Files
chat/chat/web/skip.py
T

303 lines
11 KiB
Python

"""Shared skip-flow controllers (T62).
Both the drawer skip routes (T59) and the natural-language skip parse
(T62) call into these controllers. Keep the controllers free of HTTP
concerns — they take ``conn`` + ``client`` + ``settings`` and structured
args, append events, and return a small result dict the caller can map
to whatever response shape it owes (drawer partial, 204, 422, etc.).
``ValueError`` is the controller-level signal for caller-mappable
validation failure (bad ISO timestamp, backwards skip). The drawer
routes translate it to ``HTTP 400``; the natural-language path either
swallows it (the parser handed us a degenerate hint) or surfaces it the
same way. Anything else (LLM failure, unexpected exception) propagates
uncaught — :func:`narrate_skip` already has its own deterministic
fallback for the routine LLM-down case, so a real exception here means
something we want to see.
The two controllers mirror the drawer T59 logic closely so the v1
guarantees (``time_skip_*`` lands first → memory writes ride the
post-skip clock → narration ``assistant_turn`` is appended last) hold
identically across the two entry points.
"""
from __future__ import annotations
from datetime import datetime, timezone
from sqlite3 import Connection
from chat.config import Settings
from chat.eventlog.log import append_and_apply, append_event
from chat.llm.client import LLMClient
from chat.services.memory_write import record_turn_memory_for_present
from chat.services.skip_narration import narrate_skip
from chat.services.synthesized_memories import synthesize_memories
from chat.state.entities import get_bot, get_you
from chat.state.world import get_activity, get_chat
class ChatNotFoundError(Exception):
"""Raised when a ``chat_id`` doesn't resolve to a chat row.
Distinguishes the missing-chat case from generic input-validation
failures (which still raise :class:`ValueError`). HTTP callers map
this to ``404`` and ``ValueError`` to ``400`` — replacing the
earlier ``str(exc).startswith("chat not found")`` prefix sniff
(T81) with a typed dispatch.
"""
def _parse_iso_time(value: str) -> datetime | None:
"""Permissive ISO 8601 parser shared with the drawer routes (T59).
``datetime.fromisoformat`` doesn't accept a trailing ``Z`` until
Python 3.11; we normalize it to ``+00:00`` so older interpreters
parse the same set of strings the drawer accepts.
"""
if not value:
return None
try:
v = value.strip()
if v.endswith("Z"):
v = v[:-1] + "+00:00"
return datetime.fromisoformat(v)
except (TypeError, ValueError):
return None
def _validate_new_time(chat: dict, new_time: str) -> None:
"""Raise ``ValueError`` if ``new_time`` is unparseable or backwards.
The drawer route maps the raised error to ``HTTP 400``; the
natural-language path may also surface it as a ``400``. Centralizing
the rule here means both entry points enforce the same invariant
(no causality-corrupting backwards jumps).
"""
new_dt = _parse_iso_time(new_time)
if new_dt is None:
raise ValueError(f"new_time must be ISO 8601, got {new_time!r}")
cur_dt = _parse_iso_time(chat.get("time") or "")
if cur_dt is not None and new_dt < cur_dt:
raise ValueError(
"new_time must not be earlier than the current chat clock"
)
async def process_elision_skip(
conn: Connection,
client: LLMClient,
settings: Settings,
*,
chat_id: str,
new_time: str,
landing_state_hint: str = "",
) -> dict:
"""Run an elision skip end-to-end.
Validates ``new_time`` against the current chat clock, appends a
``time_skip_elision`` event (chat clock advances), generates a
transition narration via :func:`narrate_skip`, and appends an
``assistant_turn`` carrying the narration. ``narrate_skip`` has its
own deterministic fallback so this never blocks on the model.
Returns ``{"assistant_text": ..., "speaker_id": ..., "skip_event_id":
..., "assistant_event_id": ...}`` so callers can introspect the
generated turn (e.g. for SSE rebroadcast or test assertions).
Raises :class:`ChatNotFoundError` when the chat row is missing
(HTTP ``404``) and ``ValueError`` on input-validation failure
(HTTP ``400``). Splitting the two lets the drawer route dispatch
on type instead of sniffing the error string (T81).
"""
chat = get_chat(conn, chat_id)
if chat is None:
raise ChatNotFoundError(f"chat not found: {chat_id}")
_validate_new_time(chat, new_time)
