serversdown/project-lyra
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

refactor(P1): extract the turn pipeline into lyra/mind.py (behavior-preserving)

Browse Source 
First step of the cognition control plane (docs/COGNITION.md). The chat turn is now
an explicit society of parts over a shared TurnContext blackboard:
  perceive (stub) -> route (session mode) -> compose (tiered prompt) -> deliberate.

- lyra/mind.py (new): TurnContext + the pipeline + assemble(); moved build_messages
  and the deliberation helpers here (the assembly belongs in the control plane).
- lyra/chat.py: slimmed to "speak + persist" — calls mind.assemble(), runs the
  tool/generation loop, persists. No behavior change (same prompt, same output).
- tests: point test_time/test_chat at mind; add an assemble() structure test;
  make test_chat/test_tools hermetic (CHAT_DELIBERATE off so respond() doesn't make
  a real LLM call). Suite 86 green in ~5s, ruff clean, no import cycle.

This is the frame; perceive/route/learn get filled in next phases — each opt-in.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
serversdown
2026-06-24 05:19:39 +00:00
parent f1f15972ac
commit 904eda3388
5 changed files with 345 additions and 299 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lyra/chat.py
+42 -279
View File
@@ -1,22 +1,16 @@
"""The chat turn loop: persona + tiered memory + recent context -> reply.
"""The chat turn: assemble the prompt (lyra.mind) then speak + persist.
Context is assembled in tiers (oldest/most-compacted first):
1. persona
2. long-term gist — relevant *summaries* of other sessions
3. sharp details — a few raw cross-session exchanges (so specifics survive)
4. recent raw turns of the current session (full fidelity)
5. the new user message
After replying, the session is compacted if enough new turns have accumulated.
`mind.assemble()` runs the society of parts (perceive → route → compose →
deliberate) and hands back a ready message list + the active mode; `chat` runs the
tool/generation loop (the "speak" part) and persists the exchange. Keeping speak
here (not in mind) is deliberate — it's tangled with streaming and tool dispatch.
"""
from __future__ import annotations
from lyra import clock, config, llm, logbus, memory, modes, persona, self_state, summary, thoughts
from lyra import config, llm, logbus, memory, mind, modes, summary
from lyra import tools as toolkit
from lyra.llm import Backend, Message
from lyra.llm import Backend
RECALL_K = 3 # raw cross-session "sharp detail" hits
RECENT_N = 10 # raw turns of the current session
SUMMARY_K = 3 # other-session gists
MAX_TOOL_ROUNDS = 5 # cap tool-call iterations per turn
# Backends that support function-calling. The MI50's llama.cpp server only does
# tools when launched with --jinja; until it is, keep tools to cloud so MI50 chat
@@ -24,256 +18,40 @@ MAX_TOOL_ROUNDS = 5 # cap tool-call iterations per turn
TOOL_BACKENDS = {"cloud"}
def _mode_state_note(mode: modes.Mode | None) -> str | None:
"""Dynamic, per-turn state for the active mode. Currently: surface Alligator
Blood while it's engaged on the live session, so she stays in that register."""
if not mode or mode.key != modes.CASH.key:
return None
from lyra import poker # local import: keep the core/domain coupling at call time
if poker.alligator_active():
return (
"🐊 ALLIGATOR BLOOD is ON for this session. Coach Brian in that register: "
"hang around, refuse to die, don't force miracles, make opponents beat him "
"correctly. Tough, patient, steady — no heroics, no spew, no quitting."
)
return None
def _maybe_switch_mode(session_id: str, tool_name: str) -> None:
"""Keep the chat framing aligned with the live data: opening a poker session
auto-flips this chat into Cash mode (so the next turn gets the cash card + the
full live toolset). Manual UI switching still overrides anytime."""
