jeuner/emergence-mini-dilles

3 commits 1 branch 0 tags 121 KiB

Author	SHA1	Message	Date
Jeuners	8a52e3dfa3	Fix WebSocket disconnect crash and missing 'personality' field Two bugs that crashed the engine in production: 1. world.nearby_agents() did not SELECT the 'personality' column, so _reaction_turn raised KeyError on every reactive trigger, killing the engine thread silently. Engine-Thread stieg aus ohne Log. Fix: select personality and json-parse it so callers get a real list, matching agents_mod.get(). 2. server.py ws() handler caught the generic 'Exception' from asyncio.to_thread(queue.get) and tried to send a ping back, but the WebSocket was already closed by the client. Starlette raised RuntimeError: Cannot call 'send' once a close message has been sent. Fix: drop the ping, just break the loop on any exception. Client disconnect now handled cleanly. Live-verified: 0 errors in log after 3 abrupt disconnects, engine continues producing ticks.	2026-06-15 02:04:49 +02:00
Jeuners	887c913bcd	Add Ollama LLM integration with rule-based fallback - engine/llm.py: Ollama /api/chat client with OpenAI-style tool schema - engine/reasoning.py: LLM path with 4-tier validation: 1. tool exists in registry 2. tool passes location-gating 3. args parse cleanly 4. otherwise fall back to rule-based engine - env vars: EMERGENCE_LLM_{URL,MODEL,TIMEOUT,ENABLED} - Default model: llama3.2:3b (best speed/quality tradeoff for tool use) - 11 new mock tests in tests/test_llm.py (no network) - smoke_test_llm.py: live smoke against real Ollama - README: 'LLM Integration' section with model table + setup Live-verified: 4/4 decisions via llama3.2:3b in 1-3s, character-consistent ('facilitate honest debate', 'work together', 'urgency and collaboration').	2026-06-15 01:30:58 +02:00
Jeuners	ddf9598518	Emergence-Mini: minimaler Klon von Emergence-World 4 Agenten, 14 Landmarks, 15 Tools, 240x240 Grid, SQLite-Persistenz. Round-Robin Turn-Manager mit Reactive Triggern, Town-Hall-Voting (70%-Threshold) mit Live-Constitution-Amendment. - engine/: db, world, agents, needs, tools, reasoning, governance, turn - web/: Canvas-basierte Live-View mit WebSocket-Stream - server.py: FastAPI + WebSocket auf 127.0.0.1:8080 - tests/: 70 Unit + Integration Tests (pytest), alle gruen - smoke_test.py: 50+ End-to-End-Checks - README: Quickstart, Architektur, Security, Tests, Lizenz - .gitignore: DB, Cache, Logs Basiert auf https://github.com/EmergenceAI/Emergence-World (Lizenz: CC-BY-NC-4.0, Research-only)	2026-06-15 01:07:38 +02:00

Author

SHA1

Message

Date

Jeuners

8a52e3dfa3

Fix WebSocket disconnect crash and missing 'personality' field

Two bugs that crashed the engine in production:

1. world.nearby_agents() did not SELECT the 'personality' column, so
   _reaction_turn raised KeyError on every reactive trigger, killing the
   engine thread silently. Engine-Thread stieg aus ohne Log.

   Fix: select personality and json-parse it so callers get a real list,
   matching agents_mod.get().

2. server.py ws() handler caught the generic 'Exception' from
   asyncio.to_thread(queue.get) and tried to send a ping back, but the
   WebSocket was already closed by the client. Starlette raised
   RuntimeError: Cannot call 'send' once a close message has been sent.

   Fix: drop the ping, just break the loop on any exception. Client
   disconnect now handled cleanly.

Live-verified: 0 errors in log after 3 abrupt disconnects, engine
continues producing ticks.

2026-06-15 02:04:49 +02:00

Jeuners

887c913bcd

Add Ollama LLM integration with rule-based fallback

- engine/llm.py: Ollama /api/chat client with OpenAI-style tool schema
- engine/reasoning.py: LLM path with 4-tier validation:
    1. tool exists in registry
    2. tool passes location-gating
    3. args parse cleanly
    4. otherwise fall back to rule-based engine
- env vars: EMERGENCE_LLM_{URL,MODEL,TIMEOUT,ENABLED}
- Default model: llama3.2:3b (best speed/quality tradeoff for tool use)
- 11 new mock tests in tests/test_llm.py (no network)
- smoke_test_llm.py: live smoke against real Ollama
- README: 'LLM Integration' section with model table + setup

Live-verified: 4/4 decisions via llama3.2:3b in 1-3s, character-consistent
('facilitate honest debate', 'work together', 'urgency and collaboration').

2026-06-15 01:30:58 +02:00

Jeuners

ddf9598518

Emergence-Mini: minimaler Klon von Emergence-World

4 Agenten, 14 Landmarks, 15 Tools, 240x240 Grid, SQLite-Persistenz.
Round-Robin Turn-Manager mit Reactive Triggern, Town-Hall-Voting
(70%-Threshold) mit Live-Constitution-Amendment.

- engine/: db, world, agents, needs, tools, reasoning, governance, turn
- web/: Canvas-basierte Live-View mit WebSocket-Stream
- server.py: FastAPI + WebSocket auf 127.0.0.1:8080
- tests/: 70 Unit + Integration Tests (pytest), alle gruen
- smoke_test.py: 50+ End-to-End-Checks
- README: Quickstart, Architektur, Security, Tests, Lizenz
- .gitignore: DB, Cache, Logs

Basiert auf https://github.com/EmergenceAI/Emergence-World
(Lizenz: CC-BY-NC-4.0, Research-only)

2026-06-15 01:07:38 +02:00