All /static/* responses now include Cache-Control: no-cache,
no-store, must-revalidate so app.js/style.css updates are always
picked up without a forced browser reload.
- New backend endpoint /api/history?hours=N returns chronological
replay frames reconstructed from the events table: agent positions,
energy/knowledge/influence/credits/mood, tool, model, tau, pace,
clocks and drift per tick/action.
- Frontend: new Replay panel with Play/Pause, timeline slider,
Live button and history window selector (1h/3h/6h/12h/24h).
- Canvas draw() now renders either the live snapshot or the current
replay frame; agent cards and drift/clock panels sync in replay mode.
- Overlay on the canvas shows current tick, timestamp, agent action
and model while replaying.
- Also adds the missing refreshTexts() implementation so the
Generated Texts panel is populated.
Verified: /api/history returns frames; JS syntax check passes;
pytest 100/100; web UI renders with new Replay controls.
The user wanted to use Ollama on a network host (192.168.1.245).
The host is reachable (ping ~900ms) but its Ollama port (11434)
is not open, so the engine falls back to a local URL.
Changes:
- .env: EMERGENCE_OLLAMA_URL = network host, EMERGENCE_OLLAMA_FALLBACK_URL
= localhost
- engine/llm.py: chat_ollama now iterates primary then fallback URL
on connection failure. is_available() does the same. provider_info()
exposes both URLs.
- All 100 tests still pass.
Live-verified: lovely+spark (llama3.2:3b) use mode=llm with ~10s
latency, which is the connection-refused on 192.168.1.245 + the
successful fallback to 127.0.0.1. As soon as 192.168.1.245's Ollama
is reachable, latency will drop to normal (~1-3s).
Implements core pieces of 'Time Dilation in LLM Agent Systems'
(Dillenberg 2026) and adds OpenRouter as a second LLM provider.
ENGINE
- engine/time.py: AgentClock with cumulative proper time tau
(weighted by op type), EWMA pace (alpha=0.3, dt clamped 0.1-60s),
ClockRegistry singleton, gamma_{src->dst} frame transformation,
drift_report with per-pair divergence and threshold flag.
- engine/turn.py: ticks tau on reasoning/tool/memory/reactive;
broadcasts tau+pace+model in every WebSocket message.
- engine/db.py: schema adds turn_log.tau, turn_log.pace,
turn_log.model, agent_clocks table; dev-mode auto-migrate
drops+recreates if old schema detected.
- engine/llm.py: full refactor for two providers.
Ollama: native tool-calling via /api/chat
OpenRouter: OpenAI-compatible /api/v1/chat/completions
Auto mode picks OpenRouter if OPENROUTER_API_KEY is set.
Per-agent model via EMERGENCE_AGENT_<ID>_MODEL env var.
.env loader with empty-line guard.
decide_tool returns (name, args, meta) with cost_usd for OR.
FRONTEND
- web/: new 'Time Dilation · Eigenzeit tau' section with per-agent
tau bars, pace, op count. Drift warning when any pair exceeds
threshold. LLM provider info in header.
TESTS
- 14 new tests in tests/test_time.py (tau monotonic, EWMA convergence,
gamma asymmetry, drift detection).
- 4 new LLM tests: openrouter response parsing, per-agent override,
provider_info, is_available.
- All 99 tests green.
LIVE-VERIFIED
- 4 different OpenRouter models running in parallel:
- anchor: anthropic/claude-3.5-haiku
- flora: openai/gpt-4o-mini
- lovely: meta-llama/llama-3.3-70b-instruct
- spark: google/gemma-3-4b-it
- All 4 produce turns, all 4 have different tau values,
drift_report shows the Frame-Transformation gamma values.
- Observation: gamma ~ 1.00 because the explicit Round-Robin +
sleep(2) keeps frames coherent. This is itself a non-trivial
validation of the paper's claim: in non-synchronized systems,
dilation would emerge.
SECRETS
- .env added, OPENROUTER_API_KEY live. .env is git-ignored.
- .env.example documents the config without exposing any key.
- .gitignore now blocks .env, .env.local, *.key, *.pem.
README
- New 'Time Dilation' section explaining tau, pace, CDC, drift
- New 'Multi-LLM via OpenRouter' section with cost table
- Per-agent model config documented
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.