if tool_name == "start_session":
memory.set_session_mode(session_id, modes.CASH.key)
logbus.log("info", "mode auto-switch", session=session_id, mode=modes.CASH.key)
def _summary_note(summaries: list[memory.Summary]) -> Message:
lines = [f"- ({(s.session_started_at or s.created_at)[:10]}) {s.content}" for s in summaries]
body = "Gist of earlier sessions (compacted — ask if you need specifics):\n" + "\n".join(lines)
return {"role": "system", "content": body}
def _detail_note(exchanges: list[memory.Exchange]) -> Message:
lines = [f"- ({ex.created_at[:10]}, {ex.role}) {ex.content}" for ex in exchanges]
body = "Specific things you recall from past conversations:\n" + "\n".join(lines)
return {"role": "system", "content": body}
def _inner_life_note() -> Message | None:
"""One coherent window onto what she's been doing on her own since last time —
the threads she's turning over plus the things she's written for herself. Sits
with her self-state so chat reads as a continuous mind, not a fresh boot. The
persona tells her to weave this in naturally when it fits."""
parts: list[str] = []
threads = thoughts.context_note() # active threads, with their latest thought
if threads:
parts.append(threads)
wrote = memory.list_journal(limit=3, kinds=("journal", "note"))
if wrote:
lines = "\n".join(f"- ({w['created_at'][:10]}) {w['content']}" for w in reversed(wrote))
parts.append(
"Things you've written in your journal lately (yours — you can refer back "
"to them if they're relevant):\n" + lines
)
if not parts:
return None
return {"role": "system", "content": "\n\n".join(parts)}
def _now_note() -> Message:
"""Current wall-clock time + how long since Brian last said anything.
Stated as plain fact — she has no clock otherwise, so without this 'now' and
the gap since the last turn are invisible to her.
"""
line = f"The current date and time is {clock.stamp()}."
gap = clock.humanize_gap(memory.last_exchange_at())
line += (
f" It has been {gap} since Brian last spoke with you."
if gap else " This is the first thing Brian has ever said to you."
)
return {"role": "system", "content": line}
def _render(messages: list[Message]) -> str:
"""Human-readable dump of the exact prompt, for the live-log inspector."""
return "\n\n".join(f"[{m['role']}]\n{m['content']}" for m in messages)
# Trivial acknowledgements that don't warrant a private thinking pass.
_TRIVIAL = {"ok", "okay", "k", "kk", "lol", "haha", "thanks", "thank you", "ty", "yeah",
"yep", "yes", "no", "nope", "nice", "cool", "sure", "right", "true", "gotcha", "👍"}
def _should_deliberate(user_msg: str) -> bool:
m = user_msg.strip().lower().rstrip("!.?")
return len(m) >= 12 and m not in _TRIVIAL
_DELIBERATE_SYS = (
"Before you answer Brian, think privately — he will NOT see this. What do you ACTUALLY "
"think about what he just said? Your real take, the specific substance worth giving, any "
"genuine opinion, disagreement, or doubt. Draw on your own current thoughts/threads and "
"what you actually know if they're relevant. Be concrete; skip pleasantries and generic "
"enthusiasm. 2-5 sentences of honest thinking — no lists, no answer yet, just the thinking."
)
def _deliberate(messages: list[Message], backend: Backend, model: str | None) -> str:
"""One private 'what do I actually think' pass before replying. Returns her thinking
(empty on any failure — chat must never break because deliberation hiccuped)."""
try:
out = llm.complete(messages + [{"role": "system", "content": _DELIBERATE_SYS}],
backend=backend, model=model)
return (out or "").strip()
except Exception as exc:
logbus.log("error", "deliberation failed", error=str(exc)[:160])
return ""
def _answer_from(thinking: str) -> Message:
"""The system note that turns private thinking into a grounded, in-voice reply — placed
last (most influential) to beat gpt-4o's default-assistant boilerplate."""
return {"role": "system", "content": (
"Your private thinking just now (Brian can't see it):\n" + thinking +
"\n\nNow reply to Brian FROM that thinking, in your own voice — warm, direct, "
"specific, opinionated. Give the actual substance, not a survey of options. Do NOT "
"default to a numbered list or a how-to outline unless he explicitly asked for steps. "
"No 'would you like to…' / 'let me know' closer — make your point and stop."
