Twirre Meulenbelt
11b5345ae7
fix: do not await add_behavior anymore
...
ref: N25B-299
2025-11-25 11:33:35 +01:00
Twirre Meulenbelt
d513111ef3
Merge remote-tracking branch 'origin/dev' into feat/norms-and-goals-program
2025-11-25 11:29:27 +01:00
e5949a7273
fix: fix test race condition
...
ref: N25B-301
2025-11-25 11:21:25 +01:00
Twirre Meulenbelt
8ea8d4a8d4
feat: support history, norms and goals for LLM
...
ref: N25B-299
2025-11-24 17:58:44 +01:00
Twirre Meulenbelt
f2a67637c6
feat: add program manager
...
ref: N25B-299
2025-11-24 17:13:40 +01:00
ef00c03ec5
feat: pydantic models and inter-process messaging
...
Moved `InternalMessage` into schemas and created a `BeliefMessage`
model. Also added the ability for agents to communicate via ZMQ to
agents on another process.
ref: N25B-316
2025-11-24 14:03:34 +01:00
4d076eac48
perf: improved speed of BDI
...
By efficiently checking when the next work has to be done, we can
increase performance not having to "busy loop". Time from transcription
-> message to LLM agent is now down to sub 1 millisecond.
ref: N25B-316
2025-11-22 19:53:19 +01:00
1f9926fe00
chore: apply suggestion
...
Changed `add_background_task` to `add_behavior` and added extra docs.
2025-11-22 10:28:52 +01:00
5fb923e20d
refactor: testing
...
Redid testing structure, added tests and changed some tests.
ref: N25B-301
2025-11-21 17:03:40 +01:00
98d087417f
docs: document how to use agents
...
ref: N25B-300
2025-11-21 13:28:37 +01:00
1c510c661e
feat: more robust belief management
...
ref: N25B-316
2025-11-21 12:08:53 +01:00
610c4b526d
fix: incorrect receiver and incorrect belief
...
ref: N25B-300
2025-11-20 15:04:40 +01:00
bb3f81d2e8
refactor: remove SPADE dependencies
...
Did not look at tests yet, this is a very non-final commit.
ref: N25B-300
2025-11-20 14:35:28 +01:00
Twirre Meulenbelt
efe49c219c
feat: apply new agent naming standards
...
Expanding abbreviations to remove ambiguity, simplifying agent names to reduce repetition.
ref: N25B-257
2025-11-19 15:56:09 +01:00
Björn Otgaar
0e45383027
refactor: rename all agents and improve structure pt1
...
ref: N25B-257
2025-11-12 11:04:49 +01:00
Luijkx,S.O.H. (Storm)
1c756474f2
test: added tests for text_belief_extractor
2025-11-06 12:57:09 +00:00
d9fef22090
Merge branch 'dev' into refactor/logging
2025-11-05 15:09:14 +01:00
c7bdb5aeda
chore: run linter and formatter
2025-11-04 21:00:12 +01:00
270df83fab
Merge branch 'dev' into refactor/logging
2025-11-04 20:54:03 +01:00
a98018ddda
refactor: agents inherit logger from BaseAgent
...
Created a class `BaseAgent`, from which all agents inherit. They get
assigned a logger with a nice name (something like
`control_backend.agents.AgentName`).
The BDI core takes care of its own logger, as bdi is still a module.
ref: N25B-241
2025-11-04 20:48:55 +01:00
Twirre Meulenbelt
8e4d8f9d1e
Merge remote-tracking branch 'origin/dev' into demo
...
# Conflicts:
# src/control_backend/agents/bdi/behaviours/receive_llm_resp_behaviour.py
# src/control_backend/agents/llm/llm.py
# src/control_backend/agents/ri_command_agent.py
# src/control_backend/agents/transcription/speech_recognizer.py
2025-11-02 21:07:50 +01:00
48c9746417
style: apply ruff check and format
...
Made sure all ruff checks pass and formatted all files.
ref: N25B-224
2025-11-02 19:45:01 +01:00
d43cb9394a
refactor: improve logging and module structure
...
Changed some folders to not be modules and organized some `__init__.py`
files.
ref: N25B-223
2025-11-02 11:32:21 +01:00
Twirre Meulenbelt
86938f79c0
feat: end to end connected for demo
...
