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

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>

lyra/chat.py

@@ -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):
+`mind.assemble()` runs the society of parts (perceive → route → compose →
-  1. persona
+deliberate) and hands back a ready message list + the active mode; `chat` runs the
-  2. long-term gist  — relevant *summaries* of other sessions
+tool/generation loop (the "speak" part) and persists the exchange. Keeping speak
-  3. sharp details   — a few raw cross-session exchanges (so specifics survive)
+here (not in mind) is deliberate — it's tangled with streaming and tool dispatch.
-  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.
 """
 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:
+def _resolve_model(backend: Backend, model_override: str | None, cfg) -> str:
-    """Dynamic, per-turn state for the active mode. Currently: surface Alligator
+    """Live chat uses the stronger chat_model on cloud; local/mi50 use their own.
-    Blood while it's engaged on the live session, so she stays in that register."""
+    The UI's cloud-model picker only applies on the cloud backend."""
-    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.
     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(
+    return model
-        "info", "chat request", 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.
+def _maybe_switch_mode(session_id: str, tool_name: str) -> None:
-    note = _deliberation_note(session_id, user_msg, backend, model, messages)
+    """Keep the chat framing aligned with the live data: opening a poker session
-    if note:
+    auto-flips this chat into Poker mode (next turn gets the card + full live tools).
-        messages.append(note)
+    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.
+def respond(session_id: str, user_msg: str, backend: Backend = "cloud",
-    tool_specs = toolkit.specs(mode.tools) if backend in TOOL_BACKENDS else None
+            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)
-
+    summary.maybe_summarize_async(session_id)  # compact once enough new turns pile up
-    # Compact this session once enough new turns have piled up.
-    summary.maybe_summarize_async(session_id)
     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
+    Yields ("delta", text) as content streams in, ("tool", name) when a tool runs,
-    runs. Persists the full exchange and yields a final ("done", reply) — matching
+    and a final ("done", reply). Persists the exchange — same side effects as `respond`.
-    `respond`'s side effects (memory + compaction) exactly.
     """
     cfg = config.load()
-    model = {"local": cfg.local_model, "cloud": cfg.chat_model, "mi50": cfg.mi50_model}.get(
+    model = _resolve_model(backend, model_override, cfg)
-        backend, backend
+    logbus.log("info", "chat request (stream)", session=session_id, backend=backend,
-    )
+               model=model, embed=cfg.embed_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,
-    )
 
-    mode = modes.get(memory.get_session_mode(session_id))
+    turn = mind.assemble(session_id, user_msg, backend, model)
-    messages = build_messages(session_id, user_msg, mode=mode)
+    messages = turn.messages
-
+    tool_specs = toolkit.specs(turn.mode.tools) if backend in TOOL_BACKENDS else None
-    # 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
     ctx = {"session_id": session_id, "backend": backend}
     parts: list[str] = []
     for _ in range(MAX_TOOL_ROUNDS):