)}
def _deliberation_note(session_id: str, user_msg: str, backend: Backend,
model: str | None, messages: list[Message]) -> Message | None:
"""Run the private thinking pass if warranted; return the answer-from-thinking note."""
if not config.load().chat_deliberate or not _should_deliberate(user_msg):
return None
thinking = _deliberate(messages, backend, model)
if not thinking:
return None
logbus.log("info", "deliberated", session=session_id, chars=len(thinking), detail=thinking)
return _answer_from(thinking)
def build_messages(session_id: str, user_msg: str,
mode: modes.Mode | None = None) -> list[Message]:
"""Assemble the full, tiered message list for one turn."""
messages: list[Message] = [{"role": "system", "content": persona.system_prompt()}]
# Autonomy Core: Lyra's own evolving interiority (mood, self-narrative). Comes
# right after the persona — her sense of self before her model of the world.
messages.append({"role": "system", "content": self_state.render_for_context(self_state.load())})
# Her ongoing inner life — the threads she's turning over and what she's written
# for herself — so she's continuous across conversations and can pick up where she
# left off, not only when a thought crosses the surface bar below. Rides with the
# self; the persona tells her to bring it into conversation naturally when it fits.
inner = _inner_life_note()
if inner:
messages.append(inner)
# Mode card: how to behave *right now* (e.g. live-cash copilot). High priority —
# it sits just after her sense of self, before her model of the world. Talk mode
# has no card (the persona's default voice is the Talk register).
if mode and mode.card:
messages.append({"role": "system", "content": mode.card})
# Live ritual state (e.g. Alligator Blood ON) — dynamic, so it rides alongside
# the static card and keeps her in-register for the whole stretch, not just the
# turn she flipped it.
state_note = _mode_state_note(mode)
if state_note:
messages.append({"role": "system", "content": state_note})
# When she is: current time + the gap since Brian last spoke (she has no clock).
messages.append(_now_note())
# Thought loop: if Brian's been away and one of her own threads has built past
# the surface bar, let her lead with it (once). This is her #6 — bringing what
# she thought about while alone *to* him. Runs before the world-model tiers so
# it's framed as her interiority, like the self-state.
surfaced = thoughts.maybe_surface(memory.last_exchange_at())
if surfaced:
messages.append({"role": "system", "content": surfaced})
# Semantic memory: the distilled profile (who Brian is) — answers identity
# questions that raw recall can't. Always in context when it exists.
profile = memory.get_profile()
if profile:
messages.append(
{"role": "system", "content": "What you know about Brian:\n" + profile}
)
# Time-aware memory: the current narrative (recent arc, trends, callbacks).
narrative = memory.get_narrative()
if narrative:
messages.append(
{"role": "system", "content": "What's going on with Brian lately:\n" + narrative}
)
recent = memory.recent(session_id, n=RECENT_N)
recent_ids = {ex.id for ex in recent}
# Tier 1: compacted gists of *other* sessions (long-term, general idea).
summaries = memory.recall_summaries(user_msg, k=SUMMARY_K, exclude_session=session_id)
if summaries:
messages.append(_summary_note(summaries))
# Tier 2: a few sharp raw details from other sessions (so specifics survive
# compaction). Skip the current session (its raw turns are in `recent`).
recalled = [
ex for ex in memory.recall(user_msg, k=RECALL_K)
if ex.id not in recent_ids and ex.session_id != session_id
]
if recalled:
messages.append(_detail_note(recalled))
# Tier 3: current session, full fidelity.
for ex in recent:
messages.append({"role": ex.role, "content": ex.content})
messages.append({"role": "user", "content": user_msg})
logbus.log(
"debug", "context built",
recent=len(recent), summaries=len(summaries), details=len(recalled),
chars=sum(len(m["content"]) for m in messages), detail=_render(messages),
)
return messages
def respond(session_id: str, user_msg: str, backend: Backend = "cloud",
model_override: str | None = None) -> str:
"""Produce Lyra's reply to a single user message and persist the exchange.
`model_override` (from the UI's cloud-model picker) only applies on the cloud
backend; local/mi50 keep their own configured models.
"""
cfg = config.load()
# Live chat uses the stronger chat_model on cloud (bulk consolidation keeps
# cloud_model). local/mi50 use their own configured model.
def _resolve_model(backend: Backend, model_override: str | None, cfg) -> str:
"""Live chat uses the stronger chat_model on cloud; local/mi50 use their own.
