8b2ecfcec2
Clarify how to work with VCR
2025-07-25 14:56:03 +02:00
539f83eaee
Add VCR fixtures for test
2025-07-25 14:51:28 +02:00
46ba6035c5
Merge pull request #813 from basecamp/event-summary-tweaks
...
Event summary tweaks
2025-07-25 07:30:51 -05:00
ad7d7bbe89
Revert prompt tweaks, they cause test failures
2025-07-25 07:30:02 -05:00
919741da61
Merge branch 'main' into event-summary-tweaks
...
* main:
Make output scrollable
Dialog target needs to be in the DOM on connect
Remove debug
Update badge counts clientside because we can't count on pushes to remove badges
2025-07-25 07:24:15 -05:00
43aa34174c
Merge pull request #808 from basecamp/update-badge-counts
...
Update badge counts clientside
2025-07-25 07:23:35 -05:00
af99a466c0
Merge branch 'main' into update-badge-counts
...
* main:
Skip failing activity summary test
Add missing test
Little refactor + missing test
Add comment
Regenerate test's fixtures to see if that fixes it for JZ
Make output scrollable
Dialog target needs to be in the DOM on connect
2025-07-25 07:22:54 -05:00
7ea24c628a
Merge pull request #809 from basecamp/fix-dialog-controller-error
...
Dialog target needs to be in the DOM on connect
2025-07-25 07:22:41 -05:00
85aa0465ac
Merge branch 'main' into fix-dialog-controller-error
...
* main:
Skip failing activity summary test
Add missing test
Little refactor + missing test
Add comment
Regenerate test's fixtures to see if that fixes it for JZ
Make output scrollable
2025-07-25 07:21:57 -05:00
f8256e62cd
Merge pull request #812 from basecamp/scrollable-command-output
...
Make output scrollable
2025-07-25 07:21:42 -05:00
4e935e4800
Merge branch 'main' into scrollable-command-output
...
* main:
Skip failing activity summary test
Add missing test
Little refactor + missing test
Add comment
Regenerate test's fixtures to see if that fixes it for JZ
2025-07-25 07:20:52 -05:00
9707f19b87
Merge branch 'main' into event-summary-tweaks
...
* main:
Skip failing activity summary test
Add missing test
Little refactor + missing test
Add comment
Regenerate test's fixtures to see if that fixes it for JZ
2025-07-25 07:17:15 -05:00
2ca156b2e4
Shorter word count
2025-07-25 07:17:08 -05:00
02bdfc780c
Skip failing activity summary test
2025-07-25 11:45:22 +01:00
d90fac853f
Add missing test
2025-07-25 10:09:00 +02:00
33c3d419d4
Merge pull request #814 from basecamp/optimize-summarizable
...
Little refactor + missing test
2025-07-25 10:06:21 +02:00
711d9207ed
Little refactor + missing test
2025-07-25 10:04:07 +02:00
fbf003d7ec
Add comment
2025-07-25 06:32:40 +02:00
d5bedd812d
Regenerate test's fixtures to see if that fixes it for JZ
2025-07-25 06:27:12 +02:00
6186c0fd63
Tweak prompt
2025-07-24 17:45:54 -05:00
b9e1bf2447
Adjust styles so summaries feel more connected to the day they describe
2025-07-24 17:40:44 -05:00
f15fac94d9
Make output scrollable
2025-07-24 17:09:56 -05:00
d3a01cf9bb
Dialog target needs to be in the DOM on connect
...
Moves it out of the turbo frame so it's available even when empty
2025-07-24 14:58:52 -05:00
1d6a60cd17
Remove debug
2025-07-24 14:49:53 -05:00
8c9d7d9d91
Update badge counts clientside because we can't count on pushes to remove badges
2025-07-24 14:43:51 -05:00
ef7403c600
Merge pull request #803 from basecamp/ai-improvements
...
Semantic searches + Get Insight about cards with gpt-4o
2025-07-24 17:48:51 +02:00
c128b07203
Add test
2025-07-24 17:47:42 +02:00
18597aabad
Make sure we sort closed cards by recency by default
...
So that the filter used for the insight context fetches the most recent cards when using indexed_by closed
2025-07-24 17:46:40 +02:00
95e065a0c4
Reduce the injected load a bit
2025-07-24 17:33:40 +02:00
523f3f0acb
Set some hard limits on the prompt lenghts we inject
2025-07-24 17:32:50 +02:00
0429dc28f3
Fix for injecting the current context
...
This is a workaround to make the prototype work. We create a context on the fly to execute AI-derived
commands. When those require listing cards, we ended up losing the notion of "being on a perma screen".
2025-07-24 17:27:32 +02:00
c2120fe83d
Remove results when pressing up
2025-07-24 16:58:36 +02:00
b7200509f4
Bundle after merge issues
2025-07-24 16:49:22 +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
e61ee25b47
Suite passing
2025-07-24 16:48:05 +02:00
4574c0d85c
Include stage information about the card
2025-07-24 16:48:05 +02:00
ba97ec05d6
Remove transaction as the AI commands can hold the transaction for too long
2025-07-24 16:48:05 +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
7a8bf4895c
More prompt fixes
2025-07-24 16:48:01 +02:00
4d3e7bf0af
Fix: llm model
2025-07-24 16:48:01 +02:00
1c6adf54a8
Restore semantic searches
2025-07-24 16:47:57 +02:00
df9c1e0674
Make sure we pass expressions as a single term
...
Multiple terms refine the search on each term and works way
worse with the semantic approach
2025-07-24 16:47:54 +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
Jorge Manrubia