Includes the Transcription agent. Involved updating the RI agent to receive messages from other agents, sending speech commands to the RI agent, and some performance optimizations.
ref: N25B-216
2025-10-30 10:42:25 +01:00
Twirre Meulenbelt
2fae230977
feat: incomplete working pipeline
...
ref: all
2025-10-29 16:43:23 +01:00
Twirre Meulenbelt
d05276b081
Merge remote-tracking branch 'origin/feat/belief-from-text' into feat/belief-from-text
...
# Conflicts:
# src/control_backend/agents/bdi/test_agent.py
# src/control_backend/main.py
2025-10-29 15:29:00 +01:00
Twirre Meulenbelt
889ec1db51
chore: fix merge conflicts and small items
...
ref: N25B-208
2025-10-29 15:28:15 +01:00
Twirre Meulenbelt
7744852e88
Merge remote-tracking branch 'origin/dev' into feat/belief-from-text
...
# Conflicts:
# src/control_backend/main.py
2025-10-29 15:12:18 +01:00
Storm
041edd4c1e
feat: implement demo version for demo
...
ref: N25B-208
2025-10-29 14:53:14 +01:00
Twirre Meulenbelt
7779d3a41c
style: another tiny style fixes
2025-10-29 13:58:10 +01:00
Twirre Meulenbelt
5f2fd11a33
style: tiny style fixes
2025-10-29 13:55:18 +01:00
JobvAlewijk
91df16ebbc
build: merge bdi improvements
...
ref: N25B-197
2025-10-29 13:44:57 +01:00
2da02946ed
chore: remove manual testing function
...
ref: N25B-197
2025-10-29 13:21:55 +01:00
JobvAlewijk
c7a2effa78
style: linted everything
...
ref: N25B-207
2025-10-29 13:01:00 +01:00
JobvAlewijk
af789bd459
feat: norms and goals to llm
...
base goals and norms can be defined in llm_instructions.py
cleaned the code
ref: N25B-215
2025-10-29 12:45:13 +01:00
3b7aeafe5e
fix: correct belief management
...
There was an issue in how we treated beliefs, specifically with multiple beliefs of the same name but different arguments. This is fixed with this commit.
Also implemented correct updating of the "responded" belief, when the user_said belief is updated (when we get a new user message, we state that we have not yet responded to that message)
ref: N25B-197
2025-10-29 11:23:56 +01:00
JobvAlewijk
6846a18b3b
build: merge
...
merge with riAgent
ref: N25B-208
2025-10-28 15:03:47 +01:00
JobvAlewijk
f44413ca1e
style: typo
...
ref: N25B-207
2025-10-28 13:47:48 +01:00
JobvAlewijk
f8d08ac7ca
chore: moved behavoir
...
moved recieve llm behavoir into a the behavoir folder
ref: N25B-207
2025-10-28 13:44:28 +01:00
Storm
a43e5111db
fix: quick first fix in preparation of merge
...
ref: N25B-208
2025-10-28 13:28:42 +01:00
JobvAlewijk
281bc57b6e
chore: cleanup
...
made bdi match incoming messages
changed llm from test agent to llm agent in config.
ref: N25B-207
2025-10-28 12:03:30 +01:00
JobvAlewijk
17056da832
chore: cleanup
...
made llm get url from settings
cleanup uneceserry fstring
ref: N25B-207
2025-10-28 11:07:28 +01:00
4859c3ac04
style: fix style
2025-10-27 15:10:31 +01:00
JobvAlewijk
c5b71450fc
feat: LLM agent
...
body: added the llmAgent class and made it run at the start.
modified the bdi_core to send a test message and recieve an awnser from LLM agent
Added a connection to a local llm via lmstudio.
Tests are Tba.
ref: N25B-207
2025-10-27 14:21:18 +01:00
Storm
bece44bf7d
feat: implemented basic belief-from-text extractor
...
The communication with other agents has been tested with mock data as the other agents (transcriber and belief collector) are not yet implemented.
ref: N25B-208
2025-10-24 17:25:25 +02:00
e057cf3003
test: add unit tests to BeliefCollector
...
ref: N25B-197
2025-10-22 14:51:20 +02:00
Storm
4cf1e5aaf7
docs: added docstrings to bdi_core and BeliefSetter behaviour
...
ref: N25B-197
2025-10-21 12:33:47 +02:00
31882f8d63
feat: add BDI core agent
...
Main BDI brain structure implemented. Still some TODOs left, and very
basic implementation (only one belief "user_said(Message)" and every
message is sent straight to a function which is responsible for getting
an LLM response.
ref: N25B-197
2025-10-18 17:50:17 +02:00