The UI's cloud-model picker only applies on the cloud backend."""
model = {"local": cfg.local_model, "cloud": cfg.chat_model, "mi50": cfg.mi50_model}.get(
backend, backend
)
if model_override and backend == "cloud":
model = model_override
logbus.log(
"info", "chat request", session=session_id, backend=backend,
model=model, embed=cfg.embed_backend,
)
return model
mode = modes.get(memory.get_session_mode(session_id))
messages = build_messages(session_id, user_msg, mode=mode)
# Live thought loop: think privately about what to actually say before answering.
note = _deliberation_note(session_id, user_msg, backend, model, messages)
if note:
messages.append(note)
def _maybe_switch_mode(session_id: str, tool_name: str) -> None:
"""Keep the chat framing aligned with the live data: opening a poker session
auto-flips this chat into Poker mode (next turn gets the card + full live tools).
Manual UI switching still overrides anytime."""
if tool_name == "start_session":
memory.set_session_mode(session_id, modes.CASH.key)
logbus.log("info", "mode auto-switch", session=session_id, mode=modes.CASH.key)
# Tool loop: offer Lyra her tools (scoped to the mode); if she calls one, run it
# and feed the result back so she can continue, until she returns a text reply.
tool_specs = toolkit.specs(mode.tools) if backend in TOOL_BACKENDS else None
def respond(session_id: str, user_msg: str, backend: Backend = "cloud",
model_override: str | None = None) -> str:
"""Produce Lyra's reply to a single user message and persist the exchange."""
cfg = config.load()
model = _resolve_model(backend, model_override, cfg)
logbus.log("info", "chat request", session=session_id, backend=backend,
model=model, embed=cfg.embed_backend)
turn = mind.assemble(session_id, user_msg, backend, model)
messages = turn.messages
# Tool loop (speak): offer her tools (scoped to the mode); run any she calls and
# feed results back until she returns a text reply.
tool_specs = toolkit.specs(turn.mode.tools) if backend in TOOL_BACKENDS else None
ctx = {"session_id": session_id, "backend": backend}
reply = ""
for _ in range(MAX_TOOL_ROUNDS):
@@ -295,9 +73,7 @@ def respond(session_id: str, user_msg: str, backend: Backend = "cloud",
memory.remember(session_id, "user", user_msg)
memory.remember(session_id, "assistant", reply)
# Compact this session once enough new turns have piled up.
summary.maybe_summarize_async(session_id)
summary.maybe_summarize_async(session_id) # compact once enough new turns pile up
return reply
@@ -305,30 +81,17 @@ def respond_stream(session_id: str, user_msg: str, backend: Backend = "cloud",
model_override: str | None = None):
"""Streaming generator version of `respond`.
Yields ("delta", text) as content streams in, and ("tool", name) when a tool
runs. Persists the full exchange and yields a final ("done", reply) — matching
`respond`'s side effects (memory + compaction) exactly.
Yields ("delta", text) as content streams in, ("tool", name) when a tool runs,
and a final ("done", reply). Persists the exchange — same side effects as `respond`.
"""
cfg = config.load()
model = {"local": cfg.local_model, "cloud": cfg.chat_model, "mi50": cfg.mi50_model}.get(
backend, backend
)
if model_override and backend == "cloud":
model = model_override
logbus.log(
"info", "chat request (stream)", session=session_id, backend=backend,
model=model, embed=cfg.embed_backend,
)
model = _resolve_model(backend, model_override, cfg)
logbus.log("info", "chat request (stream)", session=session_id, backend=backend,
model=model, embed=cfg.embed_backend)
mode = modes.get(memory.get_session_mode(session_id))
messages = build_messages(session_id, user_msg, mode=mode)
# Live thought loop: think privately about what to actually say before answering.
note = _deliberation_note(session_id, user_msg, backend, model, messages)
if note:
messages.append(note)
tool_specs = toolkit.specs(mode.tools) if backend in TOOL_BACKENDS else None
turn = mind.assemble(session_id, user_msg, backend, model)
messages = turn.messages
tool_specs = toolkit.specs(turn.mode.tools) if backend in TOOL_BACKENDS else None
ctx = {"session_id": session_id, "backend": backend}
parts: list[str] = []
for _ in range(MAX_TOOL_ROUNDS):