lyra/mind.py

@@ -0,0 +1,272 @@
+"""The control plane: assemble one turn from a society of small parts.
+
+This is the explicit version of what used to be inline in `chat.py`. A turn is
+built by running an ordered pipeline of *parts* over a shared `TurnContext`
+(blackboard): each part reads what it needs and annotates the context, and the
+last steps produce the message list `chat` then hands to the voice model.
+
+P1 (this): the frame, behavior-preserving. The parts wrap the existing logic —
+  perceive (stub) -> route (the session's mode) -> compose (tiered prompt) ->
+  deliberate (private 'what do I actually think' pass).
+Later phases fill in perceive (read the moment), route (register/intent + model
+routing), and a learn loop — see docs/COGNITION.md. Most parts are cheap
+deterministic code; the LLM is the exception (deliberate here, speak in `chat`).
+"""
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+
+from lyra import clock, config, llm, logbus, memory, modes, persona, self_state, thoughts
+from lyra.llm import Backend, Message
+
+RECALL_K = 3  # raw cross-session "sharp detail" hits
+RECENT_N = 10  # raw turns of the current session
+SUMMARY_K = 3  # other-session gists
+
+
+# --- prompt parts (compose) ----------------------------------------------
+
+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 _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."""
+    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)
+
+
+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 — threads she's turning over + what she's written for
+    # herself — so chat reads as a continuous mind, not a fresh boot.
+    inner = _inner_life_note()
+    if inner:
+        messages.append(inner)
+
+    # Mode card: how to behave *right now*. Talk mode has no card (persona is Talk).
+    if mode and mode.card:
+        messages.append({"role": "system", "content": mode.card})
+
+    # Live ritual state (e.g. Alligator Blood ON) — dynamic, rides with the card.
+    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 a thread has built past the surface bar,
+    # let her lead with it (once) — her #6, bringing what she thought about *to* him.
+    surfaced = thoughts.maybe_surface(memory.last_exchange_at())
+    if surfaced:
+        messages.append({"role": "system", "content": surfaced})
+
+    # Semantic memory: the distilled profile (who Brian is).
+    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.
+    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).
+    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
+
+
+# --- deliberation (a private 'what do I actually think' pass) -------------
+
+# 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)
+
+
+# --- the pipeline (a society of parts over a shared blackboard) -----------
+
+@dataclass
+class TurnContext:
+    """The blackboard for one turn: parts read what they need and annotate it."""
+    session_id: str
+    user_msg: str
+    backend: Backend
+    model: str | None = None
+    mode: modes.Mode | None = None
+    moment: dict = field(default_factory=dict)  # perceive fills this in (P2)
+    messages: list[Message] = field(default_factory=list)
+
+
+def _perceive(ctx: TurnContext) -> TurnContext:
+    """Read the moment (sentiment / kind / tilt). Stub for now — P2 fills it in."""
+    ctx.moment = {}
+    return ctx
+
+
+def _route(ctx: TurnContext) -> TurnContext:
+    """Pick how she shows up. Manual for now: the mode chosen for this session."""
+    ctx.mode = modes.get(memory.get_session_mode(ctx.session_id))
+    return ctx
+
+
+def _compose(ctx: TurnContext) -> TurnContext:
+    """Assemble the tiered prompt for the voice model."""
+    ctx.messages = build_messages(ctx.session_id, ctx.user_msg, ctx.mode)
+    return ctx
+
+
+def _deliberate_part(ctx: TurnContext) -> TurnContext:
+    """Private 'what do I actually think' pass, appended last so it shapes the reply."""
+    note = _deliberation_note(ctx.session_id, ctx.user_msg, ctx.backend, ctx.model, ctx.messages)
+    if note:
+        ctx.messages.append(note)
+    return ctx
+
+
+PIPELINE = (_perceive, _route, _compose, _deliberate_part)
+
+
+def assemble(session_id: str, user_msg: str, backend: Backend,
+             model: str | None = None) -> TurnContext:
+    """Run the parts over a fresh TurnContext and return it ready for `chat` to speak."""
+    ctx = TurnContext(session_id=session_id, user_msg=user_msg, backend=backend, model=model)
+    for part in PIPELINE:
+        ctx = part(ctx)
+    return ctx

tests/test_chat.py

@@ -1,4 +1,4 @@
-"""Live chat: the deliberation pass (think privately before answering)."""
+"""The mind pipeline: the deliberation pass (think privately before answering)."""
 from __future__ import annotations
 
 import importlib
@@ -13,31 +13,31 @@ def lyra(tmp_path, monkeypatch):
     monkeypatch.setattr(llm, "embed", lambda texts: [[0.1, 0.2, 0.3] for _ in texts])
     import lyra.memory as memory
     importlib.reload(memory)
-    import lyra.chat as chat
+    import lyra.mind as mind
-    importlib.reload(chat)
+    importlib.reload(mind)
-    return memory, chat
+    return memory, mind
 
