzy bar V1
2025-08-25 07:16:42 +02:00
f87a403107
Fix PR review comments
2025-08-22 07:33:26 +02:00
89af9066d3
Remove Fizzy Do command logic
2025-08-22 07:33:24 +02:00
c8569ce8b9
Split indexed_by into two filters: indexed by and sort by
...
https://3.basecamp.com/2914079/buckets/37331921/todos/8877489555#__recording_8987808963
2025-08-21 19:12:54 +02:00
fa82dc0384
Remove code related to Fizzy Do /command support and filtering
...
https://3.basecamp.com/2914079/buckets/37331921/messages/8961776532
2025-08-18 13:41:20 +02:00
4f219fadf3
Add test for the price calculation
2025-08-13 15:14:12 +02:00
aa11c82e1c
Add test for the list comments tool
2025-08-13 15:14:12 +02:00
0807337ede
Add test for the list collections tool
2025-08-13 15:14:12 +02:00
8574e53d83
Add test for the list users tool
2025-08-13 15:14:12 +02:00
33daa866f3
Test the list cards tool
2025-08-13 15:14:12 +02:00
c1bd68d0e6
Add tests for OrderClause
2025-08-13 15:14:12 +02:00
7f38586bda
Fix crash when searching
2025-08-13 15:14:12 +02:00
8a8888c3ef
Tidy up #ask & #respond
2025-08-13 15:14:12 +02:00
db4415d6c7
Add tests for conversations and messages
2025-08-13 15:14:12 +02:00
09739fdba4
Add tests for the Conversation object
2025-08-13 15:14:12 +02:00
13eeb8574d
Add the ask command
2025-08-13 15:14:12 +02:00
aa13853ae4
Add a third, "On deck" column in Collections
2025-08-12 17:58:12 -05:00
588f03e927
Remove insight experimental code
...
Also, downgrade LLM for commands to mini. It's much cheaper and I only upgraded because of the
interpretation complexities that the insight command introduced.
We are implementing a much better approach with Ask.
2025-08-11 13:40:56 +02:00
9bdc273c76
Prefer Account#slug to Account.script_name
...
Caching the script name in a class instance variable seemed like a bug
to me.
2025-08-09 14:27:41 -04:00
ece1751538
Merge pull request #805 from basecamp/bold-event-actions
...
Update system message to highlight verbs
2025-07-28 13:23:34 -05:00
07a470a8ac
Update tests
2025-07-28 13:12:53 -05:00
d90fac853f
Add missing test
2025-07-25 10:09:00 +02:00
711d9207ed
Little refactor + missing test
2025-07-25 10:04:07 +02:00
d5bedd812d
Regenerate test's fixtures to see if that fixes it for JZ
2025-07-25 06:27:12 +02:00
8e795f183d
Update system message to highlight verbs
2025-07-24 13:42:19 -05:00
c128b07203
Add test
2025-07-24 17:47:42 +02:00
7de45cc061
Remove vcr_record! and fix VCR fixtures due to different timestamps
2025-07-24 16:48:06 +02:00
b2ee79bbd0
Format
2025-07-24 16:48:06 +02:00
5ad2d09eae
Move the hack to fetch completed cards to the insight command logic
...
We need to rework this as part of the filters revamp. "indexed_by" being
a mix of filters keeps biting us.
2025-07-24 16:48:05 +02:00
fc26329daf
Restore default to open cards. Use special "all" value instead.
...
The change could have side effects (e.g: when running commands).
This also include further changes.
2025-07-24 16:48:04 +02:00
018c746d2a
Make the prompt smarter about the current context to make better calls
2025-07-24 16:48:03 +02:00
8bb7783215
Extract "prompt generation" logic to models for events, comments and cards
...
So that we can reuse in other scenarios
2025-07-24 16:48:03 +02:00
dd28e3d1e9
Replace special value with just not asuming that filters are about open cards by default
2025-07-24 16:48:03 +02:00
9d0887f6bd
Use a workaround with a special indexed_by filter to "query all"
2025-07-24 16:48:02 +02:00
83d743fe2a
Make the translator use the /insight command
2025-07-24 16:48:02 +02:00
1c6adf54a8
Restore semantic searches
2025-07-24 16:47:57 +02:00
6080c2aa9b
Refine when to filter by cards, make it more relaxes with the expressions it accepts
2025-07-24 16:47:53 +02:00
84f19183be
Add model test for read and unread
2025-07-23 17:28:15 -05:00
fc1ff7bf5e
Fix tests
2025-07-23 12:21:20 +02:00
fd0484176c
Format
2025-07-22 18:59:10 +02:00
70f19e54b5
Add assertion on HTML content
2025-07-22 18:47:48 +02:00
e87ed26f75
Add tests
2025-07-22 18:45:07 +02:00
Jorge Manrubia