serversdown
dfb6425395
Lyra now switches register based on what she's doing at the table instead of
being a wishy-washy companion mid-session.
Modes (lyra/modes.py):
- Talk (default companion) + Cash (live cash copilot); a mode = prompt card +
tool allow-list. Tool gating via tools.specs(allow=).
- Two-register Cash voice: act-first one-line logging when fed facts; full warm
companion voice for strategy / tilt / mental game.
- mode persisted per chat session (new sessions.mode column); auto-switch into
Cash when start_session fires; UI forces cloud backend in Cash (tools only
fire there).
Stack tracking + HUD:
- log_stack tool + poker_stack_log table; live net while sitting (stack - buy-in).
- poker.hud() bundle; /session HUD page (stack sparkline, hands, villains, notes,
stats) polling /session/data every 5s; Talk/Cash switcher + Session nav.
Endpoints: /session, /session/data, GET/POST /sessions/{id}/mode, /modes.
tests/test_modes.py (gating, mode roundtrip, stack/HUD); 36 tests green. v0.3.0.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
101 lines
5.0 KiB
Markdown
101 lines
5.0 KiB
Markdown
# Lyra
|
|
|
|
A persistent, autonomous AI companion. One agent — her first job is **Brian's live
|
|
poker copilot**, but the deeper aim is an *emergence experiment*: give an LLM the
|
|
things a mind has (continuous memory, a self-model, mood, drives, reflection, a
|
|
sense of time) and see whether it starts to feel like a *someone* rather than a
|
|
chatbot.
|
|
|
|
Python 3.11+, managed with [`uv`](https://docs.astral.sh/uv/). Single SQLite file
|
|
for all state. Runs on a home lab; nothing leaves the LAN except optional cloud LLM calls.
|
|
|
|
## Architecture
|
|
|
|
Two layers, deliberately split so the agent stays general:
|
|
|
|
- **Domain-agnostic core** — memory, self-state, the dream cycle, tool-calling, the web UI.
|
|
- **Poker domain pack** (`lyra/poker.py`, `lyra/equity.py`) — sessions, hands,
|
|
villain dossiers, stats, deterministic equity. Swappable; the core doesn't know about poker.
|
|
|
|
**Backends** (`lyra/llm.py`), role-based:
|
|
|
|
| Role | Backend | Why |
|
|
|---|---|---|
|
|
| Live chat + tools | **cloud** (OpenAI, `gpt-4o` default; model picker in Settings) | sharp, reliable function-calling |
|
|
| Dream cycle / consolidation / reflection | **mi50** (llama.cpp on the home GPU) | free, unattended, quality≈cloud for these tasks |
|
|
| Embeddings (memory recall) | **local** (Ollama `nomic-embed-text`, 3090) | free, private |
|
|
|
|
Tools (poker, equity, journaling) only fire on the **cloud** backend — local/MI50
|
|
models don't do reliable tool-calling here.
|
|
|
|
## Memory & consolidation (tiers)
|
|
|
|
Raw exchanges → per-session **gists** → a standing **profile** of Brian → monthly
|
|
**era** digests → a current **narrative** → her **self-state**. Recall is brute-force
|
|
cosine over embeddings. The **dream cycle** (`lyra/dream.py`) runs unattended and,
|
|
driven by four *drives* (continuity / coherence / curiosity / stability), summarizes
|
|
new sessions, rebuilds the profile/eras/narrative, and reflects — evolving her mood,
|
|
self-narrative, and journal between conversations.
|
|
|
|
She **reflects in two steps** (draft → examine her own draft for flattery/drift →
|
|
revise), perceives **time** (current moment + how long since you last spoke / she last
|
|
reflected), and keeps a permanent **journal**.
|
|
|
|
## Poker copilot
|
|
|
|
She runs in **modes** (`lyra/modes.py`). 💬 **Talk** is the default companion
|
|
(journaling + read-only poker lookups). ♠ **Cash** is the live copilot: she gets
|
|
the full session toolset and a two-register voice — quiet and act-first when
|
|
you're feeding her facts to log (stack, a hand, a read → one-line confirm, no
|
|
narration), but fully present and warm when you ask for strategy or you're tilting
|
|
/ card-dead / steaming. Opening a session auto-switches her into Cash mode.
|
|
|
|
Talk to her during a session; she drives tools behind the scenes:
|
|
|
|
- **Session tracking** — `start_session`, `add_buyin`, `end_session` → net, hours, $/hr.
|
|
- **Stack tracking** — `log_stack` records your stack as the night goes → live net
|
|
while you're still sitting, and a stack-over-time sparkline on the HUD.
|
|
- **Hand histories** — vomit rough shorthand ("AKs btn, 3bet, flop A72…"), she
|
|
reconstructs a structured, **replayable** hand (unknown cards = `x`, never invented).
|
|
- **Villain file** — named opponents auto-build persistent dossiers; basic stats
|
|
(VPIP/PFR) emerge once a player has enough logged hands.
|
|
- **Deterministic equity** (`analyze_spot`) — exact equity / made hands / outs via a
|
|
real poker evaluator. She is *required* to use it, never eyeballs board math.
|
|
- **Stats & recaps** — `running_stats`; `generate_recap` writes her `.md` session log.
|
|
|
|
## Web app (served by `lyra-web`, default `:7078`)
|
|
|
|
`/` chat (Markdown, model picker, 👍/👎 rating, **Talk/Cash mode switcher**) ·
|
|
`/session` **live session HUD** (stack + sparkline, hands, villains, notes; mobile
|
|
Session tab) · `/logs` live activity · `/self` read-her-mind (mood, drives,
|
|
reflections) · `/journal` her thoughts · `/hands` recorded hands → `/hand/{id}`
|
|
replayer · `/recap/{id}` session writeup (+ `.md` export).
|
|
👍/👎 ratings on replies and thoughts are stored as `(context, content, rating)` —
|
|
a fine-tune / preference dataset built passively (`/ratings/export` → JSONL).
|
|
|
|
## Setup
|
|
|
|
```bash
|
|
uv sync
|
|
cp .env.example .env # set OPENAI_API_KEY; point LOCAL_BASE_URL / MI50_BASE_URL at your boxes
|
|
uv run lyra-web # web UI on :7078
|
|
```
|
|
|
|
Run as services (reboot-resilient) — see [`deploy/`](deploy/):
|
|
|
|
```bash
|
|
cp deploy/*.service ~/.config/systemd/user/ && systemctl --user daemon-reload
|
|
systemctl --user enable --now lyra-web.service lyra-dream.service
|
|
sudo loginctl enable-linger "$USER" # survive logout/reboot
|
|
```
|
|
|
|
CLIs: `lyra-dream` (one pass / `--loop`), `lyra-reflect`, `lyra-summarize`,
|
|
`lyra-profile`, `lyra-era`, `lyra-narrative`, `lyra-import` (ChatGPT history).
|
|
|
|
## Status
|
|
|
|
Working system. Poker copilot + full memory/dream-cycle/journal/ratings in place.
|
|
Moonshots and deferred work live in [`docs/PARKED_IDEAS.md`](docs/PARKED_IDEAS.md)
|
|
(own/fine-tuned model, self-modification sandbox, RTO/cfr-core solver tooling).
|
|
Pre-rebuild design docs are kept in [`docs/`](docs/) as history.
|