 
 def test_should_deliberate_skips_trivial(lyra):
-    _, chat = lyra
+    _, mind = lyra
-    assert chat._should_deliberate("How would we actually start building this?")
+    assert mind._should_deliberate("How would we actually start building this?")
-    assert chat._should_deliberate("I disagree, that seems risky")
+    assert mind._should_deliberate("I disagree, that seems risky")
     for trivial in ("ok", "lol", "thanks", "yeah", "nice", "👍", "k"):
-        assert not chat._should_deliberate(trivial)
+        assert not mind._should_deliberate(trivial)
-    assert not chat._should_deliberate("ok!")        # punctuation stripped
+    assert not mind._should_deliberate("ok!")        # punctuation stripped
-    assert not chat._should_deliberate("hey")         # too short
+    assert not mind._should_deliberate("hey")         # too short
 
 
 def test_deliberation_note_runs_and_appends(lyra, monkeypatch):
-    _, chat = lyra
+    _, mind = lyra
     calls = []
 
     def fake_complete(messages, backend=None, model=None):
         calls.append(messages)
         return "I actually think the first move is the smallest end-to-end slice."
 
-    monkeypatch.setattr(chat.llm, "complete", fake_complete)
+    monkeypatch.setattr(mind.llm, "complete", fake_complete)
-    note = chat._deliberation_note("s1", "How would we start on this?", "cloud", None, [])
+    note = mind._deliberation_note("s1", "How would we start on this?", "cloud", None, [])
     assert note and note["role"] == "system"
     assert "first move is the smallest" in note["content"]      # her thinking carried in
     assert "numbered list" in note["content"].lower()           # voice enforcement attached
@@ -45,9 +45,19 @@ def test_deliberation_note_runs_and_appends(lyra, monkeypatch):
 
 
 def test_deliberation_skipped_when_disabled(lyra, monkeypatch):
-    _, chat = lyra
+    _, mind = lyra
     monkeypatch.setenv("CHAT_DELIBERATE", "false")
     called = []
-    monkeypatch.setattr(chat.llm, "complete", lambda *a, **k: called.append(1) or "x")
+    monkeypatch.setattr(mind.llm, "complete", lambda *a, **k: called.append(1) or "x")
-    assert chat._deliberation_note("s1", "a real substantive question here", "cloud", None, []) is None
+    assert mind._deliberation_note("s1", "a real substantive question here", "cloud", None, []) is None
     assert called == []                                          # no LLM call when off
+
+
+def test_assemble_runs_the_pipeline(lyra, monkeypatch):
+    memory, mind = lyra
+    monkeypatch.setenv("CHAT_DELIBERATE", "false")  # keep it offline for the structure test
+    memory.ensure_session("s1")
+    turn = mind.assemble("s1", "hey what's up", "cloud", None)
+    assert turn.mode is not None                       # route ran
+    assert turn.messages and turn.messages[-1]["role"] == "user"   # compose ran
+    assert turn.messages[-1]["content"] == "hey what's up"

tests/test_time.py

@@ -39,8 +39,8 @@ def lyra(tmp_path, monkeypatch):
 
 
 def test_now_note_first_contact(lyra):
-    from lyra import chat
+    from lyra import mind
-    note = chat._now_note()["content"]
+    note = mind._now_note()["content"]
     assert "current date and time is" in note
     assert "first thing Brian has ever said" in note
 
@@ -48,6 +48,6 @@ def test_now_note_first_contact(lyra):
 def test_now_note_reports_gap(lyra):
     memory = lyra
     memory.remember("s1", "user", "hey")
-    from lyra import chat
+    from lyra import mind
-    note = chat._now_note()["content"]
+    note = mind._now_note()["content"]
     assert "since Brian last spoke with you" in note

tests/test_tools.py

@@ -9,6 +9,7 @@ import pytest
 @pytest.fixture
 def lyra(tmp_path, monkeypatch):
     monkeypatch.setenv("LYRA_DB_PATH", str(tmp_path / "test.db"))
+    monkeypatch.setenv("CHAT_DELIBERATE", "false")  # don't make a real LLM call in respond()
     from lyra import llm
     monkeypatch.setattr(llm, "embed", lambda texts: [[0.1, 0.2, 0.3] for _ in texts])
     import lyra.memory as memory