host_bot = get_bot(conn, chat["host_bot_id"]) or {
"id": chat["host_bot_id"],
"name": "host",
"persona": "",
}
you_entity = get_you(conn) or {"name": "you"}
# The drawer route reaches into the host bot's current activity to
# surface the verb to the narration helper — we do the same so both
# entry points produce the same prose for the same chat state.
bot_activity = get_activity(conn, chat["host_bot_id"]) or {}
current_activity = (bot_activity.get("action") or {}).get("verb") or ""
narration = await narrate_skip(
client,
narrative_model=settings.narrative_model,
skip_kind="elision",
speaker_bot=host_bot,
you_name=you_entity.get("name") or "you",
current_time=chat.get("time") or "",
new_time=new_time,
current_activity=current_activity,
landing_state_hint=landing_state_hint,
timeout_s=settings.classifier_timeout_s,
)
skip_event_id = append_and_apply(
conn,
kind="time_skip_elision",
payload={"chat_id": chat_id, "new_time": new_time},
)
speaker_id = host_bot.get("id") or chat["host_bot_id"]
assistant_event_id = append_event(
conn,
kind="assistant_turn",
payload={
"chat_id": chat_id,
"speaker_id": speaker_id,
"text": narration,
"truncated": False,
},
)
return {
"assistant_text": narration,
"speaker_id": speaker_id,
"skip_event_id": skip_event_id,
"assistant_event_id": assistant_event_id,
}
async def process_jump_skip(
conn: Connection,
client: LLMClient,
settings: Settings,
*,
chat_id: str,
new_time: str,
notable_prose: str = "",
reset_activity: bool = False,
) -> dict:
"""Run a jump skip end-to-end.
Same validations as :func:`process_elision_skip`. Emits
``time_skip_jump`` *before* synthesizing memories so per-bot writes
record the post-jump chat clock (mirroring how a regular turn's
memory carries the chat clock). When ``notable_prose`` is non-empty,
runs :func:`synthesize_memories` once per present bot witness, then
fans the resulting memories out via
:func:`record_turn_memory_for_present` with ``source="synthesized"``.
Finally appends the narration ``assistant_turn``.
Returns ``{"assistant_text": ..., "speaker_id": ..., "skip_event_id":
..., "assistant_event_id": ...}``.
Raises :class:`ChatNotFoundError` on missing chat (caller maps to
``404``) and ``ValueError`` on input-validation failure (caller maps
to ``400``).
"""
chat = get_chat(conn, chat_id)
if chat is None:
raise ChatNotFoundError(f"chat not found: {chat_id}")
_validate_new_time(chat, new_time)
host_bot = get_bot(conn, chat["host_bot_id"]) or {
"id": chat["host_bot_id"],
"name": "host",
"persona": "",
}
you_entity = get_you(conn) or {"name": "you"}
you_name = you_entity.get("name") or "you"
guest_bot_id = chat.get("guest_bot_id")
guest_bot = get_bot(conn, guest_bot_id) if guest_bot_id else None
# Emit time_skip_jump up front so subsequent memory writes ride the
# post-jump chat clock (matches the drawer T59 behavior pinned by
# test_post_skip_jump_with_notable_prose_writes_synthesized_memories).
skip_event_id = append_and_apply(
conn,
kind="time_skip_jump",
payload={
"chat_id": chat_id,
"new_time": new_time,
"reset_activity": reset_activity,
},
)
# Synthesize per-bot memories when prose is non-empty. The helper
# short-circuits on whitespace prose, but gating the loop here keeps
# the canned-LLM-queue accounting predictable for tests.
if notable_prose.strip():
present_bots: list[dict] = [host_bot]
if guest_bot is not None:
present_bots.append(guest_bot)
for bot in present_bots:
digest = await synthesize_memories(
client,
classifier_model=settings.classifier_model,
prose=notable_prose,
bot_name=bot.get("name") or "",
bot_persona=bot.get("persona") or "",
you_name=you_name,
timeout_s=settings.classifier_timeout_s,
)
for mem in digest.memories:
# ``record_turn_memory_for_present`` writes one row per
# present bot per call — we already iterate by bot here,
# so guest_bot_id=None avoids double-writing the guest's
# row when bot==guest.
record_turn_memory_for_present(
conn,
chat_id=chat_id,
host_bot_id=bot["id"],
guest_bot_id=None,
narrative_text=mem.text,
chat_clock_at=new_time,
source="synthesized",
significance=mem.significance,
)
narration = await narrate_skip(
client,
narrative_model=settings.narrative_model,
skip_kind="jump",
speaker_bot=host_bot,
you_name=you_name,
current_time=chat.get("time") or "",
new_time=new_time,
current_activity="",
landing_state_hint=notable_prose,
timeout_s=settings.classifier_timeout_s,
)
speaker_id = host_bot.get("id") or chat["host_bot_id"]
assistant_event_id = append_event(
conn,
kind="assistant_turn",
payload={
"chat_id": chat_id,
"speaker_id": speaker_id,
"text": narration,
"truncated": False,
},
)
return {
"assistant_text": narration,
"speaker_id": speaker_id,
"skip_event_id": skip_event_id,
"assistant_event_id": assistant_event_id,
}
def _now_iso() -> str:
"""UTC ISO timestamp used by callers as a chat-clock fallback."""
return datetime.now(timezone.utc).isoformat()
__all__ = [
"ChatNotFoundError",
"process_elision_skip",
"process_jump_skip",
"_now_iso",
"_parse_iso_time",
]