8e73ad6f4e
feat(prompts): adding better prompts & restoring tool_stop
...
Mistral's models seem to do something really strange if you allow for
`tool_choice` to be anything but `any`. They start putting the tool call
inside the `content` instead of an actual tool call. This means that I
need this `stop` mechanism using a tool call instead because I cannot
trust the model to do it by itself.
I quite like this model though, it's cheap, it's fast and it's open
source. And all the answers are pretty good!
2025-04-17 15:24:21 +01:00
4b0ef8b17f
feat(orchestrator): removing the end tool call
...
fix
2025-04-17 13:00:39 +01:00
57c760e7f0
chore: removing unnecessary logging
2025-04-17 13:00:24 +01:00
f5fdaff7c1
wip(orchestrator): improving orchestrator system prompt and tool description
2025-04-17 12:52:54 +01:00
8fff043849
feat(event-location): communicating using tool calls correctly
2025-04-17 11:15:02 +01:00
d1fd2aeaf1
fix(logger): nil pointer error + log debug level clean
2025-04-17 11:07:37 +01:00
1e5028177f
refactor(agents): not returning an error on factory method
2025-04-17 11:02:11 +01:00
c4569e925b
refactor(agents): encapsulating prompt and calls inside factory method
2025-04-17 10:58:19 +01:00
8fed2f9b9a
fix: using correct eventAgent instead of orchestrator bug + better logging
2025-04-17 10:48:30 +01:00
1651926c4d
refactor(agents): no need to wrap them in another struct
2025-04-17 10:36:11 +01:00
fa127c2331
feat: event agent calling location agent about location ID
...
This is pretty nice. We can now have agents spawn other agents and
actually get super cool functionality from it.
The pattern might be a little fragile.
2025-04-16 14:43:07 +01:00
7be669e49e
wip(agents): allowing event agent to call location agent
2025-04-15 16:44:00 +01:00
7b6bdf2c7b
feat: Adding text message to describe an action3
2025-04-15 16:43:27 +01:00
7b40959125
fix
2025-04-14 20:08:07 +01:00
63201280bb
rollback: not using link functions as they are very problematic
2025-04-14 10:59:08 +01:00
64f8aa032e
ffix
2025-04-14 10:40:02 +01:00
4ba41258e0
prompt
2025-04-14 10:38:25 +01:00
2e092e5fe4
more prompt
2025-04-14 10:36:21 +01:00
60273c5782
fix more prompt
2025-04-14 10:33:56 +01:00
8e7ee204ce
fix: prompts
2025-04-14 10:28:31 +01:00
fca4a6445c
chore: removing old agent that was messy and too coupled
...
chore
2025-04-13 16:30:20 +01:00
17cc12f0c9
feat(event): seperate event agent
2025-04-13 16:30:20 +01:00
b57968b938
feat(location): agent to create locations
2025-04-13 16:30:20 +01:00
0fcdd73a47
feat(sse): very rough events. Not used in the client yet
...
feat(sse): very rough events. Not used in the client yet
2025-04-13 14:27:59 +01:00
1560d1504e
fix: tests
2025-04-12 14:43:01 +01:00
ae9ac1fe4f
refactor(agent): main agent loop extracted away
...
Still not super sure how to represent these agents in code.
It doesn't make the most amount of sense to keep them in structs. A
curried function is more like it, with system prompt and tooling.
Maybe that's what I'll end up doing.
2025-04-12 14:39:16 +01:00
ca8583575e
fix(event)
2025-04-12 14:15:07 +01:00
02490c6c84
fix(orchestrator): better describing the note taking agent
2025-04-12 07:53:43 +01:00
36e776789e
fix(notes): improving note taking capabilities
2025-04-12 07:48:42 +01:00
70d4411270
feat(contact-agent): linking to existing instead of creating new ones
2025-04-12 07:29:29 +01:00
6b181aac9f
fix: removing extra log line
2025-04-12 07:22:35 +01:00
324aac438b
feat(log): pretty logging agent responses and tool calls
2025-04-12 07:16:30 +01:00
b0f4a45c40
feat(contact-agent): working contact agent
...
Built this in under 20 minutes. Getting some really good agents
2025-04-11 21:12:06 +01:00
1a9b707533
feat(orchestrator): async processing and ending the loop3
2025-04-09 15:23:51 +01:00
c35951063a
fix(tool-calls): ToolLoop
2025-04-09 15:15:31 +01:00
f294f9cdc0
fix(tools): testing and processing
...
fix
2025-04-09 13:56:30 +01:00
88fda32125
fix(types): agent processing stuff
2025-04-09 12:12:09 +01:00
5502fc6b19
feat(chat): more simplified chat messages and tool handling
2025-04-09 12:04:44 +01:00
28ee32e2ff
fixup(chat): better way to organize agent messages and tool calls
2025-04-06 20:24:40 +01:00
f5f4008034
fix(tools): dont error if AI invested a tool
2025-04-05 15:04:09 +01:00
d474b1700a
refactor(tools): removing pointer map
...
This is not needed
2025-04-05 14:59:50 +01:00
d78f34a7aa
feat(tools): return error to agent if any happened
2025-04-05 14:58:38 +01:00
1cafc31e0a
test(tools): more robust multiple tool call handling
2025-04-05 14:52:31 +01:00
a1ce96d2e3
test(tools): starting test suite for tools
2025-04-05 14:35:54 +01:00
03e7803467
feat(orchestrator): calling needed agents when it needs to
2025-04-05 11:01:43 +01:00
286a9a8472
fix(tool): raw text not scaling so well ey?
2025-04-04 22:50:19 +01:00
aa153de185
refactor(agents): working e2e now
...
I guess some repeated code doesnt hurt anyone, if it keeps things
simpler. Trying to be fancy with the interfaces didn't work so well.
2025-04-04 22:40:45 +01:00
cd27f1105a
refactor(tool-calls): to be handled more generally
2025-04-04 22:17:58 +01:00
71d4581110
refactor(ai-client): moving tool handling and client into seperate folders
2025-04-04 22:03:46 +01:00
8a165c2042
wip(orchestrator): basic scaffolding for the agent
2025-04-04 20:40:31 +01:00
