Commit Graph

18 Commits

Author SHA1 Message Date
Ettore Di Giacinto
c23e655f44 feat(agent): shared state, allow to track conversations globally (#148)
* feat(agent): shared state, allow to track conversations globally

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Cleanup

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* track conversations initiated by the bot

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-05-11 22:23:01 +02:00
Ettore Di Giacinto
c4618896cf chore: default to gemma-3-12b-it-qat (#60)
* chore: default to gemma-3-12b-it-qat

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix: simplify tests to run faster

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-04-22 11:44:42 +02:00
Richard Palethorpe
77189b6114 fix(test): Encourage LLM to plan multiple searches (#36)
Signed-off-by: Richard Palethorpe <io@richiejp.com>
2025-04-14 17:35:19 +02:00
mudler
601dba3fc4 chore(tests): try to be more expressive
Signed-off-by: mudler <mudler@localai.io>
2025-04-14 16:08:54 +02:00
mudler
00ab476a77 chore(tests): try to be more extensive in timeouts
Signed-off-by: mudler <mudler@localai.io>
2025-04-14 12:37:31 +02:00
Ettore Di Giacinto
60c249f19a chore: cleanup, identify goal from conversation when evaluting achievement (#29)
* chore: cleanup, identify goal from conversation when evaluting achievement

Signed-off-by: mudler <mudler@localai.io>

* change base cpu model

Signed-off-by: mudler <mudler@localai.io>

* this is not necessary anymore

Signed-off-by: mudler <mudler@localai.io>

* use 12b

Signed-off-by: mudler <mudler@localai.io>

* use openthinker, it's smaller

* chore(tests): set timeout

Signed-off-by: mudler <mudler@localai.io>

* Enable reasoning in some of the tests

Signed-off-by: mudler <mudler@localai.io>

* docker compose unification, small changes

Signed-off-by: mudler <mudler@localai.io>

* Simplify

Signed-off-by: mudler <mudler@localai.io>

* Back at arcee-agent as default

Signed-off-by: mudler <mudler@localai.io>

* Better error handling during planning

Signed-off-by: mudler <mudler@localai.io>

* Ci: do not run jobs for every branch

Signed-off-by: mudler <mudler@localai.io>

---------

Signed-off-by: mudler <mudler@localai.io>
2025-04-12 21:01:01 +02:00
Ettore Di Giacinto
c2ec333777 Enlarge timeout window 2025-04-09 21:59:18 +02:00
mudler
0eb68b6c20 feat: add loop detection
Signed-off-by: mudler <mudler@localai.io>
2025-04-09 19:13:41 +02:00
Ettore Di Giacinto
5111738b3b Wait for API to be ready 2025-04-08 22:45:15 +02:00
Ettore Di Giacinto
e7111c6554 Rename 2025-04-08 22:18:32 +02:00
Ettore Di Giacinto
c940141e61 fix: make new_conversation to work (#112)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-03-29 00:21:00 +01:00
mudler
75a8d63e83 Finish moving types 2025-03-23 21:57:09 +01:00
Ettore Di Giacinto
abb3ffc109 feat: track plan action when is being executed, also tests (#72)
* feat: track plan action when is being executed, also tests

* Update core/agent/agent_test.go

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update core/agent/actions.go

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-03-21 16:32:24 +01:00
Ettore Di Giacinto
33483ab4b9 feat(planning): enable agent planning (#68)
* feat(planning): Allow the agent to plan subtasks

Signed-off-by: mudler <mudler@localai.io>

* feat(planning): enable planning toggle in the webui

Signed-off-by: mudler <mudler@localai.io>

* feat(planning): take in consideration the overall goal

Signed-off-by: mudler <mudler@localai.io>

* Update core/action/plan.go

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Signed-off-by: mudler <mudler@localai.io>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-03-21 12:28:11 +01:00
Ettore Di Giacinto
e32a569796 try to fixup tests, enable e2e (#53)
* try to fixup tests, enable e2e

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Generate JSON character data with tools

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Rework generation of character

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Simplify text

Signed-off-by: mudler <mudler@localai.io>

* Relax some test constraints

Signed-off-by: mudler <mudler@localai.io>

* Fixups

* Properly fit schema generation

* Swap default model

* ci fixups

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: mudler <mudler@localai.io>
2025-03-18 23:28:02 +01:00
mudler
5b4f618ca3 Standardize action results 2025-03-01 17:27:07 +01:00
Ettore Di Giacinto
b66e698b5e Rename package 2025-02-26 22:51:29 +01:00
Ettore Di Giacinto
296734ba3b reordering 2025-02-25 22:18:08 +01:00